Physical training plan intelligent generation and management method

Abstract

The invention relates to the technical field of data processing, in particular to a physical training plan intelligent generation and management method. Comprising the steps that physiological data, athletic performance data, external environment data and health state data of an athlete are obtained and serve as original multi-dimensional data, the original multi-dimensional data are preprocessed, and preprocessed multi-dimensional data are obtained; performing feature extraction to obtain preliminary feature data; performing enhancement processing to obtain feature data after enhancement processing, and performing preliminary analysis in combination with a training target to generate a preliminary training plan; in the training process of the preliminary training plan, real-time data of the athletes are obtained, a dynamic adjustment algorithm based on multi-dimensional data analysis and self-adaptive feedback optimization is used for analysis, and quantitative feedback is obtained; and dynamically adjusting and optimizing the preliminary training plan to obtain an optimal training plan. The technical problems that related data processing of athletes is not accurate and comprehensive enough, and the real-time performance of the data is poor are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for intelligently generating and managing a sports training plan. Background Art

[0002] At present, with the development of sports technology, the training mode of athletes has gradually changed from traditional empirical methods to data-driven personalized training methods. Traditional training methods often rely on the experience and intuition of coaches, and usually ignore the physical reactions, psychological state and external environment of athletes when designing training plans. This method cannot reflect the training effect and physical state of athletes in real time, which may lead to a mismatch between the intensity of training and the actual needs of athletes, thus affecting the performance and health of athletes.

[0003] In order to improve training results, many sports teams have begun to rely on various sensors and wearable devices, such as heart rate monitors, sports trackers, etc. These devices can collect athletes' physiological data in real time, such as heart rate, breathing rate, exercise intensity, etc. Through these physiological data, athletes and coaches can better understand the athletes' physiological state and make corresponding adjustments to training. However, the data generated by these devices are usually only a single physiological parameter, lacking comprehensive analysis of multiple factors such as sports performance, health status, external environment, etc., so it is difficult to provide completely personalized training suggestions.

[0004] At the same time, the existing intelligent generation and management methods of sports training plans have the following technical problems: the processing of athlete-related data is not accurate or comprehensive enough, and the data real-time performance is poor. Summary of the invention

[0005] The present invention provides a method for intelligently generating and managing a sports training plan, so as to solve the technical problems that the processing of athlete-related data is not accurate and comprehensive enough and the real-time performance of the data is poor.

[0006] A method for intelligently generating and managing a sports training plan of the present invention specifically includes the following technical solutions: A method for intelligently generating and managing a sports training plan comprises the following steps: S1. Acquire the athlete's physiological data, sports performance data, external environment data and health status data and use them as original multi-dimensional data, pre-process the original multi-dimensional data to obtain pre-processed multi-dimensional data; perform feature extraction on the pre-processed multi-dimensional data to obtain preliminary feature data; perform enhancement processing on the preliminary feature data to obtain enhanced feature data, and perform preliminary analysis in combination with training goals to generate a preliminary training plan; S2. During the training process according to the preliminary training plan, the real-time data of the athletes are monitored and analyzed using a dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization to obtain quantitative feedback; based on the quantitative feedback, the preliminary training plan is dynamically adjusted and optimized to obtain the best training plan.

[0007] Preferably, the S1 specifically includes: The feature adaptive enhancement formula is introduced to enhance the preliminary feature data to obtain the enhanced feature data. The specific implementation formula is: , in, It is Feature data after enhancement processing; It is Preliminary characteristic data; It is The weight coefficient of the preliminary feature data; It is Preliminary characterization data and The weighted relationship coefficient between the preliminary feature data; It is the data describing the preliminary characteristics and Function of nonlinear relationship between It is Preliminary characteristic data; It is Preliminary characterization data and The influence of the square difference between the preliminary feature data on the enhancement effect; It is Preliminary characterization data and The square term of the difference between the preliminary feature data; is the coefficient of the logarithmic transformation term; is the exponential decay coefficient; It is an exponential function operation; It is Time decay factor of the preliminary characteristic data; is a time variable; It is The coefficients of the feature matrix transformation corresponding to the preliminary feature data; is a matrix element, indicating the Preliminary characterization data and The correlation between the preliminary feature data; It is Preliminary feature data.

[0008] Preferably, the S2 specifically includes: In the process of realizing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the real-time data of the athletes are subjected to standardized preprocessing to obtain the real-time data after standardized preprocessing; and the real-time data after standardized preprocessing is analyzed in real time by the weighted comprehensive analysis method to obtain the comprehensive feedback value.

[0009] Preferably, the S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the comprehensive feedback value enters the dynamic adjustment stage to adjust the magnitude and direction of the initial training plan.

[0010] Preferably, the S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multidimensional data analysis and adaptive feedback optimization, the adaptive adjustment amount calculation formula is introduced to calculate the adaptive adjustment amount of the preliminary training plan, and dynamic optimization is performed based on the deviation between the feedback value of the physiological index and the target feedback value, as well as the adjustment intensity of the preliminary training plan.

[0011] Preferably, the S2 specifically includes: The calculation formula of the adaptive adjustment amount is: , in, is the adaptive adjustment of the training plan; is the adjustment factor; is the total number of physiological indicators contained in the athlete's standardized pre-processed real-time data; It is The evaluation function of the physiological index is Feedback value of physiological indicators; It is Target feedback value of each physiological index; It is an exponential function operation; is the attenuation coefficient; It’s training time; It is the weight factor for adjusting the gap between the comprehensive feedback value and the target feedback value; Represents the comprehensive feedback value during the training process; Represents the target feedback value during training.

[0012] Preferably, the S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the training intensity is optimized, and the training intensity optimization calculation formula is introduced to calculate the optimized training intensity. The specific implementation formula is: , in, is the optimized training intensity; is the weight factor for training intensity adjustment; is the training effectiveness adjustment factor; It is an indicator of training effectiveness; is the heart rate adjustment factor; is the current heart rate; is the target heart rate; It is a state of psychological stress; It is the state of maximum psychological stress; is the comprehensive feedback gap adjustment factor; It is an exponential function operation.

[0013] Preferably, the S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the adaptive adjustment amount and the optimized training intensity are used as input to enter the quantitative feedback calculation stage to obtain quantitative feedback.

[0014] The beneficial effects of the technical solution of the present invention are: By collecting and preprocessing the original multi-dimensional data, preprocessed multi-dimensional data is obtained, and features are extracted from the preprocessed multi-dimensional data to obtain preliminary feature data; and the preliminary feature data is enhanced to obtain enhanced feature data, a personalized training plan can be formulated according to the specific physiological and health status of each athlete, avoiding a one-size-fits-all standardized plan, making the training more in line with individual differences and improving the overall training effect; the preliminary feature data is enhanced by designing a feature adaptive enhancement formula, and the various parameters in the formula can capture the nonlinear relationship between each preliminary feature data and improve the expressiveness of the preliminary feature data; by monitoring the real-time data of the athletes, the fatigue condition or health abnormality of the athletes can be discovered at any time, and the training intensity can be adjusted in time to avoid overtraining and reduce the risk of sports injuries. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the method for intelligently generating and managing a sports training plan according to the present invention. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] The specific scheme of the method for intelligently generating and managing a sports training plan provided by the present invention is described in detail below with reference to the accompanying drawings.

[0019] Refer to the attached Figure 1 , which shows a flow chart of a method for intelligently generating and managing a sports training plan provided by an embodiment of the present invention, the method comprising the following steps: S1. Acquire the athlete's physiological data, sports performance data, external environment data and health status data, and use them as original multi-dimensional data, pre-process the original multi-dimensional data to obtain pre-processed multi-dimensional data; perform feature extraction on the pre-processed multi-dimensional data to obtain preliminary feature data; perform enhancement processing on the preliminary feature data to obtain enhanced feature data, and perform preliminary analysis in combination with training goals to generate a preliminary training plan; The athletes' physiological data, including heart rate, blood oxygen saturation, body temperature, respiratory rate, cadence, stride, etc., are collected through smart sensors such as heart rate monitors, gait analyzers, smart watches, sports shoes, etc.; the athletes' sports performance data in training, such as exercise duration, exercise intensity, movement quality, exercise speed, exercise acceleration, etc., are collected through existing sports tracking equipment; at the same time, the athletes' external environment data, such as temperature, humidity, air quality, etc., are obtained through environmental sensors; and the athletes' health status data, such as weight, diet, sleep, etc., are obtained; the above-obtained data are used as original multi-dimensional data, and the original multi-dimensional data are pre-processed such as data cleaning, data noise reduction, data standardization and normalization, data unified dimension processing, etc., to obtain pre-processed multi-dimensional data. The technical means used in the above pre-processing are well known to technicians in this field and will not be elaborated here.

[0020] Furthermore, the existing feature engineering technology is used to extract features from the preprocessed multi-dimensional data to obtain preliminary feature data. For example, time series analysis is used to extract feature data such as the athlete's recovery rate and fatigue index from the heart rate data; and indicators such as stride stability and step frequency change rate are extracted from gait analysis. The feature adaptive enhancement formula is introduced to enhance the preliminary feature data. The formula is as follows: , in, It is Feature data after enhancement processing; It is Preliminary characteristic data; It is The weight coefficient of the preliminary feature data is determined by expert experience; It is Preliminary characterization data and The weighted relationship coefficient between two different preliminary feature data reflects the strength of the mutual influence between two different preliminary feature data and is determined by experimental method; It is the data describing the preliminary characteristics and The nonlinear relationship between the functions is a function of the feature interaction model established according to the specific task requirements through expert experience; It is Preliminary characteristic data; It is Preliminary characterization data and The influence of the square difference between the preliminary feature data on the enhancement effect is used to capture the nonlinear difference between different preliminary feature data, which is determined by experimental method; It is Preliminary characterization data and The square term of the difference between the two preliminary feature data is used to enhance the influence of the large difference between the two preliminary feature data; is the coefficient of the logarithmic transformation term, which is used to adjust the influence of the logarithmic transformation on the preliminary feature data during the enhancement process and is determined according to the expert experience method; is the exponential decay coefficient, which is used to adjust the effect of the initial feature data decaying over time and is determined based on the expert experience method; It is an exponential function operation; It is The time decay factor of the preliminary characteristic data determines the The speed at which a preliminary characteristic data decays over time. A larger value means that the influence of the preliminary characteristic data decreases rapidly. This is determined based on existing physiological principles. is a time variable, indicating the The trend of the preliminary characteristic data over time; It is The coefficients of the feature matrix transformation corresponding to the preliminary feature data are used to adjust the influence of the feature matrix transformation in the enhancement process and are determined by experimental method; is a matrix element, indicating the Preliminary characterization data and The correlation between the preliminary feature data usually reflects the synergy between multiple features and is calculated using the existing multiple regression method. It reflects the degree of influence of different characteristics on a certain target; It is Preliminary feature data.

[0021] Furthermore, based on the enhanced feature data, a preliminary analysis is conducted in combination with the training objectives, which include: endurance improvement, strength enhancement, muscle recovery, flexibility improvement and other dimensions, so as to generate a preliminary training plan; the specific implementation content includes: first, by constructing a multi-objective optimization model, the interaction and constraint relationship between the training objectives are comprehensively considered. For example, while improving endurance, it will automatically balance the training objectives such as strength and flexibility to avoid the regression of other training objectives due to overtraining of a single objective. Specifically, a multi-objective optimization method based on nonlinear programming is adopted. By gradually adjusting the weight coefficient of each training objective, each training objective can be coordinated with each other while being maximized, avoiding conflicts between different training objectives. After multi-objective optimization, a preliminary training plan framework will be generated through the multi-objective optimization model, including the specific tasks and training volume of each training objective. For example, some training cycles focus on strength training, while other training cycles focus on endurance training.

[0022] S2. During the training process according to the preliminary training plan, the real-time data of the athletes are monitored and analyzed using a dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization to obtain quantitative feedback; based on the quantitative feedback, the preliminary training plan is dynamically adjusted and optimized to obtain the best training plan.

[0023] After the preliminary training plan is generated, the athlete trains according to the preliminary training plan. During the training process, the real-time data of the athlete is monitored by real-time sensors, including data in multiple dimensions such as heart rate, blood oxygen saturation, exercise intensity, and psychological state. Based on the real-time data of the athlete, the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization is used to analyze and obtain quantitative feedback, and the preliminary training plan is dynamically adjusted and optimized based on the quantitative feedback to obtain the best training plan. The specific implementation process is as follows: First, the real-time data of athletes is subjected to a series of standardized preprocessing operations to remove noise and unify data of different dimensions into a standardized format, so as to obtain real-time data after standardized preprocessing for subsequent analysis; after standardized preprocessing, the real-time data after standardized preprocessing is subjected to real-time analysis by weighted comprehensive analysis method. The core idea of ​​the weighted comprehensive analysis method is to assign different weight coefficients to each physiological indicator of the athlete according to its importance in the overall training process, and then perform weighted comprehensive analysis on each physiological indicator according to the weight coefficient to obtain a comprehensive feedback value. The calculation formula of the comprehensive feedback value is: , in, Represents the comprehensive feedback value during the training process; is the total number of physiological indicators contained in the athlete's standardized pre-processed real-time data; It is The weight coefficient of each physiological index indicates the influence of the physiological index on the training effect, which is determined according to the expert experience method; It is The evaluation function of the physiological index is Feedback values ​​of physiological indicators are used to map the real-time data after standardized preprocessing to the corresponding training effect scores, which are determined based on existing physiological models or through regression analysis; It is real-time data after standardized preprocessing.

[0024] Furthermore, the comprehensive feedback value Enter the dynamic adjustment stage to adjust the amplitude and direction of the initial training plan. In order to achieve the best training effect, the adaptive adjustment amount calculation formula is introduced to calculate the adaptive adjustment amount of the initial training plan. , and dynamically optimize according to the deviation between the feedback value of the physiological index and the target feedback value, as well as the adjustment strength of the initial training plan. The specific adaptive adjustment formula is: , in, is the adaptive adjustment of the training plan; It is the adjustment factor, which indicates the sensitivity of the adaptive adjustment amount to the adjustment of the total training plan. By adjusting the size of the adjustment factor, it is used to control the intensity of the training plan adjustment to avoid the intensity of the training plan adjustment being too drastic or too slow. It is obtained by experimental method. It is The target feedback value of each physiological index is set according to the expert experience method; It is an exponential function operation; is the decay coefficient, which is used to control the time decay rate during the training plan adjustment process. As the training time goes by, the amplitude of the training plan adjustment gradually decreases to avoid excessive adjustment interfering with the long-term training effect of athletes. It is determined by experimental method; is the training time, which indicates the duration of the training, usually referring to the time from the start of the training to the current moment; It is the weight factor for adjusting the gap between the comprehensive feedback value and the target feedback value, which is determined according to the expert experience method; Represents the target feedback value during training.

[0025] The main purpose of the above formula is to dynamically calculate the adaptive adjustment required for the training plan by calculating the deviation between the feedback value of the physiological index and the target feedback value. And through the time decay mechanism, the exponential function operation is used to gradually reduce the adjustment range of the training plan to avoid too frequent adjustments interfering with the athletes' training rhythm.

[0026] In order to ensure that the training intensity can improve the performance of athletes without causing excessive fatigue or overtraining, the training intensity is optimized and the training intensity optimization calculation formula is introduced to calculate the optimized training intensity. , which is used to balance the athlete's current training load and recovery needs. The specific training intensity optimization calculation formula is: , in, is the optimized training intensity; It is the weight factor of training intensity adjustment, which is used to control the sensitivity of training intensity to the training effect of athletes. It determines the influence of training intensity on the adjustment results of the overall training plan during the training intensity optimization process. It is determined according to the experimental method. It is the training effectiveness adjustment factor, which indicates the degree of influence of the adjustment of the training effectiveness index on the training intensity, and is determined by the experimental method; It is a training effectiveness indicator used to measure whether the training is effective. It is calculated based on multi-dimensional data such as the athlete's physical fitness, recovery status, and goal achievement, and is determined according to expert experience. is the heart rate adjustment factor, which indicates the degree of influence of the deviation between the athlete's current heart rate and the target heart rate on the adjustment of training intensity. It determines the sensitivity of heart rate difference to the adjustment of training intensity and is determined by experimental method. is the current heart rate, obtained through the real-time heart rate sensor; is the target heart rate, which is preset based on expert experience; It is the psychological stress state, which indicates the athlete’s current psychological stress level, obtained through psychological state monitoring equipment (such as heart rate variability analysis, brain wave monitoring, etc.); It is the maximum psychological stress state, which indicates the athlete’s maximum psychological tolerance, that is, the maximum psychological stress that the athlete can withstand under extreme conditions, obtained through psychological tests and the athlete’s psychological tolerance assessment; is the comprehensive feedback gap adjustment factor, determined based on the expert experience method; It is an exponential function operation.

[0027] The above formula can comprehensively consider the effects of heart rate, exercise intensity and psychological state, so that the training intensity is physiologically matched with the actual state of the athlete, preventing sports injuries caused by excessive psychological pressure or excessive heart rate.

[0028] Furthermore, the adaptive adjustment amount and optimized training intensity Together they serve as inputs and enter the next quantitative feedback calculation phase. The quantitative feedback formula is as follows: , in, It is quantitative feedback; Finally, based on quantitative feedback and the preliminary training plan, the constraints are set according to the specific scenario and actual situation through expert experience, and the preliminary training plan is dynamically adjusted and optimized using the existing multi-objective optimization algorithm to obtain the best training plan.

[0029] In summary, a method for intelligent generation and management of sports training plans has been completed.

[0030] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0031] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0032] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for intelligently generating and managing a sports training plan, characterized in that: The following steps are involved: S1. Acquire the athlete's physiological data, sports performance data, external environment data, and health status data, and use them as original multi-dimensional data, and pre-process the original multi-dimensional data to obtain pre-processed multi-dimensional data; Perform feature extraction on the preprocessed multi-dimensional data to obtain preliminary feature data; The preliminary feature data is enhanced to obtain the enhanced feature data, and preliminary analysis is performed in combination with the training objectives to generate a preliminary training plan; S2. During the training process according to the preliminary training plan, the real-time data of the athletes is monitored and analyzed using a dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization to obtain quantitative feedback; Based on quantitative feedback, the initial training plan is dynamically adjusted and optimized to obtain the best training plan.

2. A method for intelligently generating and managing a sports training plan according to claim 1, characterized in that: The S1 specifically includes: The feature adaptive enhancement formula is introduced to enhance the preliminary feature data to obtain the enhanced feature data. The specific implementation formula is: ， in, It is Feature data after enhancement processing; It is Preliminary characteristic data; It is The weight coefficient of the preliminary feature data; It is Preliminary characterization data and The weighted relationship coefficient between the preliminary feature data; It is the data describing the preliminary characteristics and Function of nonlinear relationship between It is Preliminary characteristic data; It is Preliminary characterization data and The influence of the square difference between the preliminary feature data on the enhancement effect; It is Preliminary characterization data and The square term of the difference between the preliminary feature data; is the coefficient of the logarithmic transformation term; is the exponential decay coefficient; It is an exponential function operation; It is Time decay factor of the preliminary characteristic data; is a time variable; It is The coefficients of the feature matrix transformation corresponding to the preliminary feature data; is a matrix element, indicating the Preliminary characterization data and The correlation between the preliminary feature data; It is Preliminary feature data.

3. A method for intelligently generating and managing a sports training plan according to claim 1, characterized in that: The S2 specifically includes: In the process of realizing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the real-time data of the athletes are subjected to standardized preprocessing to obtain the real-time data after standardized preprocessing; and the real-time data after standardized preprocessing is analyzed in real time by the weighted comprehensive analysis method to obtain the comprehensive feedback value.

4. A method for intelligently generating and managing a sports training plan according to claim 3, characterized in that: The S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the comprehensive feedback value enters the dynamic adjustment stage to adjust the magnitude and direction of the initial training plan.

5. A method for intelligently generating and managing a sports training plan according to claim 4, characterized in that: The S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multidimensional data analysis and adaptive feedback optimization, the adaptive adjustment amount calculation formula is introduced to calculate the adaptive adjustment amount of the preliminary training plan, and dynamic optimization is performed based on the deviation between the feedback value of the physiological index and the target feedback value, as well as the adjustment intensity of the preliminary training plan.

6. A method for intelligently generating and managing a sports training plan according to claim 5, characterized in that: The S2 specifically includes: The calculation formula of the adaptive adjustment amount is: ， in, is the adaptive adjustment of the training plan; is the adjustment factor; is the total number of physiological indicators contained in the athlete's standardized pre-processed real-time data; It is The evaluation function of the physiological index is Feedback value of physiological indicators; It is Target feedback value of each physiological index; It is an exponential function operation; is the attenuation coefficient; It’s training time; It is the weight factor for adjusting the gap between the comprehensive feedback value and the target feedback value; Represents the comprehensive feedback value during the training process; Represents the target feedback value during training.

7. A method for intelligently generating and managing a sports training plan according to claim 6, characterized in that: The S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the training intensity is optimized, and the training intensity optimization calculation formula is introduced to calculate the optimized training intensity. The specific implementation formula is: ， in, is the optimized training intensity; is the weight factor for training intensity adjustment; is the training effectiveness adjustment factor; It is an indicator of training effectiveness; is the heart rate adjustment factor; is the current heart rate; is the target heart rate; It is a state of psychological stress; It is the state of maximum psychological stress; is the comprehensive feedback gap adjustment factor; It is an exponential function operation.

8. A method for intelligently generating and managing a sports training plan according to claim 7, characterized in that: The S2 specifically includes: In the process of implementing the dynamic adjustment algorithm based on multi-dimensional data analysis and adaptive feedback optimization, the adaptive adjustment amount and the optimized training intensity are used as input to enter the quantitative feedback calculation stage to obtain quantitative feedback.

Images