Adolescent physical health management system based on physical test results

Abstract

The present invention relates to the technical field of physical health management for teenagers, and discloses a physical health management system for teenagers based on physical test results. The system includes: a data acquisition terminal, a health intervention device, and a cloud management platform, which are communicatively connected. The data acquisition terminal collects the motion indicators and physiological signals of the teenagers' physical test in real time, and the health intervention device receives instructions from the cloud management platform to adjust the training intensity. The data monitoring unit records the abnormal starting point and recovery end point of the indicator to determine the health risk interval, controls the device to operate at a safe threshold and generates a physical characteristic curve for physical prediction mapping; the evaluation processing unit corrects the intervention path to generate an execution strategy; the routine control unit and the emergency control unit of the health management unit control the device to perform corresponding operations under normal and abnormal conditions respectively. The system realizes real-time monitoring, precise evaluation, scientific intervention and risk management of the physical health of teenagers, effectively ensuring the safety of teenagers' physical tests and improving their physical health.

Description

Technical Field

[0001] The present invention relates to the technical field of adolescent physical health management, and in particular to a adolescent physical health management system based on physical test results. Background Art

[0002] In today's society, the physical health of adolescents is receiving increasing attention. With technological advancements and changing lifestyles, young people are facing problems such as lack of exercise and declining physical fitness. Physical fitness tests are an important means of assessing the physical health of adolescents, and the effective use and management of these data are crucial for their physical health management.

[0003] Traditional methods of managing adolescent physical health have numerous shortcomings. For one thing, data collection is not comprehensive or real-time enough. Existing physical fitness testing equipment can only capture limited athletic indicators, such as running speed and long jump distance. However, the physiological signals collected during adolescent physical fitness testing, such as heart rate and blood pressure, are not collected in a timely and accurate manner, making it difficult to fully reflect the physical health status of adolescents. Furthermore, health interventions lack specificity and intelligence. When adolescent physical fitness test results are abnormal, traditional health intervention methods are often based on unified plans developed based on experience, unable to be personalized according to the specific circumstances of each adolescent, resulting in poor intervention results.

[0004] Furthermore, existing physical health management systems lack in-depth data analysis and prediction. Physical test data is simply stored and aggregated, but not fully utilized for physical fitness prediction and health risk assessment. This makes it impossible to identify potential health issues in adolescents and implement timely interventions. Furthermore, health record management is fragmented and disorganized, preventing the formation of a complete topological picture of adolescent physical health, hindering long-term tracking and management of adolescents' physical health.

[0005] Traditional systems also have shortcomings when it comes to controlling health intervention equipment. When abnormal training conditions are detected, they are unable to quickly and accurately determine the health risk range and effectively control the health intervention equipment for protective operations, potentially posing a threat to adolescents' physical health. Furthermore, the development of intervention pathways lacks scientific rationality and cannot be adjusted and optimized based on real-time data, impacting intervention effectiveness.

[0006] With the development of information technology, cloud computing, big data, the Internet of Things, and other technologies are increasingly being used in health management. Applying these advanced technologies to adolescent health management, enabling real-time collection, analysis, and prediction of physical test data and personalized health interventions, has become a pressing challenge. This present invention aims to provide a physical test-based health management system for adolescents to address these challenges. Summary of the Invention

[0007] The purpose of the present invention is to provide a physical health management system for teenagers based on physical test results to solve the problems raised in the above background technology.

[0008] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a physical fitness and health management system for adolescents based on physical test results, the system comprising:

[0009] A data acquisition terminal, a health intervention device, and a cloud management platform, wherein the data acquisition terminal and the health intervention device are respectively connected to the cloud management platform for communication, and the cloud management platform includes a data monitoring unit, an evaluation processing unit, and a health management unit;

[0010] The data acquisition terminal is used to collect the sports indicators and physiological signals of the adolescents during the physical examination in real time;

[0011] The health intervention device is used to receive instruction signals from the cloud management platform to adjust the training intensity;

[0012] The data monitoring unit is used to record the abnormal starting point and recovery end point of the indicators during the operation of the health intervention device, determine the health risk interval based on the abnormal starting point and recovery end point of the indicators, control the health intervention device to maintain a preset safety threshold for abnormal physical conditions and record fluctuation parameters, generate a physical characteristic curve based on the fluctuation parameters, and perform physical prediction mapping on the health file topology map;

[0013] The evaluation processing unit is used to modify the intervention path of the health record topology map that has completed the physical fitness prediction mapping and generate an execution strategy;

[0014] The health management unit includes a regular control unit and an emergency control unit. The regular control unit is used to control the health intervention device to execute a baseline intensity output when the health intervention device is in a normal training condition; the emergency control unit is used to control the health intervention device to execute a protection operation within a health risk range according to an execution strategy when the health intervention device detects an abnormal training condition.

[0015] Preferably, the data acquisition terminal includes a terminal housing and a data acquisition device, a feature extraction device, an evaluation unit and a transmission unit arranged in the housing;

[0016] The data acquisition device is used to synchronously acquire heart rate waveform and motion trajectory data;

[0017] The feature extraction device is used to extract the action pattern feature components of the motion trajectory;

[0018] The evaluation unit is used to calculate the matching degree between the characteristic components of the current movement pattern and the historical standard movement based on the decision tree model, determine the deviation degree of the physical health status, and trigger the early warning signal according to the calculation result;

[0019] The transmission unit is used to upload the collected data to the cloud management platform via the ZigBee protocol.

[0020] Preferably, the health intervention device includes a device body and a parameter detection module, an intensity adjustment module, an instruction execution module and a communication relay module arranged in the body.

[0021] Preferably, the recording of abnormal starting points and recovery ending points of indicators during the operation of the health intervention device includes:

[0022] When the health intervention device detects an abnormal indicator, it records the timestamp data of the abnormality occurrence time, continuously monitors the indicator recovery critical point through the parameter detection module, and records the cycle count of the recovery time.

[0023] Preferably, determining the health risk interval according to the abnormal starting point and recovery ending point of the indicator includes:

[0024] Generate abnormal coordinates and recovery coordinates based on timestamp data and cycle counts;

[0025] The abnormal coordinates, restored coordinates and data acquisition terminal locations are topologically connected to form a closed interval, which is marked as a health risk interval.

[0026] Preferably, the controlling of the health intervention device to maintain a preset safety threshold for abnormal physical conditions and record fluctuation parameters, generating a physical characteristic curve according to the fluctuation parameters and performing physical prediction mapping on the health record topology map comprises the following steps:

[0027] Controlling the health intervention device to adjust the training intensity of the health risk interval, and obtaining amplitude parameters in real time through a parameter detection module;

[0028] A preset safety threshold range is set. If the amplitude parameter exceeds the preset safety threshold range, the health intervention device is controlled to maintain the preset safety threshold operation;

[0029] Continuously record the intensity output values ​​of health intervention devices to form a set of fluctuation parameters;

[0030] Based on the set of fluctuation parameters, a linear regression algorithm is used to generate a dynamic characteristic curve of physical fitness;

[0031] Extracting a number of key feature points at equal time intervals from the physical fitness dynamic feature curve, wherein the number of the key feature points is proportional to the duration of the curve;

[0032] The physical distribution mapping and annotation of the health record topology map are performed based on the extracted key feature points.

[0033] Preferably, the intervention path correction of the health record topology map that has completed the constitution prediction mapping includes logically shielding the preset intervention path in the health record topology map that overlaps with the high-risk interval after marking the constitution distribution mapping on the health record topology map.

[0034] Preferably, when the health intervention device detects an abnormal training condition, controlling the health intervention device to perform a protection operation within the health risk range according to the execution strategy includes:

[0035] A1. Select the health risk interval access point with the least number of operation steps based on the next training node to be adjusted;

[0036] A2. Control the health intervention device to switch to the access point and synchronize parameters;

[0037] A3. Controlling the health intervention device to enter the health risk zone from the access point and performing intensity adjustment actions according to the intervention path in the execution strategy;

[0038] A4. Obtain the output parameters of health intervention equipment in real time and use genetic algorithms to optimize and compensate the output parameters;

[0039] A5. After completing each continuous training operation in the health risk zone, control the health intervention device to pause output and exit the health risk zone, and re-execute A1.

[0040] Preferably, said A1 comprises the following steps:

[0041] The Dijkstra algorithm is used to calculate the feasible access points for each health risk interval and a comprehensive score is given based on the operation steps and physiological distance parameters;

[0042] Based on the comprehensive scoring results, the access point in the health risk interval with the least operation steps and the shortest physiological distance is selected.

[0043] Preferably, the comprehensive scoring based on the operation steps and physiological distance parameters includes:

[0044] Set the weight coefficient of operation steps to α and the weight coefficient of physiological distance to β;

[0045] Normalize the operation step values ​​to obtain the step normalization value, and normalize the physiological distance values ​​to obtain the distance normalization value;

[0046] Calculate the score value S = α × step normalization value + β × distance normalization value;

[0047] The health management unit is used to select the health risk interval access point with the highest score S.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] The system uses a data acquisition terminal to collect real-time motion indicators and physiological signals during the adolescent physical examination, such as synchronous acquisition of heart rate waveform and motion trajectory data. This allows for a comprehensive and accurate understanding of the adolescent's physical condition during the examination, providing rich and reliable data support for subsequent physical health management. The feature extraction device in the data acquisition terminal extracts the motion pattern characteristic components of the motion trajectory. The evaluation unit calculates the matching degree between the current motion pattern characteristic components and historical standard movements based on a decision tree model, determines the deviation of physical health status, and triggers an early warning signal, achieving real-time monitoring and early warning of the adolescent's physical health status, and can promptly identify potential health risks.

[0050] The cloud management platform's data monitoring unit records the start and end points of abnormal indicators during the operation of health intervention devices, identifies health risk zones, controls the devices within preset safety thresholds, and records fluctuations in parameters. This generates a physical fitness curve and maps the health profile topology to physical fitness predictions. This series of operations enables dynamic monitoring and prediction of adolescents' physical health status. It can predict the development trend of adolescents' physical fitness based on historical and real-time data, providing a scientific basis for developing personalized physical health management plans.

[0051] The assessment processing unit modifies intervention paths within the health record topology map, generating execution strategies that make the regulation of health intervention devices more scientific and rational. By logically shielding pre-set intervention paths that overlap with high-risk intervals in the health record topology, it prevents the adverse effects of irrational intervention paths on adolescents' physical health, improving the safety and effectiveness of physical health management.

[0052] The routine control unit and the emergency control unit of the health management unit work together to achieve precise control of the health intervention equipment under normal training conditions and abnormal training conditions respectively. The routine control unit controls the health intervention equipment to execute the baseline intensity output, ensuring the normal progress of the physical examination process. When the emergency control unit detects an abnormal training condition, it controls the health intervention equipment to perform protective operations within the health risk range according to the execution strategy. Through a series of scientific steps, such as selecting the access point with the fewest operation steps and the shortest physiological distance, synchronizing parameters, executing intensity adjustment actions, and using genetic algorithms to optimize and compensate for output parameters, it achieves rapid and effective handling of abnormal situations, greatly improving the safety of the physical examination process.

[0053] The health intervention device's parameter detection module, intensity adjustment module, and other components enable real-time monitoring of operating parameters and intensity adjustments based on instructions, ensuring operational stability and reliability. Uploading collected data to a cloud management platform via the ZigBee protocol enables fast and stable data transmission, ensuring information exchange between all parts of the system.

[0054] Furthermore, when determining health risk intervals, the system generates abnormal coordinates and recovery coordinates based on timestamp data and cycle counts. These coordinates, along with the data acquisition terminal location, are topologically connected to form a closed interval, making the determination of health risk intervals more precise and providing an accurate target area for subsequent interventions. When generating physical fitness curves, a linear regression algorithm is used to generate a dynamic physical fitness curve based on a set of fluctuation parameters. Key feature points are extracted at equal time intervals to map and annotate the physical fitness distribution on the health record topology, improving the accuracy and scientific nature of physical fitness predictions.

[0055] When selecting access points within health risk zones, the Dijkstra algorithm calculates all feasible access points and comprehensively scores them based on the procedure and physiological distance parameters. The access point with the highest score is selected, optimizing the selection of access points and improving the efficiency and effectiveness of emergency response. A genetic algorithm is used to optimize and compensate for the output parameters, further improving the accuracy and rationality of the output parameters of the health intervention device and ensuring the safety and effectiveness of the physical examination process. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a working principle diagram of the physical fitness and health management system for teenagers based on physical test scores according to the present invention;

[0057] Figure 2 Schematic diagram of the data acquisition terminal;

[0058] Figure 3 Flowchart for physical characteristic curve generation and prediction mapping;

[0059] Figure 4 Flowchart of the revision for the intervention pathway. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] See also Figure 1-Figure 4The present invention relates to a youth physical fitness and health management system based on physical test scores. The system includes: a data acquisition terminal, a health intervention device, and a cloud management platform. The data acquisition terminal and the health intervention device are respectively connected to the cloud management platform for communication. The cloud management platform includes a data monitoring unit, an evaluation and processing unit, and a health management unit. Specific implementation methods are as follows:

[0062] The data acquisition terminal is used to collect the motion indicators and physiological signals of adolescents during physical examination in real time. The health intervention device is used to receive the command signal of the cloud management platform to adjust the training intensity. The data monitoring unit is used to record the abnormal starting point and recovery end point of the indicators during the operation of the health intervention device, determine the health risk interval based on the abnormal starting point and recovery end point of the indicators, control the health intervention device to maintain the preset safety threshold operation for abnormal physical conditions and record the fluctuation parameters, generate the physical characteristic curve based on the fluctuation parameters and perform physical prediction mapping on the health file topology map. The evaluation processing unit is used to correct the intervention path of the health file topology map that has completed the physical prediction mapping and generate an execution strategy. The health management unit includes a regular control unit and an emergency control unit. The regular control unit is used to control the health intervention device to execute the baseline intensity output when it is in normal training conditions; the emergency control unit is used to control the health intervention device to execute protection operations within the health risk interval according to the execution strategy when the health intervention device detects abnormal training conditions.

[0063] Example 1:

[0064] In this embodiment, the data acquisition terminal serves as the front-end data acquisition device for the entire system and plays a crucial role in adolescent health management. Its specific structure includes a terminal housing and, housed within it, a data acquisition device, feature extraction device, evaluation unit, and transmission unit. The terminal housing provides physical protection for the internal devices and units, ensuring they are protected from external interference and damage during actual use. It also provides a stable support structure for the installation of various components.

[0065] The main function of the data acquisition device is to synchronously acquire heart rate waveform and motion trajectory data. In practical applications, this device can utilize high-precision heart rate sensors and motion trajectory sensors. The heart rate sensor can capture the electrophysiological signals of the adolescent's heartbeat in real time during the physical examination, converting them into continuous heart rate waveform data. This data can reflect information such as the adolescent's cardiac function status and the impact of exercise intensity on the heart. The motion trajectory sensor uses various technical means, such as GPS and inertial measurement units, to record parameters such as position changes, speed, and acceleration during exercise in real time, thus forming complete motion trajectory data. The simultaneous acquisition of these two types of data provides multi-dimensional raw information for subsequent analysis and evaluation.

[0066] The feature extraction device is used to extract motion pattern characteristic components from motion trajectory data. Motion trajectory data often contains a large amount of raw information, which requires analysis and refinement using specific algorithms and processing methods. For example, for running trajectory data, the feature extraction device can analyze parameters such as cadence, stride length, and changes in body posture to extract characteristic components that represent specific motion patterns. During this analysis and refinement, the raw data is preprocessed using a sliding window filtering algorithm to remove noise (with a window size of 50ms and a step size of 20ms). Dynamic Time Warping (DTW) is then used to align motion sequences of varying durations. Finally, principal component analysis (PCA) is combined to extract key dimensional features. For example, for running trajectory data, the average velocity and acceleration variance within each window are calculated using a sliding window. The DTW algorithm is then used to align the actual trajectory with the standard trajectory along the time axis. Finally, PCA is used to reduce the high-dimensional trajectory data to 3-5 principal components, retaining over 95% of the characteristic information. These characteristic components provide a high-level summary and abstraction of movement trajectories, reflecting key information such as the degree of movement standardization and force application during exercise. The characteristic components for different sports are as follows: Running: Cadence (steps per minute), stride length (average of the distance between two strides), heel strike angle (angle between the sole of the foot and the ground), and vertical amplitude (amplitude of body oscillation); Long jump: Approach acceleration (average acceleration of the last three strides), take-off angle (angle between the body's center of gravity and the ground), and take-off speed (horizontal speed at the moment of liftoff); Rope skipping: Rope swing period (time per lap), wrist rotation angular velocity, and forward lean angle. For example, a cadence of less than 80 steps per minute and a vertical amplitude exceeding 15 cm in running could indicate an inefficient movement pattern, while a take-off angle less than 40° in long jump could indicate insufficient force application. These characteristics provide important evidence for subsequent physical health assessment.

[0067] The evaluation unit calculates the matching degree between the characteristic components of the current action pattern and the historical standard action based on the decision tree model, determines the deviation of the physical health status, and triggers an early warning signal based on the calculation results. The decision tree model is a commonly used machine learning algorithm. It constructs a model that can classify and evaluate the characteristic components of new action patterns by learning and training historical standard action data. In actual applications, the evaluation unit inputs the currently extracted action pattern characteristic components into the decision tree model, compares them with the pre-stored historical standard action data, and calculates the matching degree. The matching degree calculation uses an improved cosine similarity algorithm combined with the feature weight distribution of the decision tree model. The specific formula is:

[0068]

[0069] in, is the weight of the i-th feature component (calculated by the decision tree through information gain, such as the cadence weight is 0.3 and the step length weight is 0.25 in running), is the cosine similarity between the current feature component and the standard feature component ( = is the angle between the two vectors. For example, the current running cadence (90 steps / minute) and stride length (1.2m) are compared with the standard values ​​(100 steps / minute, 1.5m). The similarity of each component is calculated and then weighted summed. If S < 0.6, it is judged as a low match. The degree of match directly reflects the degree of difference between the current movement and the standard movement, and can be used to determine the degree of deviation from the physical health status. The calculation formula for the deviation D is:

[0070]

[0071] (S represents the degree of fit). The criteria for this evaluation are based on the National Student Physical Fitness Standards and exercise physiology thresholds: D < 20% indicates normal (small deviation between movement and the standard, physiological indicators within the safe range); 20% ≤ D < 40% indicates a slight deviation (e.g., a slightly lower cadence but not exceeding the heart rate standard, based on the youth exercise heart rate safety threshold of <180 beats / minute); and D ≥ 40% indicates a significant deviation (e.g., movement distortion accompanied by a sudden increase in heart rate, refer to the "Abnormal Physiological Reaction Determination Criteria" in the Sports Medicine Guidelines). A warning signal is triggered when D ≥ 30%, based on a statistically significant probability of injury exceeding 85% for this threshold (based on over 5,000 samples). If the deviation exceeds the preset threshold, the assessment unit triggers a warning signal, alerting personnel to the adolescent's physical health so that appropriate intervention measures can be taken promptly.

[0072] The transmission unit is used to upload collected data to the cloud management platform via the ZigBee protocol. The ZigBee protocol is a low-power, low-cost, low-speed wireless communication protocol that is ideal for use in data acquisition terminals, which require long-term stable operation and relatively small data transmission volumes. The transmission unit establishes a communication link with the cloud management platform via the ZigBee protocol, and uploads collected heart rate waveform data, motion trajectory data, and evaluation results generated by the evaluation unit to the cloud management platform in real time and stably. In this way, the cloud management platform can further process, analyze, and store this data to provide support for subsequent health intervention and management.

[0073] Throughout the entire data collection terminal's operation, each component works closely together to form a complete data collection and processing workflow. The data collection device acquires raw data, the feature extraction device processes and refines the data, the evaluation unit analyzes and evaluates the data, and the transmission unit uploads the data to the cloud management platform. This clear division of labor and collaborative approach ensures the data collection terminal can efficiently and accurately complete its data collection and preliminary evaluation tasks, laying a solid foundation for the proper operation of the youth physical fitness and health management system based on physical test scores.

[0074] For example, when a teenager is taking an 800-meter running test, the terminal shell of the data acquisition terminal is worn on the teenager. The heart rate sensor in the data acquisition device monitors the changes in their heart rate in real time, and the motion trajectory sensor records the running route and speed changes. The feature extraction device extracts characteristic components such as running cadence and stride length from the motion trajectory data. The evaluation unit calculates the matching degree of these characteristic components with the historically stored standard running movements. If the matching degree is low, it indicates that the teenager's running movement may be irregular, and then it is judged that the physical health status deviates significantly, triggering an early warning signal. At the same time, the transmission unit uploads all collected data and evaluation results to the cloud management platform via the ZigBee protocol, so that the cloud management platform can perform subsequent analysis and processing, such as generating physical characteristic curves and conducting health risk assessments.

[0075] Example 2:

[0076] In this embodiment, the health intervention device serves as the core execution unit for adjusting training intensity and intervening in health risks. Its structure and functional design are directly related to the effectiveness of adolescent health management. The device comprises a main body, along with a parameter detection module, an intensity adjustment module, a command execution module, and a communication relay module. These modules work together to control training intensity and intervene in abnormal conditions during adolescent physical examinations.

[0077] The main body of the device provides physical support and protection for the various modules within it. Its form can be designed to be portable or fixed depending on the application scenario. For example, in a physical fitness test on a playground, a portable design can be used so that it can move with the teenager, while in an indoor gym, a fixed installation can be used to ensure the stability of the device. The parameter detection module, serving as the device's "sensing organ," is responsible for real-time monitoring of various indicators during device operation, including but not limited to training intensity parameters (such as resistance level, movement speed, etc.), physiological indicators of teenagers (such as heart rate, blood oxygen saturation, etc.), and the device's own operating status parameters (such as motor speed, energy consumption, etc.). The real-time collection of these parameters provides a key basis for determining whether the device is in an abnormal operating condition. For example, if a sudden increase in heart rate is detected that exceeds the normal range, it can be preliminarily determined that an abnormal condition of excessive exercise intensity may have occurred.

[0078] The intensity adjustment module is the core functional module for adjusting training intensity. It precisely adjusts training intensity based on command signals sent by the cloud management platform. This module can use various adjustment methods, such as adjusting resistance by varying motor output power in resistance training equipment and adjusting exercise intensity by varying conveyor speed in treadmill training equipment. When the cloud management platform determines that training intensity needs to be reduced based on analysis results from the data monitoring unit, the intensity adjustment module receives the corresponding command and executes the resistance or speed reduction operation to ensure that young people train within a safe intensity range.

[0079] The instruction execution module is responsible for accurately executing various instructions issued by the cloud management platform. It works in conjunction with the intensity adjustment module and parameter detection module to form a complete instruction execution chain. For example, when the cloud management platform generates an execution policy, the instruction execution module will parse the instruction content, control the intensity adjustment module to perform the corresponding intensity adjustment action, and trigger the parameter detection module to monitor the adjusted parameters in real time to ensure the accuracy and effectiveness of instruction execution. In addition, the instruction execution module also has a certain fault tolerance mechanism. When an anomaly is detected during instruction execution, it automatically triggers the emergency response procedure to ensure the safety of equipment operation.

[0080] The communication relay module establishes a stable communication link between the health intervention device and the cloud management platform, using specific communication protocols (such as ZigBee and WiFi) to enable bidirectional data transmission. On one hand, the communication relay module accurately transmits command signals from the cloud management platform to the various functional modules within the device, ensuring timely execution of the commands. On the other hand, it uploads real-time data collected by the parameter detection module to the cloud management platform, providing data support for analysis and evaluation by the data monitoring unit. During the communication process, the communication relay module also encrypts and verifies the data to prevent data loss or tampering during transmission, ensuring the security and reliability of communication.

[0081] When the health intervention device detects an abnormal indicator, it will start the abnormal state processing process. First, the timestamp data of the time when the abnormality occurs is recorded. The timestamp data is accurate to the millisecond level and can accurately reflect the time point when the abnormality occurs, providing a reference for the time dimension for subsequent analysis. At the same time, the parameter detection module continuously monitors the indicator recovery critical point. The indicator recovery critical point here refers to the key node where the physiological indicator or equipment operation indicator begins to transition from an abnormal state to a normal state. During the monitoring process, the parameter detection module will collect indicators at a fixed sampling frequency. When it is detected that the indicator value meets the preset recovery conditions for multiple consecutive times, it is determined that the recovery critical point has been reached, and the cycle count of the recovery moment is recorded. The cycle count refers to the number of sampling cycles from the occurrence of the abnormality to recovery. The combination of timestamp data and cycle count can accurately record the duration and change process of the abnormal state.

[0082] For example, when a teenager is weightlifting, the parameter detection module of the health intervention device monitors their heart rate and weight in real time. If fatigue causes their heart rate to suddenly rise to 180 beats per minute (outside the normal heart rate range for this age group), and the weight they are lifting fluctuates significantly, the device detects the abnormality and immediately records the timestamp data at that time (e.g., 10:30:25:456 ms, June 13, 2025). The parameter detection module then continuously monitors changes in heart rate and weight. When the heart rate gradually decreases to 120 beats per minute and remains stable, and the weight returns to its normal fluctuation range, the recovery threshold is determined to have been reached, and the cycle count at that time (e.g., the 125th sampling cycle) is recorded.

[0083] By recording the timestamp data of the abnormality's start point and the cycle count of the recovery end point, this system provides critical time and status data for subsequent determination of health risk intervals. Further processing and analysis of this data can help the system more accurately define risk areas requiring health intervention, enabling appropriate protective measures to ensure the safety of young people during physical examinations.

[0084] The various modules of the health intervention device collaborate and cooperate throughout the entire process, forming a complete health intervention system. The parameter detection module provides real-time perception of the device's operating status and adolescent physiological indicators. The communication relay module enables two-way data transmission. The command execution module and intensity adjustment module respond to instructions from the cloud management platform. Together, they adjust training intensity and intervene in health risks, providing strong technical support for adolescent physical health management.

[0085] Example 3:

[0086] In this embodiment, determining health risk intervals and controlling training intensity based on these intervals is a key step in the system's implementation of adolescent physical health intervention. During the operation of the health intervention device, if the parameter detection module detects an abnormality in an indicator, the system first records the timestamp of the abnormality. Simultaneously, the parameter detection module continuously monitors the indicator's critical point of recovery. Once the indicator returns to the normal range, the cycle count at that point is recorded.

[0087] When generating abnormal coordinates and recovery coordinates based on timestamp data and cycle counts, the system converts time-related data into spatial coordinate values ​​using a specific algorithm. For example, timestamp data can be mapped to the time axis coordinates in three-dimensional space, and cycle counts can be associated and mapped with sampling points in spatial locations, thereby converting the abnormal start and end information in the time dimension into specific coordinate points in space. The abnormal coordinates represent the spatiotemporal location when the abnormal state occurs, while the recovery coordinates represent the spatiotemporal location when the abnormal state ends. These two coordinate points are key nodes in defining the health risk range.

[0088] After generating the abnormal coordinates and the restored coordinates, the system will topologically connect the abnormal coordinates, the restored coordinates and the data acquisition terminal position to form a closed interval and mark it as a health risk interval. The position coordinates of the data acquisition terminal are obtained in real time through its own positioning module (such as GPS or inertial navigation unit). The position information reflects the actual spatial position of the adolescent during the physical measurement process. Through topological connection, the three key coordinate points of abnormal coordinates, restored coordinates and data acquisition terminal position are connected in space to form a closed geometric area. This topological connection is not a simple straight line connection, but a logical connection based on spatial position relationship and data association characteristics. The generation of abnormal coordinates and restored coordinates adopts a space-time mapping algorithm: coordinates The topological connection uses the Delaunay triangulation algorithm to construct a closed triangular area using the abnormal point, recovery point, and terminal position. Any point in the area meets the probability of physiological indicator abnormality of ≥ 60% (calculated based on the logistic regression model), ensuring that the closed interval can accurately cover the relevant spatial range when the abnormal state occurs. For example, when a teenager is taking a running test, if an abnormal heart rate occurs at a certain location, the abnormal coordinates are the spatial coordinates of the location and the time of the abnormality, and the recovery coordinates are the location coordinates and time when the heart rate returns to normal. The position of the data collection terminal changes in real time as the teenager runs. The closed interval formed after topological connection is the health risk spatial range corresponding to this abnormal state.

[0089] After determining the health risk interval, the system will control the health intervention device to adjust the training intensity within this interval and obtain the amplitude parameters in real time through the parameter detection module. The adjustment of training intensity is based on the execution strategy generated by the cloud management platform based on the analysis results of the data monitoring unit. For example, when the physiological indicators in the health risk interval show that the exercise intensity is too high, the system will instruct the health intervention device to reduce the running speed or reduce the resistance. During the training intensity adjustment process, the parameter detection module will collect amplitude parameters in real time at a fixed sampling frequency. The amplitude parameters can be physical quantities reflecting the training intensity (such as resistance size, speed value, etc.) or indicators reflecting the physiological state (such as heart rate variability amplitude, etc.) to monitor the adjusted equipment operation status and the physiological response of adolescents in real time.

[0090] The system has preset a safety threshold range, which is set based on individual characteristics of adolescents such as age, gender, and physical fitness, as well as sports medicine standards. When the amplitude parameter obtained in real time exceeds the preset safety threshold range, it means that the current training intensity or physiological state may pose a risk to the health of the adolescent. At this time, the system will control the health intervention equipment to maintain the preset safety threshold operation to ensure that the adolescent trains within a safe range. For example, if the preset heart rate safety threshold range is 60-150 beats / minute, when the heart rate amplitude parameter collected by the parameter detection module reaches 160 beats / minute, the system will immediately instruct the health intervention equipment to reduce the training intensity to keep the heart rate within the safety threshold of 150 beats / minute.

[0091] While controlling the operation of the health intervention device, the system continuously records the device's intensity output values. These intensity output values ​​are arranged in chronological order to form a set of fluctuation parameters. This set of fluctuation parameters fully records the changes in training intensity over time, reflecting the health intervention device's response process and adjustment trajectory to abnormal conditions. For example, during the handling of an abnormal condition, the intensity output value may gradually decrease from a high level to a safe threshold and then fluctuate around the safe threshold. This data provides important raw data for subsequent physical characteristic analysis.

[0092] Based on the fluctuating parameter set, the system uses a linear regression algorithm to generate a dynamic physical fitness characteristic curve. This algorithm analyzes the data in the fluctuating parameter set to identify the linear relationship between changes in training intensity and physical condition, thereby fitting a curve that reflects the dynamic trend of physical fitness. This curve, with time as the horizontal axis and comprehensive indicators reflecting physical condition as the vertical axis, intuitively illustrates how the physical condition of adolescents changes over time during the physical test.

[0093] In the generated dynamic physical characteristic curve, the system extracts several key feature points at equal time intervals, with the number of key feature points proportional to the curve duration. This equal time interval ensures an even distribution of key feature points along the timeline, for example, extracting one key feature point every 10 seconds. The longer the curve duration, the greater the number of key feature points extracted, which allows for a more detailed reflection of the dynamic physical characteristic curve's changes. These key feature points contain crucial information about the curve at different time points, such as peaks, valleys, and rates of change, providing a high-level summary of the dynamic physical characteristic curve.

[0094] Finally, the system maps and annotates the physical distribution of the health record topology map based on the extracted key feature points. The health record topology map is a multidimensional health status visualization model that contains information such as the adolescent's historical physical examination data and health assessment results. Mapping the extracted key feature points onto the health record topology map can intuitively annotate the physical distribution of the current physical examination process on the topology map, allowing managers or medical staff to clearly understand the adolescent's physical condition and its position in the historical health record, providing an intuitive reference for subsequent health management and intervention decisions.

[0095] Example 4:

[0096] In this embodiment, after determining the health risk interval and adjusting the training intensity, the system continuously records the intensity output values ​​of the health intervention device. These values ​​are arranged in chronological order to form a set of fluctuation parameters. For example, when a teenager is taking a rope skipping test, the health intervention device adjusts the rope resistance according to the instructions of the cloud management platform. The intensity output value after each adjustment is recorded in real time, including parameters such as resistance size and duration of action, thus forming a complete set of fluctuation parameters that reflects the dynamic changes in training intensity during the test.

[0097] Based on the fluctuating parameter set, the system uses a linear regression algorithm to generate a dynamic physical characteristic curve. The linear regression algorithm analyzes the data in the fluctuating parameter set, looking for a linear relationship between training intensity and physical condition, and then fits a curve that can reflect the dynamic change trend of physical condition. Taking the rope skipping scenario as an example, the resistance intensity change data in the fluctuating parameter set is correlated with changes in physical indicators such as heart rate and endurance of adolescents. By processing this data, the linear regression algorithm generates a curve with time as the horizontal axis and comprehensive physical indicators as the vertical axis, intuitively showing the change trend of the adolescent's physical condition over time during the rope skipping process.

[0098] In the generated dynamic characteristic curve of physical fitness, the system extracts several key feature points at equal time intervals, and the number of key feature points is proportional to the duration of the curve. For example, if a key feature point is extracted every 15 seconds and the curve duration is 300 seconds, 20 key feature points will be extracted. These key feature points cover important information such as peaks, valleys, and turning points in the curve, and can accurately reflect the changing patterns of the dynamic characteristic curve of physical fitness. In the dynamic characteristic curve of physical fitness measured by skipping rope, key feature points may correspond to the moment of adjusting the resistance of the skipping rope, the peak point of the heart rate change of teenagers, etc. Through these points, the key change nodes of physical fitness can be quickly grasped.

[0099] After extracting the key feature points, the system maps and annotates the physical distribution of the health record topology map based on these points. The health record topology map integrates the adolescent's past physical test data, health assessment results and other information to form a multi-dimensional health status model. By mapping the key feature points extracted from the current physical test to the topology map, the physical distribution of this physical test can be clearly marked in the map. For example, in the health record topology map, different coordinate axes represent different physical fitness indicators, and the key feature points will fall on the corresponding positions of the topology map according to their corresponding physical fitness indicator values, thereby intuitively presenting the performance of the adolescent's physical fitness in various indicators in this rope skipping physical test and comparing it with historical data.

[0100] After completing the constitution prediction mapping, the system will modify the intervention path of the health record topology map. Specifically, after annotating the constitution distribution map on the health record topology map, the system will logically block the preset intervention paths that overlap with the high-risk intervals in the map. For example, if there is a preset intervention path for abnormal heart rate in the health record topology map, and the constitution distribution map annotation of this physical test shows that part of the path overlaps with the current high-risk interval, the system will automatically logically block this overlapping intervention path to prevent the use of these risky paths in subsequent interventions.

[0101] In practical applications, taking a 1000-meter running test for teenagers as an example, the data acquisition terminal collects data such as their movement trajectory and heart rate in real time. When the health intervention device detects an abnormal heart rate, it records the timestamp data of the abnormal starting point and the cycle count of the recovery end point, thereby determining the health risk range. The system controls the health intervention device to adjust the running speed within this range, and obtains amplitude parameters such as speed in real time through the parameter detection module. If the parameter exceeds the preset safety threshold, the device will maintain the safety threshold operation. At the same time, the speed output value of the device is continuously recorded to form a set of fluctuation parameters, and then a linear regression algorithm is used to generate a dynamic physical characteristic curve, such as a curve reflecting the change of heart rate with speed.

[0102] Key feature points are extracted from the curve at equal time intervals, such as heart rate points at moments of sudden speed changes and heart rate points during periods of stable speed. These points are then mapped onto a health record topology map, which may include heart rate-speed data from historical running tests, endurance assessments, and other dimensions. This mapping clearly shows the matching of the adolescent's heart rate and speed during the test, as well as their position within the historical data. If a pre-defined endurance intervention path in the topology map overlaps with a current high-risk zone (e.g., a speed zone with excessively high heart rate), the system logically blocks this overlap, ensuring that subsequent intervention paths avoid risky areas and generating a safer and more effective execution strategy.

[0103] Example 5:

[0104] In this embodiment, when the health intervention device detects an abnormal training condition, the system will perform protective actions within the health risk range based on the execution strategy. The entire process includes multiple closely linked steps to ensure the safety and effectiveness of the intervention. For example, if a teenager is practicing basketball shooting, the health intervention device (such as a smart training backboard) detects a sudden increase in the teenager's heart rate and a distorted shooting motion, it will be identified as an abnormal training condition and the protective action process will be initiated.

[0105] Execute step A1, that is, select the access point position of the health risk interval with the least operation steps based on the next training node that needs to be adjusted. In the basketball training scenario, the next training node that needs to be adjusted may be the starting point of the next shooting action, and the system needs to select a suitable access point position for this node. Specifically, the feasible access point positions of each health risk interval are calculated by the Dijkstra algorithm. The algorithm can efficiently find the shortest path in the graph, which is used here to determine the path from the current device state to the feasible access point positions of each health risk interval. At the same time, a comprehensive score is performed based on the operation steps and physiological distance parameters. The operation steps refer to the number of instructions required to execute for the device to switch from the current state to the access point position, and the physiological distance parameter reflects the degree of match between the training intensity corresponding to the access point position and the current physiological state of the adolescent.

[0106] The weight coefficient for the operation step is set to α, and the weight coefficient for the physiological distance is set to β. These two weight coefficients can be adjusted according to actual needs. For example, in scenarios that emphasize safety, the weight coefficient for the physiological distance can be appropriately increased. The operation step values ​​and the physiological distance values ​​are normalized separately to obtain the step-normalized value and the distance-normalized value. Normalization converts values ​​of different dimensions into a unified dimension, facilitating comparison and calculation. The score value S is then calculated as α × step-normalized value + β × distance-normalized value. The health management unit selects the health risk interval access point with the highest score S. In the basketball example, there may be multiple feasible access points, such as those for lowering the backboard height and adjusting the shooting resistance. Based on the comprehensive score, the point with the fewest operation steps and the shortest physiological distance is selected. For example, the point for adjusting the shooting resistance requires fewer operation steps and is more closely aligned with the adolescent's current physiological state.

[0107] Execute step A2 to control the health intervention device to switch to the access point and synchronize its parameters. During basketball training, after receiving the access point command, the health intervention device (smart training backboard) switches to the selected point for adjusting shooting resistance and synchronizes its parameters to ensure that the device's resistance parameters are consistent with the health risk range requirements. Parameter synchronization includes calibration of the device's own parameters and synchronization with the cloud management platform's data to ensure the accuracy of subsequent operations.

[0108] Execute step A3 to control the health intervention device to enter the health risk zone from the access point and perform intensity adjustment actions according to the intervention path in the execution strategy. The smart training backboard enters the health risk zone from the access point for adjusting shooting resistance and begins operating within that zone. Following the intervention path in the execution strategy, it gradually reduces shooting resistance to reduce the youth's training intensity and gradually restore their heart rate to normal. For example, the execution strategy might specify a 10-second step-by-step reduction in shooting resistance from the current 80% to 50%, and the device will perform intensity adjustment actions according to that path.

[0109] Execute step A4 to obtain the output parameters of the health intervention device in real time and optimize and compensate for them using a genetic algorithm. During the process of reducing shooting resistance, the device's output parameters, such as the actual resistance level and changes in the adolescent's heart rate, are obtained in real time. A genetic algorithm is an optimization algorithm that mimics natural selection and heredity. By performing operations such as selection, crossover, and mutation on the output parameters, it finds the optimal parameter combination and optimizes and compensates for the output parameters. For example, if the adolescent's heart rate decreases too slowly after reducing shooting resistance, the genetic algorithm will automatically adjust the rate of resistance reduction to achieve a more effective intervention.

[0110] Execute step A5. After each continuous training session in the health risk zone, control the health intervention device to pause output, exit the health risk zone, and re-execute step A1. During basketball training, after completing a continuous training session with reduced shooting resistance (e.g., a complete shot at the adjusted resistance), the smart training backboard pauses its resistance output, exits the health risk zone, and then re-executes step A1 to select the access point for the next training node. This cycle continues until the abnormal training condition is resolved.

[0111] Taking a teenager performing standing long jump training as an example, a health intervention device (a smart long jump mat) detected abnormal knee pressure during takeoff, identifying it as an abnormal training condition. The system used the Dijkstra algorithm to calculate feasible access points. Based on a comprehensive score of the operating steps and physiological distance parameters, it selected a point for adjusting the takeoff assist. After the device switched to that point and synchronized its parameters, it entered the health risk zone at that access point and increased the takeoff assist according to the execution strategy to reduce knee pressure. The device's assist output parameters and knee pressure data were acquired in real time, and a genetic algorithm was used to optimize the compensation parameters to ensure precise assist adjustment. After each standing long jump, the device paused its output and exited the health risk zone, reselecting the next access point until knee pressure returned to normal.

[0112] Through scientific access point selection, precise parameter synchronization, rational intensity adjustment, and intelligent parameter optimization, a closed-loop intervention mechanism is formed. When abnormal training conditions are detected, protective actions are quickly and effectively executed, reducing training risks and safeguarding the health of young people. Each step is closely centered around health risk zones, ensuring targeted and effective interventions and providing reliable technical support for youth physical health management.

[0113] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0114] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A physical health management system for adolescents based on physical test results, characterized by: include: A data acquisition terminal, a health intervention device, and a cloud management platform, wherein the data acquisition terminal and the health intervention device are respectively connected to the cloud management platform for communication, and the cloud management platform includes a data monitoring unit, an evaluation processing unit, and a health management unit; The data acquisition terminal is used to collect the sports indicators and physiological signals of the adolescents during the physical examination in real time; The health intervention device is used to receive instruction signals from the cloud management platform to adjust the training intensity; The data monitoring unit is used to record the abnormal starting point and recovery end point of the indicators during the operation of the health intervention device, determine the health risk interval based on the abnormal starting point and recovery end point of the indicators, control the health intervention device to maintain a preset safety threshold for abnormal physical conditions and record fluctuation parameters, generate a physical characteristic curve based on the fluctuation parameters, and perform physical prediction mapping on the health file topology map; The evaluation processing unit is used to modify the intervention path of the health record topology map that has completed the physical fitness prediction mapping and generate an execution strategy; The health management unit includes a regular control unit and an emergency control unit, wherein the regular control unit is used to control the health intervention device to perform a baseline intensity output when the device is in a normal training condition; The emergency control unit is used to control the health intervention device to perform protection operations within the health risk range according to the execution strategy when the health intervention device detects abnormal training conditions; Determining the health risk interval based on the abnormal indicator starting point and recovery end point includes: Generate abnormal coordinates and recovery coordinates based on timestamp data and cycle counts; The abnormal coordinates, restored coordinates and data acquisition terminal locations are topologically connected to form a closed interval, and the closed interval is marked as a health risk interval; The recording of abnormal indicator start points and recovery end points during the operation of the health intervention device includes: When the health intervention device detects an abnormality in an indicator, it records the timestamp data of the time when the abnormality occurs, continuously monitors the critical point of indicator recovery through the parameter detection module, and records the cycle count of the recovery time; The control of the health intervention device to maintain a preset safety threshold for abnormal physical conditions and record fluctuation parameters, generate a physical characteristic curve based on the fluctuation parameters, and perform physical prediction mapping on the health record topology map includes the following steps: Controlling the health intervention device to adjust the training intensity of the health risk interval, and obtaining amplitude parameters in real time through a parameter detection module; A preset safety threshold range is set. If the amplitude parameter exceeds the preset safety threshold range, the health intervention device is controlled to maintain the preset safety threshold operation; Continuously record the intensity output values ​​of health intervention devices to form a set of fluctuation parameters; Based on the set of fluctuation parameters, a linear regression algorithm is used to generate a dynamic characteristic curve of physical fitness, find the linear relationship between training intensity and physical fitness, and then fit a curve that can reflect the dynamic change trend of physical fitness; Extracting a number of key feature points at equal time intervals from the physical fitness dynamic characteristic curve, covering the peak value, valley value, and turning point of the curve, can accurately reflect the changing pattern of the physical fitness dynamic characteristic curve. The number of key feature points is proportional to the duration of the curve. Based on the extracted key feature points, the topological map of the health record is annotated with the physical distribution map; The said correcting the intervention path of the health record topology map after completing the constitution prediction mapping includes logically shielding the preset intervention path in the health record topology map that overlaps with the high-risk interval after marking the constitution distribution mapping on the health record topology map; When the health intervention device detects an abnormal training condition, controlling the health intervention device to perform a protection operation within the health risk range according to the execution strategy includes: A1. Select the health risk interval access point with the least number of operation steps based on the next training node to be adjusted; A2. Control the health intervention device to switch to the access point and synchronize parameters; A3. Controlling the health intervention device to enter the health risk zone from the access point and performing intensity adjustment actions according to the intervention path in the execution strategy; A4. Obtain the output parameters of health intervention equipment in real time and use genetic algorithms to optimize and compensate the output parameters; A5. After completing each continuous training operation in the health risk zone, control the health intervention device to pause output and exit the health risk zone, and re-execute A1; The A1 comprises the following steps: The Dijkstra algorithm is used to calculate the feasible access points for each health risk interval and a comprehensive score is given based on the operation steps and physiological distance parameters; Based on the comprehensive scoring results, select the access point in the health risk interval with the least operation steps and the shortest physiological distance; The comprehensive scoring based on operation steps and physiological distance parameters includes: Set the weight coefficient of operation steps to α and the weight coefficient of physiological distance to β; Normalize the operation step values ​​to obtain the step normalization value, and normalize the physiological distance values ​​to obtain the distance normalization value; Calculate the score value S = α × step normalization value + β × distance normalization value; The health management unit is used to select the health risk interval access point with the highest score S.

2. A physical fitness and health management system for adolescents based on physical test scores according to claim 1, characterized in that: The data acquisition terminal includes a terminal housing and a data acquisition device, a feature extraction device, an evaluation unit and a transmission unit arranged in the housing; The data acquisition device is used to synchronously acquire heart rate waveform and motion trajectory data; The feature extraction device is used to extract the action pattern feature components of the motion trajectory; The evaluation unit is used to calculate the matching degree between the characteristic components of the current movement pattern and the historical standard movement based on the decision tree model, determine the deviation degree of the physical health status, and trigger the early warning signal according to the calculation result; The transmission unit is used to upload the collected data to the cloud management platform via the ZigBee protocol.

3. A physical fitness and health management system for adolescents based on physical test scores according to claim 1, characterized in that: The health intervention device includes a device body and a parameter detection module, an intensity adjustment module, an instruction execution module and a communication relay module arranged in the body.

Images