Care Village Digital Twin System and Method

Abstract

A system of entities is represented by digital twins. Each digital twin incorporates a specification of the entity's capabilities. Each digital twin incorporates the entity's physical characteristics. Each digital twin represents the state of the entity. The interactions between digital twins provide an accurate and timely representation of the interactions between the entities.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Patent Application No. 63 / 385,592, filed November 30, 2022, which is incorporated herein by reference in its entirety.

[0002] Aspects of the present disclosure generally relate to a system for monitoring a care recipient. [Background technology]

[0003] In traditional infrastructure technology environments, personal emergency response systems (PERS), also known as medical emergency response systems, allow a person to call for help in an emergency by pressing a button.

[0004] One exemplary system is a two-way voice communication pendant, which allows a person to call for assistance anywhere around their home. Personal emergency response devices enable aging in place and independent living for care recipients. Personal emergency response devices allow a person to stay connected to family and emergency services via their existing landline phone. Summary of the Invention

[0005] A system of entities is represented by digital twins. Each digital twin incorporates a specification of the entity's capabilities. Each digital twin incorporates the entity's physical characteristics. Each digital twin represents the state of the entity. The interactions between digital twins provide an accurate and timely representation of the interactions between the entities.

[0006] One aspect includes a system for monitoring a care recipient by a stakeholder. A transceiver receives a plurality of tokens from a plurality of environmental sensors configured to monitor the care recipient. Each of the tokens includes, at least in part, a detected dataset representing the care recipient's behavior in an environment. Each of the behaviors is represented by a multidimensional feature set forming part of the care recipient's healthcare profile, and the tokens are encrypted using a cryptographic key. A non-transitory computer-readable storage medium stores a digital twin of the care recipient. The digital twin includes a dynamic tokenized representation of the care recipient's static behavior in the environment. At least one processor analyzes the digital twin of the care recipient instead of analyzing the plurality of tokens received from the plurality of environmental sensors until the at least one processor receives a token indicating that a wellness event or care event has occurred. When the wellness event or care event has occurred, the processor is configured to decrypt the plurality of tokens using the cryptographic key, analyze the plurality of tokens, and change the state of the plurality of environmental sensors or notify a stakeholder.

[0007] The at least one processor may be configured to identify potential future conditions of the care recipient by analyzing the digital twin.

[0008] The at least one processor may be configured to identify potential future states of the care recipient by analyzing the digital twin and the plurality of tokens.

[0009] The processor may use machine learning to analyze the digital twin and the plurality of tokens.

[0010] The encryption key may be unique to the care recipient.

[0011] Changing the state of multiple environmental sensors may change the monitoring focus of the environmental sensors.

[0012] The monitoring focus may increase the fidelity or granularity of the environmental sensors.

[0013] The detected data set may be from a respiration sensor or a heart rate sensor.

[0014] The transceiver may transmit the token to a second care system.

[0015] The second system of care may make a decision based in part on the detected data set.

[0016] The system of care may be determined in part based on the relationship of at least one stakeholder to the care recipient.

[0017] The at least one stakeholder may be determined by data relating to a relationship between the at least one stakeholder and the care recipient.

[0018] Another aspect includes a method for monitoring a care recipient by a stakeholder. A transceiver receives a plurality of tokens from a plurality of environmental sensors configured to monitor the care recipient. Each of the tokens includes, at least in part, a detected data set representing the care recipient's behavior in an environment. Each of the behaviors is represented by a multidimensional feature set forming part of the care recipient's healthcare profile, and the tokens are encrypted using a cryptographic key. A non-transitory computer-readable storage medium stores a digital twin of the care recipient. The digital twin includes a dynamic tokenized representation of the care recipient's static behavior in the environment. At least one processor analyzes the digital twin of the care recipient instead of analyzing the received plurality of tokens until the at least one processor receives a token from the plurality of environmental sensors indicating that a wellness event or care event has occurred. When the wellness event or care event has occurred, the processor is configured to decrypt the plurality of tokens using the cryptographic key, analyze the plurality of tokens, and change the state of the plurality of environmental sensors or notify a stakeholder.

[0019] Another aspect includes a non-transitory computer-readable storage medium encoded with data and instructions. When executed by a processor, the data and instructions cause a computing device to perform a method for monitoring a care recipient by a stakeholder. A transceiver receives a plurality of tokens from a plurality of environmental sensors configured to monitor the care recipient. Each of the tokens includes a detected data set representing the care recipient's behavior in an environment. Each of the behaviors is represented, at least in part, by a multidimensional feature set forming part of the care recipient's healthcare profile, and the tokens are encrypted using a cryptographic key. The non-transitory computer-readable storage medium stores a digital twin of the care recipient. The digital twin includes a dynamic tokenized representation of the care recipient's static behavior in the environment. The at least one processor analyzes the digital twin of the care recipient instead of analyzing the plurality of tokens received from the plurality of environmental sensors until the at least one processor receives a token indicating that a wellness event or care event has occurred. When the wellness event or care event has occurred, the processor is configured to decrypt the plurality of tokens using the cryptographic key, analyze the plurality of tokens, and change the state of the plurality of environmental sensors or notify a stakeholder.

[0020] For a better understanding of the nature and advantages of the present disclosure, reference should be made to the following description and accompanying drawings. It should be understood, however, that each of the drawings is provided for illustrative purposes only and is not intended as a definition of the limits of the scope of the present disclosure. Also, as a general rule, unless otherwise apparent from the description, in which elements in different figures use the same reference numerals, the elements are generally identical or at least similar in function or purpose. [Brief explanation of the drawings]

[0021] [Figure 1] Figure 1 is a block diagram of the Care Village Digital Twin (CVDT) execution environment.

[0022] [Figure 2]Figure 2 is a block diagram of CVDT for stakeholders.

[0023] [Figure 3] FIG. 3 is a block diagram of a care village digital twin for a device(s).

[0024] [Figure 4] Figure 4 is a block diagram of a care village digital twin for the environment.

[0025] [Figure 5] Figure 5 shows a block diagram of the care village digital twin at different times.

[0026] [Figure 6] Figure 6 is a block diagram of an alternative predicted care village digital twin.

[0027] [Figure 7] Figure 7 is a block diagram of an alternative linearly predicted care village digital twin.

[0028] [Figure 8] FIG. 8 is a block diagram of the predicted state of the monitored person (PUM).

[0029] [Figure 9] Figure 9 is a block diagram of a predicted care village digital twin with configuration.

[0030] [Figure 10] FIG. 10 is a block diagram of a pattern identification, matching and creation system.

[0031] [Figure 11] Figure 11 is a block diagram of the care village digital twin system.

[0032] [Figure 12]Figure 12 is a block diagram of the care village digital twin system.

[0033] [Figure 13] Figure 13 shows the timeline of the care village digital twin forecast.

[0034] [Figure 14] Figure 14 is a diagram of the care village digital twin analysis.

[0035] [Figure 15] Figure 15 is a diagram of a care village digital twin simulation.

[0036] [Figure 16] Figure 16 is a block diagram of the care village digital twin environment.

[0037] [Figure 17] Figure 17 is a block diagram of the Care Village Digital Twin CVDT Pattern and Response System.

[0038] [Figure 18] Figure 18 is a block diagram of the care village digital twin response system. DETAILED DESCRIPTION OF THE INVENTION

[0039] Aspects of the present disclosure include representations of physical entities such as devices, sensors, stakeholders, environments, and other entities that can be made through the creation of digital twins. These digital twins in the context of care villages are known as care village digital twins (CVDTs). Each care village digital twin can provide a representation of the physical entity it represents, including specifications, configuration, state, and any data such entities can generate in a particular context. This can include, for example, multiple sensors that can provide a comprehensive data set that can be represented by multiple care village digital twins arranged in a composite CVDT to represent an environment containing any arrangement of devices, sensors, stakeholders, and other entities.

[0040] A care village digital twin can represent the configuration of sensors in an environment, such as a device, and can be in the form of a software simulation that mimics the configuration and operation of the sensors, such that it accurately generates the output of a physical sensor when fed incoming data to that sensor, which may include and / or be based in whole or in part on a replica of that data. Such a configuration can include feedback mechanisms so that, using known, predictable configurations and sensor behaviors and the data generated by the sensors, the inputs to the sensors can be more accurately represented. This can also be true when there are multiple sensors that can capture the environment and context in similar or different ways to more accurately capture the conditions of the input to at least one sensor.

[0041] The Care Village Digital Twin can be correlated with the actual sensors to represent the state and configuration of the sensors and the datasets generated by the sensors. This ability to create, initialize, deploy and operate such Care Village Digital Twins of individual sensors and groups of sensors provides a unique approach to the operation and management of these sensors, their configuration, the datasets they generate, and the environment and context in which they reside.

[0042] Each stakeholder, device, system, infrastructure and other embodied element of the care village can have at least one digital twin that represents their state.

[0043] Such a care village digital twin can then be continuously, periodically and / or updated with events, triggers, alerts, or other real-time data, and / or refreshed in response to any changes in the state of the embodied elements that it represents.

[0044] One important aspect of this approach is to avoid imposing an unsustainable processing burden on the embodied elements operating within the care village, the care village digital twins representing those embodiments, and the care village management, administration and / or reporting systems as a whole.

[0045] The state of each embodied element, the data it generates and / or communicates, and representations of the state of stakeholders are generally, for the most part, confidential and private to those stakeholders, the devices monitoring them, and the systems and infrastructure that enable and support their activities.

[0046] The system's use of tokens to facilitate data communication significantly ameliorate these concerns, but the system can also use a series of vector representations of these tokens to partially avoid overly cumbersome and complex key management for such tokenized data.

[0047] The use of a comprehensive set of digital twins to predict, detect, and avoid misguided incentives, rolts, or other actions, behaviors, and outcomes provides a unique approach to addressing such problems.

[0048] Care Village Digital Twin

[0049] In Care Village, each entity in the system can have a digital twin, which is a representation of that entity. These representations can initially be frameworks that contain a set of data that represents the entity and can be populated over time with data sets generated by the Care Village system, for example, from those entities, other sensors, behaviors, patterns, and / or other data sources.

[0050] A Care Village Digital Twin can have a state in that each instance of a CVDT can represent the state of the entity that the Care Village Digital Twin represents. For example, a Care Village Digital Twin of a Person Under Monitoring (PUM) is a representation of that PUM at a particular time (a particular time or period), and data of the state of the PUM is integrated into the Care Village Digital Twin to provide a corresponding state for that CVDT.

[0051] As the Care Village Digital Twin receives data from the monitored person and their environment, it can correlate that data with the PUM's Health Care Profile (HCP) and their behavioral patterns in those situations. This provides a current representation of the state of the PUM and the environment.

[0052] For example, the state of a care village digital twin at a point in time is a snapshot of the monitored person, their environment, and any relationships with stakeholders currently interacting at that time. This snapshot can then be stored in a repository as a record of that state. This snapshot and further subsequent snapshots can then form a history, and in some embodiments, such snapshots can be recorded on a regular schedule and / or can be triggered automatically or manually. These snapshots form an audit trail and can be recorded in at least one distributed ledger.

[0053] One advantage of a care village digital twin is that a state comprising a set of such states can be used by at least one predictive technology to identify potential future states of, for example, PUMs and their environments. In this manner, sensor configuration decisions, stakeholder alerts, pre-provisioning of resources, and / or other actions can be taken. Such action decisions may be made by system monitoring functions and / or may include manual intervention and / or assistance. For example, in some embodiments, at least one machine learning technology can be deployed to create a set of specifications including, for example, sensor configurations, messages to stakeholders and / or PUMs, etc.

[0054] A care village digital twin, for example, can provide multiple predictive options to be instantiated. Each of these instances can itself be a CVDT, for example, and represent the expected state of the monitored person and their environment. The system monitoring function can then compare these predicted outcomes to see which is most likely to occur and then generate a specification that can be deployed when appropriate.

[0055] Such a Care Village digital twin, in some embodiments, can be compared to other Care Village digital twins representing similar or the same HCP and / or other PUMs with similar patterns. In this way, predicted outcomes can be compared to the actual or historical outcomes of the monitored person, as represented by the predicted Care Village digital twin. This comparison can be used to inform the system assessing the CVDT, and therefore alter the predictive weightings and subsequent actions of the monitoring system with respect to that CVDT.

[0056] A care village digital twin can include multiple CVDTs for a set of physical entities in any configuration. This can include patterns of motion and / or behavior of those entities. In the case of sensors or other configurable entities, this can include a representation of their configuration so that the datasets generated by such entities can be predicted and represented within a set of CVDTs.

[0057] In some embodiments, an environmental care village digital twin may comprise a set of sensor representations that populate the contextual environment and the representation of the physical environment. Each of these sensor representations may include specifications for their operation, such as their performance parameters, e.g., sensitivity, capture rate, data format, and other configuration parameters. In this way, the care village digital twin may assume a configuration for the sensor representation, the CVDT of the sensor, such that if an event occurs that is part of a pattern being manipulated by the CVDT, the sensor will generate a dataset representing that event. This configuration may be a proposed or assumed configuration and may differ from the sensor's current operating configuration. This assumed dataset in such a configuration may then be compared to the actual dataset being received by the physical sensor. If the dataset received from the sensor is insufficient to identify the event the care village digital twin is predicting, the physical sensor's configuration may be altered to match the assumed configuration of the sensor's CVDT. In this way, the CVDT may operate several configurations for the sensor, and in some embodiments, a best-fit method is used to establish a configuration for the sensor that matches the predicted event set. Such an approach can be very beneficial when an event is detected from one sensor, for example, a sudden increase in acceleration from a device worn by a PUM, which can be confirmed or verified by another sensor in the environment.

[0058] Personnel Care Village Digital Twin (PUM)

[0059] In some embodiments, a person to be monitored in a care village setting is assigned a unique system-wide identity when they are introduced to the village. There may be certain further data sets that form part of the initial representation. These may include, for example:

[0060] Relationships - Other stakeholders with whom you have a relationship (e.g., doctors, caregivers, friends and family, neighbors, pharmacies, delivery services, other services, etc.).

[0061] Health Data - The initial health condition(s) that initiated the need for monitoring represented by a Healthcare Profile (HCP), which may include existing and current health conditions and a set of parameters to be monitored.

[0062] Environment - their initial residence while under supervision and other places to which they regularly travel. This may also include location, nearby health and care-related services, and social, cultural, and economic information associated with the location.

[0063] Care Village Sponsor - At least one entity that sponsors the supervisee's membership in the Care Village (e.g., finance, insurance, VA, Medicare, etc.) and characteristics of support, including available services, responsibilities / liabilities, rules of care, and other specifications.

[0064] This data set can form the initial framework for the monitored person's digital twin, but as the PUM undergoes monitoring, a range of data sets can populate the digital twin to make it more representative of the PUM's state. This data and improved accuracy can then be used to enrich the PUM's profile data.

[0065] In some embodiments, the Care Village digital twin framework can include a Healthcare Profile (HCP) that represents the condition of the PUM for which monitoring is invoked. This can include, for example, the specific condition(s) and / or treatment(s) the PUM is receiving. This HCP provides the care framework as determined by relevant medical professionals.

[0066] Compliance with health data protections, including HIPAA and the like, is often mandated, and such data may be stored in at least one repository that complies with such mandated protections.

[0067] Such a Care Village Digital Twin may include health data and form the basis for recording the health journey of the HCP, PUM providing the care framework as determined by the relevant medical professionals, creating a "health twin" that may be anonymized to form part of the Care Village health dataset. The use of the HCP and profile for initial context may form the basis of a set of touchpoints for stakeholders and the Care Village system when interacting with the PUM.

[0068] Once the care village digital twin is initialized, the HCP and their patterns can be integrated into the CVDT by referencing and / or embedding. This creates an initial state for the CVDT and can include at least one configuration of at least one device incorporating sensing capabilities. Such configuration can be used to initially establish the state of the monitored person, the environment, and any stakeholders. The initial operation of the configured device, including any sensors, is to establish a relationship between the patterns deployed for the HCP and the state of the PUM in the environment associated with those patterns.

[0069] One aspect is to create a "resting" state of the person under surveillance and environment, described as a resting state, which is the expected actual behavior of the PUM and environment under normal conditions within the context of the appropriate HCP.

[0070] Sensor's Care Village Digital Twin

[0071] A care village sensor can have a digital twin. When a sensor is initialized, its configuration and specifications are recorded in a repository, along with its identification, location, stakeholder relationships, device and other sensor relationships, and the appropriate management and processing system of and for the sensor, which represents the sensor's environment and context. This forms an initial care village digital twin for that sensor, into which the initial data set from the sensor is also recorded when initialized. This combination provides the CVDT with an initial quiescent state of the sensor and environment.

[0072] The care village digital twin of the sensor incorporates the sensor's capabilities, the sensor's configuration including any alternative configurations, and the sensor's dataset in its initial rest state, as well as the environment in which the sensor is deployed.

[0073] The Care Village Digital Twin, representing the sensors and their relationship to the environment, provides an initial data set from which any variations can be represented as changes in the initial state of the Care Village Digital Twin. These variations can be compared to an expected data set or set of patterns from sensors that are part of the environment. In some embodiments, there may be multiple CVDTs created based on an operating CVDT, with inputs of data representing different patterns, and then with different configurations applied to determine different outputs.

[0074] One aspect of a care village digital twin for a sensor or set thereof is as a means to track the reliability of the sensor, for example, using Byzantine algorithms. This can include, for example, analysis of sensor behavior expressed as a metric that combines the configuration and operation of the sensor with the dataset generated in the environment, for detection of failures, inaccuracies, and / or other variations in the dataset provided by the sensor.

[0075] This can include comparing the care village digital twin sensor behavior with physical sensors deployed in the environment and / or deployed in a manner that establishes a baseline for the sensors, which can be used to establish a metric for the reliability of the sensors, which can be used by the CVDT to evaluate the data transmitted by the sensors and modify the operation of the CVDT to maintain accurate alignment between the physical sensors and the CVDT.

[0076] Environmental Care Village Digital Twin

[0077] An initial framework of an environment can be established using data provided by the environment owner and / or occupant, e.g., a PUM residing in such environment, a digital representation of any architectural 2D or 3D plan, including the location of the environment and the location within that environment of any features and amenities, including, for example, power or other outlets, inlets and outlets, furniture, facilities and any appliances, and any health and wellness related equipment. This initial framework can be substantiated, in part or in whole, by physical sensing of the environment through the capabilities of one or more sensors temporarily or permanently deployed in such environment.

[0078] One aspect is the overall context within which the Care Village digital twin, representing the environment, is located. This can include the physical location and, as a result, can include, for example, both static and dynamic weather and other environmental considerations. For example, if weather events such as heat waves, heavy rain, tornadoes, hurricanes, etc. are predicted or experienced by the environment, the Care Village digital twin can represent these environmental changes and, in some embodiments, can be used to predict fluctuations in the intensity of such events. This can inform a response system regarding the resources and potential actions needed to ensure the wellness of PUMs within such environments when such conditions occur.

[0079] A Care Village digital twin may have a dispersion metric that is a representation of the difference between the observed real-time entity that the Care Village digital twin represents and the state of that entity represented by the Care Village digital twin. For example, this may include time data, such as the time elapsed since the last update of the CVDT by a physical entity, the degree of dispersion and / or accuracy of any set of data that such entity may provide to the CVDT, or any other attributes of such data that the entity may provide. For example, if a sensor is monitoring a single environmental aspect such as temperature, the time of the measurement, the degree of dispersion, and the reliability or accuracy of that data may be communicated to the Care Village digital twin of that sensor as a dispersion metric. In more complex examples, such as a sensor capturing audio, the dispersion metric may comprise a calculated value for the degree of accuracy that the sensor, directly and / or in combination with a signal processing system, determines for that data set.

[0080] As part of the initial configuration of the Care Village digital twin for the environment, an HCP for the monitored person is included. The HCP contains a set of patterns that represent the behavior and activity of the PUM, including the resting states of those patterns. In this way, the overall resting state of the environment and PUM can be established within the operating patterns.

[0081] The care village digital twin can be replicated as an instance of a CVDT representing the actual state of the environment to represent potential changes in patterns. These different patterns can be selected by a monitoring system as most likely to occur based on sensor data from the CVDT representing the actual state of the environment and PUM. These variations can then be considered, for example, by a machine learning system to predict the most likely changes in patterns. Such an approach can include using a combination of game theory and machine learning to create a decision matrix of possible outcomes. This can then be used to vary the configuration of sensors within any of the CVDTs, including those representing the actual environment and PUM.

[0082] In some embodiments, datasets from sensors, both physical sensors and sensors represented by one or more care village digital twins, can use an accumulation technique such that as each dataset changes, overall trends are accumulated over multiple time periods using multiple CVDTs to predict with varying levels of certainty the relative likelihood of data from the physical sensors matching data from sensors represented by one or more CVDTs.

[0083] The integration of sensors, which can use visible or invisible materials, with indicia that may be used by the sensors, such as barcodes, painted or applied location indicia, such as circles, numbers, geometric shapes, arrows, or other directional indicators, can be included in a care village digital twin. In this way, changes in the state of the CVDT can be accurately measured and calculated using a combination of sensors and indicia. For example, if a sensor monitors a painted line or other shape, using a material that is translucent at visible and visible-to-infrared wavelengths, the movement of PUMs passing through such a shape can be recorded. This is also true for pets, where indicia are placed at a height above the pet's threshold. Such an approach can be used for entry and exit points to different rooms within a building, allowing tracking of PUMs' movements without compromising their privacy.

[0084] In some cases, the use of a care village digital twin can predict the optimal placement of such markings within the environment. These markings can be serialized to create unique instances. These representations can be applied to vehicles as well as outdoors.

[0085] A care village digital twin representing the actual initial state of the environment and PUM can form a representation of the environment in a "resting" state, and other CVDTs based on this initial state can be used to represent potential states of the environment and PUM in different situations. These predicted CVDTs can, in some embodiments, be used as a corpus for one or more machine learning techniques to identify the most likely future states for the PUM and environment, which can then inform one or more systems, including the configuration of sensors in the environment, including those worn by the PUM, of possible predicted changes in state.

[0086] Stakeholder Care Village Digital Twin

[0087] Each stakeholder in a care village can have a care village digital twin. This includes people and organizations. For example, an insurer can have a CVDT that represents the insurer's policies with respect to other stakeholders, including, for example, the PUM, and / or suppliers of goods and services to the insurer for providing, in whole or in part, directly or indirectly, to, for example, the PUM.

[0088] Individuals as entities can have care village digital twins that represent their actions and activities within the care village, such as a PUM, the PUM's family, friends, neighbors, etc. Additionally, each individual, such as a caregiver, can also have a CVDT that is their representation for their interactions within the care village. If a caregiver contracts with a service organization to provide their skills to the PUM, that organization can also have a CVDT. In this example, interactions with the PUM can include CVDTs for at least three entities: the PUM, one caregiver, and one caregiver stakeholder organization. This can also include a CVDT for the environment, including one or more sensors and devices within that environment, and any other CVDTs for entities involved in the PUM.

[0089] While there may be potential complexities in a care village digital twin that represents the organization as a whole, a stakeholder organization's CVDT may include a set of stakeholder CVDTs, each of which has a counterparty, in that the organization has a specific relationship with another care village stakeholder. For example, a PUM may have a health insurance contract instantiated as a contract, e.g., a smart contract, so that the stakeholder organization can instantiate that contractual relationship and create a personalized CVDT for the specific PUM. In this way, the relationship between the PUM CVDT and the sponsoring organization, e.g., the insurance company, CVDT, is a simple one-to-one relationship. A stakeholder organization CVDT may include similar relationships with the PUM's service providers, with whom the stakeholder organization has a relationship for the provision of their services to the PUM.

[0090] As trends continue toward personalized care, the use of individual care village digital twin relationships creates opportunities to predict and evaluate potential future personalized outcomes for PUMs with different sets of inputs, such as different care regimes, prescriptions, and patterns of behavior.

[0091] The use of machine learning and other big data analytics can be invoked on these datasets to identify patterns for both individuals and classes of individuals. These patterns can then be applied to the care village digital twin in a way that supports prediction of possible future states of those CVDTs to determine potential outcomes and their impact on the wellness of PUMs.

[0092] One aspect of using a care village digital twin in this manner is the representation of the various entities and their interaction touchpoints. These touchpoints, considered points of interaction, can have metrics that represent these interactions, such that one embodiment of these interactions can be a graph, which can then be evaluated by one or more machine learning techniques, statistical analysis, etc., for predictions of possible future interactions. Such techniques can include the declared and calculated incentives of the entities involved to ascertain a potential range of possible outcomes.

[0093] In some embodiments, such touchpoints may be represented as a network, for example, a neural network, which may also include the use of constraint-based logic to determine which outcomes are most likely and / or which outcomes represent the incentive sets of each of the stakeholders, individually and collectively.

[0094] In some embodiments, the care village digital twin can be configured as a "high touch" sampling mode monitored by the system, so that if the difference between the CVDT and the real environment and the entities and stakeholders in the real environment exceeds or approaches a threshold and / or includes an alert / event, the monitoring system switches to the real environment. This can include changing the configuration of entities in the real environment for higher granularity, increased sample rate, larger and more diverse data sets, etc.

[0095] In some embodiments, strategies for data collection and / or sampling of the care village digital twin and / or real environment, and entities within the real environment, may be determined through the use of game theory, which may include, for example, the deployment of a CVDT specialized in verifying the suitability of the monitored entities, including evaluating the incentives of the stakeholders involved.

[0096] Care Village Digital Twin Interactions for Prediction

[0097] Each Care Village Digital Twin has specifications that can be embodied in an operating CVDT. For example, a Care Village Digital Twin can be instantiated in a computing environment based on its CVDT specifications, and such an instance can then be operated in a temporal state that is equivalent to actual time in the real world, which is a network or other reference time. However, a Care Village Digital Twin can also operate in accelerated time, for example, a CVDT instance operating at a multiple of network or real time.

[0098] In this example, the care village digital twin can use patterns that represent the wellness state of the monitored person in the context of the HCP to accelerate time, e.g., to establish a future time range in which a wellness event is more likely using comparisons with other PUMs with the same HCP. This allows the CVDT to propose configuration changes to the PUM's sensors in anticipation of such events, thereby mitigating any adverse effects as much as possible. This can include determining and selecting the most appropriate response to such situations.

[0099] One aspect of this approach may be to alert a neighbor or relative that a wellness event is more likely to occur so that they can provide additional care resources, such as additional time or visits from a caregiver, or check on the monitored individual more frequently. For example, a relative or other stakeholder delegated by the PUM as a proxy with elevated rights to the configuration of at least one sensor in the PUM's environment can take on a more active monitoring role. This may include, for example, a stakeholder with an application that can recognize certain aspects of the PUM's behavior, such as image, audio, or other sensing, and can use the Care Village system to interpret those sensor data, thereby providing a critical monitoring function at or near the time of the wellness event.

[0100] In some embodiments, monitoring of either an operating or simulated care village digital twin may be delegated to other systems, including, for example, environmental sensing, signal processing, token evaluation, incentive misalignment, or other general or specialized systems configured to monitor any real environment, including entities in and / or CVDTs representing such environments. In this way, specialized monitoring functions may exist that are optimized for specific monitoring capabilities and may include human interaction.

[0101] The ability of the Care Village system to instantiate multiple Care Village Digital Twins and operate them at various time rates provides the secure ability to use, for example, machine learning, to determine the most likely outcome for at least one of such CVDTs, which may include those representing devices, stakeholders, systems, infrastructure, etc.

[0102] One aspect of this approach is the determination, prediction, extrapolation and / or validation of at least one touchpoint for each of the care village digital twins interacting with each other, either as instances within a computing environment on a variable time basis and / or as a representation of an actual situation in reality.

[0103] In some embodiments, there may be a root care village digital twin that is a representation of the current state of stakeholders, devices, environment, monitored individuals, etc. The root CVDT may also have specifications that represent the state of the CVDT at rest.

[0104] There may then be multiple instances of that care village digital twin branched off from the root, using at least one algorithm to predict the future state of each of these branched CVDTs.

[0105] In some embodiments, different input data may be applied to multiple identical care village digital twin instances, for example, data from a previous corresponding situation may be input into at least one CVDT, which may then be used as at least a partial basis for predicting possible situations in the CVDT, which is being monitored for PUM in real time, using accelerated time.

[0106] One aspect of this approach may be the deployment of evolutionary and genetic type algorithms to create a set of care village digital twins with different inputs, and the application of the different algorithms to create a set of possible situations, which can then be used as a corpus for at least one machine learning, weighting, forecasting and / or other probabilistic technique, including, for example, Bayesian techniques, to identify likely situations and outcomes of PUM over various time scales.

[0107] For example, these variances of at least one care village digital twin using different behaviors exhibited by at least one PUM with similar HCPs can then be used, for example, in combination with an evolutionary algorithm to identify and potentially monitor behaviors that are likely to have at least one wellness event.

[0108] This may include, for example, instantiating multiple care village digital twins, each of which has at least one touchpoint that is a point of interaction with another CVDT. These touchpoints may then be represented by a graph or other node structure, including, for example, using a manifold or other topological representation such as a Hilbert space. In these configurations, at least one machine learning technique may be applied to evaluate, determine, and / or predict interactions with respect to their incentives, dynamics, behavior, and / or outcomes.

[0109] These node interactions can, in some embodiments, be represented as vectors that can include multiple attributes and arbitrary metadata, and thus can be presented as a graphical representation for both machine and human interpretation.

[0110] In situations where sensor data feeds are limited and / or constrained, e.g., limited battery or energy availability or communication capabilities, the Care Village digital twin can create a more continuous data set based on calculations and / or via lookup tables of previous similar data sets. This can include, for example, retroactive data revisions to account for delayed data feeds, for example, when a care recipient is in a vehicle between home and a medical facility with limited or no communication capabilities.

[0111] Use of the Care Village Digital Twin for predictions, including data sets, states, and / or interactions, can provide the ability to model, emulate, and / or simulate patterns of behavior and data sets that represent those patterns in any arrangement. This can include relationships between multiple Care Village Digital Twins, such as monitored individuals, caregivers, and stakeholder organizations, so that interactions between parties can be evaluated to determine, for example, which parties have the least impact on the wellness of the PUM or the least negative impact on all of the parties involved.

[0112] Part of this evaluation is the determination and use of metrics, particularly metrics that represent the profiles, contractual relationships, and / or incentives of the parties involved. In some embodiments, one aspect is the use of incentive weighting in the care village digital twin to identify potential misalignments.

[0113] Each of these assessment systems may include configurations that support the selection of one or more assessment methods so that the relationship between incoming data, the methods and techniques applied to that data for assessment, and the results can be determined and / or audited. In this approach, there may be one or more permission systems so that stakeholders can choose to opt in or out of assessment of one or more datasets related to their wellness and environment.

[0114] Digital Twin and Directed Learning / Supervised

[0115] Machine learning, a subfield of artificial intelligence, focuses on computer algorithms that use computational methods to "learn" information directly from data, without relying on predetermined equations, instruction sequences, and / or similar deterministic specifications. Machine learning algorithms function to enable their performance to improve as the amount of data available for learning increases. A very common approach to implementing machine learning is through the use of artificial neural networks (ANNs), which are computer systems designed to simulate the workings of the human brain by modeling how neurons process and transmit information. A typical artificial neural network consists of several nodes, or neurons, each of which takes multiple data inputs and produces a single data output that is a function of the weighted sum of the inputs; these nodes are typically interconnected in a layered topology in which the output of one layer of nodes serves as the input for the next layer of nodes. Artificial neural networks can have other topologies, and the way each node combines its data inputs to produce a data output can vary as well.

[0116] Training in artificial neural network-based machine learning systems involves adjusting the weights applied to all inputs and the output thresholds of all nodes to improve the overall output result of the network. Approaches to training in these systems are typically categorized as supervised, unsupervised, and reinforcement learning. Each method is best suited to a particular set of applications.

[0117] Supervised machine learning methods implement learning from data by providing relevant feedback. This feedback can be in the form of metadata including, for example, labels or class indicators assigned to input datasets. For example, an image of a person on a floor assigned a "fall" label, or a combination of acceleration, elevation, and tilt sensor datasets assigned a "walking" label. The feedback can also be in the form of a function that maps the input data to a desired output value. The input data and associated metadata or output mapping are known as training data. The goal of supervised machine learning is to build a model that generalizes from the training data to new, larger datasets.

[0118] Supervised machine learning is well suited for use in classification, which refers to predicting a discrete response from input data, such as whether a sensor data set represents a fall, step, or other movement-related state of a PUM, whether a sequence of sounds represents a PUM calling for help, and / or whether a combination of PUM risk factors should result in a call to emergency medical services.

[0119] Supervised machine learning is also used in regression applications, where a system predicts a continuous response from an input data set. For example, in some embodiments, a supervised machine learning system can be used to estimate a physical quantity, such as room temperature, and can act as a virtual sensor based on historical temperature data to provide missing data from an actual sensor that, for example, stops working or communicating under certain conditions. This approach can also be used in other embodiments to generate simulated sensor inputs to sensors, devices, and / or environmental care village digital twins to model actual behavior and / or conditions for the CVDT.

[0120] In some embodiments, the selection and deployment of a care village digital twin or set thereof may be determined, at least in part, to simulate or model specific behaviors and confirm predictive properties using machine learning in a directed manner. This may include the use of one or more frameworks to establish outcomes based on determined variations in the care village digital twin configuration. For example, there may be specifications of the degree of acceptable variation in different contexts for a given / desired / intended / predicted outcome (including a set thereof). This may include system-derived pattern detection for outcomes indicative of compatibility variations determined in whole or in part through the use of machine learning techniques.

[0121] Digital Twin and Undirected / Unsupervised Learning

[0122] Unsupervised machine learning methods, on the other hand, do not require labeled training data. Instead, they rely on the data itself to identify patterns and relationships. These methods are useful for identifying hidden patterns and / or inherent structures in input data. Unsupervised machine learning is used to cluster data points together based on common characteristics. For example, in image recognition applications, or to identify pixels and / or other elements of an image that belong to an object or person to find groups of sensor signals or patterns that are most likely to exist for a particular PUM situation. In some embodiments, clustering based on unsupervised machine learning systems can also be used to identify outliers. For example, if a sensor dataset pattern is outside the range of normal conditions, this may indicate an emergency or a faulty sensor, as the case may be.

[0123] In some embodiments, machine learning-based clustering can also be used to identify patterns within the care village digital twin that lead to particular types of outcomes. For example, such a system can be used to identify associations between different combinations of datasets representing sensor inputs, PUM states, actions, and / or environmental conditions and desired outcomes (such as a fall or another emergency being averted, an emergency response occurring on time, etc.) or undesired outcomes (such as an emergency occurring, resources not being ready to respond on time, notifications not being provided on time, etc.).

[0124] Another category of machine learning methods is reinforcement learning, which uses a feedback mechanism similar to supervised machine learning. However, in reinforcement learning, feedback is provided in the form of a general reward value for the generated output instead of a set of correct output datasets. Machine learning models are typically trained through a series of trial-and-error iterations until they are able to correctly solve each case. This technique is useful for training systems to make decisions to achieve desired goals in uncertain environments. In some embodiments, this machine learning method can be combined with one or more care village digital twins, which are run multiple times and the machine learning system is trained to generate appropriate responses in the form of decision datasets to achieve the desired outcome of the PUM.

[0125] The combination of machine learning and game theory can provide for the identification and development of games that represent the characteristics and behaviors of stakeholders and other entities in the environment, which can be particularly useful when monitoring conflicting data sets, out-of-band data, and / or internal self-serving interests to detect data discrepancies.

[0126] One aspect of this approach is to identify actual or potential unintended conditions, behaviors, and / or outcomes; for example, reconciliation of datasets provided by one or more entities with datasets generated by machine learning, both of which may be represented by one or more care village digital twins, can result in assessments and adjustments that identify such conditions, behaviors, or outcomes.

[0127] One application of directed machine learning is the identification of context and the derivation and construction of new patterns derived from system datasets, such as those represented by simulated CVDTs, that match one or more characteristics of PUM behavioral variability.

[0128] Illustrative Embodiments

[0129] A care village digital twin can be instantiated as a set of class-like specifications, which, once the appropriate operating environment is deployed, become a stateful operational CVDT. A care village digital twin includes specifications representing physical entities such as devices, sensors, stakeholders, and the environment. These specifications include both the entity's defining capabilities and its configuration. For example, a device may have a defining specification of its capabilities, such as a thermometer or a camera with a specific focus and resolution. For stakeholders, this may include, for example, the stakeholder's role. Each entity may have a configuration specification if the entity supports such configuration. For example, a camera may have adjustable resolution and / or focus, a device with multiple sensors may have the ability to increase or decrease the sensitivity of each sensor, etc. For stakeholders, configuration specifications may include their availability and / or operation time, cost rate, technical capabilities, etc.

[0130] When a Care Village Digital Twin is instantiated by deploying a supporting operational environment, each of the entities represented by a CVDT has a state that is determined at least in part by the configuration of that entity represented by the CVDT, which is an operational CVDT.

[0131] A Care Village Digital Twin contains relationships between the entities represented by its CVDT. In a simple example, a CVDT can have two entities: a device and a stakeholder (e.g., a PUM). In this example, the device is worn by the PUM and includes three sensors, an accelerometer, a gyroscope, and an altimeter, each of which has a definition and configuration specification. The Care Village Digital Twin has a represented relationship between the device and the stakeholder in that the device is worn and provides a set of data about the state of the device and the sensors therein. This data can form a pattern that represents the state of the device and the wearer and is represented as a set of inputs, data from the device, and a set of outputs. This pattern can be placed within the CVDT as a further specification and / or placed in the system monitoring the CVDT, such as a signal processing system. In either case, if the data set changes in a way that it no longer matches specifications, including parameters, thresholds, tolerances, etc., built into the operating pattern, including those managed by the system monitoring the pattern, one or more response systems can be invoked to take action, declare an event, provide one or more configuration specifications for one or more sensors and / or CVDTs representing those entities, etc., potentially using a decision matrix to provide an effective response to those data set changes.

[0132] The state of the care village digital twin representing those entities can be adapted along with that data, for example, through changes to the configuration of those entities.

[0133] This may include invoking new patterns that represent data from the entities, and / or may include invoking additional care village digital twins into operation, and / or may include adding additional entities to an operating CVDT in any configuration.

[0134] Execution environment

[0135] A Care Village operating environment capable of supporting instantiating a Care Village digital twin specification into an operational CVDT includes a set of general operating system functions such as processing, preemptive scheduling, threading (including single-threading and multithreading), storage, persistence, and repository functions, e.g., a data management system, and other standard functions in the form of libraries and modules. It can also include a set of engines incorporating specific sets of functions, e.g., physics engines, which can be invoked and fed, e.g., via APIs and / or via messaging systems, which may be secure, with datasets from the Care Village digital twin representing a set of devices, sensors, stakeholders, and / or the environment. Such engines can then apply specific operations, such as providing a model of real-world physics to provide outputs to another system that represent real-world physical outcomes. The operating environment can include any arrangement of specialized engines that encompass aspects of the physical world represented by the CVDT, e.g., health engines, stakeholder engines, which may include stakeholders that are organizations, and specific logic and processing can be performed on behalf of organizational stakeholders, CVDT prediction and simulation engines, etc.

[0136] The operating environment may be instantiated in whole or in part, e.g., a subset of functionality may be part of a device incorporating, for example, a set of sensors, and may provide a minimum level of support for a care village digital twin representing at least one of the sensors. In this example, the operating environment may include communications capabilities that allow data from the care village digital twin and / or sensors to be securely provided to another CVDT, including, for example, a device-based CVDT as well as a set of other CVDTs. For example, such a care village digital twin may incorporate the CVDT from the device and a further set of sensors monitoring PUM in the environment.

[0137] The operational support environment can be distributed, including edge computing embodiments, and can include the use of cloud-based systems, including, for example, containers, serverless, and other similar cloud-based scalable deployment embodiments.

[0138] The operational support environment can include a Care Village digital twin engine, which provides a set of capabilities supporting predictions, simulations, and other machine learning-based techniques that may be based on specifications and inputs from the operational CVDT. This engine can be invoked by one or more systems, such as a monitoring system, to create one or more Care Village digital twins that replicate the operational CVDT with different inputs, configuration specifications, and resulting outputs. These variations can then be considered by additional systems to establish potential trends, vectors, and / or other potential outcomes that may affect the wellness of the PUMs represented in the operational CVDT. Each of these derived CVDTs, including one or more variants from the operational Care Village digital twin, can be configured to run at an accelerated rate to determine outcomes based on changes to the inputs. These results can then be compared with the outputs of other derived CVDTs with different inputs and with direct copies of the original operational CVDT to determine a set of possible outcomes, which can then be evaluated to confirm the probability of such outcomes based on the dataset. In some circumstances, the configuration of sensors represented by the operational Care Village digital twin can be altered to more accurately determine whether a particular predicted wellness event has occurred or is likely to occur. For example, the camera may be configured to operate to detect movement within a particular time frame such that a prediction based on a dataset of the operating CVDT and the evaluated results of the predicted CVDT indicates a high likelihood of a wellness event, e.g., that the PUM may experience dizziness when standing up from a seated position, which may lead to a fall.

[0139] This ability to call multiple versions of the operating care village digital twin, including one or more direct copies, supports the prediction and assessment of potential wellness events without intervention of the physical PUM and its environment. This approach can be used to provide necessary resources, including predictive scheduling of those resources, based on the likelihood that the PUM will have a wellness event.

[0140] The dataset created during this process may then be used as part of a corpus for training machine learning and AI systems, and can include outcomes including the occurrence or non-occurrence of wellness events to improve the overall accuracy of predictive techniques.

[0141] The use of multiple care village digital twins can include multiple branches of the CVDT with different inputs leading to different outputs that can be provided to one or more response systems including one or more decision matrices, with the responses evaluated by one or more evaluation systems. These response sets can be evaluated for their potential effectiveness in responding to the wellness of the PUM, for example, using machine learning and / or other automated processes as well as human evaluation, with the goal of determining the optimal response to the situation.

[0142] In this way, consideration of possible alternatives that provide PUMs with outcomes that optimize their wellness and well-being can be invoked, providing a valuable advantage over fixed, rule-based systems that are often ineffective, inflexible, and difficult and decisive to provide optimal responses.

[0143] Based on the behavioral CVDT data, consistent fluctuations are detected, such as when a person experiences momentary dizziness, detected as any head movement, and subsequently leads to a fall or other wellness event. This fluctuation, predicted by further CVDT, is then formalized as a behavioral CVDT pattern. In this way, a range of potential situations that may affect a PUM are captured and persisted so that they can be distributed to other PUMs with similar conditions, becoming part of the set of patterns used in the monitoring process.

[0144] In some embodiments, the operational support environment may include a stakeholder engine that may provide capabilities for interpretation and execution of specifications, e.g., specifications in the form of contracts or other structured formats, such that based on input received by the specification engine and processing of specifications presented to and / or maintained by the engine, the engine may generate output that may include data, further specifications and / or configurations, or other instructions for other operational support environments and / or CVDTs and other entities that interact with such environments.

[0145] The details of the specification depend on the stakeholder, for example, a PUM or a caregiver may have a specification that, in the case of a PUM, expresses their preferences, incentives and / or constraints, and in the case of a caregiver, may have a similar set of specifications, such as, for example, their availability, working hours or other determinants that express their current capacity within the care village.

[0146] In examples where the stakeholder is an organization, the specification may include a contractual relationship between the organization, e.g., an insurance company, and the PUM.

[0147] Such specifications may be in the form of smart contracts, and the relationship between the stakeholder engine, the smart contracts, and the distributed ledger is such that the processing of the specifications is protected, for example using a protected processing environment, to ensure a chain of custody and control such that the processing of such contracts supports immutable recording on the distributed ledger.

[0148] The stakeholder organization engine can be used to simulate potential stakeholder responses based on procedural specifications, for example, procedural specifications held in contracts between parties, including smart contracts, and this data can then be used in one or more response system evaluations to determine optimal outcomes for PUM and / or other counterparty stakeholders.

[0149] Through the provisioning of a physics engine and stakeholder engine and the capabilities of the operating environment, a generic operating environment can enable simulations, such as those that can be invoked by a CVDT engine. This can include single- and multi-party simulations that can simulate a range of planned states and outcomes. This can include a hybrid of actual and simulated outcomes in any configuration. Both actual and simulated outcomes may be based, in whole or in part, on stored datasets originating from other stakeholders and environments that have sufficient similarity to the current simulation. In this way, data from previous situations involving PUMs with similar conditions, HCPs, and behavior patterns in an environment similar to the current situation being simulated can be used to evaluate potential outcomes.

[0150] In some embodiments, the simulation can provide a dataset that is tested for compatibility with one or more specification sets and the CVDT that represents those sets to assess any variability. For example, establishing that a PUM cannot exist in two different locations simultaneously. Further compatibility considerations may be in the form of constraints, such as when a PUM uses a particular drug, and the effects of that drug are specified in the simulation to identify the effects of overdose.

[0151] One aspect of such a simulation is the representation of relationships between entities, including stakeholders. For example, a fixed sensor may only exist in a single location and, as a result, have a set of relationships with other collocated entities.

[0152] Response System

[0153] The Care Village Digital Twin, supported by the execution environment and its engines and modules, can generate datasets that are specifications that are candidates for deployment in an operating CVDT that represents the physical environment, including stakeholders within the physical environment, and / or can be fed directly to sensors, devices, communications and other systems operating in the environment represented by the CVDT.

[0154] In some embodiments, such a data set can be passed to a response system, which includes a set of modules that can respond to and act on the data, and which can include a decision support system, such as a decision matrix.

[0155] The results of the response system may be passed to one or more execution modules that can act to undertake any variations in the configuration of the system and manage any dependencies, scheduling, prioritization, or other processing.

[0156] The execution module can output specifications to an actively operating care village digital twin for deployment within a physical environment, and / or can output specifications to one or more CVDTs to simulate the effects of the output specifications on the actual operating CVDTs and entities represented by the care village digital twin.

[0157] In some embodiments, the response system may include the following modules:

[0158] Communications Module: The communications module provides one or more APIs that can communicate with the CVDTs to enable communication with the CVDTs and / or systems that operate on behalf of and / or in conjunction with those CVDTs. The primary function of the communications system is to send and receive data sets to and from the CVDTs. The communications module may be invoked by the execution modules to transfer data from the execution modules to the CVDTs.

[0159] Executive Mesh: The response system may include an executive capability in the form of an executive mesh, which includes a set of modules that can be configured and operated in any arrangement.

[0160] The Executive Mesh includes logical processes that determine, in whole or in part, which datasets the response system can provide directly to an operational CVDT and / or to the environment represented by that CVDT. The Executive includes a set of modules that can evaluate received datasets and generate outputs. This can include requesting the instantiation of additional CVDTs with different data, and can include state monitoring, so that the output of a CVDT can be provided to any module in any arrangement.

[0161] The Executive Mesh may include an operating environment that supports the processing of Executive Mesh operations, including, for example, temporary and persistent storage, memory, processing units, machine learning systems, and other general operational support systems. In some embodiments, this may include the execution environment described herein.

[0162] Executive mesh operations may use patterns, in part or in whole, which are sets of specifications that include the configuration and / or operation of modules managed by the executive. For example, as part of a pattern, an executive may evaluate an incoming dataset for one or more CVDTs through a comparison with an existing dataset, and based on the results of that comparison, execute a set of configurations and instructions to modules managed by that executive.

[0163] In some embodiments, these modules include:

[0164] decision matrix.

[0165] The decision matrix, in some embodiments, may be embodied as a graph system, lattice, or other formalized decision structure. For example, a multidimensional lattice may be used to select the appropriate data set to be passed from the decision matrix to another module. The decision matrix may embody one or more patterns of results so that traversal of the decision matrix yields consistent results in light of the input data. In some cases, these deterministic results may be modified as more data becomes available, for example, when additional CVDT of other entities, such as sensors, become available.

[0166] Game Theory Module (GTM)

[0167] A game theory module (GTM) can use a set of games to determine likely appropriate outcomes for an incoming dataset to generate results that can be passed on to one or more modules.

[0168] In some embodiments, these games may be consistent with other care village games used to identify misaligned incentives, for example. The GTM may include games identified through observation and evaluation of the actions of one or more stakeholders within the care village.

[0169] The GTM, under the direction of the Executive, can operate with other system modules to determine appropriate games to be deployed and the associated hierarchy and selection of such games, which can include games deployed in one or more CVDTs, including those instantiated by the Executive Mesh, which can include selections to be deployed for one or more machine learning techniques, either for training and / or operational deployment.

[0170] The Executive Mesh can invoke one or more games deployed in any arrangement for different situations and interactions, representing interactions between stakeholders, systems, devices, sensors, and other care village entities, which can include cooperative and non-cooperative games, regular and extensible games, simultaneous and sequential move games, fixed calculation, zero-sum and non-zero-sum games, and symmetric and asymmetric games.

[0171] Contract Review Module

[0172] In some embodiments, there may be contractual agreements, including smart contracts employing program logic, expressed as, for example, specifications. These specifications may be evaluated, for example, by a matching and comparison system. This evaluation of the contract under consideration may determine an appropriate data set that may be provided to one or more other modules.

[0173] In some embodiments, a contract can include a set of conditions for the provision of a service, product, or interaction, and the contract can represent predicates that are required before an event or action can occur. The Executive Mesh can have specific contract specifications that determine the operation of the Care Village system. These specifications can be arranged within a hierarchical or priority framework such that if the conditions represented by data from a set of CVDTs represent specifically identified conditions, the Executive Mesh, through one or more Executive Modules, can operate to take action in response to those specific conditions. For example, this may be the case if a PUM experiences a life-threatening event, and therefore the Executive Mesh contacts 911.

[0174] Incentive Evaluation Module

[0175] In some embodiments, there may be a set of incentives declared by each of the stakeholders and / or calculated by the system, which may be used in whole or in part to determine weights or other values ​​for sets of data and / or may be represented as sets of data that may be provided to one or more other modules.

[0176] In some circumstances, incentives may be used to modify one or more CVDT configurations to allow executives to obtain additional data sets for executive processing.

[0177] Risk Assessment Module

[0178] In some embodiments, there may be a risk assessment module that has a set of patterns expressed as a specification that represents the risk posed to a stakeholder in their environment. This may include, for example, data based on behavioral patterns of HCPs and / or PUMs. The data set created by this module may be provided to one or more other modules.

[0179] For example, the risk assessment module may include consideration of a range of specifications, such as stakeholder well-being, economics, contractual commitments, service and / or product availability, etc. In some embodiments, there may be conflicting specifications from different stakeholders, where the Executive Mesh may reconcile and / or evaluate the output of such specifications within one or more CVDTs instantiated for that purpose.

[0180] This can include new models for payment, such as usage-based insurance.

[0181] In some embodiments, these modules of the executive mesh can be arranged in a matrix such that each module can provide input to any other module and each module can receive output from any other module. The executive can then use any of the modules to select an appropriate data set to be communicated to one or more execution modules.

[0182] Each of these modules can be invoked by an execution module to provide it and / or other modules with one or more data sets, which can then pass the resulting data sets to one or more execution modules for onward transmission to one or more endpoints, using either fixed or variable logic.

[0183] The executive module communicates data to the appropriate endpoint and manages the state of that endpoint, including any dependencies. The communication includes acknowledgment capabilities, so that although the communication may be asynchronous, the state of the endpoint is maintained by the executive module. This state can be reported back to the executive module to maintain the overall state of the system.

[0184] One aspect of the execution module is its ability to simultaneously support multiple, potentially conflicting datasets. These datasets can be compared to ascertain the scope of the dataset sent to the execution module, within any constraints of the execution environment, e.g., a physics engine. For example, this can include datasets that configure sensors in the environment to acquire additional datasets that may support or conflict with the dataset under consideration.

[0185] This evaluation may include the use of machine learning techniques such as deep learning, neural networks, regression modeling, etc. The executive may generate a set of candidate data and then, in some embodiments, provide such data to one of the executive's modules; for example, this data may be provided as input to a game theory module, an incentive module, and / or a risk assessment module, each of which may then generate further data sets for evaluation by the executive module.

[0186] A further aspect is the use of a simulation system using the Care Village digital twin, where such simulations can provide datasets representing interventions. For example, these can be configured as CVDT-sponsored, proposed, initiated interventions, which can result in predictions of outcomes based on different interventions. In some embodiments, there can be configurable interventions based on these predictions that can be applied to operate the CVDT.

[0187] The intervention may be passed to a response system, where, based on the action of the executive, the intervention may be passed to an execution module for onward transmission to the operating CVDT and / or the environment represented by that CVDT. This may include creating a set of possible interventions by invoking one or more CVDTs to identify appropriate actions. For example, this may include changing the configuration of a CVDT representing an HVAC system in an environment to evaluate the consequences for the environment and stakeholders within the environment.

[0188] In some embodiments, systems such as response systems, care village digital twin management systems, and / or other care village systems can evaluate a set of cost-benefit, cost-value, or other action and outcome relationships. This can include different perspectives, such as wellness, stress, ease or effort expenditure, economics or finances, from the perspective of one or more stakeholders. This can include evaluation through the use of multiple CVDTs of state changes and their actual and / or potential outcomes based on these evaluations. This can result in conflicting potential configurations or other changes to operational CVDTs, which can then be reviewed by the care village system, including through the use of machine learning and / or human intervention.

[0189] Care Village Digital Twin and Vector Token

[0190] One challenge with a set of sensors potentially operating on a 24 / 7 / 365 basis is the ability of those sensors to generate a set of data that may be continuous. This is exacerbated by the presence of multiple sensors, such as sensors in a multi-sensor device, which in many situations can generate a total volume of data that may require significant processing power to evaluate. One approach to this data stream is to use periodic sampling to reduce the processing burden. Additional strategies deployed to manage this data flow include the use of evaluation of data feeds at the edge of the network to identify events that can trigger actions that can trigger a data stream. Each of these approaches has various limitations, including battery life, missing important data, dependence on the device's capabilities for processing, lack of precision or granularity, privacy and security, etc. In some situations, periodic approaches are often used, where data is sampled on a fixed periodic basis, determined as appropriate for the situation.

[0191] Each of these approaches has some limitations, notably the availability of the raw data feed to another device and / or system, or a consolidated version of that data being available to another device and / or system.

[0192] The use of edge processing, such as image recognition, is generally constrained by the processing power of the device at the edge; therefore, if raw data is made available to a supporting system with processing power and significantly more capabilities, the extent to which that data can be evaluated can be significantly enhanced, e.g., time of evaluation, granularity, comparisons, trigger identification, integration of additional data, etc.

[0193] To address this issue of deploying appropriate processing and evaluation techniques when needed, each of the edge devices may be enabled and / or configured to use vector simplifications of its sensor and / or device states.

[0194] In some embodiments, this may include a set of vectors representing interactions between entities such as sensors and devices, and such a set may be represented by one or more tokens in any arrangement.

[0195] The vectors may be represented as tokens to enable efficient distribution, management and use of tokens by at least one system element including signal processing, devices and / or sensors, repositories and / or other care village system elements.

[0196] A vector is a simplification of the data represented by the tokens; such a vector indicates the trajectory of the data set with respect to the resting state of the sensor.

[0197] In some embodiments, the dynamics of motion patterns, represented as vectors, e.g., represented as tokens generated by sensors, can be evaluated within dynamic threshold boundaries. For example, such boundaries can be used in determining which patterns (including sets thereof) are active and / or should be active or inactive. Vector analysis can use support vector machines to establish associated hyperplanes that represent at least one decision boundary. These boundaries can be adaptive and responsive to the set of vectors under evaluation.

[0198] In some embodiments, a care village digital twin may have a set of vectors that represent the trajectories of its CVDT, particularly simulated or actual sensor data sets. These vectors may be passed as cryptographically protected tokens to one or more other authorized and authenticated services. Such tokens may incorporate identifying characteristics of sensors, devices, environments, and one or more CVDTs that incorporate or reference them, such that this identification can provide sufficient data regarding actions taken by one or more systems on those entities.

[0199] In some embodiments, there may be one or more vector evaluation systems, such as support vector machines, operating as part of the execution support environment. For example, this may include evaluation of vectors by one or more monitoring systems, which may require access to the data in the token and / or the configuration of at least one sensor providing the data.

[0200] For example, in some embodiments, a signal processing system may be configured to receive multiple inputs from multiple sources (devices / sensors) and evaluate combinations of vectors from the multiple sensors / devices, which may be represented as patterns. These patterns may then be represented by further vectors, which are expressed as tokens for further communication and evaluation.

[0201] These relationships of vectors and patterns can provide lead indicators of changes in the state of entities including sensors, devices, environments, stakeholders, etc., allowing for a simplified evaluation process and representation of patterns and behavioral states. This can include configurations of multiple sensors to enhance data accuracy by evaluating multiple sensor data sets to confirm and / or validate the accuracy of these data sets. For example, graphs and other node arrangements may be used for both vectors and data sets in any arrangement.

[0202] In some embodiments, an entity such as a sensor or device that generates raw data may incorporate the ability to then represent that data as a token that incorporates one or more vectors.

[0203] The above description of the embodiments is provided to enable any person skilled in the art to practice the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and features disclosed herein.

Claims

1. A system for monitoring a care recipient by a stakeholder, comprising: a transceiver configured to receive a plurality of tokens from a plurality of environmental sensors configured to monitor the care recipient, each of the tokens comprising at least in part a sensed dataset representative of a behavior of the care recipient in an environment, each of the behaviors being represented by a set of multi-dimensional features forming part of a healthcare profile of the care recipient, and the tokens being encrypted using an encryption key; a non-transitory computer-readable storage medium configured to store a digital twin of the care recipient, the digital twin including a dynamic tokenized representation of stationary behavior of the care recipient in the environment; and at least one processor configured to analyze the digital twin of the care recipient without analyzing the plurality of tokens received from the plurality of environmental sensors until the at least one processor receives a token indicating that a wellness or care event has occurred; When the wellness event or care event occurs, the processor decrypting the plurality of tokens using the encryption key; analyzing the plurality of tokens; changing the state of the plurality of environmental sensors or notifying the stakeholder; The system is configured to:

2. The system of claim 1 , wherein the at least one processor is further configured to identify potential future states of the care recipient by analyzing the digital twin.

3. The system of claim 2 , wherein the at least one processor is further configured to identify potential future states of the care recipient by analyzing the digital twin and the plurality of tokens.

4. The system of claim 3 , wherein the processor uses machine learning to analyze the digital twin and the plurality of tokens.

5. The system of claim 4 , wherein the encryption key is unique to the care recipient.

6. The system of claim 5 , wherein changing the state of the plurality of environmental sensors changes the monitoring focus of the environmental sensors.

7. The system of claim 6 , wherein the monitoring focus increases the fidelity or granularity of the environmental sensors.

8. The system of claim 7 , wherein the detected data set is from a respiration sensor or a heart rate sensor.

9. The system of claim 1 , wherein the transceiver is configured to transmit the token to a second care system.

10. The system of claim 9 , wherein the second care system is determined based in part on the detection data set.

11. The system of claim 10 , wherein the second care system is determined based in part on the at least one stakeholder's relationship to the care recipient.

12. The system of claim 11 , wherein the at least one stakeholder is determined by data related to the at least one stakeholder's relationship with the care recipient.

13. A method for monitoring a care recipient by a stakeholder, comprising: receiving, via a transceiver, a plurality of tokens from a plurality of environmental sensors configured to monitor the care recipient; Including, each of said tokens comprises at least in part a detection dataset representative of the care recipient's behavior in an environment, each of said behaviors being represented by a multi-dimensional feature set forming part of the care recipient's healthcare profile, said tokens being encrypted using an encryption key; Furthermore, the method comprises: storing the digital twin of the care recipient in a non-transitory computer-readable storage medium; Including, the digital twin comprises a dynamic tokenized representation of the care recipient's static behavior in the environment; Furthermore, the method comprises: analyzing, via the at least one processor, the digital twin of the care recipient instead of analyzing the plurality of tokens received from the plurality of environmental sensors until the at least one processor receives a token indicating that a wellness event or a care event has occurred; Including, When the wellness event or care event occurs, the processor: decrypting the plurality of tokens using the encryption key; analyzing the plurality of tokens; changing the state of the plurality of environmental sensors or notifying the stakeholder; The method is characterized in that it is configured to:

14. 14. The method of claim 13, wherein the at least one processor is further configured to identify potential future states of the care recipient by analyzing the digital twin.

15. 15. The method of claim 14, wherein the at least one processor is further configured to identify potential future states of the care recipient by analyzing the digital twin and the plurality of tokens.

16. 16. The method of claim 15, wherein the processor uses machine learning to analyze the digital twin and the plurality of tokens.

17. The method of claim 16, wherein the encryption key is unique to the care recipient.

18. The method of claim 17 , further comprising changing the monitoring focus of the environmental sensors by changing the states of the plurality of environmental sensors.

19. 1. A non-transitory computer-readable storage medium encoded with data and instructions, comprising: The instructions, when executed by a processor, receiving, via a transceiver, a plurality of tokens from a plurality of environmental sensors configured to monitor the care recipient; on a computing device, each of said tokens comprises at least in part a detection dataset representative of the care recipient's behavior in an environment, each of said behaviors being represented by a multi-dimensional feature set forming part of the care recipient's healthcare profile, said tokens being encrypted using an encryption key; Further, the instructions, when executed by the processor, storing the digital twin of the care recipient in a non-transitory computer-readable storage medium; on the computing device, the digital twin comprises a dynamic tokenized representation of the care recipient's static behavior in the environment; Further, the instructions, when executed by the processor, analyzing, via the at least one processor, the digital twin of the care recipient instead of analyzing the plurality of tokens received from the plurality of environmental sensors until the at least one processor receives a token indicating that a wellness event or a care event has occurred; on the computing device, When the wellness event or care event occurs, the processor decrypting the plurality of tokens using the encryption key; analyzing the plurality of tokens; changing the state of the plurality of environmental sensors or notifying the stakeholder; A non-transitory computer-readable storage medium configured to:

20. 20. The non-transitory computer-readable storage medium of claim 19, wherein the at least one processor is further configured to identify potential future states of the care recipient by analyzing the digital twin.

Images