Intelligent sports data analysis method and system based on Internet of Things, and medium

Abstract

The invention relates to the technical field of intelligent sports data analysis, in particular to an intelligent sports data analysis method and system based on the Internet of Things and a medium. The method comprises the following steps: acquiring real-time state data of physical exercise of an athlete through an intelligent bracelet worn by the athlete; based on an electronic video recording device, motion posture data mapping is carried out according to the real-time state data of the athletes in physical exercise, and motion posture mapping data is obtained; performing instantaneous explosive power evaluation on the motion attitude mapping data, performing abnormal load limit coupling processing, and performing motion risk level evaluation to obtain motion risk level data; making an intelligent motion feedback strategy based on the motion risk level data to obtain the intelligent motion feedback strategy; and sending the intelligent motion feedback strategy to the intelligent bracelet to execute sports data analysis. The intelligent sports data analysis technology is optimized, so that the intelligent sports data analysis technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the technical field of smart sports data analysis, and in particular to a smart sports data analysis method, system and medium based on the Internet of Things. Background Art

[0002] Internet of Things (IoT) technology has gradually penetrated into various industries, and the sports industry has ushered in huge opportunities and challenges in the process of intelligent and digital transformation. Traditional sports data collection methods rely on manual recording and simple equipment, which cannot meet the high efficiency, high precision and real-time requirements of modern sports events and training. The combination of IoT technology, intelligent sensors, wireless networks and cloud computing platforms, can collect and analyze multi-dimensional data of athletes, events and venues in real time and accurately, greatly improving the accuracy and application scope of sports data analysis. Smart sports, as an important field of IoT technology application, can achieve real-time monitoring and intelligent analysis of athletes' physiological data, behavioral data, competition data, etc. with the help of sensors, wearable devices, high-definition video monitoring and other technical means. By integrating a variety of sensor technologies, IoT can obtain a number of physiological and sports data such as athletes' heart rate, cadence, movement trajectory, muscle load, etc. in real time. At the same time, IoT can also provide accurate analysis based on big data to help coaches and athletes formulate training plans more scientifically and evaluate athletes' physical status and health risks. However, a traditional IoT-based smart sports data analysis method has the problem of inaccurate identification of athletes' load status and inability to accurately evaluate the risk level of sports. Summary of the invention

[0003] Based on this, it is necessary to provide a smart sports data analysis method, system and medium based on the Internet of Things to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a smart sports data analysis method based on the Internet of Things is provided, the method comprising the following steps: Step S1: obtaining the real-time state data of the athlete's sports through the smart bracelet worn by the athlete; mapping the sports posture data based on the real-time state data of the athlete's sports based on the electronic video recording device to obtain the sports posture mapping data; Step S2: performing instantaneous explosive force evaluation on the motion posture mapping data to obtain posture-enhanced instantaneous explosive force data; performing abnormal load limit coupling processing based on the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data; Step S3: evaluating the sports risk level according to the abnormal load limit data to obtain sports risk level data; formulating an intelligent sports feedback strategy based on the sports risk level data to obtain an intelligent sports feedback strategy; Step S4: Send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

[0005] The present invention collects the real-time status data of athletes through a smart bracelet, and combines the electronic video recording device to map the sports posture, effectively obtaining the details and dynamics of the athletes' movements. This step can realize accurate sports monitoring, combine the athletes' physical fitness, movements and physiological data, and form a comprehensive sports data model. This provides rich original data support for subsequent evaluation and feedback, ensures accurate monitoring of sports performance, and lays the foundation for the personalized training program of athletes. By evaluating the instantaneous explosive power of sports posture data, the changes in the explosive power of athletes in training or competition can be captured in real time, and the instantaneous sports ability of athletes can be fed back in time. In addition, based on these data, abnormal load limit coupling processing is performed to help discover the overload phenomenon or uneven load that occurs when athletes perform high-intensity exercise. This step can help trainers identify the potential physical bottlenecks and the risk of excessive load of athletes, adjust the training intensity and content in time, and avoid athletes from being injured by excessive load. Evaluating the sports risk level through abnormal load limit data is an important link to ensure the safety of athletes. This step can identify the risk level of athletes in specific sports states, help trainers adjust training plans in time, and avoid injuries caused by excessive exercise or unreasonable training. The assessment of sports risk levels is not only crucial to the health of athletes, but also serves as an early warning in preventing sports injuries. The intelligent sports feedback strategy developed based on this assessment result will further optimize the training process and improve the safety and effectiveness of athletes' training. By sending the intelligent sports feedback strategy to the smart bracelet and performing sports data analysis, athletes can get real-time training feedback and understand their sports status and progress. This link can not only effectively guide athletes to adjust their movements and intensity in time, but also enhance athletes' self-awareness of the sports process. As a real-time feedback tool, the bracelet enables athletes to respond quickly to intelligent strategies, thereby achieving the purpose of improving sports efficiency, optimizing training results, and reducing sports injuries. Through continuous intelligent analysis and feedback, athletes' performance can be precisely controlled and improved.

[0006] Preferably, step S1 comprises the following steps: Step S11: obtaining the athlete's real-time sports status data through the smart bracelet worn by the athlete; Step S12: Cleaning the real-time sports status data of the athletes to obtain cleaned real-time sports status data; Step S13: performing time-series segmentation on the sports real-time state cleaning data to obtain sports real-time state segmentation data; Step S14: Based on the electronic video recording device, the motion posture data is mapped according to the real-time motion state segmentation data to obtain the motion posture mapping data.

[0007] The present invention collects the real-time status data of athletes through smart bracelets, and can accurately capture the athletes' physiological indicators (such as heart rate, exercise intensity, cadence, acceleration, etc.) and sports performance (such as exercise speed, angle change, exercise posture, etc.). The advantages of smart bracelets are their convenience and wearability, and athletes can monitor their own status in real time during training or competition. By obtaining these real-time data, comprehensive original information is provided for subsequent analysis and evaluation, thereby providing strong support for personalized training and health management. Data cleaning of athletes' real-time status data can eliminate noise, erroneous data and outliers to ensure the accuracy and reliability of the data. Athletes' sports status data are usually affected by various factors (such as environmental conditions, equipment errors, etc.), and data cleaning can eliminate these influences and ensure that the basis for subsequent analysis is more reliable. The cleaned data makes subsequent analysis more accurate, avoids erroneous judgments caused by inaccurate or redundant data, and ensures the accuracy of athletes' health and performance evaluation. Time series segmentation is to divide the athlete's sports data according to time sequence and feature changes, which helps to carry out refined analysis of different sports stages. For example, segmented data can help identify athletes' warm-up stage, burst stage, recovery stage, etc. Through time segmentation, targeted evaluation and optimization suggestions can be provided for each stage, avoiding a one-size-fits-all analysis method, so that more targeted research and feedback can be conducted on the performance of athletes in different states. This process helps to manage the training load of athletes and ensure that the data of each stage is fully utilized. By combining the mapping of athletes' postures with electronic video recording equipment, more detailed sports performance data can be obtained. Electronic video recording equipment can accurately capture the movements and postures of athletes, and conduct accurate posture analysis with the data of time segmentation. For example, it can be evaluated whether the athlete's movements are standard, whether there are irregular postures, or whether there are high-risk movements in a specific sport. In this way, it is possible to identify the changes in the athlete's posture in different sports states, further optimize the training plan, reduce the occurrence of sports injuries, and improve sports performance. This step is a key link in data analysis and athlete feedback, and provides a basis for the generation of personalized sports suggestions.

[0008] Preferably, step S2 comprises the following steps: Step S21: performing posture amplitude enhancement analysis on the motion posture mapping data to obtain motion posture amplitude enhancement data; Step S22: performing instantaneous explosive force evaluation on the movement posture amplitude enhancement data to obtain posture enhancement instantaneous explosive force data; Step S23: analyzing the instantaneous heart rate fluctuation of the athlete's sports real-time state data according to the posture-enhanced instantaneous explosive power data to obtain posture-associated instantaneous heart rate fluctuation data; Step S24: performing abnormal load limit coupling processing based on the posture-associated instantaneous heart rate fluctuation data and the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data.

[0009] The present invention can more accurately evaluate the changes in the athlete's body posture and its amplitude in a specific action by performing posture amplitude enhancement analysis on the motion posture mapping data. The posture amplitude enhancement analysis can reveal the potential and physiological performance of each action of the athlete during the exercise process by amplifying or enhancing the amplitude characteristics of key actions. This process can help coaches and athletes identify potential improvement spaces in posture and action, especially in terms of strength, explosive power and speed, provide more detailed data support, provide a scientific basis for personalized training, and thus optimize the athlete's sports performance. Performing instantaneous explosive power evaluation on the motion posture amplitude enhancement data can accurately evaluate the explosive power output of the athlete in the instantaneous motion state. This evaluation can help coaches understand key information such as the muscle explosive power and reaction time of the athlete under specific actions. Instantaneous explosive power is a very critical indicator in many sports. Through real-time evaluation of data, the potential and shortcomings of athletes can be discovered in time, and athletes can be guided to make more targeted adjustments in explosive power training to improve training effects and competition performance. According to the posture enhancement instantaneous explosive power data, the real-time heart rate fluctuation of athletes is analyzed to reveal the heart rate response and adjustment of athletes under different exercise intensities. Instantaneous heart rate fluctuation is an important indicator for measuring athletes' endurance, recovery ability and cardiovascular health. Analysis combined with posture-enhanced instantaneous explosive power data can help understand the trend of heart rate changes and whether there is excessive load when athletes are doing high-intensity explosive power training. This step provides a more accurate dynamic assessment of the athlete's physiological state, helps to find signs of excessive exercise and avoid injuries caused by overtraining. Based on the abnormal load limit coupling processing of posture-associated instantaneous heart rate fluctuation data and posture-enhanced instantaneous explosive power data, it is possible to comprehensively consider the athlete's explosive power and heart rate fluctuations and accurately assess their exercise load. Through coupling processing, the relationship between heart rate and posture explosive power during high-intensity training can be revealed, so as to determine whether the athlete's load limit has been exceeded. This step helps identify potential risks for athletes, especially physical injuries or excessive fatigue caused by extreme loads, thereby providing a scientific basis for the adjustment of training loads and athlete safety assurance, optimizing the training effect of athletes and reducing the occurrence of injuries.

[0010] Preferably, step S24 includes the following steps: Step S241: Perform momentum rapid change analysis on the posture enhancement instantaneous explosive force data to obtain instantaneous momentum rapid change data; Step S242: Calculate the motion state conversion time difference for the instantaneous momentum rapid change data to obtain the motion state conversion time difference; Step S243: performing muscle damage stress limit simulation according to the motion state conversion time difference and instantaneous momentum rapid change data to obtain muscle damage stress limit data; Step S244: performing nonlinear jump instability analysis based on the posture-associated instantaneous heart rate fluctuation data to obtain nonlinear jump instability data; Step S245: performing abnormal load limit coupling processing based on the nonlinear jump instability data and the muscle injury stress limit data to obtain abnormal load limit data.

[0011] The rapid change analysis of momentum of the present invention can reveal the instantaneous change of the athlete's power transformation and power output in a short period of time. The change of instantaneous momentum has a direct impact on the load of the athlete's muscles and joints during high-intensity actions (such as jumping, acceleration, etc.). By analyzing the rapid change of momentum, it can help coaches understand the distribution of the athlete's explosive power in key actions and evaluate whether the athlete has excessive load fluctuations during the execution of the action. This analysis can identify high-risk actions and potential excessive loads, which is of great significance for optimizing training programs and avoiding sports injuries. The time difference of motion state conversion refers to the time difference required for an athlete to convert from one motion state (such as stillness, acceleration, deceleration, etc.) to another state. This data reflects the reaction speed and adaptability of athletes when performing complex sports actions. For example, in the acceleration and deceleration process in sprinting or basketball, the time difference of motion state conversion can help analyze how athletes react quickly at high speeds and whether these conversions are uncoordinated or unreasonable. By accurately calculating the conversion time difference, the coordination and rhythm of movements in training can be optimized, and the reaction efficiency of athletes in competitions can be improved. Muscle injury stress limit simulation can evaluate the stress limit of athletes' muscles during high-intensity training or competition by combining instantaneous momentum changes and the time difference of motion state conversion. Each conversion of motion state and drastic change of momentum will cause a certain amount of pressure on the muscles, and exceeding a certain stress value will cause muscle damage. By simulating the stress distribution under different motion states, the risk of muscle injury in athletes in specific movements can be predicted, helping coaches to scientifically arrange training loads and avoid muscle strain or fatigue injury caused by overtraining or too fast action switching. Nonlinear jump instability analysis is used to study the relationship between heart rate fluctuations and posture changes of athletes during exercise. Heart rate fluctuations are an important reflection of the athlete's physiological state. Nonlinear jump instability analysis can reveal the nonlinear law of heart rate changes under different exercise intensities. For example, when an athlete reaches a certain critical point, his heart rate will suddenly jump or become unstable, which usually indicates that his physiological state is close to the limit. By analyzing these nonlinear fluctuations, it is possible to evaluate the athlete's endurance limit and exercise load tolerance, and timely detect excessive fatigue or physiological discomfort in athletes, help adjust training plans, and avoid overtraining and sports injuries. In this step, by coupling the nonlinear jump instability data and the muscle damage stress limit data, the load limit that athletes are subjected to during exercise can be comprehensively evaluated. This process can reveal the comprehensive stress that athletes' physiological systems and muscles are subjected to during high-intensity training or competition, especially in the case of physiological imbalance (such as the nonlinear jump of heart rate and the high load of muscle stress).Through this coupled analysis, the abnormal load limits of athletes under specific conditions can be determined, the risks of injury or discomfort can be identified in advance, and training intensity, rest and recovery cycles can be adjusted to improve the scientific nature of training, reduce injuries caused by excessive load, and ensure the long-term health and stable performance of athletes.

[0012] Preferably, step S245 includes the following steps: Calculate the injury yield point of the muscle injury stress limit data to obtain the muscle injury yield point data; According to the muscle injury yield point data, the plastic deformation stress relationship analysis is performed on the muscle injury stress limit data to obtain the plastic deformation stress relationship data; Based on the plastic deformation stress relationship data and muscle injury yield point data, risk trend identification is performed to obtain muscle injury risk trend data; The nonlinear jump instability data is numerically simulated to obtain the jump instability value; Abnormal load limit coupling processing is performed according to the jump instability value and muscle injury risk trend data to obtain abnormal load limit data.

[0013] The present invention can identify the critical point of muscle damage in athletes during high-intensity training or competition by calculating the damage yield point of muscle damage stress limit data. The damage yield point refers to the maximum stress value that the muscle can withstand. If this value is exceeded, the muscle tissue will be irreversibly damaged. Calculating the damage yield point can provide a quantitative reference for the training load and recovery time of athletes, help coaches understand when to adjust the training intensity or increase rest under high-intensity exercise, prevent athletes from unconsciously overusing muscles, and reduce the risk of injury. Based on the muscle damage yield point, plastic deformation stress relationship analysis is performed to help study the stress response of muscles after exceeding the yield point. Plastic deformation refers to the process in which a material undergoes permanent deformation when the force is too large. By analyzing the plastic deformation stress relationship of muscles, it is possible to clarify the continuous load changes that the muscles bear after the stress exceeds the yield point. This analysis provides athletes with more detailed physiological response data, helps to judge the adaptation process and recovery ability of athletes' muscles in long-term high-intensity exercise, and thus formulates a more scientific load control strategy to avoid excessive muscle fatigue and injury. By combining plastic deformation stress relationship data and muscle injury yield point data for risk trend identification, the injury trend of athletes under different training loads can be effectively predicted. This process reveals whether the athlete's muscles will enter a high-risk state under increasing loads through comprehensive analysis of historical data. For example, as the training intensity increases, if the muscle stress approaches the yield point, there will be a trend of increasing injury risk. Through the identification of risk trends, athletes and coaches can identify potential muscle injuries at an early stage and adjust training plans in time to avoid long-term injuries caused by overtraining. The instability numerical simulation of nonlinear jump instability data can deeply analyze the physiological reactions of athletes under intense exercise or sudden states. Physiological data such as heart rate and blood pressure often experience nonlinear fluctuations during exercise, especially when the intensity of exercise changes sharply (such as sudden acceleration or deceleration). The instability numerical simulation reveals whether these fluctuations will cause physiological instability phenomena, such as excessive heart rate or abnormal fluctuations, through numerical analysis. By simulating different sports scenarios, it is possible to predict the physiological limits faced by athletes in high-intensity training or competition, help warn athletes of physiological imbalances, and formulate reasonable exercise loads and recovery cycles. By combining the jump instability value and muscle injury risk trend data for abnormal load limit coupling processing, the risks faced by athletes under extreme load can be comprehensively assessed. This process can reveal how the athlete's muscle stress, heart rate fluctuations and other physiological data interact with each other under high-intensity exercise loads and lead to potential overload or injury risks. For example, when the jump instability value and muscle injury risk data simultaneously indicate the limit of a certain training load, the athlete's body will enter a high-risk state, increasing the possibility of injury.Through coupling analysis, athletes can be provided with more accurate load adjustment suggestions to help them avoid injuries caused by overtraining or unreasonable loads, and ensure the health and safety of training and competition.

[0014] Preferably, step S3 comprises the following steps: Step S31: normalizing the abnormal load limit data to obtain abnormal load limit normalized data; Step S32: evaluating the sports risk level of the athlete's real-time sports state data according to the abnormal load limit normalization data to obtain sports risk level data; Step S33: Formulate an intelligent motion feedback strategy based on the motion risk level data and the abnormal load limit normalization data to obtain an intelligent motion feedback strategy.

[0015] The present invention normalizes the abnormal load limit data, aiming to convert the original data into a unified standard range, which is convenient for subsequent analysis and processing. Since the abnormal load limit data comes from different athletes, different sports types or different training conditions, the numerical range is inconsistent. Therefore, through normalization, the differences between the data can be eliminated and placed in a unified standard scale. The beneficial effect of this step is to ensure the consistency and comparability of data processing, which helps to accurately evaluate the sports state and load limit of athletes in the future, and then provide reliable basic data for the formulation of sports risk assessment and intelligent feedback strategies. The abnormal load limit normalized data is used in combination with the real-time state data of athletes to evaluate the sports risk level. This process compares the physiological parameters of athletes (such as heart rate, pace, muscle load, etc.) with the load limit data after normalization, and can evaluate the risk level of athletes at the current exercise intensity. Through the evaluation of different load levels, the physiological burden and injury risk of athletes can be monitored in real time. For example, if the real-time state of the athlete is close to the load limit or exceeds the tolerable range, the system can automatically evaluate a higher sports risk level, issue a warning in time, and reduce the injury caused by excessive exercise. In this way, accurate sports monitoring can be provided for athletes to ensure sports safety. Based on the sports risk level data and abnormal load limit normalization data, an intelligent sports feedback strategy is formulated. This step analyzes the athlete's real-time sports risk and physiological state, combined with their load limit data, to formulate a personalized sports feedback strategy. Feedback strategies include reducing exercise load, adjusting training intensity, increasing rest time, or providing other recovery suggestions. By dynamically adjusting the training plan, athletes can avoid sports injuries due to overtraining or improper load. The intelligent feedback strategy can help athletes adjust the exercise rhythm in real time during training, maximize the training effect, and reduce the risk of injury. The beneficial effect of this strategy is to provide personalized training and recovery plans to ensure the health and efficient performance of athletes, especially suitable for high-intensity, complex sports training and competition scenarios.

[0016] Preferably, step S33 includes the following steps: Step S331: constructing a motion load correlation matrix for the abnormal load limit normalized data to obtain a motion load correlation matrix; Step S332: performing exercise rhythm adaptability feedback on the exercise load correlation matrix and the exercise risk level data based on the fourth-order Runge-Kutta algorithm to obtain exercise rhythm adaptability feedback data; Step S333: performing differential dynamic programming on the motion rhythm adaptability feedback data to obtain motion rhythm differential dynamic data; Step S334: formulating an intelligent motion feedback strategy based on the motion rhythm differential dynamic data to obtain an intelligent motion feedback strategy.

[0017] The present invention can help analyze and understand the relationship between different training loads and athletes' physiological responses by constructing a sports load association matrix. The abnormal load limit normalized data represents the athlete's physiological limit, and the sports load association matrix provides a structured data perspective by quantifying the connection between load and physiological response under different training conditions. By constructing this matrix, the influence of different loads on various physiological indicators of athletes (such as heart rate, muscle fatigue, etc.) can be revealed, thereby realizing accurate prediction of load regulation. The beneficial effect of this step is to provide basic data for subsequent feedback and adjustment, ensure the rationality of training load, and provide a scientific basis for personalized training plans. The fourth-order Runge-Kutta algorithm is an efficient numerical solution for processing the dynamic relationship between sports load and risk level data. In step S332, by combining the sports load association matrix with the sports risk level data and using the fourth-order Runge-Kutta algorithm for feedback calculation, the sports rhythm adaptability feedback data can be obtained. These feedback data reveal how athletes should adjust their sports rhythm under different loads to avoid overload or excessive fatigue. The algorithm provides real-time and accurate feedback by simulating the nonlinear dynamics during the exercise process with high precision, so that athletes can adjust the intensity or rhythm of exercise according to the real-time physical state and reduce the risk of injury. The beneficial effect of this step is that the exercise rhythm can be adjusted in real time and accurately according to the physiological response of the athlete, so as to achieve dynamic adjustment and precise control, and ensure the training effect and safety. Differential dynamic programming is an optimization method. The adaptive feedback data of the exercise rhythm is further analyzed by dynamic programming technology to optimize the exercise rhythm adjustment strategy of the athlete. In step S333, differential dynamic programming converts the feedback data into an adaptive dynamic adjustment strategy. Taking into account the complex relationship between training load, exercise risk and physiological state, a set of optimal exercise rhythm adjustment schemes are obtained through repeated optimization. This method can comprehensively consider multiple factors, such as the current physical state of the athlete, training plan and long-term recovery needs, so as to provide athletes with a more sophisticated rhythm adjustment scheme. The beneficial effect of this process is to provide a personalized dynamic adjustment strategy to help athletes optimize the exercise rhythm according to the real-time situation, maximize the training effect, and avoid excessive fatigue and sports injuries. By analyzing the differential dynamic data of the exercise rhythm, an intelligent exercise feedback strategy is formulated. These strategies combine the athlete's current exercise rhythm, load and risk level, as well as the athlete's physical condition, to form personalized adjustment suggestions. For example, if the data shows that the athlete's current training load is too large, the system will recommend reducing the training intensity or adjusting the exercise rhythm; if the athlete's rhythm is too slow, the system will encourage faster exercise pace. These intelligent feedback strategies can accurately adapt to the specific needs of each athlete through automated adjustments, maximizing training effects while reducing the risk of injury.The beneficial effect of this step is that it provides a highly personalized and intelligent sports feedback mechanism, which provides scientific and practical guidance to athletes and coaches through real-time data analysis, ensuring the health and safety of athletes during training.

[0018] Preferably, step S332 includes the following steps: Based on the fourth-order Runge-Kutta algorithm, the fourth-order Runge-Kutta numerical solution of the motion load correlation matrix is ​​performed to obtain the dynamic evolution sequence of the motion load; According to the dynamic evolution sequence of sports load, load pattern clustering processing is performed on the sports risk level data to obtain load pattern clustering data; According to the load pattern clustering data, the dynamic load zero boundary point matching is performed on the motion load correlation matrix to obtain the dynamic load zero boundary data; According to the dynamic load zero-bound data, the motion risk level data is processed by fourth-order Runge-Kutta iteration to obtain the motion rhythm stability matrix; The exercise load characteristic matrix is ​​feedback-adjusted according to the exercise rhythm stability matrix to obtain exercise rhythm adaptability feedback data.

[0019] The fourth-order Runge-Kutta algorithm of the present invention is a high-precision numerical integration method, which is widely used to solve ordinary differential equations. In this step, by performing a fourth-order Runge-Kutta numerical solution on the sports load association matrix, the dynamic changes of the sports load at different time points can be accurately simulated. The dynamic evolution sequence reflects the trend of the sports load over time, including its growth, decay or stable stage. Through this high-precision numerical simulation, the nonlinear changes of the sports load can be captured more carefully, helping to analyze the adaptability and potential risks of athletes under different load conditions. The beneficial effect of this step is that an accurate load evolution curve can be obtained, which provides important data support for subsequent risk assessment, load pattern identification and rhythm adjustment. Load pattern clustering processing is to identify different load patterns by analyzing the dynamic evolution sequence of the sports load. For example, there are obvious differences in the physiological reactions and sports performance of athletes under light load, medium load and high load conditions. Through cluster analysis, the data under these different load states can be grouped to form a group with similar load characteristics, and a corresponding risk level is specified for each load pattern. This process helps to identify the sports risks of athletes under different training loads, as well as the physiological stress and injury risks they face. Through load pattern clustering, the health status of athletes can be more accurately assessed under different load conditions, and the training intensity or exercise plan can be adjusted in a targeted manner, thereby achieving personalized training. The beneficial effect of this step is that a scientific load identification model can be provided for athletes through clustering processing, which assists in formulating a more personalized and safe training plan. Dynamic load zero-cutoff point matching refers to further analyzing the load pattern clustering data to find the critical point that has a significant impact on the athlete's physiological state during the evolution of the sports load. The load zero-cutoff point usually refers to the point at which the athlete's physiological system changes from an adaptive state to an overload state under a certain load threshold, or the point at which the risk level increases sharply. By matching these load zero-cutoff points, the physiological stress limit encountered by athletes at different training stages and the turning point of sports risks can be accurately identified. The beneficial effect of this process is that it can help accurately identify the key conversion points of the load and provide athletes with an early warning system to prevent overtraining and injury. At the same time, dynamic load zero-cutoff point matching can also provide an important basis for athletes' load adjustment and recovery plans, making training more scientific and targeted. Using the dynamic load zero cutoff point data, the dynamic relationship between exercise load and exercise risk level is further analyzed through iterative processing of the fourth-order Runge-Kutta algorithm. This iterative processing can simulate how athletes adjust their rhythm to maintain body stability when approaching or exceeding the load zero cutoff point by refining the change trend of exercise load. The exercise rhythm stability matrix reflects the ability of athletes to maintain a healthy exercise rhythm under different load conditions, and helps determine whether their exercise rhythm will lead to excessive physiological burden or exercise imbalance.The beneficial effect of this step is that it can predict and adjust the rhythm stability of athletes in real time, prevent athletes from entering an overload state or becoming overly fatigued, and thus reduce the probability of sports injuries. By feedback-adjusting the sports load characteristic matrix through the sports rhythm stability matrix, the sports rhythm of athletes can be finely regulated. Feedback adjustment is to dynamically optimize the athlete's training plan based on the athlete's current rhythm stability and its load characteristics. Specifically, if the athlete's rhythm is unstable or the sports load is close to the zero threshold, the system will adjust its sports rhythm according to the feedback, appropriately reduce the training intensity or adjust the training method, thereby improving the athlete's adaptability and safety. This feedback process not only optimizes the sports rhythm, but also reduces the risk of overload or injury to athletes. The beneficial effect of this step is to provide a personalized sports rhythm adjustment plan through a dynamic feedback mechanism, effectively improve training efficiency, protect the health of athletes, and ensure the continuous improvement of their sports performance.

[0020] Preferably, the present invention also provides a smart sports data analysis system based on the Internet of Things, which is used to execute the smart sports data analysis method based on the Internet of Things as described above. The smart sports data analysis system based on the Internet of Things includes: The data acquisition module is used to obtain the real-time status data of the athlete's sports through the smart bracelet worn by the athlete; based on the electronic video recording device, the sports posture data is mapped according to the real-time status data of the athlete's sports to obtain the sports posture mapping data; The abnormal load analysis module is used to evaluate the instantaneous explosive force of the motion posture mapping data to obtain the posture-enhanced instantaneous explosive force data; perform abnormal load limit coupling processing based on the posture-enhanced instantaneous explosive force data to obtain the abnormal load limit data; A motion feedback module is used to evaluate the motion risk level according to the abnormal load limit data to obtain the motion risk level data; and to formulate an intelligent motion feedback strategy based on the motion risk level data to obtain the intelligent motion feedback strategy; The analysis and feedback module is used to send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

[0021] Preferably, the present invention also provides a computer-readable medium, wherein a computer program is stored in the storage medium, and the computer program is loaded by a processor and executes the smart sports data analysis method based on the Internet of Things as described in any one of the above.

[0022] The beneficial effect of the present invention is to collect the real-time status data of athletes through smart bracelets, and map the sports posture in combination with electronic video recording equipment, so as to effectively obtain the details and dynamics of athletes' movements. This step can realize accurate sports monitoring, and form a comprehensive sports data model in combination with the physical fitness, movement and physiological data of athletes. This provides rich original data support for subsequent evaluation and feedback, ensures accurate monitoring of sports performance, and lays the foundation for athletes' personalized training programs. By evaluating the instantaneous explosive power of sports posture data, the changes in the explosive power of athletes in training or competition can be captured in real time, and the instantaneous sports ability of athletes can be fed back in time. In addition, based on these data, abnormal load limit coupling processing is carried out to help discover the overload phenomenon or uneven load that occurs when athletes perform high-intensity exercise. This step can help trainers identify the potential physical bottlenecks and the risk of excessive load of athletes, adjust the training intensity and content in time, and avoid athletes from being injured by excessive load. Evaluating the sports risk level through abnormal load limit data is an important link to ensure the safety of athletes. This step can identify the risk level of athletes in specific sports states, help trainers adjust the training plan in time, and avoid injuries caused by excessive exercise or unreasonable training. The assessment of sports risk levels is not only crucial to the health of athletes, but also serves as an early warning in preventing sports injuries. The intelligent sports feedback strategy developed based on this assessment result will further optimize the training process and improve the safety and effectiveness of athletes' training. By sending the intelligent sports feedback strategy to the smart bracelet and performing sports data analysis, athletes can get real-time training feedback and understand their sports status and progress. This link can not only effectively guide athletes to adjust their movements and intensity in time, but also enhance athletes' self-awareness of the sports process. As a real-time feedback tool, the bracelet enables athletes to respond quickly to intelligent strategies, thereby achieving the purpose of improving sports efficiency, optimizing training results, and reducing sports injuries. Through continuous intelligent analysis and feedback, athletes' performance can be precisely controlled and improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of a smart sports data analysis method based on the Internet of Things; Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0024] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figure 1 to Figure 2 , a smart sports data analysis method based on the Internet of Things, the method comprising the following steps: Step S1: obtaining the real-time state data of the athlete's sports through the smart bracelet worn by the athlete; mapping the sports posture data based on the real-time state data of the athlete's sports based on the electronic video recording device to obtain the sports posture mapping data; Step S2: performing instantaneous explosive force evaluation on the motion posture mapping data to obtain posture-enhanced instantaneous explosive force data; performing abnormal load limit coupling processing based on the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data; Step S3: evaluating the sports risk level according to the abnormal load limit data to obtain sports risk level data; formulating an intelligent sports feedback strategy based on the sports risk level data to obtain an intelligent sports feedback strategy; Step S4: Send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

[0029] In the embodiment of the present invention, reference Figure 1FIG. 1 is a schematic diagram of a step flow of a smart sports data analysis method based on the Internet of Things of the present invention. In this example, the smart sports data analysis method based on the Internet of Things includes the following steps: Step S1: obtaining the real-time state data of the athlete's sports through the smart bracelet worn by the athlete; mapping the sports posture data based on the real-time state data of the athlete's sports based on the electronic video recording device to obtain the sports posture mapping data; In an embodiment of the present invention, the real-time state data of the athlete's sports is obtained through the smart bracelet worn by the athlete, and the sports state data of the athlete is mapped to the sports posture based on the electronic video recording device. In the implementation process of this step, first, the smart bracelet obtains the real-time state data of the athlete through the built-in sensor (such as an accelerometer, a gyroscope, a heart rate sensor, etc.). These data mainly include information such as the athlete's sports intensity, cadence, heart rate, type of exercise, and duration of activity. Through wireless communication protocols (such as Bluetooth, Wi-Fi), these data are transmitted to the processing module in real time. Secondly, based on the real-time state data of the athlete, the electronic video recording device (such as a high-definition camera or a dedicated sports monitoring camera) starts to record the athlete's motion trajectory and posture changes. The electronic video recording device collects video images and performs synchronous analysis in combination with the athlete's real-time data. The video data will be calibrated at the frame level through the athlete's motion state information to determine the athlete's body posture at different stages. For example, through an image processing algorithm, the athlete's marker points or skeletal joint points in the video are used to extract the athlete's body angle, joint motion trajectory and other posture features. Then, posture mapping is performed in combination with the athlete's motion intensity and timing data to generate motion posture mapping data. In this process, image processing algorithms such as background modeling, image difference method, motion estimation algorithm, etc. are used to ensure the accuracy and real-time performance of posture mapping. Posture mapping combined with time series data can effectively associate the athlete's movement state with his movement posture, providing accurate input data for subsequent explosive power evaluation.

[0030] Step S2: performing instantaneous explosive force evaluation on the motion posture mapping data to obtain posture-enhanced instantaneous explosive force data; performing abnormal load limit coupling processing based on the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data; In an embodiment of the present invention, the instantaneous explosive force evaluation is performed on the motion posture mapping data, and abnormal load limit coupling processing is performed based on the data. First, after the posture mapping data is generated, the data is analyzed to extract the evaluation index of the athlete's instantaneous explosive force. The instantaneous explosive force is a key indicator to measure the maximum force output generated by the athlete in a short period of time, and is often used to analyze the explosive sports ability of the athlete. In the evaluation process, a mechanical model based on acceleration and motion trajectory is used to combine the motion angle of the athlete's joints and the force transmission path to calculate the instantaneous explosive force of the athlete at each moment. The explosive force evaluation is calculated by a dynamic formula, and a mechanical model is used to estimate the force applied by the athlete at a certain moment. At the same time, combined with the data such as the athlete's joint angle and acceleration change, the posture enhanced instantaneous explosive force data is further obtained through forward dynamic analysis. This process involves a comprehensive analysis of kinematics and dynamics, which can accurately reflect the instantaneous force output of the athlete in a specific motion state. Next, abnormal load limit coupling processing is performed based on the obtained posture enhanced instantaneous explosive force data. This processing is to identify the extreme load level reached by the athlete in the movement through the combination of mechanical analysis, load analysis and limit state theory. The coupling process of abnormal load limit determines the maximum load that the athlete can bear in the current state of motion by calculating the athlete's motion state, load changes and physiological limits. Once the load exceeds the safety threshold, the system can issue an early warning.

[0031] Step S3: evaluating the sports risk level according to the abnormal load limit data to obtain sports risk level data; formulating an intelligent sports feedback strategy based on the sports risk level data to obtain an intelligent sports feedback strategy; In an embodiment of the present invention, the sports risk level is evaluated by evaluating the abnormal load limit data, and the intelligent sports feedback strategy is formulated based on the sports risk level data. In this step, the abnormal load limit data is first normalized. Normalization is to convert the data into a standard range (for example, between 0 and 1) to eliminate the influence caused by the difference in data magnitude. Through normalization, the abnormal load data can be compared and analyzed under a unified scale. Based on the normalized abnormal load data, the sports risk level is evaluated. This evaluation is based on the athlete's sports state, current load and pre-set risk standards. Sports risk level evaluation usually adopts a classification standard, such as low risk, medium risk and high risk levels, and determines the athlete's sports risk by setting different load thresholds. For example, when the athlete's load value exceeds a certain critical value, its risk level is marked as high risk, and the system will trigger a related early warning mechanism. According to the sports risk level data, the intelligent sports feedback strategy is formulated next. This strategy provides personalized training suggestions for athletes by combining the athlete's sports goals, real-time status and sports risk level. Specific strategies include adjusting exercise intensity, modifying exercise methods or suggesting recovery periods. For example, when the system recognizes that an athlete's load is close to the limit, it will recommend slowing down the intensity of exercise or taking some kind of recovery training to avoid excessive fatigue or sports injuries. This feedback strategy relies on the individual characteristics of the athlete and real-time sports risk assessment to ensure that the athlete can exercise within a safe load range.

[0032] Step S4: Send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

[0033] In an embodiment of the present invention, the intelligent sports feedback strategy is sent to the smart bracelet to perform sports data analysis. In this step, first, the intelligent sports feedback strategy is transmitted from the sports feedback module to the smart bracelet worn by the athlete through wireless communication technology (such as Bluetooth, Wi-Fi). After receiving the feedback strategy, the smart bracelet immediately starts its built-in processing unit to adjust the athlete's training plan according to the exercise intensity, exercise mode and recovery suggestions set in the feedback strategy. In addition, the smart bracelet will also adjust the exercise intensity according to the real-time monitored physiological data (such as heart rate, acceleration, gait, etc.), and work in coordination with the motion analysis algorithm in the system. The data acquisition module in the bracelet is combined with the real-time feedback system to dynamically adjust the exercise strategy during exercise. For example, during exercise, the bracelet can automatically adjust the training intensity or issue reminders according to changes in heart rate or exercise posture to help athletes better achieve their training goals. The smart bracelet can also compare and analyze the athlete's feedback strategy with the data during exercise to ensure the implementation effect of the feedback strategy and further optimize subsequent training and sports feedback adjustments.

[0034] Preferably, step S1 comprises the following steps: Step S11: obtaining the athlete's real-time sports status data through the smart bracelet worn by the athlete; Step S12: Cleaning the real-time sports status data of the athletes to obtain cleaned real-time sports status data; Step S13: performing time-series segmentation on the sports real-time state cleaning data to obtain sports real-time state segmentation data; Step S14: Based on the electronic video recording device, the motion posture data is mapped according to the real-time motion state segmentation data to obtain the motion posture mapping data.

[0035] In an embodiment of the present invention, the real-time state data of the athlete's sports is obtained through the smart bracelet worn by the athlete. The smart bracelet has built-in multiple sensors (such as accelerometers, gyroscopes, heart rate sensors, GPS modules, etc.), which can monitor in real time the various physiological and sports data generated by athletes during exercise. Specifically, the accelerometer is used to detect the acceleration changes of the athlete, the gyroscope is used to record the changes in the athlete's posture, the heart rate sensor measures the athlete's heart rate fluctuations in real time, and the GPS module can provide location information for further analysis of the athlete's movement trajectory. During the implementation process, the smart bracelet continuously transmits these data to the data receiving module for processing through wireless communication protocols (such as Bluetooth, Wi-Fi, etc.). At this time, the collected data includes information such as the athlete's exercise intensity (for example, step frequency, acceleration), exercise type (such as running, cycling, swimming, etc.), heart rate and exercise duration. These data provide detailed status of the athlete at a specific time point, providing basic data for subsequent sports analysis and evaluation. It involves data cleaning of the athlete's real-time state data of sports to obtain real-time cleaned data of sports. The purpose of data cleaning is to remove noise from the original data, correct outliers, and fill in missing data to ensure the accuracy of subsequent analysis. Specifically, first, the data collected by the sensor needs to be preliminarily screened to remove abnormal data caused by sudden movements of athletes or equipment failures. For example, if the heart rate data increases or decreases suddenly, it is caused by poor sensor contact or equipment failure. These unreasonable heart rate fluctuation data need to be excluded. After removing the outliers, data smoothing is then performed, and the data is smoothed using the sliding average method to make the data more continuous and stable. The size of the sliding window is adjusted according to the type and intensity of the athlete's exercise. Common window sizes are 5 seconds, 10 seconds, etc. In the process of data cleaning, if some sensor data have missing values, interpolation methods (such as linear interpolation, spline interpolation, etc.) can be used to fill the missing parts to ensure the integrity of the data. Finally, through this series of data cleaning operations, the real-time state cleaning data of sports is obtained, which provides high-quality input for subsequent time series segmentation and posture mapping. The real-time state cleaning data of sports is segmented in time series to obtain real-time state segmentation data of sports. The purpose of time series segmentation is to divide the continuous data in the exercise process into multiple stages, so that the data of each stage can correspond to a specific exercise state or action mode, which is convenient for subsequent analysis. First, the division criteria need to be determined. The criteria for time segmentation can be set according to the athlete's movement mode (such as running, jumping, acceleration, deceleration, etc.). For example, during running, the athlete's pace frequency, acceleration changes, and heart rate fluctuations have obvious periodicity, so the time segments can be divided according to the periodic changes in acceleration or heart rate. Each time segment represents a specific movement state of the athlete over a period of time (such as steady-state running, starting, emergency stop, etc.).The specific method of dividing the time segment can be to set a threshold or use an algorithm to automatically detect state transitions. For example, by performing fluctuation analysis on the acceleration data, the time points with large acceleration changes can be identified, and these time points can be used as the boundaries of the segments. The length of each segment can be adjusted according to the intensity of exercise, the type of exercise and the individual differences of the athletes. Usually, the length of a time segment is between 1 second and 10 seconds. After the division is completed, the obtained real-time state segmented data of the movement can include the start time, end time, athlete's heart rate, step frequency, acceleration and other indicators of each time segment. These segmented data provide structured data input for subsequent posture mapping and explosive power evaluation. Based on the electronic video recording device, the movement posture data is mapped according to the real-time state segmented data of the movement to obtain the movement posture mapping data. In this step, it is first necessary to ensure that the electronic video recording device (such as a high-definition camera) has been synchronized with the athlete's movement process. Through video analysis technology, the athlete's body posture can be extracted and analyzed. The real-time state segmented data of the movement will be used as input to guide the electronic video recording device to identify and mark the athlete's movement posture in each time segment. Key points in video frames (e.g., human joints, limb positions, etc.) are detected and calibrated using computer vision technology. Common methods include using skeleton extraction algorithms (such as OpenPose or AlphaPose) for human posture estimation, which can extract the positions of each joint of an athlete from a video frame and then analyze the athlete's posture and movement. Posture data mapping combines the posture information obtained from video analysis with the real-time state segmentation data of the movement to form mapping data. For example, within a certain time segment, video analysis will detect the change in the athlete's knee joint angle. Combined with the acceleration data of the time segment, the athlete's action type (such as take-off, squatting, etc.) can be further inferred. In addition, posture data mapping also involves analyzing the periodic changes in the athlete's movements in order to more accurately understand the athlete's movement patterns. Ultimately, the generated sports posture mapping data will contain the relationship between the athlete's posture characteristics (such as joint angles, limb positions, etc.) and the sports intensity data for each time segment, which will serve as the basic data for subsequent explosive power evaluation and risk analysis.

[0036] Preferably, step S2 comprises the following steps: Step S21: performing posture amplitude enhancement analysis on the motion posture mapping data to obtain motion posture amplitude enhancement data; Step S22: performing instantaneous explosive force evaluation on the movement posture amplitude enhancement data to obtain posture enhancement instantaneous explosive force data; Step S23: analyzing the instantaneous heart rate fluctuation of the athlete's sports real-time state data according to the posture-enhanced instantaneous explosive power data to obtain posture-associated instantaneous heart rate fluctuation data; Step S24: performing abnormal load limit coupling processing based on the posture-associated instantaneous heart rate fluctuation data and the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data.

[0037] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing posture amplitude enhancement analysis on the motion posture mapping data to obtain motion posture amplitude enhancement data; In the embodiment of the present invention, the motion posture mapping data is subjected to posture amplitude enhancement analysis to obtain motion posture amplitude enhancement data. The purpose of this step is to enhance the amplitude of the sports posture data of the athlete to identify and strengthen the key motion features in the posture change, and further extract more representative data. In the implementation process, it is first necessary to calculate the posture amplitude in each time segment according to the joint position and angle change extracted from the sports posture mapping data of the athlete. The posture amplitude reflects the motion amplitude of the athlete's limbs in a specific time period, and is usually determined by calculating the displacement and angle change of key points (such as knee joints, hip joints, shoulder joints, etc.) in space. In order to enhance the amplitude, data amplification technology can be used, such as applying weighted coefficients to the relatively weak motion amplitude during the motion process to increase its contribution to the overall motion posture. Then, for the posture data in each time segment, a differential method (such as finite difference) is used to calculate the rate of change of the athlete's joint angle, and then the instantaneous rate of motion amplitude change is obtained. This rate of change can not only reflect the athlete's movement speed, but also help identify the intensity of the movement in certain key motion stages. Through enhanced analysis of posture amplitude, the movement amplitude of each time segment is further amplified to obtain enhanced movement posture amplitude data, which will provide key input for subsequent explosive power evaluation and heart rate fluctuation analysis.

[0038] Step S22: performing instantaneous explosive force evaluation on the movement posture amplitude enhancement data to obtain posture enhancement instantaneous explosive force data; In an embodiment of the present invention, it is related to perform instantaneous explosive force evaluation on the sports posture amplitude enhancement data to obtain posture enhancement instantaneous explosive force data. This step is intended to evaluate the explosive force of athletes during exercise, especially the force and instantaneous explosive force generated by athletes when the posture amplitude changes significantly. First, when processing the posture amplitude enhancement data, the kinetic energy and acceleration formula in physics are used to estimate the instantaneous explosive force. The core of the explosive force evaluation is to deduce the instantaneous explosive force by calculating the acceleration change in each time segment of the athlete. The specific method is to combine the acceleration data with the athlete's weight and the athlete's limb length (which can be obtained from the posture data), and use the classic dynamic formula to deduce the instantaneous explosive force. By integrating the acceleration data, the explosive force of the athlete at each moment can be obtained. The change value of this instantaneous explosive force reflects the intensity of the athlete's exercise under different sports postures. Once the instantaneous explosive force of each time segment is calculated, the data points with large changes in explosive force can be further screened out in combination with the posture amplitude enhancement data to obtain the posture enhancement instantaneous explosive force data. These data can fully reflect the explosive force characteristics of athletes in specific postures and provide a basis for subsequent sports risk assessment.

[0039] Step S23: analyzing the instantaneous heart rate fluctuation of the athlete's sports real-time state data according to the posture-enhanced instantaneous explosive power data to obtain posture-associated instantaneous heart rate fluctuation data; In an embodiment of the present invention, the instantaneous heart rate fluctuation analysis is performed on the real-time state data of the athlete's sports according to the posture-enhanced instantaneous explosive power data to obtain the posture-associated instantaneous heart rate fluctuation data. The goal of this step is to combine the athlete's heart rate fluctuation with the change in the explosive power of the sports, analyze the relationship between the two, and provide more dimensional data support for evaluating the athlete's physical state. In the implementation process, it is first necessary to align the posture-enhanced instantaneous explosive power data with the athlete's heart rate data in time series. The heart rate data is collected in real time by the smart bracelet, reflecting the athlete's physiological response during exercise. Then, a filtering algorithm (such as Kalman filtering or low-pass filtering) is used to smooth the heart rate data to remove high-frequency fluctuations caused by noise. Then, a correlation analysis method (such as the Pearson correlation coefficient) is used to calculate the correlation between the posture-enhanced instantaneous explosive power data and the instantaneous heart rate data. If there is a strong positive correlation between the dramatic change in the posture-enhanced instantaneous explosive power and the heart rate fluctuation, it indicates that the athlete's heart rate fluctuates significantly when performing high-intensity actions. In this way, the posture-associated instantaneous heart rate fluctuation data can be obtained, further revealing the physiological response characteristics of athletes at different exercise intensities. In addition, the sliding window method can be used to calculate the dynamic relationship between posture-enhanced explosive power and heart rate fluctuations in each time segment. This analysis can not only reveal the characteristics of instantaneous heart rate fluctuations, but also provide physiological data support for the formulation of intelligent sports feedback strategies.

[0040] Step S24: performing abnormal load limit coupling processing based on the posture-associated instantaneous heart rate fluctuation data and the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data.

[0041] In an embodiment of the present invention, abnormal load limit coupling processing is performed based on the posture-associated instantaneous heart rate fluctuation data and the posture-enhanced instantaneous explosive power data to obtain abnormal load limit data. The goal of this step is to identify the load limit of the athlete during exercise by comprehensively analyzing the posture-enhanced instantaneous explosive power and heart rate fluctuation, and to perform abnormal load identification. In the implementation process, it is first necessary to establish a load limit model, which takes into account the relationship between the athlete's heart rate fluctuation and explosive power. The definition of load limit is based on physiological theory, which usually refers to the athlete's body load approaching the limit when the heart rate exceeds a certain threshold and is accompanied by a dramatic change in posture when performing high-intensity exercise, thereby bringing potential sports risks. By setting multiple thresholds and defining the critical point of heart rate and explosive power changes, the athlete's exercise load can be evaluated. Then, by inputting the posture-enhanced instantaneous explosive power data and the posture-associated instantaneous heart rate fluctuation data into the load limit model, the algorithm is used for coupling processing. The coupling process uses weighted average method, fuzzy logic and other methods to calculate the comprehensive evaluation of the athlete's current exercise load according to the weights of different data. If the model detects that the athlete's load exceeds the set limit value, it is marked as an abnormal load state and abnormal load limit data is generated. These data will provide data support for subsequent sports risk assessments and help avoid the risk of excessive load on athletes during high-intensity exercise.

[0042] Preferably, step S24 includes the following steps: Step S241: Perform momentum rapid change analysis on the posture enhancement instantaneous explosive force data to obtain instantaneous momentum rapid change data; Step S242: Calculate the motion state conversion time difference for the instantaneous momentum rapid change data to obtain the motion state conversion time difference; Step S243: performing muscle damage stress limit simulation according to the motion state conversion time difference and instantaneous momentum rapid change data to obtain muscle damage stress limit data; Step S244: performing nonlinear jump instability analysis based on the posture-associated instantaneous heart rate fluctuation data to obtain nonlinear jump instability data; Step S245: performing abnormal load limit coupling processing based on the nonlinear jump instability data and the muscle injury stress limit data to obtain abnormal load limit data.

[0043] In an embodiment of the present invention, the posture-enhanced instantaneous explosive power data is subjected to a momentum rapid change analysis to obtain instantaneous momentum rapid change data. The purpose of this step is to analyze the speed and amplitude of the change of explosive power when the athlete performs high-intensity movements, so as to understand the severity of his or her motion state. In the implementation process, it is first necessary to calculate the instantaneous momentum of the athlete at different time points based on the posture-enhanced instantaneous explosive power data. By combining the mass of the athlete and the acceleration information in the posture-enhanced instantaneous explosive power data, the instantaneous momentum in each time segment is obtained. Then, by calculating the rate of change of momentum between adjacent time segments (for example, using the differential method to calculate the rate of change of speed), the instantaneous momentum rapid change data is obtained. This data reflects the degree of fluctuation of the momentum of the athlete when performing high-intensity movements, and is an important indicator for evaluating whether the athlete is in an extreme motion state. In this process, it is also necessary to pay attention to combining the rate of change of momentum with factors such as the athlete's body shape and weight for standardization to eliminate the influence of individual differences. Through these operations, the severity of the change of the explosive power of the athlete during exercise can be fully evaluated, providing a basis for subsequent muscle injury assessment. The time difference of motion state conversion is calculated for the instantaneous momentum rapid change data to obtain the motion state conversion time difference. This step aims to identify the time interval of the athlete's conversion from one motion state to another during intense exercise, so as to further evaluate the athlete's exercise intensity and its impact on the body load. In the implementation process, the standard of motion state conversion needs to be defined first. This standard can be determined based on the mutation point of the athlete's instantaneous momentum rapid change data. For example, when the momentum change rate exceeds the set threshold, it indicates that the athlete's motion state has changed dramatically, usually corresponding to the athlete's conversion from one motion mode (such as running) to another mode (such as jumping or changing direction). By performing mutation point detection on the instantaneous momentum rapid change data (such as using a gradient change algorithm or a threshold-based jump detection method), the moment of each motion state conversion can be identified. Once the state conversion point is identified, the conversion time difference from one state to another is calculated next. The calculation method of this time difference is determined by measuring the time interval between two adjacent points before and after the state conversion. These time difference data can be used to reflect the frequency of changes in the athlete's motion mode and help analyze the athlete's athletic ability and adaptation to high-intensity exercise. The combination of instantaneous momentum rapid change data and conversion time difference provides key time information for subsequent muscle injury stress assessment. Muscle injury stress limit simulation is performed based on the motion state conversion time difference and instantaneous momentum rapid change data to obtain muscle injury stress limit data. This step aims to evaluate the muscle injury risk that athletes suffer during exercise by analyzing the time difference of motion state conversion and the speed of momentum change. The muscle injury theoretical model (such as tensile or compressive stress model) is used to simulate the load of muscles in high-intensity exercise.The variables that need to be input into the model include the rapid change data of instantaneous momentum and the time difference of motion state conversion. Based on the change of the athlete's momentum, the stress of the athlete's muscles at different moments can be calculated. The stress-strain relationship formula (such as Hooke's law) is usually used to estimate the stress of the muscle. The stress value refers to the magnitude of the force that the muscle bears in a short period of time. These forces can cause microscopic damage or tearing of muscle tissue. Secondly, by combining the time difference of motion state conversion, the change of muscle stress during the conversion of different motion modes is judged. If the conversion time difference is short and the change of instantaneous momentum is large, the muscle load is high, the stress will increase rapidly, and the risk of injury will increase. Conversely, a longer conversion time difference means that the athlete gradually transitions to a new motion mode, the muscle stress fluctuation is small, and the risk of injury is low. Through the simulation processing of these data, the muscle injury stress limit data can be obtained, which provides key input for the subsequent abnormal load limit coupling analysis. Nonlinear jump instability analysis is performed based on the posture-related instantaneous heart rate fluctuation data to obtain nonlinear jump instability data. The goal of this step is to analyze the nonlinear characteristics of heart rate fluctuations during high-intensity exercise, identify the jump characteristics of heart rate fluctuations, and further evaluate the athlete's physiological instability. In the implementation process, the posture-associated instantaneous heart rate fluctuation data needs to be denoised first. By using methods such as wavelet transform or empirical mode decomposition, the noise caused by measurement equipment errors or external interference is removed. The processed heart rate fluctuation data can more accurately reflect the athlete's physiological state during exercise. Next, nonlinear dynamic analysis methods (such as Lyapunov exponent or bifurcation analysis) are used to study the instability of heart rate fluctuations. By calculating the Lyapunov exponent of heart rate fluctuations, the nonlinear jump characteristics of heart rate can be evaluated. When the Lyapunov exponent is large, it indicates that the heart rate fluctuation has a strong nonlinear jump and the athlete is in a state of physiological instability. The nonlinear jump instability data provides a basis for identifying the athlete's physiological risks such as exercise overload and fatigue. In addition, the jump instability analysis can also be combined with the heart rate mutation point for analysis to determine the athlete's physiological stability during high-intensity exercise. These data can provide important information at the physiological response level for subsequent abnormal load assessment. Based on the nonlinear jump instability data and muscle injury stress limit data, abnormal load limit coupling processing is performed to obtain abnormal load limit data. The goal of this step is to conduct a comprehensive analysis by combining the nonlinear jump instability data and muscle injury stress limit data to identify whether the athlete is at risk of overload or overload. First, the nonlinear jump instability data and muscle injury stress limit data are standardized to eliminate the dimensional differences between different data dimensions. Then, the two sets of data are coupled using a weighted comprehensive analysis method (such as weighted average method or fuzzy logic method). By setting their respective weight values, the athlete's comprehensive load limit state assessment is obtained.If both the nonlinear jump instability data and the muscle injury stress limit data show abnormal fluctuations, it indicates that the athlete is in an abnormal load state. Finally, by setting a predetermined load threshold, it is determined whether the athlete has exceeded the safe load limit. If the coupled data exceeds the threshold, abnormal load limit data is generated and the athlete is marked as a high-risk state. These data provide an important reference for subsequent athlete health management and training adjustments.

[0044] Preferably, step S245 includes the following steps: Calculate the injury yield point of the muscle injury stress limit data to obtain the muscle injury yield point data; According to the muscle injury yield point data, the plastic deformation stress relationship analysis is performed on the muscle injury stress limit data to obtain the plastic deformation stress relationship data; Based on the plastic deformation stress relationship data and muscle injury yield point data, risk trend identification is performed to obtain muscle injury risk trend data; The nonlinear jump instability data is numerically simulated to obtain the jump instability value; Abnormal load limit coupling processing is performed according to the jump instability value and muscle injury risk trend data to obtain abnormal load limit data.

[0045] In an embodiment of the present invention, the muscle injury stress limit data is analyzed to calculate the muscle injury yield point in each time period. The muscle injury yield point is defined as the point at which microscopic cracks or strains begin to occur in the muscle tissue, that is, the critical value at which the muscle is subjected to excessive force, resulting in irreversible damage. In a specific implementation, the calculation of the muscle injury yield point is based on the yield criterion in material mechanics. For example, a stress-strain curve is used to fit the performance of the muscle under different load conditions. By fitting the muscle injury stress limit data, the plastic deformation characteristics of the muscle tissue when the stress reaches the limit value are identified, and the yield point of the injury is determined on this basis. Commonly used yield criteria include the maximum shear stress criterion and the von Mises stress criterion. Specifically, when the stress exceeds the yield limit of the muscle, irreversible damage will occur to the muscle tissue. The calculation of the yield point provides basic data for the subsequent analysis of the plastic deformation stress relationship. Based on the obtained muscle injury yield point data, a plastic deformation stress relationship analysis is performed. The goal of this analysis is to reveal the relationship between the stress and deformation that the muscle is subjected to when plastic deformation occurs after yielding, and to evaluate further damage to the muscle during the deformation process. In this step, the plastic mechanics model in material mechanics is used, especially the nonlinear analysis of stress-strain relationship to simulate the deformation process of muscle after yielding. Usually, plastic stress analysis is based on numerical calculation methods such as Newton-Raphson method or finite element method, combined with the load characteristics of different types of sports, to evaluate whether the muscle stress reaches irreversible damage during the deformation process. Through comprehensive analysis of stress and strain data, plastic deformation stress relationship data can be calculated, which is specifically manifested as the stress distribution of muscle after yield point under different exercise intensities. This data reflects the recovery ability of muscle under high load conditions and the degree of damage accumulation. Based on the obtained plastic deformation stress relationship data and muscle injury yield point data, risk trend identification is performed to obtain muscle injury risk trend data. The goal of this process is to identify the trend and time node of muscle injury. In this process, by analyzing the relationship between plastic deformation stress and injury yield point, combined with the athlete's exercise load and physiological characteristics, a risk trend model can be constructed. The risk trend identification method adopts a threshold-based cumulative risk assessment algorithm. For example, when the ratio of the plastic deformation stress value and the yield point of an athlete in a specific time period exceeds the set threshold, it indicates that the risk of muscle injury begins to increase. Through multi-stage analysis of risk data, it is determined whether the risk of muscle injury is in a gradually increasing trend. The final result of this step is to obtain a risk trend data of muscle injury, which represents the cumulative probability of muscle injury, and predicts the probability of injury in a certain period of time in the future based on factors such as the athlete's training intensity and recovery status. Based on the nonlinear jump instability data, the instability numerical simulation is performed to obtain the jump instability value.The purpose of this simulation is to evaluate the physiological instability of athletes in high-intensity exercise, that is, whether the athlete's motion control system will become unstable when facing excessive load, resulting in uncontrollable movement. The numerical simulation of instability is based on nonlinear dynamics methods. Nonlinear jump instability data usually involves the feedback mechanism of the athlete's physiological system, which is highly complex and nonlinear. In the simulation process, common numerical analysis techniques such as finite difference method or computational fluid dynamics simulation are used to input the instability data into the simulation system to calculate the response behavior of the system under load changes. For example, dynamic equations can be used to simulate the interaction between the athlete's muscle groups and movement patterns. By simulating the system response under different load conditions, the instability point and its time evolution can be identified. Through the simulation results, the jump instability value can be obtained to reflect the athlete's physiological stability under high-intensity exercise and whether it enters an unstable state. Based on the obtained muscle injury risk trend data and the obtained jump instability value, abnormal load limit coupling processing is performed to obtain abnormal load limit data. The goal of this step is to combine physiological injury risk and instability data to evaluate whether the athlete is subjected to a load exceeding the safety threshold. First, the muscle injury risk trend data and the jump instability value are input into a coupled analysis framework. This framework uses a weighted fusion method to integrate the two sets of data, and combines factors such as the athlete's exercise type, intensity and duration to calculate the maximum load that the athlete can bear in the current state. If the risk trend data and the instability value simultaneously indicate that the athlete exceeds the safe load threshold, abnormal load limit data is generated to prompt the athlete to enter the overload risk zone. The generation of abnormal load limit data is based on the load threshold and risk assessment algorithm, and is usually defined based on physiological thresholds, such as maximum heart rate, maximum acceleration and other parameters. If this data exceeds the set threshold, it means that the athlete's load has approached or exceeded its safe tolerance and needs to be adjusted or stopped. Through these operations, abnormal load limit data is finally obtained, providing important data support for athletes' training adjustments, health monitoring and other aspects.

[0046] Preferably, step S3 comprises the following steps: Step S31: normalizing the abnormal load limit data to obtain abnormal load limit normalized data; Step S32: evaluating the sports risk level of the athlete's real-time sports state data according to the abnormal load limit normalization data to obtain sports risk level data; Step S33: Formulate an intelligent motion feedback strategy based on the motion risk level data and the abnormal load limit normalization data to obtain an intelligent motion feedback strategy.

[0047] In an embodiment of the present invention, the abnormal load limit data is normalized to obtain abnormal load limit normalized data. The purpose of normalization is to standardize load data from different sources and different scales to facilitate subsequent analysis and processing. First, the abnormal load limit data is preprocessed to ensure the quality of the data. For example, outliers, missing values ​​and noise in the data are removed, which are caused by factors such as improper wearing of athletes' equipment and sensor errors. Statistical methods such as mean filling method or median filling method are used to repair missing values; at the same time, moving average method or local weighted regression method can be used to smooth abnormal fluctuation values. After completing data cleaning, a normalization algorithm is used for standardization. Common normalization methods include minimum-maximum normalization and Z-score normalization. Through this method, the values ​​of all abnormal load limit data are standardized to the interval [0,1]. In this way, the subsequent sports risk level assessment will not be affected by the size of the original data range, which is convenient for unified processing and comparison of data. Finally, the abnormal load limit normalized data is obtained, which provides standardized load information for subsequent steps to ensure the consistency and stability of the data. According to the normalized data of abnormal load limit, the real-time state data of the sports of the athlete is evaluated for the sports risk level, and the sports risk level data is obtained. The purpose of this evaluation is to evaluate the risk level encountered during the sports process according to the real-time state data and load bearing capacity of the athlete. First, the real-time physiological data (such as heart rate, respiratory rate, body temperature, movement speed, etc.) of the athlete is combined with the normalized abnormal load limit data, and a weighted evaluation method is adopted to evaluate the current sports state of the athlete. Specifically, the physiological indicators such as the heart rate fluctuation, respiratory rate and physical exertion of the athlete, as a direct reflection of its sports load bearing capacity, are combined with the abnormal load limit data through a weighted coefficient. By real-time monitoring of the sports state data of the athlete, combined with the normalized load data, this comprehensive evaluation method can be used to make an accurate quantitative evaluation of the current sports risk of the athlete. For example, when the gap between the heart rate fluctuation of the athlete and the abnormal load limit is large, it indicates that the sports load it bears is close to the limit, and the sports risk level increases, indicating that there is a high risk of sports injury. Finally, the sports risk level data is obtained to provide a basis for the subsequent sports feedback strategy formulation. According to the sports risk level data and the abnormal load limit normalized data obtained in step S32, an intelligent sports feedback strategy is formulated. The purpose of this strategy is to adjust the athlete's training plan or exercise intensity in real time to avoid overtraining or potential sports injury risks. First, combined with the sports risk level data, different exercise load adjustment rules can be set. For example, when the sports risk level reaches 4 or 5, the athlete's training load should be automatically reduced or even suspended; when the sports risk level is 2 or 3, the training content and intensity can be adjusted to increase restorative exercise. According to the individual differences of athletes, a dynamic adjustment strategy is used, that is, the training intensity is adjusted in real time according to the actual performance of the athletes.When developing a feedback strategy, the focus is on monitoring key indicators during the athlete's exercise. For example, during exercise, parameters such as heart rate, cadence, and speed can be used as a basis for real-time feedback. If the athlete's heart rate exceeds the safe range, the athlete can be automatically reminded to slow down the intensity of the exercise, or prompted to take appropriate rest. These feedbacks can provide real-time reminders to athletes through wearable devices such as smart bracelets, or display corresponding feedback information through smartphone applications.

[0048] Preferably, step S33 includes the following steps: Step S331: constructing a motion load correlation matrix for the abnormal load limit normalized data to obtain a motion load correlation matrix; Step S332: performing exercise rhythm adaptability feedback on the exercise load correlation matrix and the exercise risk level data based on the fourth-order Runge-Kutta algorithm to obtain exercise rhythm adaptability feedback data; Step S333: performing differential dynamic programming on the motion rhythm adaptability feedback data to obtain motion rhythm differential dynamic data; Step S334: formulating an intelligent motion feedback strategy based on the motion rhythm differential dynamic data to obtain an intelligent motion feedback strategy.

[0049] In an embodiment of the present invention, a motion load association matrix is ​​constructed according to the abnormal load limit normalized data, and the matrix is ​​used to analyze the correlation between the motion load and various physiological parameters. First, various physiological data (such as heart rate, cadence, body temperature, motion speed, etc.) and abnormal load limit normalized data of athletes in different exercise stages (such as warm-up, load period, recovery period, etc.) are collected. These data need to cover the multi-dimensional performance of athletes during training. Based on these data, a motion load association matrix is ​​constructed using a covariance matrix or a Pearson correlation coefficient method. Specifically, a matrix is ​​set in which each element represents the correlation between different physiological parameters and abnormal load limit data. For example, an element in the matrix can represent "the correlation between the athlete's heart rate fluctuation and the motion load". The fourth-order Runge-Kutta algorithm is used to perform adaptive feedback on the motion rhythm of the motion load association matrix and the motion risk level data. The fourth-order Runge-Kutta algorithm is a commonly used numerical solution that can accurately solve ordinary differential equations and adjust the athlete's motion rhythm. First, the athlete's motion state is associated with the sports risk level data through the sports load correlation matrix, and the fourth-order Runge-Kutta algorithm is combined to simulate the sports rhythm adaptability of athletes under different risk levels. The ordinary differential equation is solved by the fourth-order Runge-Kutta algorithm to obtain the sports rhythm feedback data that adapts to the changes in the athlete's physiological state. This process uses known initial values ​​and boundary conditions (such as the athlete's starting rhythm and sports risk level) to obtain high-precision sports rhythm feedback through a four-step iterative process. The sports rhythm adaptability feedback data is processed by differential dynamic programming to obtain sports rhythm differential dynamic data. The core of this process is to analyze the change trend of sports rhythm in different time intervals through the dynamic programming method, and then optimize the adjustment strategy of sports rhythm. First, for the sports rhythm adaptability feedback data, a multi-stage dynamic programming model is set to calculate the optimal strategy for sports rhythm adjustment at each stage. The key to differential dynamic programming is to perform differential operations on the rhythm feedback at each moment to obtain the rhythm change trend of the athlete at each stage. By continuously calculating the rhythm differences at each moment, the dynamic changes of sports rhythm at each time node are obtained. Next, the dynamic programming method is used to combine the optimal rhythm change strategy of each stage to calculate the optimal rhythm change sequence in the entire exercise process. This process is recursive, combining the risk level data and rhythm feedback data of each stage to obtain the differential dynamic data of the movement rhythm, providing accurate rhythm change trends for the subsequent intelligent movement feedback strategy. Based on the differential dynamic data of the movement rhythm, an intelligent movement feedback strategy is formulated. This strategy dynamically adjusts the movement feedback strategy by comprehensively analyzing the trend of the athlete's rhythm change during training and the athlete's current risk level. First, the differential dynamic data of the movement rhythm is combined with the athlete's movement risk level data to set different feedback rules.For example, if the exercise rhythm changes greatly at a certain moment and the exercise risk level is high, the system will give feedback to reduce the exercise intensity; conversely, if the rhythm changes slightly and the risk level is low, the system can give feedback to accelerate the exercise rhythm. The formulation of intelligent exercise feedback strategies relies on processed rhythm differential dynamic data and real-time risk assessment data. Specifically, multiple thresholds are set to adjust the feedback strategy according to the athlete's state changes. For example: when the exercise rhythm changes greatly and the risk level is high, it is recommended to slow down the exercise rhythm and reduce the training intensity; when the exercise rhythm is stable and the risk level is low, it is encouraged to increase the exercise intensity and improve the training effect. Each exercise feedback strategy should adapt to the changes in the athlete's physiological state in real time, adjust the exercise rhythm in real time through sensor feedback, and provide voice or visual prompts to help athletes adjust their exercise methods to ensure training effectiveness and safety.

[0050] Preferably, step S332 includes the following steps: Based on the fourth-order Runge-Kutta algorithm, the fourth-order Runge-Kutta numerical solution of the motion load correlation matrix is ​​performed to obtain the dynamic evolution sequence of the motion load; According to the dynamic evolution sequence of sports load, load pattern clustering processing is performed on the sports risk level data to obtain load pattern clustering data; According to the load pattern clustering data, the dynamic load zero boundary point matching is performed on the motion load correlation matrix to obtain the dynamic load zero boundary data; According to the dynamic load zero-bound data, the motion risk level data is processed by fourth-order Runge-Kutta iteration to obtain the motion rhythm stability matrix; The exercise load characteristic matrix is ​​feedback-adjusted according to the exercise rhythm stability matrix to obtain exercise rhythm adaptability feedback data.

[0051] In the embodiment of the present invention, it is first necessary to perform a fourth-order Runge-Kutta numerical solution on the sports load association matrix. The purpose of this process is to simulate the dynamic changes of the sports load by numerical methods, and obtain the evolution sequence of the sports load, so as to facilitate further analysis of the relationship between the sports rhythm and the load. Through repeated iterative solutions, a dynamic sequence of the sports load evolution over time is obtained, which reflects the changes of the sports load at different time points and serves as the basic data for subsequent processing. Based on the dynamic evolution sequence of the sports load, load pattern clustering is performed. The purpose of load pattern clustering is to identify the change patterns of the sports load in different time periods, and classify the loads of athletes according to these patterns, so as to provide a basis for subsequent sports rhythm feedback. The dynamic evolution sequence of the sports load is standardized to ensure that the sports load data of different time periods have a unified scale. This process can use Z-score standardization or maximum and minimum normalization methods. The K-means clustering algorithm is used to cluster the sports load data. First, the number of clusters (cluster number) is determined, which can be selected by the elbow rule or the silhouette coefficient. According to the characteristics of the motion load, the clustering algorithm divides the motion load data into multiple clusters, each cluster represents a load pattern, including: randomly selecting k initial centroids, assigning each data point to the nearest centroid, updating the centroid of each cluster until the centroid no longer changes or reaches the maximum number of iterations. After clustering, different patterns of motion load data are obtained, each pattern represents a different motion load state, such as low load, high load, etc. Based on the load pattern clustering data, dynamic load zero boundary point matching is performed, the goal is to identify the key zero boundary points in the load change process, and help determine the key turning points of load change. Based on the load pattern clustering data, the time series of each cluster is analyzed to find the turning points of load change. A threshold-based method is used to set a critical value. If the exercise load exceeds this value, it is considered that the load has changed significantly. During the load change process, the zero crossing points of the exercise load from negative to positive or from positive to negative are determined. These zero boundary points reflect the critical state of the exercise load. According to the dynamic changes of different load modes, the dynamic time warping (DTW) algorithm is used to match the zero boundary points of the exercise load to ensure that the zero boundary points in different modes can be effectively associated, which is convenient for subsequent adjustments. Through this method, the dynamic load zero boundary data is obtained, which is convenient for further optimization of the exercise rhythm and load adjustment strategy. According to the dynamic load zero boundary data, the fourth-order Runge-Kutta iterative processing is performed to solve the stability of the exercise rhythm.This process is based on the aforementioned fourth-order Runge-Kutta numerical solution method. The dynamic load zero boundary point is further iterated to obtain the stability matrix of the movement rhythm. According to the dynamic load zero boundary data, a differential equation describing the change of movement rhythm over time is constructed to express how the load change affects the movement rhythm. The fourth-order Runge-Kutta iterative processing: The fourth-order Runge-Kutta method is used to solve the above equation to obtain the stability matrix of the movement rhythm over time. This matrix can reflect the adaptability and stability of the movement rhythm under different load conditions, and the movement rhythm stability matrix is ​​obtained: Through the iterative process, a movement rhythm stability matrix is ​​finally obtained, which is used to measure the stability and adaptability of the movement rhythm under different load conditions. According to the movement rhythm stability matrix, feedback adjustment of the movement load characteristic matrix is ​​performed. This step aims to optimize the movement rhythm adjustment strategy through the feedback mechanism to ensure that athletes can adjust their movement rhythm in real time to adapt to the current load state. According to the movement rhythm stability matrix, feedback rules are set. When the movement rhythm stability is high, the athlete is allowed to maintain the current movement rhythm; when the stability is low, the feedback prompts the athlete to reduce the load or adjust the rhythm. Adjustment is made by combining the movement rhythm stability matrix with the movement load characteristic matrix. By setting the threshold and adjusting the values ​​in the load matrix, athletes can maintain the best exercise rhythm under different load modes. Finally, through feedback adjustment, the adaptive feedback data of exercise rhythm is obtained to help athletes adjust the rhythm in real time according to the current exercise load status and optimize the training effect.

[0052] Preferably, the present invention also provides a smart sports data analysis system based on the Internet of Things, which is used to execute the smart sports data analysis method based on the Internet of Things as described above. The smart sports data analysis system based on the Internet of Things includes: The data acquisition module is used to obtain the real-time status data of the athlete's sports through the smart bracelet worn by the athlete; based on the electronic video recording device, the sports posture data is mapped according to the real-time status data of the athlete's sports to obtain the sports posture mapping data; The abnormal load analysis module is used to evaluate the instantaneous explosive force of the motion posture mapping data to obtain the posture-enhanced instantaneous explosive force data; perform abnormal load limit coupling processing based on the posture-enhanced instantaneous explosive force data to obtain the abnormal load limit data; A motion feedback module is used to evaluate the motion risk level according to the abnormal load limit data to obtain the motion risk level data; and to formulate an intelligent motion feedback strategy based on the motion risk level data to obtain the intelligent motion feedback strategy; The analysis and feedback module is used to send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

[0053] Preferably, the present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program is loaded by a processor and executes any one of the above-described smart sports data analysis methods based on the Internet of Things.

[0054] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0055] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A smart sports data analysis method based on the Internet of Things, characterized in that: The following steps are involved: Step S1: obtaining the real-time state data of the athlete's sports through the smart bracelet worn by the athlete; mapping the sports posture data based on the real-time state data of the athlete's sports based on the electronic video recording device to obtain the sports posture mapping data; Step S2: evaluating the instantaneous explosive force of the motion posture mapping data to obtain posture-enhanced instantaneous explosive force data; Based on the posture-enhanced instantaneous explosive force data, abnormal load limit coupling processing is performed to obtain abnormal load limit data; Step S3: evaluating the sports risk level according to the abnormal load limit data to obtain sports risk level data; Formulate intelligent sports feedback strategy based on sports risk level data to obtain intelligent sports feedback strategy; Step S4: Send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

2. The method for analyzing smart sports data based on the Internet of Things according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: obtaining the athlete's real-time sports status data through the smart bracelet worn by the athlete; Step S12: Cleaning the real-time sports status data of the athletes to obtain cleaned real-time sports status data; Step S13: performing time-series segmentation on the sports real-time state cleaning data to obtain sports real-time state segmentation data; Step S14: Based on the electronic video recording device, the motion posture data is mapped according to the real-time motion state segmentation data to obtain the motion posture mapping data.

3. The method for analyzing smart sports data based on the Internet of Things according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing posture amplitude enhancement analysis on the motion posture mapping data to obtain motion posture amplitude enhancement data; Step S22: performing instantaneous explosive force evaluation on the movement posture amplitude enhancement data to obtain posture enhancement instantaneous explosive force data; Step S23: analyzing the instantaneous heart rate fluctuation of the athlete's sports real-time state data according to the posture-enhanced instantaneous explosive power data to obtain posture-associated instantaneous heart rate fluctuation data; Step S24: performing abnormal load limit coupling processing based on the posture-associated instantaneous heart rate fluctuation data and the posture-enhanced instantaneous explosive force data to obtain abnormal load limit data.

4. The method for analyzing smart sports data based on the Internet of Things according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: Perform momentum rapid change analysis on the posture enhancement instantaneous explosive force data to obtain instantaneous momentum rapid change data; Step S242: Calculate the motion state conversion time difference for the instantaneous momentum rapid change data to obtain the motion state conversion time difference; Step S243: performing muscle damage stress limit simulation according to the motion state conversion time difference and instantaneous momentum rapid change data to obtain muscle damage stress limit data; Step S244: performing nonlinear jump instability analysis based on the posture-associated instantaneous heart rate fluctuation data to obtain nonlinear jump instability data; Step S245: performing abnormal load limit coupling processing based on the nonlinear jump instability data and the muscle injury stress limit data to obtain abnormal load limit data.

5. The method for analyzing smart sports data based on the Internet of Things according to claim 4 is characterized in that: Step S245 includes the following steps: Calculate the injury yield point of the muscle injury stress limit data to obtain the muscle injury yield point data; According to the muscle injury yield point data, the plastic deformation stress relationship analysis is performed on the muscle injury stress limit data to obtain the plastic deformation stress relationship data; Based on the plastic deformation stress relationship data and muscle injury yield point data, risk trend identification is performed to obtain muscle injury risk trend data; The nonlinear jump instability data is numerically simulated to obtain the jump instability value; Abnormal load limit coupling processing is performed according to the jump instability value and muscle injury risk trend data to obtain abnormal load limit data.

6. The method for analyzing smart sports data based on the Internet of Things according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: normalizing the abnormal load limit data to obtain abnormal load limit normalized data; Step S32: evaluating the sports risk level of the athlete's real-time sports state data according to the abnormal load limit normalization data to obtain sports risk level data; Step S33: Formulate an intelligent motion feedback strategy based on the motion risk level data and the abnormal load limit normalization data to obtain an intelligent motion feedback strategy.

7. The method for analyzing smart sports data based on the Internet of Things according to claim 6, characterized in that: Step S33 includes the following steps: Step S331: constructing a motion load correlation matrix for the abnormal load limit normalized data to obtain a motion load correlation matrix; Step S332: performing exercise rhythm adaptability feedback on the exercise load correlation matrix and the exercise risk level data based on the fourth-order Runge-Kutta algorithm to obtain exercise rhythm adaptability feedback data; Step S333: performing differential dynamic programming on the motion rhythm adaptability feedback data to obtain motion rhythm differential dynamic data; Step S334: formulating an intelligent motion feedback strategy based on the motion rhythm differential dynamic data to obtain an intelligent motion feedback strategy.

8. The method for analyzing smart sports data based on the Internet of Things according to claim 7, characterized in that: Step S332 includes the following steps: Based on the fourth-order Runge-Kutta algorithm, the fourth-order Runge-Kutta numerical solution of the motion load correlation matrix is ​​performed to obtain the dynamic evolution sequence of the motion load; According to the dynamic evolution sequence of sports load, load pattern clustering processing is performed on the sports risk level data to obtain load pattern clustering data; According to the load pattern clustering data, the dynamic load zero boundary point matching is performed on the motion load correlation matrix to obtain the dynamic load zero boundary data; According to the dynamic load zero-bound data, the motion risk level data is processed by fourth-order Runge-Kutta iteration to obtain the motion rhythm stability matrix; The exercise load characteristic matrix is ​​feedback-adjusted according to the exercise rhythm stability matrix to obtain exercise rhythm adaptability feedback data.

9. A smart sports data analysis system based on the Internet of Things, characterized in that: Used to execute the smart sports data analysis method based on the Internet of Things as claimed in claim 1, the smart sports data analysis system based on the Internet of Things includes: The data acquisition module is used to obtain the real-time status data of the athlete's sports through the smart bracelet worn by the athlete; based on the electronic video recording device, the sports posture data is mapped according to the real-time status data of the athlete's sports to obtain the sports posture mapping data; The abnormal load analysis module is used to evaluate the instantaneous explosive force of the motion posture mapping data to obtain the posture-enhanced instantaneous explosive force data; perform abnormal load limit coupling processing based on the posture-enhanced instantaneous explosive force data to obtain the abnormal load limit data; A motion feedback module is used to evaluate the motion risk level according to the abnormal load limit data to obtain the motion risk level data; and to formulate an intelligent motion feedback strategy based on the motion risk level data to obtain the intelligent motion feedback strategy; The analysis and feedback module is used to send the intelligent sports feedback strategy to the smart bracelet to perform sports data analysis.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is loaded by a processor and executes the smart sports data analysis method based on the Internet of Things as described in any one of claims 1-8.

Images