Intelligent analysis method and device for sports medicine data

Abstract

The invention relates to the technical field of sports medicine data analysis, and discloses a sports medicine data intelligent analysis method and device.The sports medicine data intelligent analysis method comprises the following steps that firstly, a unified time axis is set, and then physiological index data, sports performance data, sports injury data and rehabilitation process data of a single athlete are collected according to the time sequence; classifying to form a data set; 2, analyzing the skill level of a single athlete in an uninjured state, and generating a corresponding level coefficient; 3, the health level of a single athlete in the injury state is analyzed, a corresponding injury coefficient is generated, and multi-dimensional analysis is more comprehensive; 4, a horizontal threshold value and an injury threshold value of a fixed range and a monitoring period of a fixed duration are set, the health state and the injury risk of a single athlete are evaluated in combination with the horizontal coefficient and the injury coefficient, a corresponding early warning signal and a corresponding exercise suggestion are generated, any node in a time axis has the corresponding horizontal coefficient or injury coefficient, and the health state and the injury risk of the single athlete are evaluated. And the intelligent evaluation precision is high.

Description

Technical Field

[0001] The present invention relates to the technical field of sports medicine data analysis, and specifically to an intelligent analysis method and device for sports medicine data. Background Art

[0002] Sports medicine data refers to various information related to sports and health collected, recorded, and analyzed in sports medicine research and practice, which reflects the athlete's physical condition, sports performance, injury risk, and training effect from multiple dimensions. Scientifically collecting and intelligently analyzing sports medicine data can provide strong support for optimizing training plans, improving sports performance, and preventing injuries, helping athletes achieve the best competitive state and healthy physique. The types of sports medicine data include physiological index data, sports performance data, sports injury data, and rehabilitation process data. Physiological index data such as weight, height, body fat percentage, heart rate, blood pressure, blood sugar, blood lipid, etc. directly reflects the athlete's physical condition, aerobic exercise ability, and energy metabolism. Sports performance data such as action accuracy, competition time, exercise time, exercise frequency, etc. directly reflects the athlete's sports skill level, which helps to reasonably arrange training plans and avoid overtraining and sports injuries. Sports injury data such as fractures, sprains, strains, muscle tears, etc. is of great significance for determining the cause of the injury and taking corresponding treatment measures. Rehabilitation process data such as pain level, joint range of motion, muscle strength, psychological state, etc. has an important impact on the rehabilitation effect, and timely intervention can effectively relieve the pain level and ensure the treatment effect and safety.

[0003] Currently, traditional intelligent analysis methods for sports medicine data tend to neglect the monitoring of psychological states, and are unable to accurately evaluate the mutual influence among various sports medicine indicators. The single-dimensional analysis method limits the depth of data mining, making it difficult to accurately judge the athlete's health status and the injury risk during subsequent sports processes. Summary of the Invention

[0004] Technical Problem to be Solved: Aiming at the deficiencies of the prior art, the present invention provides an intelligent analysis method and device for sports medicine data, which have the advantages of more comprehensive multi-dimensional analysis and higher accuracy of intelligent evaluation, and solves the problems that traditional intelligent analysis methods for sports medicine data neglect the monitoring of psychological states and it is difficult to accurately judge the health status and injury risk with a single dimension.

[0005] Technical Solution: To achieve the above object, the present invention provides the following technical solution: An intelligent analysis method for sports medicine data, characterized by comprising the following steps: Step 1: Set a unified time axis, and then collect the physiological index data, sports performance data, sports injury data, and rehabilitation process data of a single athlete in chronological order, and classify and form a physiological data set, a sports data set, an injury data set, and a rehabilitation data set; Step 2: Analyze the skill level of a single athlete in the uninjured state based on the physiological dataset and the sports dataset, and generate the corresponding level coefficient ; Step 3: Analyze the health level of a single athlete in the injured state based on the injury dataset and the rehabilitation dataset, and generate the corresponding injury coefficient ; Step 4: Set a fixed range of level thresholds , injury thresholds and a monitoring period of fixed duration , and then combine the level coefficient and the injury coefficient to evaluate the health status and injury risk of a single athlete, and generate the corresponding warning signals and exercise recommendations.

[0006] Preferably, in the above Step 1, the expression of the physiological dataset is , represents the weight of a single athlete, represents the height of a single athlete, represents the body fat percentage of a single athlete, represents the muscle mass of a single athlete, represents the heart rate of a single athlete, represents the maximum oxygen uptake of a single athlete, represents the specific time point for collecting the physiological index data of a single athlete, and each time point corresponds to a single node on the time axis.

[0007] Preferably, in the above Step 1, the expression of the sports dataset is , represents the action achievement rate of a single athlete, represents the exercise duration of a single athlete, represents the specific time point for collecting the exercise performance data of a single athlete, and each time point corresponds to a single node on the time axis.

[0008] Preferably, in the above Step 1, the expression of the injury dataset is , to represent the sports injury data from the first to the th time. The sports injury data includes the injury site and the injury degree, represents the specific time point when a single athlete has a sports injury, and each time point corresponds to a single node on the time axis.

[0009] Preferably, in the above Step 1, the expression of the rehabilitation dataset is , to Indicates the rehabilitation process data from the first day to the th day. The rehabilitation process data includes pain level, muscle strength, and psychological test scores. Indicates the specific time points for collecting the rehabilitation process data of a single athlete, and each time point corresponds to a single node on the time axis.

[0010] Preferably, in the second step, the horizontal coefficient The calculation process is as follows: Statistically analyze the physiological index data and sports performance data of a single athlete before the first sports injury according to the time axis and mark them as , to Indicates the first node to the th node in the time axis; ; In the formula, Indicates the th node in the time axis, and , Indicates the weight for the ratio of height to weight of a single athlete, Indicates the weight for the ratio of muscle mass to body fat percentage of a single athlete, Indicates the weight for the ratio of maximum oxygen uptake to heart rate of a single athlete, Indicates the standard achievement rate for measuring whether the action achievement rate meets the standard, Indicates the weight for the ratio of the standard achievement rate to the action achievement rate of a single athlete, Indicates the standard duration for measuring whether the sports duration meets the standard, Indicates the weight for the ratio of the standard duration to the sports duration of a single athlete, , , , and are all constants, and , Indicates that according to the , , , and weights, when calculating the th node, the horizontal coefficient of the single athlete in the uninjured state is .

[0011] Preferably, in the third step, the injury coefficient The calculation process is as follows: Statistically analyze the sports injury data and rehabilitation process data of a single athlete at the time of the first sports injury and after the first sports injury according to the time axis and mark them as , to represent the first node to the th node in the time axis; If at the th node, the injury site of a single athlete is the brain, internal organs, bones, joints or tendons, ; In the formula, represents the th node in the time axis, represents the injury degree of a single athlete at the th node, represents the weight for the injury degree of a single athlete, represents the pain degree of a single athlete at the th node, represents the weight for the pain degree of a single athlete, represents the muscle strength of a single athlete at the th node, represents the basic strength for measuring whether the muscle strength is normal, represents the weight for the ratio of the basic strength to the muscle strength of a single athlete, represents the psychological test score of a single athlete at the th node, represents the basic score for measuring whether the psychological test score is normal, represents the weight for the ratio of the basic score to the psychological test score of a single athlete, , , and are all constants, and , represents calculated according to the , , and weights, the injury coefficient of a single athlete in the injury state at the th node ; If at the th node, the injury site of a single athlete is blood vessels, ligaments or soft tissues, ; In the formula, represents the th node in the time axis, represents the weight for the injury degree of a single athlete, represents the weight for the pain degree of a single athlete, Represents the weight for the ratio of an individual athlete's muscle strength to the basic strength, Represents the weight for the ratio of an individual athlete's psychological test score to the basic score, 、 、 and are all constants, and , , , , , Represents that according to the weights of 、 、 and , when calculating the th node, the injury coefficient of an individual athlete in the injured state is .

[0012] Preferably, in the fourth step, each node in the time axis has a corresponding horizontal coefficient or injury coefficient . If the horizontal coefficient of a single node is lower than the horizontal threshold , it indicates that the athlete's health status is not good, and it is recommended to reduce the exercise intensity and difficulty. If the injury coefficient of a single node exceeds the injury threshold , it indicates that the athlete's health status is not good, and it is recommended to extend the rehabilitation period.

[0013] Preferably, in the fourth step, within a single monitoring period , the proportional relationship between the horizontal coefficient and the injury coefficient of an individual athlete is a direct proportional relationship, indicating that the risk of sports injury is significantly increased, generating a corresponding injury warning signal, and it is recommended to adjust the exercise plan.

[0014] A sports medicine data intelligent analysis device includes a multi-dimensional acquisition module, an intelligent analysis module, and a warning management module, and the multi-dimensional acquisition module, the intelligent analysis module, and the warning management module are interconnected through a network; The multi-dimensional acquisition module sets a unified time axis for standardizing real-time data. The multi-dimensional acquisition module is connected to a database, a monitoring device, and an optical motion capture device through a network, and real-time collects the physiological index data, sports performance data, sports injury data, and rehabilitation process data of an individual athlete, and classifies and forms a physiological data set, a sports data set, an injury data set, and a rehabilitation data set; The intelligent analysis module analyzes the skill level of an individual athlete in the uninjured state according to the physiological data set and the sports data set, and generates a corresponding horizontal coefficient , the intelligent analysis module analyzes the health level of a single athlete in the injured state according to the injury dataset and the rehabilitation dataset, and generates a corresponding injury coefficient ; The warning management module is set with a horizontal threshold within a fixed range , injury threshold and a monitoring period with a fixed duration . Then, combined with the horizontal coefficient and the injury coefficient , it evaluates the health status and injury risk of a single athlete, and generates corresponding warning signals and exercise suggestions.

[0015] Compared with the prior art, the present invention provides a method and device for intelligent analysis of sports medicine data, having the following beneficial effects: The present invention sets a unified time axis through the multi-dimensional acquisition module for standardizing real-time data. The multi-dimensional acquisition module is connected to a database, a monitoring device, and an optical motion capture device through a network, and real-time collects physiological index data, sports performance data, sports injury data, and rehabilitation process data of a single athlete, and classifies and forms a physiological dataset, a sports dataset, an injury dataset, and a rehabilitation dataset, ensuring the consistency and comparability of multi-dimensional data in the time dimension. The intelligent analysis module analyzes the skill level of a single athlete in the uninjured state according to the physiological dataset and the sports dataset, and generates a corresponding horizontal coefficient , and each weight can be adjusted according to the characteristics of different athletes and project requirements, and can flexibly adapt to the individual differences of different athletes, providing a more targeted status assessment. The intelligent analysis module analyzes the health level of a single athlete in the injured state according to the injury dataset and the rehabilitation dataset, and generates a corresponding injury coefficient , comprehensively considering the degree of injury, the degree of pain, the change of muscle strength relative to the basic strength, and the change of psychological test score relative to the basic score, accurately evaluating the health status of the athlete, which helps to formulate corresponding training and recovery plans subsequently, and the multi-dimensional analysis is more comprehensive.

[0016] The present invention sets a horizontal threshold within a fixed range through the warning management module , injury threshold and a monitoring period with a fixed duration . Then, combined with the horizontal coefficient and the injury coefficient , it evaluates the health status and injury risk of a single athlete. Any node in the time axis has a corresponding horizontal coefficient or injury coefficient . If the horizontal coefficient of a single node is lower than the horizontal threshold When it indicates that the athlete's health condition is poor, it is recommended to reduce the exercise intensity and difficulty. If the injury coefficient of a single node exceeds the injury threshold When it does, it indicates that the athlete's health condition is poor, and it is recommended to extend the rehabilitation period. Any node in the time axis has a corresponding level coefficient or injury coefficient If the level coefficient of a single node is lower than the level threshold When it is, it indicates that the athlete's health condition is poor, and it is recommended to reduce the exercise intensity and difficulty. If the injury coefficient of a single node exceeds the injury threshold When it does, it indicates that the athlete's health condition is poor, and it is recommended to extend the rehabilitation period. The intelligent evaluation has high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flowchart of the method steps of the present invention; Figure 2 is a schematic structural diagram of the device of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Since the traditional intelligent analysis method of sports medicine data ignores the monitoring of the psychological state and it is difficult to accurately judge the health status and injury risk from a single dimension, a method and device for intelligent analysis of sports medicine data are provided. Please refer to Figure 1 - Figure 2 A method for intelligent analysis of sports medicine data includes the following steps: Step 1: Set a unified time axis, and then collect the physiological index data, sports performance data, sports injury data, and rehabilitation process data of a single athlete in chronological order, and classify and form a physiological data set, a sports data set, an injury data set, and a rehabilitation data set, ensuring the consistency and comparability of multi-dimensional data in the time dimension; The expression of the physiological data set is , represents the weight of a single athlete, represents the height of a single athlete, represents the body fat percentage of a single athlete, represents the muscle mass of a single athlete, represents the heart rate of a single athlete, Represents the maximum oxygen uptake of a single athlete, Represents the specific time point for collecting the physiological index data of a single athlete, and each time point corresponds to a single node on the time axis. As time goes by, the physiological index data is collected regularly and recorded on the unified time axis, which can clearly observe the changing trend of the athlete's physiological state and help to deeply understand the basic conditions such as the athlete's cardiopulmonary function and metabolic level; The expression of the motion data set is , Represents the action achievement rate of a single athlete, Represents the exercise duration of a single athlete, Represents the specific time point for collecting the sports performance data of a single athlete, and each time point corresponds to a single node on the time axis. Quantitatively evaluating the athlete's performance in training or competition helps to study and discover the laws and characteristics of the athlete's sports performance; The expression of the injury data set is , to Represents the sports injury data from the first time to the th time. The sports injury data includes the injury site and the degree of injury. Specifically, the degree of injury is divided into three grades: serious injury, minor injury, and slight injury. In the subsequent formula, slight injury corresponds to the number 2, minor injury corresponds to the number 4, and serious injury corresponds to the number 6. Represents the specific time point when a single athlete has a sports injury, and each time point corresponds to a single node on the time axis, which is convenient for tracing the athlete's injury history; The expression of the rehabilitation data set is , to Represents the rehabilitation process data from the first day to the th day. The rehabilitation process data includes pain level, muscle strength, and psychological test scores. Specifically, the pain intensity is described by 11 numbers from 0 to 10. 0 means no pain, 0 - 3 means mild pain, 3 - 7 means moderate pain, >7 means severe pain, and 10 means intense pain. Muscle strength is divided into primary, intermediate, and advanced. Primary muscle strength is below 50 kg, suitable for low-intensity physical exercise and rehabilitation training, corresponding to the number 6. Intermediate muscle strength is between 50 - 100 kg, suitable for moderate-intensity physical exercise and competition, corresponding to the number 4. Advanced muscle strength is above 100 kg, suitable for high-intensity physical exercise and competition, corresponding to the number 2. The psychological test score is obtained in the form of a questionnaire. It represents the specific time points for collecting data on the rehabilitation process of a single athlete, and each time point corresponds to a single node on the time axis, enabling real-time tracking of the rehabilitation progress, timely detection of problems and obstacles during the rehabilitation process, accurate observation and analysis of the athlete's physiological state, athletic performance, injury situation, and rehabilitation progress at different time points, and avoiding data chaos and analysis errors caused by inconsistent time standards; Step 2: According to the physiological data set and the sports data set, analyze the skill level of a single athlete in the uninjured state and generate the corresponding level coefficient ; Level coefficient The calculation process is as follows: Statistically analyze the physiological index data and athletic performance data of a single athlete before the first sports injury according to the time axis and mark them as , to represent the first node to the th node in the time axis; ; In the formula, represents the th node in the time axis, and , represents the weight for the ratio of height to weight of a single athlete, represents the weight for the ratio of muscle mass to body fat percentage of a single athlete, represents the weight for the ratio of maximum oxygen uptake to heart rate of a single athlete, represents the standard achievement rate for measuring whether the action achievement rate meets the standard, represents the weight for the ratio of the standard achievement rate to the action achievement rate of a single athlete, represents the standard duration for measuring whether the exercise duration meets the standard, represents the weight for the ratio of the standard duration to the exercise duration of a single athlete, , , , and are all constants, and , represents that according to , , , and weights, when calculating the th node, the level coefficient of a single athlete in the uninjured state . Considering various factors comprehensively, specifically, the weight of each item can be adjusted according to the characteristics of different athletes and the requirements of the event. For events that require high-intensity endurance, the weight of the ratio of maximum oxygen uptake to heart rate can be appropriately increased. For events that focus on skills and accuracy, the weight related to the action achievement rate can be increased, which can flexibly adapt to the individual differences of different athletes and provide more targeted status assessment; Step 3: According to the injury dataset and the rehabilitation dataset, analyze the health level of a single athlete in the injured state and generate the corresponding injury coefficient ; Injury coefficient The calculation process is as follows: Statistically analyze the sports injury data and rehabilitation process data of a single athlete at the time of the first sports injury and after the first sports injury according to the time axis and mark them as , to represent the first node to the th node in the time axis; If at the th node, the injured part of a single athlete is the brain, internal organs, bones, joints or tendons, ; In the formula, represents the th node in the time axis, represents the degree of injury of a single athlete at the th node, represents the weight for the degree of injury of a single athlete, represents the degree of pain of a single athlete at the th node, represents the weight for the degree of pain of a single athlete, represents the muscle strength of a single athlete at the th node, represents the basic strength for measuring whether the muscle strength is normal, represents the weight for the ratio of the basic strength to the muscle strength of a single athlete, represents the psychological test score of a single athlete at the th node, represents the basic score for measuring whether the psychological test score is normal, represents the weight for the ratio of the basic score to the psychological test score of a single athlete, , , and are all constants, and , represents according to , , and weights, when calculating the th node, the injury coefficient of a single athlete in the injured state ; If at the th node, the injured part of a single athlete is blood vessel, ligament or soft tissue, ; In the formula, represents the th node in the time axis, represents the weight for the injury degree of a single athlete, represents the weight for the pain degree of a single athlete, represents the weight for the ratio of muscle strength to basic strength of a single athlete, represents the weight for the ratio of psychological test score to basic score of a single athlete, , , and are all constants, and , , , , , represents that according to , , and weights, when calculating the th node, the injury coefficient of a single athlete in the injured state . It comprehensively considers the injury degree, pain degree, the change of muscle strength relative to the basic strength, and the change of psychological test score relative to the basic score, accurately evaluates the health status of the athlete, and helps to formulate corresponding training and recovery plans in the follow-up; Step 4: Set a fixed range of horizontal threshold , injury threshold and a monitoring period with a fixed duration , and then combined with the horizontal coefficient and the injury coefficient , evaluate the health status and injury risk of a single athlete, and generate corresponding warning signals and exercise suggestions; Any node in the time axis has a corresponding horizontal coefficient or injury coefficient or injury coefficient . If the horizontal coefficient of a single node is lower than the horizontal threshold When it indicates that the athlete's health condition is poor, it is recommended to reduce the exercise intensity and difficulty. If the injury coefficient of a single node exceeds the injury threshold When it indicates that the athlete's health condition is poor, it is recommended to extend the rehabilitation period. Any node in the time axis has a corresponding level coefficient or injury coefficient . If the level coefficient of a single node is lower than the level threshold When it indicates that the athlete's health condition is poor, it is recommended to reduce the exercise intensity and difficulty. If the injury coefficient of a single node exceeds the injury threshold When it indicates that the athlete's health condition is poor, it is recommended to extend the rehabilitation period.

[0020] A sports medicine data intelligent analysis device includes a multi-dimensional acquisition module, an intelligent analysis module, and a warning management module. The multi-dimensional acquisition module, the intelligent analysis module, and the warning management module are interconnected through a network; The multi-dimensional acquisition module sets a unified time axis for standardizing real-time data. The multi-dimensional acquisition module is connected to a database, a monitoring device, and an optical motion capture device through a network to collect physiological index data, sports performance data, sports injury data, and rehabilitation process data of a single athlete in real time, and classify and form a physiological data set, a sports data set, an injury data set, and a rehabilitation data set; The intelligent analysis module analyzes the skill level of a single athlete in the uninjured state according to the physiological data set and the sports data set, and generates a corresponding level coefficient . The intelligent analysis module analyzes the health level of a single athlete in the injured state according to the injury data set and the rehabilitation data set, and generates a corresponding injury coefficient , and the multi-dimensional analysis is more comprehensive; The warning management module sets a fixed range of level thresholds , injury thresholds and a monitoring period with a fixed duration . Then, combined with the level coefficient and the injury coefficient , it evaluates the health status and injury risk of a single athlete, and generates corresponding warning signals and exercise suggestions, and the intelligent evaluation accuracy is high.

[0021] Example 1: In this example, a male long-distance runner is selected as the experimental subject. After testing, the athlete's height is 170 cm, weight is 120 jin, muscle mass is 30%, body fat percentage is 15%, maximum oxygen uptake is 50 ml / kg / min, heart rate is 150 beats / min. When running a single 500-meter sprint, the action achievement rate is 90%, and the exercise duration is 60 seconds. The level coefficient of this athlete The calculation process is as follows: ; ; In the formula, the weight for the injury degree of a single athlete is 0.25, the weight for the pain degree of a single athlete is 0.25, the weight for the ratio of muscle strength to basic strength of a single athlete is 0.25, and the weight for the ratio of the psychological test score to the basic score of a single athlete is 0.25. The basic strength for measuring whether the muscle strength is normal corresponds to the number 6, and the basic score for measuring whether the psychological test score is normal is 80. 、 、 and are all constants, and , , , , According to 、 、 and weights, the injury coefficient of this athlete in the current injury state is calculated to be 2.525.

[0022] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent analysis method for sports medicine data, characterized in that, It includes the following steps: Step 1: Set a unified timeline, and then collect the physiological index data, sports performance data, sports injury data, and rehabilitation process data of individual athletes in chronological order, and classify and form a physiological data set, a sports data set, an injury data set, and a rehabilitation data set; Step 2: Analyze the skill level of a single athlete in the uninjured state based on the physiological data set and the motion data set, and generate the corresponding level coefficient ; Step 3: Analyze the health level of individual athletes in the injury state based on the injury dataset and the rehabilitation dataset, and generate corresponding injury coefficients ; Step 4: Set horizontal thresholds within a fixed range , injury thresholds and a monitoring period of fixed duration , and then combine with the horizontal coefficient and the injury coefficient , evaluate the health status and injury risk of individual athletes, and generate corresponding warning signals and exercise recommendations.

2. The intelligent analysis method for sports medicine data according to claim 1, characterized in that: In the first step, the expression of the physiological data set is , represents the weight of a single athlete, represents the height of a single athlete, represents the body fat percentage of a single athlete, represents the muscle mass of a single athlete, represents the heart rate of a single athlete, represents the maximum oxygen uptake of a single athlete, represents the specific time point for collecting the physiological index data of a single athlete, and each time point corresponds to a single node on the time axis.

3. The intelligent analysis method for sports medicine data according to claim 2, characterized in that: In the first step, the expression of the motion data set is , represents the action achievement rate of a single athlete, represents the motion duration of a single athlete, represents the specific time point for collecting the motion performance data of a single athlete, and each time point corresponds to a single node on the time axis.

4. The intelligent analysis method for sports medicine data according to claim 3, wherein: In the first step, the expression of the injury dataset is , to represent the sports injury data from the first to the th time. The sports injury data includes the injury location and the degree of injury. represents the specific time point when a single athlete sustains a sports injury, and each time point corresponds to a single node on the time axis.

5. A method for intelligent analysis of sports medicine data according to claim 4, characterized in that: In the first step, the expression of the rehabilitation data set is , to represent the rehabilitation process data from the first day to the th day. The rehabilitation process data includes pain level, muscle strength, and psychological test scores. represents the specific time point for collecting the rehabilitation process data of a single athlete, and each time point corresponds to a single node on the time axis.

6. The intelligent analysis method for sports medicine data according to claim 5, characterized in that: In the second step, the horizontal coefficient The calculation process is as follows: Statistically analyze the physiological index data and sports performance data of a single athlete before the first sports injury according to the timeline, and mark them as , to represent the first node to the th node in the timeline; ； In the formula, represents the th node in the time axis, and , represents the weight for the ratio of height to weight of a single athlete, represents the weight for the ratio of muscle mass to body fat percentage of a single athlete, represents the weight for the ratio of maximum oxygen uptake to heart rate of a single athlete, represents the standard achievement rate for measuring whether the action achievement rate meets the standard, represents the weight for the ratio of the standard achievement rate to the action achievement rate of a single athlete, represents the standard duration for measuring whether the exercise duration meets the standard, represents the weight for the ratio of the standard duration to the exercise duration of a single athlete, , , , and are all constants, and , represents that when calculating the , , , and weights, the horizontal coefficient of a single athlete in the uninjured state at the th node is obtained.

7. The intelligent analysis method for sports medicine data according to claim 6, characterized in that: In the third step above, the injury coefficient The calculation process is as follows: Statistically analyze the sports injury data and rehabilitation process data of a single athlete at the time of the first sports injury and after the first sports injury according to the timeline, and mark them as , to represent the first node to the th node in the timeline; If at the th node, the injury site of a single athlete is the brain, internal organs, bones, joints or tendons, ； In the formula, represents the th node in the time axis, represents the degree of injury of a single athlete at the th node, represents the weight for the degree of injury of a single athlete, represents the degree of pain of a single athlete at the th node, represents the weight for the degree of pain of a single athlete, represents the muscle strength of a single athlete at the th node, represents the basic strength for measuring whether the muscle strength is normal, represents the weight for the ratio of the basic strength to the muscle strength of a single athlete, represents the psychological test score of a single athlete at the th node, represents the basic score for measuring whether the psychological test score is normal, represents the weight for the ratio of the basic score to the psychological test score of a single athlete, , , and are all constants, and , represents that according to the weights of , , and , the injury coefficient of a single athlete in the injury state at the th node is calculated as ; If at the th node, the injury site of a single athlete is blood vessel, ligament or soft tissue, ； In the formula, represents the th node in the time axis, represents the weight for the degree of injury of a single athlete, represents the weight for the degree of pain of a single athlete, represents the weight for the ratio of muscle strength to basic strength of a single athlete, represents the weight for the ratio of the psychological test score to the basic score of a single athlete, , , and are all constants, and , , , , , represents that when calculating the , , and weights, the injury coefficient of a single athlete in the injury state at the th node is obtained.

8. The intelligent analysis method for sports medicine data according to claim 7, characterized in that: In step four, any node in the timeline has a corresponding horizontal coefficient or injury coefficient . If the horizontal coefficient of a single node is lower than the horizontal threshold , it indicates that the athlete's health condition is poor, and it is recommended to reduce the intensity and difficulty of the exercise. If the injury coefficient of a single node exceeds the injury threshold , it indicates that the athlete's health condition is poor, and it is recommended to extend the rehabilitation period.

9. The intelligent analysis method for sports medicine data according to claim 8, wherein: In the fourth step, within a single monitoring period the proportional relationship between the horizontal coefficient and the injury coefficient of a single athlete is a direct proportional relationship, indicating a significant increase in the risk of sports injuries, generating a corresponding injury warning signal, and suggesting adjusting the exercise plan.

10. An intelligent analysis device for sports medicine data, which is applied to an intelligent analysis method for sports medicine data according to any one of claims 1-9, and is characterized in that: It includes a multi-dimensional acquisition module, an intelligent analysis module, and an early warning management module, and the multi-dimensional acquisition module, the intelligent analysis module, and the early warning management module are interconnected through a network; The multi-dimensional acquisition module sets a unified timeline for standardizing real-time data. The multi-dimensional acquisition module is connected to a database, a monitoring device, and an optical motion capture device through a network to collect the physiological index data, sports performance data, sports injury data, and rehabilitation process data of individual athletes in real time, and classify and form a physiological data set, a sports data set, an injury data set, and a rehabilitation data set; The intelligent analysis module analyzes the skill level of a single athlete in the uninjured state based on the physiological data set and the motion data set, and generates a corresponding level coefficient The intelligent analysis module analyzes the health level of a single athlete in the injured state based on the injury data set and the rehabilitation data set, and generates a corresponding injury coefficient ; The early warning management module is set with horizontal thresholds within a fixed range , injury thresholds and a monitoring period of a fixed duration . Combining with the horizontal coefficient and the injury coefficient , it evaluates the health status and injury risks of individual athletes and generates corresponding early warning signals and exercise recommendations.

Images