Consumer Products – Gregory Knox, Individual

Abstract for “System and Method for Recommendations in Ubiquitous Computing Environments”

“Systems and methods to create an ad-hoc pervasive computing environment consisting of an inference recommendation engine coupled with commodity devices and sensors that passively record human activity and behavior data. Machine learning and deep learning are two methods that use data analysis to generate preference-based recommendations to guide, inform and assist subjects who interact with a connected living area and their connected social networks.

Background for “System and Method for Recommendations in Ubiquitous Computing Environments”

“Field of Disclosure”

“The present invention relates to computerized AI applications in pervasive computing environments and, more specifically, to systems and methods that provide inference recommendations that encourage optimal user interactions with associated technologies and users.”

“Description of Related Art.”

“Ubiquitous computing technologies can be one component of intelligent system designed for technology enabled humans experiences. They can enhance user experiences in many areas of connected lifestyles.” User interaction with any device, sensor, or computer, regardless of location or format, is called ubiquitous computing.

“On a single basis, today’s ubiquitous computing systems may produce data in the realm Ambient Intelligence. These hardware and software configurations can be used to aid human decision-making using historical and real-time data. Connected consumer appliances and the Internet of Things (IoT) contain commodity sensors. connected consumer appliances, Internet of Things (?IoT?) devices, and smart devices at such a level that ad-hoc ubiquitous computation (hereinafter??ubicomp?)) can be achieved. By pairing basic devices with neural network apps that interpret the data, environments can be created. Technology makes it possible to measure and predict user preferences using available sensor data. This is due to the large amount of data that can easily be collected from common devices, such as biometric and human physiology data, facial expressions, moods, location data with GPS, and movement data that can all be labeled with accelerometers, cameras, and gyroscopes.

“Generally speaking, the cost of these commodity devices and sensor evolutions has driven down their costs and made them more ubiquitous in daily life. Many applications can be designed to provide a specific user experience using a small number of data signals. The performance promised is always delivered. A narrowly defined user experience can limit the ability to extract insights from users and use data collected. Multiple sensor and device data channels that indicate interactions do not necessarily equate with ‘insights. “Where there are no means of contextualizing or learning user experiences.”

“Overall, there are sufficient data, hardware and software to be able to approximate limited forms of evaluating or predicting human behavior at the consumer level. Passive preference data, or?inference Intelligence? Pervasive computing environments may allow for passive preference data or?inference intelligence. Edge computing architectures are where data science methods like customized machine learning and deep learning are used on devices that parse, analyze, and interpret data. It is possible to enhance understanding of the user’s subjective thoughts in certain settings, provided there are sufficient reference information.

“In one aspect, the present disclosure discloses a method for tracking the activity at least one person from at least two of the ubicomp devices. This method could include steps such as generating tracking data from at least two ubicomp device, collecting each generated tracking information, conglomerating each generated trackingdata, converting each conglomerated tracking dataset into at least one standard data format, classifying each converted conglomerated tracked data using interaction preference insights and sending recommendations to the at most one human based upon the classified converted conglomerated tracked data.

In another aspect of this disclosure, the method for tracking activity may also include pairing two or more ubicomp device. Smart devices include a smart meter and a thermostat, as well as a smart temperature sensor, smart humidity sensor, smart pressure sensor, and a sensor for smart vibration.

“In another aspect, the step of transmitting recommendation may also include the use of an inference recommendation engine to generate interaction recommendations for the human.”

“Another aspect of the disclosure is that the generated tracking information may include behavioral and activity data from the human. The method of tracking the activity could also include the analysis of each of the generated track data.

“In another aspect, the present disclosure may also include the generation of interaction recommendations by at least one person in response to the analysis of the behavioral data.”

“Another aspect of the disclosure is that the interaction recommendations can include time, location frequency, duration, and/or feelings.”

“Another aspect of the disclosure is that the method for tracking activity may include updating interaction recommendations on at minimum one of a time frequency base, a biometrical level basis or an emotion level based, a sentiment level based, and a motion level basis. A temperature level base, a humidity level basis. a barometric level based, a light level basis. a frequency level basis. and a radiation level basis.

“Another aspect of the disclosure is that the step of transmitting suggested interactions may also include the generation of feedback to at least two ubicomp device pairs.”

“In another aspect, the method for tracking activity may also include the storage of generated tracking data in at most one cloud computing network.”

“A network for tracking activity of at least one person from two or more paired Ubicomp devices is disclosed in another aspect of this disclosure. The network could include a first and second track computing devices for generating tracking information from each of at least two paired Ubicomp devices, as well as a collect computing unit for collecting each generated tracking detail, a conglomerate computing facility for conglomerating all of the generated data, a convert computing apparatus for converting the conglomerated tracking to at least one standard data format, and a classify computing tool for classifying the converted conglomerated tracked data using interaction preference insights. A transmitting device is used for sending recommendations to the at least one person based on the classified conglomerated generation of tracking data.

A smart meter, smart thermostat, smart temperature sensor and smart humidity sensor are all possible ubicomp devices under another aspect of the disclosure.

“Another aspect of the disclosure is that the transmitting device could include an inference recommendation system engine system that generates interaction recommendations for at least one person.”

“In another aspect, the present disclosure may also include an analyzing computing unit for analyzing activity or behavioral data from the tracking data at least one person.”

“In another aspect, the network could include an interactive computing unit for generating interaction recommendations in response the the analyzing computing devices analyzing the behavior data.”

“In another aspect, the present disclosure may also include interaction recommendations that could include time, location frequency, duration, or sentiments.”

“In another aspect, the present disclosure may also include an updating computing unit for updating interaction recommendations on the basis time, motion, temperature, humidity, barometric level or light level.

“In another aspect, the present disclosure may provide a means for the transmitting device to generate a feedback signal to the pair of ubicomp devices.”

“Another aspect of the present disclosure is that the network may also include a cloud computing system coupled with the first track computing device and the second track computing device for storing the generated tracking information from the two paired Ubico devices.”

The benefits of using neural network solutions to enhance lifestyle experiences are well-known. A system that uses basic sensors and devices to provide reliable intelligence about a person’s lifestyle preferences can be economically viable. It is also useful for the subject, their families and friends as well as any other social networks or service providers. A method that presents interaction recommendations based upon known behaviors, learned engagement preferences, and expected outcomes creates new channels for communication to user lifestyle insights. With machine learning and sensor level reliability, you can improve the accuracy and efficiency of your response time, anticipate your needs and provide assistance. The proposed applications need to secure the collection, storage, and exchange of the data. In order to reduce the risk of data theft and misuse, it would be a good idea to incorporate immutable technology like blockchain encryption. This will prevent data modification and ensure that only authorized users have access.

“Systems, methods and devices, according to various examples of disclosure, may address one of the aforementioned shortcomings experienced in generating comprehensive interactions recommendations using commodity sensors that accurately reflect users’ intent and desired outcomes. Certain aspects of the disclosures allow for the collection, analysis, and presentation of lifestyle, biometric, and behavioral data. This allows users to respond in a timely fashion to the subject. An interaction recommendation system can generally provide recommendations for a large number of user engagement events or instances. However, optimal performance requires adequate sensor data, computing power, and reference information.

“In addition, personal device lifestyle integrations are part of the ‘connected lifestyle. The concept of a “connected lifestyle” has evolved beyond traditional networked systems like lighting controls, heating and cool, audio and video, security cameras, and heating and cooling. Data driven applications that measure specific interactions are possible with the IoT innovation. This is due to the large number of consumer products embedded with network applications like microwaves and toasters, coffeemakers, dishwashers and water faucets.

A ubiquitous computing environment, or ubicomp, can be created either on an ad-hoc basis or permanently using a few or many connected consumer products that are common in homes that operate on LAN or WIFI networks. These include cameras, motion sensors smart phones, thermostats door entry/exit sensors smart TVs, thermostats, door sensors, door sensors, wearable devices and tablets. Basic cameras can now recognize faces, recognize facial expressions, identify objects, recognize gestural patterns, and measure physical movements to catalogue specific activity types. These devices and sensor signals provide only a small amount of information. Given their networked environment, however, there are tremendous opportunities to gain from methods that combine these information sources and use their unique data channels to generate more robust and contextualized insight.

“There are some benefits to adding context and personalized information to interactions involving connected device and sensors that enhance upon existing technology. Inference intelligence is a way to improve basic engagements with connected technology. Connected devices need human input-physical controls to set the settings. Remote control via mobile app or voice commands can be sent from a voice-enabled computer. Software applications can predict these actions and the decision points leading up to them. Predictions for single actions are made based on repetition. This level of engagement does not give much insight into intent, motive, desired outcome or special conditions. If a coffee maker is scheduled to make coffee at 6 AM every day, but the subject decides to stay up until 8 AM, how will the coffee maker adapt to this situation without human intervention? For example, the present disclosure describes a method for identifying sleep conditions. This may include using camera motion sensors or data from a smartphone to determine the waking phase. The data then triggers the coffeemaker operation based upon real-time inference data which adjusts to different waking hours each day.

“Second-level, inference intelligence can increase engagement insights for interactions among users. Current technologies allow humans to identify, track, measure, and eventually catalog their activities and habits. Inference data can be used for understanding contextualized exceptions to daily routines. Lifestyle habits and habits are indicative of preferences. Inference intelligence is more efficient and accurate for users who are connected remotely. Inference intelligence allows remote users to adapt to changing circumstances by receiving notification updates. Inference intelligence could send automated updates to third parties if the subject is awake and has an appointment or visitor scheduled to arrive at a specific time.

Inference intelligence applications, third, can use natural language processing to provide rich context information. Machine learning applications can use sentiment, desire, and intent to efficiently assist machine learning applications in predictive analytics. They also offer personalized recommendations for each individual based on their unique circumstances. Artificial intelligence solutions that use many sensors and devices to connect can be greatly improved by obtaining the user’s preferences and subjective thoughts in real time.

Fourth, improving efficiency and accuracy in human interactions yields substantial intangible benefits. Remote relationships offer a wealth in collateral benefits, especially for mental health and emotional support. Deep learning applications improve insight data through continuous interactions and increase recommendation quality for all parties regarding optimal engagement circumstances, timing, best practice, contingencies for unforeseen situations, and the like.

“Accordingly to one aspect of the current disclosure, an inference recommendation system system and method for generating interaction suggestions informed by user-centric activity and behavioral data from commodity sensors and commercial devices in a pervasive computing ecosystem are described. This teaching is not intended to be a complete description of the disclosure. The disclosed aspects are sufficiently detailed to allow one skilled in art to use them, but it is important to understand that they are only examples. You can therefore derive other implementations, aspects and/or configurations from the disclosed information without departing from its spirit and scope.

The present discloses a software solution to improve human interactions using data from disparate networked sensors and devices operating in a subject?s home to identify interactions and the subject?s preferences (time and location, frequency, duration and sentiments for each interaction). These preference data can be used to guide, assist, and inform users in a home or to other connected devices.

An enterprise solution can be deployed using cloud or edge architecture. A client device, such as a smart phone, can connect to a network of sensors and devices that measure and identify human behavior and activity. An API can collect data from connected devices and sensors and process it via cloud computing to make usable formats. This allows analytic apps to determine the subject’s interactions, preferences, recommendations, and predictive analytics for interactions with other connected users.

“In one aspect, the present disclosure teaches systems and methods for conglomerating data and converting it to a standard data format. This can be used in consumer sensors or devices that operate on standard networks, such as Wi-Fi, Bluetooth, and so forth. This provides information about human behavior and activity. These interactions may be classified and interaction preference insights more clearly identified-information that can inform and guide interaction recommendations for the subject and their associated users.”

This approach is technically possible due to changes in the consumer technology landscape. The first is that the cost of sensors and devices providing activity and behavior data has dropped drastically, while their functionality and data quality have increased. Second, common sensors (cameras and wearables as well as wireless chipsets), are deployed everywhere. They actively capture user information (sleep, activity levels, types of activity, gestures etc., diet, physiological biometrics), location, media consumption, sentiments and social connectivity. These technologies are being developed by major companies (e.g. Apple, Google and Microsoft) at a rapid pace. They also offer open-source platforms that allow for the integration of different hardware and software technologies onto a single platform. The viability of this technology is supported by the growing market for artificial intelligence software chipsets, edge computing solutions that allow for low latency and improved network capacity and speed.

“In one aspect, the present disclosure teaches systems and methods for conglomerating data and converting it to a standard data format. This can be used in consumer sensors or devices that operate on standard networks, such as Wi-Fi, Bluetooth, and so forth. This provides information about human behavior and activity. These interactions may be classified and interaction preference insights more clearly identified-information that can inform and guide interaction recommendations for the subject and their associated users.”

The present disclosure may, in one aspect, use a multichannel, multimodal solution to more effectively enable a subject?s unique set of experiences to be captured digitally (within the limits of accessible devices and sensor). Because of lifestyle preferences, such as fear or missing out (‘FOMO), personalized data could be readily available. “, and other secret settings for device privacy.”

The present disclosure describes a data-agnostic method for capturing sensor and device data from connected devices in a dwelling that is occupied or occupied. It also provides instructions for predictive or recommendation models and patterns to guide and inform users both inside and outside of the dwelling. This information is tailored based on the unique lifestyle, routine, and preferences of each subject. Machine learning is used to refine insight analytics.

“In one aspect, the disclosure teaches a software program for enterprise-level architecture. An enterprise-level architecture could include a cloud computing network and storage resource, which could be used in a hybrid edge computing configuration to optimize efficiency and energy priorities. A mobile client or downloadable version of the software can be used on any smart device that connects with a local network. This allows it to identify available devices and sensors and provide engagement data resources. This could be the foundation for ubiquitous computing environments. The cloud can convert captured data into a usable format that allows bulk processing and analytics to take place. Once enough data has been captured to create an interaction, the system can then create user settings based on the user?s preferences. Preference data, or “inference intelligence?” is information that the system uses to determine which interaction the user prefers. The preference data or?inference intelligence can be directly input by a user, or learnt by the system through repeated interactions. An API is used to send recommendation and predictive analytics information via smart devices to known interaction associates. This information can then be incorporated into automated operations commands for sensors and networked devices.

Referring to FIG. “Referring to FIG. System 10 comprises ubiquitous computing environment 12, server 16, recommendation engine 18, blockchain module 22, inference intelligence 20, and computing device 26. FIG. 10 is an illustration of the system 10. FIG. 1A shows only one component of system 10. However, other aspects may include multiple ubiquitous computing environments 12, servers 16, recommendation engines 18, and 18-bit inference intelligences 20, as well as blockchain modules 22, inference engines 20, inference algorithms 20 and computing devices 26. System 10 is a platform that improves interaction and engagement for users within and outside the ubiquitous computing environment 12. It uses data collected from the system 10 and interprets it. System 10’s main focus is on the subjects observed activities, moods and biometric data within the ubiquitous computing environment 12. However, system 10 can also collect information about other users via APIs 24 operating computing devices 26 in order to better understand interaction related data. This may improve interaction quality, efficiency and reliability.

“Generally, ubiquitous computing environment (hereinafter?ubicomp?) 12 includes software and hardware components, including sensors, appliances, and portable networked devices. In some cases, ubicomp 12 could be made up of a small number or a large collection of sensors and networked devices as shown in FIG. 1B. 1B. In some cases, ubicomp 12 could be represented by a smart device such as a smartwatch or a smart phone. The composition of the available devices and sensors that can capture behavioral data signals and human activity to determine ubicomp12 operation and utility, regardless of the original commercial applications, is what defines ubicomp 12. If a manufacturer installed motion detection software on a security camera to detect movement, the present innovation could use that data signal to identify emotions, identify gestures and label objects. System 10 can collect data signals from ubicomp 12 devices, sensors, and other sources to format, index, and catalog the available data for use by recommendation engine 18 or inference intelligence 20.

“System 10 is possible to implement according to ubicomp 12, configurations that differ based on sensor and device inputs, and the raw and processed data generated accordingly. In certain aspects of the disclosure, ubicomp 12 includes a Body Area Network. (BAN), where one or more sensors can be carried by a subject. In some cases, ubicomp 12 includes a Personal Area Network. This is where one or more sensors can be deployed in a physical environment. Some aspects of ubicomp 12, such as sensors and devices, can execute programming and operations. These include the detection and classification of physical movement and the labelling and classifying of a set activities (sleeping/walking, cooking, grooming etc.). Recognize physical objects and their status, assess cognitive levels, identify emotions and learn personal patterns and lifestyle habits. Remote users can also be notified about activity events and data-related benchmarks.

“In some aspects system 10, ubicomp 12, recommendation engine 18, blockchain module 22, computing device 26 and external system communicate, use and transfer data through network 14. These implementations may use standard communications technologies such as the Internet, wired, wireless, Ethernet, WiMAX, 3G, 4G, CDMA and LTE, digital subscriber lines (DSL), broadcast network and the like. Network 14 may employ networking protocols in one aspect. These include file transfer protocol, SMTP, multiprotocol label shifting (MPLS), transmission protocol/Internet protocol TCP/IP, User Datagram Protocol UDP, hypertext transport protocol (HTTP), etc. Data exchanged over network 14 may be encrypted using traditional encryption technologies like secure sockets layer, transport layer security and Internet Protocol security. It can also formatted with technologies including hypertext Markup Language (HTML) or extensible markup Language (XML). Network 14 can be described as a data center, edge computing, cloud-based computing system architecture or combination thereof. It is connected via the Internet using a variety of computing systems, computing resource, storage hardware and security applications.

“One or more servers 16 can be connected to ubicomp 12, network 14, and provide selected data and information access for computing device 26 and external systems 28. Server 16 may be a component of a server network. Server 16 can be described as an independent host, gateway, and network access within the system 10 for recommendation engines 18, 20, and 22 and 24 respectively.

Recommendation engine 18 generally collects ubicomp12 data for processing, analysis and indexing, labeling and cataloging human behavior and human activity. Recommendation engine 18 can manage artificial intelligence, deep learning, and other neural network applications in some aspects. It processes, analyzes, converts, and interprets ubicomp12 information into human activity, and behavioral data that can be used by system 10 components or inference intelligence 20. Recommendation engine 18 can correlate inference intelligence 20 and human activity with behavioral data.

“Inference intelligence 20” is a system 10 network agent and recommendation engine 18. Inference intelligence 20 can be described as a neural network application that includes deep learning applications, machine learning and artificial intelligence. Inference intelligence 20 gathers data from 10 system components, including subjects within ubicomp 12 and sensors within ubicomp 12. It also processes data from the recommendation engine 18, computing device 26 and general reference data from external systems 28 to be used in neural network models. Neural network models can be used to determine context data about conditions, circumstances and triggers, indicators and variables. These data are used to reliably and accurately match user preference and expected outcome with the referenced human activity and behavioral information for a particular engagement or interaction type.

“Blockchain module 22, architecture, protects data generated by system 10, and user activity. Blockchain module 22 may include cryptographically secure processes steps such as user activity data record generation and validation, audience feedback data, user profile data, and immutable blockchain technology user data. Blockchain module 22 can include a private, public, and blockchain database. It also includes a data anonymizer, crypto wallet, and a blockchain processor.

“Application Program Interface (API 24) applications allow ubicomp 12 subjects to access system 10 components. API 24 can be coupled with sensors and devices from ubicomp 12. API 24 can be described as a program that is operated by a user interface application on a computing device 26. API 24 can be described as a host, network 14 gateway and programmatic interface to computing device 26. It facilitates and manages communications with system components, other system users remote operating computing devices 26, recommendation engines 18 data exchanges and external systems 28. API 24 can be used by users to create user accounts and provide information about interaction preferences and engagement types. API 24 can be used by users to configure and access ubicomp 10, sensors, and data exchange for access, data transfer, and operation by system components.

“Computing device 26″ is composed of components such network communications, data processing and interface controls. It also includes components such as camera, display screen and microphone. This allows users to interact with other computing device 26 users and system components. A computing device 26 aspect can include smart devices, smartphones, portable computers and smart televisions. A computing device 26 or multiple computing devices 26 can transmit and receive input from users. Data is transmitted and received via network 14 using protocols that could include any combination of wired and wireless communication systems. Computing device 26 can execute operations using an operating system, such as Microsoft Windows compatible OS, Apple OS X (OS), Linux, iOS and Tizen, and/or ANDROID. Computing device 26 may execute a browser app to access network services such as video, audio, instant messaging, web services and third-party services (IM), services (SMS services (MMS services), FTP services voice or IP (VOIP), services for calendaring, phone services, advertising, etc. Computing device 26 can interact with an API 24 with an outside system 28. This could include a website, server and an electronic data file. Computing device 26 may display content through processing a markup languages that describe instructions for formatting or presentation. This includes (XML), extensible hypertext Markup Language (XHTML), JavaScript Object Notation data, JavaScript with padding (JSONP) and JavaScript data. Computing device 26 may include one or more data cookies that indicate system 10 operations such as log in, location and interactions with ubicomp 12. These data cookies can also be used to log in, log out, log time within ubicomp 12, communications with other computing devices 26, and current operating systems and computing programs. One or more computing devices 26 may be operating as part of ubicomp 12. One example is that a computing device 26 can operate within ubicomp 12. It may include, but not be limited to, wearable device and camera, laptop computer or tablet computer, smart TV, networked appliance and home automation control apparatus as well as other hardware described further in FIG. 1B.”

“FIG. “FIG. A ubiquitous computing environment, also known as?ubicomp? or?pervasive computing is the basic purpose. User interaction with any device at any time, from any place, and in any format. The present disclosure identifies ubicomp 12 as a combination of networked hardware components and software components, coupled to recommendation engine 18, that can be programmed (per systems 10) to execute computerized processes, which, among other functions, generate “engagement data?” 80 are derived from user-initiated, user-controlled and automated device and appliance operations within ubicomp 12. These operations detect, track and identify human activity and behavior.

“Human activity and behavioral data from engagement data 80 extracted in ubicomp 12 and its related components, API 24 and computing device 26 may be identified, indexed and labeled according to the processing and analytics requirements and specifications for respective recommendation engines 18 and 20. Recommendation engine(s), 18 identify and name the activities, habits, routines, and behaviors that are derived from processing engagement data 80 associated to a subject in Ubicomp 12. Inference intelligence 20 applications work to correlate activity and routine data identified by recommendation engine 18, with measurable data indicating user intention, preference, context and desired outcome. This includes facial expressions, emotions and moods as well as natural language data generated through system 10 usage.

“Ubicomp 12 is a system that can be used for 10 applications using at least network 14 server 16 API 24, where network 14 hosts server 16 and server16 stores data transfers and exchanges between ubicomp 12 networked parts and software. Ubicomp 12, hardware, devices, peripherals or appliances, firmware, and software applications can be represented in a wide variety of configurations. The disclosure does not limit the description of aspects. An example ubicomp 12 arrangement might include 30-50 components (sensors and cameras, wearables and appliances, as well as home automation controls). Delivering data to recommendation engine(s), 18 to implement the disclosed innovations. In another aspect, ubicomp12 configuration only requires a few networked parts such as a smartphone and a coffeemaker to provide the inventive advantages.

“Some aspects of ubicomp 12 could include a subsystem 54 of audio peripherals 54 that can capture audio signals such as human speech, voice and audible commands. The microphone 54 can be either a standalone device that is located in a fixed place or a part of an appliance 26 that is portable or stationary. In some cases, ubicomp 12 may also include a subsystem 56 of networked cameras. These devices can capture, detect and identify data activities related to everyday life, including images of objects, brands, labels, people, animals, faces, and facial expressions that reflect emotions, gesture combinations, eye gaze, eye movements, and digital data. Camera 56 can be sensitive in the visible spectrum, or in a confined wave like infrared or ultraviolet bands. In some aspects, they are capable of capturing video images at 30 frames per second or 1920 pixels per line. Camera 56 can be used as a standalone device in a fixed place or as part of an appliance 26 that is stationary or mobile. In certain aspects, ubicomp 12 could include a subsystem of networked, device-based sensors 58. These sensors may include inertial sensors (such a accelerometer, vibration, or magnetic fields), for measuring activity-related signals; bio-sensors that can measure physiological signs like electrocardiogram (ECG), heart rate(HR), temperature, electrodermal activ (EA), blood pressure (BP), and respiratory rate (RR). Radio frequency sensors such Wi-Fi, WiMAX, Wi-Fi Mesh and Wi-radio signals and terrestrial broadcasts of radio and television, DAB, DVB and UHF TV, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DAB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DAB, DVB, DAB, DVB and GSM. The device-based sensors 58 can be either a standalone device in a fixed place or a component of an appliance 26 that is portable or stationary. The device-based sensors, 58 can be coupled to one or more actuators that are part of complex mechanisms within ubicomp 12. In some aspects, ubicomp 12 may include a subsystem of networked device free sensors that monitor and capture structural or environmental data 60 that may be stationary in a fixed location as a stand-alone device or may be a component of a device 26 or appliance that is stationary or portable, including but not limited to pressure or force sensors to track weight change, footsteps and location; ultrasound to indicate relative location of devices; infrastructure-mediated such as resistance to detect inductive electrical load changes; luminosity sensors to detect light levels; electromagnetic interference to detect proximity; water pressure to detect change in water-pressure within the pipe system; gas flow to detect gas consumption; electromagnetic noise to detect electrostatic discharges from humans touching and gestures; and passive radar that detects and tracks objects.”

“In certain aspects, ubicomp 12 includes a device subsystem 62 that allows access to control protocols that manage devices and device features, network communications, power consumption, transmission power output, power consumption, and network communications. To control access protocols for mobile devices that require multi-hop wireless connectivity schemes, ubicomp 12 also has a wired subsystem 64. In some cases, ubicomp 12 also has a gateway subsystem 66 that controls access to sensor and device subsystems to other networks such as Wide Area Networks, the Internet, cellular, or satellite. In some aspects, ubicomp 12 includes a security subsystem 68 that controls user access, encryption identity verification, defeat gateway attacks, and other functions. Security subsystem 68 may be coupled to a Blockchain system 26 or related components in some instances. In some cases, ubicomp 12 could include user interface device 70 which is coupled to the application program interface 24. In some cases, ubicomp 12 could include system interface device 72 which is coupled to application program interface 24, User interface device 70 and 72 may communicate data using networked ubicomp12 devices and components that operate API 24, such as a mobile phone or wearable device, television, home appliance, sound system, tablet, keypad and audio system. System interface 72 and user interface 70 via API 24 can enable the operation of networked devices, sensors, controls, and systems within Ubicomp 12. These include a television, appliance, camera system and audio system, as well as a light, interior/exterior dwelling mobile drone, and computerized device. System interface 72 and user interface 70 via API 24 are used to manage administrative functions, including user access authority, device access levels, communication access permissions, security parameters, passwords and content filters for devices and users within the ubicomp 12 as well as remote access to ubicomp 12, including networked systems and users, user groups, and computing equipment 26. System interface 72 may be used to communicate with 26 computing devices via API 24 in order to allow remote control of ubicomp 12’s sensors, controls, and devices. In some cases, ubicomp 12 can communicate with a server network 74 and an operating system 76. Server network 74 may be referred to as server 14 in FIG. 1A. Operating system 76 performs computerized operations in some aspects using a Microsoft Windows compatible OS (OS), Apple OS X or Linux, iOS, Tizen and ANDROID.

“In certain aspects, the ubicomp 12 apps are stored and managed by server 74. Data server 74 can be referred to as server 16. Server 74 can be described as a cloud-based or edge computing server architecture. Computer applications 78 can be coupled to server 74 via API 24, and connected to ubicomp12 components. One or more computer programs 78 may be used by ubicomp 12 to process, store, analyze, interpret, and convert system 10 and ubicomp 12 data into the engagement data 80. Engagement data 80 may be stored in a dataset repository (84). Some aspects store dataset repository 84 on computing device 26. Computer application 78 can refer to one program or a combination of multiple programs that are designed for a particular task, function, process, or operation. Computer application 78 can refer to a neural program in a particular configuration, including deep learning, artificial intelligence, and machine learning. Computer application 78 may be called a recommendation engine 18. Computer application 78 can also be called inference intelligence 20. Further examples include engagement data 80 being formatted using blockchain encryption techniques by the blockchain module 22. Computer applications 78 can execute programs such data analysis, data feature attributes computations, assign data classes, and determine a value for an engagement data80 record with applications such a linear classifier, support vector machines and decision trees.

Computer applications 78 can parse engagement data 80 and create training data 82 in various categories for comparison, labeling, labeling, assigning classes, features, attributes, etc. Training data 82 may be stored in data repository 84 in some cases. Data repository 84 may contain training data 82 attributes and labels. These include metadata identifiers, names, standards, scores, formats and categories. Individual and interrelated data, and/or datasets. 1C. 1C. Computer applications 78 can create customized data profiles for engagement and training data 80 associated with specific users. This includes anonymized and generic user activity data from Ubiccomp 12. Computer application 78 can create custom engagement data profiles 80 based on data feature attributes that have been calculated for each engagement dataset 80. This is done by applying combinatorial equations to neural network applications that assign weights or biases to feature attributes. These values either promote or degrade the feature attribute 86, as shown in FIG. 1D. These feature attributes and value represent inference intelligence 20, which is used by system 10 or related components. Attribute values, or?inference? Computer application 78 may use attribute values or?inference? to compare and identify user preferences data that is associated with engagement data 80 events. Comparative and predictive analysis programs can rate and rank experiences that are similar or different. Computer applications 78 can apply computational analytics programming, including artificial intelligence, machine-learning and deep learning to new system 10 activity data. This reduces computation errors and computational requirements, while increasing data integrity, validity and reliability. Computer application 78 can format engagement data 80 or training data 82 depending on the file type, operating system and label. It may also use variable, value, attribute, feature, and other data types. Computer application 78 can be ‘clean? in some instances. computer application 78 may clean engagement data 80 or training data 82 by correcting, removing, or adding data, such as modifications based on the desired solution focus, information sensitive, filtering high-frequency noise, data anonymization, or other data. Computer application 78 might select a sample from the collected data to help analyze larger datasets more efficiently.

“FIG. “FIG. Interaction recommendation engine, or recommendation engine 100, manages the physical and conceptual elements of system 10. It interprets actions and rules that govern interactions between system components and users. This document discloses recommendation engine 100 for the purpose of providing interaction recommendations based upon identifiable engagement data 110 input from systems or methods that capture and present relevant information, including but not restricted to: inputs such as behavior, sentiments and lifestyle preferences, biometrics and user devices, networked communication device, networked appliances and media content, platform systems, unique user profiles and external systems. Recommendation engine 100 generally collects engagement data 110 from Ubicomp 12, including API 24, system 10 components, as well as users running API 24 on computing device 26. Recommendation engine 100 generates two main datasets in certain aspects. Recommendation engine 100 uses the collected engagement data 110 to create a set of interaction data 130. This data represents an identified or desired human behavior or activity. Interaction data 130 is derived from the engagement data 110 that has been assigned to each user’s profile account. It is based on the interactions of those users. Second, recommendation engine 100 uses collected engagement data 110 to implement a computerized process and analyze steps to determine a set of information or inference Intelligence 132 that correlates preference and contextual information with interaction datasets 130. These datasets are assigned to basic user activity within Ubicomp 12. They include interactions between users and other services, interactions between users, as well as interactions between users and other services. Recommendation engine 100, for example, detects and identifies human gestures and actions that have been assigned the interaction data 130 “late night beverage”. A networked camera is used to observe the subject in action. For example, a networked camera can be placed in a kitchen and the subject will open a fridge and pour a drink into a glass at certain times of the night. The camera may employ object and label recognition to identify the drink and brand that the subject prefers and extract inference intelligence 130 associated with the specific user interaction dataset 130. Inference intelligence 132 can be referred to as inference intelligence 20. The recommendation engine 100 uses networked smart fridge inventory management technology to alert the subject and other users. It can also use automated grocery list apps and relevant external services in order to replenish the subject?s favorite late-night beverages.

“Recommendation engine 100 may contain network 102, API104, database server server 106, database 108, processor servers 116 and 118, as well as computer application 128. Network 102 allows data transfers, exchanges, and communication connections between system components 10 and recommendation engine 100. Network 102 can be referred to as network 74 or network 14. The database server 106 can be connected to network 102 and API 104. It also provides selected data, communications, and information access to ubicomp 12, computing devices 26 and 28. Server 106 may be a component of a network. Server 106, on the other hand, is an edge computing server architecture network. Server 106 can be described as an independent host, gateway, and network access within the system 10 for recommendation engine 100. Server 106 may be referred to as server 16. Database 108 could store data that is generated and sent to system 10 components. Database 108 may be referred to as a network of databases. Database 108 can be described as data repository 84 in some aspects. Database 108 can be described as a decentralized blockchain database. Database 108 contains engagement data 110. Engagement data 110 can be referred to as engagement data 80 in some aspects. Database 108 contains training data 112. Training data 112 can be referred to as training data 82 in some aspects. Data processor 118 parses engagement data inputs 110 and imports data via network 102, to use as training data 112. Computer applications 128 perform algorithmic functions like reference, comparison, recommendation or predictive analytics. Recommendation engine 100 may refer to or compare engagement data 110 class samples using a set 112 of training data. Training data 112 can include descriptive data that describes the features and attributes of class samples, including labels, contextual information, preferences, and data origin. In some aspects, database 108 stores user profile data 114. User profile data 114 can include a unique user ID, username, password, gender and age as well as e-mail address and password. User profile data 114 can also include historical user activity data, such as user engagement routines, inference Intelligence 132, platform activity and device activity, and user interaction relationships.

“Data processor server 112 hosts computerized applications for recommendation engines 100 and provides gateway access into system 10 and other related components. Data processor server 116 can be described as a network of process servers. Data processor server 116, on the other hand, is comprised of an edge computing architecture network. Data processor server 116 may be considered an independent host, gateway, and network access within the system 10 for recommendation engine 100. Data processor 118 can assign or use assigned labels and descriptors to data summaries, origin information, features and attributes, and other data, in order to process and identify engagement data 110. Data processor 118, for example, collects, cleans and prepares engagement information 110 according to the various processing, formatting and indexing requirements. These are required by recommendation engine 100 applications that generate interaction data 130 and inference Intelligence 132. Data processor 118 also includes segmentation application 122 and extraction application 124, as well as classification application 126.

“In certain aspects, data processor 120 may use filtering software 120 to manage, import and transfer engagement data 110. Filtering application 120 can be used to create training datasets, sample data, and test data. It also allows for windowing, high frequency noise reduction, and data processing by other computational applications that are fed information from engagement data 110 inputs. Filtering application 120 can execute operations like Split Data, Clean Missing Data and Partition and Sample. It also applies SQL Transformation and Clip Values. Data processor 118 can use segmentation application 122 to group engagement data 110 into different groups for machine learning, artificial intelligence and other analytic programs, data processes and signal mapping, as well as system-related programs. Segmentation software 122 can create data segments by using algorithmic clustering methods that combine unsupervised, semi-supervised and supervised categories. This method is based on applied domain expertise. Data processor 118 can use extraction application 122.4 to identify the characteristics and attributes of engagement data 110 inputs. This includes video signals, networked cameras, image recognition and facial recognition as well as gesture identification and activity labeling. Extract application 124 can transform data input to create more information or a representation of relevant features. Extract application 124 can also calculate the statistical and morphological characteristics represented data. Some aspects of training data 112 can be imported into database 108 by recommendation engine 100 from network 102 source. This includes generic information for comparison data use or generated by computer program 128 programs that extract training data from existing engagement records 110. Classification application 126 compares newly introduced engagement data 110 with existing training data 112. This is done using unsupervised, semi-supervised and supervised methods to determine if the newly presented data represents engagement data 110, training information 112, or interaction data 130. Classification application 126 can execute algorithmic operations and techniques such as k?Nearest Neighbors and Linear Discriminant Analysis. Logistic Regression and Support Vector Machines are some examples. Decision Trees and Boosted Trees, Random Forests, Neural Networks and Nearest Neighbor are also executed. Data processor 118 can use multiple classification apps 126 in certain aspects to improve classification accuracy. Data processor 118 may use multiple classification applications 126 to make classifications. These include engagement instances and outcomes, as well as predicting qualitative or quantitative engagement. Subjects’ subjective experiences with the system, components and other users will affect the measured values and unique engagement conditions. Qualitative and qualitative aspects of interactions can vary depending on their subjective experiences. A user can be the focal point, or subject, in an instance of engagement parameters or conditions, as defined by interaction data 130. Engagement recommendation intelligence 132 qualifies for the nature or value the interaction based upon the individual’s preferences and empirical profile data. It also includes contextual data. Inference intelligence132 is a reference information that is unique to each user. It can be used to validate and compare the measurements assigned to users using empirical data, as well as to predict future engagement opportunities based on objectively favorable information. In anticipation of the innovations discussed herein, engagement data 110 is captured, processed, and stored by system components. These data are used to reference the innovations described herein. They use various computational, artificial Intelligence, machine learning and deep learning techniques to identify obvious or non-obvious aspects measurable human behavior and activity that can be considered interaction data 130. This data 130 is based on subjective experiences and desired outcomes of users. While collected engagement data 110 might be useful upon introduction to recommendation engine 100 it may not have a cumulative effect as additional context and information is applied. Or, they could be more relevant as archived data which assists other applications that use time-based information.

“In certain aspects, recommendation engine 100 may include one or more computer applications 128. Recommendation engine 100 executes machine-learning programs using algorithms and neural networks architectures to improve prediction and classification accuracy. Computer application 128 can be referred to as computer applications 78 in some aspects. Computer application 128 can be used as a learning module. It is designed to compare, extrapolate, extrapolate, and validate engagement data 110 with training information 112. One example is that computer application 128 can be used as a learning module to associate, correlate, analyze, compare, extrapolate and validate engagement data 110 with training data 112. Some aspects collect engagement data 110 from inputs and assign them to the appropriate class of user or system activity. This data is then matched with engagement 110 for one of several pre-defined classes of system and user activities. Recommendation engine 100 can use learning module computer software 128 to match features and attributes of unidentified user engagement data 110 and stored training data 112. When applicable to user interactions, learning module computer application 128 may adapt existing training information 112 to create inference intelligence 132. This is stored as user profile data (114), creating an unique engagement data 110 model to a specific interaction dataset 130. FIG. FIG. 1F shows how a model can be used by recommendation engine 100 in order to identify engagement data 110 conditions, user profile data, 114 preferences, and interaction data 130, based upon inference intelligence (i.e. If required, the appropriate parties will be notified promptly and accurately. Recommendation engine 100 can use learning module computer software 128 to test an engagement modeling by comparing similar user data. This data may be reliable in predicting future interactions of a similar nature.

“In another example computer application 128 can be configured as a context agent. This software is programmed in order to identify, associate and analyze, compare and extrapolate inference intelligence 132 generated from interaction data 130 and engagement data 110. One aspect of contextual agent computer application 128 is that it can be programmed to assign biases and weights. As shown in FIG. 1D is associated with interaction data 130 and engagement data 110. These data are used to calculate various computer applications 128 and perform reliable and accurate inference intelligence (132) for recommendation engine 100. Some aspects of contextual agent computer application 128 can identify variables, conditions, or circumstances that are evidenced by analysis of engagement information 110, user profile data, 114, and interaction data 130. These factors and conditions can be introduced into recommendation engine 100 to improve the interpretability of interaction data 130 and engagement data 110. To optimize the performance of algorithmic and computational and predictive analytics programs, data insights may be stored as empirical user data 112 or training data 112 for future reference. The data provided to recommendation engine 100 may allow contextual agent computer application 128 to add, delete, modify or enhance engagement data 110, interaction data 130 features, attributes, and weights, as well as create new data classes to support inference intelligence 132. A contextual agent computer application 128 may ask for feedback from users who use API 24 on their computing devices 36. Feedback can include, but is not limited, to information about the device, such as location, text messaging and camera data, API 24 activity and the like.

“In certain aspects, the contextual agent computer software 128 may be used in conjunction with the learning module computer application 128. This is to train data analysis models and fine-tune models for optimal performances, reduce analytic error, identify bias, generalization and so on. The contextual agent computer 128 and the learning module computer 128 can be used to solicit feedback from system users 10 to validate and confirm newly presented interaction data 130, engagement data 110 or training data 112 using reference information from outside sources 28. This information may include the subject of the data to be compared and associated users via automated notifications, requests for information, surveys and the like.

Computer application 128 can be used as a recommendation module. It is programmed to analyze and compile interaction data 130 and inference Intelligence 132 and to interpret, evaluate, and predict outcomes to guide recommendation selections for positive, neutral, or unfavorable user interactions. A user can choose one or more actions or decisions to make in an interaction recommendation selection. These decisions are based upon analyzed interaction data 130 or inference intelligence 132. They may be presented as ranked or rated lists that reflect favorable outcomes, user intentions, circumstantial acts based on data instances, time-based decisions and user responses. Recommendation module computer application 128 may create engagement data 110 classes for each user to improve the predictive analysis of interaction outcomes. If a subject is shown a particular media content type that has varying engagement metrics for each media exposure event, recommendation computer application 128 might use training 114 or engagement data 110 to help them understand the differences. This will allow them to rank and rate interaction recommendations such as user preference for media genres or artists, who should present it, when they should do so, what environment conditions are best, what technical means are optimal, how long should the media presentation last, how often the media should be presented, which media options are comparable, etc. The recommendation module can identify interaction data 130, including all user data, environmental conditions and preferences. This is for example, if the subject likes to view images of yellow roses on a tablet at noon, while also eating lunch alone on weekdays (and weekends). By class, such as the one shown in the example (frequency: once per day; subject: yellowroses; method: tablet; activity: lunch; behavior; alone; schedule: only weekdays @ noon), the recommendation module will create recommendations for interactions that can be presented to the subject and/or their associated users to help them make decisions and take action. With a push notification of this interaction description, either via a designated schedule setting or an impromptu instance of recommendation engine 100, subject’s associated users will be able to receive reminders about each interaction element that constitutes an optimal engagement. This empowers them, in turn, to create the conditions necessary for the subject. You can order lunch delivery at the specified time, locate suitable images according to your subject’s preferences, send images to your tablet device and remind other users to respect your privacy during the activity. Interaction recommendations can also be generated for the subject based on either scheduled or impromptu detections of optimal conditions. The recommendation module computer software 128 can send interaction recommendations via API 24 or ubicomp’s user interface 70 to a subject’s computing devices 26 and 26. Associating user devices 26 are located outside ubicomp 12. System 10 can recognize patterns, routines, and behaviors based on training and empirical data. It can also identify user preferences and provide recommendations for interaction. This includes suggestions for favorite TV programs, availability of favorite user associates via ubicomp 12, and transportation or meals from outside services. Recommendation module computer application 128 might use a data identifyr that recognizes patterns and routines associated with interaction datasets 130. This information can be used by recommendation engine 100 to predict user activity, or behavior that follows an interaction with ubicomp 12, API 24, users operating computing devices 26 or ubicomp 12 components.

Referring to FIG. “Referring to FIG. 2, a flow diagram illustrates an example of a process 200 that delivers interaction recommendations to users according some implementations. The process starts at step 202, where engagement is associated with interactions within a ubiquitous computing environment. An engagement could include activity by a subject in a ubicomp, activity between a subjec and ubicomp parts; activity between subject and associated users either inside a remote location or within ubicomp; and activity between subject and associated users located either within or outside the ubicomp.

“Activity in step 202 can be represented in different forms of engagement data 110 in some aspects. This includes but is not limited to: physical movements, gestures and walking, speech, voice commands and haptic control motions, moods and biometrics; remote or automated operations by system 10, network 14 and/or remotely connected devices 26; user engagement via API 22 or ubicomp 12 components or network 14. Process 200 detects activity at step 204 using a trigger that is a computational model for measuring, analysing, and interpreting engagement information 110 information about an event, sequence or benchmark, user action and/or operations associated with a device program network system. The associated data are labeled interaction data 130. Process 200 then associates the activity detected with a subject or subjects. In step 208, process 220 identifies a potential audience of associated users 208. Automated operations can be used to identify a prospective audience member using predetermined thresholds or user profile information. 114, current and previous status, communication via API 24 or networked devices 26. The audience member 208 can be excluded or included in 200 process based on certain filters, such as activity category and authority level, permissions or subject matter relevance, interaction availability, correlations or comparisons between the subject’s user profile data and those associated users or other parameters.

“At step 220, process 200 collects the inference intelligence 132 from recommendation engines 100 and 128. Inference intelligence 132 could be indicative of past activities or current activities that are associated with the subject, audience, and unique engagement data 110 conditions recognized as trigger 204. A benchmark or threshold-level reference file may be created in some aspects. It is labeled and stored with user data 114. This data can then be used by system 10 (or recommendation engine 100) in the future. Process 200 creates a computational model from activity data 202 and trigger data 204. It also uses audience data, 208, inference intelligence 220, and user profile information 206. Process 200 uses the model to determine possible interactions between the subject and the audience members in step 214. Step 216 is where process 200 uses the model to calculate and assign a data value for user intentions and possible interactions. This is done by integrating activity data, user profile information (subject/audience) 206, and inference intelligence (132 with computational model 212). Process 200 uses the model to calculate outcome scores and values. These are based on the probabilities of possible outcomes and participants’ intentions. The possible outcomes are then ranked using computational model 212 to identify plausible interaction recommendations. Process 200 uses the model in step 220 to apply subject and audience member interaction rules. These rules can be used to include or exclude interaction recommendation distribution. They are based either on pre-set parameters from identification step 208, or new conditions that are based upon calculations of inclusion and exclusion based upon activity category, authority, permissions and subject matter relevancy. Process 200 creates a record using the model of engagement conditions. This includes the calendar time stamp, type, unique identification labels, related scores, values of possible interactions recommendations, instructions for participants, reminder schedule, user distribution list, and interaction instructions. The model is used to compile the engagement information and interaction recommendation data records. These are then distributed to the respective users using communication language, such as symbols, alphanumeric characters, audible signals or other executable commands. Process 200 creates interaction recommendations and engagement information for distribution to system peripherals 10. API 24, computing devices 26. external networks 28. Other ubicomp12 components. This is based on the user’s profile information. In step 226, process 200 also delivers interaction information and recommendations to system peripherals 10. These are based on the user’s profile information 206. One or more of the interaction recommendations may be rejected by a recipient. This creates new rule and filter information, and new inference intelligence (132), which then returns process 200 to step 210. Process 200 can provide additional information regarding the current engagement, or interaction recommendations, upon a user executable command control or user executable function. This includes historical data about the subject and engagement matter, graphs, charts, and interaction data analytics for the subject. Also, ratings and ranked recommendations are based on aggregated data that is local, national and anonymized. Process 200 will create a computational model that tracks, analyzes and compares expected engagement conditions with predicted interaction outcomes using known data (202,204,206,208, 208, 208). This model will be generated by process 200 upon an executable function or automated control. The probabilities calculations are based on changes to the benchmark or threshold values of the known data. Process 200 will then recalculate interaction recommendations beginning with step 202. Process 200 creates a new context data record 210 for use by process 200. This record is associated with user profile information (206) and unique engagement conditions (204).

“In step 223, process 200 will collect feedback data from participants based on the time allocated for the desired interaction. This will confirm the outcome and confirm the interaction. You can request feedback in a variety of formats by using automated programs and notifications to users devices. This allows you to communicate directly with the subject or associated users about the engagement subject matter. A user executable function, or automated command control may initiate data verification. This allows a user to be presented with various ways of communicating interaction outcomes responses, such as voice-enabled queries presented on a communication device, electronic questions delivered directly to a communications system, audible sounds and haptic gestures, facial expressions and eye movements.

Referring to FIG. “Referring to FIG. 3A, a flow chart is shown that illustrates a system or method 300 for determining interaction opportunities for a subject in a ubiquitous computing environment. This implementation of the disclosure is described. Processing logic may comprise hardware, software or a combination thereof. System or method 300 can be executed by recommendation engine 100 and ubicomp 12. Some aspects allow a subject or associated user to interact remotely with ubicomp 12 via API 24. Block 302 determines whether engagement activity was detected in ubicomp 12 by a user, networked devices 26, system operation, or from a remote source such as a networked 26 device, program stored on server 16 or an external system 28. An engagement data 110 event can be identified, labeled, and cataloged if a pre-defined threshold or benchmark is reached. This information may be based on user profile information, training data, or other data to create an interaction dataset 130. An engagement data 110 event, or a sequence of engagement data 110 events, may be considered a single interaction. An interaction can be identified using a label, unique ID, category, name or other input, depending on whether it is automated or manually.

“At block304, processing logic uses ubicomp engagement information 110 to train an neural network computational model to determine potential interaction opportunities involving subject, associated users, and system program applications, devices, or a combination thereof. In some cases, algorithms are used to determine possible interactions using available and/or referenced engagement data 110. Some aspects may contain available and referenced data such as the following: access permissions, privacy settings, user preferences and status, context data, and other information. Inference intelligence 132 may be used to determine the applicability, bias or weighted values that are used by algorithm applications. Block 306 is where processing logic calculates scores to indicate positive and negative interaction outcomes. In certain aspects, indicators can be calculated using user profile data and historical interaction 130 reference data. Block 308 is where processing logic generates a list with recommendations for interactions. The list can be ranked in some cases. This is where recommendations are associated to a score or value that is based on user preferences, user situation, or any other interaction-related dataset. These lists can then be ranked or rated according to favorability/unfavourability or neutrality. Some aspects of the recommendations may be associated with interaction conditions that define or qualify terms or requirements for a potential interaction. These are based on data available and identify a single or range that is considered acceptable or optimal. As an example, associated users might recommend visiting a subject. This could include conditions such as day, time and permitted or prohibited individuals. Block 310 receives interaction confirmations from all relevant parties, including subject matter, method and schedule, location, terms and requirements, as well as prospective participants. The interaction confirmation information may be presented in certain aspects based on pre-set conditions or user profile data. Block 312 is where the interaction outcome data are added to the neural network computational model. Block 314, the neural net computational model is updated by changes to user profile data, system data, preference data and interaction data for respective users. The system/method 300 process can be extended to block 302, 303 or 306, 308, 308, 310 or 312, depending on its aspects.

Referring to FIG. “Referring to FIG. 3B, a flow chart is shown that illustrates a system or method for determining interaction intelligence 132 for a subject related with a ubiquitous computing ecosystem, according an implementation of this disclosure. Processing logic may comprise hardware, software or a combination thereof. System or method 320 can be executed by recommendation engine 100 and ubicomp 12. Block 322, processing logic determines engagement data 110 events, and interactions 130 that are associated with a subject. A subject and/or an associated user can interact with each other from within ubicomp 12, while in others, a subject might be physically located while interfacing with ubicomp12 and its associated users. Block 324 is where processing logic applies engagement data 110 and interactions 130 to train an neural network model to recognize inference intelligence 132 information. Inference intelligence 132 can include data from subjects, users associated with them, system programs, devices or a combination thereof. Inference intelligence can be calculated from individual datasets, or a combination thereof, including, but not limited, environmental data and user profile data, user preferences data, historical data, generic training data, and user preference data. The relevancy of identified engagement data 110 in some aspects is a calculated value that can be used as weights or biases based on individual data or multiple datasets such as historical data of user profiles and past interactions, training data and probabilities values related to user preference and intentions, desired outcomes, etc. Processing logic calculates a score that compares inference intelligence to interaction outcome values 326. Block 328: Processing logic uses correlated inference Intelligence 132 and interaction outcome scores in order to train a neural net model to identify engagement data 110 precursors. This adds contextual data to inferenceintelligence 132. The precursor (or precursors) may be a value or a set of data points, or a set of parameters that establish a baseline or threshold, or other similar data. The precursor value calculation may be based on a probability or algorithm, an analytical program, or the like. The precursors can be represented in some ways by a label or category, type, number percentage, unique identifying codes, and the like. Block 330 is where processing logic applies engagement data 110 precursors in order to train a neural model that can create notifications, indicators, and triggers based upon interaction outcomes desired by the user. Notifications, indicators, and triggers may be presented in a variety of formats, including graph, line charts and percentage charts. Some aspects allow notifications, indicators, and triggers to be linked with interaction recommendations that are presented to users based upon non-computational data such as type, category, schedule, attendees and content. Block 332 updates the neural network model with engagement data 110, precursor data, and other data. Block 334 is where the neural network model gets updated with changes to user profile data, system data, preference data and interaction data for respective users. The system or method 320 process can be continued to block 322, 324 or 326.

Referring to FIG. Referring to FIG. 3C, a flow chart is shown that illustrates system or method 340 for creating interaction recommendations using preference-related data associated with a ubiquitous computing ecosystem, according an implementation of the disclosure. Processing logic may comprise hardware, software or a combination thereof. System or method 340 can be executed by recommendation engine 100, which is coupled to API 24/ubicomp 12. Block 342 is where the processing logic creates a neural network model by using computer application 78 to corroborate ubicomp 12, system data 10, interaction data 110, 130, inference Intelligence 132, and user preferences data 114. The processing logic uses the neural network model to train the model to determine the user’s intent using the above correlated data. This includes real-time event information, environmental data, archived interactions data, and generic training data. The neural network model is used to train the model to determine the desired outcome of a user using correlated data. This includes preference data, environmental data, preference information, archived interactions data and generic training data. The neural network model is used to determine the likelihood of interaction outcomes being available. This is done based on the user’s intention and preference data. Prerequisites and conditions are also considered. The processing logic calculates a comparability score at block 350 based on the value of non-physical and physical elements as well as user intention preference data. This is used to determine the likelihood that the desired interaction outcome will occur. Block 352 generates interaction recommendations. It also includes prerequisites and precursors that can be associated with the desired outcome. Block 354, the processing logic generates interaction recommendations based upon the interaction selected. Based on the response data, the processing logic calculates a correlation value, either higher or lower, between the subject’s desired outcome and the actual outcome of the interaction. The processing logic may solicit user feedback data from multiple sources, including device data, biometric and electronic data, subject centric data, user centric information of the subject, text based communications, system 10 data, inference intelligence132, system 10 data and subject centric data. Block 356 updates the neural network model with interaction recommendation information. Block 358: The neural network model is updated by changes to user profile data, system data, preference data and interaction data for respective users. The system or method 340 may continue to block 342, 344 or 346 or 348 or 350 or 352, 352, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354 or 358 in certain aspects.

Referring to FIG. Referring to FIG. 3D, a flow chart is shown that illustrates a system or method 360, which manages interaction recommendations using interaction data associated in a ubiquitous computing environment. This implementation of the disclosure is described. Processing logic may comprise hardware, software, or any combination thereof. System or method 360 can be executed by recommendation engine 100, coupled to ubicomp 12, API 24, and user profile data (114) stored on database 110. Block 362, the ubicomp engagement data event triggers generation(s) of interaction recommendation(s). Block 364, API 24’s processing logic identifies, correlates, and filters interaction recommendations according to users who are associated with a specified interaction dataset 130. The data file containing the user profile data 114 may contain the available recommendations. Block 366 is where the processing logic determines the nature and hierarchy of the interaction recommendation lists using a neural network model. This model uses at least part of the user data, inference information and audience member status. It also considers privacy settings, notification protocol, user status, and authorization level. Block 368 is where the processing logic coupled with API 24 selects at most one recommendation from user profile data.114. The recommendations are then served to user interface 70 within Ubico 12 or to a computing device 26 via a distribution method, confirmation means. A confirmation method and distribution method can be an audible tone, voice, sound, visual or graphic, alphanumeric values, video clip, and other elements. Some aspects may require a time-sensitive response, such as a number of users who choose the same recommendation, or based on which audience members have responded, in order to render recommendations. Block 370 allows the processing logic to modify, edit, or revise a recommendation list if the options presented are not accepted by one or more participants in the distributed interaction recommendations. Additional recommendations can be re-distributed and added to associated user profile data (114). The processing logic may edit, revise, or delete the recommendation list in some instances. This is done using a neural network model that uses at least part of the user data, inference information and audience status. Notification protocol, user status and other relevant data are also considered. Processing logic can request or receive interaction alternatives from users’ interfaces via API 24, and then add them to the associated user profile data data 114. These interaction recommendations are based on engagement data events or future reference of interaction data and user preference. A user can initiate the distribution to a particular audience of a personalized interaction recommendation list if they are associated with an engagement event. Block 372 updates the neural network model with interaction recommendation distribution service, responses data, and user data 114. Block 374 is where the neural network model gets updated with system data, preference data and interaction data. The system or method 360 process can be continued to block 362, 364, 366, 368 and 372 for certain aspects.

Referring to FIG. Referring to FIG. 3E, a flow chart is shown that illustrates a system or method for optimizing interaction recommendations using interaction information associated with a ubiquitous computing ecosystem, according an implementation of the disclosure. Processing logic may comprise hardware, software or a combination thereof. System or method 380 can be executed by recommendation engine 100, which is coupled to API 24 and user profile information 114 stored in database 108. Block 382 is where processing logic creates a neural network model with computer application 78 to match engagement data 110 with interaction data 130 in order to identify user intent information and desired outcomes information. The neural network model is used to calculate and assign bias values and weights to engagement data that are associated with user intent information 344 and desired outcomes information 346. Some aspects may use historical data from a user profile or generic training data to generate weights and biases. The neural network model is used to determine correlations between user intent and interaction outcome information. This logic can then be applied to block 386. The processing logic at block 388 determines whether there is a minimum threshold for the calculated weight or bias score combination. This improves the accuracy and precision of interaction recommendations. If the minimum threshold is not met, the processing logic will not recommend interaction. Instead, it will save data to be used in the future. The neural network model is used to generate block 392 which determines the interaction recommendation hierarchy. It uses higher correlation scores between the user intent information and the desired outcome information. The neural network model generates triggers at block 394. This processing logic uses assigned weights and bias values to identify similar engagement data 110. These weights and biases indicate conditions, prerequisites, or precursors for interaction outcomes. Block 396 is where the processing logic displays and presents recommendations to users. It also includes conditions, prerequisites and precursors to interaction outcomes. Block 398 is where the neural network model, including user profile, preference, data and interaction data are updated. The system or method 380 process can be continued to block 382, 384 or 386 or 388 or 390 or 392, 394 or 396 in certain aspects.

“Objectively recommendation engine 100 performs at a more efficient and precise basis as engagement events 110 provide greater intelligence of interactivity data 130 and inference Intelligence 132 insights including user preference, lifestyle habits and behaviors. These insights include user preferences, lifestyle choices, habits, tastes and behaviors, conditions, variables, contingencies, and schedules so that interaction recommendations can be presented in a timely and more relevant way that encourages and promotes user interaction and fosters meaningful engagement between users of the system.”

Referring to FIG. “Referring to FIG. 4A, an illustration of a blockchain-based engagement platform is shown. Method or system 400 can be described as a blockchain system technique, or method 22 in some aspects. This disclosure discloses blockchain methods for protecting and transacting interaction data and engagement data that is generated and resulting from users, apps, and hardware connected to or operating in a ubiquitous computing environment. These aspects describe the foundational information that can be accessed (engagement) or interpreted (interactions), on a peer to peer platform using computerized programs and apps for purposes such as identification and classification analytics, predictions and recommendations. They can also be used in various processes, networks, devices, and methods. These transactions, also known as Engagement Interaction Data (or EID), can be managed by blockchain components, including blocks, nodes and miners, consensus protocols and tokens, encrypted key, smart contracts, and other tools. An EID transaction record, or ledger, is maintained by all nodes in method 400. Each newly created block is time stamped and independently verified by consensus protocols. EID transactions can include information headers that describe various block data structures, including side branches, main branch, and orphan. These blocks are then mined and replicated to every node in the network. EID can be detected by system 400 and a block is assigned a token value. Based on EID ownership and permissions granted by authorized associated users (receivers), the value is digitally signed by adding the previous transaction to the hash and the public key for the receiver in a Blockchain 404. A token can be described as an unit of digital value that EID has assigned to it. It may also exist in the blockchain register on system 400. A smart contract is a software code or protocol used to verify, contribute or execute the negotiation or performance a contract using method or system 400. Smart contracts are used in the current example to manage the transfer of EID among users, devices, and applications of the innovation, including related applications, parameters, protocols and protocols for identity management and authentication, digital privacy and authorization access.

It is notable that, based upon the disclosures made in this document about EID sources, it is clear that the importance of following principles and standard to collect, interpret, and share such data is highlighted. The present disclosure aspects describe how to interpret and discover personal communication methods, style, emotions, sentiments, bioinformatics, and other quantified-self types such as lifestyle habits, preferences, and lifestyle habits, using current technologies. The methods and systems described herein use centralized and decentralized models to create and manage immutable blocks data and metadata. This supports data integrity, digital rights management, data security, device registration, authentication and validation, and data integrity. Method or system 400 generally generates, manages and operates various components for blockchain technologies customized to EID transactions, including decision managers and distributed ledgers.

“Method or System 400 is associated with or a component a peer-to?peer engagement platform 402 which includes a Blockchain 404, a Blockchain Sub-science System 406, an API 408 and a Network 410. A first user or?subject? 412, a second or associate user? Subject 414: A first node 416 and a second 426. Engagement platform 402 can be described as system 10 in some aspects. Engagement platform 402 communicates and operates with some of the system 10 components. These include ubicomp 12, network 14, API 24, computing device 26, external 28 and recommendation engine 100. One or more of the nodes 416, 426, may represent the user, device, and activity in innovation. Node 416 and 426 could be computing devices 26 controlled by a User Operating API 24. This API provides a user interface that allows the user to manage their engagement activity, user identity as well as subscriber activity, profile information, and other related platform data. Node 416, 426, may be a user interface 70 that is controlled by a user-operating API 24 to manage engagement activity and subscriber activity. Profile information and other related platform data can also be managed from node 416, 426, in some cases. Automated programming may be used to represent a node 416 or 426 on a hardware component, appliance, or networked via API 24. Node 416 and 426 can be represented by automated programming on the system 10 operating system software components of ubicomp 12, network 14 or 16, API 24 or external system 28, or recommendation engine 100. System or method 400, in some aspects, is a virtual machine that runs decentralized applications (or Dapps), on a computer network to manage nodes that keep EID transaction records and smart contract histories. System or method 400 can be described as a public blockchain or permissionless network. System or method 400, in some aspects, is a private or consortium-based blockchain that grants access to only those who have permission.

“Method or System 400 includes one or more Blockchains 404. Blockchain 404 may be referred to as engagement data 110 in some instances. Blockchain 404 can be linked to a subscience system 406 which includes memory or storage for the blockchain-related system, platform data, programs and instructions. One or more sub-science system 406 may be included in method or system 400. To perform the following operations, functions and execute programs, applications, instructions and other blockchain-related tasks, the Blockchain Sub-science System 406 can be linked to engagement platform 402 or method 400. As described in the previous description of the innovation, interaction and engagement activity between users on engagement platform 402. may generate a blocked chained EID. This can be used to integrate EID transactions for individual user accounts and shared user accounts using both blockchain database 404 or blockchain sub-science systems 406. The method or system 400 can be coupled with the application programming interface (API 408). API 408 may be referred to as API 24 in some instances. API 408 can implement interface operations for method 400, related components, and devices, including inputs, outputs, video and graphics for the user. To facilitate communication between components, method or system 400 can use network 410. Network 410 may be called network 14 in some instances. Method 400 can include at least one user 412 and one user 414. A first user 412 and a second user 414 may, in some instances, be referred or defined as account holders, third party participants, subscribers, contributors, or subscribers on method or system 400. A first user 412 and second user 414 may be a living organism, such as a human or a pet. A second user 414 can be identified as an associate of the first user 412. In some cases, the first user 412 can be identified as the associate user of second user 414. One or more first nodes 416 or second nodes 426, may be included in method or system 400. Node 416 can contain one or more components, including processor 420 and API 422, memory 418, and EID key 424. Memory 418 can store software, data and instructions, or any other executable commands, for processors 420, API 422, and method 400. One or more memory 418 may be found in some aspects. The electronic circuits and logic that make up processor 420 can be used to process data, run programs, or issue commands for hardware or software components of method 400. One or more processors 420 may be found in some aspects. The processor 420 architecture could include a microprocessor or microcontroller, an arithmetic unit, video and graphics processors and other components. API 422 can implement communication interfaces to user input, video, graphics components, devices, apps, and software in digital or analog configurations. API 422 may be referred to as API 24 in certain aspects. EID key 424 could include any 412 interaction or engagement information used in cryptographic transactions using public and private keys to identify, authenticate and encrypt. EID key 424 could be a combination of alphanumeric characters digitally stored in a memory 418. EID key 424 can be assigned to multiple accounts (412 accounts), one account with multiple users, or a single account.

“Node 426 could contain one or more memory 428 and processor 430, API 432, and EID key 444. Memory 428 can store software, data or other executable commands, either permanently or temporarily, for processors 430 and 400 on the hardware and software components. One or more memory 428 may be present in some cases. The electronic circuits and logic that make up processor 430 can be used to process data, run programs, or issue commands for hardware or software components of method 400. One or more processors 430 may be found in some cases. A processor 430 architecture could include a microprocessor or microcontroller, an arithmetic unit, video and graphics processors and the like. API 432 can implement communication interfaces to user input, video, graphics and component operations. It also allows for the execution of applications and software in digital or analog configurations. API 432 may be referred to as API 24 in certain aspects. EID key 434 could include any user interaction or engagement information 414 used in cryptographic transactions using public and private keys to identify, authenticate and encrypt. EID key 434 could be a combination of alphanumeric characters digitally stored in memory 428. EID key 434 can be assigned to one user account 414, multiple user accounts or multiple accounts with multiple users. Nodes 416 or 426 could be devices that can communicate with components of system 400. Nodes 416 or 426 may be at least one of the computing devices 26. The first and second nodes 416 and 426 are electronic, machine-based, networked devices, with or without user interfaces. These include a vacuum cleaner, flying robot, automated vehicle, home appliance, voice interface device, camera and HVAC system.

Referring to FIG. 4B is a block diagram of a subscience computing system 440 that implements a blockchain-based transaction on an engagement platform 400. Sub-science system 440 can be referred to as sub-science systems 406. Sub-science computing systems 440 include a processor 442, an API 444, and an EID 446. The electronic circuits and logic that make up processor 442 could be used to process data, run programs, or issue commands for hardware or software components of computing system 442.

“Sub-science computing system 442 includes one or more processors in some aspects. Some processors 442 can be configured to access blockchained EID storage 456 to operate blockchain data applications 458 operations with blockchain instructions 460 on remote and local blockchain databases 454 which are connected via an API 444 interface. API 444 can implement communication interfaces to video, graphics components, devices and applications in digital or analog configurations. API 444 can implement communication between different components of computing system or method 400 in certain aspects. API 444 may be called API 408. EID system 446 could include at least one operating systems 448, EID program 405 and decision module 452. It also may contain a blockchain database 454. EID system 446 may be one or more systems within a blockchain computer network that manage EID records, EID transactions and other aspects. Operating system 448 could contain or access one of several software, applications, executable programs, or 450 for block functions, transactions, controls, and/or commands for various parts of computing system 440. EID program(s), 450 could be one or more programs within a blockchain computer network that manage EID records, EID transactions, and other information. EID program (450) may be coupled with programs on engagement platform 402. These programs extract, generate, and analyze EID records. EID module 452 can run software, apps, or executable programs that analyze, process, store, and transfer EID records to a blockchain database 454. In certain aspects, decision module 452 may be one or more modules of a blockchain computer network that manage EID records or EID transactions. Decision module 452 can be described as a neural network program that is generated from computer software 78. Decision module 452 can be considered a component of recommendation engine 101 in some instances.

The EID system contains a 456-blockchain database, which also includes data storage 456, and blockchain applications 458, as well as instructions 460. Data storage 456 could also include storage of blockchained data 404. Data storage 456 could include EID records and EID transaction records in some cases. Data storage 456 could include EID key 424 and 434 information. Blockchain applications 458 could include cryptography, encryption, data formatting, data formatting, computation applications, tokenization, logic applications and smart contract applications. Instructions for blockchain applications 460 could include operating system 448, programs 452, and decision module 452 operation. Users can control the EID generated by ubicomp 12 and its interpretation through blockchain 404. This includes other users, system components, and third-party services that are connected via API 444 and system 400. Decision module 452 could be used with processor 442, operating systems 448 and programs 450 depending on filters, access permissions, commands for distribution, etc. These preferences are controlled by blockchain applications 458, instructions 460, which determine what EID is extracted and formatted for processing by system 400. This information can then be used in blockchained transactions or records. EID blocks 404 that represent a user, as well as associated activity, master level control, and ownership, can be stored locally or remotely on an account associated to a user. Some aspects store stored EID blocks404 on data storage 456. Some aspects store stored EID blocks404 on node 418. 428 are associated with users or linked to user devices. A network of sub-science computing system 440 can operate on a blockchain network in order to aggregate and anonymize EID data for system 400. Modified versions of generic EID data may be used to aggregate user behaviors, interactions, and engagement preferences in order to support various statistical, algorithmic and/or predictive programs and applications.

“Various implementations relate to engagement platform activity and, more specifically, interaction recommendations generated from a recommendation engine. Some implementations concern interactions between individuals and ubiquitous computing environments or ubicomps and the networked technologies that are associated with them. Some implementations deal with user interactions where a subject in a ubicomp interacts to one or more associated users who are remote networked to him/her and the relevant ubicomp activity data. Some implementations also relate to interactions between users who are not associated with the ubicomp. This is where subject activity can influence interaction and recommendation. Some implementations also relate to engagement platforms that use artificial intelligence to learn behaviors, lifestyle habits and engagement preferences. Authorized users can receive insights based upon interactions of both the subject and the associated users. This allows them to optimize all aspects of user engagements relating to a variety of subjects and activities such as sleep, eating, media consumption and phone calls. The platform can easily map user preferences and provide insight into their optimal conditions and schedules. This will allow individuals and groups to plan and execute personalized interactions with other users. If the platform has collected intelligence about a subject’s life that shows they like images and photos of a particular nature, it can alert associated users and direct them to the appropriate content online. It also prompts them to add the material into a queue to be presented at the requested time on the device. As the engagement platform provides more information about the user’s lifestyle and engagement preferences, it can also identify media and interaction recommendation elements tailored to the schedule and conditions of the subject.

A recommendation engine using artificial intelligence and machine-learning programming would improve the ability to identify nuanced elements of desired activities (subject behavior, location, time, mood, etc.). Engagement precursors (inference information), and triggers (physical event or user engagement setting) are all indicators of the desired interactions that each user will have. Artificial intelligence programming can interpret these preferences, trigger, and precursor elements. It compares the training or reference data with the subject, verifies the users and compares it with historical data to tailor recommendations for user interactions. The system can anticipate user preferences and lifestyles and use this information to improve the overall experience for users of the engagement platform. It also uses passive sensor applications to predict possible intentions and outcomes based on interaction data analytics. These experiences should include a style and method of providing recommendations (device configuration, displayed information; timing, language, audio, images, symbols; etc.). And logic programming that is tailored to the user’s interaction perspective in relation to outcomes and intentions. An engagement platform that gives access to reliable lifestyle preferences information can greatly influence professional relationships. This allows authorized users to schedule transportation, delivery of streaming content, primary caregiving visits, emergency responses systems, elder care, petcare, home security, scheduling transport, messaging, video calls, and broadcast television viewing. An engagement platform can help users determine when and how to engage. It also offers tremendous benefits in terms of social, emotional, and economic collateral.

Referring to FIG. “Referring to FIG. 5A, a diagram showing exemplary components of an engagement system system 500 for interaction suggestions in which broad implementations may be used. System 500 can be described as system 10. System 500 is a ubiquitous computing environment, or?ubicomp? 502, a network 504, 506, 506 and 508 respectively. 508 is a recommendation engine 508, 508, 506 and 508 respectively. 502 also includes a database 506 and 506 as well as a 506 and 506 databases. 502 has a number program interfaces 512. In some aspects, the ubicomp 502 can be called ubicomp 12. In certain aspects, ubicomp 502 may be referred to collectively as?ubicomp data. 514 to be used by system 500 from activities initiated within and outside 518 Ubicomp 502. This automated programming operates both on fixed 520 and portable 522 networked computers and uses software technologies within ubicomp 522. Database 506 may include one or more storage systems. Database 506 can store system data, user data and program application data. It also stores recommendation engine data 508, Blockchain information 510 and other similar data in accordance to previously disclosed implementations. Recommendation engine 508 can be described as recommendation engine 18. A blockchain 510 can be considered a blockchain 22 in some cases. API 512 allows communication between users and system components. This can be done within a single system 500, or across a network 500. Interface applications enable communication including text, audio, and video data sharing, as well as user profile data, program execution, commands, platform data analytics, and user activity data. API 512 can be referred to as API 22 in certain aspects. API 512 can be used to operate on one device or on multiple devices at once, without restrictions on its scope, function, controls, and/or access authorisation. API 512 functionality, operation, and scope may vary depending on user role, device type, purpose, system configuration, and physical or non-physical nature. API 512 also facilitates connection recommendations and user activity for various components and any number users. This includes comparable systems, user activities and administrative users as well as devices, third-party service, ecommerce services and other vehicles, appliances and robots. API 512, in some instances, can allow users 516 and 518 to control, manage, and control information, components and network access on system 500. Administrator 542 might create unique user groups 544 that include user profiles accounts 516,518 and third-party services and networks. These user groups may contain specific information, data and data created and/or managed in different ways by 516,518 who are part of group 544. Some aspects of system 500 software and hardware components can create biases in data values and skewed data classes. These data attributes may also be used to generate data value variations for ubicomp 514 and other programs that are part of system 500. Data biases can influence or alter ubicomp 514 collection, interpretation and classification, categories calculations, comparisons, predictions, and the like. There may be one or more subject users 516 within group 544. Subject user 516 doesn’t have to interact or engage with system 500 only from within ubicomp 502 as devices and monitoring apps provide enough interaction and data 514.”

“API512 can be configured as a user-oriented API to recommend interactions to animal or human users 516, 518. API 512, in some cases, can communicate recommendations between human and animal 516 and 518 users with an automatic system interface 520 or device interface 522 responsive physical controls, voice enabled commands and facial recognition, emotion detection, audible and biometric data status. API 512 may be used to configure administrative controls and authorizations. For example, an automated program or user can establish rules, filters, or parameters for accessing, sharing, or collecting ubicomp data 514. API 512 can be used to request user 516, 518 feedback information. This is done using computer application number 78. Device 522 controls are used to identify user preferences prior, during, or after events in which ubicomp data 514 has been collected and recorded. API 512 can also initiate feedback information inquiries. It may solicit user responses using a variety of user engagement methods, including a text message or electronic survey.

API 512 can be configured in certain aspects so that a user 518 from outside ubicomp 502 can manage networked connections to API 512 inside ubicomp. This includes system 500 operations, networked devices 520 and devices 522 as well access to ubicomp data 514. User 516 within Ubicop 512 represents a human or an animal. An outside user 518 controls automated system 520 and device 522. This includes lighting, surveillance cameras and 2-way audio, automated feeders, HVAC, door locks, etc. Another example is user 516 in ubicomp512 who is disabled or incapacitated. Outside user 518 controls automated system 520 and device 522. These controls include lighting, surveillance cameras and HVAC zones. Video calls, biometric measuring devices, motion sensors, home appliances, and selection, delivery, and presentation of audio and text via cloud server, streaming service, cloud service, cellular network or commercial subscription service. Files stored on local databases are also controlled by outside user 518. Another example is that an outside user 518 could modify API 512 filters and settings to acquire and analyze ubicomp data 514 generated from user 516 within Ubicomp 512. This is based on the recommendation engine 508 information regarding observed, past and anticipated lifestyle preferences and habits.

“API512 can be set up for developer controls via integration platform 526. At least one third-party program could be created to run on system 500. Any number of software programs or program code may be included in a third-party program. These applications can enhance or complement engagement system functions, platform operations and user experiences. Database 506 can store components of integration platform 526 in some aspects. These include a minimum one software development kit, a program window, debugger and visual editor, compiler and runtimes. Integration platform 526 allows third-party applications to add user controls and components, as well as user experience features, on top of API512. Based on the recommendation engine 508 data, integration platform 526 allows third-party programs access to API 512 and add components, user experience features, and user controls. Integration platform 526 allows API 512 to communicate with third-party programs, web services, streaming data services, and other APIs. API 512 allows interaction recommendations to be generated from any combination of ubicomp data 514 sequences or combinations that define an interaction. These interactions can be unique to one user 516-518, multiple users 516-518, multiple user groups 544, system 500, or related components. This includes individual components of the system as well as a networked grouping of system components. Information and media content can also be delivered to the user 516-518, 518 or 518. Interaction recommendations can be delivered in many formats, including emails, text messages and multimedia presentations, images and graphs, surveys, polls and customer reviews. API 512 allows users 516, 518 access to information, components, network connections, and devices on system 500. Administrator 542 can create unique user groups or forums 544 that are composed of user profile accounts 516 and 518. These user profiles may include, for instance, related devices, components, programs and networks. System 500 users have access to data and information generated by 516 and 518 who are part of group 544. Administrator 542 can create a user account for another user 516 who is the primary user or subject. Administrator 542 may create a user account for another user 516 that is a primary user or?subject? A primary user or subject user’s 516 status design defines customization, orientation and modification of system 500 apps, processes, operations and analytics. One example is that subject user’s 516 status can generate biases and skewed classes of data and data attribute values ubicomp 514 used in computer application 78 and other computerized applications used by system 500 that affect or change engagement and interaction 514 collection, interpretation and classification, categories and calculations, comparisons and predictions, and the like. The user profile status for an infant can be distinguished from that of an elderly user, disabled user, handicapped user, impaired user, or any other user who has unique preferences and characteristics based on their lifestyle or living conditions. There may be one or more subject users 516 within a group 544. A subject user 516 doesn’t have to interact or engage with system 500 only from within ubicomp 502, where devices or monitoring applications provide enough ubicomp data 514. Computer application 78 can process ubicomp 514 from multiple users 516 and 518 simultaneously, using biases or attributes that are assigned to each user account. Computer application 78 might offer ubicomp 514 preference information for recommendation engine 508, where users may indicate their desire or intention for different outcomes. This is based on an outcome probabil score. At that point recommendation engine 508 will determine if there are any actions, non-actions, alternative options, or other ways to solicit feedback from the group of 544 participants. Computer application 78 can solicit bias and attribute information about group participants using activity data tracked by system 500 components. This data is derived from 516, 518 user profiles accounts. It also provides behavioral data derived ubicomp data 514. Direct inquiry via device API 502 allows for a variety forms of information such as multiple choice questionnaires, graphic images, percentage values, audible and visual sounds, graphs, charts, graphs, charts, graphs, and the like. Computer application 78 and recommendation engines 508 can submit and resubmit interaction suggestions to group 544 participants, until there is consensus on the outcome. Some examples of consensus or agreement regarding interaction outcomes may be absolute for all participants in group 544. It could also include a consensus percentage for all participants in group 544 for a specific interaction outcome (including decline or action), an affinity value for subject 516 of a group 544 and subject’s 516 associate users 518. This can be used to determine whether a subset of participants in group 544 or all participants in group 544. Computer application 78, recommendation engine 508, and other components may process bias and attribute data in certain aspects. This may lead to the possibility that the desires or intentions of a subject 516, 518 or 518 may be greater than those of another participant 516, 518 or 518 in a proposed interaction.

Administrator 542 is responsible for assigning administrative access and permissions to user 516 and 518 accounts that are part of group 544. Administrator 542 can manage group 544 access to subject 516. This includes but is not limited to user access permissions and user interaction rules. Content filters, user ubicomp 514, interaction analytical data, user engagement data, and other such functions. Administrator 542 can create a group 544 for a subject user 516 by inviting other users 518, assigning access permissions and authorization levels, engagement filters and interaction rules. This is based on user accounts 516 and 518, respectively, of group 544. User group preference data can be referred to as ubicomp data 514 in some instances. User group preference data can be established in some cases by users 516-518, 542 depending on their unique role, contribution or position within group 544, or any interaction conditions therein. In certain aspects, ubicomp 514 may be detected, acquired and processed by system 500. It can also be processed, correlated and analyzed by automated programming operations using API 512 program settings.

“Media Engagement”

“In certain aspects, media program 528 is integrated with API512 and coupled with recommendation engine 508 or blockchain 510. This allows users to select, access and present media content to 516 and 518. Media program 528, in some aspects, is a third-party subscription service that allows users to view, download, and stream media content. As previously mentioned, an administrator 542 can create a user group 544 for a subject 516 in order to use media program 528. This allows them to generate, select, share, and present media content. It also includes associated 500 data, including ubicomp 514 feedback information, which is based on user experiences with each media program 528. The ubicomp 514 feedback data may include preference data and analytic data as well as notification data, predictive, predictive, recommendation, and other data. API 512 controls can be used to send ubicomp data 514 notifications to one or more users 518 of user 516 preference data. This data includes data such as language preference, music genre preference, location, type, type, and type of content, and program titles and/or title. Recommendation engine 508 can generate media content lists to present to any authorized user 516. These media content lists are generated using automated programming or user-definable settings. It is based on user 516 preferences for media consumption, which were generated from historical and newly detected ubicomp data 514 that was associated with user 516. Recommendation engine 508 creates media content lists to present to any authorized user 516. 518 is derived from historical and newly detected ubicomp data 514 that was collected from users on both system 500 and 500. The present example shows that system 500 programs can include both hardware and software. These may include biometric sensors to capture physiological conditions and facial recognition sensors for identifying users and capturing emotions; motion sensors tracking physical movement, haptic gestures, and environmental sensors tracking light levels, doors locks, and temperature; audio sensors capturing voice commands; video cameras enabling 2-way communication; video cameras enabling object detection; portable devices operating API’s; and audio visual devices with automated text recognition programming. Control systems for operating drones and robotics devices and other such as well as well as well. The present example shows that recommendation engine 508 can use computer application 78 for analysis and processing ubicomp data 514, 518 from individual users; aggregated media preference data from system 500 activity and data from a select number of users within a networked group 500. Computer application 78 can implement automated recommendation engine 508 processes that identify and recommend media content. These are based on user media consumption preference data, aggregated data from groups of 500 users, or based on data from individual users. Authorized users 516, 518 can request media content lists via API 512 controls. This allows them to define and create media consumption preference data parameters using either automated programming or manually. These parameters include demographics, geographic location, device, lifestyle habits, etc. Recommendation engine 508 can generate lists of available and desired media content databases over local or remote networks 504 and present them to subject users 516 and 518. Recommendation engine 508 can be linked via network 504 with media sharing platform 528 to allow searching, browsing, purchasing, transacting, delivering, and presentation media content. This is done using automated software programming, API 512. As an example, recommendation engine 508 could be connected via network 504 with media sharing platform 528. This is automated programming that generates media content according to the user’s 516 media preferences. These preferences are derived from historical ubicomp data 514. API 512 may be used by associated group 544 users to access recommended media content. User 516 can also set parameters such as genre, length, program, triggers or thresholds from ubicomp data 514 to allow access to the content.

“Healthcare Engagement”

“In certain aspects, health program 530 is integrated with API512 and coupled with recommendation engine 508 or blockchain 510. It provides personal health care information and related information to one to three users 516, 518. Health care program 530 can be described as a subscription-based or account-based third party program service that collects, views, shares, schedules, analyzes, and analyses personal health care data. Administrator 542 can create a user group 544 for subject 516 in order to use health care program530. This will allow the administrator to generate, analyze, and share personal health information, including real-time status, interpersonal communication, care request notifications, and patient conditions. The ubicomp data 514 feedback data may include preferences, analytic, predictive, recommendation, and other data. Administrator 542 can use API 512 controls to create parameters, filters, and settings to detect, receive, and distribute ubicomp data 514 used by group 544. Administrator 542 can use API 512 controls to create parameters, filters, and settings for processing and interpreting ubicomp data 514 used by group 544. API 512 controls may allow for parameters and filters to be applied to user 516 preferences information. These could include personal health assessments, needed or desired patient care, descriptions and patient health statuses, time sensitivity to sharing and responding to notifications related to patients, the level of information that is shared with notifications and details about patient information. API 512 controls may be used to send ubicomp data 514 notifications to one or more users 518. These notifications will include user 516 preference information, generated from and associated health care program experience 530 user experiences. User 516 preferences information can include all health-related data measured by system 500, including interactions via telecommunications (call, text and chat), in person visits, nursing care and physical therapy interactions, eating or feeding, emergency care and routine personal care services. The present example shows that system 500 programs can include both hardware and software applications. These may include biometric sensors that capture physiological conditions, facial recognition sensor for identifying users, and emotional state sensors; motion sensors tracking movement and haptic gestures; environmental sensors tracking light levels and temperature; audio sensors capturing sounds and voice commands; video camera enabling 2-way video communication; video cameras enabling object detection; portable devices operating API’s; and audio visual devices with automated content recognising programming. Control systems for operating drone and robotic devices and such as well as well as well. Some examples show that user 515 preferences information can be shared with group 544 and specific members 516 and 518 using newly detected data health program 530. This software operates within or networks to ubicomp 502 and may include health diagnostic equipment, wearable biometrics, video or audio device monitor signals, emotion recognition signals; portable devices operating API’s; audio visual devices with automated content recognition programming; control systems for robotic and drone devices, and other related technologies. Recommendation engine 508 generates care-related information based upon user 516 preferences information. This includes personal care lists, care service prerequisites and care methods for any authorized user 518. It also provides personal health care information based in part on the subject user’s 516 lifestyle choices and preferences, as well as historical ubicomp data 514. API 512 may be used by users 518 to access recommended health-care practices from a variety sources, such as website services, web-based references materials, video conferencing and networked reference database. Recommendation engine 508 could use computer application 78 in the present example to analyze and process ubicomp 514 from individual users 516-518, including aggregated health-care preference data from system 500 activity or data from multiple users 516-518 that are active within a networked group of 500 systems. Computer application 78 can implement automated recommendation engine 508 processes that identify and recommend health-care practices based on user preference data 516 or aggregated data 516 from selected users identified among all users in a networked system 500.

“Caregiving Engagement”

“In certain aspects, lifestyle & wellness program 532 is integrated with API512 and coupled to recommendation engine 508 & blockchain 510. It provides personal health data, lifestyle information, and recommendations using ubicomp 502 component including system 500 software apps operating on fixed 520 and mobile devices 522. These components identify, track, measure and interpret, then analyze, and present lifestyle and wellbeing information to one or multiple users 516, 518. Lifestyle and wellness program 532 can be described as a subscription- or account-based third party program service that collects, views, shares, schedules, analyzes, and analyses personal lifestyle and wellbeing data generated from user experiences. Administrator 542 could create a user group 544 for subject 516 in order to use lifestyle and well-being program 532. This will allow the administrator to generate, analyze, and share personal lifestyle and wellbeing information, including ubicomp 514 feedback information, that is derived from user experiences with respective wellness and lifestyle programs 532. The ubicomp 514 feedback information could include preferences, analytic, predictive, recommendation, and other data. System 500 programs can be networked with fixed devices 520 or portable devices 522 to manage the lifestyle and wellness program 532. These programs may also work together or individually. The present example shows system 500 programs that may include hardware and software. These could include biometric sensors to capture physiological conditions and facial recognition sensors to identify users. Location sensors track location and proximity of other objects. Audio sensors can also be used to record sound commands. Video cameras enable 2-way audio and video communications. Portable devices can operate API’s. There are audio visual devices that can automatically recognize content. Control systems for controlling robotic and drone devices. Administrator 542 can use API 512 controls to create parameters, filters, and settings for receiving, analyzing, and distributing ubicomp data 514 used by group 544. Administrator 542 can use API 512 controls to create parameters, filters, and settings for processing and interpreting ubicomp data 514 used by group 544. API 512 controls may allow for parameters and filters to be applied to user 516 preferences information. These include mood data analysis, methods to describe health status, time sensitivity to sharing and responding to notifications, the level of information that is shared in notifications, and methods for description. API 512 controls may be used to send ubicomp data 514 notifications to recommendation engine 508 from user 516 preference information. This preference information is generated from and associated in some ways with 532 lifestyle and wellness program user experiences. User 516 preferences information can include any lifestyle or wellness data that is measurable by system 500. This includes but not limited to activity levels and sleep schedules, food consumption habits and food quality, food intake schedules, media consumption schedules, media habits, inter-personal activity schedules, online activities habits, technology use, and so on. User 516 preference information can be shared with group 544 and specific members 516 and 518 depending on the detected behavioral data within Ubico 602. This includes a wearable biometric reading or video or audio device for person-to-person communications, emotion recognition signals and motion sensors, smart device online data, download and streaming data activity, facial recognition, networked appliances and other similar data. Users 516, 518 can use API 512 to access lifestyle and wellbeing program 532. This allows them to receive recommended lifestyle and wellness interaction lists. These include user 516’s sleep hours, preferred media content, preferred media consumption times, preferred medication administration times, ideal conditions for person-to-person communications, and in-person interactions. Recommendation engine 508 could use computer application 78 in the present example to analyze and process ubicomp 514 from individual users 516 and 518. This includes lifestyle and wellness preference data from system 500, as well as aggregated data from multiple users 516,518 and groups 544 who are active within a group 544 of systems 500. Computer application 78 can implement automated recommendation engine 508 processes that identify and recommend health care services based on user preference data, aggregated data, or data from a selected group of users within a networked group 500.

“Consumer Goods Delivery Engagement

Summary for “System and Method for Recommendations in Ubiquitous Computing Environments”

“Field of Disclosure”

“The present invention relates to computerized AI applications in pervasive computing environments and, more specifically, to systems and methods that provide inference recommendations that encourage optimal user interactions with associated technologies and users.”

“Description of Related Art.”

“Ubiquitous computing technologies can be one component of intelligent system designed for technology enabled humans experiences. They can enhance user experiences in many areas of connected lifestyles.” User interaction with any device, sensor, or computer, regardless of location or format, is called ubiquitous computing.

“On a single basis, today’s ubiquitous computing systems may produce data in the realm Ambient Intelligence. These hardware and software configurations can be used to aid human decision-making using historical and real-time data. Connected consumer appliances and the Internet of Things (IoT) contain commodity sensors. connected consumer appliances, Internet of Things (?IoT?) devices, and smart devices at such a level that ad-hoc ubiquitous computation (hereinafter??ubicomp?)) can be achieved. By pairing basic devices with neural network apps that interpret the data, environments can be created. Technology makes it possible to measure and predict user preferences using available sensor data. This is due to the large amount of data that can easily be collected from common devices, such as biometric and human physiology data, facial expressions, moods, location data with GPS, and movement data that can all be labeled with accelerometers, cameras, and gyroscopes.

“Generally speaking, the cost of these commodity devices and sensor evolutions has driven down their costs and made them more ubiquitous in daily life. Many applications can be designed to provide a specific user experience using a small number of data signals. The performance promised is always delivered. A narrowly defined user experience can limit the ability to extract insights from users and use data collected. Multiple sensor and device data channels that indicate interactions do not necessarily equate with ‘insights. “Where there are no means of contextualizing or learning user experiences.”

“Overall, there are sufficient data, hardware and software to be able to approximate limited forms of evaluating or predicting human behavior at the consumer level. Passive preference data, or?inference Intelligence? Pervasive computing environments may allow for passive preference data or?inference intelligence. Edge computing architectures are where data science methods like customized machine learning and deep learning are used on devices that parse, analyze, and interpret data. It is possible to enhance understanding of the user’s subjective thoughts in certain settings, provided there are sufficient reference information.

“In one aspect, the present disclosure discloses a method for tracking the activity at least one person from at least two of the ubicomp devices. This method could include steps such as generating tracking data from at least two ubicomp device, collecting each generated tracking information, conglomerating each generated trackingdata, converting each conglomerated tracking dataset into at least one standard data format, classifying each converted conglomerated tracked data using interaction preference insights and sending recommendations to the at most one human based upon the classified converted conglomerated tracked data.

In another aspect of this disclosure, the method for tracking activity may also include pairing two or more ubicomp device. Smart devices include a smart meter and a thermostat, as well as a smart temperature sensor, smart humidity sensor, smart pressure sensor, and a sensor for smart vibration.

“In another aspect, the step of transmitting recommendation may also include the use of an inference recommendation engine to generate interaction recommendations for the human.”

“Another aspect of the disclosure is that the generated tracking information may include behavioral and activity data from the human. The method of tracking the activity could also include the analysis of each of the generated track data.

“In another aspect, the present disclosure may also include the generation of interaction recommendations by at least one person in response to the analysis of the behavioral data.”

“Another aspect of the disclosure is that the interaction recommendations can include time, location frequency, duration, and/or feelings.”

“Another aspect of the disclosure is that the method for tracking activity may include updating interaction recommendations on at minimum one of a time frequency base, a biometrical level basis or an emotion level based, a sentiment level based, and a motion level basis. A temperature level base, a humidity level basis. a barometric level based, a light level basis. a frequency level basis. and a radiation level basis.

“Another aspect of the disclosure is that the step of transmitting suggested interactions may also include the generation of feedback to at least two ubicomp device pairs.”

“In another aspect, the method for tracking activity may also include the storage of generated tracking data in at most one cloud computing network.”

“A network for tracking activity of at least one person from two or more paired Ubicomp devices is disclosed in another aspect of this disclosure. The network could include a first and second track computing devices for generating tracking information from each of at least two paired Ubicomp devices, as well as a collect computing unit for collecting each generated tracking detail, a conglomerate computing facility for conglomerating all of the generated data, a convert computing apparatus for converting the conglomerated tracking to at least one standard data format, and a classify computing tool for classifying the converted conglomerated tracked data using interaction preference insights. A transmitting device is used for sending recommendations to the at least one person based on the classified conglomerated generation of tracking data.

A smart meter, smart thermostat, smart temperature sensor and smart humidity sensor are all possible ubicomp devices under another aspect of the disclosure.

“Another aspect of the disclosure is that the transmitting device could include an inference recommendation system engine system that generates interaction recommendations for at least one person.”

“In another aspect, the present disclosure may also include an analyzing computing unit for analyzing activity or behavioral data from the tracking data at least one person.”

“In another aspect, the network could include an interactive computing unit for generating interaction recommendations in response the the analyzing computing devices analyzing the behavior data.”

“In another aspect, the present disclosure may also include interaction recommendations that could include time, location frequency, duration, or sentiments.”

“In another aspect, the present disclosure may also include an updating computing unit for updating interaction recommendations on the basis time, motion, temperature, humidity, barometric level or light level.

“In another aspect, the present disclosure may provide a means for the transmitting device to generate a feedback signal to the pair of ubicomp devices.”

“Another aspect of the present disclosure is that the network may also include a cloud computing system coupled with the first track computing device and the second track computing device for storing the generated tracking information from the two paired Ubico devices.”

The benefits of using neural network solutions to enhance lifestyle experiences are well-known. A system that uses basic sensors and devices to provide reliable intelligence about a person’s lifestyle preferences can be economically viable. It is also useful for the subject, their families and friends as well as any other social networks or service providers. A method that presents interaction recommendations based upon known behaviors, learned engagement preferences, and expected outcomes creates new channels for communication to user lifestyle insights. With machine learning and sensor level reliability, you can improve the accuracy and efficiency of your response time, anticipate your needs and provide assistance. The proposed applications need to secure the collection, storage, and exchange of the data. In order to reduce the risk of data theft and misuse, it would be a good idea to incorporate immutable technology like blockchain encryption. This will prevent data modification and ensure that only authorized users have access.

“Systems, methods and devices, according to various examples of disclosure, may address one of the aforementioned shortcomings experienced in generating comprehensive interactions recommendations using commodity sensors that accurately reflect users’ intent and desired outcomes. Certain aspects of the disclosures allow for the collection, analysis, and presentation of lifestyle, biometric, and behavioral data. This allows users to respond in a timely fashion to the subject. An interaction recommendation system can generally provide recommendations for a large number of user engagement events or instances. However, optimal performance requires adequate sensor data, computing power, and reference information.

“In addition, personal device lifestyle integrations are part of the ‘connected lifestyle. The concept of a “connected lifestyle” has evolved beyond traditional networked systems like lighting controls, heating and cool, audio and video, security cameras, and heating and cooling. Data driven applications that measure specific interactions are possible with the IoT innovation. This is due to the large number of consumer products embedded with network applications like microwaves and toasters, coffeemakers, dishwashers and water faucets.

A ubiquitous computing environment, or ubicomp, can be created either on an ad-hoc basis or permanently using a few or many connected consumer products that are common in homes that operate on LAN or WIFI networks. These include cameras, motion sensors smart phones, thermostats door entry/exit sensors smart TVs, thermostats, door sensors, door sensors, wearable devices and tablets. Basic cameras can now recognize faces, recognize facial expressions, identify objects, recognize gestural patterns, and measure physical movements to catalogue specific activity types. These devices and sensor signals provide only a small amount of information. Given their networked environment, however, there are tremendous opportunities to gain from methods that combine these information sources and use their unique data channels to generate more robust and contextualized insight.

“There are some benefits to adding context and personalized information to interactions involving connected device and sensors that enhance upon existing technology. Inference intelligence is a way to improve basic engagements with connected technology. Connected devices need human input-physical controls to set the settings. Remote control via mobile app or voice commands can be sent from a voice-enabled computer. Software applications can predict these actions and the decision points leading up to them. Predictions for single actions are made based on repetition. This level of engagement does not give much insight into intent, motive, desired outcome or special conditions. If a coffee maker is scheduled to make coffee at 6 AM every day, but the subject decides to stay up until 8 AM, how will the coffee maker adapt to this situation without human intervention? For example, the present disclosure describes a method for identifying sleep conditions. This may include using camera motion sensors or data from a smartphone to determine the waking phase. The data then triggers the coffeemaker operation based upon real-time inference data which adjusts to different waking hours each day.

“Second-level, inference intelligence can increase engagement insights for interactions among users. Current technologies allow humans to identify, track, measure, and eventually catalog their activities and habits. Inference data can be used for understanding contextualized exceptions to daily routines. Lifestyle habits and habits are indicative of preferences. Inference intelligence is more efficient and accurate for users who are connected remotely. Inference intelligence allows remote users to adapt to changing circumstances by receiving notification updates. Inference intelligence could send automated updates to third parties if the subject is awake and has an appointment or visitor scheduled to arrive at a specific time.

Inference intelligence applications, third, can use natural language processing to provide rich context information. Machine learning applications can use sentiment, desire, and intent to efficiently assist machine learning applications in predictive analytics. They also offer personalized recommendations for each individual based on their unique circumstances. Artificial intelligence solutions that use many sensors and devices to connect can be greatly improved by obtaining the user’s preferences and subjective thoughts in real time.

Fourth, improving efficiency and accuracy in human interactions yields substantial intangible benefits. Remote relationships offer a wealth in collateral benefits, especially for mental health and emotional support. Deep learning applications improve insight data through continuous interactions and increase recommendation quality for all parties regarding optimal engagement circumstances, timing, best practice, contingencies for unforeseen situations, and the like.

“Accordingly to one aspect of the current disclosure, an inference recommendation system system and method for generating interaction suggestions informed by user-centric activity and behavioral data from commodity sensors and commercial devices in a pervasive computing ecosystem are described. This teaching is not intended to be a complete description of the disclosure. The disclosed aspects are sufficiently detailed to allow one skilled in art to use them, but it is important to understand that they are only examples. You can therefore derive other implementations, aspects and/or configurations from the disclosed information without departing from its spirit and scope.

The present discloses a software solution to improve human interactions using data from disparate networked sensors and devices operating in a subject?s home to identify interactions and the subject?s preferences (time and location, frequency, duration and sentiments for each interaction). These preference data can be used to guide, assist, and inform users in a home or to other connected devices.

An enterprise solution can be deployed using cloud or edge architecture. A client device, such as a smart phone, can connect to a network of sensors and devices that measure and identify human behavior and activity. An API can collect data from connected devices and sensors and process it via cloud computing to make usable formats. This allows analytic apps to determine the subject’s interactions, preferences, recommendations, and predictive analytics for interactions with other connected users.

“In one aspect, the present disclosure teaches systems and methods for conglomerating data and converting it to a standard data format. This can be used in consumer sensors or devices that operate on standard networks, such as Wi-Fi, Bluetooth, and so forth. This provides information about human behavior and activity. These interactions may be classified and interaction preference insights more clearly identified-information that can inform and guide interaction recommendations for the subject and their associated users.”

This approach is technically possible due to changes in the consumer technology landscape. The first is that the cost of sensors and devices providing activity and behavior data has dropped drastically, while their functionality and data quality have increased. Second, common sensors (cameras and wearables as well as wireless chipsets), are deployed everywhere. They actively capture user information (sleep, activity levels, types of activity, gestures etc., diet, physiological biometrics), location, media consumption, sentiments and social connectivity. These technologies are being developed by major companies (e.g. Apple, Google and Microsoft) at a rapid pace. They also offer open-source platforms that allow for the integration of different hardware and software technologies onto a single platform. The viability of this technology is supported by the growing market for artificial intelligence software chipsets, edge computing solutions that allow for low latency and improved network capacity and speed.

“In one aspect, the present disclosure teaches systems and methods for conglomerating data and converting it to a standard data format. This can be used in consumer sensors or devices that operate on standard networks, such as Wi-Fi, Bluetooth, and so forth. This provides information about human behavior and activity. These interactions may be classified and interaction preference insights more clearly identified-information that can inform and guide interaction recommendations for the subject and their associated users.”

The present disclosure may, in one aspect, use a multichannel, multimodal solution to more effectively enable a subject?s unique set of experiences to be captured digitally (within the limits of accessible devices and sensor). Because of lifestyle preferences, such as fear or missing out (‘FOMO), personalized data could be readily available. “, and other secret settings for device privacy.”

The present disclosure describes a data-agnostic method for capturing sensor and device data from connected devices in a dwelling that is occupied or occupied. It also provides instructions for predictive or recommendation models and patterns to guide and inform users both inside and outside of the dwelling. This information is tailored based on the unique lifestyle, routine, and preferences of each subject. Machine learning is used to refine insight analytics.

“In one aspect, the disclosure teaches a software program for enterprise-level architecture. An enterprise-level architecture could include a cloud computing network and storage resource, which could be used in a hybrid edge computing configuration to optimize efficiency and energy priorities. A mobile client or downloadable version of the software can be used on any smart device that connects with a local network. This allows it to identify available devices and sensors and provide engagement data resources. This could be the foundation for ubiquitous computing environments. The cloud can convert captured data into a usable format that allows bulk processing and analytics to take place. Once enough data has been captured to create an interaction, the system can then create user settings based on the user?s preferences. Preference data, or “inference intelligence?” is information that the system uses to determine which interaction the user prefers. The preference data or?inference intelligence can be directly input by a user, or learnt by the system through repeated interactions. An API is used to send recommendation and predictive analytics information via smart devices to known interaction associates. This information can then be incorporated into automated operations commands for sensors and networked devices.

Referring to FIG. “Referring to FIG. System 10 comprises ubiquitous computing environment 12, server 16, recommendation engine 18, blockchain module 22, inference intelligence 20, and computing device 26. FIG. 10 is an illustration of the system 10. FIG. 1A shows only one component of system 10. However, other aspects may include multiple ubiquitous computing environments 12, servers 16, recommendation engines 18, and 18-bit inference intelligences 20, as well as blockchain modules 22, inference engines 20, inference algorithms 20 and computing devices 26. System 10 is a platform that improves interaction and engagement for users within and outside the ubiquitous computing environment 12. It uses data collected from the system 10 and interprets it. System 10’s main focus is on the subjects observed activities, moods and biometric data within the ubiquitous computing environment 12. However, system 10 can also collect information about other users via APIs 24 operating computing devices 26 in order to better understand interaction related data. This may improve interaction quality, efficiency and reliability.

“Generally, ubiquitous computing environment (hereinafter?ubicomp?) 12 includes software and hardware components, including sensors, appliances, and portable networked devices. In some cases, ubicomp 12 could be made up of a small number or a large collection of sensors and networked devices as shown in FIG. 1B. 1B. In some cases, ubicomp 12 could be represented by a smart device such as a smartwatch or a smart phone. The composition of the available devices and sensors that can capture behavioral data signals and human activity to determine ubicomp12 operation and utility, regardless of the original commercial applications, is what defines ubicomp 12. If a manufacturer installed motion detection software on a security camera to detect movement, the present innovation could use that data signal to identify emotions, identify gestures and label objects. System 10 can collect data signals from ubicomp 12 devices, sensors, and other sources to format, index, and catalog the available data for use by recommendation engine 18 or inference intelligence 20.

“System 10 is possible to implement according to ubicomp 12, configurations that differ based on sensor and device inputs, and the raw and processed data generated accordingly. In certain aspects of the disclosure, ubicomp 12 includes a Body Area Network. (BAN), where one or more sensors can be carried by a subject. In some cases, ubicomp 12 includes a Personal Area Network. This is where one or more sensors can be deployed in a physical environment. Some aspects of ubicomp 12, such as sensors and devices, can execute programming and operations. These include the detection and classification of physical movement and the labelling and classifying of a set activities (sleeping/walking, cooking, grooming etc.). Recognize physical objects and their status, assess cognitive levels, identify emotions and learn personal patterns and lifestyle habits. Remote users can also be notified about activity events and data-related benchmarks.

“In some aspects system 10, ubicomp 12, recommendation engine 18, blockchain module 22, computing device 26 and external system communicate, use and transfer data through network 14. These implementations may use standard communications technologies such as the Internet, wired, wireless, Ethernet, WiMAX, 3G, 4G, CDMA and LTE, digital subscriber lines (DSL), broadcast network and the like. Network 14 may employ networking protocols in one aspect. These include file transfer protocol, SMTP, multiprotocol label shifting (MPLS), transmission protocol/Internet protocol TCP/IP, User Datagram Protocol UDP, hypertext transport protocol (HTTP), etc. Data exchanged over network 14 may be encrypted using traditional encryption technologies like secure sockets layer, transport layer security and Internet Protocol security. It can also formatted with technologies including hypertext Markup Language (HTML) or extensible markup Language (XML). Network 14 can be described as a data center, edge computing, cloud-based computing system architecture or combination thereof. It is connected via the Internet using a variety of computing systems, computing resource, storage hardware and security applications.

“One or more servers 16 can be connected to ubicomp 12, network 14, and provide selected data and information access for computing device 26 and external systems 28. Server 16 may be a component of a server network. Server 16 can be described as an independent host, gateway, and network access within the system 10 for recommendation engines 18, 20, and 22 and 24 respectively.

Recommendation engine 18 generally collects ubicomp12 data for processing, analysis and indexing, labeling and cataloging human behavior and human activity. Recommendation engine 18 can manage artificial intelligence, deep learning, and other neural network applications in some aspects. It processes, analyzes, converts, and interprets ubicomp12 information into human activity, and behavioral data that can be used by system 10 components or inference intelligence 20. Recommendation engine 18 can correlate inference intelligence 20 and human activity with behavioral data.

“Inference intelligence 20” is a system 10 network agent and recommendation engine 18. Inference intelligence 20 can be described as a neural network application that includes deep learning applications, machine learning and artificial intelligence. Inference intelligence 20 gathers data from 10 system components, including subjects within ubicomp 12 and sensors within ubicomp 12. It also processes data from the recommendation engine 18, computing device 26 and general reference data from external systems 28 to be used in neural network models. Neural network models can be used to determine context data about conditions, circumstances and triggers, indicators and variables. These data are used to reliably and accurately match user preference and expected outcome with the referenced human activity and behavioral information for a particular engagement or interaction type.

“Blockchain module 22, architecture, protects data generated by system 10, and user activity. Blockchain module 22 may include cryptographically secure processes steps such as user activity data record generation and validation, audience feedback data, user profile data, and immutable blockchain technology user data. Blockchain module 22 can include a private, public, and blockchain database. It also includes a data anonymizer, crypto wallet, and a blockchain processor.

“Application Program Interface (API 24) applications allow ubicomp 12 subjects to access system 10 components. API 24 can be coupled with sensors and devices from ubicomp 12. API 24 can be described as a program that is operated by a user interface application on a computing device 26. API 24 can be described as a host, network 14 gateway and programmatic interface to computing device 26. It facilitates and manages communications with system components, other system users remote operating computing devices 26, recommendation engines 18 data exchanges and external systems 28. API 24 can be used by users to create user accounts and provide information about interaction preferences and engagement types. API 24 can be used by users to configure and access ubicomp 10, sensors, and data exchange for access, data transfer, and operation by system components.

“Computing device 26″ is composed of components such network communications, data processing and interface controls. It also includes components such as camera, display screen and microphone. This allows users to interact with other computing device 26 users and system components. A computing device 26 aspect can include smart devices, smartphones, portable computers and smart televisions. A computing device 26 or multiple computing devices 26 can transmit and receive input from users. Data is transmitted and received via network 14 using protocols that could include any combination of wired and wireless communication systems. Computing device 26 can execute operations using an operating system, such as Microsoft Windows compatible OS, Apple OS X (OS), Linux, iOS and Tizen, and/or ANDROID. Computing device 26 may execute a browser app to access network services such as video, audio, instant messaging, web services and third-party services (IM), services (SMS services (MMS services), FTP services voice or IP (VOIP), services for calendaring, phone services, advertising, etc. Computing device 26 can interact with an API 24 with an outside system 28. This could include a website, server and an electronic data file. Computing device 26 may display content through processing a markup languages that describe instructions for formatting or presentation. This includes (XML), extensible hypertext Markup Language (XHTML), JavaScript Object Notation data, JavaScript with padding (JSONP) and JavaScript data. Computing device 26 may include one or more data cookies that indicate system 10 operations such as log in, location and interactions with ubicomp 12. These data cookies can also be used to log in, log out, log time within ubicomp 12, communications with other computing devices 26, and current operating systems and computing programs. One or more computing devices 26 may be operating as part of ubicomp 12. One example is that a computing device 26 can operate within ubicomp 12. It may include, but not be limited to, wearable device and camera, laptop computer or tablet computer, smart TV, networked appliance and home automation control apparatus as well as other hardware described further in FIG. 1B.”

“FIG. “FIG. A ubiquitous computing environment, also known as?ubicomp? or?pervasive computing is the basic purpose. User interaction with any device at any time, from any place, and in any format. The present disclosure identifies ubicomp 12 as a combination of networked hardware components and software components, coupled to recommendation engine 18, that can be programmed (per systems 10) to execute computerized processes, which, among other functions, generate “engagement data?” 80 are derived from user-initiated, user-controlled and automated device and appliance operations within ubicomp 12. These operations detect, track and identify human activity and behavior.

“Human activity and behavioral data from engagement data 80 extracted in ubicomp 12 and its related components, API 24 and computing device 26 may be identified, indexed and labeled according to the processing and analytics requirements and specifications for respective recommendation engines 18 and 20. Recommendation engine(s), 18 identify and name the activities, habits, routines, and behaviors that are derived from processing engagement data 80 associated to a subject in Ubicomp 12. Inference intelligence 20 applications work to correlate activity and routine data identified by recommendation engine 18, with measurable data indicating user intention, preference, context and desired outcome. This includes facial expressions, emotions and moods as well as natural language data generated through system 10 usage.

“Ubicomp 12 is a system that can be used for 10 applications using at least network 14 server 16 API 24, where network 14 hosts server 16 and server16 stores data transfers and exchanges between ubicomp 12 networked parts and software. Ubicomp 12, hardware, devices, peripherals or appliances, firmware, and software applications can be represented in a wide variety of configurations. The disclosure does not limit the description of aspects. An example ubicomp 12 arrangement might include 30-50 components (sensors and cameras, wearables and appliances, as well as home automation controls). Delivering data to recommendation engine(s), 18 to implement the disclosed innovations. In another aspect, ubicomp12 configuration only requires a few networked parts such as a smartphone and a coffeemaker to provide the inventive advantages.

“Some aspects of ubicomp 12 could include a subsystem 54 of audio peripherals 54 that can capture audio signals such as human speech, voice and audible commands. The microphone 54 can be either a standalone device that is located in a fixed place or a part of an appliance 26 that is portable or stationary. In some cases, ubicomp 12 may also include a subsystem 56 of networked cameras. These devices can capture, detect and identify data activities related to everyday life, including images of objects, brands, labels, people, animals, faces, and facial expressions that reflect emotions, gesture combinations, eye gaze, eye movements, and digital data. Camera 56 can be sensitive in the visible spectrum, or in a confined wave like infrared or ultraviolet bands. In some aspects, they are capable of capturing video images at 30 frames per second or 1920 pixels per line. Camera 56 can be used as a standalone device in a fixed place or as part of an appliance 26 that is stationary or mobile. In certain aspects, ubicomp 12 could include a subsystem of networked, device-based sensors 58. These sensors may include inertial sensors (such a accelerometer, vibration, or magnetic fields), for measuring activity-related signals; bio-sensors that can measure physiological signs like electrocardiogram (ECG), heart rate(HR), temperature, electrodermal activ (EA), blood pressure (BP), and respiratory rate (RR). Radio frequency sensors such Wi-Fi, WiMAX, Wi-Fi Mesh and Wi-radio signals and terrestrial broadcasts of radio and television, DAB, DVB and UHF TV, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DAB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DVB, DAB, DVB, DAB, DVB and GSM. The device-based sensors 58 can be either a standalone device in a fixed place or a component of an appliance 26 that is portable or stationary. The device-based sensors, 58 can be coupled to one or more actuators that are part of complex mechanisms within ubicomp 12. In some aspects, ubicomp 12 may include a subsystem of networked device free sensors that monitor and capture structural or environmental data 60 that may be stationary in a fixed location as a stand-alone device or may be a component of a device 26 or appliance that is stationary or portable, including but not limited to pressure or force sensors to track weight change, footsteps and location; ultrasound to indicate relative location of devices; infrastructure-mediated such as resistance to detect inductive electrical load changes; luminosity sensors to detect light levels; electromagnetic interference to detect proximity; water pressure to detect change in water-pressure within the pipe system; gas flow to detect gas consumption; electromagnetic noise to detect electrostatic discharges from humans touching and gestures; and passive radar that detects and tracks objects.”

“In certain aspects, ubicomp 12 includes a device subsystem 62 that allows access to control protocols that manage devices and device features, network communications, power consumption, transmission power output, power consumption, and network communications. To control access protocols for mobile devices that require multi-hop wireless connectivity schemes, ubicomp 12 also has a wired subsystem 64. In some cases, ubicomp 12 also has a gateway subsystem 66 that controls access to sensor and device subsystems to other networks such as Wide Area Networks, the Internet, cellular, or satellite. In some aspects, ubicomp 12 includes a security subsystem 68 that controls user access, encryption identity verification, defeat gateway attacks, and other functions. Security subsystem 68 may be coupled to a Blockchain system 26 or related components in some instances. In some cases, ubicomp 12 could include user interface device 70 which is coupled to the application program interface 24. In some cases, ubicomp 12 could include system interface device 72 which is coupled to application program interface 24, User interface device 70 and 72 may communicate data using networked ubicomp12 devices and components that operate API 24, such as a mobile phone or wearable device, television, home appliance, sound system, tablet, keypad and audio system. System interface 72 and user interface 70 via API 24 can enable the operation of networked devices, sensors, controls, and systems within Ubicomp 12. These include a television, appliance, camera system and audio system, as well as a light, interior/exterior dwelling mobile drone, and computerized device. System interface 72 and user interface 70 via API 24 are used to manage administrative functions, including user access authority, device access levels, communication access permissions, security parameters, passwords and content filters for devices and users within the ubicomp 12 as well as remote access to ubicomp 12, including networked systems and users, user groups, and computing equipment 26. System interface 72 may be used to communicate with 26 computing devices via API 24 in order to allow remote control of ubicomp 12’s sensors, controls, and devices. In some cases, ubicomp 12 can communicate with a server network 74 and an operating system 76. Server network 74 may be referred to as server 14 in FIG. 1A. Operating system 76 performs computerized operations in some aspects using a Microsoft Windows compatible OS (OS), Apple OS X or Linux, iOS, Tizen and ANDROID.

“In certain aspects, the ubicomp 12 apps are stored and managed by server 74. Data server 74 can be referred to as server 16. Server 74 can be described as a cloud-based or edge computing server architecture. Computer applications 78 can be coupled to server 74 via API 24, and connected to ubicomp12 components. One or more computer programs 78 may be used by ubicomp 12 to process, store, analyze, interpret, and convert system 10 and ubicomp 12 data into the engagement data 80. Engagement data 80 may be stored in a dataset repository (84). Some aspects store dataset repository 84 on computing device 26. Computer application 78 can refer to one program or a combination of multiple programs that are designed for a particular task, function, process, or operation. Computer application 78 can refer to a neural program in a particular configuration, including deep learning, artificial intelligence, and machine learning. Computer application 78 may be called a recommendation engine 18. Computer application 78 can also be called inference intelligence 20. Further examples include engagement data 80 being formatted using blockchain encryption techniques by the blockchain module 22. Computer applications 78 can execute programs such data analysis, data feature attributes computations, assign data classes, and determine a value for an engagement data80 record with applications such a linear classifier, support vector machines and decision trees.

Computer applications 78 can parse engagement data 80 and create training data 82 in various categories for comparison, labeling, labeling, assigning classes, features, attributes, etc. Training data 82 may be stored in data repository 84 in some cases. Data repository 84 may contain training data 82 attributes and labels. These include metadata identifiers, names, standards, scores, formats and categories. Individual and interrelated data, and/or datasets. 1C. 1C. Computer applications 78 can create customized data profiles for engagement and training data 80 associated with specific users. This includes anonymized and generic user activity data from Ubiccomp 12. Computer application 78 can create custom engagement data profiles 80 based on data feature attributes that have been calculated for each engagement dataset 80. This is done by applying combinatorial equations to neural network applications that assign weights or biases to feature attributes. These values either promote or degrade the feature attribute 86, as shown in FIG. 1D. These feature attributes and value represent inference intelligence 20, which is used by system 10 or related components. Attribute values, or?inference? Computer application 78 may use attribute values or?inference? to compare and identify user preferences data that is associated with engagement data 80 events. Comparative and predictive analysis programs can rate and rank experiences that are similar or different. Computer applications 78 can apply computational analytics programming, including artificial intelligence, machine-learning and deep learning to new system 10 activity data. This reduces computation errors and computational requirements, while increasing data integrity, validity and reliability. Computer application 78 can format engagement data 80 or training data 82 depending on the file type, operating system and label. It may also use variable, value, attribute, feature, and other data types. Computer application 78 can be ‘clean? in some instances. computer application 78 may clean engagement data 80 or training data 82 by correcting, removing, or adding data, such as modifications based on the desired solution focus, information sensitive, filtering high-frequency noise, data anonymization, or other data. Computer application 78 might select a sample from the collected data to help analyze larger datasets more efficiently.

“FIG. “FIG. Interaction recommendation engine, or recommendation engine 100, manages the physical and conceptual elements of system 10. It interprets actions and rules that govern interactions between system components and users. This document discloses recommendation engine 100 for the purpose of providing interaction recommendations based upon identifiable engagement data 110 input from systems or methods that capture and present relevant information, including but not restricted to: inputs such as behavior, sentiments and lifestyle preferences, biometrics and user devices, networked communication device, networked appliances and media content, platform systems, unique user profiles and external systems. Recommendation engine 100 generally collects engagement data 110 from Ubicomp 12, including API 24, system 10 components, as well as users running API 24 on computing device 26. Recommendation engine 100 generates two main datasets in certain aspects. Recommendation engine 100 uses the collected engagement data 110 to create a set of interaction data 130. This data represents an identified or desired human behavior or activity. Interaction data 130 is derived from the engagement data 110 that has been assigned to each user’s profile account. It is based on the interactions of those users. Second, recommendation engine 100 uses collected engagement data 110 to implement a computerized process and analyze steps to determine a set of information or inference Intelligence 132 that correlates preference and contextual information with interaction datasets 130. These datasets are assigned to basic user activity within Ubicomp 12. They include interactions between users and other services, interactions between users, as well as interactions between users and other services. Recommendation engine 100, for example, detects and identifies human gestures and actions that have been assigned the interaction data 130 “late night beverage”. A networked camera is used to observe the subject in action. For example, a networked camera can be placed in a kitchen and the subject will open a fridge and pour a drink into a glass at certain times of the night. The camera may employ object and label recognition to identify the drink and brand that the subject prefers and extract inference intelligence 130 associated with the specific user interaction dataset 130. Inference intelligence 132 can be referred to as inference intelligence 20. The recommendation engine 100 uses networked smart fridge inventory management technology to alert the subject and other users. It can also use automated grocery list apps and relevant external services in order to replenish the subject?s favorite late-night beverages.

“Recommendation engine 100 may contain network 102, API104, database server server 106, database 108, processor servers 116 and 118, as well as computer application 128. Network 102 allows data transfers, exchanges, and communication connections between system components 10 and recommendation engine 100. Network 102 can be referred to as network 74 or network 14. The database server 106 can be connected to network 102 and API 104. It also provides selected data, communications, and information access to ubicomp 12, computing devices 26 and 28. Server 106 may be a component of a network. Server 106, on the other hand, is an edge computing server architecture network. Server 106 can be described as an independent host, gateway, and network access within the system 10 for recommendation engine 100. Server 106 may be referred to as server 16. Database 108 could store data that is generated and sent to system 10 components. Database 108 may be referred to as a network of databases. Database 108 can be described as data repository 84 in some aspects. Database 108 can be described as a decentralized blockchain database. Database 108 contains engagement data 110. Engagement data 110 can be referred to as engagement data 80 in some aspects. Database 108 contains training data 112. Training data 112 can be referred to as training data 82 in some aspects. Data processor 118 parses engagement data inputs 110 and imports data via network 102, to use as training data 112. Computer applications 128 perform algorithmic functions like reference, comparison, recommendation or predictive analytics. Recommendation engine 100 may refer to or compare engagement data 110 class samples using a set 112 of training data. Training data 112 can include descriptive data that describes the features and attributes of class samples, including labels, contextual information, preferences, and data origin. In some aspects, database 108 stores user profile data 114. User profile data 114 can include a unique user ID, username, password, gender and age as well as e-mail address and password. User profile data 114 can also include historical user activity data, such as user engagement routines, inference Intelligence 132, platform activity and device activity, and user interaction relationships.

“Data processor server 112 hosts computerized applications for recommendation engines 100 and provides gateway access into system 10 and other related components. Data processor server 116 can be described as a network of process servers. Data processor server 116, on the other hand, is comprised of an edge computing architecture network. Data processor server 116 may be considered an independent host, gateway, and network access within the system 10 for recommendation engine 100. Data processor 118 can assign or use assigned labels and descriptors to data summaries, origin information, features and attributes, and other data, in order to process and identify engagement data 110. Data processor 118, for example, collects, cleans and prepares engagement information 110 according to the various processing, formatting and indexing requirements. These are required by recommendation engine 100 applications that generate interaction data 130 and inference Intelligence 132. Data processor 118 also includes segmentation application 122 and extraction application 124, as well as classification application 126.

“In certain aspects, data processor 120 may use filtering software 120 to manage, import and transfer engagement data 110. Filtering application 120 can be used to create training datasets, sample data, and test data. It also allows for windowing, high frequency noise reduction, and data processing by other computational applications that are fed information from engagement data 110 inputs. Filtering application 120 can execute operations like Split Data, Clean Missing Data and Partition and Sample. It also applies SQL Transformation and Clip Values. Data processor 118 can use segmentation application 122 to group engagement data 110 into different groups for machine learning, artificial intelligence and other analytic programs, data processes and signal mapping, as well as system-related programs. Segmentation software 122 can create data segments by using algorithmic clustering methods that combine unsupervised, semi-supervised and supervised categories. This method is based on applied domain expertise. Data processor 118 can use extraction application 122.4 to identify the characteristics and attributes of engagement data 110 inputs. This includes video signals, networked cameras, image recognition and facial recognition as well as gesture identification and activity labeling. Extract application 124 can transform data input to create more information or a representation of relevant features. Extract application 124 can also calculate the statistical and morphological characteristics represented data. Some aspects of training data 112 can be imported into database 108 by recommendation engine 100 from network 102 source. This includes generic information for comparison data use or generated by computer program 128 programs that extract training data from existing engagement records 110. Classification application 126 compares newly introduced engagement data 110 with existing training data 112. This is done using unsupervised, semi-supervised and supervised methods to determine if the newly presented data represents engagement data 110, training information 112, or interaction data 130. Classification application 126 can execute algorithmic operations and techniques such as k?Nearest Neighbors and Linear Discriminant Analysis. Logistic Regression and Support Vector Machines are some examples. Decision Trees and Boosted Trees, Random Forests, Neural Networks and Nearest Neighbor are also executed. Data processor 118 can use multiple classification apps 126 in certain aspects to improve classification accuracy. Data processor 118 may use multiple classification applications 126 to make classifications. These include engagement instances and outcomes, as well as predicting qualitative or quantitative engagement. Subjects’ subjective experiences with the system, components and other users will affect the measured values and unique engagement conditions. Qualitative and qualitative aspects of interactions can vary depending on their subjective experiences. A user can be the focal point, or subject, in an instance of engagement parameters or conditions, as defined by interaction data 130. Engagement recommendation intelligence 132 qualifies for the nature or value the interaction based upon the individual’s preferences and empirical profile data. It also includes contextual data. Inference intelligence132 is a reference information that is unique to each user. It can be used to validate and compare the measurements assigned to users using empirical data, as well as to predict future engagement opportunities based on objectively favorable information. In anticipation of the innovations discussed herein, engagement data 110 is captured, processed, and stored by system components. These data are used to reference the innovations described herein. They use various computational, artificial Intelligence, machine learning and deep learning techniques to identify obvious or non-obvious aspects measurable human behavior and activity that can be considered interaction data 130. This data 130 is based on subjective experiences and desired outcomes of users. While collected engagement data 110 might be useful upon introduction to recommendation engine 100 it may not have a cumulative effect as additional context and information is applied. Or, they could be more relevant as archived data which assists other applications that use time-based information.

“In certain aspects, recommendation engine 100 may include one or more computer applications 128. Recommendation engine 100 executes machine-learning programs using algorithms and neural networks architectures to improve prediction and classification accuracy. Computer application 128 can be referred to as computer applications 78 in some aspects. Computer application 128 can be used as a learning module. It is designed to compare, extrapolate, extrapolate, and validate engagement data 110 with training information 112. One example is that computer application 128 can be used as a learning module to associate, correlate, analyze, compare, extrapolate and validate engagement data 110 with training data 112. Some aspects collect engagement data 110 from inputs and assign them to the appropriate class of user or system activity. This data is then matched with engagement 110 for one of several pre-defined classes of system and user activities. Recommendation engine 100 can use learning module computer software 128 to match features and attributes of unidentified user engagement data 110 and stored training data 112. When applicable to user interactions, learning module computer application 128 may adapt existing training information 112 to create inference intelligence 132. This is stored as user profile data (114), creating an unique engagement data 110 model to a specific interaction dataset 130. FIG. FIG. 1F shows how a model can be used by recommendation engine 100 in order to identify engagement data 110 conditions, user profile data, 114 preferences, and interaction data 130, based upon inference intelligence (i.e. If required, the appropriate parties will be notified promptly and accurately. Recommendation engine 100 can use learning module computer software 128 to test an engagement modeling by comparing similar user data. This data may be reliable in predicting future interactions of a similar nature.

“In another example computer application 128 can be configured as a context agent. This software is programmed in order to identify, associate and analyze, compare and extrapolate inference intelligence 132 generated from interaction data 130 and engagement data 110. One aspect of contextual agent computer application 128 is that it can be programmed to assign biases and weights. As shown in FIG. 1D is associated with interaction data 130 and engagement data 110. These data are used to calculate various computer applications 128 and perform reliable and accurate inference intelligence (132) for recommendation engine 100. Some aspects of contextual agent computer application 128 can identify variables, conditions, or circumstances that are evidenced by analysis of engagement information 110, user profile data, 114, and interaction data 130. These factors and conditions can be introduced into recommendation engine 100 to improve the interpretability of interaction data 130 and engagement data 110. To optimize the performance of algorithmic and computational and predictive analytics programs, data insights may be stored as empirical user data 112 or training data 112 for future reference. The data provided to recommendation engine 100 may allow contextual agent computer application 128 to add, delete, modify or enhance engagement data 110, interaction data 130 features, attributes, and weights, as well as create new data classes to support inference intelligence 132. A contextual agent computer application 128 may ask for feedback from users who use API 24 on their computing devices 36. Feedback can include, but is not limited, to information about the device, such as location, text messaging and camera data, API 24 activity and the like.

“In certain aspects, the contextual agent computer software 128 may be used in conjunction with the learning module computer application 128. This is to train data analysis models and fine-tune models for optimal performances, reduce analytic error, identify bias, generalization and so on. The contextual agent computer 128 and the learning module computer 128 can be used to solicit feedback from system users 10 to validate and confirm newly presented interaction data 130, engagement data 110 or training data 112 using reference information from outside sources 28. This information may include the subject of the data to be compared and associated users via automated notifications, requests for information, surveys and the like.

Computer application 128 can be used as a recommendation module. It is programmed to analyze and compile interaction data 130 and inference Intelligence 132 and to interpret, evaluate, and predict outcomes to guide recommendation selections for positive, neutral, or unfavorable user interactions. A user can choose one or more actions or decisions to make in an interaction recommendation selection. These decisions are based upon analyzed interaction data 130 or inference intelligence 132. They may be presented as ranked or rated lists that reflect favorable outcomes, user intentions, circumstantial acts based on data instances, time-based decisions and user responses. Recommendation module computer application 128 may create engagement data 110 classes for each user to improve the predictive analysis of interaction outcomes. If a subject is shown a particular media content type that has varying engagement metrics for each media exposure event, recommendation computer application 128 might use training 114 or engagement data 110 to help them understand the differences. This will allow them to rank and rate interaction recommendations such as user preference for media genres or artists, who should present it, when they should do so, what environment conditions are best, what technical means are optimal, how long should the media presentation last, how often the media should be presented, which media options are comparable, etc. The recommendation module can identify interaction data 130, including all user data, environmental conditions and preferences. This is for example, if the subject likes to view images of yellow roses on a tablet at noon, while also eating lunch alone on weekdays (and weekends). By class, such as the one shown in the example (frequency: once per day; subject: yellowroses; method: tablet; activity: lunch; behavior; alone; schedule: only weekdays @ noon), the recommendation module will create recommendations for interactions that can be presented to the subject and/or their associated users to help them make decisions and take action. With a push notification of this interaction description, either via a designated schedule setting or an impromptu instance of recommendation engine 100, subject’s associated users will be able to receive reminders about each interaction element that constitutes an optimal engagement. This empowers them, in turn, to create the conditions necessary for the subject. You can order lunch delivery at the specified time, locate suitable images according to your subject’s preferences, send images to your tablet device and remind other users to respect your privacy during the activity. Interaction recommendations can also be generated for the subject based on either scheduled or impromptu detections of optimal conditions. The recommendation module computer software 128 can send interaction recommendations via API 24 or ubicomp’s user interface 70 to a subject’s computing devices 26 and 26. Associating user devices 26 are located outside ubicomp 12. System 10 can recognize patterns, routines, and behaviors based on training and empirical data. It can also identify user preferences and provide recommendations for interaction. This includes suggestions for favorite TV programs, availability of favorite user associates via ubicomp 12, and transportation or meals from outside services. Recommendation module computer application 128 might use a data identifyr that recognizes patterns and routines associated with interaction datasets 130. This information can be used by recommendation engine 100 to predict user activity, or behavior that follows an interaction with ubicomp 12, API 24, users operating computing devices 26 or ubicomp 12 components.

Referring to FIG. “Referring to FIG. 2, a flow diagram illustrates an example of a process 200 that delivers interaction recommendations to users according some implementations. The process starts at step 202, where engagement is associated with interactions within a ubiquitous computing environment. An engagement could include activity by a subject in a ubicomp, activity between a subjec and ubicomp parts; activity between subject and associated users either inside a remote location or within ubicomp; and activity between subject and associated users located either within or outside the ubicomp.

“Activity in step 202 can be represented in different forms of engagement data 110 in some aspects. This includes but is not limited to: physical movements, gestures and walking, speech, voice commands and haptic control motions, moods and biometrics; remote or automated operations by system 10, network 14 and/or remotely connected devices 26; user engagement via API 22 or ubicomp 12 components or network 14. Process 200 detects activity at step 204 using a trigger that is a computational model for measuring, analysing, and interpreting engagement information 110 information about an event, sequence or benchmark, user action and/or operations associated with a device program network system. The associated data are labeled interaction data 130. Process 200 then associates the activity detected with a subject or subjects. In step 208, process 220 identifies a potential audience of associated users 208. Automated operations can be used to identify a prospective audience member using predetermined thresholds or user profile information. 114, current and previous status, communication via API 24 or networked devices 26. The audience member 208 can be excluded or included in 200 process based on certain filters, such as activity category and authority level, permissions or subject matter relevance, interaction availability, correlations or comparisons between the subject’s user profile data and those associated users or other parameters.

“At step 220, process 200 collects the inference intelligence 132 from recommendation engines 100 and 128. Inference intelligence 132 could be indicative of past activities or current activities that are associated with the subject, audience, and unique engagement data 110 conditions recognized as trigger 204. A benchmark or threshold-level reference file may be created in some aspects. It is labeled and stored with user data 114. This data can then be used by system 10 (or recommendation engine 100) in the future. Process 200 creates a computational model from activity data 202 and trigger data 204. It also uses audience data, 208, inference intelligence 220, and user profile information 206. Process 200 uses the model to determine possible interactions between the subject and the audience members in step 214. Step 216 is where process 200 uses the model to calculate and assign a data value for user intentions and possible interactions. This is done by integrating activity data, user profile information (subject/audience) 206, and inference intelligence (132 with computational model 212). Process 200 uses the model to calculate outcome scores and values. These are based on the probabilities of possible outcomes and participants’ intentions. The possible outcomes are then ranked using computational model 212 to identify plausible interaction recommendations. Process 200 uses the model in step 220 to apply subject and audience member interaction rules. These rules can be used to include or exclude interaction recommendation distribution. They are based either on pre-set parameters from identification step 208, or new conditions that are based upon calculations of inclusion and exclusion based upon activity category, authority, permissions and subject matter relevancy. Process 200 creates a record using the model of engagement conditions. This includes the calendar time stamp, type, unique identification labels, related scores, values of possible interactions recommendations, instructions for participants, reminder schedule, user distribution list, and interaction instructions. The model is used to compile the engagement information and interaction recommendation data records. These are then distributed to the respective users using communication language, such as symbols, alphanumeric characters, audible signals or other executable commands. Process 200 creates interaction recommendations and engagement information for distribution to system peripherals 10. API 24, computing devices 26. external networks 28. Other ubicomp12 components. This is based on the user’s profile information. In step 226, process 200 also delivers interaction information and recommendations to system peripherals 10. These are based on the user’s profile information 206. One or more of the interaction recommendations may be rejected by a recipient. This creates new rule and filter information, and new inference intelligence (132), which then returns process 200 to step 210. Process 200 can provide additional information regarding the current engagement, or interaction recommendations, upon a user executable command control or user executable function. This includes historical data about the subject and engagement matter, graphs, charts, and interaction data analytics for the subject. Also, ratings and ranked recommendations are based on aggregated data that is local, national and anonymized. Process 200 will create a computational model that tracks, analyzes and compares expected engagement conditions with predicted interaction outcomes using known data (202,204,206,208, 208, 208). This model will be generated by process 200 upon an executable function or automated control. The probabilities calculations are based on changes to the benchmark or threshold values of the known data. Process 200 will then recalculate interaction recommendations beginning with step 202. Process 200 creates a new context data record 210 for use by process 200. This record is associated with user profile information (206) and unique engagement conditions (204).

“In step 223, process 200 will collect feedback data from participants based on the time allocated for the desired interaction. This will confirm the outcome and confirm the interaction. You can request feedback in a variety of formats by using automated programs and notifications to users devices. This allows you to communicate directly with the subject or associated users about the engagement subject matter. A user executable function, or automated command control may initiate data verification. This allows a user to be presented with various ways of communicating interaction outcomes responses, such as voice-enabled queries presented on a communication device, electronic questions delivered directly to a communications system, audible sounds and haptic gestures, facial expressions and eye movements.

Referring to FIG. “Referring to FIG. 3A, a flow chart is shown that illustrates a system or method 300 for determining interaction opportunities for a subject in a ubiquitous computing environment. This implementation of the disclosure is described. Processing logic may comprise hardware, software or a combination thereof. System or method 300 can be executed by recommendation engine 100 and ubicomp 12. Some aspects allow a subject or associated user to interact remotely with ubicomp 12 via API 24. Block 302 determines whether engagement activity was detected in ubicomp 12 by a user, networked devices 26, system operation, or from a remote source such as a networked 26 device, program stored on server 16 or an external system 28. An engagement data 110 event can be identified, labeled, and cataloged if a pre-defined threshold or benchmark is reached. This information may be based on user profile information, training data, or other data to create an interaction dataset 130. An engagement data 110 event, or a sequence of engagement data 110 events, may be considered a single interaction. An interaction can be identified using a label, unique ID, category, name or other input, depending on whether it is automated or manually.

“At block304, processing logic uses ubicomp engagement information 110 to train an neural network computational model to determine potential interaction opportunities involving subject, associated users, and system program applications, devices, or a combination thereof. In some cases, algorithms are used to determine possible interactions using available and/or referenced engagement data 110. Some aspects may contain available and referenced data such as the following: access permissions, privacy settings, user preferences and status, context data, and other information. Inference intelligence 132 may be used to determine the applicability, bias or weighted values that are used by algorithm applications. Block 306 is where processing logic calculates scores to indicate positive and negative interaction outcomes. In certain aspects, indicators can be calculated using user profile data and historical interaction 130 reference data. Block 308 is where processing logic generates a list with recommendations for interactions. The list can be ranked in some cases. This is where recommendations are associated to a score or value that is based on user preferences, user situation, or any other interaction-related dataset. These lists can then be ranked or rated according to favorability/unfavourability or neutrality. Some aspects of the recommendations may be associated with interaction conditions that define or qualify terms or requirements for a potential interaction. These are based on data available and identify a single or range that is considered acceptable or optimal. As an example, associated users might recommend visiting a subject. This could include conditions such as day, time and permitted or prohibited individuals. Block 310 receives interaction confirmations from all relevant parties, including subject matter, method and schedule, location, terms and requirements, as well as prospective participants. The interaction confirmation information may be presented in certain aspects based on pre-set conditions or user profile data. Block 312 is where the interaction outcome data are added to the neural network computational model. Block 314, the neural net computational model is updated by changes to user profile data, system data, preference data and interaction data for respective users. The system/method 300 process can be extended to block 302, 303 or 306, 308, 308, 310 or 312, depending on its aspects.

Referring to FIG. “Referring to FIG. 3B, a flow chart is shown that illustrates a system or method for determining interaction intelligence 132 for a subject related with a ubiquitous computing ecosystem, according an implementation of this disclosure. Processing logic may comprise hardware, software or a combination thereof. System or method 320 can be executed by recommendation engine 100 and ubicomp 12. Block 322, processing logic determines engagement data 110 events, and interactions 130 that are associated with a subject. A subject and/or an associated user can interact with each other from within ubicomp 12, while in others, a subject might be physically located while interfacing with ubicomp12 and its associated users. Block 324 is where processing logic applies engagement data 110 and interactions 130 to train an neural network model to recognize inference intelligence 132 information. Inference intelligence 132 can include data from subjects, users associated with them, system programs, devices or a combination thereof. Inference intelligence can be calculated from individual datasets, or a combination thereof, including, but not limited, environmental data and user profile data, user preferences data, historical data, generic training data, and user preference data. The relevancy of identified engagement data 110 in some aspects is a calculated value that can be used as weights or biases based on individual data or multiple datasets such as historical data of user profiles and past interactions, training data and probabilities values related to user preference and intentions, desired outcomes, etc. Processing logic calculates a score that compares inference intelligence to interaction outcome values 326. Block 328: Processing logic uses correlated inference Intelligence 132 and interaction outcome scores in order to train a neural net model to identify engagement data 110 precursors. This adds contextual data to inferenceintelligence 132. The precursor (or precursors) may be a value or a set of data points, or a set of parameters that establish a baseline or threshold, or other similar data. The precursor value calculation may be based on a probability or algorithm, an analytical program, or the like. The precursors can be represented in some ways by a label or category, type, number percentage, unique identifying codes, and the like. Block 330 is where processing logic applies engagement data 110 precursors in order to train a neural model that can create notifications, indicators, and triggers based upon interaction outcomes desired by the user. Notifications, indicators, and triggers may be presented in a variety of formats, including graph, line charts and percentage charts. Some aspects allow notifications, indicators, and triggers to be linked with interaction recommendations that are presented to users based upon non-computational data such as type, category, schedule, attendees and content. Block 332 updates the neural network model with engagement data 110, precursor data, and other data. Block 334 is where the neural network model gets updated with changes to user profile data, system data, preference data and interaction data for respective users. The system or method 320 process can be continued to block 322, 324 or 326.

Referring to FIG. Referring to FIG. 3C, a flow chart is shown that illustrates system or method 340 for creating interaction recommendations using preference-related data associated with a ubiquitous computing ecosystem, according an implementation of the disclosure. Processing logic may comprise hardware, software or a combination thereof. System or method 340 can be executed by recommendation engine 100, which is coupled to API 24/ubicomp 12. Block 342 is where the processing logic creates a neural network model by using computer application 78 to corroborate ubicomp 12, system data 10, interaction data 110, 130, inference Intelligence 132, and user preferences data 114. The processing logic uses the neural network model to train the model to determine the user’s intent using the above correlated data. This includes real-time event information, environmental data, archived interactions data, and generic training data. The neural network model is used to train the model to determine the desired outcome of a user using correlated data. This includes preference data, environmental data, preference information, archived interactions data and generic training data. The neural network model is used to determine the likelihood of interaction outcomes being available. This is done based on the user’s intention and preference data. Prerequisites and conditions are also considered. The processing logic calculates a comparability score at block 350 based on the value of non-physical and physical elements as well as user intention preference data. This is used to determine the likelihood that the desired interaction outcome will occur. Block 352 generates interaction recommendations. It also includes prerequisites and precursors that can be associated with the desired outcome. Block 354, the processing logic generates interaction recommendations based upon the interaction selected. Based on the response data, the processing logic calculates a correlation value, either higher or lower, between the subject’s desired outcome and the actual outcome of the interaction. The processing logic may solicit user feedback data from multiple sources, including device data, biometric and electronic data, subject centric data, user centric information of the subject, text based communications, system 10 data, inference intelligence132, system 10 data and subject centric data. Block 356 updates the neural network model with interaction recommendation information. Block 358: The neural network model is updated by changes to user profile data, system data, preference data and interaction data for respective users. The system or method 340 may continue to block 342, 344 or 346 or 348 or 350 or 352, 352, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354, 354 or 358 in certain aspects.

Referring to FIG. Referring to FIG. 3D, a flow chart is shown that illustrates a system or method 360, which manages interaction recommendations using interaction data associated in a ubiquitous computing environment. This implementation of the disclosure is described. Processing logic may comprise hardware, software, or any combination thereof. System or method 360 can be executed by recommendation engine 100, coupled to ubicomp 12, API 24, and user profile data (114) stored on database 110. Block 362, the ubicomp engagement data event triggers generation(s) of interaction recommendation(s). Block 364, API 24’s processing logic identifies, correlates, and filters interaction recommendations according to users who are associated with a specified interaction dataset 130. The data file containing the user profile data 114 may contain the available recommendations. Block 366 is where the processing logic determines the nature and hierarchy of the interaction recommendation lists using a neural network model. This model uses at least part of the user data, inference information and audience member status. It also considers privacy settings, notification protocol, user status, and authorization level. Block 368 is where the processing logic coupled with API 24 selects at most one recommendation from user profile data.114. The recommendations are then served to user interface 70 within Ubico 12 or to a computing device 26 via a distribution method, confirmation means. A confirmation method and distribution method can be an audible tone, voice, sound, visual or graphic, alphanumeric values, video clip, and other elements. Some aspects may require a time-sensitive response, such as a number of users who choose the same recommendation, or based on which audience members have responded, in order to render recommendations. Block 370 allows the processing logic to modify, edit, or revise a recommendation list if the options presented are not accepted by one or more participants in the distributed interaction recommendations. Additional recommendations can be re-distributed and added to associated user profile data (114). The processing logic may edit, revise, or delete the recommendation list in some instances. This is done using a neural network model that uses at least part of the user data, inference information and audience status. Notification protocol, user status and other relevant data are also considered. Processing logic can request or receive interaction alternatives from users’ interfaces via API 24, and then add them to the associated user profile data data 114. These interaction recommendations are based on engagement data events or future reference of interaction data and user preference. A user can initiate the distribution to a particular audience of a personalized interaction recommendation list if they are associated with an engagement event. Block 372 updates the neural network model with interaction recommendation distribution service, responses data, and user data 114. Block 374 is where the neural network model gets updated with system data, preference data and interaction data. The system or method 360 process can be continued to block 362, 364, 366, 368 and 372 for certain aspects.

Referring to FIG. Referring to FIG. 3E, a flow chart is shown that illustrates a system or method for optimizing interaction recommendations using interaction information associated with a ubiquitous computing ecosystem, according an implementation of the disclosure. Processing logic may comprise hardware, software or a combination thereof. System or method 380 can be executed by recommendation engine 100, which is coupled to API 24 and user profile information 114 stored in database 108. Block 382 is where processing logic creates a neural network model with computer application 78 to match engagement data 110 with interaction data 130 in order to identify user intent information and desired outcomes information. The neural network model is used to calculate and assign bias values and weights to engagement data that are associated with user intent information 344 and desired outcomes information 346. Some aspects may use historical data from a user profile or generic training data to generate weights and biases. The neural network model is used to determine correlations between user intent and interaction outcome information. This logic can then be applied to block 386. The processing logic at block 388 determines whether there is a minimum threshold for the calculated weight or bias score combination. This improves the accuracy and precision of interaction recommendations. If the minimum threshold is not met, the processing logic will not recommend interaction. Instead, it will save data to be used in the future. The neural network model is used to generate block 392 which determines the interaction recommendation hierarchy. It uses higher correlation scores between the user intent information and the desired outcome information. The neural network model generates triggers at block 394. This processing logic uses assigned weights and bias values to identify similar engagement data 110. These weights and biases indicate conditions, prerequisites, or precursors for interaction outcomes. Block 396 is where the processing logic displays and presents recommendations to users. It also includes conditions, prerequisites and precursors to interaction outcomes. Block 398 is where the neural network model, including user profile, preference, data and interaction data are updated. The system or method 380 process can be continued to block 382, 384 or 386 or 388 or 390 or 392, 394 or 396 in certain aspects.

“Objectively recommendation engine 100 performs at a more efficient and precise basis as engagement events 110 provide greater intelligence of interactivity data 130 and inference Intelligence 132 insights including user preference, lifestyle habits and behaviors. These insights include user preferences, lifestyle choices, habits, tastes and behaviors, conditions, variables, contingencies, and schedules so that interaction recommendations can be presented in a timely and more relevant way that encourages and promotes user interaction and fosters meaningful engagement between users of the system.”

Referring to FIG. “Referring to FIG. 4A, an illustration of a blockchain-based engagement platform is shown. Method or system 400 can be described as a blockchain system technique, or method 22 in some aspects. This disclosure discloses blockchain methods for protecting and transacting interaction data and engagement data that is generated and resulting from users, apps, and hardware connected to or operating in a ubiquitous computing environment. These aspects describe the foundational information that can be accessed (engagement) or interpreted (interactions), on a peer to peer platform using computerized programs and apps for purposes such as identification and classification analytics, predictions and recommendations. They can also be used in various processes, networks, devices, and methods. These transactions, also known as Engagement Interaction Data (or EID), can be managed by blockchain components, including blocks, nodes and miners, consensus protocols and tokens, encrypted key, smart contracts, and other tools. An EID transaction record, or ledger, is maintained by all nodes in method 400. Each newly created block is time stamped and independently verified by consensus protocols. EID transactions can include information headers that describe various block data structures, including side branches, main branch, and orphan. These blocks are then mined and replicated to every node in the network. EID can be detected by system 400 and a block is assigned a token value. Based on EID ownership and permissions granted by authorized associated users (receivers), the value is digitally signed by adding the previous transaction to the hash and the public key for the receiver in a Blockchain 404. A token can be described as an unit of digital value that EID has assigned to it. It may also exist in the blockchain register on system 400. A smart contract is a software code or protocol used to verify, contribute or execute the negotiation or performance a contract using method or system 400. Smart contracts are used in the current example to manage the transfer of EID among users, devices, and applications of the innovation, including related applications, parameters, protocols and protocols for identity management and authentication, digital privacy and authorization access.

It is notable that, based upon the disclosures made in this document about EID sources, it is clear that the importance of following principles and standard to collect, interpret, and share such data is highlighted. The present disclosure aspects describe how to interpret and discover personal communication methods, style, emotions, sentiments, bioinformatics, and other quantified-self types such as lifestyle habits, preferences, and lifestyle habits, using current technologies. The methods and systems described herein use centralized and decentralized models to create and manage immutable blocks data and metadata. This supports data integrity, digital rights management, data security, device registration, authentication and validation, and data integrity. Method or system 400 generally generates, manages and operates various components for blockchain technologies customized to EID transactions, including decision managers and distributed ledgers.

“Method or System 400 is associated with or a component a peer-to?peer engagement platform 402 which includes a Blockchain 404, a Blockchain Sub-science System 406, an API 408 and a Network 410. A first user or?subject? 412, a second or associate user? Subject 414: A first node 416 and a second 426. Engagement platform 402 can be described as system 10 in some aspects. Engagement platform 402 communicates and operates with some of the system 10 components. These include ubicomp 12, network 14, API 24, computing device 26, external 28 and recommendation engine 100. One or more of the nodes 416, 426, may represent the user, device, and activity in innovation. Node 416 and 426 could be computing devices 26 controlled by a User Operating API 24. This API provides a user interface that allows the user to manage their engagement activity, user identity as well as subscriber activity, profile information, and other related platform data. Node 416, 426, may be a user interface 70 that is controlled by a user-operating API 24 to manage engagement activity and subscriber activity. Profile information and other related platform data can also be managed from node 416, 426, in some cases. Automated programming may be used to represent a node 416 or 426 on a hardware component, appliance, or networked via API 24. Node 416 and 426 can be represented by automated programming on the system 10 operating system software components of ubicomp 12, network 14 or 16, API 24 or external system 28, or recommendation engine 100. System or method 400, in some aspects, is a virtual machine that runs decentralized applications (or Dapps), on a computer network to manage nodes that keep EID transaction records and smart contract histories. System or method 400 can be described as a public blockchain or permissionless network. System or method 400, in some aspects, is a private or consortium-based blockchain that grants access to only those who have permission.

“Method or System 400 includes one or more Blockchains 404. Blockchain 404 may be referred to as engagement data 110 in some instances. Blockchain 404 can be linked to a subscience system 406 which includes memory or storage for the blockchain-related system, platform data, programs and instructions. One or more sub-science system 406 may be included in method or system 400. To perform the following operations, functions and execute programs, applications, instructions and other blockchain-related tasks, the Blockchain Sub-science System 406 can be linked to engagement platform 402 or method 400. As described in the previous description of the innovation, interaction and engagement activity between users on engagement platform 402. may generate a blocked chained EID. This can be used to integrate EID transactions for individual user accounts and shared user accounts using both blockchain database 404 or blockchain sub-science systems 406. The method or system 400 can be coupled with the application programming interface (API 408). API 408 may be referred to as API 24 in some instances. API 408 can implement interface operations for method 400, related components, and devices, including inputs, outputs, video and graphics for the user. To facilitate communication between components, method or system 400 can use network 410. Network 410 may be called network 14 in some instances. Method 400 can include at least one user 412 and one user 414. A first user 412 and a second user 414 may, in some instances, be referred or defined as account holders, third party participants, subscribers, contributors, or subscribers on method or system 400. A first user 412 and second user 414 may be a living organism, such as a human or a pet. A second user 414 can be identified as an associate of the first user 412. In some cases, the first user 412 can be identified as the associate user of second user 414. One or more first nodes 416 or second nodes 426, may be included in method or system 400. Node 416 can contain one or more components, including processor 420 and API 422, memory 418, and EID key 424. Memory 418 can store software, data and instructions, or any other executable commands, for processors 420, API 422, and method 400. One or more memory 418 may be found in some aspects. The electronic circuits and logic that make up processor 420 can be used to process data, run programs, or issue commands for hardware or software components of method 400. One or more processors 420 may be found in some aspects. The processor 420 architecture could include a microprocessor or microcontroller, an arithmetic unit, video and graphics processors and other components. API 422 can implement communication interfaces to user input, video, graphics components, devices, apps, and software in digital or analog configurations. API 422 may be referred to as API 24 in certain aspects. EID key 424 could include any 412 interaction or engagement information used in cryptographic transactions using public and private keys to identify, authenticate and encrypt. EID key 424 could be a combination of alphanumeric characters digitally stored in a memory 418. EID key 424 can be assigned to multiple accounts (412 accounts), one account with multiple users, or a single account.

“Node 426 could contain one or more memory 428 and processor 430, API 432, and EID key 444. Memory 428 can store software, data or other executable commands, either permanently or temporarily, for processors 430 and 400 on the hardware and software components. One or more memory 428 may be present in some cases. The electronic circuits and logic that make up processor 430 can be used to process data, run programs, or issue commands for hardware or software components of method 400. One or more processors 430 may be found in some cases. A processor 430 architecture could include a microprocessor or microcontroller, an arithmetic unit, video and graphics processors and the like. API 432 can implement communication interfaces to user input, video, graphics and component operations. It also allows for the execution of applications and software in digital or analog configurations. API 432 may be referred to as API 24 in certain aspects. EID key 434 could include any user interaction or engagement information 414 used in cryptographic transactions using public and private keys to identify, authenticate and encrypt. EID key 434 could be a combination of alphanumeric characters digitally stored in memory 428. EID key 434 can be assigned to one user account 414, multiple user accounts or multiple accounts with multiple users. Nodes 416 or 426 could be devices that can communicate with components of system 400. Nodes 416 or 426 may be at least one of the computing devices 26. The first and second nodes 416 and 426 are electronic, machine-based, networked devices, with or without user interfaces. These include a vacuum cleaner, flying robot, automated vehicle, home appliance, voice interface device, camera and HVAC system.

Referring to FIG. 4B is a block diagram of a subscience computing system 440 that implements a blockchain-based transaction on an engagement platform 400. Sub-science system 440 can be referred to as sub-science systems 406. Sub-science computing systems 440 include a processor 442, an API 444, and an EID 446. The electronic circuits and logic that make up processor 442 could be used to process data, run programs, or issue commands for hardware or software components of computing system 442.

“Sub-science computing system 442 includes one or more processors in some aspects. Some processors 442 can be configured to access blockchained EID storage 456 to operate blockchain data applications 458 operations with blockchain instructions 460 on remote and local blockchain databases 454 which are connected via an API 444 interface. API 444 can implement communication interfaces to video, graphics components, devices and applications in digital or analog configurations. API 444 can implement communication between different components of computing system or method 400 in certain aspects. API 444 may be called API 408. EID system 446 could include at least one operating systems 448, EID program 405 and decision module 452. It also may contain a blockchain database 454. EID system 446 may be one or more systems within a blockchain computer network that manage EID records, EID transactions and other aspects. Operating system 448 could contain or access one of several software, applications, executable programs, or 450 for block functions, transactions, controls, and/or commands for various parts of computing system 440. EID program(s), 450 could be one or more programs within a blockchain computer network that manage EID records, EID transactions, and other information. EID program (450) may be coupled with programs on engagement platform 402. These programs extract, generate, and analyze EID records. EID module 452 can run software, apps, or executable programs that analyze, process, store, and transfer EID records to a blockchain database 454. In certain aspects, decision module 452 may be one or more modules of a blockchain computer network that manage EID records or EID transactions. Decision module 452 can be described as a neural network program that is generated from computer software 78. Decision module 452 can be considered a component of recommendation engine 101 in some instances.

The EID system contains a 456-blockchain database, which also includes data storage 456, and blockchain applications 458, as well as instructions 460. Data storage 456 could also include storage of blockchained data 404. Data storage 456 could include EID records and EID transaction records in some cases. Data storage 456 could include EID key 424 and 434 information. Blockchain applications 458 could include cryptography, encryption, data formatting, data formatting, computation applications, tokenization, logic applications and smart contract applications. Instructions for blockchain applications 460 could include operating system 448, programs 452, and decision module 452 operation. Users can control the EID generated by ubicomp 12 and its interpretation through blockchain 404. This includes other users, system components, and third-party services that are connected via API 444 and system 400. Decision module 452 could be used with processor 442, operating systems 448 and programs 450 depending on filters, access permissions, commands for distribution, etc. These preferences are controlled by blockchain applications 458, instructions 460, which determine what EID is extracted and formatted for processing by system 400. This information can then be used in blockchained transactions or records. EID blocks 404 that represent a user, as well as associated activity, master level control, and ownership, can be stored locally or remotely on an account associated to a user. Some aspects store stored EID blocks404 on data storage 456. Some aspects store stored EID blocks404 on node 418. 428 are associated with users or linked to user devices. A network of sub-science computing system 440 can operate on a blockchain network in order to aggregate and anonymize EID data for system 400. Modified versions of generic EID data may be used to aggregate user behaviors, interactions, and engagement preferences in order to support various statistical, algorithmic and/or predictive programs and applications.

“Various implementations relate to engagement platform activity and, more specifically, interaction recommendations generated from a recommendation engine. Some implementations concern interactions between individuals and ubiquitous computing environments or ubicomps and the networked technologies that are associated with them. Some implementations deal with user interactions where a subject in a ubicomp interacts to one or more associated users who are remote networked to him/her and the relevant ubicomp activity data. Some implementations also relate to interactions between users who are not associated with the ubicomp. This is where subject activity can influence interaction and recommendation. Some implementations also relate to engagement platforms that use artificial intelligence to learn behaviors, lifestyle habits and engagement preferences. Authorized users can receive insights based upon interactions of both the subject and the associated users. This allows them to optimize all aspects of user engagements relating to a variety of subjects and activities such as sleep, eating, media consumption and phone calls. The platform can easily map user preferences and provide insight into their optimal conditions and schedules. This will allow individuals and groups to plan and execute personalized interactions with other users. If the platform has collected intelligence about a subject’s life that shows they like images and photos of a particular nature, it can alert associated users and direct them to the appropriate content online. It also prompts them to add the material into a queue to be presented at the requested time on the device. As the engagement platform provides more information about the user’s lifestyle and engagement preferences, it can also identify media and interaction recommendation elements tailored to the schedule and conditions of the subject.

A recommendation engine using artificial intelligence and machine-learning programming would improve the ability to identify nuanced elements of desired activities (subject behavior, location, time, mood, etc.). Engagement precursors (inference information), and triggers (physical event or user engagement setting) are all indicators of the desired interactions that each user will have. Artificial intelligence programming can interpret these preferences, trigger, and precursor elements. It compares the training or reference data with the subject, verifies the users and compares it with historical data to tailor recommendations for user interactions. The system can anticipate user preferences and lifestyles and use this information to improve the overall experience for users of the engagement platform. It also uses passive sensor applications to predict possible intentions and outcomes based on interaction data analytics. These experiences should include a style and method of providing recommendations (device configuration, displayed information; timing, language, audio, images, symbols; etc.). And logic programming that is tailored to the user’s interaction perspective in relation to outcomes and intentions. An engagement platform that gives access to reliable lifestyle preferences information can greatly influence professional relationships. This allows authorized users to schedule transportation, delivery of streaming content, primary caregiving visits, emergency responses systems, elder care, petcare, home security, scheduling transport, messaging, video calls, and broadcast television viewing. An engagement platform can help users determine when and how to engage. It also offers tremendous benefits in terms of social, emotional, and economic collateral.

Referring to FIG. “Referring to FIG. 5A, a diagram showing exemplary components of an engagement system system 500 for interaction suggestions in which broad implementations may be used. System 500 can be described as system 10. System 500 is a ubiquitous computing environment, or?ubicomp? 502, a network 504, 506, 506 and 508 respectively. 508 is a recommendation engine 508, 508, 506 and 508 respectively. 502 also includes a database 506 and 506 as well as a 506 and 506 databases. 502 has a number program interfaces 512. In some aspects, the ubicomp 502 can be called ubicomp 12. In certain aspects, ubicomp 502 may be referred to collectively as?ubicomp data. 514 to be used by system 500 from activities initiated within and outside 518 Ubicomp 502. This automated programming operates both on fixed 520 and portable 522 networked computers and uses software technologies within ubicomp 522. Database 506 may include one or more storage systems. Database 506 can store system data, user data and program application data. It also stores recommendation engine data 508, Blockchain information 510 and other similar data in accordance to previously disclosed implementations. Recommendation engine 508 can be described as recommendation engine 18. A blockchain 510 can be considered a blockchain 22 in some cases. API 512 allows communication between users and system components. This can be done within a single system 500, or across a network 500. Interface applications enable communication including text, audio, and video data sharing, as well as user profile data, program execution, commands, platform data analytics, and user activity data. API 512 can be referred to as API 22 in certain aspects. API 512 can be used to operate on one device or on multiple devices at once, without restrictions on its scope, function, controls, and/or access authorisation. API 512 functionality, operation, and scope may vary depending on user role, device type, purpose, system configuration, and physical or non-physical nature. API 512 also facilitates connection recommendations and user activity for various components and any number users. This includes comparable systems, user activities and administrative users as well as devices, third-party service, ecommerce services and other vehicles, appliances and robots. API 512, in some instances, can allow users 516 and 518 to control, manage, and control information, components and network access on system 500. Administrator 542 might create unique user groups 544 that include user profiles accounts 516,518 and third-party services and networks. These user groups may contain specific information, data and data created and/or managed in different ways by 516,518 who are part of group 544. Some aspects of system 500 software and hardware components can create biases in data values and skewed data classes. These data attributes may also be used to generate data value variations for ubicomp 514 and other programs that are part of system 500. Data biases can influence or alter ubicomp 514 collection, interpretation and classification, categories calculations, comparisons, predictions, and the like. There may be one or more subject users 516 within group 544. Subject user 516 doesn’t have to interact or engage with system 500 only from within ubicomp 502 as devices and monitoring apps provide enough interaction and data 514.”

“API512 can be configured as a user-oriented API to recommend interactions to animal or human users 516, 518. API 512, in some cases, can communicate recommendations between human and animal 516 and 518 users with an automatic system interface 520 or device interface 522 responsive physical controls, voice enabled commands and facial recognition, emotion detection, audible and biometric data status. API 512 may be used to configure administrative controls and authorizations. For example, an automated program or user can establish rules, filters, or parameters for accessing, sharing, or collecting ubicomp data 514. API 512 can be used to request user 516, 518 feedback information. This is done using computer application number 78. Device 522 controls are used to identify user preferences prior, during, or after events in which ubicomp data 514 has been collected and recorded. API 512 can also initiate feedback information inquiries. It may solicit user responses using a variety of user engagement methods, including a text message or electronic survey.

API 512 can be configured in certain aspects so that a user 518 from outside ubicomp 502 can manage networked connections to API 512 inside ubicomp. This includes system 500 operations, networked devices 520 and devices 522 as well access to ubicomp data 514. User 516 within Ubicop 512 represents a human or an animal. An outside user 518 controls automated system 520 and device 522. This includes lighting, surveillance cameras and 2-way audio, automated feeders, HVAC, door locks, etc. Another example is user 516 in ubicomp512 who is disabled or incapacitated. Outside user 518 controls automated system 520 and device 522. These controls include lighting, surveillance cameras and HVAC zones. Video calls, biometric measuring devices, motion sensors, home appliances, and selection, delivery, and presentation of audio and text via cloud server, streaming service, cloud service, cellular network or commercial subscription service. Files stored on local databases are also controlled by outside user 518. Another example is that an outside user 518 could modify API 512 filters and settings to acquire and analyze ubicomp data 514 generated from user 516 within Ubicomp 512. This is based on the recommendation engine 508 information regarding observed, past and anticipated lifestyle preferences and habits.

“API512 can be set up for developer controls via integration platform 526. At least one third-party program could be created to run on system 500. Any number of software programs or program code may be included in a third-party program. These applications can enhance or complement engagement system functions, platform operations and user experiences. Database 506 can store components of integration platform 526 in some aspects. These include a minimum one software development kit, a program window, debugger and visual editor, compiler and runtimes. Integration platform 526 allows third-party applications to add user controls and components, as well as user experience features, on top of API512. Based on the recommendation engine 508 data, integration platform 526 allows third-party programs access to API 512 and add components, user experience features, and user controls. Integration platform 526 allows API 512 to communicate with third-party programs, web services, streaming data services, and other APIs. API 512 allows interaction recommendations to be generated from any combination of ubicomp data 514 sequences or combinations that define an interaction. These interactions can be unique to one user 516-518, multiple users 516-518, multiple user groups 544, system 500, or related components. This includes individual components of the system as well as a networked grouping of system components. Information and media content can also be delivered to the user 516-518, 518 or 518. Interaction recommendations can be delivered in many formats, including emails, text messages and multimedia presentations, images and graphs, surveys, polls and customer reviews. API 512 allows users 516, 518 access to information, components, network connections, and devices on system 500. Administrator 542 can create unique user groups or forums 544 that are composed of user profile accounts 516 and 518. These user profiles may include, for instance, related devices, components, programs and networks. System 500 users have access to data and information generated by 516 and 518 who are part of group 544. Administrator 542 can create a user account for another user 516 who is the primary user or subject. Administrator 542 may create a user account for another user 516 that is a primary user or?subject? A primary user or subject user’s 516 status design defines customization, orientation and modification of system 500 apps, processes, operations and analytics. One example is that subject user’s 516 status can generate biases and skewed classes of data and data attribute values ubicomp 514 used in computer application 78 and other computerized applications used by system 500 that affect or change engagement and interaction 514 collection, interpretation and classification, categories and calculations, comparisons and predictions, and the like. The user profile status for an infant can be distinguished from that of an elderly user, disabled user, handicapped user, impaired user, or any other user who has unique preferences and characteristics based on their lifestyle or living conditions. There may be one or more subject users 516 within a group 544. A subject user 516 doesn’t have to interact or engage with system 500 only from within ubicomp 502, where devices or monitoring applications provide enough ubicomp data 514. Computer application 78 can process ubicomp 514 from multiple users 516 and 518 simultaneously, using biases or attributes that are assigned to each user account. Computer application 78 might offer ubicomp 514 preference information for recommendation engine 508, where users may indicate their desire or intention for different outcomes. This is based on an outcome probabil score. At that point recommendation engine 508 will determine if there are any actions, non-actions, alternative options, or other ways to solicit feedback from the group of 544 participants. Computer application 78 can solicit bias and attribute information about group participants using activity data tracked by system 500 components. This data is derived from 516, 518 user profiles accounts. It also provides behavioral data derived ubicomp data 514. Direct inquiry via device API 502 allows for a variety forms of information such as multiple choice questionnaires, graphic images, percentage values, audible and visual sounds, graphs, charts, graphs, charts, graphs, and the like. Computer application 78 and recommendation engines 508 can submit and resubmit interaction suggestions to group 544 participants, until there is consensus on the outcome. Some examples of consensus or agreement regarding interaction outcomes may be absolute for all participants in group 544. It could also include a consensus percentage for all participants in group 544 for a specific interaction outcome (including decline or action), an affinity value for subject 516 of a group 544 and subject’s 516 associate users 518. This can be used to determine whether a subset of participants in group 544 or all participants in group 544. Computer application 78, recommendation engine 508, and other components may process bias and attribute data in certain aspects. This may lead to the possibility that the desires or intentions of a subject 516, 518 or 518 may be greater than those of another participant 516, 518 or 518 in a proposed interaction.

Administrator 542 is responsible for assigning administrative access and permissions to user 516 and 518 accounts that are part of group 544. Administrator 542 can manage group 544 access to subject 516. This includes but is not limited to user access permissions and user interaction rules. Content filters, user ubicomp 514, interaction analytical data, user engagement data, and other such functions. Administrator 542 can create a group 544 for a subject user 516 by inviting other users 518, assigning access permissions and authorization levels, engagement filters and interaction rules. This is based on user accounts 516 and 518, respectively, of group 544. User group preference data can be referred to as ubicomp data 514 in some instances. User group preference data can be established in some cases by users 516-518, 542 depending on their unique role, contribution or position within group 544, or any interaction conditions therein. In certain aspects, ubicomp 514 may be detected, acquired and processed by system 500. It can also be processed, correlated and analyzed by automated programming operations using API 512 program settings.

“Media Engagement”

“In certain aspects, media program 528 is integrated with API512 and coupled with recommendation engine 508 or blockchain 510. This allows users to select, access and present media content to 516 and 518. Media program 528, in some aspects, is a third-party subscription service that allows users to view, download, and stream media content. As previously mentioned, an administrator 542 can create a user group 544 for a subject 516 in order to use media program 528. This allows them to generate, select, share, and present media content. It also includes associated 500 data, including ubicomp 514 feedback information, which is based on user experiences with each media program 528. The ubicomp 514 feedback data may include preference data and analytic data as well as notification data, predictive, predictive, recommendation, and other data. API 512 controls can be used to send ubicomp data 514 notifications to one or more users 518 of user 516 preference data. This data includes data such as language preference, music genre preference, location, type, type, and type of content, and program titles and/or title. Recommendation engine 508 can generate media content lists to present to any authorized user 516. These media content lists are generated using automated programming or user-definable settings. It is based on user 516 preferences for media consumption, which were generated from historical and newly detected ubicomp data 514 that was associated with user 516. Recommendation engine 508 creates media content lists to present to any authorized user 516. 518 is derived from historical and newly detected ubicomp data 514 that was collected from users on both system 500 and 500. The present example shows that system 500 programs can include both hardware and software. These may include biometric sensors to capture physiological conditions and facial recognition sensors for identifying users and capturing emotions; motion sensors tracking physical movement, haptic gestures, and environmental sensors tracking light levels, doors locks, and temperature; audio sensors capturing voice commands; video cameras enabling 2-way communication; video cameras enabling object detection; portable devices operating API’s; and audio visual devices with automated text recognition programming. Control systems for operating drones and robotics devices and other such as well as well as well. The present example shows that recommendation engine 508 can use computer application 78 for analysis and processing ubicomp data 514, 518 from individual users; aggregated media preference data from system 500 activity and data from a select number of users within a networked group 500. Computer application 78 can implement automated recommendation engine 508 processes that identify and recommend media content. These are based on user media consumption preference data, aggregated data from groups of 500 users, or based on data from individual users. Authorized users 516, 518 can request media content lists via API 512 controls. This allows them to define and create media consumption preference data parameters using either automated programming or manually. These parameters include demographics, geographic location, device, lifestyle habits, etc. Recommendation engine 508 can generate lists of available and desired media content databases over local or remote networks 504 and present them to subject users 516 and 518. Recommendation engine 508 can be linked via network 504 with media sharing platform 528 to allow searching, browsing, purchasing, transacting, delivering, and presentation media content. This is done using automated software programming, API 512. As an example, recommendation engine 508 could be connected via network 504 with media sharing platform 528. This is automated programming that generates media content according to the user’s 516 media preferences. These preferences are derived from historical ubicomp data 514. API 512 may be used by associated group 544 users to access recommended media content. User 516 can also set parameters such as genre, length, program, triggers or thresholds from ubicomp data 514 to allow access to the content.

“Healthcare Engagement”

“In certain aspects, health program 530 is integrated with API512 and coupled with recommendation engine 508 or blockchain 510. It provides personal health care information and related information to one to three users 516, 518. Health care program 530 can be described as a subscription-based or account-based third party program service that collects, views, shares, schedules, analyzes, and analyses personal health care data. Administrator 542 can create a user group 544 for subject 516 in order to use health care program530. This will allow the administrator to generate, analyze, and share personal health information, including real-time status, interpersonal communication, care request notifications, and patient conditions. The ubicomp data 514 feedback data may include preferences, analytic, predictive, recommendation, and other data. Administrator 542 can use API 512 controls to create parameters, filters, and settings to detect, receive, and distribute ubicomp data 514 used by group 544. Administrator 542 can use API 512 controls to create parameters, filters, and settings for processing and interpreting ubicomp data 514 used by group 544. API 512 controls may allow for parameters and filters to be applied to user 516 preferences information. These could include personal health assessments, needed or desired patient care, descriptions and patient health statuses, time sensitivity to sharing and responding to notifications related to patients, the level of information that is shared with notifications and details about patient information. API 512 controls may be used to send ubicomp data 514 notifications to one or more users 518. These notifications will include user 516 preference information, generated from and associated health care program experience 530 user experiences. User 516 preferences information can include all health-related data measured by system 500, including interactions via telecommunications (call, text and chat), in person visits, nursing care and physical therapy interactions, eating or feeding, emergency care and routine personal care services. The present example shows that system 500 programs can include both hardware and software applications. These may include biometric sensors that capture physiological conditions, facial recognition sensor for identifying users, and emotional state sensors; motion sensors tracking movement and haptic gestures; environmental sensors tracking light levels and temperature; audio sensors capturing sounds and voice commands; video camera enabling 2-way video communication; video cameras enabling object detection; portable devices operating API’s; and audio visual devices with automated content recognising programming. Control systems for operating drone and robotic devices and such as well as well as well. Some examples show that user 515 preferences information can be shared with group 544 and specific members 516 and 518 using newly detected data health program 530. This software operates within or networks to ubicomp 502 and may include health diagnostic equipment, wearable biometrics, video or audio device monitor signals, emotion recognition signals; portable devices operating API’s; audio visual devices with automated content recognition programming; control systems for robotic and drone devices, and other related technologies. Recommendation engine 508 generates care-related information based upon user 516 preferences information. This includes personal care lists, care service prerequisites and care methods for any authorized user 518. It also provides personal health care information based in part on the subject user’s 516 lifestyle choices and preferences, as well as historical ubicomp data 514. API 512 may be used by users 518 to access recommended health-care practices from a variety sources, such as website services, web-based references materials, video conferencing and networked reference database. Recommendation engine 508 could use computer application 78 in the present example to analyze and process ubicomp 514 from individual users 516-518, including aggregated health-care preference data from system 500 activity or data from multiple users 516-518 that are active within a networked group of 500 systems. Computer application 78 can implement automated recommendation engine 508 processes that identify and recommend health-care practices based on user preference data 516 or aggregated data 516 from selected users identified among all users in a networked system 500.

“Caregiving Engagement”

“In certain aspects, lifestyle & wellness program 532 is integrated with API512 and coupled to recommendation engine 508 & blockchain 510. It provides personal health data, lifestyle information, and recommendations using ubicomp 502 component including system 500 software apps operating on fixed 520 and mobile devices 522. These components identify, track, measure and interpret, then analyze, and present lifestyle and wellbeing information to one or multiple users 516, 518. Lifestyle and wellness program 532 can be described as a subscription- or account-based third party program service that collects, views, shares, schedules, analyzes, and analyses personal lifestyle and wellbeing data generated from user experiences. Administrator 542 could create a user group 544 for subject 516 in order to use lifestyle and well-being program 532. This will allow the administrator to generate, analyze, and share personal lifestyle and wellbeing information, including ubicomp 514 feedback information, that is derived from user experiences with respective wellness and lifestyle programs 532. The ubicomp 514 feedback information could include preferences, analytic, predictive, recommendation, and other data. System 500 programs can be networked with fixed devices 520 or portable devices 522 to manage the lifestyle and wellness program 532. These programs may also work together or individually. The present example shows system 500 programs that may include hardware and software. These could include biometric sensors to capture physiological conditions and facial recognition sensors to identify users. Location sensors track location and proximity of other objects. Audio sensors can also be used to record sound commands. Video cameras enable 2-way audio and video communications. Portable devices can operate API’s. There are audio visual devices that can automatically recognize content. Control systems for controlling robotic and drone devices. Administrator 542 can use API 512 controls to create parameters, filters, and settings for receiving, analyzing, and distributing ubicomp data 514 used by group 544. Administrator 542 can use API 512 controls to create parameters, filters, and settings for processing and interpreting ubicomp data 514 used by group 544. API 512 controls may allow for parameters and filters to be applied to user 516 preferences information. These include mood data analysis, methods to describe health status, time sensitivity to sharing and responding to notifications, the level of information that is shared in notifications, and methods for description. API 512 controls may be used to send ubicomp data 514 notifications to recommendation engine 508 from user 516 preference information. This preference information is generated from and associated in some ways with 532 lifestyle and wellness program user experiences. User 516 preferences information can include any lifestyle or wellness data that is measurable by system 500. This includes but not limited to activity levels and sleep schedules, food consumption habits and food quality, food intake schedules, media consumption schedules, media habits, inter-personal activity schedules, online activities habits, technology use, and so on. User 516 preference information can be shared with group 544 and specific members 516 and 518 depending on the detected behavioral data within Ubico 602. This includes a wearable biometric reading or video or audio device for person-to-person communications, emotion recognition signals and motion sensors, smart device online data, download and streaming data activity, facial recognition, networked appliances and other similar data. Users 516, 518 can use API 512 to access lifestyle and wellbeing program 532. This allows them to receive recommended lifestyle and wellness interaction lists. These include user 516’s sleep hours, preferred media content, preferred media consumption times, preferred medication administration times, ideal conditions for person-to-person communications, and in-person interactions. Recommendation engine 508 could use computer application 78 in the present example to analyze and process ubicomp 514 from individual users 516 and 518. This includes lifestyle and wellness preference data from system 500, as well as aggregated data from multiple users 516,518 and groups 544 who are active within a group 544 of systems 500. Computer application 78 can implement automated recommendation engine 508 processes that identify and recommend health care services based on user preference data, aggregated data, or data from a selected group of users within a networked group 500.

“Consumer Goods Delivery Engagement

Click here to view the patent on Google Patents.