Integrated multi-modal computing for personal health navigation

Abstract

A method (300) and apparatus (200) for personal health navigation. The method (300) includes a processor determining a personal health state space comprising a set of connected biological states of an individual (302); the processor determining a region of interest within the personal health state space for the individual, wherein the region of interest is defined by a target state relative to a current state of the individual, the target state being associated with a personal health goal of the individual (304); the processor determining a route comprising the current state, the target state, and an intermediate state within the personal health state space, the intermediate state being closer in distance to the target state than the current state (306); and the processor providing health instructions to the individual indicating a recommended action, the recommended action being based on a connection between the current state and the intermediate state, wherein the recommended action is selected to guide the individual to transition to the intermediate state (308).

Description

[0001] Cross-references to related applications

[0002] This application is the Chinese national phase of PCT international application No. PCT / CN2022 / 098829, filed on June 15, 2022, which claims priority and benefits to U.S. provisional patent application No. 63 / 212,542, filed on June 18, 2021, and U.S. formal patent application No. 17 / 830,571, filed on June 2, 2022, the entire disclosure of which is incorporated herein by reference. Technical Field

[0003] This application relates to wearable computing, and more particularly to integrated multimodal computing for personal health navigation. Background Technology

[0004] With the help of modern technology, we are able to continuously sense and calculate health-related data in many ways and use this information to improve health.

[0005] Current research on health recommendation systems typically takes a fully automated approach or combines human expertise with computer assistance for decision-making. Automated systems for health recommendations are functionally limited, primarily used to maintain simple homeostasis, such as monitoring glucose with an insulin pump. Human experts can personally or via telecommunications provide recommendations on individual health status and inputs to decision support systems. These forms of guidance can be real-time and synchronous, or asynchronous through various forms of communication and multimedia. Summary of the Invention

[0006] This disclosure generally relates to wearable computing, and more particularly to integrated multimodal computing for personal health navigation. Aspects of this disclosure include, for example, methods, apparatuses, and non-transitory computer-readable media for personal health navigation.

[0007] One aspect of the disclosed implementation is a method for personal health navigation. The method includes: a processor determining a personal health state space, the personal health state space including a set of connected biological states of an individual; the processor determining a region of interest (ROI) within the personal health state space for the individual, wherein the ROI is defined by a target state relative to the individual's current state, the target state being associated with the individual's personal health goals; the processor determining a route including the current state, the target state, and intermediate states within the personal health state space, the intermediate states being closer to the target state in distance than the current state; and the processor providing the individual with health instructions instructing recommended actions based on the connection between the current state and the intermediate states, wherein the recommended actions are selected to guide the individual to transition to the intermediate state.

[0008] In some implementations, the method may further include one or more of the following features: when it is determined that the individual has completed the recommended action, the current state transitions to the intermediate state; when it is determined that the individual has taken an action different from the recommended action, causing the current state to transition to another state different from the intermediate state, a route for the individual is recalculated based on the other state and the target state; the region of interest is semantically labeled with domain knowledge associated with the personal health goal; input indicating the personal health goal is received from the individual; and the processor decomposes the personal health goal into sub-goals represented as nodes in the region of interest; the processor determines a state transition network including edges, each edge representing a state transition based on the individual's... The associated personal model transitions from a first state to a second state; the processor determines a route including the current state, the target state, and the intermediate states, further comprising: determining a route within the state transition network for an individual associated with the personal health goal from the current state to the target state, wherein the route includes an optimal subset of states between the current state and the target state and corresponding edges; the health instruction indicating the recommended action includes at least one of lifestyle events and medical events; the current state is estimated based on physiological measurements of the individual from a wearable device; the personal health state space includes a subset of the individual's possible biological states within a multidimensional overall health state space, the subset of possible biological states being determined based on characteristics specific to the individual.

[0009] Another aspect of the disclosed embodiments is an apparatus for personal health navigation. The apparatus includes: a non-transitory memory; and a processor configured to execute instructions stored in the non-transitory memory to: determine a personal health state space, the personal health state space including a set of connected biological states of an individual; determine a region of interest for the individual within the personal health state space, wherein the region of interest is defined by a target state relative to the individual's current state, the target state being associated with the individual's personal health goals; determine a route including the current state, the target state, and intermediate states within the personal health state space, the intermediate states being closer to the target state in distance than the current state; and provide the individual with health instructions instructing recommended actions based on the connection between the current state and the intermediate states, wherein the recommended actions are selected to guide the individual to transition to the intermediate state.

[0010] In some embodiments, the apparatus may further include one or more of the following features: when it is determined that the individual has completed the recommended action, the current state transitions to the intermediate state; when it is determined that the individual has taken an action different from the recommended action, causing the current state to transition to another state different from the intermediate state, a route for the individual is recalculated based on the other state and the target state; the region of interest is semantically labeled with domain knowledge associated with the personal health goal; input indicating the personal health goal is received from the individual; and the processor decomposes the personal health goal into sub-goals represented as nodes in the region of interest; the processor determines a state transition network including edges, each edge representing a state transition based on the relationship between the individual and the target state. The associated personal model transitions from a first state to a second state; the processor determines a route including the current state, the target state, and the intermediate states, further comprising: determining a route within the state transition network for an individual associated with the personal health goal from the current state to the target state, wherein the route includes an optimal subset of states between the current state and the target state and corresponding edges; the health instruction indicating the recommended action includes at least one of lifestyle events and medical events; the current state is estimated based on physiological measurements of the individual from a wearable device; the personal health state space includes a subset of the individual's possible biological states within a multidimensional overall health state space, the subset of possible biological states being determined based on characteristics specific to the individual.

[0011] Another aspect of the disclosed embodiments is a non-transitory computer-readable storage medium configured to store a computer program for personal health navigation. The computer program includes instructions executable by a processor to: determine a personal health state space, the personal health state space comprising a set of connected biological states of an individual; determine a region of interest for the individual within the personal health state space, wherein the region of interest is defined by a target state relative to the individual's current state, the target state being associated with the individual's personal health goals; determine a route including the current state, the target state, and intermediate states within the personal health state space, the intermediate states being closer to the target state in distance than the current state; and provide the individual with health instructions instructing recommended actions based on the connection between the current state and the intermediate states, wherein the recommended actions are selected to guide the individual to transition to the intermediate state.

[0012] In some embodiments, the non-transitory computer-readable storage medium may further include one or more of the following features: when it is determined that the individual has completed the recommended action, the current state transitions to the intermediate state; when it is determined that the individual has taken an action different from the recommended action, causing the current state to transition to another state different from the intermediate state, a route for the individual is recalculated based on the other state and the target state; the region of interest is semantically labeled with domain knowledge associated with the personal health goal; input indicating the personal health goal is received from the individual; and the processor decomposes the personal health goal into sub-goals represented as nodes in the region of interest; the processor determines a state transition network including edges, each edge representing a state transition based on... The individual's associated personal model transitions from a first state to a second state; the processor determines a route including the current state, the target state, and the intermediate states, further comprising: determining a route from the current state to the target state within the state transition network for an individual associated with the personal health goal, wherein the route includes an optimal subset of states between the current state and the target state and corresponding edges; the health instruction indicating the recommended action includes at least one of lifestyle events and medical events; the current state is estimated based on physiological measurements of the individual from a wearable device; the personal health state space includes a subset of the individual's possible biological states within a multidimensional overall health state space, the subset of possible biological states being determined based on characteristics specific to the individual. Attached Figure Description

[0013] Figure 1This is a block diagram illustrating an example of a Personal Health Navigation (PHN) according to one embodiment.

[0014] Figure 2 This is a block diagram of an example computing device that can be used to implement the functions of PHN according to embodiments of the present disclosure.

[0015] Figure 3 This is a diagram illustrating an exemplary process of a PHN according to an embodiment of the present disclosure.

[0016] Figure 4 This is a flowchart illustrating an exemplary system framework for PHN.

[0017] Figure 5A This is an example diagram illustrating PHN in a cardiovascular health environment.

[0018] Figure 5B This is an example graph illustrating multiple user trends for PHN based on experimental data collected from the cardiovascular health environment.

[0019] Figure 5C An exemplary flowchart of a daily exercise guidance algorithm for PHN in a cardiovascular health environment is shown. Detailed Implementation

[0020] As the mobile healthcare market continues to grow, devices and systems using wearable technology to aid in fitness or health assessments have become widely available. Wearable devices such as smartwatches and fitness trackers are already being used for individual health monitoring and fitness tracking. Wearable devices can be used in various applications, such as step counting, activity tracking, or calorie burn estimation. Current wearable devices primarily display a stream of data back to the user without providing explanations or actionable information. This makes these devices less useful and relevant for people to lead healthy lives.

[0021] Good health provides the foundation for a happy and fulfilling life. It is well known that an individual's health trajectory is influenced by choices made at every moment, such as lifestyle or medical decisions. With the advent of modern sensing technologies, individuals possess more data and information about themselves than at any time in history. Translating this collected data into real-world improvements in individual health remains challenging. Furthermore, providing people with better quality of health without increasing costs is also key to enabling societal resources to drive progress in other areas.

[0022] To make this rich data actionable and relevant to maintaining personal health, methods, apparatus, and systems for Personal Health Navigation (PHN) have been proposed. PHN enables individuals to achieve their individual health goals by, for example, processing multimodal data streams, estimating current health status, calculating the optimal route through intermediate states using a given personal model, and providing guidance on actionable inputs to help individuals achieve their individual health goals.

[0023] According to embodiments of this disclosure, wearable data measured from an individual can be used to guide the individual to a desired healthy lifestyle state in a personalized, adaptive, and contextualized manner, so that the individual can exercise in a way that improves his or her health level (e.g., cardiorespiratory health).

[0024] According to embodiments of this disclosure, PHN can be equipped with cybernetics control and long-term intelligent planning capabilities.

[0025] Exemplary embodiments of this disclosure will now be described with reference to the accompanying drawings. Unless otherwise stated, the same reference numerals in the drawings set forth in the following description represent the same or similar elements. The embodiments set forth in the following description do not represent all embodiments or examples consistent with this disclosure; rather, they are merely examples of apparatuses and methods according to some aspects of this disclosure as claimed.

[0026] It should be noted that the application and implementation of this disclosure are not limited to these examples, and that alternatives, variations or modifications of the implementation of this disclosure can be made for any computing environment.

[0027] Figure 1 This is a block diagram illustrating an example of a Personal Health Navigation (PHN) according to one embodiment. Figure 1 The concept of Personal Health Navigation (PHN) is illustrated with an example. In this example, the PHN guides an individual (also referred to here as a "user") to achieve their personal health goals. Personal health goals can be computed and defined based on regions of interest (ROIs) within a multidimensional space, where each dimension of the multidimensional space represents a different component (or aspect) of personal health. These different components of personal health can be defined, for example, by biomedical knowledge. These dimensions are transformed into discrete biological states (also referred to as "nodes," "health states," or "states"), such as... Figure 1 As shown, this forms the General Health State Space (GHSS)101, which serves as the base graph for the PHN. The states are then connected by input knowledge, a process that can be knowledge-driven during cold starts and iteratively improved through data-driven analytics.

[0028] For a specific user such as the individual described above, due to his or her biological uniqueness, the individual can only access a subset of GHSS101. This subset is called the Personal Health State Space (PHSS)102, which includes all possible states of the individual given personal circumstances. Figure 1 As shown, PHSS 102 is displayed with thick lines, which represent the boundaries within PHSS 101. PHSS 102 can be marked with different ROIs, such as... Figure 1 As shown in ROIs 112 and 114, an individual can choose one of them as the target. PHSS 102 also includes edges between states, where each edge represents knowledge (also referred to here as "input") of the actions an individual takes to perform state transitions.

[0029] Once PHSS 102 is determined, Health Status Estimate (HSE) 104 is used to determine the individual's current status 110 on PHSS 102. Current status 110 represents the individual's current health status. Once the individual provides goals, such as... Figure 1 As illustrated in the example of route planning and selection 106, the goal is mapped to ROI 112, and the individual is offered various routes from the current state 110 to the goal state (represented by ROI 112 in this example) to choose from. Once a route is selected, the system implementing this example transitions to cybernetics control 108, where control mechanisms are implemented to ensure a smooth transition to the next adjacent state along the selected route. Cybernetics control 108 guides the individual to execute inputs (actions) to reach the next adjacent state on the selected route. The inputs / actions executed by the individual include inputs / actions suggested by the system and / or inputs / actions not suggested by the system, which are measured and fed into a new estimate of the individual's current state 110, and controlled using cybernetics control 108 to stay on track. The updated current state 110 is then used to update the next suggested action. A cycle, including route planning and selection 106 (for replanning when the current state 110 is updated) and cybernetics control 108, is repeatedly executed, causing the individual's health state to move closer to the target state until the individual reaches (and in some cases remains) the target state (ROI 112 in this example). Upon reaching the destination, the system can continue to ensure that the deviation from the target state is minimized. Further details, examples, and implementation methods are described below in conjunction with the remaining figures.

[0030] Figure 2This is a block diagram of an example of a computing device 200 that can be used to implement personal health navigation functions according to embodiments of the present disclosure. The computing device 200 may be in the form of a computing system including multiple computing devices, or in the form of a single computing device, such as a mobile phone, tablet computer, laptop computer, notebook computer, desktop computer, wearable device, smart scale, etc.

[0031] The CPU 202 in computing device 200 may be a central processing unit. Alternatively, the CPU 202 may be any other type of device or multiple devices capable of manipulating or processing existing or later-developed information. Although the disclosed embodiments may be implemented with a single processor (e.g., CPU 202) as shown, using more than one processor may provide advantages in speed and efficiency.

[0032] In one embodiment, the memory 204 in the computing device 200 may be a read-only memory (ROM) device or a random access memory (RAM) device. Any other suitable type of storage device may be used as memory 204. Memory 204 may include code and data 206 accessed by the CPU 202 using bus 212. Memory 204 may also include an operating system 208 and an application 210, which includes at least one program that allows the CPU 202 to perform the methods described herein. For example, application 210 may include applications 1 to N, which may also include applications incorporating some or all of the personal health navigation features. The computing device 200 may also include secondary storage 214, which may be, for example, a removable memory card used with the computing device 200.

[0033] The computing device 200 may also include one or more output devices, such as a display 218. In one example, the display 218 may be a touch-sensitive display, which combines a display with a touch-sensitive element operable to sense touch input. The display 218 may be coupled to the CPU 202 via a bus 212. In addition to or as an alternative to the display 218, other output devices may be provided that allow the user to program or otherwise use the computing device 200. When the output device is a display or includes a display, the display may be implemented in various ways, including a liquid crystal display (LCD), a cathode ray tube (CRT) display, or a light-emitting diode (LED) display, such as an organic LED (OLED) display.

[0034] The computing device 200 may include one or more sensors 220 capable of measuring or communicating with one or more types of wearable data from a user. Sensors may include, for example, cameras, microphones, accelerometers, gyroscopes, inertial measurement unit (IMU) sensors, magnetometers, PPG (photoplethysmography) or ECG (electrocardiogram) heart rate sensors, EKG (electrocardiogram) sensors, light sensors, SpO2 (blood oxygen saturation) sensors, GPS (Global Positioning System), cameras, dot projectors, temperature sensors, humidity sensors, barometers, etc. Sensors may be located in, for example, smart earbuds, watches, wristbands or mobile phones, smart scales, laptops or TVs, home IoT (Internet of Things) devices, connected cars, etc.

[0035] The computing device 200 may include or communicate with a communication component 222, which may be a hardware or software component configured to transmit data to one or more external devices (e.g., another computing device or wearable device). The communication component may operate via a wired or wireless communication connection, such as a wireless network connection, Bluetooth connection, infrared connection, NFC connection, cellular network connection, radio frequency connection, or any combination thereof. In some embodiments, the communication component includes an active communication interface, such as a modem, transceiver, etc. In some embodiments, the communication component includes a passive communication interface, such as a Quick Response (QR) code, Bluetooth identifier, radio frequency identification (RFID) tag, near field communication (NFC) tag, etc. In some embodiments, the communication component may use audio signals as input and output, such as ultrasonic signals or audio signals via an audio jack. Implementations of the communication component may include a single component, each of the aforementioned types of components, or any combination of the aforementioned components.

[0036] although Figure 2The CPU 202 and memory 204 in computing device 200 are depicted, but other configurations can be utilized. The operation of CPU 202 can be distributed across multiple machines (each machine having one or more processors), which can be directly coupled or coupled across a local area network or other network. Memory 204 can be distributed across multiple machines, such as network-based memory or memory across multiple machines performing the operations of computing device 200. Although depicted herein as a single bus, bus 212 of computing device 200 can consist of multiple buses. Furthermore, auxiliary memory 214 can be directly coupled to other components of computing device 200, or can be accessed via a network, and can include a single integrated unit such as a memory card or multiple units such as multiple memory cards. Therefore, computing device 200 can be implemented in a wide variety of configurations.

[0037] Computing device 200 Figure 2 The examples shown herein are for illustrative purposes only and are not limited to any particular type or number of systems disclosed herein. Computing device 200 can be implemented by any configuration of one or more computers, such as microcomputers, mainframes, supercomputers, general-purpose computers, special-purpose computers, integrated computers, database computers, remote server computers, personal computers, laptop computers, tablet computers, cellular phones, personal data assistants (PDAs), wearable computing devices (e.g., smartwatches), or computing services provided by computing service providers (e.g., websites or cloud service providers). In some embodiments, certain operations described herein may be performed by multiple sets of computers (e.g., server computers) located in different geographical locations and may or may not communicate with each other via means such as a network. While some operations may be shared by multiple computers, in some embodiments, different computers may be assigned different operations.

[0038] Figure 3 This is a diagram illustrating an exemplary process 300 of personal health navigation according to embodiments of the present disclosure. In some embodiments, some or all of process 300 may be implemented in, for example... Figure 2 This is implemented in a device or apparatus such as the computing device 200 shown. In some embodiments, portions of process 300 may be executed by instructions executable on the computing device 200 and / or one or more other devices (e.g., wearable devices or mobile phones). In some embodiments, the computing device 200 itself may be a mobile phone. In other embodiments, the computing device 200 may be a wearable device, such as a smartwatch or a cloud server.

[0039] In operation 302, a Personal Health State Space (PHSS) is defined for the individual. The PHSS comprises a set of connected biological states of the individual. Biological states are also referred to as nodes or health states in this paper.

[0040] An individual's health status space can be determined from, for example, the overall health status space (GHSS). The personal health status space (PHSS) is a subset of the overall health status space. For example... Figure 1 The General Health State Space (GHSS) discussed here encompasses all possible health states a human can be in. For example, in the cardiovascular health scenario, the GHSS includes all possible measurements of a person's cardiovascular state. Measurements can include, for example, heart rate (such as PPG, EGK, or ECG measurements) or maximum oxygen uptake (VO2Max). Measurements can also include any components related to fitness, cardiovascular disease, and other medical events. For instance, the GHSS can be a multidimensional health state space with more than one type of measurement as components. The following section will combine... Figures 5A to 5C This paper discusses examples of such a multidimensional health state space. Based on an individual's specified goals or areas of interest, a set of corresponding dimensions related to those goals or areas of interest can be identified.

[0041] As discussed, when the GHSS is applied to an individual, the PHSS is determined, which includes a subset of the individual's possible biological states within the GHSS. In other words, the PHSS includes all possibilities for an individual given a particular situation. Based on individual-specific characteristics, the subset of an individual's possible biological states may include, for example, the biological states that the individual can reach. For example, the individual-specific characteristics used to generate the PHSS may include features relating to at least one of individual-specific genetics and demographics (e.g., sex, age), which can be used to provide boundary thresholds for determining the PHSS within the GHSS.

[0042] Within the PHSS, connections, also known as edges, can be established between states. Each edge in the PHSS represents a transition from one individual state to another. The edges between the first and second states include knowledge of the actionable inputs that can cause the state transition between them. For example, when a biological state includes a cardiovascular component (also called a "heart state"), it can be determined which actionable inputs will transition the heart state. State transitions consider the various potential actionable inputs that will lead to the next state. For example, exercise, medication, experiencing stress, or nutrition (e.g., eating a high-sodium diet) may individually or in combination cause a state transition in the PHSS. For an individual, the connection between any two nodes within their PHSS is also unique. For example, for individuals A and B, the actions required to improve heart health parameters or gain a pound of muscle may differ between A and B.

[0043] In some implementations, the state transition network of PHSS is determined based on an individual model associated with each individual. The state transition network includes edges, also referred to as connections in the description above. For a state transition network, an edge represents a transition from a first state to a second state based on the individual model associated with the individual. Individual models can use various levels of specificity; for example, multiple individuals can be grouped into subgroups if insufficient data is available at the individual level. There can be multiple individual models associated with an individual. For example, a set of individual models for an individual as a layer can include (non-comprehensive) models such as basic physiological knowledge, multi-model data streams, demographic patterns, clinical medical research, geographic information systems, etc.

[0044] As discussed, various personal models can be stratified for an individual as a single user. For example, image models can include facial recognition, skin analysis, or medical imaging such as CT (Computed Tomography) / X-ray / MRI (Magnetic Resonance Imaging). Audio models can include speech analysis, speech recognition, or music entertainment models. Emotion and behavioral models can span multiple modalities to understand how an individual psychologically responds to input in virtual or real-world environments. Personalized Geographic Information Systems (GIS) tell people how context and environment enhance changes in a user to enable location-based service enhancements. Cross-modal models allow the fusion of many different data types related to the individual, such as omics / genetic data, wearable device physiological flows, or medical records. Combinations of these media types include, for example, language analysis, virtual interaction models, or video / AR (Augmented Reality) / VR (Virtual Reality) models. In one example, these personalized models can be integrated through physical interaction based on remote AI monitoring video / AR, where the user's physiological and genetic data is taken into account through real-time 3D analysis to provide feedback or guidance to the user during rehabilitation therapy, gaming experiences, or fitness exercises.

[0045] return Figure 3 State transitions and individual models can be learned through various machine learning techniques. Furthermore, modeling clusters using health states and state transition trajectories, and developing machine learning models based on these clusters, can accelerate learning time and improve personalization.

[0046] The knowledge layers and regions of interest, described in detail below, can be identified in the PHSS associated with the region of interest. The top layer of the PHSS contains knowledge about the relevant health domain, analogous to a physical map described using latitude, longitude, and altitude. Information layers such as roads, oceans, borders, and satellite imagery enable navigation within space, depending on the scenario (e.g., driving requires road and traffic layers). The knowledge layer represents the real world, in which humans can understand their state of interest.

[0047] In operation 304, a region of interest is determined within the individual's personal health state space. The region of interest is defined by a target state relative to the individual's current state. The target state is associated with the individual's personal health goals.

[0048] An individual’s current state can be determined in various ways, including, for example, by estimating it based on an individual’s physiological measurements through wearable devices, by manual input by the individual, or by importing it from an existing physiological profile.

[0049] To determine a precise location within PHSS, up-to-date data from individuals can be used to predict the current state. The current state can be determined, for example, as a location with a range of precision on PHSS. Different applications may require different levels of precision to provide services to individuals as users.

[0050] For example, monitoring cardiovascular health is useful for endurance athletes and heart disease patients. Estimation techniques can be used in many applications, but health applications will require increasingly deeper layers of biological knowledge to define and improve the estimated health status calculated from input data.

[0051] The value of good health to an individual depends largely on how they wish to live. For personal health navigation, individuals can specify one or more personal health goals. Personal health goals can be specified by the individual, for example, including one or more states within a region of interest (ROI). ROIs can also be specified as personal health goals. Examples of ROIs include... Figure 1 The discussion covers ROIs 112 and 114, and more examples will be provided below. Figure 5A The discussion is ongoing.

[0052] ROI is defined based on an individual's area of ​​interest. Therefore, different ROIs or goals are associated with different areas of interest. ROI can also be associated with a multidimensional space, where dimensions represent different components of health as defined by biomedical knowledge.

[0053] Goal decomposition can be used to transform a goal state into (typically short-term) sub-goals. This process involves identifying unique utilities associated with a particular goal.

[0054] ROIs can be semantically labeled using domain knowledge associated with personal health goals. In some implementations, input indicating personal health goals is received from the individual. The personal health goals are then decomposed into sub-goals represented as nodes in the ROI.

[0055] In operation 306, a route is determined within the region of interest. This route includes, for example, the current state, the target state, and intermediate states, where each intermediate state comprises one or more intermediate states within the region of interest. An intermediate state is closer to the target state than the current state.

[0056] In some implementations, for an individual associated with a personal health goal, a path from the current state to the target state can be determined in a state transition network, and the path includes an optimal subset of states between the current state and the target state and the corresponding edges.

[0057] After measuring, estimating, modeling, and receiving an individual's personal health goals, routes to neighboring states leading to the target state can be determined, thus providing the user with guidance on the next steps needed to achieve their personal health goals. Intermediate states and sub-goals between the current state and the target state, as well as the costs and constraints of transitioning between intermediate states along the route, can be identified. Route planning may include, for example, computing an optimal set of inputs to generate state changes leading to neighboring states along the route to the goal. For example, means-ends analysis and other techniques can be used with routing algorithms to determine the optimal intermediate states for an individual to reach their personal health goals. Multiple routes may be available to reach the desired goal, and route selection can be based on one or more criteria, such as user preference, efficiency, speed, or available resources.

[0058] With a map, location, and goal, a path can be set from the current state to the target state. Navigation allows users to move through intermediate states to the desired target state over time. Drawing routes on a map requires not only knowing the start and end points but also all layers of roads and traffic. In the case of PHN, each set of intermediate states and sub-goals has its own information layer, which relates to the cost and constraints of drawing and transitions between intermediate states. Due to the high dimensionality of PHN, interactions within it are very complex. Conflicting user goals often need to be addressed through methods such as prioritization or weighting. Means-ends analysis or other problem-solving techniques, along with appropriate routing algorithms, can reveal the optimal intermediate states for the user to reach their goal. There may be multiple routes to the desired goal. However, route selection can be made based on various optimization criteria, including at least one of, for example, user preferences, efficiency, speed, and resources.

[0059] After measuring, assessing, modeling, and accepting the goal for an individual, the individual needs to receive guidance on the next steps required to achieve that goal. For situations where the individual needs to make decisions about events leading to the target state, PHN routes intermediate steps through PHSS. Instructions for the next appropriate action are provided at every moment. Actionable inputs that can be part of the guidance include lifestyle events (exercise, nutrition, sleep, meditation, etc.) or medical events (medications, surgical procedures, etc.), or combinations thereof.

[0060] In operation 308, health instructions are provided to the individual, indicating recommended actions. These recommended actions are based on the connection between the current state and intermediate states, and are selected to guide the individual through the transition to the intermediate state.

[0061] Cybernetics control is used to guide individuals to take actions that change their health status. The state transitions resulting from control can be described by the following equation:

[0062] X[k+1]=[k][k]+B[k]U[k](Equation 1)

[0063] Y[k]=[k][k]+D[k]U[k](Equation 2)

[0064] Where X, U, and Y are the system's true state, input, and measured output vectors, respectively. A, B, C, and D are matrices that provide appropriate transformations of these variables at a given time k. An individual's health state at time k is represented by X[k], and the input at time k (actions taken or to be taken) is represented by U[k]. Both play a role in determining the individual's health state at time k+1, which is represented by X[k+1].

[0065] At each time point, e.g., k or k+1, instructions for the next appropriate action are given. As discussed, actionable inputs that can serve as part of the guidance include at least one of lifestyle events (e.g., exercise, nutrition, meditation, etc.) and medical events (e.g., medication, surgical procedures, etc.). Therefore, health instructions instructing recommended actions can include, for example, at least one of lifestyle events and medical events. The key difference between navigation and recommendation is that recommendations made only at a specific point in time do not consider routing to the target state through the state space.

[0066] Cybernetics control can also be achieved by using self-driven actions as input, such as changing thermostats, lighting, and screen devices in a home to automatically help readjust circadian rhythms from time zone differences. Minimum data requirements (e.g., accuracy, sampling frequency, etc.) should be considered to provide effective control in a given scenario.

[0067] Actions performed by individuals, including recommended actions or other measurable actions, are used to determine new estimates of the current state.

[0068] In some implementations, the current state is transitioned to an intermediate state when it is determined that an individual has completed the recommended action.

[0069] In some implementations, when it is determined that an individual has taken an action different from the recommended action, resulting in a transition to a state different from the intermediate state, the route for the individual is recalculated based on the other state and the target state.

[0070] Once a new estimate of the current state has been performed, process 300 can return to operation 306 to determine a new route to the target state. Next, in operation 308, an updated recommended action is determined and provided to the individual. A loop, including operations 306 and 308 when the current state is updated, is repeated until the individual reaches the target state.

[0071] In some implementations, upon reaching the target state, process 300 may continue calculating and sending health commands to minimize deviations from the target state. As described above, this can be accomplished, for example, by repeating a loop formed by operations 306 and 308.

[0072] Figure 4 This is an exemplary flowchart illustrating the framework of an exemplary system 400 for PHN. In summary, the PHN functionality is divided into multiple layers, including a health status estimation layer 402, a state space layer 404, and a guidance layer 406, as... Figure 4 As shown, it has already been combined above. Figure 1 and Figure 3 The process 300 is described. Other layers, such as knowledge base 408, data storage layer 410, personal modeling layer 412, etc., may also be included. In some embodiments, some or all of the components in system 400 may be comprised of, for example, Figure 2 The computing device 200 shown is a device or apparatus such as Figure 3 The process 300 is implemented in the process described above. In some embodiments, portions of system 400 may be executed by instructions executable on computing device 200 and / or one or more other devices (e.g., wearable devices, mobile phones, or cloud servers). In some embodiments, computing device 200 may be a mobile phone, a wearable device such as a smartwatch, or a cloud server. Each layer described below may be implemented entirely in hardware, entirely in software, or a combination of software and hardware. These layers may be implemented as software modules, hardware, firmware, or a combination thereof.

[0073] Health Status Estimate (HSE) Layer 402: It is important to note that an individual's PHSS (Health Status Estimate and Psychological State) is constantly changing based on their location in the state space. For success, navigation is needed to specify a precise location within the PHSS, much like GPS provides navigation in the physical world. HSE layer 402 is used to determine this location, which requires up-to-date data from data storage layer 410 and domain knowledge from knowledge base 408 to arrive at a predicted current state. For example, in the case of cardiovascular health status estimation, wearable sensor data, such as heart rate, activity, or steps, can be obtained from data storage layer 410, and the estimation of cardiovascular disease (CVD), such as the relative mortality risk using resting heart rate, VO2 max, and power-to-heart rate ratio, can be performed by knowledge base 408. The HSE layer can be used to determine a location with a range of accuracy. Considering the accuracy of HSE is important because different applications require different levels of accuracy to serve the user. The same HSE tool may be useful for many applications. For example, monitoring cardiovascular health status is useful for endurance athletes and patients with heart disease. Estimation techniques can be used in the design of many applications, but health applications will require increasingly deeper biological knowledge bases to define and improve the estimated health status calculated from input data. Finally, the estimated health status can be shared with the state space layer 404 and stored in the data storage layer 410.

[0074] State Space Layer 404: The value of good health to an individual depends largely on how they wish to live. When an individual's specified goal is provided by the guidance layer 406, the system 400 can retrieve an appropriate state space based on the goal in the state space layer 404. This process involves identifying a unique set of dimensions that may include health states estimated by the HSE layer 402 that are relevant to a specific goal. Goals may include states that can be designated as ROIs within these navigation dimensions. The GHSS describes the maximum state space a human can occupy. For example, when the state space of interest is cardiovascular status, all possible estimates of cardiovascular status can be considered, including all components such as fitness, cardiovascular disease, and structural formation. This state space is then further refined into a PHSS for each individual based on individual-specific characteristics (e.g., genetics, sex, age) that provide boundary thresholds. This PHSS with ROIs is shared with the guidance layer 406, the HSE layer 402, and the personal modeling layer 412.

[0075] Individual Modeling Layer 412: In PHSS, there are connections / edges between the possibilities of each individual state, such as... Figure 1As illustrated in the example, each edge in the network represents a transition for an individual from one node to another. State transitions consider all inputs (actions) that will lead to the next state, thus establishing connections or relationships between states. Personal modeling transforms actionable inputs into predictive outputs. In personal modeling layer 412, system 400 discovers these relationships in the data and predicts how an input should affect the current health status by extending the model to future points in time. Personal models can include various types of relationship mappings. HSE modeling is used to accurately understand how specific inputs affect an individual's health status. Inputs can come from lifestyle choices, medications, the environment, etc. From a biological perspective, inputs cause changes in the metabolism and gene expression of the user's cells, which in turn alter the structure and function of organs and tissues. This change in biological structure is reflected in changes in health status. Personal state space modeling can be used to assist PHSS in more detail. It requires identifying knowledge layers and ROIs within a space related to the topic of interest. These relationships map to known domain knowledge in personal modeling layer 412. Domain knowledge is transformed into rule-based algorithms that can represent the current understanding of biomedical science. Once sufficient data has been accumulated for each individual user, the basic personal model can be improved by matching user patterns with data-driven clustering of user subgroups. Subgroups can then be modified for individuals using data generated solely by those individuals. Personal models can utilize various levels of specificity, such as grouping into subgroups, which is common in cold-start scenarios. Furthermore, modeling clusters using health states and state transition trajectories, and developing machine learning models based on these clusters, can improve personalization while accelerating learning time. This, combined with... Figure 3 The state transition network discussed can also be included as the sole layer on top of the PHSS.

[0076] Guidance Layer 406: After measuring, estimating, modeling, and receiving the goal for an individual, guidance is provided for the next steps the individual needs to take to achieve that goal. Guidance Layer 406 contains a map, location, and goal, and sets out the steps for routing from the current state to the goal state, such as... Figure 1As illustrated in the example, drawing a route on a map requires not only knowing the starting and ending points but also connecting them. PHN utilizes its information layer to compute a set of intermediate states and sub-goals, which is associated with map drawing, and calculates the costs and constraints of transitioning between intermediate states along the planned route. Problem-solving techniques, along with appropriate routing algorithms, can be used to determine the optimal intermediate state for the user to reach their goal. There may be multiple routes to the desired goal. However, route selection can be made based on various optimization criteria, including user preferences, efficiency, speed, and available resources. Control mechanisms guide individuals through state transitions at different time scales. At each moment, instructions for the next appropriate action are given. Actionable inputs that can be part of the guidance include at least one of lifestyle events (exercise, nutrition, sleep, meditation, etc.) or medical events (medications, surgical procedures, etc.).

[0077] Figure 5A Figure 500 illustrates an example of PHN application in a cardiovascular health setting. According to research, cardiovascular health is the leading cause of death in humans. The clinical need to improve cardiovascular and cardiopulmonary (CRF) health is high, but it is often addressed only in high-demand care or critical situations using expensive laboratory testing and rehabilitation programs. This task can be accomplished by using a low-cost wearable device incorporating PHN.

[0078] Based on this use case implementation, PHN was deployed to improve cardiovascular and cardiorespiratory health (CRF) in each individual. Other scenarios, such as improving mental health and event-specific exercise training (e.g., marathon), can also leverage PHN. Multiple objectives can also be combined. Examples of application scenarios could include, for example, food, exercise, sleep, shopping, travel, and business.

[0079] Sensor data streams are received from an individual's wearable device (e.g., a smartwatch, wristband, or earbuds) and / or mobile device, and these streams can be aggregated. Sensor data streams may include at least one of the following: timestamps, steps, heart rate (HR) (heart beats per minute, BPM), activity patterns (e.g., resting, walking, running), sleep (e.g., deep sleep, light sleep, REM sleep, sleep score), resting heart rate, age, sex, height, weight, etc. Domain knowledge used to construct the PHSS may include, for example, knowledge about at least one of exercise science or bioenergy science. Medical data may include, for example, at least one of ASCVD or cardiac risk factors. ASCVD refers to atherosclerotic cardiovascular disease, measured by cholesterol levels, diabetes status, smoking habits, blood pressure, age, and sex.

[0080] To estimate cardiovascular health, the risk of heart disease can be determined by measuring an individual's ASCVD risk, which can be further improved by relative risk correction of resting heart rate extracted during deep sleep. Deep sleep can be determined, for example, using intermittent medical blood data sensed at high frequencies using wearable devices. Indicators of VO2 max can be determined from exercise, such as walking.

[0081] according to Figure 5A The two dimensions, ASCVD and VO2 max, represented by the y-axis and x-axis respectively, are used to generate the GHSS cardiac map. For example, it can be based on... Figure 1 , Figure 3 and Figure 4 The description in the document (e.g., GHSS 101, process 302, etc.) is used to determine GHSS.

[0082] Knowledge of cardiovascular health was then applied to the GHSS. PHSS could be determined from the GHSS using an individual's demographic information (e.g., age, sex). For example, it could be based on... Figure 1 , Figure 3 and Figure 4 The description in the table (e.g., PHSS102, Operation 302, etc.) is used to determine the PHSS. Additionally, the ROI can be determined. For example, ROI 504 indicates a “moderate” ASCVD risk and an “excellent” VO2 max. Another ROI, 502, indicates a “low” ASCVD risk and an “excellent” VO2 max. In this example, target state 506 falls within ROI 504.

[0083] For example, rule-based HSE models can be constructed using domain knowledge derived from bioenergy science. For instance, they can be based on... Figure 1 , Figure 3 and Figure 4 The description in the document is used to determine the HSE model (e.g., HSE 104 or Operation 304). Using this model, actionable daily exercise guidance can be sent to participants via the cardiac PHN system, and changes in individual CRF indicators can be monitored.

[0084] To construct the individual module of the cardiac PHN system, a knowledge layer on how increasing exercise intensity and duration reduces cardiovascular disease risk was used. Advanced physiological cardiovascular endurance training strategies from bioenergetics can also be used to construct personalized, rule-based daily exercise guidance models. Table I below explains the definitions used in the rule-based model. One or more of the following rules can be used in the navigation module:

[0085] TSB≥+10: Transition zone. The user is well-rested. This value is typically reached when the user is resting for an extended period.

[0086] +5≤TSB<+10: Energy Zone. The zone where the user recovers optimally from exercise.

[0087] -5≤TSB<+5: Middle zone. This zone is typically reached when the user is in a rest or recovery period.

[0088] -30≤TSB<-5: Optimal training zone. The area where users can exercise most effectively.

[0089] -30>TSB: Overtraining zone. The user is overtraining and should rest to prevent injury.

[0090] TSB should be kept in the optimal training zone to improve ASCVD and VO2 max.

[0091] TRIMP w =CT L t-1 ×(1+R)+C1 (Equation 3)

[0092] CTL increased, maximum rate limit not exceeding 5 times per week.

[0093] CT L t-1 -CT L t-8 <5 (Equation 4)

[0094] The TSB temperature will not drop below -20 degrees Celsius more than once within 10 days.

[0095] If the TSB drops below -20 degrees Celsius in a week, the training target for the following week should be lowered slightly.

[0096] Table I

[0097]

[0098] Using a rule-based model defined in the individual modeling layer, a guidance module encompassing routing and control can be constructed. Utilizing the rules within the guidance module, the appropriate intensity and duration of exercise can be gradually determined over time through cybernetics within the PHN system. Furthermore, the Training Stress Balance (TSB), reflecting each participant's current fatigue and fitness levels, can be used to display the user's current state and adjust the guidance within the cybernetics control, even when participants do not always follow PHN instructions.

[0099] Figure 5B This is an example graph illustrating user trends in physical fitness levels, fatigue levels, and stress balance for PHN based on experimental data collected from the cardiovascular health environment. Figure 5BThe PHN system demonstrates how it progressively improves an individual's Atmospheric Level of Tolerance (ATL) and Competency Level of Tolerance (CTL) while keeping the Test Stroke Count (TSB) within the "Optimal Training Zone." Individual users can monitor and maintain a healthy lifestyle by keeping the bar graph within the "Optimal Training Zone."

[0100] Figure 5C An exemplary flowchart of a daily exercise guidance algorithm is shown. By using this algorithm, individuals can be guided to reach and remain within their optimal training zone, such as... Figure 5B As shown, this may help improve CRF levels. Daily exercise guidance can include, for example, exercise type, intensity, and duration, such as, "jog for at least 40 minutes, keeping your heart rate above 113 bpm." Daily TRIP goals can be translated into a set of recommended actions as follows:

[0101] Minutes of low-intensity exercise while maintaining 0.55×MaxHR<=HR<0.70×MaxHR.

[0102] Engage in moderate-intensity exercise for 1 minute while maintaining a body temperature of 0.70 × MaxHR <= HR < 0.80 × MaxHR.

[0103] Minutes of high-intensity exercise while maintaining 0.80×MaxHR<=HR<=1.00×MaxHR.

[0104] Where c1, c2, and c3 are Lucia coefficients, which can be 1, 2, and 3 respectively.

[0105] In another example from a cardiovascular health setting, a personal model of cardiac exercise response is used. According to this example, the personal model shows that standard-volume exercise does not effectively affect the cardiovascular health status of each participant in the same way. Therefore, the connections between nodes within the PHSS are unique to the individual.

[0106] An individual's exercise group can be defined based on factors such as frequency (e.g., low: once a week, medium: 2-4 times a week, high: 5-7 times a week), volume (e.g., low: less than 30 minutes per session, high: more than 30 minutes per session), and exercise intensity (e.g., low: below the estimated maximum heart rate of a 75-person model, high: above the estimated maximum heart rate of a 75-person model). Based on these criteria, each individual can be categorized into a corresponding exercise group. For example, an individual could belong to the following group: High (frequency) - High (volume) - High (intensity).

[0107] A strong causal relationship links CRF to the prediction of cardiovascular disease. Furthermore, epidemiological studies have shown that resting heart rate is an independent predictor of cardiovascular disease. Therefore, resting heart rate can be used as an indicator of CRF, and each individual's cardiovascular exercise response can be categorized according to the rate of change of resting heart rate as positive (Vrhr(t) < 0.5), neutral (0.5 <= Vrhr(t) <= 0.5), and negative (Vrhr(t) > 0.5):

[0108]

[0109] Where t is the total number of weeks, x i For 1, 2, 3, ..., t, y i The resting heart rate in week i. For x i The sum of For y i The sum of these factors. A positive responder is someone whose resting heart rate decreases after several weeks of exercise. A negative responder is someone whose resting heart rate increases after several weeks of exercise. A neutral responder is someone whose resting heart rate does not change significantly even after several weeks of exercise.

[0110] Finding individual differences over time and leveraging these factors, such as joint learning, to personalize the model is beneficial for building individual models. Most people (e.g., according to our experiment, 67 individual models) may not exhibit standard responses to external influences. Since these differences are difficult to know initially, if sufficient data cannot be obtained from individual users, a subpopulation-based model can be used, and then the individual model can be progressively enhanced within the closed loop of the PHN framework.

[0111] Individual users' exercise, heart rate, and sleep data were processed and analyzed. Experimental data showed clustering of CRF responses across different individuals. This clustering information, matched to the user's CRF response type, can then be applied to provide personalized daily guidance. Furthermore, individual data can be used to simulate individual response lag times to predict PHSS state transitions.

[0112] Furthermore, in some implementations, PHN can be used in scenarios such as the following:

[0113] Early detection and prevention: Observe changes in health status in the precursor state. In the precursor state, the healthy state can easily turn into a healthy state, thereby avoiding disease.

[0114] Continuously accumulate user data for various applications: understand the data to help individuals in all aspects of life, such as exercise, entertainment, shopping, travel, enjoying better food, and improving quality of life.

[0115] Quantitative interaction in health: Transforming health assessments into dynamic quantitative measurements, rather than categorizing them as normal or abnormal, enables individuals to engage with their health.

[0116] Cost Reduction: Through trickle-down technology and computational scale, we expect more people to access high-quality guidance, reducing the cost barriers to achieving a healthy life, especially in developing regions where there is no well-developed physical health infrastructure.

[0117] Those skilled in the art will understand that the embodiments described in this disclosure can be implemented as methods, systems, or computer program products. Therefore, this disclosure can be implemented entirely in hardware, entirely in software, or in a combination of software and hardware. Furthermore, this disclosure can be embodied as one or more computer program products, which are computer-executable program codes in a computer-writable storage medium (including but not limited to disk storage and optical storage).

[0118] This disclosure is described in accordance with methods, apparatus (systems), and flowcharts and / or block diagrams of computer program products, and should be understood as each flow and / or block of the flowcharts and / or block diagrams implemented by computer program instructions, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams. The computer program instructions may be provided to a general-purpose computer, special-purpose computer, embedded computer, or other processor of a programmable data processing apparatus to produce a machine, wherein the instructions, which execute on the computer or other processor of the programmable data processing apparatus, create means for implementing the functions specified by one or more flows and / or blocks in the flowcharts and / or block diagrams.

[0119] Computer program instructions may also be stored in a computer-readable storage medium capable of directing a computer or other programmable data processing device into a particular mode of operation, wherein the instructions stored in the computer-readable storage medium produce a manufactured product containing an instruction device that implements a function specified by one or more flows in a flowchart and / or one or more boxes in a block diagram.

[0120] Computer program instructions may also be loaded into a computer or another programmable data processing device to execute a series of operating procedures in the computer or another programmable data processing device, thereby producing a process implemented by the computer, whereby the computer program instructions executed in the computer or another programmable data processing device provide operating procedures for functions specified by one or more flows in a flowchart and / or one or more boxes in a block diagram.

[0121] It is obvious that those skilled in the art can make any variations and / or modifications to this disclosure based on the principles of this disclosure and within its scope. Therefore, this disclosure is intended to include any variations and modifications that fall within the scope of the claims and other equivalents herein.

[0122] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. Methods and materials similar to or equivalent to those described herein may be used in practice or testing of this disclosure. As used in the specification and appended claims, the singular forms “a,” “an,” and “the” include plural indicators unless the context clearly specifies otherwise. The term “comprising” and variations thereof, as used herein, are used synonymously with the term “including” and variations thereof, and are open-ended and non-limiting terms. The terms “optional” or “optionally” as used herein mean that a feature, event, or condition subsequently described may or may not occur, and the description includes both the possibility that the feature, event, or condition occurs and the possibility that it does not occur. The terms “at least one of A or B,” “at least one of A and B,” “one or more of A or B,” and “A and / or B” as used herein mean “A,” “B,” or “A and B.”

[0123] While this disclosure has been described in conjunction with certain embodiments or implementations, it should be understood that this disclosure is not limited to the disclosed embodiments. Rather, this disclosure is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims, which is subject to the broadest interpretation to include all such modifications and equivalent structures permitted by law.

Claims

1. A method for personal health navigation, comprising: The processor determines the individual's personal health state space based on individual-specific characteristics. The personal health state space includes a set of connected biological states of the individual. The connections between biological states in the personal health state space represent knowledge of actionable inputs that can cause the biological states to change. The individual-specific characteristics include at least one of the individual's genetic characteristics and demographic characteristics. The individual-specific characteristics also include the exercise group to which the individual belongs. The processor receives the individual's personal health goals input by the individual; The processor determines a region of interest within the individual's personal health state space for the individual based on the individual's personal health goals, wherein the region of interest is defined by a target state relative to the individual's current state, and the target state is associated with the individual's personal health goals; The processor determines the current state of the individual; The processor determines the optimal route from the current state to the target state. The optimal route includes an optimal set of intermediate states between the current state and the target state, and a corresponding set of actions. The optimal set of intermediate states includes multiple intermediate states, and the set of actions generates state changes that lead to adjacent states along the optimal route. The processor provides the individual with a health instruction indicating the next recommended action to be performed by the individual. The next recommended action is based on the connection between the current state and adjacent intermediate states in the set of optimal intermediate states. The next recommended action is selected to guide the individual to transition to the adjacent intermediate state. The next recommended action includes exercise intensity and exercise duration.

2. The method according to claim 1, further comprising: The processor determines the action to be performed by the individual based on the sensor data stream; When the processor determines that the individual has completed the next recommended action, it determines that the individual transitions from the current state to the adjacent intermediate state. The processor provides the individual with health instructions for recommended actions along the optimal route from the adjacent intermediate state to the next adjacent state.

3. The method according to claim 1, further comprising: When the processor determines that the individual has taken an action different from the next recommended action, causing the current state to transition to a state different from the adjacent intermediate state, it recalculates a new route for the individual to reach the target state based on the other state and the target state. The processor determines an updated recommended action based on the new route and provides the updated recommended action to the individual.

4. The method according to any one of claims 1-3, further comprising: The processor builds a personal model for the individual, and the personal model is used to transform actionable inputs into predictive outputs. The processor determines the optimal route from the current state to the target state based on the personal model.

5. The method according to any one of claims 1-3, further comprising: The processor decomposes the personal health goal into short-term sub-goals represented as nodes in the region of interest.

6. The method according to any one of claims 1-3, further comprising: The processor determines a state transition network comprising edges, each edge representing a transition from a first state to a second state based on a personal model associated with the individual.

7. The method according to claim 6, further comprising: The processor determines the exercise group to which the individual belongs based on the individual's exercise frequency, amount of exercise, and exercise intensity.

8. The method according to any one of claims 1-3, wherein, The health instruction that directs the next recommended action includes at least one of a lifestyle event and a medical event.

9. The method according to any one of claims 1-3, wherein, The current state is estimated based on physiological measurements of the individual obtained through wearable devices; or The current state is obtained by processing and analyzing the individual's exercise data, heart rate data, and sleep data; or The current state is obtained based on the individual's training impulse.

10. The method according to any one of claims 1-3, further comprising: The processor receives sensor data streams from at least one of the individual's wearable and mobile devices, the sensor data streams including at least one of timestamps, steps, heart rate, activity patterns, and sleep.

11. A device for personal health navigation, the device comprising: Non-temporary memory; as well as The processor is configured to execute instructions stored in the non-transitory memory to: Based on individual-specific characteristics, an individual's personal health state space is determined. The personal health state space includes a set of connected biological states of the individual. The connections between biological states in the personal health state space represent knowledge of actionable inputs that can cause transitions in the biological states. The individual-specific characteristics include at least one of the individual's genetic characteristics and demographic characteristics. The individual-specific characteristics also include the exercise group to which the individual belongs. Receive the individual's personal health goals input by the individual; Based on the individual's personal health goals, a region of interest is determined for the individual within the personal health state space, wherein the region of interest is defined by a target state relative to the individual's current state, and the target state is associated with the individual's personal health goals; Determine the current state of the individual; Determine the optimal route from the current state to the target state, the optimal route including an optimal set of intermediate states between the current state and the target state and a corresponding set of actions, the optimal set of intermediate states including multiple intermediate states, and the set of actions used to generate state changes that lead to adjacent states along the optimal route; and The individual is provided with a health instruction indicating the next recommended action to be performed by the individual, the next recommended action being based on the connection between the current state and adjacent intermediate states in the set of optimal intermediate states, wherein the next recommended action is selected to guide the individual to transition to the adjacent intermediate state, and the next recommended action includes exercise intensity and exercise duration.

12. The apparatus according to claim 11, wherein, The instructions also include instructions for the following: Based on the sensor data stream, determine the action performed by the individual; When it is determined that the individual has completed the next recommended action, the individual is transitioned from the current state to the adjacent intermediate state. Provide the individual with health instructions on recommended actions to proceed from the adjacent intermediate state to the next adjacent state along the optimal route.

13. The apparatus of claim 11, wherein the instructions further include instructions for: When it is determined that the individual has taken an action different from the next recommended action, causing the current state to transition to a state different from the adjacent intermediate state, a new route for the individual to reach the target state is recalculated based on the other state and the target state. Based on the new route, an updated recommended action will be determined and provided to the individual.

14. The apparatus according to any one of claims 11-13, wherein, The instructions also include instructions for the following: A personal model is established for the individual, which is used to transform actionable inputs into predictive outputs; Based on the personal model, determine the optimal route from the current state to the target state.

15. The apparatus according to any one of claims 11-13, wherein, The instructions also include instructions for the following: The personal health goal is decomposed into short-term sub-goals represented as nodes in the region of interest.

16. The apparatus according to any one of claims 11-13, wherein, The instructions also include instructions for the following: A state transition network is defined, comprising edges, each edge representing a transition from a first state to a second state based on a personal model associated with the individual.

17. The apparatus according to claim 16, wherein, The instructions further include instructions for the following: Based on the individual's exercise frequency, amount of exercise, and exercise intensity, the exercise group to which the individual belongs is determined.

18. The apparatus according to any one of claims 11-13, wherein, The health instruction that directs the next recommended action includes at least one of a lifestyle event and a medical event.

19. The apparatus according to any one of claims 11-13, wherein, The current state is estimated based on physiological measurements of the individual obtained through wearable devices; or The current state is obtained by processing and analyzing the individual's exercise data, heart rate data, and sleep data; or The current state is obtained based on the individual's training impulse.

20. The apparatus according to any one of claims 11-13, wherein, The instructions also include instructions for receiving sensor data streams from at least one of the individual's wearable and mobile devices, the sensor data streams including at least one of timestamps, steps, heart rate, activity patterns, and sleep.

21. A non-transitory computer-readable storage medium configured to store a computer program for personal health navigation, the computer program including instructions executable by a processor to perform the method as claimed in any one of claims 1-10.

Images