Multi-scene application method and system of sports watch

Abstract

The invention relates to the technical field of health management, and discloses a multi-scene application method and system for a sports watch, and the method comprises the steps: obtaining user account information, constructing a physical condition feedback model, obtaining sports watch detection performance information and a long-term monitoring target of a user, constructing a target monitoring algorithm, obtaining a real-time scene through a user interaction instruction, and carrying out the real-time monitoring of the real-time scene. The method comprises the following steps: acquiring scene detection data, analyzing and switching to a corresponding detection mode to acquire data, substituting the scene detection data into a target monitoring algorithm, generating and providing a scene guidance countermeasure, dynamically adjusting a physical condition feedback model according to the scene detection data, and realizing accurate physical condition information feedback. Through multi-scene intelligent switching and real-time feedback, the data acquisition validity and user experience of the sports watch are improved, accurate and dynamic health monitoring and guidance are realized, and the problem that the available scene of the sports watch in the prior art is single is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of health management, and in particular to a multi-scenario application method and system for a sports watch. Background Art

[0002] With the continuous advancement of technology and the increasing attention paid to health management, smart wearable devices, especially sports watches, are being used more and more widely in the field of health management. Traditional sports watches mainly provide basic health feedback by collecting users' exercise data (such as steps, heart rate, calorie consumption, etc.). However, with the diversification of user needs and the increasing complexity of health management, a single data collection and feedback model can no longer meet users' requirements for personalization, real-timeness and accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide a multi-scenario application method and system for a sports watch, aiming to solve the problem of a single applicable scenario of a sports watch in the prior art.

[0004] The present invention is implemented as follows. In a first aspect, the present invention provides a multi-scenario application method for a sports watch, comprising: Obtaining the user's account registration information, and performing a digital simulation of the user's physical condition based on the account registration information to obtain a user's physical condition feedback model; Acquiring detection performance information of the sports watch and a long-term monitoring goal of the user, and constructing a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal to obtain a target monitoring algorithm based on the physical condition feedback model; Acquiring a real-time scene of the user through interactive instructions with the user, analyzing the detection mode of the real-time scene according to the target monitoring algorithm, and switching the sports watch to a corresponding detection mode according to the analysis result to collect scene detection data of the real-time scene; Substituting the scene detection data into the target monitoring algorithm, and allowing the target monitoring algorithm to perform real-time analysis and countermeasure generation on the scene detection data according to the physical condition feedback model, so as to obtain scene guidance countermeasures and perform interactive guidance operations on the user; The target monitoring algorithm is used to synchronously adjust the model parameters of the physical condition feedback model according to the scene detection data, so as to realize feedback of the user's physical condition information through the physical condition feedback model.

[0005] In a second aspect, the present invention provides a multi-scenario application system for a sports watch, configured to implement the multi-scenario application method for a sports watch described in any one of the first aspects, comprising: A physical feedback module is used to obtain the user's account registration information and perform digital simulation of the user's physical condition based on the account registration information to obtain a physical condition feedback model of the user; an algorithm construction module, configured to obtain detection performance information of the sports watch and a long-term monitoring goal of the user, and construct a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal, so as to obtain a target monitoring algorithm based on the physical condition feedback model; a scene detection module, configured to obtain the user's real-time scene through interactive instructions with the user, analyze the real-time scene for a detection mode according to the target monitoring algorithm, and switch the sports watch to a corresponding detection mode based on the analysis result to collect scene detection data for the real-time scene; An interactive guidance module, configured to substitute the scene detection data into the target monitoring algorithm, causing the target monitoring algorithm to perform real-time analysis and generate countermeasures on the scene detection data according to the physical condition feedback model, so as to obtain scene guidance countermeasures and perform interactive guidance operations on the user; The model adjustment module is used to synchronously adjust the model parameters of the physical condition feedback model according to the scene detection data through the target monitoring algorithm, so as to realize feedback of the user's physical condition information through the physical condition feedback model.

[0006] The present invention provides a multi-scenario application method for a sports watch, which has the following beneficial effects: The present invention obtains user account information, constructs a physical condition feedback model, obtains sports watch detection performance information and user long-term monitoring goals, constructs a target monitoring algorithm, obtains real-time scenes through user interaction instructions, analyzes and switches to corresponding detection modes to collect data, substitutes scene detection data into the target monitoring algorithm, generates and provides scene guidance countermeasures, dynamically adjusts the physical condition feedback model according to the scene detection data, and realizes accurate physical condition information feedback. This method provides personalized health management, improves the data collection effectiveness and user experience of sports watches through multi-scene intelligent switching and real-time feedback, realizes accurate and dynamic health monitoring and guidance, and solves the problem of single application scenarios of sports watches in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a schematic diagram of the steps of a multi-scenario application method for a sports watch provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a multi-scenario application system for a sports watch provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0008] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0009] The implementation of the present invention is described in detail below with reference to specific embodiments.

[0010] Reference Figure 1 、 Figure 2 As shown, a preferred embodiment of the present invention is provided.

[0011] In a first aspect, the present invention provides a multi-scenario application method for a sports watch, comprising: S1: Obtaining the user's account registration information, and performing a digital simulation of the user's physical condition based on the account registration information to obtain a user's physical condition feedback model; S2: Acquire detection performance information of the sports watch and the long-term monitoring goal of the user, and construct a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal to obtain a target monitoring algorithm based on the physical condition feedback model; S3: obtaining the real-time scene of the user through interactive instructions with the user, analyzing the detection mode of the real-time scene according to the target monitoring algorithm, and switching the sports watch to a corresponding detection mode according to the analysis result to collect scene detection data of the real-time scene; S4: Substituting the scene detection data into the target monitoring algorithm, and causing the target monitoring algorithm to perform real-time analysis and generate countermeasures on the scene detection data according to the physical condition feedback model, so as to obtain scene guidance countermeasures and perform interactive guidance operations on the user; S5: Synchronously adjusting the model parameters of the physical condition feedback model according to the scene detection data through the target monitoring algorithm, so as to realize feedback of the user's physical condition information through the physical condition feedback model.

[0012] Specifically, in step S1 of the embodiment provided by the present invention, the user registers or logs in to an account through a sports watch or related application and enters personal information, which includes: gender, age, height, weight, and medical history (such as hypertension, diabetes, heart disease, etc.). Data collection can be carried out through the interactive interface of the sports watch (such as touch screen, voice input, etc.) or synchronously with the mobile phone application.

[0013] More specifically, the user's physical condition is digitally simulated based on the account registration information. According to the gender, age, height, weight and other information provided by the user, the system first establishes a basic body parameter model, which usually includes: Body mass index (BMI) model: BMI is calculated by height and weight to assess whether there are problems such as obesity or underweight; Basal metabolic model: Based on age, gender, weight and other data, the minimum daily calorie requirement (ie basal metabolic rate) is estimated; Cardiovascular function model: Combined with age, gender, weight, athletic ability and other data, cardiovascular health status is assessed; Athletic ability model: Based on weight, height, exercise history and other information, the user's athletic ability is inferred, including endurance, strength, flexibility, etc.

[0014] More specifically, the various models (such as BMI, basal metabolism, cardiovascular function, etc.) are synergistically combined to form a comprehensive physical condition feedback model. This model not only considers each independent parameter, but also the interaction between them. For example, the correlation between BMI and cardiovascular health and exercise capacity can be optimized using multidimensional modeling methods (such as machine learning algorithms or statistical regression models) to make the feedback model more accurate.

[0015] More specifically, based on the results of the above model combination, the system automatically generates a user's physical condition feedback model and displays it to the user in the form of charts or text on the watch or application interface. The feedback content may include: the user's overall health status assessment (such as whether the weight is healthy, whether the metabolism is normal, etc.), possible health risks (such as cardiovascular disease risk, insufficient exercise capacity, etc.), and personalized suggestions for health conditions (such as dietary suggestions, exercise amount recommendations, chronic disease management tips, etc.). It is understandable that personalized modeling is performed based on the user's basic information to ensure that the health feedback received by each user is relevant to his or her specific situation. The model can adjust exercise and diet recommendations based on the user's actual situation to help users achieve more reasonable physical condition improvement goals. Through comprehensive analysis of multiple body parameters, the health feedback obtained is more accurate and can detect potential health problems, such as abnormal weight, metabolic problems, cardiovascular disease risks, etc., to provide users with early warnings. Using deep digital modeling, feedback on physical condition can cover a wider range of health dimensions and accurately simulate and predict. The user's physical condition feedback model is not only generated at the time of initial registration, but can also be updated and adjusted in real time with the continued use of the sports watch, thereby gradually improving the health management plan. Combined with the user's exercise, diet, rest and other behavioral data, the model can be automatically optimized to respond to changes in the user's physical condition in real time and achieve long-term health monitoring.

[0016] Specifically, in step S2 of the embodiment provided by the present invention, the types and performance parameters of built-in sensors are obtained, including acceleration sensors, gyroscopes, heart rate sensors, temperature sensors, blood oxygen sensors, ECG (electrocardiogram) modules, etc. The obtained content includes: detection frequency (such as Hz), accuracy range (such as ±0.5 bpm error), power consumption, whether continuous detection or scene switching is supported, and data processing capabilities, including the computing power of the watch chip, cache capacity, and data synchronization frequency with the cloud / mobile terminal.

[0017] More specifically, to determine the user's long-term monitoring goals, the user can set or infer the following long-term monitoring goals during the initial setting or system learning process: weight control (fat loss / muscle gain), sleep optimization, heart rate / blood pressure management, chronic disease monitoring (such as hypertension, diabetes), physical fitness / endurance improvement, mood and stress monitoring (can be combined with EDA and other sensors). The system can also intelligently predict the user's long-term goals through historical health data, scenario habits, interactive feedback, etc.

[0018] More specifically, the long-term monitoring goals are matched with the performance of the watch. Based on the goals, the system deduces the types of body parameters that need to be monitored and the accuracy requirements: for example, weight management requires focusing on monitoring exercise volume, calorie consumption, basal metabolism, etc.; sleep optimization pays more attention to heart rate variability, body movement amplitude, skin temperature, etc.; based on the above monitoring requirements, the system will match the sensors supported by the sports watch and determine the monitoring strategy: if a sensor supports continuous monitoring, the continuous mode is enabled; if an indicator does not support high-precision monitoring, an estimation model is selected or the user is reminded to use external equipment for assistance.

[0019] More specifically, a rule engine, machine learning model or deep learning model is used to perform target prediction and analysis based on the feedback model; a personalized parameter adjustment mechanism is introduced: the model weights will be adjusted as age increases or lifestyle habits change, and the key monitoring points and data sampling frequencies of each day / week / month will be clarified; watch resources are reasonably allocated, taking into account both accuracy and battery life, and a reasonable threshold range is set for each long-term goal; once the safety value is exceeded, the system will prompt, intervene or suggest adjustment plans through the watch interface or mobile terminal.

[0020] More specifically, the constructed monitoring algorithm is coupled with the physical condition feedback model to form a dynamic adjustment system; the model will be optimized as real-time detection data changes, gradually improving prediction accuracy and feedback intelligence.

[0021] It is understandable that each user's body feedback model generates a corresponding monitoring algorithm due to their different long-term goals. It is no longer a universal solution, but a "customized health consultant". The detection capabilities of the watch are fully utilized to avoid waste of resources (such as unnecessary high-frequency detection); the monitoring algorithm clearly defines the detection focus and rhythm, so that the system can identify risks and provide feedback in a timely manner at critical moments. The system can support multiple long-term monitoring goals at the same time, and coordinate resources and algorithm priorities according to weights during the monitoring process; for example, a user wants to lose weight and improve sleep. The system can focus on monitoring exercise and calories during the day and switch to sleep-related indicators at night.

[0022] Specifically, in step S3 of the embodiment provided by the present invention, the user actively inputs the current scene (such as running, working, sleeping, etc.) through the watch interface, mobile app or voice assistant, and the watch uses built-in sensors and historical data to automatically identify the user's current scene (such as determining whether he is exercising through the accelerometer, determining whether he is resting through heart rate variability, etc.).

[0023] More specifically, the acquired real-time scene information is matched with the preset scene library to determine the current scene category. The target monitoring algorithm determines the required detection mode based on the current scene and the user's health goals. The detection mode includes detection frequency, detection parameter types, detection accuracy, etc. Based on the algorithm analysis results, the system automatically adjusts the watch's detection mode, turns on or off specific sensors, adjusts the sensor's operating frequency, and switches the detection algorithm (such as switching from low-power mode to high-precision mode); ensures that the watch's computing resources and battery resources are reasonably allocated in different detection modes to ensure the continuity and accuracy of detection.

[0024] More specifically, after switching to the corresponding detection mode, the watch begins to collect scene detection data of real-time scenes. The collected data includes heart rate, number of steps, movement trajectory, sleep quality and other health parameters related to the current scene. The detection data is synchronized in real time or periodically to the mobile app or cloud server via Bluetooth or Wi-Fi for further analysis and storage.

[0025] It is understandable that the system dynamically adjusts the detection mode according to the real-time scenario to ensure that the collected data is more targeted and accurate, avoids the generation of invalid data, and maximizes the battery life of the watch by reasonably allocating the detection frequency and sensor working mode. At the same time, the continuity and accuracy of the detection are guaranteed. The user only needs simple interaction or no active operation, and the system can intelligently identify the scene and adjust the detection mode to provide a better user experience and more accurate health monitoring. According to different real-time scenarios and users' health goals, personalized health monitoring and suggestions are provided to help users better manage their own health. The system can realize dynamic monitoring in various scenarios of users' daily life (such as exercise, work, sleep, etc.) and provide comprehensive health management services.

[0026] Specifically, in step S4 of the embodiment provided by the present invention, scene detection data obtained from the watch sensor, including heart rate, number of steps, motion trajectory, sleep quality, etc., are collected and organized, and the detection data is preprocessed, such as denoising and normalization, to ensure data quality and consistency, and the preprocessed scene detection data is imported into the input interface of the target monitoring algorithm for further analysis.

[0027] More specifically, the target monitoring algorithm analyzes the current test data based on the physical condition feedback model. The physical condition feedback model includes but is not limited to the following: physiological parameters (such as heart rate, blood oxygen, blood pressure), behavioral data (such as exercise volume, sleep quality), historical health data (such as past medical history, long-term trends). The target monitoring algorithm analyzes the input test data in real time to identify the user's current health status and potential problems, such as abnormal heart rate, lack of exercise, poor sleep quality, etc.

[0028] More specifically, based on the results of actual situation analysis, the target monitoring algorithm searches for the most suitable countermeasures for the current health status from the preset countermeasure library, and combines the current detection data and the countermeasure library to generate personalized scenario-guidance countermeasures. The countermeasures may include: exercise suggestions (such as increasing walking frequency and stretching exercises), health reminders (such as prompting deep breathing and drinking water), and rest arrangements (such as recommending early bedtime and taking a nap).

[0029] More specifically, the generated scenario guidance measures are conveyed to users through watches, mobile apps or voice assistants. The push methods can be notification reminders, voice prompts, vibration reminders, etc. Users can perform corresponding operations based on the received guidance measures and provide feedback through the device (such as confirming execution, adjusting plans, etc.). The system continuously adjusts and optimizes subsequent guidance measures based on user feedback to improve applicability and user satisfaction.

[0030] It is understandable that the system can quickly analyze the user's current health status based on the data collected in real time, provide timely and accurate health feedback, help users maintain good health, and provide customized health advice based on the user's real-time health data and historical health records to improve the effectiveness and pertinence of the advice. The system can dynamically adjust health advice based on user feedback and behavior, continuously optimize the applicability of countermeasures, ensure the continuity and effectiveness of health management, and help users develop good health habits, improve health awareness, and prevent potential health problems through real-time health reminders and guidance. It provides a variety of interactive methods (such as notification reminders, voice prompts, vibration reminders, etc.) to ensure that users can receive health advice in a timely manner and improve user experience and satisfaction.

[0031] Specifically, in step S5 of the embodiment provided by the present invention, the user's real-time scene detection data is collected, including but not limited to heart rate, blood pressure, blood oxygen, exercise volume, sleep quality, etc., and the collected data is preprocessed, such as denoising and normalization, to ensure the accuracy and consistency of the data. The preprocessed data is input into the current physical condition feedback model to perform a preliminary health status analysis and generate preliminary health status feedback information, such as current heart rate status, exercise status, sleep quality assessment, etc.

[0032] More specifically, the target monitoring algorithm determines whether the model parameters need to be adjusted based on the preliminary analysis results and the user's historical health data, compares the current analysis results with the user's long-term trend data, identifies potential deviations or deficiencies in the model, designs and implements a parameter adjustment algorithm, and dynamically adjusts the parameters of the physical condition feedback model based on the scene detection data. Commonly used methods include: gradient descent method: adjusts the model parameters according to the error to minimize the error, Bayesian optimization: optimizes the parameters through a probability model to find the optimal parameter combination, online learning algorithm: updates the model parameters in real time to adapt the model to the latest data changes, and synchronously updates the adjusted parameters to the physical condition feedback model to ensure the real-time and accuracy of the model.

[0033] More specifically, the adjusted model is used to re-analyze the scene detection data to generate updated health status feedback information, ensuring that the feedback information is more accurate and more in line with the user's actual situation. The updated health status feedback information is pushed to the user through a watch, mobile phone application or other terminal device, providing detailed health advice, such as adjusting exercise plans, dietary recommendations, rest arrangements, etc., recording the user's response and implementation of health status feedback information, and collecting user subjective feedback, such as satisfaction with health advice, execution difficulty, etc. Based on user feedback, the model parameters are further optimized and the adjustment algorithm is formed to form a closed-loop system, continuously improving the accuracy of the model and user experience.

[0034] It is understandable that by adjusting the model parameters in real time, the physical condition feedback model can dynamically adapt to the individual differences and status changes of users, improve the flexibility and accuracy of the model, and the adjusted model can more accurately reflect the user's health status, provide more accurate health feedback and suggestions, and help users make more informed health decisions. Through the closed-loop system of user feedback and model adjustment, the physical condition feedback model is continuously optimized, and the accuracy and effectiveness of the model are gradually improved. The model parameters are dynamically adjusted to better reflect changes in individual health status, provide personalized health management plans, and enhance the user's health management experience. Through accurate health feedback and personalized health suggestions, the user's satisfaction and trust in the health management system are improved, and user compliance is enhanced.

[0035] The present invention provides a multi-scenario application method for a sports watch, which has the following beneficial effects: The present invention obtains user account information, constructs a physical condition feedback model, obtains sports watch detection performance information and user long-term monitoring goals, constructs a target monitoring algorithm, obtains real-time scenes through user interaction instructions, analyzes and switches to corresponding detection modes to collect data, substitutes scene detection data into the target monitoring algorithm, generates and provides scene guidance countermeasures, dynamically adjusts the physical condition feedback model according to the scene detection data, and realizes accurate physical condition information feedback. This method provides personalized health management, improves the data collection effectiveness and user experience of sports watches through multi-scene intelligent switching and real-time feedback, realizes accurate and dynamic health monitoring and guidance, and solves the problem of single application scenarios of sports watches in the prior art.

[0036] Preferably, the steps of obtaining the user's account registration information and performing digital simulation of the user's physical condition based on the account registration information to obtain the user's physical condition feedback model include: S11: Obtaining the user's account registration information; wherein the account registration information includes the user's gender, age, height, weight, and medical history; S12: performing in-depth analysis and digital modeling of the user's physical parameters based on the account registration information to obtain the user's height and weight index model, basal metabolic model, cardiovascular function model, and exercise capacity model; S13: Synergistically combining the user's height and weight index model, basal metabolic model, cardiovascular function model, and exercise capacity model to obtain a user's physical condition feedback model.

[0037] Specifically, basic information of users, including gender, age, height, weight, medical history, etc., is collected. Users fill in and submit this information through the application or device to ensure the accuracy and completeness of the data.

[0038] More specifically, in-depth analysis and digital modeling of body parameters, including the body mass index (BMI) model, are used to calculate BMI (Body Mass Index). The formula is: BMI = weight (kg) / height (m)², and BMI values are used for classification, such as normal, overweight, and obese. The basal metabolic model calculates BMR (Basal Metabolic Rate). The commonly used formula is the Harris-Benedict formula: for men, BMR = 88.362 + (13.397 × weight (kg)) + (4.799 × height (cm)) - (5.677 × age); for women, BMR = 447.593 + (9.247 × weight (kg)) + (3.098 × height (cm)) - (4.330 × age). Daily energy requirements are estimated based on BMR values.

[0039] More specifically, the cardiovascular function model assesses cardiovascular health by integrating the user's age, gender, and medical history (such as hypertension, heart disease, etc.) to establish a cardiovascular function model, and uses a risk scoring system (such as the Framingham risk score) to assess the risk of cardiovascular disease; the athletic ability model assesses athletic ability by assessing the user's athletic ability based on the user's weight, height, age, gender and other information, combined with medical history, and establishing an athletic ability model to predict the user's performance and endurance in specific sports.

[0040] More specifically, the above models (BMI model, BMR model, cardiovascular function model, and exercise capacity model) are synergistically combined to form a comprehensive physical condition feedback model through multi-model integration. By comprehensively analyzing the relationship between different models, more comprehensive user health status information can be obtained. For example, the BMR and exercise capacity models can be combined to evaluate the user's exercise and nutritional needs; the cardiovascular function model and BMI model can be combined to evaluate the user's cardiovascular health risks.

[0041] More specifically, it generates feedback on physical condition and a detailed health status report based on the analysis results of the comprehensive model. The report content includes: BMI assessment, basal metabolic rate, cardiovascular health status, exercise capacity analysis, etc. Based on the analysis results, it provides personalized health management suggestions, such as diet adjustments, exercise plans, disease prevention measures, etc. The health status report and personalized suggestions are pushed to users through applications or devices, and users can check their health status and improvement suggestions at any time.

[0042] It is understandable that by obtaining detailed account registration information, conducting in-depth analysis and digital modeling, we can accurately assess the user's health status, provide precise health feedback, and combine multiple health models (such as BMI, BMR, cardiovascular function, and exercise capacity) to conduct multi-dimensional health status analysis and provide more comprehensive health information. Based on the comprehensive analysis results, we provide personalized health management suggestions to help users develop scientific and reasonable health plans and improve health management effects. As the user's health data is continuously updated, the model can be dynamically optimized to continuously provide accurate health feedback and suggestions to maintain the effectiveness and timeliness of user health management.

[0043] Preferably, the steps of obtaining the detection performance information of the sports watch and the long-term monitoring goal of the user, and constructing a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal to obtain the target monitoring algorithm based on the physical condition feedback model include: S21: Acquire detection performance information of the sports watch; wherein the detection performance information includes function type information and performance index information of a built-in sensor group of the sports watch, the built-in sensor group including a temperature sensor, a blood pressure sensor, a motion posture sensor, an image acquisition sensor, and a sound sensor; S22: Obtaining the user's long-term monitoring goals; wherein the long-term monitoring goals include weight control monitoring goals, physiological cycle monitoring goals, and chronic disease monitoring goals; S23: Digitally modeling the detection performance information and the long-term monitoring target to obtain a data fusion simulation level corresponding to the detection performance information and a data analysis simulation level corresponding to the long-term monitoring target; S24: analyzing the mapping relationship between the monitoring target and the physical condition in the physical condition feedback model according to the data analysis simulation level to obtain a first mapping relationship; S25: analyzing the mapping relationship between the detection data and the physical condition on the physical condition feedback model according to the data fusion simulation level to obtain a second mapping relationship; S26: performing a connection mapping process on the first mapping relationship and the second mapping relationship based on the physical condition feedback model to obtain a connection mapping relationship between the built-in sensor group of the sports watch and the long-term monitoring target; S27: simulating the expected scenario of the detection data on the physical condition feedback model according to the connection mapping relationship, so as to obtain feedback results of the physical condition feedback model corresponding to different detection data in each real-time scenario of the expected simulation; S28: performing an effect evaluation on the feedback result, analyzing the interactive countermeasures of the traversal simulation detection data according to the effect evaluation result to obtain an expected interactive countermeasure corresponding to the traversal simulation detection data, and performing format conversion on the effect evaluation result to obtain an expected evaluation standard; S29: Constructing a target monitoring algorithm for the physical condition feedback model according to the connection mapping relationship, the expected evaluation standard, and the expected interaction strategy to obtain a target monitoring algorithm based on the physical condition feedback model.

[0044] Specifically, identify the various sensors built into the sports watch, such as temperature sensors, blood pressure sensors, motion posture sensors (such as accelerometers and gyroscopes), image acquisition sensors, and sound sensors, and collect their performance indicators, such as accuracy, sensitivity, sampling frequency, and response time. This information can help determine the reliability and applicability of the sensors.

[0045] More specifically, the user's long-term monitoring goals are obtained. Weight control monitoring goals involve weight management goals, including target weight, daily calorie intake and consumption, etc. Menstrual cycle monitoring goals include tracking of menstrual cycles, ovulation prediction, etc. Chronic disease monitoring goals include parameter monitoring of chronic diseases such as hypertension and diabetes, including blood pressure levels, blood sugar levels, etc.

[0046] More specifically, the detection performance information and long-term monitoring objectives are digitally modeled. The data fusion simulation layer digitally models the detection performance information of the sensor to create a simulation layer that can process and fuse data from different sensors. The data analysis simulation layer digitally models the user's long-term monitoring objectives to create a simulation layer for analyzing and processing the relevant data of these objectives.

[0047] More specifically, in the mapping relationship analysis, the first mapping relationship is based on the data analysis simulation level to analyze the relationship between the long-term monitoring goal and the physical condition, for example, the relationship between the weight control goal and the daily intake and consumption of calories; the second mapping relationship is based on the data fusion simulation level to analyze the relationship between the sensor detection data and the physical condition, for example, the relationship between the blood pressure data measured by the blood pressure sensor and the cardiovascular health status; the first mapping relationship and the second mapping relationship are combined to form a connection mapping relationship between the built-in sensor group of the sports watch and the user's long-term monitoring goal. This step ensures that the sensor data can be effectively mapped to the user's health monitoring goal.

[0048] More specifically, based on the connection mapping relationship, the expected scenario simulation is carried out to simulate how the sensor detection data will affect and feedback the user's physical condition in various possible real-time scenarios, and the effect evaluation and interactive countermeasures analysis are carried out: the simulated feedback results are evaluated to determine whether their effects can meet the user's long-term monitoring goals. According to the effect evaluation results, countermeasures are analyzed and formulated, the processing and feedback mechanism of the detection data are optimized, and the format of the evaluation results is converted to form a unified expected evaluation standard, which will help future improvements and optimizations. The connection mapping relationship, expected evaluation standards and expected interactive countermeasures are used to construct the final target monitoring algorithm, which will be used to monitor the user's physical condition in real time and provide corresponding feedback and suggestions.

[0049] It is understandable that through high-precision sensors and optimized algorithms, it is possible to accurately monitor the user's health status, provide reliable data support, integrate and analyze multiple sensor data, improve the understanding and monitoring effect of complex physiological states, provide a more comprehensive health assessment, and provide dynamic feedback in real time to help users understand changes in their physical condition in a timely manner and make corresponding adjustments to achieve health management goals. Through simulation and evaluation, the target monitoring algorithm is continuously optimized to improve monitoring accuracy and reliability. According to the user's long-term monitoring goals, personalized health management plans are provided to improve the user's health level and quality of life.

[0050] Preferably, the steps of obtaining the real-time scene of the user through interactive instructions with the user, analyzing the detection mode of the real-time scene according to the target monitoring algorithm, and switching the sports watch to a corresponding detection mode according to the analysis result to collect scene detection data of the real-time scene include: S31: receiving a user's interaction instruction through the human-computer interaction function of the sports watch, and parsing the instruction content of the interaction instruction to obtain a real-time scene where the user is located; S32: Analyzing the detection mode of the real-time scene according to the target monitoring algorithm to obtain the detection mode of the long-term monitoring target corresponding to the real-time scene; wherein the real-time scene includes a diet scene, a sports scene, and a rest scene, and the detection mode includes a diet detection mode, a sports detection mode, and a rest detection mode; S33: activating a corresponding detection function of the sports watch according to the detection mode corresponding to the real-time scene, so that the sports watch switches to the corresponding detection mode to collect scene detection data of the real-time scene; When the sports watch switches to the diet detection mode, the sports watch activates the image acquisition sensor to perform image acquisition and content analysis on the user's diet objects to obtain corresponding scene detection data; When the sports watch switches to the motion detection mode, the sports watch activates the temperature sensor and the motion posture sensor to detect and combine the intensity, time, and frequency of the user's motion behavior data to obtain corresponding scene detection data; When the sports watch switches to the rest detection mode, the sports watch activates the temperature sensor and the sound sensor to collect data and extract features of the user's physical condition during rest to obtain corresponding scene detection data.

[0051] Specifically, the user's interaction instructions are received through the human-computer interaction function of the sports watch (such as touch screen, voice commands, etc.), and the received interaction instructions are parsed to obtain the instruction content, so as to determine the real-time scene in which the user is currently located, analyze the real-time scene and determine the detection mode: according to the target monitoring algorithm, the current real-time scene is analyzed, and the corresponding detection mode is identified and determined. The real-time scene may include eating scenes, exercise scenes and rest scenes; the corresponding detection modes include eating detection mode, exercise detection mode and rest detection mode.

[0052] More specifically, switch and activate the detection mode: according to the detection mode corresponding to the real-time scene, switch the sports watch to the corresponding detection mode, activate the corresponding sensors and functions in the sports watch to collect real-time data, the diet detection mode activates the image acquisition sensor, performs image acquisition and content analysis on the user's diet objects to obtain diet-related scene detection data, the motion detection mode activates the temperature sensor and motion posture sensor, detects the user's exercise behavior, including exercise intensity, time, frequency, etc., to obtain detection data of the exercise scene, the rest detection mode activates the temperature sensor and sound sensor, collects the user's physical condition data during rest, and obtains detection data of the rest scene through feature extraction.

[0053] It is understandable that it has achieved intelligent switching of detection modes according to the user's real-time scenario, thereby accurately collecting relevant data and improving the accuracy and relevance of the data. Through automated mode switching and data collection, it reduces the user's operating burden, improves the user experience, provides personalized and real-time health monitoring and suggestions, supports detection of multiple scenarios (diet, exercise, rest), covers the main activities of the user's daily life, and provides comprehensive health monitoring. Through the collected multi-dimensional data, more in-depth analysis and application can be carried out, including health assessment, behavior prediction, personalized suggestions, etc., to provide users with a full range of health management solutions, upgrade traditional passive monitoring to active intelligent monitoring, and improve the automation and intelligence level of the monitoring system.

[0054] Preferably, the step of substituting the scene detection data into the target monitoring algorithm, and allowing the target monitoring algorithm to perform real-time analysis and countermeasure generation on the scene detection data according to the physical condition feedback model to obtain scene guidance countermeasures and perform interactive guidance operations on the user includes: S41: parsing the data type of the scene detection data, and scheduling a target monitoring algorithm corresponding to the scene detection data according to the parsing result; S42: performing information feedback analysis on the scene detection data relative to the physical condition feedback model according to the target monitoring algorithm to obtain information feedback features of the scene detection data; S43: Retrieving information feedback features of scene detection data of the same data type from a historical database of the sports watch as a historical feedback feature sequence, and performing a time-series correlation feature analysis on the information feedback features according to the historical feedback feature sequence to obtain a time-series correlation feedback feature of the information feedback features; S44: performing a real-time analysis of the long-term monitoring target on the physical condition feedback model according to the time-series correlation feedback feature by the target monitoring algorithm to obtain the target condition feature of the user corresponding to the long-term monitoring target; S45: performing, by the target monitoring algorithm, an effect analysis and an effect evaluation of the information feedback feature relative to the long-term monitoring target based on the target status feature, to obtain an expected evaluation result of the scene detection data corresponding to the long-term monitoring target, and performing an adjustment plan analysis on the expected evaluation result based on the target monitoring algorithm to generate a scene behavior adjustment plan corresponding to the scene detection data; S46: Performing human-computer interaction on the user according to the scenario behavior adjustment plan to guide the user to perform corresponding operations in the real-time scenario according to the scenario behavior adjustment plan.

[0055] Specifically, the data type of the collected scene detection data is parsed to identify the attributes and types of the data (such as dietary data, exercise data, rest data, etc.). Based on the parsing results, the target monitoring algorithm corresponding to the scene detection data is scheduled to adapt to different data types. The scene detection data is analyzed using the target monitoring algorithm to extract information feedback features relative to the physical condition feedback model (such as nutritional components of dietary intake, exercise intensity, rest quality, etc.). These information feedback features are used to describe the user's physical condition and behavioral characteristics in real-time scenarios.

[0056] More specifically, the historical database of the sports watch is called up to retrieve the information feedback features of scene detection data of the same data type to form a historical feedback feature sequence. The current information feedback features are subjected to time series correlation analysis. By comparing the current features with the historical features, the time series correlation feedback features are obtained, which helps to understand the user's long-term behavior patterns and trends.

[0057] More specifically, through the target monitoring algorithm, based on the time-series correlation feedback characteristics, the physical condition feedback model is analyzed in real time for long-term monitoring targets (such as long-term weight control, chronic disease management, etc.), and the target status characteristics of the user corresponding to the long-term monitoring target are obtained. These characteristics describe the achievement of the user's long-term health goals. According to the target status characteristics, the information feedback characteristics are analyzed and evaluated for their effects, and the expected evaluation results of the scene detection data in the long-term monitoring targets are determined (such as the impact of the current diet on long-term weight control, the impact of current exercise on cardiovascular health, etc.). Adjustment plan analysis is performed to generate scene behavior adjustment plans for the current scene detection data (such as adjusting the diet plan, exercise plan, etc.). According to the scene behavior adjustment plan, the user is guided to perform corresponding operations in the real-time scenario (such as adjusting diet, increasing exercise, changing rest methods, etc.) through human-computer interaction (such as notifications, prompts, suggestions, etc.), ensuring that the user can make appropriate behavioral adjustments according to the real-time scenario and health goals.

[0058] It is understandable that it can accurately parse various types of scene detection data and dispatch corresponding target monitoring algorithms to ensure the accuracy and applicability of data processing. Through the extraction and analysis of information feedback features, it can deeply understand the user's immediate health status and behavioral characteristics, and provide a basis for further analysis and suggestions. It uses historical feedback feature sequences for time series correlation analysis to identify the user's long-term behavior patterns and health trends, which helps to formulate more accurate and personalized health management plans, continuously monitor and analyze the user's long-term health goals, help users achieve long-term health management goals, improve the effectiveness of health management, and generate personalized scene behavior adjustment plans based on target status characteristics and effect evaluation. Through real-time user interaction guidance, it helps users make scientific and reasonable health behavior adjustments in specific situations and improve the effectiveness of user health management.

[0059] Preferably, the step of synchronously adjusting the model parameters of the physical condition feedback model according to the scene detection data by the target monitoring algorithm to implement feedback of the user's physical condition information through the physical condition feedback model includes: S51: continuously collecting scene detection data of the real-time scene until the real-time scene ends, and performing time sequence processing on all the scene detection data of the real-time scene to obtain a scene detection sequence of the real-time scene; S52: evaluating each scene detection data in the scene detection sequence in sequence according to the target monitoring algorithm to obtain an independent evaluation result corresponding to each scene detection data in the scene detection sequence; S53: performing a comprehensive analysis of the temporal correlation of the sequentially arranged independent evaluation results to obtain temporal causal characteristics between the independent evaluation results, and constructing an overall effect network for the independent evaluation results based on the temporal causal characteristics between the independent evaluation results to obtain an overall effect simulation network of the scene detection sequence; S54: performing weight assignment and weighted fusion on the overall effect simulation network to obtain overall effect characteristics of the scene detection sequence, and synchronously adjusting model parameters of the physical condition feedback model according to the overall effect characteristics.

[0060] Specifically, scene detection data of the real-time scene is continuously collected until the real-time scene ends. These data may include heart rate, number of steps, calorie consumption, activity type, sleep data, etc. All the obtained scene detection data are arranged in chronological order to form a scene detection sequence.

[0061] More specifically, a target monitoring algorithm is used to evaluate each scene detection data in the scene detection sequence one by one to obtain an independent evaluation result for each data point. The evaluation content may include changes in health indicators, evaluation of exercise intensity, nutritional analysis of dietary intake, etc. Each independent evaluation result is subjected to correlation analysis in chronological order to identify the temporal causal relationship between each evaluation result, for example, evaluating the impact of exercise intensity on heart rate, the impact of dietary intake on blood sugar levels, etc. Based on these causal relationships, an overall effect network is constructed for each independent evaluation result. This network reflects the mutual influence and comprehensive effect between various health behaviors and feedback.

[0062] More specifically, weights are assigned to each node in the overall effect simulation network (i.e., independent evaluation results). The weights can be based on the importance of the data, the priority of health goals, the user's personalized needs, etc. The weighted independent evaluation results are integrated to obtain the overall effect characteristics of the scene detection sequence. This characteristic represents the comprehensive impact of the entire scene detection sequence on the user's physical condition. According to the overall effect characteristics, the parameters of the physical condition feedback model are synchronously adjusted to ensure that the model can accurately reflect the user's current health status and behavioral characteristics. The adjusted model can provide more accurate physical condition information feedback to help users better understand their health status and areas that need improvement.

[0063] It is understandable that through continuous collection and real-time processing, results can be obtained immediately after the scene ends, which improves the real-time and timeliness of data processing and feedback. The target monitoring algorithm independently evaluates each data point to ensure the accuracy of the evaluation results. Time series correlation analysis and effect network construction make the comprehensive impact analysis of health behavior more comprehensive and systematic, revealing the complex relationship between behavior and health indicators. Weight distribution is based on individual needs and health goals, making the model adjustment more in line with the user's actual situation, providing personalized health management plans, and synchronously adjusting the model parameters based on the overall effect characteristics to ensure that the physical condition feedback model can dynamically reflect the actual situation, improving the adaptability and accuracy of the model. Accurate model feedback and personalized suggestions can help users better understand their own health status, conduct scientific health management, improve the effectiveness of health management, and reduce adverse effects caused by inaccurate or delayed information.

[0064] Reference Figure 2 As shown, in a second aspect, the present invention provides a multi-scenario application system for a sports watch, which is used to implement the multi-scenario application method for a sports watch described in any one of the first aspects, including: A physical feedback module is used to obtain the user's account registration information and perform digital simulation of the user's physical condition based on the account registration information to obtain a physical condition feedback model of the user; an algorithm construction module, configured to obtain detection performance information of the sports watch and a long-term monitoring goal of the user, and construct a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal, so as to obtain a target monitoring algorithm based on the physical condition feedback model; a scene detection module, configured to obtain the user's real-time scene through interactive instructions with the user, analyze the real-time scene for a detection mode according to the target monitoring algorithm, and switch the sports watch to a corresponding detection mode based on the analysis result to collect scene detection data for the real-time scene; An interactive guidance module, configured to substitute the scene detection data into the target monitoring algorithm, causing the target monitoring algorithm to perform real-time analysis and generate countermeasures on the scene detection data according to the physical condition feedback model, so as to obtain scene guidance countermeasures and perform interactive guidance operations on the user; The model adjustment module is used to synchronously adjust the model parameters of the physical condition feedback model according to the scene detection data through the target monitoring algorithm, so as to realize feedback of the user's physical condition information through the physical condition feedback model.

[0065] In this embodiment, for the specific implementation of each module in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0066] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-scenario application method for a sports watch, characterized in that: include: Obtaining the user's account registration information, and performing a digital simulation of the user's physical condition based on the account registration information to obtain a user's physical condition feedback model; Acquiring detection performance information of the sports watch and a long-term monitoring goal of the user, and constructing a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal to obtain a target monitoring algorithm based on the physical condition feedback model; Acquiring a real-time scene of the user through interactive instructions with the user, analyzing the detection mode of the real-time scene according to the target monitoring algorithm, and switching the sports watch to a corresponding detection mode according to the analysis result to collect scene detection data of the real-time scene; Substituting the scene detection data into the target monitoring algorithm, and allowing the target monitoring algorithm to perform real-time analysis and countermeasure generation on the scene detection data according to the physical condition feedback model, so as to obtain scene guidance countermeasures and perform interactive guidance operations on the user; The target monitoring algorithm is used to synchronously adjust the model parameters of the physical condition feedback model according to the scene detection data, so as to realize feedback of the user's physical condition information through the physical condition feedback model.

2. The multi-scenario application method of a sports watch according to claim 1, wherein: The steps of obtaining the user's account registration information and performing digital simulation of the user's physical condition based on the account registration information to obtain the user's physical condition feedback model include: Obtain the user's account registration information; wherein the account registration information includes the user's gender, age, height, weight, and medical history; Performing in-depth analysis and digital modeling of the user's physical parameters based on the account registration information to obtain the user's height and weight index model, basal metabolic model, cardiovascular function model, and exercise capacity model; The user's height and weight index model, basal metabolic model, cardiovascular function model and exercise capacity model are synergistically combined to obtain the user's physical condition feedback model.

3. The multi-scenario application method of a sports watch according to claim 1, wherein: The steps of obtaining detection performance information of a sports watch and a long-term monitoring goal of a user, and constructing a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal to obtain the target monitoring algorithm based on the physical condition feedback model include: Acquire detection performance information of the sports watch; wherein the detection performance information includes function type information and performance index information of the built-in sensor group of the sports watch, the built-in sensor group including a temperature sensor, a blood pressure sensor, a motion posture sensor, an image acquisition sensor, and a sound sensor; Obtaining the user's long-term monitoring goals; wherein the long-term monitoring goals include weight control monitoring goals, physiological cycle monitoring goals, and chronic disease monitoring goals; Digitally modeling the detection performance information and the long-term monitoring target to obtain a data fusion simulation level corresponding to the detection performance information and a data analysis simulation level corresponding to the long-term monitoring target; performing a mapping relationship analysis between a monitoring target and a physical condition on the physical condition feedback model according to the data analysis simulation level to obtain a first mapping relationship; performing a mapping relationship analysis between the detection data and the physical condition on the physical condition feedback model according to the data fusion simulation level to obtain a second mapping relationship; performing a connection mapping process on the first mapping relationship and the second mapping relationship based on the physical condition feedback model to obtain a connection mapping relationship between the built-in sensor group of the sports watch and the long-term monitoring target; Performing an expected scenario simulation of the detection data on the physical condition feedback model according to the connection mapping relationship to obtain feedback results of the physical condition feedback model corresponding to different detection data in each real-time scenario expected to be simulated; Performing an effect evaluation on the feedback results, analyzing the interactive countermeasures of the traversal simulation detection data based on the effect evaluation results to obtain expected interactive countermeasures corresponding to the traversal simulation detection data, and performing format conversion on the effect evaluation results to obtain expected evaluation standards; A target monitoring algorithm is constructed for the physical condition feedback model according to the connection mapping relationship, the expected evaluation standard, and the expected interaction strategy to obtain a target monitoring algorithm based on the physical condition feedback model.

4. The multi-scenario application method of a sports watch according to claim 1, wherein: The steps of obtaining a real-time scene of the user through interactive instructions with the user, analyzing the detection mode of the real-time scene according to the target monitoring algorithm, and switching the sports watch to a corresponding detection mode according to the analysis result to collect scene detection data of the real-time scene include: Receiving user interaction instructions through the human-computer interaction function of the sports watch, and parsing the interaction instructions to obtain the real-time scene of the user; Analyzing the detection mode of the real-time scene according to the target monitoring algorithm to obtain the detection mode of the long-term monitoring target corresponding to the real-time scene; wherein the real-time scene includes a diet scene, a sports scene, and a rest scene, and the detection mode includes a diet detection mode, a sports detection mode, and a rest detection mode; activating a corresponding detection function of the sports watch according to the detection mode corresponding to the real-time scene, so that the sports watch switches to the corresponding detection mode to collect scene detection data of the real-time scene; When the sports watch switches to the diet detection mode, the sports watch activates the image acquisition sensor to perform image acquisition and content analysis on the user's diet objects to obtain corresponding scene detection data; When the sports watch switches to the motion detection mode, the sports watch activates the temperature sensor and the motion posture sensor to detect and combine the intensity, time, and frequency of the user's motion behavior data to obtain corresponding scene detection data; When the sports watch switches to the rest detection mode, the sports watch activates the temperature sensor and the sound sensor to collect data and extract features of the user's physical condition during rest to obtain corresponding scene detection data.

5. The multi-scenario application method of a sports watch according to claim 1, wherein: Substituting the scene detection data into the target monitoring algorithm, and allowing the target monitoring algorithm to perform real-time analysis and generate countermeasures on the scene detection data according to the physical condition feedback model to obtain scene guidance countermeasures and perform interactive guidance operations on the user include the following steps: Parsing the data type of the scene detection data, and scheduling a target monitoring algorithm corresponding to the scene detection data according to the parsing result; performing information feedback analysis on the scene detection data relative to the physical condition feedback model according to the target monitoring algorithm to obtain information feedback features of the scene detection data; Retrieving information feedback features of scene detection data of the same data type from a historical database of the sports watch as a historical feedback feature sequence, and performing a time-series correlation feature analysis on the information feedback features based on the historical feedback feature sequence to obtain a time-series correlation feedback feature of the information feedback features; Performing a real-time analysis of a long-term monitoring target on the physical condition feedback model according to the time-series correlation feedback feature by the target monitoring algorithm to obtain a target condition feature of the user corresponding to the long-term monitoring target; Performing an effect analysis and effect evaluation of the information feedback feature relative to the long-term monitoring target based on the target condition feature by the target monitoring algorithm to obtain an expected evaluation result of the scene detection data corresponding to the long-term monitoring target, and performing an adjustment plan analysis on the expected evaluation result based on the target monitoring algorithm to generate a scene behavior adjustment plan corresponding to the scene detection data; Human-computer interaction is performed on the user according to the scenario behavior adjustment plan to guide the user to perform corresponding operations in a real-time scenario according to the scenario behavior adjustment plan.

6. The multi-scenario application method of a sports watch according to claim 5, characterized in that: The step of synchronously adjusting the model parameters of the physical condition feedback model according to the scene detection data by using the target monitoring algorithm to implement feedback of the user's physical condition information through the physical condition feedback model includes: Continuously collecting scene detection data of the real-time scene until the real-time scene ends, and performing time sequence processing on all the scene detection data of the real-time scene obtained to obtain a scene detection sequence of the real-time scene; evaluating each scene detection data in the scene detection sequence in sequence according to the target monitoring algorithm to obtain an independent evaluation result corresponding to each scene detection data in the scene detection sequence; Performing a comprehensive analysis of the temporal correlation of the sequentially arranged independent evaluation results to obtain temporal causal characteristics between the independent evaluation results, and constructing an overall effect network for the independent evaluation results based on the temporal causal characteristics between the independent evaluation results to obtain an overall effect simulation network of the scene detection sequence; The overall effect simulation network is weighted and fused to obtain the overall effect characteristics of the scene detection sequence, and the model parameters of the physical condition feedback model are synchronously adjusted according to the overall effect characteristics.

7. A multi-scenario application system for a sports watch, characterized in that: A method for implementing a multi-scenario application of a sports watch according to any one of claims 1 to 6, comprising: A physical feedback module is used to obtain the user's account registration information and perform digital simulation of the user's physical condition based on the account registration information to obtain a physical condition feedback model of the user; an algorithm construction module, configured to obtain detection performance information of the sports watch and a long-term monitoring goal of the user, and construct a target monitoring algorithm for the physical condition feedback model based on the detection performance information and the long-term monitoring goal, so as to obtain a target monitoring algorithm based on the physical condition feedback model; a scene detection module, configured to obtain the user's real-time scene through interactive instructions with the user, analyze the real-time scene for a detection mode according to the target monitoring algorithm, and switch the sports watch to a corresponding detection mode based on the analysis result to collect scene detection data for the real-time scene; An interactive guidance module, configured to substitute the scene detection data into the target monitoring algorithm, causing the target monitoring algorithm to perform real-time analysis and generate countermeasures on the scene detection data according to the physical condition feedback model, so as to obtain scene guidance countermeasures and perform interactive guidance operations on the user; The model adjustment module is used to synchronously adjust the model parameters of the physical condition feedback model according to the scene detection data through the target monitoring algorithm, so as to realize feedback of the user's physical condition information through the physical condition feedback model.

Images