Three-dimensional motion data resource library construction structure

Abstract

The invention discloses a three-dimensional exercise data resource library construction structure, and relates to the technical field of public fitness, and the three-dimensional exercise data resource library construction structure comprises a multi-modal data acquisition module, a data processing module, a data storage module and an application service module. The data acquisition module is used for acquiring relevant data of sportsmen; whether the three-dimensional data meet the storage requirement or not is preliminarily judged by analyzing the physiological indexes, and the personnel meeting the storage requirement are finally determined by analyzing the technical indexes; by extracting the basic data of the new exerciser, calculating the similarity of the basic data, screening each reference person according to the exercise type, and extracting the mode value of the training frequency of each reference person as the training frequency of the new exerciser, the scientificity and safety of the exercise are effectively improved, and the defects in the prior art are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of mass fitness, and in particular to a three-dimensional motion data resource library construction structure. Background Art

[0002] With the rapid development of national fitness and competitive sports, scientific and precise sports guidance and management are becoming increasingly important. Traditional sports data processing methods often focus on data from a single dimension, making it difficult to fully and deeply reflect the physical condition and performance of athletes. For example, in sports training, coaches only formulate training plans based on the athlete's exercise duration and simple heart rate data, failing to fully consider the individual athlete's technical characteristics and personalized needs. In the field of fitness, fitness enthusiasts also lack scientific exercise program recommendations and real-time health warnings. Therefore, the invention of a three-dimensional sports data resource library construction structure is of great significance for improving exercise effectiveness, ensuring sports safety, and promoting the development of sports.

[0003] The existing technology also has the following technical defects, which are specifically reflected in: 1. In the existing technology, the data collection method is single and mostly limited to basic physiological indicator monitoring. It is impossible to obtain comprehensive exercise-related data, making it difficult to conduct in-depth analysis of the exercise process. Data management is extensive and lacks a systematic data screening and analysis process. It cannot effectively combine physiological indicators and technical indicators for comprehensive analysis, making it difficult to ensure the quality of exercise data, resulting in poor data availability.

[0004] 2. In the existing technology, the formulation of exercise plans lacks precise basis, and it is impossible to fully utilize historical data to achieve personalized matching. The training plan is not targeted enough, resulting in the formulation of exercise plans being unscientific and unreasonable, and unable to meet the personalized needs of different athletes. When formulating new exercise plans, it is impossible to provide different athletes with personalized plans that suit their own characteristics. Summary of the Invention

[0005] The purpose of the present invention is to provide a three-dimensional motion data resource library construction structure to solve the problems existing in the background technology.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a three-dimensional motion data resource library construction structure, including: a multimodal data acquisition module: used to obtain relevant data of each athlete from the database.

[0007] Data processing module: used to analyze the physiological indicators of each athlete based on the relevant data of each athlete, preliminarily determine whether the three-dimensional data of each athlete meets the storage requirements, preliminarily obtain each athlete whose three-dimensional data meets the storage requirements, and then analyze the technical indicators of each type of sports of each athlete, and finally determine whether the three-dimensional data of each athlete meets the storage requirements, and finally obtain each athlete whose three-dimensional data meets the storage requirements.

[0008] Data storage module: used to store the three-dimensional data of each athlete that ultimately meets the storage requirements and generate a three-dimensional sports data resource library.

[0009] Application service module: used to set up exercise plans based on the three-dimensional exercise data resource library when new athletes appear.

[0010] Preferably, the relevant data of each athlete include: basic data and heart rate at each monitoring time point during various types of exercise, electrical signals of target muscle groups and antagonistic muscle groups, and three-dimensional spatial coordinates of each key position, wherein the basic data include age, height, weight, and BMI.

[0011] Preferably, the physiological indicators of each athlete are analyzed, and the specific implementation method is as follows: extract the age of each athlete, calculate the maximum heart rate of each athlete based on the heart rate calculation formula, extract the heart rate of each athlete at each monitoring time point during each type of exercise, divide the heart rate of each athlete at each monitoring time point during each type of exercise by the maximum heart rate of each athlete, and obtain the heart rate ratio of each athlete at each monitoring time point during each type of exercise, perform mean processing on the heart rate ratio at each monitoring time point, and obtain the heart rate ratio of each athlete during each type of exercise, and compare the heart rate ratio of each athlete during each type of exercise with the heart rate ratio range corresponding to each type of exercise and exercise intensity in the database to obtain the exercise intensity of each type of exercise for each athlete.

[0012] The electrical signals of the target muscle groups and antagonistic muscle groups at each monitoring time point during each type of exercise of each athlete are extracted, and the electrical signals of the target muscle groups at each monitoring time point during each type of exercise of each athlete are divided by the electrical signals of the antagonistic muscle groups at each monitoring time point during each type of exercise of each athlete to obtain the muscle activation efficiency at each monitoring time point during each type of exercise of each athlete, and the muscle activation efficiency at each monitoring time point is averaged to obtain the muscle activation efficiency of each type of exercise of each athlete.

[0013] Preferably, the preliminary judgment of whether the three-dimensional data of each athlete meets the storage requirements is specifically implemented by extracting the exercise intensity of each athlete for each type of exercise and the muscle activation efficiency of each athlete for each type of exercise, inputting them into the three-dimensional data storage preliminary judgment model, and outputting the judgment result of whether the three-dimensional data of each athlete meets the storage requirements.

[0014] The judgment result of whether the three-dimensional data of each athlete meets the storage requirements includes the values ​​of 2 and 1. If the judgment result of whether the three-dimensional data of a certain athlete meets the storage requirements is 2, it means that the three-dimensional data of the athlete meets the storage requirements. If the judgment result of whether the three-dimensional data of a certain athlete meets the storage requirements is 1, it means that the three-dimensional data of the athlete does not meet the storage requirements.

[0015] Preferably, the three-dimensional data storage preliminary judgment model expression is: where α ip Indicates the judgment result of whether the three-dimensional data of the p-th type of motion of the i-th person meets the storage requirements, A ip 、B ip They represent the exercise intensity and muscle activation efficiency of the p-th type of exercise of the i-th athlete, A′ p , B′ p They respectively represent the appropriate exercise intensity range and the appropriate muscle activation efficiency range for the p-th type of exercise stored in the database, i represents the number of the athlete, i=1,2,...,j, j is a positive integer greater than 2, p represents the number of the exercise type, p=1,2,...,q, q is a positive integer greater than 2.

[0016] Preferably, the technical indicators of various types of sports of various athletes are analyzed, and the specific implementation method is: extracting the three-dimensional spatial coordinates of each key position at each monitoring time point during each type of sports of a single athlete, comparing the three-dimensional spatial coordinates of each key position during each type of sports of the athlete with the three-dimensional spatial coordinates of each key position at each monitoring time point in the standard posture during each type of sports stored in the database, and calculating the displacement offset of each key position at each monitoring time point during each type of sports of the athlete; according to the analysis process of the displacement offset of each key position at each monitoring time point during each type of sports of a single athlete, the displacement offset of each key position at each monitoring time point during each type of sports of each athlete is analyzed.

[0017] Preferably, the three-dimensional data of each athlete finally obtained meets the storage requirements, and the specific implementation method is: extract the displacement offset of each key position at each monitoring time point in the various types of sports of each athlete, and compare it with the displacement offset range of each key position at each monitoring time point in the various types of sports stored in the database. If the displacement offset of a key position at a certain monitoring time point in a certain type of sports of a certain athlete is not within the displacement offset range of the key position at the monitoring time point in the sports of this type stored in the database, it is determined that the three-dimensional data of the athlete in this type of sports is abnormal, and it is determined that the three-dimensional data of the athlete does not meet the storage requirements; otherwise, it is determined that the three-dimensional data of the athlete meets the storage requirements.

[0018] Preferably, the specific implementation method of setting the exercise plan is: extracting the basic data entered by the new athlete, calculating the similarity between the basic data of the new athlete and each athlete, screening each athlete with similar basic data, extracting the exercise type of the new athlete, further screening each athlete with the same exercise type from each athlete with similar basic data, taking each athlete with the same exercise type as each reference athlete, extracting the training frequency of each reference athlete from the database, screening to obtain the mode value of the training frequency, and using it as the training frequency of the new athlete.

[0019] Preferably, a database is also included, specifically including: relevant data of each athlete, heart rate ratio range corresponding to each type of exercise and each exercise intensity, suitable exercise intensity range and suitable muscle activation efficiency range for each type of exercise, three-dimensional spatial coordinates of each key position at each monitoring time point in a standard posture during each type of exercise, displacement offset range of each key position at each monitoring time point during each type of exercise, and training frequency of each reference athlete.

[0020] The beneficial effects of the present invention are: 1. A multi-module collaborative system is constructed in the present invention. Through multimodal data acquisition and multi-level data processing, three-dimensional data screening is performed by integrating physiological indicators and technical indicators to ensure the high quality of the data entering the database, realize accurate assessment of the status of athletes, and ensure the quality and effectiveness of resource library data. Compared with traditional simple storage, the data accuracy and reliability are greatly improved.

[0021] 2. Intelligent customization of exercise plans is achieved based on the data resource library. By combining the similarity of new personnel's basic data with the matching of exercise types, a scientific reference plan is provided, breaking through the traditional "one-size-fits-all" training model and realizing personalized exercise guidance. It can provide athletes with more scientific, accurate and personalized exercise guidance, which helps to improve the effect of exercise training, reduce exercise risks and promote the scientific development of sports. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 This is a schematic diagram of the system structure connection of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] Reference Figure 1 As shown, the present invention provides a three-dimensional sports data resource library construction structure, including: a multimodal data acquisition module: used to obtain relevant data of each athlete from the database.

[0026] In a specific embodiment, the relevant data of each athlete include: basic data and heart rate at each monitoring time point during various types of exercise, electrical signals of target muscle groups and antagonistic muscle groups, and three-dimensional spatial coordinates of each key position, wherein the basic data include age, height, weight, and BMI.

[0027] Data processing module: used to analyze the physiological indicators of each athlete based on the relevant data of each athlete, preliminarily determine whether the three-dimensional data of each athlete meets the storage requirements, preliminarily obtain each athlete whose three-dimensional data meets the storage requirements, and then analyze the technical indicators of each type of sports of each athlete, and finally determine whether the three-dimensional data of each athlete meets the storage requirements, and finally obtain each athlete whose three-dimensional data meets the storage requirements.

[0028] In the present invention, a multi-module collaborative system is constructed. Through multimodal data collection and multi-level data processing, physiological indicators and technical indicators are integrated to perform three-dimensional data screening to ensure the high quality of the incoming data, realize the accurate assessment of the status of athletes, and ensure the quality and effectiveness of the resource library data. Compared with traditional simple storage, the data accuracy and reliability are greatly improved.

[0029] In a specific embodiment, the physiological indicators of each athlete are analyzed, and the specific implementation method is as follows: extract the age of each athlete, calculate the maximum heart rate of each athlete based on the heart rate calculation formula, extract the heart rate of each athlete at each monitoring time point during each type of exercise, divide the heart rate of each athlete at each monitoring time point during each type of exercise by the maximum heart rate of each athlete, and obtain the heart rate ratio of each athlete at each monitoring time point during each type of exercise, perform mean processing on the heart rate ratio at each monitoring time point, and obtain the heart rate ratio of each athlete during each type of exercise, and compare the heart rate ratio of each athlete during each type of exercise with the heart rate ratio range corresponding to each type of exercise and exercise intensity in the database to obtain the exercise intensity of each type of exercise for each athlete.

[0030] It should be noted that the heart rate calculation formula in this embodiment adopts a general formula: maximum heart rate = 220 - age. For example, a 30-year-old's maximum heart rate is theoretically 220 - 30 = 190 beats / minute. The heart rate percentage ranges corresponding to various types of exercise and exercise intensities in the database are set by organizing people of different age groups and physical conditions to conduct various types of exercise tests. During the test, professional heart rate monitoring equipment is used to accurately record heart rate data during exercise. The subjects exercise at different intensities. After collecting a large amount of test data, the data is statistically analyzed. The percentage of heart rate to maximum heart rate at different exercise intensities is calculated, and the average heart rate percentage range for each intensity level is determined. For example, the percentage of heart rate to maximum heart rate for low-intensity exercise is 40%-60%; for moderate intensity exercise, it is 60%-75%; and for high intensity exercise, it is 75%-90%.

[0031] The electrical signals of the target muscle groups and antagonistic muscle groups at each monitoring time point during each type of exercise of each athlete are extracted, and the electrical signals of the target muscle groups at each monitoring time point during each type of exercise of each athlete are divided by the electrical signals of the antagonistic muscle groups at each monitoring time point during each type of exercise of each athlete to obtain the muscle activation efficiency at each monitoring time point during each type of exercise of each athlete, and the muscle activation efficiency at each monitoring time point is averaged to obtain the muscle activation efficiency of each type of exercise of each athlete.

[0032] It should be noted that the target muscle groups and antagonist muscle groups during the various types of exercise vary depending on the type of exercise. For example, the target muscle groups for running mainly include the quadriceps femoris, gluteus maximus, and calf triceps, and the antagonist muscle groups are mainly the biceps femoris. The target muscle groups for push-ups mainly include the pectoralis major, anterior deltoid, and triceps, and the antagonist muscle groups mainly include the latissimus dorsi, posterior deltoid, and biceps.

[0033] In a specific embodiment, the preliminary judgment of whether the three-dimensional data of each athlete meets the storage requirements is specifically implemented by extracting the exercise intensity of each athlete for each type of exercise and the muscle activation efficiency of each athlete for each type of exercise, inputting them into the three-dimensional data storage preliminary judgment model, and outputting the judgment result of whether the three-dimensional data of each athlete meets the storage requirements.

[0034] The judgment result of whether the three-dimensional data of each athlete meets the storage requirements includes the values ​​of 2 and 1. If the judgment result of whether the three-dimensional data of a certain athlete meets the storage requirements is 2, it means that the three-dimensional data of the athlete meets the storage requirements. If the judgment result of whether the three-dimensional data of a certain athlete meets the storage requirements is 1, it means that the three-dimensional data of the athlete does not meet the storage requirements.

[0035] In a specific embodiment, the three-dimensional data storage preliminary judgment model expression is: where α ip Indicates the judgment result of whether the three-dimensional data of the p-th type of motion of the i-th person meets the storage requirements, A ip 、B ip They represent the exercise intensity and muscle activation efficiency of the p-th type of exercise of the i-th athlete, A′ p , B′ p They respectively represent the appropriate exercise intensity range and the appropriate muscle activation efficiency range for the p-th type of exercise stored in the database, i represents the number of the athlete, i=1,2,...,j, j is a positive integer greater than 2, p represents the number of the exercise type, p=1,2,...,q, q is a positive integer greater than 2.

[0036] It should be noted that the appropriate exercise intensity range and appropriate muscle activation efficiency range for each type of exercise are set as follows: in different types of exercise, electromyographic tests are performed on the exercise intensity, target muscle groups and antagonistic muscle groups, and the exercise intensity and muscle activation efficiency at different exercise intensities are recorded. Combined with the characteristics of the athletes, appropriate adjustments are made to obtain the appropriate exercise intensity range and appropriate muscle activation efficiency range for each type of exercise.

[0037] In a specific embodiment, the technical indicators of various types of sports of various athletes are analyzed, and the specific implementation method is: extracting the three-dimensional spatial coordinates of each key position at each monitoring time point during each type of sports of a single athlete, comparing the three-dimensional spatial coordinates of each key position during each type of sports of the athlete with the three-dimensional spatial coordinates of each key position at each monitoring time point in the standard posture during each type of sports stored in a database, and calculating the displacement offset of each key position at each monitoring time point during each type of sports of the athlete; according to the analysis process of the displacement offset of each key position at each monitoring time point during each type of sports of a single athlete, the displacement offset of each key position at each monitoring time point during each type of sports of each athlete is analyzed and obtained.

[0038] It should be noted that the calculation obtains the displacement offset of each key position at each monitoring time point during various types of exercise of the athlete using the Euclidean distance method. The Euclidean distance method is an existing technology and will not be described in detail here.

[0039] In a specific embodiment, the three-dimensional data of each athlete that finally meets the storage requirements is specifically implemented as follows: the displacement offset of each key position at each monitoring time point during each type of exercise of each athlete is extracted, and the displacement offset is compared with the displacement offset range of each key position at each monitoring time point during each type of exercise stored in the database. If the displacement offset of a key position at a monitoring time point during a certain type of exercise of a certain athlete is not within the displacement offset range of the key position at the monitoring time point during the exercise of this type of exercise stored in the database, it is determined that the three-dimensional data of the athlete during this type of exercise is abnormal, and it is determined that the three-dimensional data of the athlete does not meet the storage requirements. Otherwise, it is determined that the three-dimensional data of the athlete meets the storage requirements.

[0040] It should be noted that the displacement offset ranges of each key position at each monitoring time point during the various sports processes stored in the database are set by using advanced motion capture technology, such as optical motion capture systems and inertial measurement units, to accurately record the movements of a large number of professional athletes when performing various sports. These systems can obtain the coordinate data of each key position of the athlete's body (such as joints, body center of gravity, etc.) in three-dimensional space in real time, filter out samples with excellent performance and technical specifications from the collected data, and remove abnormal data caused by unexpected situations (such as injuries, mistakes, etc.). The filtered data is then sorted to obtain the displacement offset ranges of each key position at each monitoring time point during the various sports processes.

[0041] Data storage module: used to store the three-dimensional data of each athlete that ultimately meets the storage requirements and generate a three-dimensional sports data resource library.

[0042] Application service module: used to set up exercise plans based on the three-dimensional exercise data resource library when new athletes appear.

[0043] In a specific embodiment, the specific implementation method of setting the exercise plan is: extracting the basic data entered by the new athlete, calculating the similarity between the basic data of the new athlete and each athlete, screening out athletes with similar basic data, extracting the exercise type of the new athlete, further screening out athletes with the same exercise type from athletes with similar basic data, taking athletes with the same exercise type as reference athletes, extracting the training frequency of each reference athlete from the database, screening out the mode value of the training frequency, and using it as the training frequency of the new athlete.

[0044] It should be noted that the calculation of the basic data similarity between the new athlete and each athlete is specifically as follows: the basic data entered by the new athlete and the basic data of each athlete are converted into basic vectors, and with reference to the cosine similarity calculation formula, the cosine similarity of the vector of the basic data entered by the new athlete and the vector of the basic data of each athlete are calculated as the basic data similarity between the new athlete and each athlete; the screening of athletes with similar basic data is specifically as follows: extracting the basic data similarity between the new athlete and each athlete, and comparing it with the appropriate basic data similarity range stored in the database. If the basic data similarity between the new athlete and a certain athlete is within the appropriate basic data similarity range stored in the database, it is determined that the basic data of the athlete is similar to the new athlete.

[0045] Based on the data resource library, intelligent customization of exercise plans is achieved, and the similarity of new personnel's basic data is combined with the matching of exercise types to provide a scientific reference plan, breaking through the traditional "one-size-fits-all" training model and realizing personalized exercise guidance. It can provide athletes with more scientific, accurate and personalized exercise guidance, which helps to improve the effect of exercise training, reduce exercise risks and promote the scientific development of sports.

[0046] In a specific embodiment, a database is also included, specifically including: relevant data of each athlete, heart rate ratio range corresponding to each type of exercise and each exercise intensity, suitable exercise intensity range and suitable muscle activation efficiency range for each type of exercise, three-dimensional spatial coordinates of each key position at each monitoring time point in a standard posture during each type of exercise, displacement offset range of each key position at each monitoring time point during each type of exercise, and training frequency of each reference athlete.

[0047] It should be noted that the multimodal data acquisition module is connected to the data processing module, the data processing module is connected to the data storage module, the data storage module is connected to the application service module, and the multimodal data acquisition module, the data processing module and the application service module are connected to the database at the same time.

[0048] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. The construction structure of the 3D motion data resource library is characterized by: include: Multimodal data acquisition module: used to obtain relevant data of each athlete from the database; Data processing module: used to analyze the physiological indicators of each athlete based on the relevant data of each athlete, preliminarily determine whether the three-dimensional data of each athlete meets the storage requirements, and preliminarily obtain the athletes whose three-dimensional data meets the storage requirements, and then analyze the technical indicators of each athlete's various sports, and finally determine whether the three-dimensional data of each athlete meets the storage requirements, and finally obtain the athletes whose three-dimensional data meets the storage requirements; Data storage module: used to store the 3D data of each athlete that ultimately meets the storage requirements and generate a 3D sports data resource library; Application service module: used to set up exercise plans based on the three-dimensional exercise data resource library when new athletes appear.

2. The three-dimensional motion data resource library construction structure according to claim 1 is characterized in that: The relevant data of each athlete include: basic data and heart rate at each monitoring time point during various types of exercise, electrical signals of target muscle groups and antagonist muscle groups, and three-dimensional spatial coordinates of each key position, among which basic data include age, height, weight, and BMI.

3. The three-dimensional motion data resource library construction structure according to claim 2 is characterized in that: The specific implementation method of analyzing the physiological indicators of each athlete is as follows: Extract the age of each athlete, calculate the maximum heart rate of each athlete based on the heart rate calculation formula, extract the heart rate of each athlete at each monitoring time point during each type of exercise, divide the heart rate of each athlete at each monitoring time point during each type of exercise by the maximum heart rate of each athlete to obtain the heart rate ratio of each athlete at each monitoring time point during each type of exercise, average the heart rate ratios at each monitoring time point to obtain the heart rate ratio of each athlete during each type of exercise, compare the heart rate ratio of each athlete during each type of exercise with the heart rate ratio range corresponding to each type of exercise and exercise intensity in the database to obtain the exercise intensity of each type of exercise for each athlete; The electrical signals of the target muscle groups and antagonistic muscle groups at each monitoring time point during each type of exercise of each athlete are extracted, and the electrical signals of the target muscle groups at each monitoring time point during each type of exercise of each athlete are divided by the electrical signals of the antagonistic muscle groups at each monitoring time point during each type of exercise of each athlete to obtain the muscle activation efficiency at each monitoring time point during each type of exercise of each athlete, and the muscle activation efficiency at each monitoring time point is averaged to obtain the muscle activation efficiency of each type of exercise of each athlete.

4. The three-dimensional motion data resource library construction structure according to claim 3 is characterized in that: The preliminary determination of whether the three-dimensional data of each athlete meets the storage requirements is specifically implemented as follows: Extract the exercise intensity and muscle activation efficiency of each athlete's various exercises, input them into the preliminary judgment model of 3D data storage, and output the judgment result of whether the 3D data of each athlete meets the storage requirements; The judgment result of whether the three-dimensional data of each athlete meets the storage requirements includes the values ​​of 2 and 1. If the judgment result of whether the three-dimensional data of a certain athlete meets the storage requirements is 2, it means that the three-dimensional data of the athlete meets the storage requirements. If the judgment result of whether the three-dimensional data of a certain athlete meets the storage requirements is 1, it means that the three-dimensional data of the athlete does not meet the storage requirements.

5. The three-dimensional motion data resource library construction structure according to claim 4 is characterized in that: The three-dimensional data storage preliminary judgment model expression is: where α ip Indicates the judgment result of whether the three-dimensional data of the p-th type of motion of the i-th person meets the storage requirements, A ip 、B ip They represent the exercise intensity and muscle activation efficiency of the p-th type of exercise of the i-th athlete, A′ p , B′ p They respectively represent the appropriate exercise intensity range and the appropriate muscle activation efficiency range for the p-th type of exercise stored in the database, i represents the number of the athlete, i=1,2,...,j, j is a positive integer greater than 2, p represents the number of the exercise type, p=1,2,...,q, q is a positive integer greater than 2.

6. The three-dimensional motion data resource library construction structure according to claim 5 is characterized in that: The specific implementation method of analyzing the technical indicators of various sports of various athletes is as follows: The three-dimensional spatial coordinates of each key position at each monitoring time point during each type of movement of a single athlete are extracted, and the three-dimensional spatial coordinates of each key position at each monitoring time point during each type of movement of the athlete are compared with the three-dimensional spatial coordinates of each key position at each monitoring time point under standard posture during each type of movement stored in a database, and the displacement offset of each key position at each monitoring time point during each type of movement of the athlete is calculated. According to the analysis process of the displacement offset of each key position at each monitoring time point during each type of movement of a single athlete, the displacement offset of each key position at each monitoring time point during each type of movement of each athlete is analyzed.

7. The three-dimensional motion data resource library construction structure according to claim 6 is characterized in that: The three-dimensional data of each athlete that meets the storage requirements is finally obtained, and the specific implementation method is as follows: The displacement offset of each key position at each monitoring time point during each type of movement of each athlete is extracted, and compared with the displacement offset range of each key position at each monitoring time point during each type of movement stored in the database. If the displacement offset of a key position at a monitoring time point during a certain type of movement of an athlete is not within the displacement offset range of the key position at the monitoring time point during the movement of this type of movement stored in the database, it is determined that the three-dimensional data of the athlete in this type of movement is abnormal, and it is determined that the three-dimensional data of the athlete does not meet the storage requirements. Otherwise, it is determined that the three-dimensional data of the athlete meets the storage requirements.

8. The three-dimensional motion data resource library construction structure according to claim 7 is characterized in that: The specific implementation method of setting up the exercise plan is as follows: extracting the basic data entered by the new athlete, calculating the similarity between the basic data of the new athlete and each athlete, screening each athlete with similar basic data, extracting the exercise type of the new athlete, further screening each athlete with the same exercise type from each athlete with similar basic data, using each athlete with the same exercise type as each reference athlete, extracting the training frequency of each reference athlete from the database, screening to obtain the mode value of the training frequency, and using it as the training frequency of the new athlete.

9. The three-dimensional motion data resource library construction structure according to claim 8, characterized in that: It also includes a database, specifically including: relevant data of each athlete, the heart rate ratio range corresponding to each type of exercise and each exercise intensity, the appropriate exercise intensity range and the appropriate muscle activation efficiency range for each type of exercise, the three-dimensional spatial coordinates of each key position at each monitoring time point in a standard posture during each type of exercise, the displacement offset range of each key position at each monitoring time point during each type of exercise, and the training frequency of each reference athlete.

Images