Sports student development core accomplishment comprehensive management method and system based on big data

Abstract

The invention provides a sports student development core accomplishment comprehensive management method and system based on big data, and the method comprises the steps: receiving and integrating multi-channel sports student dynamic data streams, and constructing a personal growth trajectory map; analyzing nodes and edges in the atlas by using an association rule mining algorithm, identifying key factors and turning points influencing growth, and performing optimal matching on educational resources and training plans in combination with a core literacy framework and a particle swarm optimization algorithm to generate a matching result; personalized learning materials and training suggestions are accurately pushed to form a preliminary development path plan; monitoring the execution progress in real time through a reinforcement learning algorithm, and dynamically adjusting the preliminary plan to obtain a target development path plan; and establishing a multi-dimensional feedback mechanism, collecting feedback information of coaches, sports students and third-party reviews, performing analysis processing to obtain an evaluation result, and finally generating an optimized final target development path plan. According to the invention, the management effect of core accomplishment of sports students is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of big data technology, and in particular to a comprehensive management method and system for the development of core competencies of sports students based on big data. Background Art

[0002] In modern sports training, coaches and managers are faced with the challenge of comprehensive and precise management and optimization of athletes. In order to ensure that each athlete can fully realize his or her potential, it is necessary not only to consider training performance and competitive results, but also to comprehensively evaluate physical function indicators and psychological state. Traditional management methods usually rely on manual recording and evaluation, which is inefficient and prone to errors. In recent years, with the advancement of technology, some institutions have begun to use specific software or platforms to analyze a certain type of data, such as training performance or physical function.

[0003] Existing technologies mainly rely on manual records, single-point data analysis tools, and preliminary sentiment analysis models. Specifically, coaches and managers usually track the performance of athletes through paper records or simple spreadsheets. Although this method is intuitive, it is inefficient and prone to human errors. At the same time, some institutions use specific software or platforms to analyze a certain type of data, such as training performance or physical function, but these tools often lack the ability to comprehensively analyze multi-source data and cannot provide a comprehensive perspective. Although some systems have begun to introduce sentiment analysis models to process feedback information from coaches and athletes, these applications are limited and have failed to form a closed-loop optimization cycle, resulting in poor overall optimization results and poor management of the core literacy of athletes. Summary of the invention

[0004] The embodiments of the present application provide a comprehensive management method and system for the core competencies of sports students based on big data, so as to solve the problem of poor management effect of core competencies of sports students in the prior art.

[0005] In the first aspect, the embodiment of the present application provides a comprehensive management method for the core literacy of sports students based on big data, including: Receiving and integrating sports student dynamic data streams from multiple channels, wherein the sports student dynamic data streams at least include the sports student's training performance, competitive results, physical function indicators and psychological state assessment; Building a personal growth trajectory map for each athlete based on the dynamic data stream of the athlete, wherein the personal growth trajectory map is used to reflect the data of the athlete at different time points and their interrelationships; Analyze the relationship between nodes and edges in the personal growth trajectory map using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students, and optimize the matching of educational resources and training plans suitable for sports students based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, to obtain a matching result, which refers to the result of optimal resource allocation and optimal configuration of training effects; Accurately push personalized learning materials and training suggestions corresponding to the matching results to generate a preliminary development path plan; Using a reinforcement learning algorithm, real-time monitoring of the progress and changes of the athletes in the process of executing the preliminary development path planning is performed to obtain monitoring results, and the preliminary development path planning is dynamically adjusted based on the monitoring results to obtain a target development path planning; Based on the target development path planning, a multi-dimensional feedback mechanism is established. By collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model, the feedback information is analyzed and processed to obtain evaluation results, and the target development path planning will be optimized based on the evaluation results.

[0006] Optionally, the association rule mining algorithm is used to analyze the relationship between nodes and edges in the personal growth trajectory map to identify key factors and turning points that affect the growth of sports students, and based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, the educational resources and training plans suitable for sports students are optimally matched to obtain matching results, including: The association rule mining algorithm is used to analyze the dynamic data stream of sports students after cleaning and normalization, and the training performance, competitive results, physical function indicators and psychological state evaluation at each time point are converted into nodes in the graph, and the logical relationship or causal relationship between different nodes is represented as edges to generate a personal growth trajectory graph; Based on the personal growth trajectory map, an association rule mining algorithm is applied to explore the relationship between the nodes and edges, and by setting the minimum support and confidence thresholds, frequent item sets and strong association rules are found to obtain the key factors affecting the growth of athletes and their turning points; According to the strong association rules, combined with the knowledge of domain experts, the key factors affecting the growth of athletes and their turning points are analyzed and processed, the factors that are crucial to the development of athletes and the situations in which significant changes occur are determined, and a list of key factors and a set of turning points are generated; Using a pre-set core literacy framework for sports students, matching the list of key factors and the set of turning points, determining the core literacy aspects that need to be strengthened or adjusted, and generating personalized literacy development goals, the pre-set core literacy framework for sports students includes physical health, mental health, and sports skills; Using the particle swarm optimization algorithm, search and process the educational resource allocation plan and training plan configuration that meet the personalized literacy development goals, update the particle position using its own experience and group experience, find the global optimal solution, and obtain the most optimized resource allocation plan and training plan; According to the optimized resource allocation scheme and training plan, personalized matching is carried out for the specific situation of the sports students, and the optimization of personalized education and training is achieved in combination with individual differences, and specific education resource allocation and training plan arrangements are generated to obtain matching results.

[0007] Optionally, the particle swarm optimization algorithm is used to search and process the educational resource allocation scheme and training plan configuration that meet the personalized literacy development goals, and the particle positions are updated using the own experience and group experience to find the global optimal solution to obtain the optimal resource allocation scheme and training plan, including: Using the random distribution principle, the position and speed of the particle group are initialized to obtain an initial particle group, a fitness function is set according to the personalized literacy development goal, the fitness value of the initial particle group is calculated, and a fitness evaluation result is generated; Based on the fitness evaluation result, combined with the best historical position of the particle itself and the best historical position of the entire group, the speed and position of the particle are updated to make the particle approach a better solution, thereby obtaining an updated particle state; The updated particle state is used to iterate all particles, the fitness value is re-evaluated in each iteration, and the best historical position of the particle itself and the best historical position of the entire group are updated until a preset termination condition is met, and an iterative optimization result is generated. According to the iterative optimization result, the optimal resource allocation and training plan arrangement are obtained. The preset termination condition refers to stopping the iterative search when the maximum number of iterations reached during the algorithm iteration or the change in the fitness value is less than a set threshold.

[0008] Optionally, the use of a reinforcement learning algorithm to monitor in real time the progress and changes of the sports students in the process of executing the preliminary development path planning, obtain monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results to obtain the target development path planning, including: Using a multi-agent system framework, multiple agents are initialized so that the multiple agents have their own observation range and action capabilities, and the development path of sports students is jointly optimized through cooperation and competition mechanisms to build a multi-agent collaborative environment. The multiple agents include coaches or assistants from different disciplines. Based on the multi-agent collaborative environment and combined with the hierarchical reinforcement learning method, the short-term behavior immediate reward and the long-term goal achievement cumulative reward are defined to obtain a preliminary reward mechanism, and the inverse reinforcement learning technology is used to infer the implicit objective function from the expert demonstration, and the preliminary reward mechanism is optimized to generate a reward mechanism that meets the best practice standards; A deep deterministic policy gradient algorithm combined with a generative adversarial network is used to simulate training scenarios, provide training suggestions for sports students, deploy high-frequency data acquisition equipment to achieve real-time data stream transmission, obtain dynamic data, apply time series prediction models and smoothing processing, and use adaptive filters to pre-process the dynamic data to obtain high-quality state feedback; Based on the reward mechanism that meets the best practice standards and the high-quality status feedback, dual-Q learning, meta-learning and evolutionary strategies are combined to explore different strategy variants, find stable and efficient decision rules, based on the decision rules, analyze unstructured feedback information by developing a sentiment analysis toolkit, and use the Bayesian optimization algorithm to optimize parameter configuration to obtain comprehensive evaluation results, and fine-tune and develop path planning based on the comprehensive evaluation results to generate a target development path plan.

[0009] Optionally, based on the reward mechanism that meets the best practice standards and the high-quality state feedback, dual Q learning, meta-learning and evolutionary strategies are combined to explore different strategy variants to find stable and efficient decision rules. Based on the decision rules, unstructured feedback information is analyzed by developing a sentiment analysis toolkit, and parameter configuration is optimized using a Bayesian optimization algorithm to obtain a comprehensive evaluation result. Fine-tuning and development path planning are performed based on the comprehensive evaluation result to generate a target development path planning, including: Using the reward mechanism that meets the best practice standards and the high-quality state feedback, the optimization search process is initialized, the process of finding the optimal training and development strategy that maximizes the cumulative reward and adapts to the dynamic changes of athletes is started, and the initialization conditions and environment settings are generated; According to the double Q learning algorithm, the overestimation problem is identified and reduced, and a meta-learning method is introduced to enable the system to quickly adapt to new environments or task changes, and the strategies in different situations are generalized based on the initialization conditions and the environment settings to obtain a more stable and generalized strategy; Applying evolutionary strategies to simulate the process of natural selection, exploring the more stable and generalized strategies, generating candidate solutions, and screening and optimizing the candidate solutions based on their performance to obtain efficient and stable decision rules and generate a series of optimized strategy variants; Based on the series of optimized strategy variants, a sentiment analysis toolkit is developed, which integrates natural language processing and computer vision technology to deeply analyze and process unstructured feedback information to obtain detailed feedback analysis results. The sentiment analysis toolkit includes capturing sentiment tendencies and identifying specific improvement points or potential problems. The unstructured feedback information includes feedback information from coaches, athletes themselves, and third-party reviewers; Based on the detailed feedback analysis results, the Bayesian optimization algorithm is used to optimize the configuration of key parameters, and the proxy model is constructed to approximate the objective function, obtain the global optimal solution, generate the optimized parameter configuration, and obtain the comprehensive evaluation results; Based on the comprehensive evaluation results, the preliminary development path plan is fine-tuned. By comparing the effects of different plans, the path that best promotes the growth of athletes is selected, and the target development path plan is generated in combination with individual needs and changes in the external environment.

[0010] Optionally, constructing a personal growth trajectory map of each athlete based on the athlete dynamic data stream includes: Preprocessing the received and integrated sports student dynamic data streams from multiple channels to determine the quality and consistency of the data and obtain high-quality dynamic data streams; Based on the high-quality dynamic data stream, nodes and edges in the personal growth trajectory map are defined and processed, the information at each time point is converted into nodes, and the logical relationship or causal relationship between different nodes is represented as edges, so as to generate a preliminary personal growth trajectory framework, wherein the information at each time point includes training performance, competitive results, physical function indicators and psychological state assessment; Using time series analysis methods, the preliminary personal growth trajectory framework is modeled and processed to capture the trend and pattern of data changes over time, analyze the development characteristics of sports students at different stages, and identify potential influencing factors and turning points of the potential influencing factors, so as to obtain a personal growth trajectory map with a time dimension; Combining domain knowledge and statistical analysis technology, the personal growth trajectory map with time dimension is deeply mined and processed to generate a personal growth trajectory map with semantic interpretation, so as to obtain the specific performance of sports students at various time points, and use the internal connection between various data to generate a personal growth trajectory map with deep analysis; By using visualization tools and techniques, the in-depth analyzed personal growth trajectory map is displayed in the form of a graphical interface. Through interactive charts and animation demonstrations, key information is discovered and decision-making is supported to generate a personal growth trajectory map for each sports student.

[0011] Optionally, based on the target development path planning, a multi-dimensional feedback mechanism is established, by collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model to parse and process the feedback information to obtain an evaluation result, and the target development path planning is optimized based on the evaluation result, including: Utilize multi-dimensional feedback channels to collect and process feedback information from different sources such as coaches, athletes themselves, and third-party reviewers to obtain rich and comprehensive feedback data; Based on the rich and comprehensive feedback data, preprocessing operations are performed, combined with anonymization processing to protect personal information security, to generate high-quality feedback data, wherein the preprocessing operations include text cleaning, format unification, and noise removal; Based on a hybrid sentiment analysis model that integrates natural language processing and computer vision technology, the high-quality feedback data is analyzed and processed to identify sentiment tendencies and capture specific semantic content and potential sentiment factors, generating a detailed sentiment analysis report; Utilizing the detailed sentiment analysis report and combining it with the core literacy framework, analyzing and processing the relationship between nodes and edges in the personal growth trajectory map, extracting preliminary key evaluation indicators, and generating target key evaluation indicators, wherein the preliminary key evaluation indicators include those reflecting the training effect, psychological state, and physical function improvement; Based on the target key evaluation indicators, a comprehensive evaluation report is formed to summarize the advantages and disadvantages of the path planning, and specific improvement suggestions are put forward as the basis for optimizing the path planning to obtain a comprehensive evaluation result; According to the comprehensive evaluation results, the existing target development path plan is fine-tuned and optimized, the education resource allocation plan is updated and the training plan configuration is adjusted to generate an optimized final target development path plan.

[0012] In the second aspect, the embodiment of the present application provides a comprehensive management system for the core literacy development of sports students based on big data, including: A receiving module, used for receiving and integrating sports students' dynamic data streams from multiple channels, wherein the sports students' dynamic data streams at least include the sports students' training performance, competitive results, physical function indicators and psychological state evaluation; A construction module, used to construct a personal growth trajectory map of each athlete based on the dynamic data stream of the athlete, wherein the personal growth trajectory map is used to reflect various data of the athlete at different time points and their mutual relationships; An analysis module is used to analyze the relationship between nodes and edges in the personal growth trajectory map using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students, and to optimize the matching of educational resources and training plans suitable for sports students based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, to obtain a matching result, which refers to the result of optimal resource allocation and optimal configuration of training effects; A push module, used to accurately push personalized learning materials and training suggestions corresponding to the matching results to generate a preliminary development path plan; An adjustment module is used to use a reinforcement learning algorithm to monitor in real time the progress and changes of the athletes in the process of executing the preliminary development path planning, obtain monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results to obtain a target development path planning; The processing module is used for the target development path planning and establishes a multi-dimensional feedback mechanism. By collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model, the feedback information is analyzed and processed to obtain evaluation results, and the target development path planning is optimized based on the evaluation results.

[0013] In a third aspect, an embodiment of the present application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a comprehensive management method for the core competencies of sports students based on big data as described in any one of the first aspects.

[0014] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement a comprehensive management method for the core competencies of sports students based on big data as described in any one of the first aspects.

[0015] In an embodiment of the present application, a sports student dynamic data stream from multiple channels is received and integrated, and the sports student dynamic data stream at least includes the sports student's training performance, competitive results, physical function indicators and psychological state assessment; a personal growth trajectory map of each sports student is constructed based on the sports student dynamic data stream, and the personal growth trajectory map is used to reflect the various data of the sports student at different time points and their mutual relationships; an association rule mining algorithm is used to analyze the relationship between nodes and edges in the personal growth trajectory map to identify key factors and turning points that affect the growth of sports students, and based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, the educational resources and training plans suitable for the sports student are optimally matched to obtain a matching result. The matching result refers to the result of optimal resource allocation and optimal configuration of training effects; the personalized learning materials and training suggestions corresponding to the matching result are accurately pushed and processed to generate a preliminary development path plan; the reinforcement learning algorithm is used to monitor the progress and changes of athletes in the process of executing the preliminary development path plan in real time to obtain monitoring results, and the preliminary development path plan is dynamically adjusted based on the monitoring results to obtain a target development path plan; based on the target development path plan, a multi-dimensional feedback mechanism is established, by collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model to parse and process the feedback information to obtain an evaluation result, and the target development path plan is optimized based on the evaluation result.

[0016] The technical solution of this application has the following beneficial effects: This application ensures the comprehensiveness and diversity of data by receiving and integrating dynamic data streams of sports students from multiple channels, including training performance, competitive results, physical function indicators and psychological state assessment. This provides a solid foundation for subsequent personalized analysis. Based on the dynamic data stream of sports students, a personal growth trajectory map of each sports student is constructed to reflect the various data and their interrelationships at different time points. This method not only intuitively shows the growth process of sports students, but also reveals potential influencing factors and development trends. The relationship between nodes and edges in the personal growth trajectory map is analyzed using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students. Combined with the pre-set core literacy framework and particle swarm optimization algorithm, educational resources and training plans are optimally matched to ensure optimal resource allocation and optimal configuration of training effects. The personalized learning materials and training suggestions corresponding to the matching results are accurately pushed and processed to generate a preliminary development path plan. This process ensures that each sports student can obtain guidance and support that best suits their current status and development needs. The reinforcement learning algorithm is used to monitor the progress and changes of athletes in the process of executing the preliminary development path planning in real time, obtain the monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results, and finally obtain the target development path planning. This method can respond to individual changes in a timely manner and ensure the adaptability and effectiveness of path planning. A multi-dimensional feedback mechanism is established to collect feedback information from coaches, athletes themselves, and third-party reviewers, and these feedbacks are analyzed using a hybrid sentiment analysis model to obtain evaluation results. The target development path planning is optimized based on the evaluation results to generate the optimized final target development path planning. This mechanism enhances the flexibility and practical applicability of path planning.

[0017] Furthermore, by conducting an in-depth analysis of the dynamic data stream of sports students after cleaning and normalization, the training performance, competitive results, physical function indicators and psychological state evaluation at each time point are converted into nodes in the graph, and the logical relationship or causal relationship between different nodes is represented as edges. This not only ensures the accuracy and consistency of the data, but also constructs an intuitive and comprehensive personal growth trajectory graph, providing a solid foundation for subsequent analysis. Based on the personal growth trajectory graph, the association rule mining algorithm is applied to explore the relationship between nodes and edges. By setting the minimum support and confidence thresholds, frequent item sets and strong association rules are found, so as to accurately identify the key factors and turning points that affect the growth of sports students. This method can reveal the deep relationships hidden behind the data and provide deeper insights. According to the strong association rules and combined with the knowledge of domain experts, the key factors and turning points are analyzed and processed to determine the factors and significant changes that are crucial to the development of sports students, and a list of key factors and a set of turning points are generated. Using the pre-set core literacy framework for sports students, these factors are matched and processed to generate personalized literacy development goals. This process ensures that every sports student can get the guidance and support that best suits their development. The particle swarm optimization algorithm is used to search and process the educational resource allocation plan and training plan configuration that meet the personalized literacy development goals. The particle position is updated through its own experience and group experience to find the global optimal solution, and finally the optimal resource allocation plan and training plan are obtained. This method not only improves the efficiency of resource allocation, but also ensures the scientificity and effectiveness of the training plan, and maximizes the development of sports students. According to the optimized resource allocation plan and training plan, the specific situation of the sports students is personalized and matched, and the optimization of personalized education and training is achieved by combining individual differences. This enables each sports student to obtain the best support and development path according to their actual situation, improving the overall training effect.

[0018] Furthermore, the position and speed of the particle swarm are initialized by the random distribution principle to obtain the initial particle swarm, and the fitness function is set according to the personalized literacy development goal, the fitness value is calculated, and the fitness evaluation result is generated. This step lays the foundation for the subsequent iterative optimization and ensures the diversity and extensiveness of the initial solution. Based on the fitness evaluation results, the particle's own best historical position and the best historical position of the entire group are combined to update the particle's speed and position so that the particle moves closer to a better solution. This method not only speeds up the convergence speed, but also enhances the robustness of the algorithm and avoids the problem of premature convergence. All particles are iteratively processed using the updated particle state, the fitness value is re-evaluated in each iteration, and the particle's own best historical position and the best historical position of the entire group are updated. The iterative search stops until the preset termination condition is met, such as when the maximum number of iterations is reached or the change in the fitness value is less than a certain set threshold. This iterative optimization mechanism ensures that the algorithm can find the global optimal solution within a limited time, improving the optimization efficiency and accuracy. According to the iterative optimization results, the optimal resource allocation and training plan are finally generated. This approach not only ensures the rational allocation of resources, but also customizes the most effective training plan according to the specific needs of athletes, greatly improving training results and personal development potential.

[0019] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flowchart of a comprehensive management method for the core literacy of sports students based on big data provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a comprehensive management system for the development of core competencies of sports students based on big data provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0023] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0025] Figure 1 A flowchart of a comprehensive management method for the core competencies of sports students based on big data is provided for the embodiment of this application, such as Figure 1 As shown, the method includes: Step 101: receiving and integrating sports student dynamic data streams from multiple channels; In this step, the dynamic data stream of the athlete at least includes the athlete's training performance, competitive results, physical function indicators and psychological state assessment; the dynamic data stream refers to a collection of data collected continuously at different time points, which is used to comprehensively reflect the development status of the athlete. By receiving and integrating these multi-source data, the system can build a complete database, providing a solid foundation for subsequent analysis. The diversity of data ensures a comprehensive understanding of each athlete, not only limited to the performance of a single dimension, but also including comprehensive factors such as psychological state, thereby supporting more accurate personalized analysis.

[0026] In the embodiment of the present application, it is assumed that a certain university track and field team uses a comprehensive management system that can receive and integrate data from multiple sources, including training data uploaded in real time by smart wearable devices, official performance reports after each competition, regular physical function test results, and weekly or monthly psychological state self-assessment forms. All of these data are collected in a central database, and the consistency and accuracy of the data are ensured through data cleaning and normalization. This integration of multi-source data allows coaches and managers to fully understand the performance and development trends of each team member, providing a rich information basis for formulating personalized training plans.

[0027] The integration of multi-source data in the embodiment of the present application ensures a comprehensive understanding of each athlete, provides a rich data foundation, and provides solid support for subsequent analysis and optimization. By integrating data from different channels, the system can capture a wider range of variables, reveal potential factors that affect the growth of athletes, improve the accuracy and depth of data analysis, and lay the foundation for the formulation of personalized training programs.

[0028] Step 102: constructing a personal growth trajectory map of each athlete based on the athlete's dynamic data stream; In this step, the personal growth trajectory map is used to reflect the data of athletes at different time points and their interrelationships; the map not only shows the specific data at each time point, but also reveals the interrelationships between these data, forming an intuitive time series graph. By converting the training performance, competitive results, physical function indicators and psychological state evaluation at each time point into nodes in the map, and representing the logical relationship or causal relationship between different nodes as edges, the system can intuitively display the growth process and key turning points of athletes. This map helps to identify the key factors that affect development and provides a visualization tool for subsequent optimization matching.

[0029] In the embodiment of the present application, continuing the example of the track and field team mentioned above, the system converts all collected data into nodes, and represents the logical relationship or causal relationship between different nodes as edges to generate a personal growth trajectory map. For example, the training record is used as a node to show the specific situation of each training, the competitive performance is used as a node to connect the relevant training nodes to show the training effect, the physical function index is used as a node to connect to the training and competition nodes to reflect the physical changes, and the psychological state assessment is used as a node to associate with the above nodes to reflect the impact of psychological factors on performance. In this way, coaches and managers can get a comprehensive and intuitive perspective to help them better understand the development process and potential influencing factors of sports students.

[0030] The embodiment of the present application provides coaches and managers with an intuitive and comprehensive perspective for the personal growth trajectory map, helping them to better understand the development process and potential influencing factors of sports students. Through graphical display, the system can reveal the deep relationships hidden behind the data, allowing coaches to more accurately identify key turning points and influencing factors, thereby formulating more scientific and effective training plans and improving the overall training effect.

[0031] Step 103: Analyze the relationship between nodes and edges in the personal growth trajectory map using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students, and optimize matching of educational resources and training plans suitable for sports students based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, to obtain matching results; In this step, the matching result refers to the result of the optimal configuration of resource allocation and training effect; the association rule mining algorithm is used to analyze the relationship between nodes and edges in the personal growth trajectory map, and identify the key factors and turning points that affect the growth of athletes. Combined with the pre-set core literacy framework and particle swarm optimization algorithm, the optimal allocation of educational resources and training plan configuration are determined. By setting the minimum support and confidence thresholds, frequent item sets and strong association rules are found, and finally a list of key factors and a set of turning points are generated. This method can not only reveal the relationship behind the data, but also formulate the most optimized training plan based on individual differences, thereby improving resource utilization and training effects.

[0032] In an embodiment of the present application, in the track and field team, the system applies an association rule mining algorithm to explore the relationship between nodes and edges, and finds frequent item sets and strong association rules by setting the minimum support and confidence thresholds. For example, it is found that the performance of the competition immediately after high-intensity training is improved but accompanied by increased psychological pressure, and key turning points are determined, such as a sudden increase in the amount of training at a certain stage, which leads to a decline in physical function. Combined with the knowledge of experts in the field, a list of key factors and a set of turning points are generated, and then the core literacy framework is used to match personalized literacy development goals. Finally, the optimal resource allocation and training plan are found through the particle swarm optimization algorithm. This process ensures that every sports student can get the guidance and support that best suits their current status and development needs.

[0033] The embodiment of the present application can not only identify the key factors affecting development, but also develop the most optimized training plan based on individual differences, thereby improving resource utilization and training effectiveness. Through the association rule mining algorithm, the system can reveal the deep relationships hidden behind the data, helping coaches to more accurately identify key turning points and influencing factors, thereby developing more scientific and effective training plans, significantly improving the overall training effect and personalization.

[0034] Step 104: accurately push personalized learning materials and training suggestions corresponding to the matching results to generate a preliminary development path plan; In this step, accurate push notifications are used to ensure that each athlete can obtain guidance and support that best suits their current status and development needs, thereby achieving personalized education and training goals. Personalized content includes not only specific training arrangements, but also psychological counseling and special skills training, to comprehensively improve the comprehensive quality of athletes.

[0035] In the embodiment of the present application, the track and field team system customizes a personalized training plan for each team member based on the above analysis results, including adjustments to the intensity and frequency of training, designing specific exercises for weak links, and providing emotional management and stress coping skills. For example, for a team member who performs well but needs to be strengthened in terms of psychological pressure, the system will push more learning materials and training suggestions on psychological adjustment. In this way, the system ensures that each team member can get the guidance and support that best suits their current status and development needs, improving the pertinence and effectiveness of the training.

[0036] The precise push of the embodiment of the present application ensures that each athlete can obtain the guidance and support that best suits their current status and development needs, thereby improving the pertinence and effectiveness of the training. Through personalized content push, the system can meet the unique needs of each team member to the greatest extent possible, ensuring that they receive training in their best condition, thus promoting their all-round development and improvement of their competitive level.

[0037] Step 105: using a reinforcement learning algorithm to monitor in real time the progress and changes of the sports students in the process of executing the preliminary development path planning, obtain monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results to obtain a target development path planning; In this step, by tracking the training progress and performance changes of each athlete in real time, the system can respond to individual changes in a timely manner, flexibly adjust the training plan, and ensure that the path planning is always in the optimal state. This method not only improves the overall training effect, but also enhances the adaptability and flexibility of the system.

[0038] In an embodiment of the present application, the track and field team system tracks the training progress and performance changes of each team member in real time, such as heart rate, speed, distance, etc., through smart devices. If a team member is found to have slow progress or abnormalities over a period of time, the system will automatically adjust the training plan, increase or decrease the training intensity, and change the training content to adapt to individual changes. For example, when it is detected that a team member's heart rate is continuously high, the system will recommend an appropriate reduction in training intensity to avoid the risks of overtraining. In this way, the system can flexibly respond to individual changes and ensure that each team member can receive training in the best condition.

[0039] The real-time monitoring and dynamic adjustment mechanism of the embodiment of the present application ensures that the path planning can flexibly respond to individual changes, improving the effectiveness and adaptability of the overall training. Through the reinforcement learning algorithm, the system can timely capture the performance changes of each team member and make adjustments quickly to ensure that the training plan is always in the optimal state, promoting all-round development and improvement of competitive level.

[0040] Step 106: Based on the target development path planning, a multi-dimensional feedback mechanism is established. Feedback information from coaches, athletes themselves and third-party reviewers is collected, and the feedback information is analyzed and processed using a hybrid sentiment analysis model to obtain evaluation results. The target development path planning is then optimized based on the evaluation results.

[0041] In this step, by introducing multi-dimensional feedback, the system can fully understand the opinions and suggestions of all parties, ensuring that the optimization process is closer to the actual situation. The hybrid sentiment analysis model not only identifies emotional tendencies, but also captures specific semantic content and generates detailed evaluation reports, providing a scientific basis for the optimization of path planning.

[0042] In an embodiment of the present application, the track and field team system introduces a multi-dimensional feedback mechanism to regularly collect opinions and suggestions from coaches, team members, and third-party reviewers. For example, the coach's evaluation of the training effect and team member performance, the team member's description of the training experience and psychological state, and the evaluation of external experts or competition referees. The system uses a hybrid sentiment analysis model to parse these feedbacks, generate a detailed evaluation report, and optimize the path planning accordingly. For example, if most feedback indicates that a training program is too monotonous, the system will adjust the training content and increase diversity. In this way, the system can continuously improve the training program to ensure that it always meets actual needs.

[0043] The multi-dimensional feedback mechanism of the embodiment of the present application enhances the flexibility and practical applicability of path planning, ensuring that the optimization process is closer to the actual situation. By introducing multi-party feedback, the system can fully understand the opinions and suggestions of all parties to ensure that the optimization process is more scientific and reasonable. The application of the hybrid sentiment analysis model not only improves the accuracy of feedback analysis, but also enhances the adaptability and flexibility of the system, promotes the continuous improvement of the training program, and improves the overall training effect.

[0044] Through the above steps, this method realizes the refined management and optimal configuration of the development path of sports students. First, through the integration and analysis of multi-source data, the system constructs a comprehensive personal growth trajectory map, revealing the key factors and turning points that affect development. Then, combined with the core literacy framework and particle swarm optimization algorithm, the system formulates the optimal resource allocation and training plan, and achieves the goal of personalized education and training through precise push. Real-time monitoring and dynamic adjustment mechanisms ensure that path planning can flexibly respond to individual changes, while the multi-dimensional feedback mechanism further optimizes the final path planning to ensure that it always meets actual needs. Overall, this method not only improves resource utilization and training effects, but also promotes the overall improvement of the core literacy of sports students, providing strong support for their all-round development and improvement of competitive level.

[0045] Optionally, in step 103, the relationship between nodes and edges in the personal growth trajectory map is analyzed by using an association rule mining algorithm to identify key factors and turning points that affect the growth of athletes, and based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, the educational resources and training plans suitable for athletes are optimized to obtain matching results, including: using an association rule mining algorithm to analyze the dynamic data stream of athletes after cleaning and normalization, converting the training performance, competitive results, physical function indicators and psychological state evaluation at each time point into nodes in the map, and representing the logical relationship or causal relationship between different nodes as edges to generate a personal growth trajectory map; based on the personal growth trajectory map, applying an association rule mining algorithm to explore the relationship between the nodes and edges, and by setting the minimum support and confidence thresholds, finding frequent item sets and strong association rules to obtain the key factors and turning points that affect the growth of athletes; based on the strong association rules, combined with the knowledge of experts in the field, The key factors and turning points that affect the growth of sports students are analyzed and processed, the factors that are crucial to the development of sports students and the situations in which significant changes occur are determined, and a list of key factors and a set of turning points are generated; the pre-set core literacy framework for sports students is used to match the list of key factors and the set of turning points, determine the core literacy aspects that need to be strengthened or adjusted, and generate personalized literacy development goals. The pre-set core literacy framework for sports students includes physical health, mental health, and sports skills; the particle swarm optimization algorithm is used to search and process the educational resource allocation plan and training plan configuration that meet the personalized literacy development goals, and the particle position is updated using the own experience and group experience to find the global optimal solution to obtain the optimized resource allocation plan and training plan; according to the optimized resource allocation plan and training plan, the specific situation of the sports students is personalized matched, and the optimization of personalized education and training is achieved in combination with individual differences, and a specific educational resource allocation and training plan arrangement is generated to obtain a matching result.

[0046] In the optimal management of the development path of sports students, it is crucial to ensure that resource allocation and training plan configuration can maximize the growth and development of each sports student. To this end, the particle swarm optimization (PSO) algorithm is introduced to dynamically adjust and optimize resource allocation and training plans. The algorithm simulates the collaborative mechanism in the foraging behavior of bird groups, uses individual experience and social experience to guide the search process, and finds the global optimal solution.

[0047] Optionally, the particle swarm optimization algorithm is used to search and process the educational resource allocation scheme and training plan configuration that meet the personalized literacy development goal, and the particle position is updated using the particle's own experience and group experience to find the global optimal solution to obtain the most optimized resource allocation scheme and training plan, including: using the random distribution principle to initialize the position and speed of the particle swarm to obtain an initial particle swarm, setting a fitness function according to the personalized literacy development goal, calculating the fitness value of the initial particle swarm, and generating a fitness evaluation result; based on the fitness evaluation result, combining the particle's own best historical position and the best historical position of the entire group The particle position is updated, and the particle speed and position are updated to make the particle approach a better solution to obtain an updated particle state; the updated particle state is used to iteratively process all particles, and the fitness value is re-evaluated in each iteration, and the best historical position of the particle itself and the best historical position of the entire group are updated until a preset termination condition is met, and an iterative optimization result is generated. According to the iterative optimization result, the optimal resource allocation and training plan arrangement are obtained. The preset termination condition refers to stopping the iterative search when the maximum number of iterations reached during the algorithm iteration or the change in the fitness value is less than a set threshold.

[0048] In this step, the association rule mining algorithm is used to analyze the dynamic data flow of sports students after cleaning and normalization, and the training performance, competitive results, physical function indicators and psychological state evaluation at each time point are converted into nodes in the graph, and the logical relationship or causal relationship between different nodes is represented as an edge to generate a personal growth trajectory graph. Then, based on the graph, the association rule mining algorithm is applied to find frequent item sets and strong association rules by setting the minimum support and confidence thresholds, so as to identify the key factors and turning points that affect the growth of sports students. Then, these key factors and turning points are deeply analyzed in combination with the knowledge of domain experts to determine the factors that are crucial to the development of sports students and the situations in which significant changes occur, and a list of key factors and a set of turning points are generated. Finally, the pre-set core literacy framework for sports students is used to match these lists of key factors and turning point sets, determine the core literacy aspects that need to be strengthened or adjusted, and generate personalized literacy development goals. On this basis, the particle swarm optimization algorithm is used to search and process the educational resource allocation plan and training plan configuration that meet the personalized literacy development goals. The particle position is updated through its own experience and group experience to find the global optimal solution, and the optimal resource allocation plan and training plan are obtained. According to these optimal solutions, personalized matching is carried out for the specific circumstances of sports students, and personalized education and training are optimized in combination with individual differences, and finally specific educational resource allocation and training plan arrangements are generated.

[0049] In the present application embodiment, the personal growth trajectory map of the sports student is first constructed, and the relationship between the nodes and edges in the map is analyzed by the association rule mining algorithm to identify the key factors and turning points that affect the growth of the sports student. Next, these key factors and turning points are analyzed and processed in combination with the knowledge of field experts, a list of key factors and a set of turning points are generated, and these factors are matched and processed using the pre-set sports student core literacy framework to generate personalized literacy development goals. Finally, the particle swarm optimization algorithm is used to search and process the education resource allocation scheme and training plan configuration that meet the personalized literacy development goals, and by initializing the particle swarm, calculating the fitness value, updating the particle speed and position and other steps, iterative optimization is performed until the preset termination condition is met, and the optimal resource allocation and training plan arrangement are finally obtained. This method not only ensures the optimization of resource allocation, but also realizes the optimal configuration of the training effect, so that each sports student can obtain the guidance and support that best suits its current state and development needs.

[0050] Suppose a university swimming team uses a comprehensive management system to optimize the training program of team members. The system first integrates data from multiple channels, including training data uploaded by smart wearable devices, competition results reports, regular physical function test results, and psychological state self-assessment forms. After cleaning and normalization, these data are used to construct the personal growth trajectory map of each team member. By analyzing the relationship between nodes and edges in the map through the association rule mining algorithm, the system identifies several key factors and turning points, such as the improvement of competition results immediately after high-intensity training but accompanied by increased psychological pressure, and the sudden increase in training volume at a certain stage leading to a decline in physical function. Combined with the professional knowledge of swimming coaches, the system generates a list of key factors and a set of turning points, and matches them with the pre-set core literacy framework to generate personalized literacy development goals. Subsequently, the system uses the particle swarm optimization algorithm to search for educational resource allocation plans and training plan configurations that meet these goals. Through the steps of initializing the particle swarm, calculating the fitness value, and updating the particle speed and position, the system continuously optimizes in multiple iterations and finally obtains the optimal resource allocation and training plan arrangement. For example, for a player who performs well but needs to improve his psychological stress, the system pushes more learning materials and training suggestions on psychological adjustment, and adjusts the training intensity and frequency to ensure that he receives training in the best condition. This approach not only improves resource utilization and training effects, but also promotes the overall development and competitive level of each player.

[0051] More specifically, in the process of updating the speed and position of the particle based on the fitness evaluation result and in combination with the best historical position of the particle itself and the best historical position of the entire group, the embodiment of the present invention further provides a formula for the speed vector of the particle in iteration, which is used to achieve optimal management of the development path of the sports student and ensure that resource allocation and training plan configuration can maximize the growth and development of each sports student. The specific calculation formula is as follows: ; in, Indicates The particle in The velocity vector in the iteration; represents the dynamic inertia weight, in the The value at the iteration; and represents the adaptive acceleration constant, in the The value at the iteration; and express Random numbers in the interval; Indicates The best historical position of the particle, The value at the iteration; represents the global optimal solution of the group. The value at the iteration; Indicates The particle in Position vector in the next generation; is the feedback correction factor, in The value at the iteration; represents the dynamic disturbance term, in the The value at the iteration; The overall design of the formula aims to achieve optimal management of the development path of sports students. By dynamically adjusting the speed of particles, combining the individual's historical best position, the group's global optimal position, multi-dimensional feedback mechanism and random disturbance factors, the formula ensures that path planning can flexibly respond to individual changes and continuously optimize.

[0052] The following is a brief introduction to the design reasons of each sub-item of the formula: ; In the particle's velocity vector formula in iteration, the inertia weight :Inertia weight The introduction of is to maintain the original movement trend of particles and balance the relationship between exploration and development. The value helps particles continue to explore a larger search space and find potential better solutions; while a lower The value of will cause the particles to focus more on the best position currently known and perform a more refined local search. , the focus of exploration and development can be flexibly switched at different stages of the algorithm to ensure the discovery of the global optimal solution.

[0053] Cognitive part : The cognitive part is designed to reflect the impact of the particle's own best historical position on its current velocity. Each particle has a record of its best past position. , this part of the formula encourages particles to return to these high-performing locations and use their historical experience to guide future behavior. In this way, particles can better utilize their own accumulated knowledge and avoid deviating from proven effective paths, while also helping to improve overall search efficiency.

[0054] Social Part :The social part is designed to allow particles to learn from the experience of other members in the group, especially the optimal position in the entire group This mechanism simulates the social learning process, allowing each particle to not only rely on its own experience but also benefit from the wisdom of the group. By guiding particles to move toward the optimal position of the group, the social part promotes information sharing and co-evolution, increasing the possibility of finding the global optimal solution.

[0055] Feedback correction factor Feedback correction factor The introduction of is to directly integrate the sentiment analysis results of coaches, athletes themselves and third-party reviewers into the optimization process. This sub-item ensures that the optimization process can respond to actual counter-emotional information in a timely manner, making the path planning closer to the actual situation. For example, if the coach believes that a player's mental state needs to be strengthened, the system can Adjust the Sichuan training plan and add psychological counseling content. This makes the optimization plan more realistic and targeted, and enhances the system's adaptability.

[0056] Dynamic disturbance term : Dynamic disturbance term The design of is to help particles jump out of the local optimal solution and avoid premature convergence. During the optimization process, particles may fall into the local optimal area and cannot be further improved. By introducing random perturbations, the diversity of the search can be increased, prompting particles to explore new possible solutions, thereby increasing the probability of finding the global optimal solution. In addition, It can also simulate unforeseen factors in reality, such as sudden physical conditions or changes in the external environment, making the optimization process more robust and flexible.

[0057] The following is a brief introduction to how to obtain the parameters of the formula: Weight : Inertia weight It can be set by fixed value method, linear reduction method or dynamic adjustment method.

[0058] Acceleration constant :Acceleration constant and The acquisition of is usually based on the empirical value method or the adaptive adjustment method.

[0059] Random coefficient : Random coefficient and is a random number between 0 and 1, generated by a pseudo-random number generator or by sampling from a uniform distribution.

[0060] Individual best position and the global optimal position : These two positions are obtained by recording and updating.

[0061] Current location : Current location It refers to the resource configuration and training plan configuration of the particle in the current iteration, which is obtained through the data acquisition system or database query.

[0062] Feedback correction factor : Feedback correction factor The acquisition involves a multi-dimensional feedback mechanism, which uses sentiment analysis tools to parse unstructured feedback information from coaches, athletes themselves, and third-party reviewers, identify emotional tendencies and specific points for improvement, and convert qualitative feedback into quantitative scores.

[0063] Dynamic disturbance term : Dynamic disturbance term can be obtained through random generation, environmental monitoring or expert opinion.

[0064] In order to more accurately balance the exploration and development process in the particle swarm optimization (PSO) algorithm, the system needs to adjust the inertia weight Dynamic adjustment is performed by introducing dynamic inertia weight , which ensures that a wide search is performed in the early stages of optimization to discover potential optimal solutions, while in the later stages, local search is focused to precisely locate the global optimal solution. Specifically, the dynamic inertia weight The calculation formula is as follows: ; in, and are the maximum and minimum inertia weights, is the total number of iterations; Inertia weight in dynamic The purpose of this formula is to dynamically adjust the inertia weight in a linear decreasing manner, ensuring that the particle swarm optimization (PSO) algorithm can conduct extensive exploration in the early stages to discover potential optimal solutions, while focusing on local search in the later stages to accurately locate the global optimal solution. This formula aims to balance the needs of exploration and development. As the number of iterations increases, the inertia weight increases. The inertia weight increases from the maximum value Smooth transition to minimum value , so as to flexibly switch the focus at different stages, improve the algorithm performance and stability, and reduce the risk of premature convergence, and ultimately achieve optimal management of the development path of sports students.

[0065] In order to more accurately integrate the feedback information from coaches, athletes themselves and third-party reviewers into the optimization process, the system needs to quantify the importance of feedback features from different sources and types. , which can ensure that the relative importance of each feedback feature in the optimization is reasonably reflected, thus better guiding the development path planning of athletes. Specifically, the feedback correction factor The calculation formula is as follows: ; in, is the weight of each feedback source, is the corresponding sentiment analysis score or other feedback indicator; In the feedback correction factor The purpose of this formula is to comprehensively consider multi-dimensional feedback information to ensure that the optimization process can respond to actual feedback in a timely manner and be close to the actual situation. By introducing the form of weighted summation, the system can assign corresponding weights according to the importance of different feedback features. , so that each feedback feature has an appropriate influence in the final correction factor.

[0066] In order to more accurately simulate the uncertainty factors in reality and prevent the particle swarm optimization (PSO) algorithm from converging to the local optimal solution too early, the system introduces a dynamic disturbance term. , to increase the diversity and flexibility of the search. Specifically, the dynamic perturbation term The calculation formula is as follows: ; in, is the disturbance intensity, yes A random number in the interval, is the probability of triggering a disturbance, is a function that generates a random number between 0 and 1.

[0067] In the dynamic disturbance term The purpose of this formula is to introduce random perturbations during the optimization process, help particles escape from the local optimal solution, avoid premature convergence, and ensure that the optimization process is closer to the actual situation. Through conditional judgment and random number generation, the system can introduce random perturbations within a small range under appropriate circumstances to enhance the diversity and robustness of the search.

[0068] Optionally, in step 105, the reinforcement learning algorithm is used to monitor in real time the progress and changes of the sports students in the process of executing the preliminary development path planning, obtain monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results to obtain the target development path planning, including: Using the multi-agent system framework, multiple agents are initialized so that they have their own observation range and action capabilities. Through cooperation and competition mechanisms, the development path of sports students is jointly optimized to build a multi-agent collaborative environment. The multiple agents include coaches or assistants from different disciplines. Based on the multi-agent collaborative environment and combined with the hierarchical reinforcement learning method, the immediate rewards for short-term behaviors and the cumulative rewards for achieving long-term goals are defined to obtain a preliminary reward mechanism. The inverse reinforcement learning technology is used to infer the implicit objective function from the expert demonstration, and the preliminary reward mechanism is optimized to generate a reward mechanism that meets the best practice standards. The deep deterministic policy gradient algorithm is combined with the adversarial generative network to simulate the training scenario. Sports students provide training suggestions, deploy high-frequency data acquisition equipment to achieve real-time data streaming transmission, obtain dynamic data, apply time series prediction models and smoothing processing, and use adaptive filters to pre-process the dynamic data to obtain high-quality state feedback; based on the reward mechanism that meets the best practice standards and the high-quality state feedback, combine double Q learning, meta-learning and evolutionary strategies to explore different strategy variants, find stable and efficient decision rules, based on the decision rules, analyze unstructured feedback information by developing a sentiment analysis toolkit, and use the Bayesian optimization algorithm to optimize parameter configuration to obtain comprehensive evaluation results, fine-tune and develop path planning based on the comprehensive evaluation results, and generate a target development path plan.

[0069] Optionally, based on the reward mechanism that meets the best practice standards and the high-quality state feedback, dual Q learning, meta-learning and evolutionary strategies are combined to explore different strategy variants to find stable and efficient decision rules. Based on the decision rules, unstructured feedback information is analyzed by developing a sentiment analysis toolkit, and parameter configuration is optimized using a Bayesian optimization algorithm to obtain a comprehensive evaluation result. Fine-tuning and development path planning are performed based on the comprehensive evaluation result to generate a target development path planning, including: The optimization search process is initialized by utilizing the reward mechanism that meets the best practice standards and the high-quality state feedback, and the process of finding the optimal training and development strategy that maximizes the cumulative reward and adapts to the dynamic changes of athletes is started, and the initialization conditions and environmental settings are generated; according to the double Q learning algorithm, the over-estimation problem is identified and reduced, and a meta-learning method is introduced to enable the system to quickly adapt to new environments or task changes, and the strategies in different situations are generalized based on the initialization conditions and the environmental settings to obtain more stable and generalized strategies; evolutionary strategies are applied to simulate the process of natural selection, and the more stable and generalized strategies are explored to generate candidate solutions, and the candidate solutions are screened and optimized according to their performance to obtain efficient and stable decision rules, and a series of optimized strategy variants are generated; based on the series of optimal The strategy variants after optimization are developed, and a sentiment analysis toolkit is developed. Natural language processing and computer vision technology are integrated to deeply analyze the unstructured feedback information and obtain detailed feedback analysis results. The sentiment analysis toolkit includes capturing emotional tendencies and identifying specific improvement points or potential problems. The unstructured feedback information includes feedback information from coaches, athletes themselves and third-party reviews; based on the detailed feedback analysis results, the Bayesian optimization algorithm is used to optimize the configuration of key parameters, and the global optimal solution is obtained by constructing an agent model to approximate the objective function, generate the optimized parameter configuration, and obtain a comprehensive evaluation result; according to the comprehensive evaluation results, the preliminary development path planning is fine-tuned, and the path that best promotes the growth of athletes is selected by comparing the effects of different plans, and the target development path planning is generated in combination with personalized needs and changes in the external environment.

[0070] In this step, a multi-agent system framework is constructed so that multiple agents, such as coaches or assistants from different disciplines, have their own observation range and action capabilities, and jointly optimize the development path of sports students through cooperation and competition mechanisms. The system defines the immediate rewards for short-term behaviors and the cumulative rewards for achieving long-term goals to form a preliminary reward mechanism, and infers the implicit objective function from expert demonstrations through inverse reinforcement learning technology to optimize the reward mechanism. A deep deterministic policy gradient algorithm is used in combination with a generative adversarial network to simulate training scenarios, provide training suggestions for sports students, and deploy high-frequency data acquisition equipment to achieve real-time data streaming and obtain dynamic data. The dynamic data is pre-processed using a time series prediction model, smoothing processing, and an adaptive filter to obtain high-quality state feedback. Based on a reward mechanism that meets best practice standards and high-quality state feedback, dual Q learning, meta-learning, and evolutionary strategies are combined to explore different strategy variants and find stable and efficient decision rules. A sentiment analysis toolkit is developed to analyze unstructured feedback information, and the Bayesian optimization algorithm is used to optimize parameter configuration to obtain comprehensive evaluation results. Based on these results, fine-tuning and development path planning are performed to generate target development path planning.

[0071] In the embodiment of the present application, a multi-agent collaborative environment is constructed, and multiple agents (such as coaches or assistants of different disciplines) are initialized so that they have their own observation range and action capabilities, and the development path of sports students is jointly optimized through cooperation and competition mechanisms. Next, the cumulative rewards for short-term behavior and long-term goal achievement are defined to form a preliminary reward mechanism, and the inverse reinforcement learning technology is used to infer the implicit objective function from the expert demonstration to optimize the reward mechanism. Then, a deep deterministic policy gradient algorithm is used in combination with a confrontational generative network to simulate the training scenario, provide training suggestions, and realize the real-time transmission of dynamic data through a high-frequency data acquisition device. The dynamic data is pre-processed using a time series prediction model, smoothing processing, and an adaptive filter to ensure high-quality state feedback. Based on the optimized reward mechanism and high-quality state feedback, different strategy variants are explored in combination with dual Q learning, meta-learning, and evolutionary strategies to find stable and efficient decision-making rules. A sentiment analysis toolkit is developed to parse unstructured feedback information, and the Bayesian optimization algorithm is used to optimize the parameter configuration to generate a comprehensive evaluation result. Finally, the preliminary development path plan is fine-tuned based on the comprehensive evaluation results, the path that best promotes the growth of athletes is selected, and the target development path plan is generated based on individual needs and changes in the external environment.

[0072] Suppose a college basketball team uses an advanced integrated management system to optimize the training program for players. The system first builds a multi-agent system framework, which includes agents with different roles such as basketball coaches, physical coaches, and psychological counselors. Each agent has its own observation range and action capabilities. These agents jointly optimize the development path of each player through cooperation and competition mechanisms. The system defines the immediate rewards for short-term behaviors (such as completing specific training tasks) and the cumulative rewards for achieving long-term goals (such as improving competition results), forming a preliminary reward mechanism, and inferring the implicit objective function from expert demonstrations through inverse reinforcement learning technology to optimize the reward mechanism. Then, the system uses a deep deterministic policy gradient algorithm combined with a generative adversarial network to simulate training scenarios, providing personalized training suggestions for each player, and deploying high-frequency data acquisition equipment (such as heart rate monitors and sports trackers) to achieve real-time data streaming. The system uses time series prediction models and smoothing processing and adaptive filters to preprocess dynamic data to ensure high-quality state feedback. Based on the optimized reward mechanism and high-quality state feedback, the system combines double Q learning, meta-learning and evolutionary strategies to explore different strategy variants and find stable and efficient decision rules. In order to better understand unstructured feedback information, the system has developed a sentiment analysis toolkit that integrates natural language processing and computer vision technology to capture emotional tendencies, identify specific points for improvement or potential problems, and analyze feedback information from coaches, players themselves, and third-party reviews. Finally, the system uses the Bayesian optimization algorithm to optimize the configuration of key parameters, generate comprehensive evaluation results, and fine-tune the initial development path planning based on these results, select the path that best promotes the growth of team members, and generate a target development path planning based on personalized needs and changes in the external environment. This method not only improves resource utilization and training effects, but also promotes the comprehensive development and competitive level of each team member.

[0073] Optionally, step 102 constructs a personal growth trajectory map for each athlete based on the dynamic data stream of the athlete, including: preprocessing the dynamic data stream of the athlete received and integrated from multiple channels to determine the quality and consistency of the data to obtain a high-quality dynamic data stream; defining and processing the nodes and edges in the personal growth trajectory map according to the high-quality dynamic data stream, converting the information at each time point into nodes, and representing the logical relationship or causal relationship between different nodes as edges to generate a preliminary personal growth trajectory framework, wherein the information at each time point includes training performance, competitive results, physical function indicators, and psychological state assessment; using a time series analysis method to model the preliminary personal growth trajectory framework to capture data changes over time. trends and patterns, analyze the development characteristics of sports students at different stages, identify potential influencing factors and turning points of the potential influencing factors, and obtain a personal growth trajectory map with a time dimension; combine domain knowledge and statistical analysis technology to conduct in-depth mining and processing on the personal growth trajectory map with a time dimension, generate a personal growth trajectory map with semantic interpretation, obtain the specific performance of sports students at various time points, and use the inherent connections between various data to generate a personal growth trajectory map with deep analysis; use visualization tools and techniques to display the personal growth trajectory map with deep analysis in the form of a graphical interface, discover key information and support decision-making through interactive charts and animation demonstrations, and generate a personal growth trajectory map for each sports student.

[0074] In this step, the personal growth trajectory map of each sports student is constructed based on the dynamic data stream of sports students, including preprocessing the dynamic data stream of sports students from multiple channels to ensure the quality and consistency of the data, so as to obtain high-quality dynamic data streams. These data contain at least information such as training performance, competitive results, physical function indicators, and psychological state assessment, which are used to comprehensively reflect the development status of sports students at different time points. Next, based on the high-quality dynamic data stream, the nodes and edges in the personal growth trajectory map are defined, the information at each time point is converted into nodes, and the logical relationship or causal relationship between different nodes is represented as edges to generate a preliminary personal growth trajectory framework. Using the time series analysis method, the preliminary personal growth trajectory framework is modeled and processed to capture the trend and pattern of data changes over time, analyze the development characteristics of sports students at different stages, and identify potential influencing factors and their turning points, so as to obtain a personal growth trajectory map with a time dimension. Combining domain knowledge and statistical analysis technology, the personal growth trajectory map with a time dimension is deeply mined and processed to generate a semantically interpretable personal growth trajectory map, revealing the specific performance and internal connection of each time point. Finally, using visualization tools and techniques, the deeply analyzed personal growth trajectory map is displayed in the form of a graphical interface. Through interactive charts and animation demonstrations, it helps to discover key information and support decision-making, and ultimately generates a personal growth trajectory map for each sports student.

[0075] In the embodiment of the present application, the system pre-processes the dynamic data streams of sports students from multiple channels to ensure the quality and consistency of the data and obtain high-quality dynamic data streams. Then, based on these high-quality data, the nodes and edges in the personal growth trajectory map are defined, and the information at each time point (such as training performance, competitive results, physical function indicators, and psychological state assessment) is converted into nodes, and the logical relationship or causal relationship between different nodes is represented as an edge to generate a preliminary personal growth trajectory framework. Then, the preliminary framework is modeled using the time series analysis method to capture the trend and pattern of data changes over time, analyze the development characteristics of sports students at different stages, identify potential influencing factors and their turning points, and form a personal growth trajectory map with a time dimension. Subsequently, combined with domain knowledge and statistical analysis techniques, the time dimension map is deeply mined and processed to generate a semantically interpretable personal growth trajectory map, revealing the specific performance and internal connection of each time point. Finally, using visualization tools and techniques, the deeply parsed map is displayed in the form of a graphical interface, and through interactive charts and animation demonstrations, coaches and managers are helped to discover key information and support decision-making, and finally a personal growth trajectory map for each sports student is generated.

[0076] Suppose a university track and field team uses an advanced integrated management system to optimize the training program for team members. The system first pre-processes the received multi-source data (such as training data uploaded by smart wearable devices, competition results reports, regular physical function test results, and psychological state self-assessment forms) to ensure the consistency and quality of the data and obtain high-quality dynamic data streams. Then, based on these high-quality data, the system defines the nodes and edges in the personal growth trajectory map, converts the information at each time point (such as training performance, competitive results, physical function indicators, and psychological state assessment) into nodes, and represents the logical relationship or causal relationship between different nodes as edges, generating a preliminary personal growth trajectory framework. Then, the system uses the time series analysis method to model the preliminary framework, capture the trend and pattern of data changes over time, analyze the development characteristics of each team member at different stages, identify potential influencing factors and their turning points, and form a personal growth trajectory map with a time dimension. In order to have a deeper understanding of these data, the system combines domain knowledge and statistical analysis techniques to conduct in-depth mining of the time dimension map, generating a semantically interpretable personal growth trajectory map, revealing the specific performance and internal connection of each time point. Finally, the system uses visualization tools and technologies to display the deeply analyzed graphs in the form of a graphical interface. Through interactive charts and animations, it helps coaches and managers discover key information and support decision-making. For example, a coach can intuitively see through a chart that the reason why a player's physical fitness declines in a specific period of time is that the training intensity is too high, so as to adjust the training plan. This method not only improves the efficiency of data utilization, but also promotes the formulation of personalized training programs, improving the overall training effect and personal development potential.

[0077] Optionally, in step 106, a multi-dimensional feedback mechanism is established based on the target development path planning, by collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model to parse and process the feedback information to obtain an evaluation result, and the target development path planning is optimized based on the evaluation result, including: using a multi-dimensional feedback channel to collect and process feedback information from different sources such as coaches, athletes themselves and third-party reviewers to obtain rich and comprehensive feedback data; performing preprocessing operations based on the rich and comprehensive feedback data, combined with anonymization processing to protect personal information security, and generating high-quality feedback data, the preprocessing operations including text cleaning, format unification and noise removal; based on a hybrid sentiment analysis model that integrates natural language processing and computer vision technology, the high-quality The feedback data is parsed and processed to identify emotional tendencies and capture specific semantic content and potential emotional factors, and a detailed emotional analysis report is generated; using the detailed emotional analysis report, combined with the core literacy framework, the relationship between nodes and edges in the personal growth trajectory map is analyzed and processed, preliminary key evaluation indicators are extracted, and target key evaluation indicators are generated. The preliminary key evaluation indicators include those reflecting the training effect, psychological state and physical function progress; based on the target key evaluation indicators, a comprehensive evaluation report is formed to summarize the advantages and disadvantages of the path planning, and specific improvement suggestions are put forward as the basis for optimizing the path planning, and a comprehensive evaluation result is obtained; according to the comprehensive evaluation result, the existing target development path planning is fine-tuned and optimized, the education resource allocation plan is updated and the training plan configuration is adjusted to generate an optimized final target development path planning.

[0078] In this step, feedback data from multiple sources, including but not limited to the professional opinions of coaches, the feelings and self-assessment of athletes themselves, and opinions from experts or public reviewers, are used to fully understand the development status of athletes and the effectiveness of the path. The preprocessing operation ensures the quality of the feedback data, including text cleaning, format unification and noise removal, and combines anonymization processing to protect personal information security. Next, a hybrid sentiment analysis model that integrates natural language processing and computer vision technology is used to parse high-quality feedback data, identify sentiment tendencies, capture specific semantic content and potential sentiment factors, and generate a detailed sentiment analysis report. Finally, based on the sentiment analysis report and the core literacy framework, key evaluation indicators are extracted, such as those reflecting the training effect, psychological state, and physical function progress, to generate a comprehensive evaluation report as the basis for optimizing path planning, thereby updating the education resource allocation plan and adjusting the training plan configuration, and finally forming an optimized target development path planning.

[0079] In the embodiment of the present application, the system establishes a multi-dimensional feedback channel to collect feedback information from different sources such as coaches, sports students themselves and third-party reviews to obtain rich and comprehensive feedback data. Then, the collected data is pre-processed, including text cleaning, format unification and noise removal, and anonymization is implemented to protect personal information security and ensure the generation of high-quality feedback data. Next, the high-quality feedback data is parsed using a hybrid sentiment analysis model that integrates natural language processing and computer vision technology to identify emotional tendencies and capture specific semantic content and potential emotional factors, and generate a detailed sentiment analysis report. Subsequently, combined with the core literacy framework, the relationship between nodes and edges in the personal growth trajectory map is analyzed, and preliminary key evaluation indicators such as training effect, psychological state and physical function progress are extracted to generate target key evaluation indicators. Based on these indicators, the system will form a comprehensive evaluation report, summarize the advantages and disadvantages of path planning, and put forward specific improvement suggestions as the basis for optimizing path planning. Finally, according to the comprehensive evaluation results, the existing target development path planning is fine-tuned and optimized, the education resource allocation plan is updated, and the training plan configuration is adjusted to generate the optimized final target development path planning to better support the development of sports students.

[0080] In a professional basketball training camp, the management introduced an advanced feedback system to optimize the players' target development path. The system first established a multi-dimensional feedback channel to collect feedback information from multiple angles, such as the professional guidance of coaches, the players' own experience sharing, and the observations and suggestions of external experts or fans, to ensure rich and comprehensive feedback data. Then, the system pre-processed the collected raw data, including cleaning irrelevant text, unifying the input format, removing noise information, and anonymizing the information of all participants to ensure personal privacy, thereby generating high-quality feedback data. Then, a hybrid sentiment analysis model that combines natural language processing and computer vision technology was used to analyze these high-quality feedback data, which not only identified positive or negative sentiment tendencies, but also captured the specific semantic content and potential emotional factors behind the comments, and generated a detailed sentiment analysis report. Based on this report and the core literacy framework of basketball, the system analyzed the relationship between nodes and edges in the personal growth trajectory map, and extracted key evaluation indicators that reflect the training effect, psychological state, and physical function improvement. Based on these indicators, the management formed a comprehensive evaluation report on the development of each player, pointed out the advantages and problems of the current path planning, and put forward specific improvement suggestions. Finally, the management fine-tuned and optimized the existing target development path based on these suggestions, such as reallocating training resources, adjusting training intensity and schedule, etc., and finally generated an optimized final target development path plan for each player, so that each player can maximize their potential in the most suitable environment and achieve their career development goals.

[0081] Figure 2 A schematic diagram of a comprehensive management system for the development of core competencies of sports students based on big data is provided for the present application embodiment. Figure 2 As shown, the system includes: A receiving module 21 is used to receive and integrate sports student dynamic data streams from multiple channels, wherein the sports student dynamic data streams at least include the sports student's training performance, competitive results, physical function indicators and psychological state evaluation; A construction module 22 is used to construct a personal growth trajectory map of each athlete based on the dynamic data stream of the athlete, and the personal growth trajectory map is used to reflect various data of the athlete at different time points and their mutual relationships; The analysis module 23 is used to analyze the relationship between nodes and edges in the personal growth trajectory map by using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students, and to optimize the matching of educational resources and training plans suitable for sports students based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, to obtain a matching result, which refers to the result of optimal resource allocation and optimal configuration of training effects; A push module 24 is used to accurately push the personalized learning materials and training suggestions corresponding to the matching results to generate a preliminary development path plan; The adjustment module 25 is used to use a reinforcement learning algorithm to monitor in real time the progress and changes of the sports students in the process of executing the preliminary development path planning, obtain monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results to obtain a target development path planning; Processing module 26 is used for the target development path planning and to establish a multi-dimensional feedback mechanism. It collects feedback information from coaches, athletes themselves and third-party reviewers, and uses a hybrid sentiment analysis model to parse and process the feedback information to obtain evaluation results, and optimizes the target development path planning based on the evaluation results.

[0082] Figure 2 The comprehensive management system for the core competencies of sports students based on big data can be implemented Figure 1 The implementation principle and technical effects of the comprehensive management method for the core literacy of sports students based on big data described in the embodiment shown will not be repeated. The specific way in which each module and unit performs operations in the comprehensive management system for the core literacy of sports students based on big data in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0083] In one possible design, Figure 2 A comprehensive management system for the core competencies of sports students based on big data in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0084] The processing component 32 is used to: receive and integrate sports students' dynamic data streams from multiple channels, the sports students' dynamic data streams at least including the sports students' training performance, competitive results, physical function indicators and psychological state assessment; construct a personal growth trajectory map for each sports student based on the sports students' dynamic data streams, the personal growth trajectory map is used to reflect the various data of the sports students at different time points and their mutual relationships; use an association rule mining algorithm to analyze the relationship between nodes and edges in the personal growth trajectory map to identify key factors and turning points that affect the growth of sports students, and according to the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, optimize the matching of educational resources and training plans suitable for sports students to obtain matching results. The matching result refers to the result of optimal resource allocation and optimal configuration of training effects; the personalized learning materials and training suggestions corresponding to the matching result are accurately pushed and processed to generate a preliminary development path plan; the progress and changes of the athletes in the process of executing the preliminary development path plan are monitored in real time by using a reinforcement learning algorithm to obtain monitoring results, and the preliminary development path plan is dynamically adjusted based on the monitoring results to obtain a target development path plan; based on the target development path plan, a multi-dimensional feedback mechanism is established, by collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model to parse and process the feedback information to obtain an evaluation result, and the target development path plan is optimized based on the evaluation result.

[0085] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0086] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0087] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0088] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0089] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0090] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0091] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is a comprehensive management method for the core competencies of sports students based on big data.

[0092] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0093] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0094] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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 application.

Claims

1. A comprehensive management method for the core competencies of sports students based on big data, characterized in that: include: Receiving and integrating sports student dynamic data streams from multiple channels, wherein the sports student dynamic data streams at least include the sports student's training performance, competitive results, physical function indicators and psychological state assessment; Building a personal growth trajectory map for each athlete based on the dynamic data stream of the athlete, wherein the personal growth trajectory map is used to reflect the data of the athlete at different time points and their interrelationships; Analyze the relationship between nodes and edges in the personal growth trajectory map using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students, and optimize the matching of educational resources and training plans suitable for sports students based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, to obtain a matching result, which refers to the result of optimal resource allocation and optimal configuration of training effects; Accurately push personalized learning materials and training suggestions corresponding to the matching results to generate a preliminary development path plan; Using a reinforcement learning algorithm, real-time monitoring of the progress and changes of the athletes in the process of executing the preliminary development path planning is performed to obtain monitoring results, and the preliminary development path planning is dynamically adjusted based on the monitoring results to obtain a target development path planning; Based on the target development path planning, a multi-dimensional feedback mechanism is established. By collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model, the feedback information is analyzed and processed to obtain evaluation results, and the target development path planning will be optimized based on the evaluation results.

2. The method according to claim 1, characterized in that: The association rule mining algorithm is used to analyze the relationship between nodes and edges in the personal growth trajectory map to identify the key factors and turning points that affect the growth of athletes, and based on the key factors and turning points, combined with the pre-set core literacy framework and particle swarm optimization algorithm, the educational resources and training plans suitable for athletes are optimally matched to obtain matching results, including: The association rule mining algorithm is used to analyze the dynamic data stream of sports students after cleaning and normalization, and the training performance, competitive results, physical function indicators and psychological state evaluation at each time point are converted into nodes in the graph, and the logical relationship or causal relationship between different nodes is represented as edges to generate a personal growth trajectory graph; Based on the personal growth trajectory map, an association rule mining algorithm is applied to explore the relationship between the nodes and edges, and by setting the minimum support and confidence thresholds, frequent item sets and strong association rules are found to obtain the key factors affecting the growth of athletes and their turning points; According to the strong association rules, combined with the knowledge of domain experts, the key factors affecting the growth of athletes and their turning points are analyzed and processed, the factors that are crucial to the development of athletes and the situations in which significant changes occur are determined, and a list of key factors and a set of turning points are generated; Using a pre-set core literacy framework for sports students, matching the list of key factors and the set of turning points, determining the core literacy aspects that need to be strengthened or adjusted, and generating personalized literacy development goals, the pre-set core literacy framework for sports students includes physical health, mental health, and sports skills; Using the particle swarm optimization algorithm, search and process the educational resource allocation plan and training plan configuration that meet the personalized literacy development goals, update the particle position using its own experience and group experience, find the global optimal solution, and obtain the most optimized resource allocation plan and training plan; According to the optimized resource allocation scheme and training plan, personalized matching is carried out for the specific situation of the sports students, and the optimization of personalized education and training is achieved in combination with individual differences, and specific education resource allocation and training plan arrangements are generated to obtain matching results.

3. The method according to claim 2, characterized in that The particle swarm optimization algorithm is used to search and process the educational resource allocation scheme and training plan configuration that meet the personalized literacy development goals, and the particle position is updated using the own experience and group experience to find the global optimal solution to obtain the optimal resource allocation scheme and training plan, including: Using the random distribution principle, the position and speed of the particle group are initialized to obtain an initial particle group, a fitness function is set according to the personalized literacy development goal, the fitness value of the initial particle group is calculated, and a fitness evaluation result is generated; Based on the fitness evaluation result, combined with the best historical position of the particle itself and the best historical position of the entire group, the speed and position of the particle are updated to make the particle approach a better solution, thereby obtaining an updated particle state; The updated particle state is used to iterate all particles, the fitness value is re-evaluated in each iteration, and the best historical position of the particle itself and the best historical position of the entire group are updated until a preset termination condition is met, and an iterative optimization result is generated. According to the iterative optimization result, the optimal resource allocation and training plan arrangement are obtained. The preset termination condition refers to stopping the iterative search when the maximum number of iterations reached during the algorithm iteration or the change in the fitness value is less than a set threshold.

4. The method according to claim 1, characterized in that The method of using a reinforcement learning algorithm to monitor in real time the progress and changes of the athletes in the process of executing the preliminary development path planning, obtaining monitoring results, and dynamically adjusting the preliminary development path planning based on the monitoring results to obtain the target development path planning includes: Using a multi-agent system framework, multiple agents are initialized so that the multiple agents have their own observation range and action capabilities, and the development path of sports students is jointly optimized through cooperation and competition mechanisms to build a multi-agent collaborative environment. The multiple agents include coaches or assistants from different disciplines. Based on the multi-agent collaborative environment and combined with the hierarchical reinforcement learning method, the short-term behavior immediate reward and the long-term goal achievement cumulative reward are defined to obtain a preliminary reward mechanism, and the inverse reinforcement learning technology is used to infer the implicit objective function from the expert demonstration, and the preliminary reward mechanism is optimized to generate a reward mechanism that meets the best practice standards; A deep deterministic policy gradient algorithm combined with a generative adversarial network is used to simulate training scenarios, provide training suggestions for sports students, deploy high-frequency data acquisition equipment to achieve real-time data stream transmission, obtain dynamic data, apply time series prediction models and smoothing processing, and use adaptive filters to pre-process the dynamic data to obtain high-quality state feedback; Based on the reward mechanism that meets the best practice standards and the high-quality status feedback, dual-Q learning, meta-learning and evolutionary strategies are combined to explore different strategy variants, find stable and efficient decision rules, based on the decision rules, analyze unstructured feedback information by developing a sentiment analysis toolkit, and use the Bayesian optimization algorithm to optimize parameter configuration to obtain comprehensive evaluation results, and fine-tune and develop path planning based on the comprehensive evaluation results to generate a target development path plan.

5. The method according to claim 4, characterized in that Based on the reward mechanism that meets the best practice standards and the high-quality state feedback, dual Q learning, meta-learning and evolutionary strategies are combined to explore different strategy variants, find stable and efficient decision rules, analyze unstructured feedback information based on the decision rules by developing a sentiment analysis toolkit, and use the Bayesian optimization algorithm to optimize parameter configuration to obtain a comprehensive evaluation result, fine-tune and develop path planning based on the comprehensive evaluation result, and generate a target development path planning, including: Using the reward mechanism that meets the best practice standards and the high-quality state feedback, the optimization search process is initialized, the process of finding the optimal training and development strategy that maximizes the cumulative reward and adapts to the dynamic changes of athletes is started, and the initialization conditions and environment settings are generated; According to the double Q learning algorithm, the overestimation problem is identified and reduced, and a meta-learning method is introduced to enable the system to quickly adapt to new environments or task changes, and the strategies in different situations are generalized based on the initialization conditions and the environment settings to obtain a more stable and generalized strategy; Applying evolutionary strategies to simulate the process of natural selection, exploring the more stable and generalized strategies, generating candidate solutions, and screening and optimizing the candidate solutions based on their performance to obtain efficient and stable decision rules and generate a series of optimized strategy variants; Based on the series of optimized strategy variants, a sentiment analysis toolkit is developed, which integrates natural language processing and computer vision technology to deeply analyze and process unstructured feedback information to obtain detailed feedback analysis results. The sentiment analysis toolkit includes capturing sentiment tendencies and identifying specific improvement points or potential problems. The unstructured feedback information includes feedback information from coaches, athletes themselves, and third-party reviewers; Based on the detailed feedback analysis results, the Bayesian optimization algorithm is used to optimize the configuration of key parameters, and the proxy model is constructed to approximate the objective function, obtain the global optimal solution, generate the optimized parameter configuration, and obtain the comprehensive evaluation results; Based on the comprehensive evaluation results, the preliminary development path plan is fine-tuned. By comparing the effects of different plans, the path that best promotes the growth of athletes is selected, and the target development path plan is generated in combination with individual needs and changes in the external environment.

6. The method according to claim 1, characterized in that The constructing of a personal growth trajectory map of each athlete based on the athlete's dynamic data stream includes: Preprocessing the received and integrated sports student dynamic data streams from multiple channels to determine the quality and consistency of the data and obtain high-quality dynamic data streams; Based on the high-quality dynamic data stream, nodes and edges in the personal growth trajectory map are defined and processed, the information at each time point is converted into nodes, and the logical relationship or causal relationship between different nodes is represented as edges, so as to generate a preliminary personal growth trajectory framework, wherein the information at each time point includes training performance, competitive results, physical function indicators and psychological state assessment; Using time series analysis methods, the preliminary personal growth trajectory framework is modeled and processed to capture the trend and pattern of data changes over time, analyze the development characteristics of sports students at different stages, and identify potential influencing factors and turning points of the potential influencing factors, so as to obtain a personal growth trajectory map with a time dimension; Combining domain knowledge and statistical analysis technology, the personal growth trajectory map with time dimension is deeply mined and processed to generate a personal growth trajectory map with semantic interpretation, so as to obtain the specific performance of sports students at various time points, and use the internal connection between various data to generate a personal growth trajectory map with deep analysis; By using visualization tools and techniques, the in-depth analyzed personal growth trajectory map is displayed in the form of a graphical interface. Through interactive charts and animation demonstrations, key information is discovered and decision-making is supported to generate a personal growth trajectory map for each sports student.

7. The method according to claim 1, characterized in that Based on the target development path planning, a multi-dimensional feedback mechanism is established, by collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model to parse and process the feedback information to obtain evaluation results, and the target development path planning is optimized based on the evaluation results, including: Utilize multi-dimensional feedback channels to collect and process feedback information from coaches, athletes themselves, and third-party reviewers to obtain feedback data; Performing preprocessing operations on the feedback data, combined with anonymization processing to protect personal information security, and generating high-quality feedback data, wherein the preprocessing operations include text cleaning, format unification, and noise removal; Based on a hybrid sentiment analysis model that integrates natural language processing and computer vision technology, the high-quality feedback data is analyzed and processed to identify sentiment tendencies and capture specific semantic content and potential sentiment factors, generating a detailed sentiment analysis report; Utilizing the detailed sentiment analysis report and combining it with the core literacy framework, analyzing and processing the relationship between nodes and edges in the personal growth trajectory map, extracting preliminary key evaluation indicators, and generating target key evaluation indicators, wherein the preliminary key evaluation indicators include those reflecting the training effect, psychological state, and physical function improvement; Based on the target key evaluation indicators, a comprehensive evaluation report is formed to summarize the advantages and disadvantages of the path planning, and specific improvement suggestions are put forward as the basis for optimizing the path planning to obtain a comprehensive evaluation result; According to the comprehensive evaluation results, the existing target development path plan is fine-tuned and optimized, the education resource allocation plan is updated and the training plan configuration is adjusted to generate an optimized final target development path plan.

8. A comprehensive management system for the core competencies of sports students based on big data, characterized by: include: A receiving module, used for receiving and integrating sports students' dynamic data streams from multiple channels, wherein the sports students' dynamic data streams at least include the sports students' training performance, competitive results, physical function indicators and psychological state evaluation; A construction module, used to construct a personal growth trajectory map of each athlete based on the dynamic data stream of the athlete, wherein the personal growth trajectory map is used to reflect various data of the athlete at different time points and their mutual relationships; An analysis module is used to analyze the relationship between nodes and edges in the personal growth trajectory map using an association rule mining algorithm to identify key factors and turning points that affect the growth of sports students, and to optimize the matching of educational resources and training plans suitable for sports students based on the key factors and turning points, combined with a pre-set core literacy framework and a particle swarm optimization algorithm, to obtain a matching result, which refers to the result of optimal resource allocation and optimal configuration of training effects; A push module, used to accurately push personalized learning materials and training suggestions corresponding to the matching results to generate a preliminary development path plan; An adjustment module is used to use a reinforcement learning algorithm to monitor in real time the progress and changes of the athletes in the process of executing the preliminary development path planning, obtain monitoring results, and dynamically adjust the preliminary development path planning based on the monitoring results to obtain a target development path planning; The processing module is used for the target development path planning and establishes a multi-dimensional feedback mechanism. By collecting feedback information from coaches, athletes themselves and third-party reviewers, and using a hybrid sentiment analysis model, the feedback information is analyzed and processed to obtain evaluation results, and the target development path planning is optimized based on the evaluation results.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a comprehensive management method for the core competencies of sports students based on big data as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a comprehensive management method for the core competencies of sports students based on big data is implemented as described in any one of claims 1 to 7.

Images