Artificial intelligence-based solid ball test correction method

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a solid ball test correction method based on artificial intelligence, and the method comprises the following steps: simulating the interaction and track of a solid ball and air based on the track data of the solid ball, and generating the aerodynamic characteristics of the track of the solid ball. According to the invention, by simulating a solid ball track and aerodynamic characteristics, identifying key factors causing throwing deviation, generating an action optimization strategy and an adjustment guide, utilizing a dynamic time bending algorithm, analyzing an action abnormal signal, identifying deviation between an existing action and an ideal action model, and evaluating real-time action performance of an athlete, the real-time action performance of the athlete is evaluated. According to the method, action correction feedback is formulated, the training difficulty and target are adjusted in combination with the ability level of the athletes, the training pertinence and effect are optimized, and the technical skills and the competitive level of the athletes are improved by adjusting the ability in real time, reducing sports injuries, optimizing the training plan, assisting the coaches in solid ball testing and formulating a correction scheme.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based solid ball test correction method. Background Art

[0002] The field of artificial intelligence technology uses artificial intelligence algorithms and machine learning technologies to analyze and improve the effectiveness of sports training, including skill improvement, movement correction, and performance evaluation. By processing and analyzing athletes' sports data, performance, and reaction information, it provides personalized training suggestions and improvement measures to help athletes achieve higher performance standards, improve their competitive level, provide scientific data support for coaches, optimize training plans, and reduce the risk of sports injuries.

[0003] Among them, an artificial intelligence-based shot put test correction method uses artificial intelligence technology to analyze the performance of athletes in shot put tests, including throwing skills, power output, and body coordination. By analyzing the athletes' movements in shot put tests, it identifies the athletes' technical deficiencies and errors, and provides targeted training suggestions or movement correction plans to help athletes improve their techniques and improve their shot put test results and performance in competitions.

[0004] In actual operation, traditional methods lack analysis of the aerodynamic characteristics of the shot volleyball trajectory and real-time movement adjustments, resulting in training suggestions that cannot be optimized for the athlete's specific technical deficiencies. There is a lack of accurate identification and real-time feedback on key deviations between the athlete's throwing action and the ideal model, resulting in inaccurate movement correction plans, making it difficult to effectively improve the athlete's performance and reduce the risk of injury. The inability to accurately identify and adjust the trajectory deviation of the shot volleyball causes athletes to continue to use incorrect movement habits, increasing the risk of injury and affecting competition results. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a solid ball test correction method based on artificial intelligence.

[0006] In order to achieve the above object, the present invention adopts the following technical solution, a solid ball test correction method based on artificial intelligence, comprising the following steps: S1: Based on the trajectory data of the solid ball, the air resistance and lift during the ball's motion are analyzed. Combined with the speed and throwing angle information of the solid ball, the interaction and trajectory of the solid ball with the air are simulated to generate the aerodynamic characteristics of the solid ball trajectory. S2: Based on the aerodynamic characteristics of the solid ball trajectory, analyze the trajectory performance of the solid ball under various throwing forces and angles, identify the key factors that cause the solid ball to deviate from the target, and generate a solid ball throwing optimization strategy; S3: Based on the shot put optimization strategy, formulate movement adjustment guidelines, including adjusting arm angle, controlling throwing force, and mastering release timing, provide athletes with movement modification directions, and generate real-time adjustment guidance plans; S4: Based on the real-time adjustment guidance scheme, by analyzing multiple steps of the athlete's shot put action, analyzing regular deviations and random disturbances in the throwing process, identifying key factors leading to poor throwing results, and generating action abnormality signal analysis results; S5: Based on the abnormal motion signal analysis results, analyze the key features of the athlete's motion signal, use a dynamic time warping algorithm to identify feature points that deviate from the ideal motion pattern, analyze the deviations in the motion execution process, and generate motion correction feedback information; S6: Based on the movement correction feedback information, evaluate the athlete's real-time movement performance, analyze the difference between the athlete's movement and the preset ideal movement, identify key deviation points in the movement execution, adjust the content and focus of the training plan, and generate a throwing movement correction plan; S7: Based on the throwing action correction plan, monitor the athlete's action correction progress, adjust the training difficulty and goals in combination with the athlete's ability level, and generate a skill enhancement and correction plan.

[0007] As a further solution of the present invention, the aerodynamic characteristics of the solid ball trajectory include the size of air resistance, lift effect influence results, and turbulence influence information; the solid ball throwing optimization strategy includes adjusting throwing angle information, deviation factor analysis results, and environmental adaptability information; the real-time adjustment guidance plan includes arm angle adjustment results, throwing force control plan, and release timing positioning information; the abnormal action signal analysis results include regular deviation identification, random disturbance analysis, and action factors that are not conducive to throwing effects; the action correction feedback information includes deviation points from the ideal action pattern, key deviations during action execution, and recommended action modification directions; the throwing action correction plan includes targeted training content adjustment, special action practice plan, and key focus areas for action execution; the skill enhancement and correction plan includes action training difficulty level, adaptive training goals, and adjustment practice plans.

[0008] As a further solution of the present invention, based on the trajectory data of a solid ball, the air resistance and lift during the ball's motion are analyzed, and combined with the speed and throwing angle information of the solid ball, the interaction and trajectory of the solid ball with the air are simulated to generate the aerodynamic characteristics of the solid ball trajectory. Specifically, the steps are as follows: S101: Based on shot put trajectory data, repeated experiments were conducted under different environmental conditions to simulate the various climate and wind speed conditions encountered by shot put in actual competitions. The key factors affecting air resistance and lift were analyzed to obtain aerodynamic effect analysis results. S102: Reconstructing the trajectory of the shot put under various throwing forces and angles based on the aerodynamic effect analysis results and in combination with the influence of external factors such as climate and wind speed on the trajectory, and obtaining a motion trajectory record of the shot put by analyzing the trajectory differences under various conditions; S103: Based on the solid ball motion trajectory record, analyzing the deviation of the solid ball trajectory under various conditions, identifying external factors and throwing parameters that affect the solid ball trajectory deviation, and formulating the aerodynamic characteristics of the solid ball trajectory.

[0009] As a further embodiment of the present invention, based on the aerodynamic characteristics of the solid ball trajectory, the trajectory performance of the solid ball under various throwing forces and angles is analyzed, the key factors causing the solid ball to deviate from the target are identified, and the steps of generating a solid ball throwing optimization strategy are specifically as follows: S201: Based on the aerodynamic characteristics of the solid ball trajectory, simulating the trajectory and landing point of the solid ball under various throwing forces and angles, analyzing the changes in the solid ball trajectory, and generating a trajectory landing point record; S202: Analyzing the landing point deviation pattern of the solid ball based on the trajectory landing point record, comparing the ideal landing point of the solid ball with the actual landing point, identifying the throwing parameters that cause the deviation, and generating a landing point deviation analysis result; S203: Based on the landing point deviation analysis results, evaluate the impact of throwing force and angle on landing point accuracy, compare trajectory results under various throwing parameter combinations, adjust throwing force and angle, and generate a shot put throwing optimization strategy.

[0010] As a further solution of the present invention, based on the medicine ball throwing optimization strategy, a movement adjustment guide is formulated, including adjusting arm angle, controlling throwing force, and mastering release timing, to provide athletes with movement modification directions. The steps of generating a real-time adjustment guidance plan are specifically as follows: S301: Based on the shot put optimization strategy, an adjustment strategy is proposed for the athlete's arm angle and force output, the effect of the adjusted action on the change of the shot put trajectory is recorded and analyzed, and an action adjustment parameter table is generated; S302: Based on the action adjustment parameter table, analyzing the trajectory and landing point of a shot put under various environmental conditions, including wind speed and temperature, and combining the athlete's arm angle and force output data, analyzing the impact of various adjustment schemes on the throwing trajectory, and generating real-time throwing effect analysis results; S303: Based on the real-time throwing effect analysis results and combined with continuous throwing tests, the arm angle and force output strategy for shot put throwing under various environmental conditions are optimized to generate a real-time adjustment guidance plan.

[0011] As a further solution of the present invention, based on the real-time adjustment guidance scheme, by analyzing multiple steps of the athlete's shot put action, analyzing regular deviations and random disturbances in the throwing process, identifying key factors leading to poor throwing results, and generating abnormal action signal analysis results, the specific steps are: S401: Based on the real-time adjustment guidance plan, analyzing the athlete's movements under differentiated throwing conditions, including movement changes under various wind speed and temperature conditions, analyzing regularity deviations and random disturbances, and generating movement regularity deviation information; S402: Based on the movement regularity deviation information, analyzing the athlete's throwing performance under different weather conditions, capturing key factors in force control and angle adjustment, and analyzing the impact of target factors on throwing accuracy, thereby generating movement key deviation analysis results; S403: Based on the analysis results of the key deviations of the movements, corrective measures are formulated, including enhancing strength training and optimizing angle adjustment methods under various conditions. By having athletes test the adjustment plans and verify the effects in a simulated competition environment, abnormal movement signal analysis results are generated.

[0012] As a further solution of the present invention, based on the analysis results of the abnormal motion signals, the key features of the athlete's motion signals are analyzed, a dynamic time warping algorithm is used to identify feature points that deviate from the ideal motion pattern, and the deviation motions during the motion execution process are analyzed to generate motion correction feedback information. Specifically, the steps are as follows: S501: Based on the abnormal motion signal analysis results, the athlete's motion data is captured by a motion monitoring device, the speed, acceleration, and limb motion trajectory are recorded, and a dynamic time warping algorithm is used to identify key deviations between the athlete's motion and the ideal motion model to obtain motion deviation data; The dynamic time warping algorithm is based on the formula: ; Calculate the athlete's movement deviation value, where Representing time series Points in and time series Points in The minimum cumulative distance reached between Representing time series Points in and time series Points in The distance measure between It is based on point Dynamic weight function of distance metric, It is a time series The index position in It is a time series The index position in .

[0013] S502: Analyze the joint angle changes and force distribution during the movement using the movement deviation data, quantify the deviation between the movement and the ideal model, identify the key points of the movement deviation, and obtain the deviation detail analysis results; S503: Based on the deviation detail analysis results, match the action correction priority, formulate action improvement measures, including adjusting body posture and movement trajectory, and generate action correction feedback information.

[0014] As a further embodiment of the present invention, based on the movement correction feedback information, the steps of evaluating the athlete's real-time movement performance, analyzing the difference between the athlete's movement and the preset ideal movement, identifying the key deviation points in the movement execution, adjusting the content and focus of the training plan, and generating a throwing movement correction plan are specifically as follows: S601: Based on the movement correction feedback information, monitor the athlete's movement performance in real time and compare it with the ideal movement model to identify differences in the athlete's movement performance and obtain a real-time movement evaluation result; S602: Based on the real-time action evaluation results, analyzing the deviations in the throwing action execution, adjusting the training focus in combination with the athlete's physical differences, including weight, height, age, and gender, and using principal component analysis to analyze the athlete's training data and action execution deviations to obtain the athlete's action adjustment strategy; S603: Based on the athlete's movement adjustment strategy, evaluate the improvement effect of corrective measures including posture adjustment and strength training, optimize the effectiveness of movement correction, and obtain a throwing movement correction plan.

[0015] As a further embodiment of the present invention, based on the throwing action correction plan, the steps of monitoring the athlete's action correction progress, adjusting the training difficulty and goals in combination with the athlete's ability level, and generating a skill enhancement and correction plan are specifically as follows: S701: Based on the throwing action correction plan, record the athlete's throwing action, combine the athlete's heart rate and muscle activity, analyze the athlete's action data during training, and generate training progress analysis information; S702: Based on the training progress analysis information, analyze the match between the athlete and the training plan, adjust the intensity and goals of the training plan in combination with the athlete's strength level and skill maturity, and generate a training difficulty adjustment plan; S703: Based on the training difficulty adjustment plan, the intensity and frequency of the training plan are adjusted, the athlete's training progress is monitored, the adjustment effect of the training plan is evaluated, and a skill enhancement and correction plan is generated.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by simulating the interaction and trajectory of a shot put and the air, the aerodynamic characteristics of the shot put trajectory are generated, the key factors that lead to deviation from the target are identified, the optimization strategy and action adjustment guide are generated, and the real-time adjustment guidance plan is carried out. The dynamic time bending algorithm is used to analyze the abnormal action signal. By identifying the deviation between the athlete's action and the ideal model, the athlete is provided with accurate action correction feedback, the throwing action is optimized, the correction progress is monitored, and the training difficulty is adjusted. Through the in-depth analysis and real-time adjustment capabilities of the shot put trajectory and the athlete's action, the pertinence and effect of the training are improved, the risk of sports injuries is reduced, and the training plan is optimized with the support of accurate data, so that coaches can make more reasonable training decisions based on scientific data and improve the competitive level and technical skills of athletes. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the main steps of the present invention; Figure 2 This is a schematic diagram of the refinement of S1 of the present invention; Figure 3 This is a schematic diagram of the refinement of S2 of the present invention; Figure 4 This is a schematic diagram of the refinement of S3 of the present invention; Figure 5 This is a schematic diagram of the refinement of S4 of the present invention; Figure 6 This is a schematic diagram of the refinement of S5 of the present invention; Figure 7 This is a schematic diagram of the refinement of S6 of the present invention; Figure 8 This is a detailed schematic diagram of S7 of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0020] Example 1 See also Figure 1 The present invention provides a technical solution, a solid ball test correction method based on artificial intelligence, comprising the following steps: S1: Based on the trajectory data of the solid ball, the air resistance and lift during the ball's motion are analyzed. Combined with the speed and throwing angle information of the solid ball, the interaction and trajectory of the solid ball with the air are simulated to generate the aerodynamic characteristics of the solid ball trajectory. S2: Based on the aerodynamic characteristics of the solid ball trajectory, analyze the trajectory performance of the solid ball under various throwing forces and angles, identify the key factors that cause the solid ball to deviate from the target, and generate a solid ball throwing optimization strategy; S3: Based on the shot put optimization strategy, develop movement adjustment guidelines, including adjusting arm angle, controlling throwing force, and mastering release timing, provide athletes with movement modification directions, and generate real-time adjustment guidance plans; S4: Based on the real-time adjustment guidance plan, by analyzing the multiple steps of the athlete's shot put action, analyzing the regular deviations and random disturbances in the throwing process, identifying the key factors leading to poor throwing results, and generating abnormal motion signal analysis results; S5: Based on the results of abnormal movement signal analysis, analyze the key features of the athlete's movement signals, use the dynamic time warping algorithm to identify the feature points that deviate from the ideal movement pattern, analyze the deviation movements during the movement execution process, and generate movement correction feedback information; S6: Based on the feedback from the corrective action, evaluate the athlete's real-time performance, analyze the differences between the athlete's action and the preset ideal action, identify key deviation points in the action execution, adjust the content and focus of the training plan, and generate a corrective action plan for the throwing action; S7: Based on the throwing action correction plan, monitor the athlete's action correction progress, adjust the training difficulty and goals based on the athlete's ability level, and generate skill enhancement and correction plans.

[0021] The aerodynamic characteristics of the shot put trajectory include the size of air resistance, the impact of lift effect, and turbulence impact information. The shot put optimization strategy includes adjusting the throwing angle information, deviation factor analysis results, and environmental adaptability information. The real-time adjustment guidance plan includes arm angle adjustment results, throwing force control plan, and release timing positioning information. The abnormal movement signal analysis results include regular deviation identification, random disturbance analysis, and movement factors that are not conducive to throwing effects. Movement correction feedback information includes deviation points from the ideal movement pattern, key deviations during movement execution, and recommended movement modification directions. The throwing movement correction plan includes targeted training content adjustment, special movement practice plan, and key focus areas for movement execution. The skill enhancement and correction plan includes movement training difficulty level, adaptive training goals, and adjustment of practice plans.

[0022] See also Figure 2 Based on the solid ball trajectory data, the air resistance and lift during the ball's motion are analyzed. Combined with the speed and throwing angle information of the solid ball, the interaction and trajectory of the solid ball with the air are simulated. The specific steps for generating the aerodynamic characteristics of the solid ball trajectory are as follows: S101: Based on shot-ball trajectory data, repeated experiments were conducted under different environmental conditions to simulate the various climate and wind speed conditions encountered by shot-balls in actual competitions. The key factors affecting air resistance and lift were analyzed, and the specific process for obtaining aerodynamic effect analysis results was as follows; Based on the trajectory data of shot put balls, experiments were repeated under differentiated environmental conditions to simulate the various climate and wind speed conditions encountered by shot put balls in actual competitions. The key factors affecting air resistance and lift were analyzed, and the aerodynamic effect analysis results were obtained. Computational fluid dynamics software was used to set the simulation environment parameters, including climate conditions, wind speed, throwing force and angle. The Navier-Stokes equation solver was used to calculate the air resistance and lift of the shot put balls under differentiated conditions, generating the aerodynamic effect analysis results.

[0023] S102: Based on the results of the aerodynamic effect analysis and the influence of external factors such as climate and wind speed on the trajectory, the trajectory of the shot put under various throwing forces and angles is reconstructed. By analyzing the trajectory differences under various conditions, the specific process of obtaining the trajectory record of the shot put is as follows; Based on the results of aerodynamic effect analysis and combined with the influence of external factors such as climate and wind speed on the trajectory, the trajectory of the solid ball under various throwing forces and angles was reconstructed. The machine learning algorithm support vector machine was used for trajectory prediction. The kernel function was set to Gaussian radial basis function. The training data set included environmental conditions and throwing parameters to generate the trajectory record of the solid ball.

[0024] S103: Based on the shot ball trajectory records, analyze the deviation of the shot ball trajectory under various conditions, identify the external factors and throwing parameters that affect the shot ball trajectory deviation, and formulate the specific process of the aerodynamic characteristics of the shot ball trajectory; Based on the trajectory records of solid balls, the deviation of solid ball trajectories under various conditions was analyzed, the external factors and throwing parameters that affect the deviation of solid ball trajectories were identified, and the aerodynamic characteristics of solid ball trajectories were formulated. Linear regression analysis was used to determine the relationship between trajectory deviation and external factors and throwing parameters. The independent variables were set as climate conditions and throwing parameters, and the dependent variable was trajectory deviation. The least squares method was used to estimate the parameters and generate the aerodynamic characteristics of solid ball trajectories.

[0025] See also Figure 3 Based on the aerodynamic characteristics of the solid ball trajectory, the trajectory performance of the solid ball under various throwing forces and angles is analyzed, and the key factors that cause the solid ball to deviate from the target are identified. The specific steps for generating the solid ball throwing optimization strategy are as follows: S201: Based on the aerodynamic characteristics of the solid ball trajectory, simulate the trajectory and landing point of the solid ball under various throwing forces and angles, analyze the changes in the solid ball trajectory, and generate the trajectory landing point record. The specific process is as follows; Based on the aerodynamic characteristics of the solid ball trajectory, the trajectory and landing point of the solid ball under various throwing forces and angles are simulated, the changes in the solid ball trajectory are analyzed, and the trajectory landing point records are generated. The dynamic system simulation MATLAB Simulink environment is applied to construct a solid ball motion model. The throwing force and angle are input, the trajectory and landing point position are calculated, and the trajectory landing point records are generated.

[0026] S202: Analyze the landing point deviation pattern of the solid ball based on the trajectory landing point record, compare the ideal landing point of the solid ball with the actual landing point, identify the throwing parameters that cause the deviation, and generate the landing point deviation analysis results. The specific process is as follows: Based on the trajectory landing point records, the landing point deviation pattern of the shot put is analyzed, the ideal landing point of the shot put is compared with the actual landing point, the throwing parameters that cause the deviation are identified, and the landing point deviation analysis results are generated. The cluster analysis K-means algorithm is used to analyze the landing point deviation pattern, the number of clusters is set, and the landing point deviation is measured using Euclidean distance to generate the landing point deviation analysis results.

[0027] S203: Based on the landing point deviation analysis results, the impact of throwing force and angle on landing point accuracy is evaluated, trajectory results under various throwing parameter combinations are compared, and the throwing force and angle are adjusted to generate a shot put throwing optimization strategy. The specific process is as follows: Based on the results of landing point deviation analysis, the influence of throwing force and angle on landing point accuracy is evaluated, the trajectory results under various throwing parameter combinations are compared, the throwing force and angle are adjusted, and the shot put throwing optimization strategy is generated. A genetic algorithm is used, and the fitness function is set as landing point accuracy, and the variables are throwing force and angle. Crossover and mutation operations are applied to capture the optimal parameter combination to generate the shot put throwing optimization strategy.

[0028] See also Figure 4 Based on the shot put optimization strategy, a movement adjustment guide is developed, including adjusting arm angle, controlling throwing force, and mastering release timing, providing athletes with movement modification directions. The specific steps for generating a real-time adjustment guidance plan are as follows: S301: Based on the shot put optimization strategy, an adjustment strategy is proposed for the athlete's arm angle and force output, and the impact of the adjusted action on the change of the shot put trajectory is recorded and analyzed. The specific process of generating the action adjustment parameter table is as follows; Based on the shot put optimization strategy, an adjustment strategy is proposed for the athlete's arm angle and force output. The impact of the adjusted action on the change of the shot put trajectory is recorded and analyzed. The motion capture technology Vicon system is used to capture the athlete's throwing action, and markers are set at key limb positions. The changes in arm angle and force output are analyzed through the Vicon system software to generate a movement adjustment parameter table.

[0029] S302: Based on the action adjustment parameter table, the trajectory and landing point of the actual shot put under various environmental conditions, including wind speed and temperature, are analyzed. In combination with the athlete's arm angle and force output data, the effects of various adjustment schemes on the throwing trajectory are analyzed to generate real-time throwing effect analysis results. The specific process is as follows: Based on the action adjustment parameter table, the trajectory and landing point of actual shot put under various environmental conditions, including wind speed and temperature, were analyzed. Combined with the athlete's arm angle and force output data, ANSYS Fluent was used to set environmental parameters to simulate actual throwing conditions. The athlete's arm angle and force output data were input into the model to generate real-time throwing effect analysis results.

[0030] S303: Based on the real-time throwing effect analysis results and combined with continuous throwing tests, the specific process of optimizing the arm angle and force output strategy for shot put throwing under various environmental conditions and generating a real-time adjustment guidance plan is as follows; Based on the results of real-time throwing effect analysis and combined with continuous throwing tests, the arm angle and force output strategy of shot put throwing under various environmental conditions are optimized. A multivariable optimization algorithm is applied, and the fitness function is set to minimize the landing point deviation. The algorithm parameters including crossover rate and mutation rate are adjusted to generate a real-time adjustment guidance plan.

[0031] See also Figure 5Based on the real-time adjustment guidance plan, the steps of analyzing the multiple steps of the athlete's shot put action are analyzed to analyze the regular deviations and random disturbances in the throwing process, identify the key factors leading to poor throwing results, and generate the abnormal motion signal analysis results. S401: Based on the real-time adjustment guidance plan, the specific process of analyzing the athlete's movements under different throwing conditions, including the changes in movements under various wind speed and temperature conditions, analyzing regularity deviations and random disturbances, and generating movement regularity deviation information is as follows; Based on real-time adjustment of guidance plans, the athletes' movements under differentiated throwing conditions are analyzed, including changes in movements under various wind speed and temperature conditions. The autoregressive moving average model is applied to analyze the movement time series data, identify regular deviations and random disturbances, and generate movement regularity deviation information.

[0032] S402: Based on the movement regularity deviation information, analyze the athlete's throwing performance under different weather conditions, capture the key factors in force control and angle adjustment, and analyze the impact of target factors on throwing accuracy. The specific process for generating the key movement deviation analysis results is as follows: Based on the deviation information of movement regularity, the throwing performance of athletes under differentiated weather conditions was analyzed to capture the key factors in force control and angle adjustment, and to analyze the impact of target factors on throwing accuracy. Partial least squares regression analysis was used, and the model variables were set as force control and angle adjustment data to generate the analysis results of key deviations in movement.

[0033] S403: Based on the results of the key deviation analysis, corrective measures are formulated, including enhancing strength training and optimizing angle adjustment methods under various conditions. The specific process of generating abnormal movement signal analysis results is to have athletes test the adjustment plans and verify the effects in a simulated competition environment. Based on the results of the key deviation analysis of movements, corrective measures are formulated, including enhancing strength training and optimizing angle adjustment methods under various conditions. Athletes are asked to test the adjustment plans and verify the effects in a simulated competition environment. Machine learning classification algorithms, specifically random forests, are applied to analyze abnormal movement signals of athletes. Classifier parameters, including the number of trees and maximum depth, are set to generate analysis results of abnormal movement signals.

[0034] See also Figure 6 Based on the results of abnormal motion signal analysis, the key features of the athlete's motion signal are analyzed. The dynamic time warping algorithm is used to identify the feature points that deviate from the ideal motion pattern. The deviation motions in the motion execution process are analyzed. The specific steps for generating motion correction feedback information are as follows: S501: Based on the results of the abnormal motion signal analysis, the athlete's motion data is captured by the motion monitoring device, the speed, acceleration, and limb motion trajectory are recorded, and the dynamic time warping algorithm is used to identify the key deviations between the athlete's motion and the ideal motion model. The specific process for obtaining the motion deviation data is as follows; Based on the results of abnormal motion signal analysis, the athlete's motion data is captured through motion monitoring equipment, and the speed, acceleration, and limb movement trajectory are recorded. A high-precision inertial measurement unit and optical motion capture system are used. The data acquisition frequency is set to 1000Hz and the sensor sensitivity is set to high-precision mode. By combining the high-precision inertial measurement unit and optical motion capture system to continuously capture the athlete's speed, acceleration, and limb movement trajectory, data fusion technology, specifically the Kalman filter algorithm, is applied to process the sensor data to reduce noise and improve the accuracy of the motion data, thereby obtaining motion deviation data.

[0035] Dynamic time warping algorithm, according to the formula: ;

[0036] Calculate the athlete's movement deviation value, where Representing time series Points in and time series Points in The minimum cumulative distance between the two time series from the beginning to the point The similarity of Representing time series Points in and time series Point in The distance metric between two points is used to measure the instantaneous difference between them. It is based on point A dynamic weighting function for the distance metric that takes into account specific physical properties or technical difficulty of the action and is used to adjust to ensure that different movement characteristics are properly considered in the movement analysis. It is a time series The index position in the sequence A specific time point or action state in It is a time series The index position in the sequence A specific point in time or action state in a process.

[0037] The specific implementation process of the improved formula is as follows: By calculating the points in the two time series and point Distance metric between , using the weight function Adjust the distance metric to take into account the physical characteristics and technical difficulty of the action and calculate the arrival point The minimum cumulative distance , by considering the point and its predecessor , , The minimum cumulative distance of the action point is calculated and the weighted distance of the current point is added. By keeping the time series aligned and combining multiple characteristics of the action, the action deviation analysis results are formulated.

[0038] S502: Using the movement deviation data, analyzing the changes in joint angles and force distribution during the movement, quantifying the deviation between the movement and the ideal model, identifying the key points of movement deviation, and obtaining the detailed deviation analysis results. The specific process is as follows: Using movement deviation data, we analyze changes in joint angles and force distribution during movement. We use the kinematic analysis and dynamics calculation software OpenSim to import movement deviation data and set up a detailed biomechanical model. Through OpenSim, we conduct in-depth analysis of joint angles and force distribution. Using simulation technology, we quantify the specific deviations between the athlete's movements and the ideal model, identify subtle deviations in movement and potential causes, and obtain detailed analysis results of the deviations.

[0039] S503: Based on the deviation detail analysis results, the action correction priority is matched, and action improvement measures are formulated, including adjusting body posture and movement trajectory, and generating action correction feedback information. The specific process is as follows; Based on the results of deviation detail analysis, the action correction priority is matched and action improvement measures are formulated. The gradient boosting tree algorithm is used to analyze the deviation details, and the action correction measures are prioritized and ranked through the gradient boosting tree algorithm. Combined with the biomechanical feedback of the movement and considering the individual differences of athletes, action correction feedback information is generated.

[0040] See also Figure 7 Based on the feedback from the corrective action, the athlete's real-time performance is evaluated, the differences between the athlete's action and the preset ideal action are analyzed, the key deviation points in the action execution are identified, and the content and focus of the training plan are adjusted. The specific steps for generating a corrective action plan for throwing are as follows: S601: Based on the movement correction feedback information, the specific process of monitoring the athlete's movement performance in real time and comparing it with the ideal movement model to identify the differences in the athlete's movement performance and obtain the real-time movement evaluation results is as follows; Based on movement correction feedback information, the athlete's training movement performance is monitored in real time and compared with the ideal movement model. The real-time feedback system and deep convolutional neural network are applied to train the model to identify and analyze subtle differences in the athlete's movement performance. Through high-speed cameras and the real-time data processing platform TensorFlow, the athlete's movement is monitored and analyzed in real time, providing instant feedback and obtaining real-time movement evaluation results.

[0041] S602: Based on the real-time action evaluation results, analyze the deviations in the throwing action execution. Taking into account the physical differences of the athletes, including weight, height, age, and gender, adjust the training focus. Principal component analysis is used to analyze the athlete's training data and action execution deviations to obtain the specific process of the athlete's action adjustment strategy. Based on the results of real-time motion evaluation, the deviations in throwing action execution are analyzed. Combined with the physical differences of athletes, random forest regression analysis is applied, considering the multi-dimensional influence of weight, height, age, and gender variables. The random forest algorithm is used to identify the physical characteristics and training focus associated with motion deviations, and the athlete's motion adjustment strategy is obtained.

[0042] S603: Based on the athlete's movement adjustment strategy, evaluate the improvement effect of corrective measures including posture adjustment and strength training, optimize the effectiveness of movement correction, and obtain the specific process of throwing movement correction plan; Based on the athletes' movement adjustment strategies, the improvement effects of corrective measures including posture adjustment and strength training were evaluated. Multivariate analysis of variance combined with a logistic regression model was used to analyze the comprehensive impact of posture adjustment and strength training on athletes' movement improvements. Through detailed statistical analysis and machine learning prediction models, the effectiveness of corrective measures and their specific impact on athletic performance were evaluated, and a throwing movement correction plan was obtained.

[0043] See also Figure 8 Based on the throwing action correction plan, the steps to monitor the athlete's action correction progress, adjust the training difficulty and goals based on the athlete's ability level, and generate skill enhancement and correction plans are as follows: S701: Based on the throwing action correction plan, the athlete's throwing action is recorded, and the athlete's heart rate and muscle activity are combined to analyze the athlete's action data during training to generate training progress analysis information. The specific process is as follows: Based on the throwing action correction plan, the athlete's throwing action is recorded. Combined with the athlete's heart rate and muscle activity, biofeedback equipment and heart rate monitors are used. The data collection frequency is set to multiple samples per second. The muscle action potential is captured through the biofeedback equipment, and the heart rate monitor records the heart rate changes during training. Data synchronization processing technology, specifically time series analysis, is applied to conduct a comprehensive analysis of the action data, heart rate and muscle activity to generate training progress analysis information.

[0044] S702: Based on the training progress analysis information, analyze the match between the athlete and the training plan, adjust the intensity and goals of the training plan in combination with the athlete's strength level and skill maturity, and generate a training difficulty adjustment plan. The specific process is as follows; Based on training progress analysis information, the match between athletes and training plans is analyzed. Combined with the athletes' strength level and skill maturity, an adaptive neuro-fuzzy inference system is used. The input includes training progress analysis information and athletes' baseline ability data. The intensity and goals of the training plan are adjusted through the adaptive neuro-fuzzy inference system to match the athletes' current training needs and ability levels, and a training difficulty adjustment plan is generated.

[0045] S703: Based on the training difficulty adjustment plan, the specific process of increasing the intensity and frequency of the training plan, monitoring the athlete's training progress, evaluating the effect of the training plan adjustment, and generating a skill enhancement and correction plan is as follows; Based on the training difficulty adjustment plan, increase the intensity and frequency of the adjusted training plan, monitor the athletes' training progress, evaluate the adjustment effect of the training plan, apply the dynamic performance monitoring system, use real-time data capture technology and advanced analysis models to track the adjustment of training intensity and the athlete's response, evaluate the skill improvement and movement correction effect through the dynamic performance monitoring system, and generate skill enhancement and correction plans.

[0046] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A solid ball test correction method based on artificial intelligence, characterized in that: The following steps are involved: Based on the trajectory data of the solid ball, the interaction and trajectory of the solid ball with the air are simulated to generate the aerodynamic characteristics of the solid ball trajectory; Based on the aerodynamic characteristics of the solid ball trajectory, identifying the key factors that cause the solid ball to deviate from the target, and generating a solid ball throwing optimization strategy; Based on the shot put optimization strategy, a movement adjustment guide is formulated to provide athletes with movement modification directions and generate a real-time adjustment guidance plan; Based on the real-time adjustment guidance scheme, regular deviations and random disturbances in the throwing process are analyzed to identify key factors leading to poor throwing results and generate abnormal motion signal analysis results; Based on the abnormal motion signal analysis results, analyzing key features of the athlete's motion signal, using a dynamic time warping algorithm to identify feature points that deviate from the ideal motion pattern, and generating motion correction feedback information; Based on the movement correction feedback information, the athlete's real-time movement performance is evaluated, the difference between the athlete's movement and the preset ideal movement is analyzed, and a throwing movement correction plan is generated; Based on the throwing action correction plan, the athlete's action correction progress is monitored, and the training difficulty and goals are adjusted in combination with the athlete's ability level to generate a skill enhancement and correction plan.

2. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: The aerodynamic characteristics of the solid ball trajectory include the size of air resistance, lift effect influence results, and turbulence influence information. The solid ball throwing optimization strategy includes adjusting throwing angle information, deviation factor analysis results, and environmental adaptability information. The real-time adjustment guidance plan includes arm angle adjustment results, throwing force control plan, and release timing positioning information. The abnormal action signal analysis results include regular deviation identification, random disturbance analysis, and action factors that are not conducive to throwing effects. The action correction feedback information includes deviation points from the ideal action pattern, key deviations during action execution, and recommended action modification directions. The throwing action correction plan includes targeted training content adjustment, special action practice plan, and key focus areas for action execution. The skill enhancement and correction plan includes action training difficulty level, adaptive training goals, and adjustment practice plans.

3. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the solid ball trajectory data, the steps to simulate the interaction and trajectory of the solid ball with the air and generate the aerodynamic characteristics of the solid ball trajectory are as follows: Based on shot-ball trajectory data, repeated experiments under different environmental conditions simulated the various climate and wind speed conditions encountered by shot-balls in actual competitions, analyzed the key factors affecting air resistance and lift, and obtained aerodynamic effect analysis results; Based on the aerodynamic effect analysis results, combined with the influence of external factors such as climate and wind speed on the trajectory, the trajectory of the solid ball under various throwing forces and angles is reconstructed, and the trajectory record of the solid ball is obtained by analyzing the trajectory differences under various conditions; Based on the solid ball motion trajectory record, the deviation of the solid ball trajectory under various conditions is analyzed, the external factors and throwing parameters that affect the deviation of the solid ball trajectory are identified, and the aerodynamic characteristics of the solid ball trajectory are formulated.

4. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the aerodynamic characteristics of the solid ball trajectory, the key factors causing the solid ball to deviate from the target are identified, and the steps for generating the solid ball throwing optimization strategy are specifically as follows: Based on the aerodynamic characteristics of the solid ball trajectory, the trajectory and landing point of the solid ball under various throwing forces and angles are simulated, the trajectory changes of the solid ball are analyzed, and the trajectory landing point record is generated; Analyzing the landing point deviation pattern of the shot put based on the trajectory landing point record, comparing the ideal landing point of the shot put with the actual landing point, identifying the throwing parameters that cause the deviation, and generating a landing point deviation analysis result; Based on the landing point deviation analysis results, the impact of throwing force and angle on landing point accuracy is evaluated, the trajectory results under various throwing parameter combinations are compared, the throwing force and angle are adjusted, and an optimization strategy for shot put throwing is generated.

5. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the shot put optimization strategy, a movement adjustment guide is formulated to provide athletes with movement modification directions. The specific steps for generating a real-time adjustment guidance plan are as follows: Based on the shot put optimization strategy, an adjustment strategy is proposed for the athlete's arm angle and force output, the effect of the adjusted action on the change of the shot put trajectory is recorded and analyzed, and an action adjustment parameter table is generated; Based on the action adjustment parameter table, the trajectory and landing point of the actual thrown solid ball under various environmental conditions, including wind speed and temperature, are analyzed. In combination with the athlete's arm angle and force output data, the effects of various adjustment schemes on the throwing trajectory are analyzed to generate real-time throwing effect analysis results; Based on the real-time throwing effect analysis results and combined with continuous throwing tests, the arm angle and force output strategy for shot put throwing under various environmental conditions are optimized, and a real-time adjustment guidance plan is generated.

6. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the real-time adjustment guidance scheme, the steps of analyzing regular deviations and random disturbances in the throwing process, identifying key factors leading to poor throwing results, and generating abnormal motion signal analysis results are as follows: Based on the real-time adjustment guidance scheme, analyzing the athlete's movements under differentiated throwing conditions, including movement changes under various wind speed and temperature conditions, analyzing regularity deviations and random disturbances, and generating movement regularity deviation information; Based on the movement regularity deviation information, the throwing performance of athletes under different weather conditions is analyzed to capture key factors in force control and angle adjustment, and the impact of target factors on throwing accuracy is analyzed to generate key movement deviation analysis results; Based on the analysis results of the key deviations in the movements, corrective measures for the movements are formulated, including enhancing strength training and optimizing angle adjustment methods under various conditions. By having athletes test the adjustment plans and verify the effects in a simulated competition environment, abnormal movement signal analysis results are generated.

7. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the abnormal motion signal analysis results, the key features of the athlete's motion signal are analyzed, a dynamic time warping algorithm is used to identify feature points that deviate from the ideal motion pattern, and motion correction feedback information is generated. The specific steps are: Based on the analysis results of the abnormal motion signals, the athlete's motion data is captured by a motion monitoring device, the speed, acceleration, and limb motion trajectory are recorded, and a dynamic time warping algorithm is used to identify key deviations between the athlete's motion and the ideal motion model to obtain motion deviation data; The dynamic time warping algorithm is based on the formula: ； Calculate the athlete's movement deviation value, where Representing time series Point in and time series Point in The minimum cumulative distance reached between Representing time series Point in and time series Point in The distance measure between It is based on point Dynamic weight function of distance metric, It is a time series The index position in It is a time series The index position in ; Utilizing the movement deviation data, analyzing the joint angle changes and force distribution during the movement, quantifying the deviation between the movement and the ideal model, identifying the key points of movement deviation, and obtaining detailed deviation analysis results; Based on the detailed analysis results of the deviations, the action correction priorities are matched and action improvement measures are formulated, including adjusting body posture and motion trajectory, and generating action correction feedback information.

8. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the motion correction feedback information, the steps of evaluating the athlete's real-time motion performance, analyzing the difference between the athlete's motion and the preset ideal motion, and generating a throwing motion correction plan are as follows: Based on the movement correction feedback information, the athlete's movement performance is monitored in real time and compared with the ideal movement model, the difference in the athlete's movement performance is identified, and a real-time movement evaluation result is obtained; Based on the real-time action evaluation results, analyzing the deviations in throwing action execution, adjusting the training focus based on the athletes' physical differences, including weight, height, age, and gender, and using principal component analysis to analyze the athletes' training data and action execution deviations to derive the athletes' action adjustment strategies; Based on the athlete's movement adjustment strategy, the improvement effect of corrective measures including posture adjustment and strength training is evaluated, the effectiveness of movement correction is optimized, and a throwing movement correction plan is obtained.

9. The artificial intelligence-based solid ball test correction method according to claim 1, characterized in that: Based on the throwing action correction plan, the steps of monitoring the athlete's action correction progress, adjusting the training difficulty and goals based on the athlete's ability level, and generating a skill enhancement and correction plan are as follows: Based on the throwing action correction plan, the athlete's throwing action is recorded, and the athlete's action data during training is analyzed in combination with the athlete's heart rate and muscle activity to generate training progress analysis information; Based on the training progress analysis information, analyzing the match between the athlete and the training plan, adjusting the intensity and goals of the training plan in combination with the athlete's strength level and skill maturity, and generating a training difficulty adjustment plan; Based on the training difficulty adjustment plan, the intensity and frequency of the training plan are adjusted, the athlete's training progress is monitored, the adjustment effect of the training plan is evaluated, and a skill enhancement and correction plan is generated.

Images