Health behavior monitoring system and method based on somatosensory interaction

Abstract

The application discloses a health behavior monitoring system and method based on somatosensory interaction, relates to the field of somatosensory interaction, and comprises the following steps: a starting module is used for carrying out identity authentication after a user carries out starting interaction, and executing device starting after passing; a task generation module is used for carrying out user data calling and configuring a touch height task; a somatosensory interaction module is used for carrying out touch height monitoring of the user after activating a tracking unit in the somatosensory interaction module and executing user authentication positioning; an action decomposition module is used for carrying out action division of a touch height monitoring data set through a calibration template, and establishing an action label; and a health perception module is used for carrying out multi-dimensional behavior health perception according to the touch height monitoring data set and the action label after initially configuring a health perception channel based on a user portrait, and establishing a behavior health perception result. The application solves the technical problems of the existing health behavior monitoring, such as insufficient action monitoring accuracy and health perception comprehensiveness, and achieves the technical effect of more accurate and comprehensive health behavior monitoring results.

Description

Technical Field

[0001] This application relates to the field of motion-sensing interaction, and in particular to a health behavior monitoring system and method based on motion-sensing interaction. Background Technology

[0002] Health behavior monitoring plays a crucial role in maintaining good health and promptly identifying potential health problems. Currently, traditional motion monitoring devices such as wristbands and athletic shoes are primarily used to monitor health behaviors. These devices typically collect user activity data and other information through built-in sensors. However, traditional monitoring methods are not precise enough in monitoring the details of movements, making it difficult to accurately classify and analyze complex actions such as reaching for high objects. Furthermore, these devices often only collect single-dimensional data, failing to achieve multi-dimensional health perception and comprehensively assess potential health problems arising from a user's health behaviors.

[0003] Currently, health behavior monitoring technologies suffer from insufficient accuracy in motion monitoring and inadequate comprehensiveness in health perception. Summary of the Invention

[0004] This application provides a health behavior monitoring system and method based on motion-sensing interaction. When a user initiates interaction, the system first performs identity authentication. After successful authentication, the device is activated and user data is retrieved to configure a personalized vertical reach task. Subsequently, the motion-sensing tracking module is activated to locate the user, monitors the vertical reach action in real time, and generates a dataset. Then, a calibration template is used to divide the action into four stages: preparation, guided response, high point reach, and recovery, and labels these stages. Finally, a health perception channel is initialized based on the user profile. Multi-dimensional behavioral health analysis is performed based on the action data and labels, and behavioral health perception results are output. These technical means solve the technical problems of insufficient accuracy in motion monitoring and comprehensiveness in health perception in existing health behavior monitoring systems, achieving a more accurate and comprehensive technical effect in health behavior monitoring.

[0005] This application provides a health behavior monitoring system based on motion-sensing interaction, comprising: a startup module, used to authenticate the user after the user initiates the interaction, and to start the device after successful authentication; a task generation module, used to retrieve user data based on the authentication result, and configure a height-reaching task based on the user data retrieval result, the user data retrieval result including user profile and user historical height-reaching data; a motion-sensing interaction module, used to activate the tracking unit in the motion-sensing interaction module after the height-reaching task configuration is completed, to perform user authentication and positioning, and to monitor the user's height-reaching action, and to establish a height-reaching monitoring dataset; an action decomposition module, used to divide the actions in the height-reaching monitoring dataset using a calibration template, and to establish action labels, the action labels including labels for preparatory actions, guided response actions, high-point reach actions, and recovery actions; and a health perception module, used to initially configure a health perception channel based on the user profile, and then perform multi-dimensional behavioral health perception based on the height-reaching monitoring dataset and the action labels, and to establish behavioral health perception results.

[0006] In a possible implementation, the health perception module performs multi-dimensional behavioral health perception based on the vertical reach monitoring dataset and the action tags, establishes behavioral health perception results, and performs the following processing: It divides the vertical reach monitoring dataset into data segments based on the action tags, establishing preparatory action sub-data segments, guided response sub-data segments, high point reach sub-data segments, and recovery sub-data segments; it calls the parameter set in the health perception channel that matches the user profile to construct a multi-dimensional behavioral health perception path mapped to the sub-data segments; and it uses the multi-dimensional behavioral health perception path to perceive the behavioral characteristics of the mapped sub-data segments, establishing behavioral health perception results.

[0007] In a possible implementation, the health perception module utilizes the multi-dimensional behavioral health perception path to perceive the behavioral characteristics of the mapped sub-data segments, establishes behavioral health perception results, and performs the following processing: It perceives the preparatory behavioral characteristics of the preparatory action sub-data segments through the preparatory action behavioral health perception path, including initial reaction delay perception and trunk sway amplitude perception; it uses the preparatory behavioral characteristic perception to perform reaction ability and balance stability analysis, establishing a first behavioral health perception result; it perceives the guiding behavioral characteristics of the guiding response sub-data segments through the guided response behavioral health perception path, including target deviation distance perception and following delay perception; it uses the guided behavioral characteristic perception to perform neuromuscular control ability and attention maintenance analysis, establishing a second behavioral health perception result; and it establishes a behavioral health perception result based on the first and second behavioral health perception results.

[0008] In a possible implementation, the health perception module establishes a behavioral health perception result based on the first and second behavioral health perception results, and performs the following processing: It perceives the reach behavior characteristics of the high-point reach sub-data segment through the high-point reach behavioral health perception path, including maximum height characteristic perception, upward speed characteristic perception, and arm span characteristic perception; it analyzes explosive power and upper limb joint range of motion based on the reach behavior characteristic perception, and establishes a third behavioral health perception result; it perceives the recovery behavior characteristics of the recovery sub-data segment through the recovery behavior health perception path, including landing stability perception, recovery time perception, and center of gravity return path perception; it analyzes the movement integrity and recovery control ability based on the recovery behavior characteristic perception, and establishes a fourth behavioral health perception result; and it establishes a behavioral health perception result based on the first, second, third, and fourth behavioral health perception results.

[0009] In a possible implementation, the health perception module performs multi-dimensional behavioral health perception based on the vertical reach monitoring dataset and the action tags, establishes behavioral health perception results, and further performs the following processing: after time-stamping the vertical reach monitoring dataset, it counts the vertical reach frequency and establishes a first additional behavioral health perception result; it performs action deformation perception on the time-stamped vertical reach monitoring dataset and establishes a second additional behavioral health perception result; and it uses the first additional behavioral health perception result and the second additional behavioral health perception result to compensate for the behavioral health perception result.

[0010] In a possible implementation, the system further includes: a matching module, used to perform abnormal health warning level matching based on the health perception results and generate matching results; and a warning issuance module, used to configure warning signals based on the matching results and execute abnormal health behavior warning issuance.

[0011] In a possible implementation, the early warning module includes: a communication module for establishing device communication with the user's wearable device; an interaction module for establishing a time-series vital sign dataset after interacting with the wearable device based on the device communication; and a compensation module for configuring an early warning signal after compensating the matching result based on the time-series vital sign dataset.

[0012] In a possible implementation, the startup module further includes: if the user is determined to be a new user, performing static data collection of the user to establish a first learning dataset; acquiring the user's input data to establish a second learning dataset; creating a user profile based on the first learning dataset and the second learning dataset and performing device startup.

[0013] In a possible implementation, the system includes: a recording module, used to evaluate the completion of the vertical reach task based on the vertical reach monitoring dataset and generate an evaluation record; and an incentive module, used to match reward points based on the evaluation record and distribute the reward points to the corresponding user account.

[0014] This application also provides a health behavior monitoring method based on motion-sensing interaction, including: after a user initiates the interaction, the user is authenticated; after successful authentication, the device is started; user data is retrieved based on the authentication result; a height-reaching task is configured based on the user data retrieval result, the user data retrieval result including a user profile and the user's historical height-reaching data; after the height-reaching task is configured, the tracking unit in the motion-sensing interaction module is activated to perform user authentication and positioning, and then the user's height-reaching data is monitored to establish a height-reaching monitoring dataset; the height-reaching monitoring dataset is divided into actions using a calibration template, and action labels are established, the action labels including labels for preparatory actions, guided response actions, high-point reaching actions, and recovery actions; after initially configuring a health perception channel based on the user profile, multi-dimensional behavioral health perception is performed based on the height-reaching monitoring dataset and the action labels, and behavioral health perception results are established.

[0015] The proposed health behavior monitoring system and method based on motion-sensing interaction involves the following steps: Upon user interaction, the startup module authenticates the user. After successful authentication, the device starts. A task generation module retrieves user data based on the authentication result and configures a height-reaching task based on this data. This data includes the user profile and historical height-reaching data. After task configuration, the tracking unit in the motion-sensing interaction module is activated to perform user authentication and positioning, then height-reaching monitoring is conducted, creating a height-reaching monitoring dataset. An action decomposition module uses a calibration template to classify the actions within the dataset and creates action labels. These labels include labels for preparatory actions, guided response actions, high-point reach actions, and recovery actions. After initial configuration of the health perception channel based on the user profile, the health perception module performs multi-dimensional behavioral health perception based on the height-reaching monitoring dataset and the action labels, establishing behavioral health perception results. This achieves the technical effect of making health behavior monitoring results more accurate and comprehensive. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 This is a schematic diagram of the structure of a health behavior monitoring system based on somatosensory interaction provided in an embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating the health behavior monitoring method based on motion-sensing interaction provided in an embodiment of this application.

[0019] Figure labeling: Startup module 10, Task generation module 20, Motion interaction module 30, Motion decomposition module 40, Health perception module 50. Detailed Implementation

[0020] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. 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 to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0023] This application provides a health behavior monitoring system based on motion-sensing interaction, such as... Figure 1 As shown, the system includes:

[0024] The startup module 10 is used to authenticate the user after the user performs a startup interaction, and to start the device after the authentication is successful.

[0025] Specifically, identity authentication refers to verifying the legitimacy of a user's identity through specific technical means, ensuring that only authorized users can use the device or system. Identity authentication can employ biometric technologies such as fingerprint recognition or facial recognition. Devices are equipped with fingerprint sensors or cameras. When a user initiates interaction (such as pressing the fingerprint recognition area or facing the camera), the system completes identity authentication by comparing the fingerprint with pre-recorded user biometric information. For example, using a capacitive fingerprint sensor, the principle is to utilize the difference in electric field created by the capacitance of the human body and the fingerprint ridges to recognize the fingerprint pattern. For facial recognition, an infrared camera can be used to capture facial feature points and construct a 3D facial model for comparison. Once identity authentication is successful, the startup circuit is triggered, switching the device from standby to operating state. Simultaneously, the startup program begins running, initializing the device's hardware and software systems. For example, the startup program loads the device's operating system kernel, initializes various sensors and interfaces, and prepares for the operation of subsequent modules.

[0026] In one possible implementation, the startup module 10 further includes: if the user is determined to be a new user, performing static data collection of the user to establish a first learning dataset; acquiring the user's input data to establish a second learning dataset; creating a user profile based on the first learning dataset and the second learning dataset and performing device startup.

[0027] Specifically, the system distinguishes between new and existing users. For example, when a user initiates the startup interaction, the device reads the current device fingerprint and compares it with previously stored device fingerprints. If no matching device fingerprint is found, the user is considered a new user. When a new user is identified, the startup module 10 initiates a series of static data collection processes. For example, it collects basic body data such as height, weight, and body proportions using hardware such as the device's camera and motion sensors. Simultaneously, the device's touchscreen or voice input module guides the user to input basic information, such as gender, age, and basic health status (whether there are chronic diseases, allergies, etc.). The collected static data is then organized and categorized to form the first learning dataset. This data provides the basic body information and background data for subsequent health monitoring and personalized task configuration. The device guides the user to input their exercise habits, dietary preferences, and health goals (such as improving athletic ability, enhancing physical fitness, or losing weight) through the touchscreen or voice input. For example, the user can choose their favorite type of sport (such as basketball, football, swimming), the amount of time available for exercise per week, and whether they like sweets. The user-input data is aggregated and organized to form a second learning dataset, which reflects the user's subjective intentions and preferences.

[0028] Based on the first and second learning datasets, the data is analyzed and processed to create user profiles. These profiles include multi-dimensional information such as the user's physical characteristics, health status, exercise habits, dietary preferences, and health goals. The device then initiates its startup based on the user profile, preparing for subsequent health behavior monitoring and personalized task configuration.

[0029] This approach, by collecting static data from new users and acquiring user input data, can create a unique user profile for each user, enabling the device to provide personalized health monitoring and task configuration based on the user's personal characteristics, health status, exercise habits, and dietary preferences.

[0030] The task generation module 20 is used to retrieve user data based on the identity authentication result and configure the height-reaching task based on the user data retrieval result. The user data retrieval result includes user profile and user historical height-reaching data.

[0031] Specifically, cloud databases are used to store user data, including user profiles (such as basic information like age, gender, height, and weight, as well as features like exercise preferences and health status) and historical vertical jump data (such as records of jump counts, highest height, and average height). Devices connect to the cloud server via network communication technologies (such as Wi-Fi or Bluetooth) to retrieve the corresponding user's data. Rule-based expert systems or machine learning algorithms are employed. The rule engine generates vertical jump tasks based on user profiles and historical data, according to predefined rules (e.g., assigning simpler tasks to younger users with poor athletic ability, gradually increasing the difficulty as age and athletic ability improve). The machine learning algorithm, through learning from large amounts of user data, predicts and configures suitable vertical jump tasks for each user.

[0032] The motion-sensing interaction module 30 is used to activate the tracking unit in the motion-sensing interaction module after the height-reaching task configuration is completed, perform user authentication and positioning, monitor the user's height-reaching activity, and establish a height-reaching monitoring dataset.

[0033] Specifically, infrared sensors are used for user positioning. Multiple infrared transmitters and receivers are deployed around the device, and the user's position is determined using triangulation. For example, infrared transmitters are placed at the four corners of the device, and the user wears an infrared reflective tag. After the receiver receives the reflected signal, the time difference of arrival is calculated to determine the user's spatial coordinates. Depth cameras, such as structured light depth cameras or Time-of-Flight (ToF) depth cameras, are used to capture the user's movements. Depth cameras can construct a 3D model of the user's body, monitor the user's limb movements in real time, capture details of the user's vertical reach movements, and establish a vertical reach monitoring dataset. This dataset is a collection of various data collected during the user's vertical reach movements, including time-series data of the movements, spatial coordinate data, and posture data, which are used for motion analysis and health perception. For example, structured light depth cameras project specific light patterns and analyze the deformation of the patterns to calculate depth information, thereby obtaining the depth coordinates of various parts of the user's body and constructing motion data.

[0034] The action decomposition module 40 is used to divide the action of the height monitoring dataset through the calibration template and establish action labels. The action labels include labels for preparatory actions, guiding response actions, high point reaching actions, and recovery actions.

[0035] Specifically, the calibration template is a predefined standard vertical reach action model, including preparatory actions (such as standing posture), guided response actions (such as raising the arm upwards), high-point reach actions (such as the action of the fingers touching the highest point), and recovery actions (such as the action of returning to the initial posture from the highest point). Dynamic Time Warping (DTW) or Hidden Markov Model (HMM) algorithms are used to segment the vertical reach monitoring dataset into actions. For example, the DTW algorithm calculates the optimal matching path between time-series data, compares continuous action data with the calibration template, determines the start and end points of the actions, and thus establishes action labels. Action labels classify and annotate actions, dividing continuous complex actions into several sub-actions with clear characteristics and meanings for more detailed analysis and processing.

[0036] The health perception module 50 is used to perform multi-dimensional behavioral health perception based on the height monitoring dataset and the action tags after initially configuring the health perception channel based on the user profile, and to establish behavioral health perception results.

[0037] Specifically, health perception channels refer to dedicated data collection and analysis pathways set up for different health dimensions (such as exercise health, nutritional health, and bone health) to comprehensively and deeply perceive the user's health status. Different health perception channels are configured based on user profiles. For example, for children, the focus is on configuring exercise health perception channels (such as monitoring exercise intensity, duration, and frequency) and nutritional health perception channels (such as analyzing the matching degree between food nutrient components and exercise expenditure). For adolescents, a bone development health perception channel is added on top of this (such as analyzing bone stress through motion monitoring).

[0038] Using deep learning algorithms (such as Convolutional Neural Networks (CNNs) or Long Short-Term Memory Networks (LSTMs), a vertical reach monitoring dataset and action labels are taken as input, combined with other health-related data (such as heart rate and sleep data) to perform multidimensional behavioral health perception. CNNs can extract spatial features of action data, while LSTMs can capture temporal features of actions, ultimately establishing behavioral health perception results. For example, by analyzing features such as speed, acceleration, and amplitude of the vertical reach action, combined with heart rate changes, the user's exercise health status can be assessed.

[0039] In one possible implementation, the health perception module 50 performs multi-dimensional behavioral health perception based on the vertical reach monitoring dataset and the action tags, and establishes behavioral health perception results. This includes: dividing the vertical reach monitoring dataset into data segments based on the action tags, establishing preparatory action sub-data segments, guided response sub-data segments, high point reach sub-data segments, and recovery sub-data segments; calling the parameter set in the health perception channel that matches the user profile to construct a multi-dimensional behavioral health perception path mapped to the sub-data segments; and using the multi-dimensional behavioral health perception path to perceive the behavioral characteristics of the mapped sub-data segments, thereby establishing behavioral health perception results.

[0040] Specifically, based on information such as the timestamp or data sequence position marked by the action tag, the preparatory action sub-data segment, the guiding response sub-data segment, the high point reach sub-data segment, and the recovery sub-data segment are extracted from the complete height reach monitoring dataset. For example, if the action tag clearly states that the preparatory action begins at the 1st second of the dataset and ends at the 3rd second, then all relevant data from the 1st to the 3rd second (such as sensor data on displacement, velocity, acceleration, etc.) are extracted from the height reach monitoring dataset as the preparatory action sub-data segment, and other sub-data segments are extracted in the same way.

[0041] The health perception channel pre-stores various parameter sets that match different user profiles. When needed, the corresponding parameter set is searched and invoked based on the user profile characteristics (such as age, gender, and athletic ability level). For example, for a user profile of a teenage sports enthusiast, the parameter set may include assessment indicators of the teenager's exercise intensity (such as maximum height reached per unit time, movement frequency, etc.) and judgment criteria for the standardization of movements (such as the correct angle range of various parts of the body during the preparatory movement, and the muscle force exertion pattern when reaching the highest point, etc.).

[0042] For each sub-data segment, a series of analytical dimensions and corresponding algorithms or models are defined to form a perception path. Taking the preparatory action sub-data segment as an example, the perception path may include the "posture standardization assessment" dimension, whose corresponding algorithm is based on a human posture estimation model (such as using a human keypoint detection model in deep learning) to analyze the body posture data in the sub-data segment and determine whether the preparatory posture is correct; and the "muscle warm-up analysis" dimension, whose corresponding algorithm is to analyze the changes in acceleration data and electromyographic signals (acquired by electromyography sensors) to assess whether the muscle activity has reached the warm-up state. Each sub-data segment has multiple perception paths with different dimensions corresponding to it.

[0043] The constructed multi-dimensional behavioral health perception path is used to map the behavioral characteristics of sub-data segments. Specifically, data in each sub-data segment is calculated and analyzed according to the algorithm or model for each dimension. For example, in the posture standardization assessment dimension, human posture data from the preparatory movement sub-data segment is input into a human posture estimation model. The model outputs angle information for various body parts, which is then compared with the preset standard angle range in the parameter set to determine whether the posture is standard. In the muscle warm-up analysis dimension, features are extracted and analyzed from acceleration data and electromyographic signals. Based on preset muscle warm-up assessment standards, a score for the degree of muscle warm-up is obtained. By synthesizing the analysis results from each dimension, a behavioral health perception result is finally established, forming a detailed report containing the user's health behavior performance at different stages of movement.

[0044] This approach, through detailed data segmentation and targeted perception path construction, enables refined analysis of the user's movement details and health status at each stage of the vertical jump process. This allows for the timely detection of potential health problems and movement defects, providing users with sufficient basis for improvement and technical support. It helps users exercise more scientifically, improve exercise results, prevent sports injuries, and achieve the goal of health management.

[0045] In one possible implementation, the health perception module 50 utilizes the multi-dimensional behavioral health perception path to perceive the behavioral characteristics of the mapped sub-data segments and establish behavioral health perception results. This includes: perceiving the preparatory behavioral characteristics of the preparatory action sub-data segments through the preparatory action behavioral health perception path, wherein the preparatory behavioral characteristics perception includes initial reaction delay perception and trunk sway amplitude perception; using the preparatory behavioral characteristics perception to perform reaction ability and balance stability analysis to establish a first behavioral health perception result; perceiving the guiding behavioral characteristics of the guiding response sub-data segments through the guided response behavioral health perception path, wherein the guiding behavioral characteristics perception includes target deviation distance perception and following delay perception; using the guiding behavioral characteristics perception to perform neuromuscular control ability and attention maintenance analysis to establish a second behavioral health perception result; and establishing a behavioral health perception result based on the first behavioral health perception result and the second behavioral health perception result.

[0046] Specifically, from the preparatory action sub-data segment, determine the time point when the action command is issued (denoted as T0) and the time point when the user's body begins to show a noticeable movement response (denoted as T1). The initial reaction delay is T1-T0. For example, the action command is issued through a device screen display or voice prompt, and the device's sensors (such as an accelerometer or depth camera) detect the time point when the user's body (such as legs or arms) begins to move. Assuming T0 is the moment the action command is issued, and T1 is the moment when the device's accelerometer detects that the acceleration of a certain part of the user's body first exceeds a set static threshold, the time difference between the two can be calculated to obtain the initial reaction delay. The calculated initial reaction delay is compared with a pre-set average initial reaction delay standard value for people of the same age and type of exercise. If the user's initial reaction delay is significantly longer than the standard value, it indicates that the user's reaction ability may have a problem; if it is close to or shorter than the standard value, it indicates that the user's reaction ability is good.

[0047] Using a depth camera or inertial measurement unit (IMU) sensor, the user's torso motion trajectory is captured in real time within the preparatory movement data segment. The torso swing amplitude is calculated by analyzing the displacement changes in the forward / backward, left / right, and vertical directions. For example, a depth camera can construct a 3D model of the user's torso; by calculating the differences in the model's position coordinates at different time points, the swing amplitude in each direction can be obtained. Alternatively, the IMU sensor can measure the torso's angular velocity and acceleration; by performing mathematical processing such as integration on these data, the swing angle and displacement amplitude of the torso can be obtained. A reasonable range for the torso swing amplitude is set based on factors such as the user's age, physical condition, and type of exercise. If the user's torso swing amplitude exceeds this range, it indicates poor balance stability during the preparatory movement phase; if it is within the range, it indicates good balance stability.

[0048] In the guidance response sub-data segment, the device pre-sets the target location for the guided action (such as a virtual target point displayed on the screen or a location specified via voice prompts). Using a depth camera or position sensor, the device tracks the user's actual movement trajectory in real time and calculates the deviation distance between the user's actual movement trajectory and the target location. For example, in a task requiring the user to guide their arm to touch a specific target point on the screen, the depth camera can accurately capture the coordinates of the user's finger position and compare them with the coordinates of the target point to determine the target deviation distance for each guided action. An allowable range of target deviation distances is set, and based on the target deviation distance data from multiple guided actions, the average deviation distance and the standard deviation of the deviation are calculated. If both the average deviation distance and the standard deviation are large, it indicates poor accuracy in the user's movements and a need to improve neuromuscular control; conversely, if both the average deviation distance and the standard deviation are small, it indicates good neuromuscular control.

[0049] For guided response actions that require the user to follow a specific rhythm or guided trajectory, the time point when the guiding stimulus is emitted (e.g., the time point when the guiding light flashes or the guiding sound is played, denoted as T2) and the time point when the user begins to follow the action (denoted as T3) are recorded. The following delay is T3-T2. For example, in a guided action task involving following a rhythmic jump, the device plays a guiding sound as a rhythm signal. By detecting the start time point of the user's body movement (e.g., leg jump or arm swing), the following delay is calculated. Similar to the initial reaction delay, the following delay is compared with the standard following delay for similar tasks. The standard following delay is preset based on factors such as the user's motor experience and skill level. If the user's following delay is too long, it indicates a problem with the user's attention allocation or the coordination of the nervous system's response; if it is within a reasonable range, it indicates that the user's attention maintenance and neuromuscular coordination are good.

[0050] After completing the perception of various behavioral characteristics of the preparatory and guided response actions, the results of the first behavioral health perception (response ability and balance stability analysis) and the second behavioral health perception (neuromuscular control ability and attention maintenance analysis) are integrated. A weighted average method can be used, assigning corresponding weights based on the importance of each analysis result to the overall health behavior. For example, the weight of reaction ability is 0.3, balance stability is 0.3, neuromuscular control ability is 0.3, and attention maintenance is 0.1 (the weight allocation can be adjusted according to actual application needs). The scores of each analysis indicator are multiplied by their weights and then summed to obtain a comprehensive behavioral health perception score. The comprehensive behavioral health perception score and the analysis results of each sub-item are presented to users or health management professionals in the form of charts or text reports. For example, a behavioral health radar chart can be generated, with each axis representing reaction ability, balance stability, neuromuscular control ability, and attention maintenance, respectively. Users can intuitively see the gap between their performance in each aspect and the health standards, as well as their overall behavioral health status, in the chart.

[0051] In one possible implementation, the health perception module 50 establishes behavioral health perception results based on the first and second behavioral health perception results, including: perceiving the reach behavior characteristics of a high-point reach sub-data segment through a high-point reach behavioral health perception path, wherein the reach behavior characteristic perception includes maximum height characteristic perception, upward speed characteristic perception, and arm span characteristic perception; analyzing explosive power and upper limb joint range of motion based on the reach behavior characteristic perception to establish a third behavioral health perception result; perceiving the recovery behavior characteristics of a recovery sub-data segment through a recovery behavior health perception path, wherein the recovery behavior characteristic perception includes landing stability perception, recovery time perception, and center of gravity return path perception; analyzing movement integrity and recovery control ability based on the recovery behavior characteristic perception to establish a fourth behavioral health perception result; and establishing behavioral health perception results based on the first, second, third, and fourth behavioral health perception results.

[0052] Specifically, using the device's depth camera or infrared range sensor, the maximum height reached by the user during a vertical reach action is measured within the high-point reach sub-data segment. For example, the depth camera can construct a 3D model of the user's body and track the highest coordinates of the user's fingers or the object they touch (such as a target point on a touchscreen) in real time. Assuming the user's starting position is on the ground, the depth camera captures the coordinates of the highest point of the user's fingers in the air, and the actual maximum height value is obtained through coordinate conversion (based on parameters such as the camera's focal length and image sensor size). The measured maximum height value is then compared with standard vertical reach height data under conditions of the same age, gender, and height. Standard vertical reach height data can be obtained through large-scale sports testing statistics. If the user's actual maximum height is lower than a certain percentage of the standard value (e.g., lower than 80%), it indicates a problem with the user's explosive power or flexibility; if it is close to or higher than the standard value, it indicates that the user has good explosive power and flexibility.

[0053] The device's accelerometer records the speed changes of the user's body (such as arms or legs) during the upward movement within the high-point contact sub-data segment. The accelerometer measures the user's acceleration data in real time, and speed data is obtained by integrating the acceleration data. For example, as the user's arm moves upward to touch the target point, the accelerometer records the arm's acceleration value at certain time intervals (e.g., 0.01 seconds), and then calculates the speed value at each time point using numerical integration. The maximum and average speed values ​​during the upward movement are calculated. A reasonable speed range is set based on factors such as the user's sport and physical condition. If the user's upward speed is below this range, it indicates low muscle power output efficiency and insufficient explosive power; conversely, if the speed is within the reasonable range or higher, it indicates good explosive power.

[0054] Using a depth camera or joint position sensor, the system captures the extension angle and range of the user's arm during the touch process within the high-point touch data segment. The depth camera determines the positions of the shoulder, elbow, and wrist joints by detecting key points in the human skeleton. For example, arm span is obtained by calculating geometric parameters such as the distance from the shoulder to the wrist joint and the angle between the arm and the torso. Alternatively, the joint position sensor directly measures the flexion and extension angles of the elbow and shoulder joints to determine the arm extension. A reasonable arm span range is determined based on ergonomic and exercise physiology standards. If the user's arm span is less than this range, it may affect the maximum touch height, reflecting limited upper limb joint mobility; if it is within the reasonable range, it indicates good upper limb joint mobility, which is conducive to better explosive power and touch performance.

[0055] Using pressure sensors (installed on the device's landing platform or in the user's smart insole) and inertial measurement unit (IMU) sensors, the system detects the user's body stability upon landing after performing a vertical jump within the recovery data segment. The pressure sensors measure the pressure distribution of the user's feet upon landing, while the IMU sensors measure body acceleration and angular velocity. For example, the pressure sensors detect whether the pressure is evenly distributed upon landing, and the IMU sensors detect the degree of body sway at the moment of landing (such as changes in the acceleration and rotation angle of the body's center of gravity). Landing stability is determined by analyzing the pressure distribution and body sway data. If the pressure distribution is uneven upon landing and the body sway is large (e.g., the acceleration of the body's center of gravity exceeds a certain threshold, or the body rotation angle exceeds a certain range), landing stability is poor; conversely, if the pressure distribution is even and the body sway is small, landing stability is good.

[0056] The recovery sub-data segment records the time from when the user completes the high-point reach action to when the user's body returns to a relatively static initial posture (e.g., both feet on the ground, body upright). Changes in the user's body posture can be detected using the device's depth camera or posture sensor. For example, the depth camera captures the user's body posture in real time; when the speed and acceleration of various parts of the user's body are detected to be below a set static threshold, the user is considered to have returned to the initial posture, and the time difference from the completion of the high-point reach to this moment is calculated as the recovery time. A reasonable recovery time range is set based on factors such as the user's exercise intensity and physical condition. If the user's recovery time is too long, it indicates high muscle fatigue or insufficient control during the recovery phase of the movement; if the recovery time is within a reasonable range, it indicates good body control and recovery ability.

[0057] Using the device's depth camera and IMU sensor, the system tracks the user's center of gravity return path in real time within the recovery data segment. The depth camera constructs a 3D model of the user's body, calculating the changes in the center of gravity's position coordinates. The IMU sensor measures the acceleration and angular velocity of various body parts, combining this data with a human kinematic model to calculate the trajectory of the center of gravity. For example, during the process of a user falling from a height and returning to a standing position, the depth camera and IMU sensor work together to accurately record the movement path of the center of gravity in the forward, backward, left, right, and vertical directions. An ideal range for the center of gravity return path is set according to the standards of sports biomechanics. If the user's center of gravity return path deviates significantly from the ideal path (e.g., the center of gravity sways noticeably from side to side or jerks forward and backward during the return), it indicates problems with the user's coordination and control during the recovery phase; if the center of gravity return path is relatively smooth and close to the ideal path, it indicates that the user performed well in terms of movement integrity and recovery control.

[0058] The health perception results of the first behavior (reaction ability and balance stability analysis), the second behavior (neuromuscular control ability and attention maintenance analysis), the third behavior (explosive power and upper limb joint range of motion analysis), and the fourth behavior (motor integrity and recovery control ability analysis) are comprehensively analyzed. A multi-dimensional data fusion method can be used. For example, a behavioral health perception evaluation model can be constructed, using each sub-result as input features and performing a comprehensive calculation through mathematical methods such as weighted summation. For instance, a weight of 0.2 can be assigned to reaction ability, 0.2 to balance stability, 0.2 to neuromuscular control ability, 0.1 to attention maintenance, 0.1 to explosive power, 0.1 to upper limb joint range of motion, 0.05 to motor integrity, and 0.05 to recovery control ability (the weights can be adjusted according to actual application needs and expert experience). The scores of each sub-result are multiplied by their respective weights and then summed to obtain a comprehensive behavioral health perception score. The results of behavioral health perception are presented to users through an intuitive graphical interface, such as generating a comprehensive health dashboard that includes detailed scores and trend curves for each sub-item. Users can see their performance across different health behavior dimensions, such as reaction time, balance stability, and explosive power, along with specific scores and trends, as well as their overall behavioral health status. Simultaneously, the system can provide textual suggestions, pointing out the user's strengths and areas for improvement based on the comprehensive analysis results, and developing personalized health improvement plans for the user.

[0059] This approach comprehensively assesses a user's physical performance during exercise through multi-dimensional and multi-stage analysis, providing a holistic health behavior assessment.

[0060] In one possible implementation, the health perception module 50 performs multi-dimensional behavioral health perception based on the vertical reach monitoring dataset and the action tags to establish behavioral health perception results. The module further includes: time-stamping the vertical reach monitoring dataset, counting vertical reach frequencies, and establishing a first additional behavioral health perception result; performing action deformation perception on the time-stamped vertical reach monitoring dataset to establish a second additional behavioral health perception result; and using the first additional behavioral health perception result and the second additional behavioral health perception result to compensate for the behavioral health perception result.

[0061] Specifically, after the motion-sensing interaction module 30 completes the vertical reach monitoring, a vertical reach monitoring dataset with timestamps is acquired. For example, the dataset contains the start and end times of each user's vertical reach action. The vertical reach actions are counted by parsing the time information in the dataset. Time series analysis algorithms can be used to identify the time interval between each complete vertical reach action. When the time interval is greater than a set threshold (e.g., 2 seconds), it is considered a new vertical reach action. For example, in a 1-minute vertical reach monitoring dataset, 30 vertical reach actions are identified by time stamps, meaning the vertical reach frequency is 30 times / minute. The statistically obtained vertical reach frequency is compared with the standard vertical reach frequency range for similar sports. The standard range can be determined based on factors such as the user's age and physical condition. For example, for adolescent users, the standard vertical reach frequency range is 20-40 times / minute. If the user's actual vertical reach frequency is lower than this range, it indicates that the user's athletic ability and endurance need improvement; if it is within the range, it indicates that the user's vertical reach frequency is reasonable. This comparison result is used as the first additional behavioral health perception result.

[0062] Deep learning algorithms (such as convolutional neural networks) were used to analyze time-stamped vertical reach monitoring datasets. Based on 3D model data of user movements captured by depth cameras, a convolutional neural network was trained to recognize movement deformation features. For example, during the training phase, a large amount of 3D model data annotated with normal movements and deformed movements (such as abnormal arm flexion angles, insufficient leg extension, etc.) was used as training samples. During actual perception, the user's time-stamped vertical reach monitoring data was input into the trained model, and the model output the degree and type of user movement deformation. Based on the degree and type of deformation output by the model, the quality of the user's movement was evaluated. For example, if the model detected that the user's arm flexion angle was more than 30 degrees smaller than the standard movement during a vertical reach, and similar deformation occurred multiple times, it was considered that the user had a significant movement deformation problem, which might affect exercise performance and increase the risk of injury. This evaluation result was used as a second additional behavioral health perception result.

[0063] Based on existing behavioral health perception results (such as analysis results based on the preparation, guidance, reach, and recovery phases), compensation is achieved by incorporating first and second supplementary behavioral health perception results. For example, a weighted fusion method can be used, setting the weight of the original behavioral health perception result to 0.7, the weight of the first supplementary result to 0.15, and the weight of the second supplementary result to 0.15 (the weights can be adjusted according to practical application and expert experience). The final compensated behavioral health perception result is obtained through weighted calculation. The first supplementary behavioral health perception result supplements the assessment of the user's motor ability from the perspective of movement frequency, while the second supplementary behavioral health perception result supplements the assessment of the user's exercise safety and effectiveness from the perspective of movement quality. These two supplementary results can compensate for the shortcomings of the original analysis method in these aspects, making the final behavioral health perception result more comprehensive and accurate.

[0064] This approach effectively reduces errors in behavioral health perception by introducing two additional perceptual dimensions: frequency of touch and perception of motion deformation. For example, analysis based solely on the movement phase might overlook differences in user movement frequency and the impact of motion deformation on exercise effectiveness and safety. By compensating for these additional results, users' health behaviors can be assessed more accurately, such as precisely identifying situations where individual movement quality is acceptable, but the movement frequency is too low or frequent motion deformation leads to poor overall exercise results.

[0065] In one possible implementation, the system further includes: a matching module, used to perform abnormal health warning level matching based on the health perception results and generate matching results; and a warning issuance module, used to configure a warning signal based on the matching results and execute abnormal health behavior warning issuance.

[0066] Specifically, the matching module has a built-in warning level rule base, which defines the abnormal health warning levels corresponding to different health perception results. For example, the warning levels are divided into minor abnormality (Level 1 warning), moderate abnormality (Level 2 warning), and severe abnormality (Level 3 warning). When the health perception module outputs the behavioral health perception result, the matching module reads the result and compares it with the rules in the warning level rule base. For example, if the behavioral health perception result shows that the user's explosive power is less than 30% of the standard value and there are serious problems with the integrity of the movements, the matching module determines that it belongs to severe abnormality (Level 3 warning) according to the rules in the rule base and records the matching result. The matching result includes the user's identification information, a detailed description of the abnormal health behavior, and the corresponding warning level. For example, for the user with insufficient explosive power and poor movement integrity, the matching result is recorded as "User ID: XXX, Abnormal Health Behavior: Insufficient Explosive Power and Poor Movement Integrity, Warning Level: Level 3 Warning".

[0067] The early warning module configures corresponding early warning signals based on the matching results generated by the matching module. These signals can take various forms, such as visual signals (displaying warning information on the screen, flashing indicator lights), auditory signals (alarm sounds), or tactile signals (vibration feedback). For example, a level 3 warning is configured with a flashing red indicator light and a high-pitched alarm sound, while a detailed description of the abnormal health behavior and suggested measures are displayed on the device screen; a level 2 warning is configured with a yellow indicator light and a medium-pitched alarm sound, and a brief abnormal information is displayed on the screen; a level 1 warning is configured with a blue indicator light and a low-pitched alarm sound, and only a prompt message is displayed on the screen. The early warning module issues warnings to the user according to the configured signal method. For example, after a user completes a vertical movement, the device immediately activates the corresponding early warning signal based on the matching results.

[0068] This implementation method, through the collaborative work of the matching module and the early warning module, can promptly issue warnings for users' abnormal health behaviors. This helps users be alerted at an early stage of problems and take timely measures, such as adjusting exercise intensity and correcting posture, thereby effectively preventing potential health risks and avoiding more serious health problems caused by ignoring abnormal health behaviors.

[0069] In one possible implementation, the early warning module includes: a communication module for establishing device communication with the user's wearable device; an interaction module for establishing a time-series vital sign dataset after interacting with the wearable device based on the device communication; and a compensation module for configuring an early warning signal after compensating the matching result based on the time-series vital sign dataset.

[0070] Specifically, the communication module in the early warning and alert module establishes a connection with the user's wearable device (such as a smart bracelet, smartwatch, heart rate monitor, etc.) using Bluetooth, Wi-Fi, or other wireless communication protocols. For example, when the device starts up, the communication module automatically scans for available wearable devices in the vicinity. The user selects the wearable device to connect to on the device and enters the corresponding pairing information (such as device name, password, etc.). After pairing is completed, a communication link is established between the devices. The communication module is responsible for sending and receiving data, ensuring the stability and security of data transmission. For example, it sends instructions and data to the wearable device via Bluetooth at a certain data transmission rate (such as 1 Mbps), while simultaneously receiving data feedback from the wearable device. After establishing communication with the wearable device, the communication module can obtain basic information about the wearable device, such as device type, battery level, signal strength, etc. Simultaneously, it prepares for subsequent data interaction, ensuring that the early warning and alert module can obtain the wearable device's vital signs data in a timely manner.

[0071] The interaction module interacts with the wearable device via the communication module. For example, it sends a data request command to the wearable device, requesting it to send vital sign data, including heart rate, blood pressure, and blood oxygen saturation, at set time intervals (e.g., per second). Upon receiving the request, the wearable device sends the real-time monitored vital sign data back to the alert and warning module via the communication module. The interaction module organizes and stores the received data to create a time-series vital sign dataset. For example, heart rate data is arranged chronologically to form a heart rate time-series dataset, where each data point includes a timestamp and the corresponding heart rate value. This time-series dataset contains the user's physiological changes over a period of time. The interaction module can perform preliminary processing on the dataset, such as data cleaning (removing outliers, noise, etc.) and data fusion (integrating different types of data). For example, by analyzing the time series of heart rate and blood pressure data, it can identify the physiological trends of the user during exercise.

[0072] The compensation module comprehensively analyzes the time-series vital sign dataset and the matching results generated by the matching module. For example, if the matching results indicate that the user exhibits moderately abnormal health behavior (Level 2 warning), but the time-series vital sign dataset shows that the user's heart rate and blood pressure are within the normal range and blood oxygen saturation is high, indicating that the user's physiological state is relatively stable, the compensation module compensates for the matching results based on this vital sign data, for example, lowering the warning level from Level 2 to Level 1. The compensation algorithm can employ a rule-based approach, such as defining a series of compensation rules: "When the heart rate and blood pressure are within the normal range, the warning level is lowered by one level." Alternatively, machine learning methods can be used to train a model to learn the relationship between vital sign data and health behavior, automatically making compensation decisions. After compensation, the compensation module configures the warning signal according to the new warning level. For example, for a Level 1 warning, a blue indicator light and a low-pitched alarm sound are configured, and a brief prompt message is displayed on the device screen: "This user's health behavior is slightly abnormal; please adjust your exercise method."

[0073] After the compensation module completes the configuration of the warning signal, it sends the configuration information to other parts of the warning reporting module (such as visual, auditory, and tactile signal generators) to ensure that the warning signal can be accurately reported to the user in the set manner.

[0074] This approach acquires users' time-series vital sign datasets through communication and interaction with wearable devices, and can compensate for matching results by integrating physiological vital sign information. This allows early warning decisions to consider not only behavioral health perception results but also the user's real-time physiological state, avoiding warning errors that may arise from relying solely on behavioral data. For example, a user may exhibit minor behavioral abnormalities, but their physiological signs indicate a good physical condition; the compensation mechanism can prevent unnecessary over-warnings, improving the accuracy of early warning decisions.

[0075] In one possible implementation, the system includes: a recording module, used to evaluate the completion of the vertical reach task based on the vertical reach monitoring dataset and generate an evaluation record; and an incentive module, used to match reward points based on the evaluation record and distribute the reward points to the corresponding user account.

[0076] Specifically, the recording module acquires the complete height-reaching monitoring dataset output by the motion-sensing interaction module 30, including data such as the number of times the user reached the height, the height of each reach, and the time taken to complete the action. Simultaneously, it combines this with action tag information to determine whether the user completed the height-reaching task according to the standard action sequence. For example, by analyzing action tags, it determines whether the user completed the four stages: preparatory action, guided response action, high-point reach action, and recovery action. According to the set evaluation rules, if the number of completions reaches the preset target (e.g., 10 times) and the height of each reach is not lower than the minimum standard (e.g., 200cm), the task completion quality is judged to be high. The recording module organizes these evaluation results into an evaluation record, including basic user information (e.g., user ID), specific indicators of task completion (e.g., actual number of completions, average height, etc.), and a comprehensive evaluation level (e.g., excellent, good, satisfactory, unsatisfactory).

[0077] The incentive module has a built-in reward points rule library that matches corresponding reward points based on evaluation records. For example, a user with an excellent overall evaluation level receives 100 points; a good level receives 70 points; a satisfactory level receives 30 points; and an unsatisfactory level receives no points. The points rule library can also include other factors, such as the number of consecutive days of task completion, to increase the flexibility of the incentive system. The incentive module distributes the matched reward points to the corresponding user account through an interface associated with the user account. For example, it can send the points data to the user's app account or cloud account via network communication, while simultaneously updating the account's points balance. Users can view their points details in their account, such as the number of points earned this time and their total points.

[0078] This implementation, through the evaluation mechanism of the recording module and the reward points mechanism of the incentive module, can effectively motivate users to actively participate in the height-reaching task. In order to obtain higher reward points, users will be more motivated to complete the task and improve the quality of task completion, thereby increasing user stickiness and usage frequency of the system.

[0079] This application's embodiment employs a system that, upon user initiation of interaction, first performs identity authentication. After successful authentication, the device is activated, and user data is retrieved to configure a personalized vertical reach task. Subsequently, the motion tracking module is activated to locate the user, monitors the vertical reach action in real time, and generates a dataset. Then, through a calibration template, four action stages are defined: preparation, guided response, high point arrival, and recovery, and these stages are labeled. Finally, the health perception channel is initialized based on the user profile, and multi-dimensional behavioral health analysis is performed based on the action data and labels to output behavioral health perception results. These technical means solve the technical problems of insufficient accuracy in action monitoring and comprehensiveness in health perception in existing health behavior monitoring, achieving a more accurate and comprehensive technical effect in health behavior monitoring results.

[0080] In the above text, refer to Figure 1 A health behavior monitoring system based on motion-sensing interaction according to an embodiment of the present invention has been described in detail. Next, reference will be made to... Figure 2 A method for monitoring health behaviors based on haptic interaction according to an embodiment of the present invention is described.

[0081] The health behavior monitoring method based on somatosensory interaction according to embodiments of the present invention is used to solve the technical problems of insufficient accuracy of motion monitoring and comprehensiveness of health perception in existing health behavior monitoring, so as to achieve the technical effect of making health behavior monitoring results more accurate and comprehensive.

[0082] The health behavior monitoring method based on motion-sensing interaction includes: after a user initiates the interaction, the user is authenticated; upon successful authentication, the device is started; user data is retrieved based on the authentication result, and a height-reaching task is configured based on the data retrieval result, which includes the user profile and the user's historical height-reaching data; after the height-reaching task is configured, the tracking unit in the motion-sensing interaction module is activated to perform user authentication and positioning, and then the user's height-reaching data is monitored to establish a height-reaching monitoring dataset; the height-reaching monitoring dataset is divided into actions using a calibration template, and action labels are established, including labels for preparatory actions, guided response actions, high-point reaching actions, and recovery actions; after initially configuring the health perception channel based on the user profile, multi-dimensional behavioral health perception is performed based on the height-reaching monitoring dataset and the action labels to establish behavioral health perception results.

[0083] The process of performing multi-dimensional behavioral health perception based on the height monitoring dataset and the action tags, and establishing behavioral health perception results, may further include: dividing the height monitoring dataset into data segments based on the action tags, establishing preparatory action sub-data segments, guided response sub-data segments, high point reach sub-data segments, and recovery sub-data segments; calling the parameter set in the health perception channel that matches the user profile to construct a multi-dimensional behavioral health perception path mapped to the sub-data segments; and using the multi-dimensional behavioral health perception path to perceive the behavioral characteristics of the mapped sub-data segments and establish behavioral health perception results.

[0084] The process of using the multidimensional behavioral health perception path to perceive behavioral features of mapping sub-data segments and establish behavioral health perception results can further include: perceiving preparatory behavioral features of preparatory action sub-data segments through the preparatory action behavioral health perception path, wherein the preparatory behavioral feature perception includes initial reaction delay perception and trunk sway amplitude perception; using the preparatory behavioral feature perception to perform reaction ability and balance stability analysis to establish a first behavioral health perception result; perceiving guiding behavioral features of guiding response sub-data segments through the guided response behavioral health perception path, wherein the guiding behavioral feature perception includes target deviation distance perception and following delay perception; using the guided behavioral feature perception to perform neuromuscular control ability and attention maintenance analysis to establish a second behavioral health perception result; and establishing a behavioral health perception result based on the first behavioral health perception result and the second behavioral health perception result.

[0085] The process of establishing behavioral health perception results based on the first and second behavioral health perception results can further include: perceiving the reach behavior characteristics of the high-point reach sub-data segment through the high-point reach behavioral health perception path, wherein the reach behavior characteristic perception includes maximum height characteristic perception, upward speed characteristic perception, and arm span characteristic perception; analyzing explosive power and upper limb joint range of motion based on the reach behavior characteristic perception to establish a third behavioral health perception result; perceiving the recovery behavior characteristics of the recovery sub-data segment through the recovery behavior health perception path, wherein the recovery behavior characteristic perception includes landing stability perception, recovery time perception, and center of gravity return path perception; analyzing movement integrity and recovery control ability based on the recovery behavior characteristic perception to establish a fourth behavioral health perception result; and establishing behavioral health perception results based on the first, second, third, and fourth behavioral health perception results.

[0086] The process of performing multidimensional behavioral health perception based on the height monitoring dataset and the action tags to establish behavioral health perception results may further include: time-stamping the height monitoring dataset, counting the frequency of height measurements, and establishing a first additional behavioral health perception result; performing action deformation perception on the time-stamped height monitoring dataset to establish a second additional behavioral health perception result; and using the first additional behavioral health perception result and the second additional behavioral health perception result to compensate for the behavioral health perception result.

[0087] The method may further include: matching abnormal health warning levels based on the health perception results to generate matching results; configuring warning signals based on the matching results; and issuing warnings for abnormal health behaviors.

[0088] The configuration of the warning signal based on the matching result may further include: establishing device communication with the user's wearable device; interacting with the wearable device according to the device communication to establish a time-series vital sign dataset; and compensating for the matching result according to the time-series vital sign dataset to configure the warning signal.

[0089] The process may further include: after a user initiates an interaction, the user is authenticated; once authentication is successful, the device is started; if the user is determined to be a new user, static data collection of the user is performed to establish a first learning dataset; user input data of the user is obtained to establish a second learning dataset; a user profile is created based on the first learning dataset and the second learning dataset, and the device is started.

[0090] The method may further include: evaluating the completion of the height-reaching task based on the height-reaching monitoring dataset and generating an evaluation record; matching reward points based on the evaluation record and distributing the reward points to the corresponding user account.

[0091] The health behavior monitoring system based on somatosensory interaction provided in the embodiments of the present invention can execute the health behavior monitoring method based on somatosensory interaction provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0092] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application. In some cases, the actions or steps described in this application can be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A health behavior monitoring system based on motion-sensing interaction, characterized in that, The system includes: The startup module is used to authenticate the user after the user performs a startup interaction, and to start the device after the authentication is successful. The task generation module is used to retrieve user data based on the identity authentication result and configure the height-reaching task based on the user data retrieval result. The user data retrieval result includes user profile and user historical height-reaching data. The motion-sensing interaction module is used to activate the tracking unit in the motion-sensing interaction module after the height-reaching task is configured, perform user authentication and positioning, monitor the user's height-reaching activity, and establish a height-reaching monitoring dataset. The action decomposition module is used to divide the action of the height monitoring dataset using a calibration template and establish action labels. The action labels include labels for preparatory actions, guiding response actions, high point reaching actions, and recovery actions. The health perception module is used to initially configure the health perception channel based on the user profile, and then perform multi-dimensional behavioral health perception based on the height monitoring dataset and the action tags to establish behavioral health perception results. In the health perception module, the behavioral feature perception of the mapped sub-data segments is performed using the multi-dimensional behavioral health perception path to establish behavioral health perception results, including: The preparatory behavior characteristics of the preparatory action sub-data segment are perceived through the preparatory action behavior health perception path. The preparatory behavior characteristics perception includes the perception of the initial reaction delay and the perception of the trunk swing amplitude. Using the aforementioned pre-behavioral characteristics, reaction ability and balance stability are analyzed to establish the first behavioral health perception results. The guidance behavior characteristics of the guidance response sub-data segment are perceived through the guidance response behavior health perception path. The guidance behavior characteristics perception includes target deviation distance perception and follow-up delay perception. The neuromuscular control ability and attention maintenance are analyzed using the aforementioned guided behavioral feature perception to establish the second behavioral health perception results. A behavioral health perception result is established based on the first behavioral health perception result and the second behavioral health perception result; In the health perception module, a behavioral health perception result is established based on the first behavioral health perception result and the second behavioral health perception result, including: The high-point reach behavior health perception path is used to perceive the reach behavior characteristics of the high-point reach sub-data segment. The reach behavior characteristic perception includes maximum height characteristic perception, upward speed characteristic perception, and arm span characteristic perception. Based on the perceived characteristics of the reach behavior, explosive force and upper limb joint range of motion are analyzed to establish the third behavior health perception results; The recovery behavior characteristics of the recovery sub-data segment are perceived through the recovery behavior health perception path. The recovery behavior characteristics perception includes landing stability perception, recovery time perception, and center of gravity return path perception. Based on the perceived characteristics of the recovery behavior, the integrity of the movement and the ability to recover control are analyzed to establish the fourth behavior health perception result; A behavioral health perception result is established based on the first behavioral health perception result, the second behavioral health perception result, the third behavioral health perception result, and the fourth behavioral health perception result.

2. The health behavior monitoring system based on somatosensory interaction as described in claim 1, characterized in that, In the health perception module, multidimensional behavioral health perception is performed based on the vertical reach monitoring dataset and the action tags to establish behavioral health perception results, including: Based on the action tags, the data segmentation of the height monitoring dataset is carried out to establish a preparatory action sub-data segment, a guiding response sub-data segment, a high point reach sub-data segment, and a recovery sub-data segment. Call the parameter set in the health perception channel that matches the user profile to construct a multi-dimensional behavior health perception path that maps to the sub-data segments; The behavioral characteristics of the mapped sub-data segments are perceived using the multi-dimensional behavioral health perception path, and behavioral health perception results are established.

3. The health behavior monitoring system based on somatosensory interaction as described in claim 1, characterized in that, The health perception module, which performs multidimensional behavioral health perception based on the vertical reach monitoring dataset and the action tags, and establishes behavioral health perception results, also includes: After time-stamping the height monitoring dataset, the frequency of height measurements is counted, and the first additional behavioral health perception result is established. Perform motion deformation perception on the height monitoring dataset after time stamping, and establish a second additional behavioral health perception result; Compensation for behavioral health perception results is performed using the first additional behavioral health perception result and the second additional behavioral health perception result.

4. The health behavior monitoring system based on somatosensory interaction as described in claim 1, characterized in that, The system also includes: The matching module is used to match abnormal health warning levels based on the health perception results and generate matching results; The early warning module is used to configure early warning signals based on the matching results and to issue early warnings for abnormal health behaviors.

5. The health behavior monitoring system based on somatosensory interaction as described in claim 4, characterized in that, The early warning dispatch module includes: The communication module is used to establish device communication with the user's wearable device; The interaction module is used to establish a time-series vital sign dataset after interacting with the wearable device based on the device communication. The compensation module is used to compensate the matching results based on the time-series vital sign dataset and then configure an early warning signal.

6. The health behavior monitoring system based on somatosensory interaction as described in claim 1, characterized in that, The startup module also includes: If a user is determined to be a new user, static data collection of the user is performed to establish the first learning dataset; Obtain user input data and build a second learning dataset; User profiles are created based on the first learning dataset and the second learning dataset, and device startup is performed.

7. The health behavior monitoring system based on somatosensory interaction as described in claim 1, characterized in that, The system includes: The recording module is used to evaluate the completion of the height-reaching task based on the height-reaching monitoring dataset and generate an evaluation record. The incentive module is used to match reward points based on the evaluation records and distribute the reward points to the corresponding user accounts.

8. A health behavior monitoring method based on somatosensory interaction, characterized in that, The method is implemented by the health behavior monitoring system based on somatosensory interaction as described in any one of claims 1-7, and the method includes: After the user initiates the startup interaction, the user's identity is authenticated. Once the authentication is successful, the device is started. User data is retrieved based on the identity authentication result, and a height-reaching task is configured based on the user data retrieval result. The user data retrieval result includes user profile and user historical height-reaching data. After the height measurement task is configured, the tracking unit in the motion-sensing interaction module is activated to perform user authentication and positioning, and then the user's height measurement is monitored to establish a height measurement monitoring dataset. The action classification of the height monitoring dataset is performed using a calibration template, and action labels are established. The action labels include labels for preparatory actions, guided response actions, high point reaching actions, and recovery actions. After initially configuring the health perception channel based on the user profile, multi-dimensional behavioral health perception is performed based on the height monitoring dataset and the action tags to establish behavioral health perception results. In the health perception module, the behavioral characteristics of the mapped sub-data segments are perceived using the multi-dimensional behavioral health perception path to establish behavioral health perception results. This includes: perceiving the preparatory behavioral characteristics of the preparatory action sub-data segments through the preparatory action behavioral health perception path, whereby the preparatory behavioral characteristics perception includes initial reaction delay perception and trunk sway amplitude perception; using the preparatory behavioral characteristics perception to perform reaction ability and balance stability analysis to establish a first behavioral health perception result; perceiving the guiding behavioral characteristics of the guiding response sub-data segments through the guided response behavioral health perception path, whereby the guiding behavioral characteristics perception includes target deviation distance perception and following delay perception; using the guided behavioral characteristics perception to perform neuromuscular control ability and attention maintenance analysis to establish a second behavioral health perception result; and establishing a behavioral health perception result based on the first behavioral health perception result and the second behavioral health perception result. The health perception module establishes behavioral health perception results based on the first and second behavioral health perception results, including: perceiving the reach behavior characteristics of the high-point reach sub-data segment through the high-point reach behavioral health perception path, wherein the reach behavior characteristic perception includes maximum height characteristic perception, upward speed characteristic perception, and arm span characteristic perception; analyzing explosive power and upper limb joint range of motion based on the reach behavior characteristic perception to establish a third behavioral health perception result; perceiving the recovery behavior characteristics of the recovery sub-data segment through the recovery behavior health perception path, wherein the recovery behavior characteristic perception includes landing stability perception, recovery time perception, and center of gravity return path perception; analyzing movement integrity and recovery control ability based on the recovery behavior characteristic perception to establish a fourth behavioral health perception result; and establishing behavioral health perception results based on the first, second, third, and fourth behavioral health perception results.

Images