Sports art personnel information management method and system

Abstract

The invention belongs to the technical field of data management, and discloses a sports art personnel information management method and system. Comprising the following steps: collecting personnel basic information and personnel professional information of different sports art personnel; integrating the personnel basic information and the personnel professional information, and constructing a development trajectory map; performing feature extraction on the development trajectory map to generate personnel feature information; carrying out quantitative analysis on the personnel characteristic information, and evaluating special technical capabilities of different sports art personnel; according to the special technical capability, a training plan is automatically made; the comprehensive ability of different sports art personnel is quantitatively evaluated in combination with the personnel feature information and the special technical ability; according to the invention, full-life-cycle intelligent management of the sports art personnel information is realized, the personnel information can be comprehensively tracked and managed in real time, the management efficiency is improved, and the requirements of refined and intelligent cultivation management are met.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and more particularly, to a method and system for managing information of sports and arts personnel. Background Art

[0002] With the rapid development of the sports industry, especially the increasing popularity and specialization of sports and arts projects, information management of sports and arts personnel has become an important issue. Sports and arts personnel refer to people engaged in professional activities, performances or competitions related to sports and arts, such as rhythmic gymnastics athletes, figure skaters, trampoline athletes, etc. In the field of modern sports and arts, personnel management not only involves basic information of personnel, but also includes multi-dimensional data such as training status, competition results, physical health status, historical performance, etc. These data are usually scattered in different departments, systems or documents, which can easily cause information lag, inaccuracy or missing, and thus affect decision-making and daily management efficiency. In order to improve management efficiency, optimize resource allocation, and enhance the comprehensive competitiveness of sports and arts projects, there is an urgent need for an integrated information management method that can comprehensively, real-timely and accurately track and manage various types of information of sports and arts personnel.

[0003] The patent with publication number CN118229245A discloses a blockchain-based Internet sports autonomous collaborative management system and method; it includes: athlete side, coach side, management side and smart contract module, etc., which realizes functions such as personal data storage, training plan monitoring, contract management, reward mechanism design and identity authentication. The system realizes safe, transparent and tamper-proof sports data storage and traceability through the blockchain network. This invention helps to build a safe, transparent and trustworthy Internet sports collaborative management platform through user completion of registration, data upload, monitoring interaction, contract management, reward design, data sharing and collaboration, etc., to achieve comprehensive sports information management.

[0004] However, although the above technology has built a secure and transparent sports collaboration management platform based on blockchain to realize personnel information management, it mainly focuses on the establishment of data transparency and security mechanisms; it lacks systematic analysis of personal development trajectories, quantitative assessment of capabilities, and intelligent training planning mechanisms during the sports careers of different sports and arts personnel, making it difficult to meet the actual needs of refined and intelligent training and management of sports and arts personnel.

[0005] In view of this, the present invention proposes a sports arts personnel information management method and system to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for managing information of sports and arts personnel, comprising:

[0007] Collect basic information of personnel in different sports and arts;

[0008] Dynamically record the professional information of different sports and arts personnel during their careers;

[0009] Based on a unified timeline, integrate basic and professional information of personnel to build a development trajectory map;

[0010] Using data mining technology, we extract features from the development trajectory map and generate personnel feature information;

[0011] Conduct quantitative analysis of personnel characteristic information and evaluate the specialized technical capabilities of personnel in different sports and arts;

[0012] Based on specific technical capabilities and combined with the principles of sports physiology, a multi-objective optimization algorithm is used to automatically formulate training plans;

[0013] Combining personnel characteristic information and special technical capabilities, and conducting multi-dimensional analysis, we can quantitatively evaluate the comprehensive capabilities of different sports and arts personnel.

[0014] Furthermore, the basic personnel information includes identity information, contact information, physical information and project information; the professional personnel information includes training information, competition information, physical information, psychological information and injury information;

[0015] The method for constructing a development trajectory map includes:

[0016] Obtain the time fields corresponding to each set of personnel basic information and personnel professional information; convert all time fields into a unified time format, and form each set of personnel basic information and the corresponding personnel professional information into a set of personnel information sets, with the personnel information sets corresponding to the personnel basic information one-to-one, where each set of personnel information sets includes multiple sets of personnel professional information;

[0017] Set the time granularity, that is, determine the length of the time unit; based on the set time granularity, build timelines, each of which corresponds to a set of personnel information. is the number of groups of personnel information sets; for each time unit on each time axis, a node is created; an index structure is established in each time axis; each data in each group of personnel information sets is stored in the corresponding node in the corresponding time axis in chronological order according to the corresponding time field, and a development trajectory map corresponding to each sports and arts personnel is constructed.

[0018] Furthermore, the personnel characteristic information includes basic characteristics, training characteristics, competition characteristics, physical characteristics, psychological characteristics and injury characteristics;

[0019] The method for generating personnel characteristic information includes:

[0020] Mark all non-numeric data in personnel basic information and personnel professional information as text data, set different numerical labels for each text data in turn, and mark them as information labels; replace the text data in each development trajectory map with the corresponding information label;

[0021] Set the window length to time window, is an integer greater than 1; count the number of storage nodes in each development trajectory map and mark them as the number of nodes. The storage nodes are the nodes that actually store data; preset the prediction threshold, which is the minimum number of data groups required to train the extraction model; subtract the number of each node from Add 1 to obtain the maximum number; compare each maximum number with the prediction threshold in turn, mark the development trajectory map with a maximum number less than the prediction threshold as an insufficient map, and mark the development trajectory map with a maximum number greater than or equal to the threshold as a sufficient map; construct a corresponding feature generation model for each insufficient map and sufficient map in turn, the feature generation model corresponds to the sports and arts personnel one by one, and the feature generation model is a deep neural network model;

[0022] According to the set time window, the corresponding starting point and end point are obtained from each development trajectory map. The starting point is the latest node in the time field, and the end point is all nodes with a time interval of no more than Among the nodes, the node with the earliest time field; obtain all the data between the starting point and the end point in each development trajectory map and mark them as feature analysis data; input each set of feature analysis data into the corresponding feature generation model to predict the corresponding personnel feature information.

[0023] Furthermore, the method of constructing a feature generation model for a sufficient graph includes:

[0024] Mark the previous node of the sufficient graph corresponding to the starting point as a training point, and divide all the data between the training point and the end point into Different sets of training data, and according to A feature generation model is constructed using a set of different training data; each set of training data includes continuous The data corresponding to each node, , is the number of nodes in the sufficient graph;

[0025] right The corresponding feature analysis data are set for each set of training data in turn, and each set of training data and the corresponding feature analysis data are converted into a corresponding set of feature vectors in turn; each set of feature vectors is used as the input of the feature generation model, and the feature generation model uses a set of predicted feature analysis data corresponding to each set of training data as the output, and the actual feature analysis data corresponding to each set of training data as the prediction target, and the actual feature analysis data is the pre-set feature analysis data corresponding to the training data; Different sets of training data are divided into training sets and test sets. The feature generation model is trained according to the training set. After each training round, the feature generation model is tested according to the test set, and the prediction error is calculated. According to the prediction error, the error change value is calculated; the error change value is compared with the preset change threshold. If the error change value is greater than or equal to the change threshold, the training continues. If the error change value is less than the change threshold, the training is stopped to complete the construction of the feature generation model.

[0026] Furthermore, the method of constructing a feature generation model for the deficiency graph includes:

[0027] According to the personnel information set of each sports and arts personnel, the density clustering algorithm is used to cluster all sports and arts personnel to obtain clusters, is an integer greater than 1; mark the sports and arts personnel corresponding to the insufficient graph as missing personnel, obtain the cluster corresponding to the missing personnel, and mark it as a supplementary cluster; use the similarity measurement method to calculate the similarity between each sports and arts personnel in the supplementary cluster and the missing personnel in turn, and mark the sports and arts personnel with the greatest similarity as a supplementary personnel; add the prediction threshold to , get the quantity threshold; subtract the number of nodes from the quantity threshold to get the insufficient quantity; take the end point corresponding to the insufficient graph as the insufficient starting point, and The empty node of the node is used as the insufficient end point. The empty node is the node that does not actually store data. =The number of insufficient personnel; mark the development trajectory map corresponding to the supplementary personnel as the supplementary map, and mark the node with the same time field as the insufficient starting point as the supplementary starting point, and mark the node with the same time field as the insufficient end point as the supplementary end point; obtain all the data between the supplementary starting point and the supplementary end point, and mark them as supplementary data. The supplementary data does not include the data corresponding to the supplementary starting point and the data corresponding to the supplementary end point; divide all the data in the insufficient map and the supplementary data into Different sets of build data, and according to A set of different construction data is used to construct a feature generation model; The method of constructing feature generation model based on different construction data is different from The method of constructing feature generation models for different sets of training data is consistent. is the prediction threshold.

[0028] Furthermore, the steps of evaluating the special technical capabilities of different sports and arts personnel include:

[0029] Step S101: Taking training characteristics, competition characteristics, and physical characteristics as technical characteristic data; constructing multiple fuzzy sets for each data in the technical characteristic data;

[0030] Step S102: converting the technical characteristic data of each sports artist into the membership degree of each corresponding fuzzy set through fuzzification technology;

[0031] Step S103: defining fuzzy rules;

[0032] Step S104: Match each set of fuzzified technical feature data with fuzzy rules respectively, and perform fuzzy reasoning using a fuzzy reasoning method to obtain the fuzzy reasoning results corresponding to each sports and arts personnel. The fuzzy reasoning results are the membership levels of each special technical ability level, which include advanced, intermediate, and low levels.

[0033] Step S105: Set the scoring space. The range of the scoring space is , is an integer greater than 1; the scoring space is evenly divided into three level spaces, and the level spaces correspond to the levels of special technical capabilities one by one; the maximum value of each level space is added to the corresponding minimum value and then divided by 2 to obtain the mean value of each level space;

[0034] Step S106: Multiply the degree of affiliation of each special technical ability level corresponding to each sports and art personnel by the mean of the corresponding level space, and then add them up in sequence to obtain the total score of each sports and art personnel; add the degree of affiliation of each special technical ability level corresponding to each sports and art personnel in sequence to obtain the total degree of affiliation; divide the total value of the score of each sports and art personnel by the corresponding total degree of affiliation to obtain the technical score value of each sports and art personnel, and use it as the evaluation result of the special technical ability.

[0035] Furthermore, the method of formulating a training plan for a sports arts person includes:

[0036] Preset plan set, which includes Different training plans, is an integer greater than 1; different numerical labels are set for the training plans in the plan set in sequence and marked as plan labels. The range of plan labels is ;

[0037] Define the iterative process, which is: randomly select from the range of plan labels values, and all of them are taken as candidate solutions. , the candidate solutions correspond to the plan labels one by one; calculate the target value set corresponding to each candidate solution in turn, and Filter out the optimal solution from the candidate solutions;

[0038] Execute the iterative process. When the number of executions of the iterative process is greater than or equal to a preset number threshold, stop executing the iterative process and select the best solution from all the optimal solutions; use the training plan corresponding to the plan label of the best solution as the training plan for the corresponding sports and arts personnel;

[0039] Methods for calculating target value sets include:

[0040] Construct a target calculation model, which includes a physical fitness calculation model, a skill calculation model, and an injury calculation model. The construction method of each target calculation model is consistent with the construction method of the feature generation model, and all are deep neural network models; the evaluation results of the corresponding special technical capabilities of sports and arts personnel, the basic information of the personnel, and the plan labels corresponding to the candidate solutions are used as calculation data; the calculation data are input into each target calculation model respectively to predict the corresponding prediction value set; the prediction value set includes the physical fitness improvement effect, the skill improvement effect, and the injury risk; the inverse of the physical fitness improvement effect, the skill improvement effect, and the injury risk in the prediction value set is used as the target value set;

[0041] from Methods for selecting the optimal solution from candidate solutions include:

[0042] A preset proportion set is provided, where the proportion set includes a proportion coefficient corresponding to each target value in the target value set; each target value in the target value set corresponding to each candidate solution is multiplied by the corresponding proportion coefficient in the proportion set, and the results are added in sequence to obtain the total target value corresponding to each candidate solution; the total target value of each candidate solution is compared, and the candidate solution with the largest total target value is taken as the optimal solution.

[0043] Furthermore, the steps for quantitatively evaluating the comprehensive abilities of different sports and arts personnel include:

[0044] Step S201: Preset search range and the division coefficient , ;

[0045] Step S202: randomly selecting a sports arts person who is not marked as a selected person and marking him as the current person;

[0046] Step S203: Based on the division coefficient , from the search interval Divide into two split points and ;

[0047] Step S204: Calculate two segmentation points respectively and The corresponding matching coefficient will split the points The corresponding matching coefficient is marked as the first coefficient, and the split point The corresponding matching coefficient is marked as the second coefficient;

[0048] Step S205: Compare the first coefficient with the second coefficient; if the first coefficient is greater than or equal to the second coefficient, proceed to step S206; if the first coefficient is less than the second coefficient, proceed to step S207;

[0049] Step S206: Update the maximum value of the search interval as the split point , the minimum value of the search interval remains unchanged, and the process goes to step S208;

[0050] Step S207: Update the minimum value of the search interval as the split point , the maximum value of the search interval remains unchanged, and the process goes to step S208;

[0051] Step S208: Determine whether the segmentation is completed. If the segmentation is completed, proceed to step S209. If the segmentation is not completed, update the segmentation coefficient according to the matching coefficient, and re-divide two segmentation points from the search interval according to the updated segmentation coefficient. and , and returns to step S204;

[0052] Step S209: taking the average of the maximum and minimum values ​​corresponding to the search interval as the comprehensive ability of the current person, marking the current person as a selected person, and returning to step S202;

[0053] Step S210: Loop step S202 to step S209 until all sports and arts personnel are marked as selected personnel. The loop ends and the quantitative evaluation of the comprehensive capabilities of different sports and arts personnel is completed.

[0054] Furthermore, in step S203, the segmentation points are divided The method is: subtract 1 from , and then multiply by , get the split point ; Divide the split point The method is: Multiply , get the split point ;

[0055] In step S204, the matching coefficient calculation method includes: using the numerical value corresponding to the split point, the basic characteristics, psychological characteristics, injury characteristics, and the evaluation results of the specific technical ability of the current person as matching data, inputting the matching data into a pre-built matching analysis model, and predicting the corresponding matching coefficient; the construction method of the matching analysis model is consistent with the construction method of the feature generation model, and both are deep neural network models;

[0056] In step S208, the method for updating the segmentation coefficient according to the matching coefficient is as follows: presetting a matching threshold and comparing the matching coefficient with the matching threshold; if the matching coefficient is greater than or equal to the matching threshold, multiplying the matching coefficient by a preset first factor to obtain the first coefficient, subtracting the adjustment coefficient from the matching coefficient to obtain the first update coefficient, and updating the segmentation coefficient according to the first update coefficient; if the matching coefficient is less than the matching threshold, multiplying the matching coefficient by a preset second factor to obtain the second coefficient, adding the second coefficient to the matching coefficient to obtain the second update coefficient, and updating the segmentation coefficient according to the second update coefficient.

[0057] A sports and arts personnel information management system, which implements the sports and arts personnel information management method, comprises:

[0058] Information collection module, used to collect basic information of different sports and arts personnel;

[0059] The information recording module is used to dynamically record the professional information of different sports and arts personnel during their sports careers;

[0060] The information integration module is used to integrate basic and professional personnel information based on a unified timeline to construct a development trajectory map;

[0061] The information extraction module is used to extract features from the development trajectory map using data mining technology to generate personnel feature information;

[0062] The technical evaluation module is used to conduct quantitative analysis of personnel characteristics and evaluate the special technical capabilities of different sports and arts personnel;

[0063] The planning module is used to automatically formulate training plans based on specific technical capabilities and combined with sports physiology principles using a multi-objective optimization algorithm;

[0064] The comprehensive evaluation module is used to combine personnel characteristic information and special technical capabilities, conduct multi-dimensional analysis, and quantitatively evaluate the comprehensive capabilities of different sports and arts personnel.

[0065] The technical effects and advantages of the sports arts personnel information management method and system of the present invention are as follows:

[0066] By integrating the basic information and professional information of different sports and arts personnel, a development trajectory map is constructed; and data mining technology is used to extract personnel characteristic information to achieve quantitative analysis and evaluation of the special technical capabilities of different sports and arts personnel; at the same time, a multi-objective optimization algorithm is used to automatically formulate personalized training plans, which helps to improve the training effect of sports and arts personnel and ensure that training is carried out in the best physiological state; in addition, through multi-dimensional analysis, the comprehensive capabilities of different sports and arts personnel can be quantitatively evaluated, providing a basis for selecting outstanding talents and optimizing resource allocation; realizing intelligent management of the entire life cycle of sports and arts personnel information, it can comprehensively and in real time track and manage personnel information, improve management efficiency, enhance the overall competitiveness of sports and arts projects, and meet the needs of refined and intelligent training management. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a schematic diagram of a sports and arts personnel information management system according to embodiment 1 of the present invention;

[0068] Figure 2 This is a flow chart of a sports and arts personnel information management method according to embodiment 2 of the present invention. DETAILED DESCRIPTION

[0069] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0070] Example 1

[0071] See also Figure 1 As shown, the sports and arts personnel information management system described in this embodiment includes an information collection module, an information recording module, an information integration module, an information extraction module, a technical evaluation module, a plan formulation module and a comprehensive evaluation module; each module is connected by wired and / or wireless means to realize data transmission between modules.

[0072] The information collection module is used to collect basic information of different sports and arts personnel.

[0073] Basic personnel information is the basic data for identifying sports and arts personnel. It includes identity information, contact information, physical information, and project information.

[0074] Identity information is used to uniquely represent the basic identity of sports and arts personnel, including name, gender, age, ethnicity, ID number, etc.; contact information is used to indicate the method of communication with sports and arts personnel, including telephone number, email address, home address, etc.; physical information is used to record the basic physical fitness of sports and arts personnel, including height, weight, arm span, leg length, BMI, etc.; project information is used to indicate the category of the sports project to which the sports and arts personnel belong, including project name (such as rhythmic gymnastics, figure skating, trampoline, etc.), grade title (such as national master, national first-level athlete, etc.), registration unit (that is, the institution or unit to which the sports and arts personnel are affiliated and registered in the official or organizational system, such as the provincial sports bureau, school sports team, national team, art group, etc.), etc.;

[0075] The basic information of personnel is obtained by sports and arts personnel by filling out relevant forms and uploading them, or by management units (such as schools, associations, sports bureaus, etc.) by batch importing them through template formats such as Excel / CSV.

[0076] The information recording module is used to dynamically record the professional information of different sports and arts personnel during their sports careers.

[0077] Personnel professional information refers to the specialized data of sports and arts personnel during their growth and development, reflecting their specialized abilities, training performance, and competition results. Personnel professional information includes training information, competition information, physical fitness information, psychological information, and injury information.

[0078] Training information is used to reflect the daily situation and training content of sports and arts personnel during the training phase. It is the basic data for measuring their skill accumulation and technical growth, including training cycles, training items, training duration, etc.; event information is used to reflect the participation and performance of sports and arts personnel in competitions at all levels. It is an important basis for evaluating their actual combat capabilities and competitive levels, including event names, event levels (such as municipal, provincial, national, etc.), event results, etc.; physical fitness information is used to reflect the objective measurement results of the physical fitness of sports and arts personnel. It is an important basis for supporting scientific training and load control, including special physical fitness tests (such as endurance Strength, explosiveness, flexibility, etc.), physiological parameters (such as heart rate recovery, vital capacity, etc.); psychological information is used to reflect the psychological quality and psychological adjustment ability of sports and arts personnel, and is an important basis for psychological intervention and auxiliary training, including emotional state before and after the game, psychological quality assessment indicators (such as test scores of dimensions such as attention, emotional control, and willpower); injury information is used to reflect the injuries suffered by sports and arts personnel during training or competition, and is an important basis for assessing training risks and formulating rehabilitation plans, including the time of injury occurrence, injury type (such as strain, fracture, overuse, etc.), rehabilitation progress, etc.

[0079] Personnel professional information is collected in real time by wearable devices worn by sports and arts personnel (such as heart rate belts, physical fitness testers, etc.), or manually entered and uploaded by sports and arts personnel by filling out relevant forms; in addition, the information management system also supports docking with the event information management platform to automatically synchronize event results and related data; through diversified data collection methods, it ensures the dynamic update and complete record of personnel professional information at all stages of their sports career.

[0080] The information integration module is used to integrate basic personnel information and professional information based on a unified timeline to construct a development trajectory map.

[0081] The development trajectory map is a multi-dimensional data visualization representation based on time series, which helps to comprehensively monitor and evaluate the progress, growth and status of sports and arts personnel.

[0082] Methods for constructing development trajectory maps include:

[0083] Obtain the time fields corresponding to each set of personnel basic information and personnel professional information from the information management system. The time fields are the specific time when the information management system records the personnel basic information or personnel professional information. Convert all time fields into a unified time format (such as ISO time format), and combine each set of personnel basic information and the corresponding personnel professional information as a set of personnel information sets. The personnel information sets correspond one-to-one with the personnel basic information, where each set of personnel information sets includes multiple sets of personnel professional information.

[0084] Set the time granularity, that is, determine the length of the time unit, such as day (one day is one time unit), week (one week is one time unit), training cycle (one training cycle is one time unit), etc. Based on the set time granularity, build timelines, each of which corresponds to a set of personnel information. is the number of groups of personnel information sets; for each time unit on each time axis, a node is created to store the personnel information set; an index structure (such as B-tree index, hash index, etc.) is established in each time axis to quickly retrieve and access information, thereby improving the efficiency of information query; each data in each group of personnel information sets is stored in the corresponding node in the corresponding time axis according to the corresponding time field and in chronological order (i.e., in the natural order from early to late), so as to construct a development trajectory map corresponding to each sports and arts personnel; wherein, the horizontal axis of the development trajectory map is time, and the vertical axis is various types of information in the personnel information set.

[0085] The information extraction module is used to extract features from the development trajectory map using data mining technology to generate personnel feature information.

[0086] Personnel characteristic information includes basic characteristics, training characteristics, competition characteristics, physical characteristics, psychological characteristics, and injury characteristics;

[0087] Basic characteristics such as the ratio of age to years of training, body shape adaptability (i.e., the degree of adaptability between the body shape of sports and arts personnel, such as height, weight, limb proportions, etc., and the sports and arts projects they are engaged in), etc., are used to evaluate the development potential and professional matching of sports and arts personnel; training characteristics such as training frequency, training load fluctuation, cumulative training time, number of project changes, etc. are used to evaluate the technical accumulation, training regularity, and project concentration of sports and arts personnel; competition characteristics such as the number of competitions participated in, performance trends, and competition level coverage are used to evaluate the competition experience accumulation and competitive status of sports and arts personnel; physical fitness signs such as the changing trends of various special physical fitness tests and the changing trends of physiological parameters are used to evaluate the physical fitness foundation and special ability support of sports and arts personnel; psychological characteristics such as mood change trends and fluctuations of psychological quality assessment indicators are used to evaluate the emotional regulation ability, stress resistance, and psychological resilience of sports and arts personnel; injury characteristics such as injury frequency and recovery period are used to evaluate the physical fragility of sports and arts personnel and control the risk of training intensity.

[0088] Methods for generating personnel characteristic information include:

[0089] All non-numeric data in personnel basic information and personnel professional information are marked as text data, and different numerical labels are set for each text data in turn, and marked as information labels; for example, for the project name, the information label is set to 1 for rhythmic gymnastics, and the information label is set to 2 for figure skating, etc. For the competition level, the information label is set to 100 for the municipal level and 101 for the provincial level. For the injury type, the information label is set to 1000 for strain and 1001 for fracture; the text data in each development trajectory map are replaced with the corresponding information label;

[0090] Set the window length to time window, An integer greater than 1, the window length The prediction threshold is preset by those skilled in the art according to the actual situation; the number of storage nodes in each development trajectory map is counted and marked as the number of nodes, and the storage node is the node that actually stores data; the prediction threshold is preset, and the prediction threshold is the minimum number of data groups required for training the extraction model. The prediction threshold is preset by those skilled in the art according to the actual situation; the number of each node is subtracted Add 1 to obtain the maximum number; compare each maximum number with the prediction threshold in turn, mark the development trajectory map with a maximum number less than the prediction threshold as an insufficient map, and mark the development trajectory map with a maximum number greater than or equal to the threshold as a sufficient map; construct a corresponding feature generation model for each insufficient map and sufficient map in turn, the feature generation model corresponds to the sports and arts personnel one by one, and the feature generation model is a deep neural network model; it should be understood that the insufficient map indicates that the amount of data in the corresponding development trajectory map is insufficient and cannot support subsequent analysis and modeling work related to model training;

[0091] According to the set time window, the corresponding starting point and end point are obtained from each development trajectory map. The starting point is the latest node in the time field, and the end point is all nodes with a time interval of no more than Among the nodes, the node with the earliest time field; obtain all the data between the starting point and the end point in each development trajectory map and mark them as feature analysis data; input each set of feature analysis data into the corresponding feature generation model to predict the corresponding personnel feature information.

[0092] Methods for constructing feature generation models for sufficient graphs include:

[0093] Mark the previous node of the sufficient graph corresponding to the starting point as a training point, and divide all the data between the training point and the end point into Different sets of training data, and according to A feature generation model is constructed using a set of different training data; each set of training data includes continuous The data corresponding to each node, , is the number of nodes in the sufficient graph;

[0094] right The corresponding feature analysis data of each set of training data are set in turn, and each set of training data and the corresponding feature analysis data are converted into a corresponding set of feature vectors in turn; the feature analysis data corresponding to the training data are analyzed by a person skilled in the art in accordance with the actual situation, and the feature analysis data corresponding to each set of training data are calculated in turn, and the feature analysis data corresponding to the training data are calculated according to the calculation results. Different sets of training data are used to set corresponding feature analysis data in turn;

[0095] Each set of feature vectors is used as the input of the feature generation model. The feature generation model takes a set of predicted feature analysis data corresponding to each set of training data as the output, and takes the actual feature analysis data corresponding to each set of training data as the prediction target. The actual feature analysis data is the pre-set feature analysis data corresponding to the training data. A set of different training data is divided into a training set and a test set. The feature generation model is trained according to the training set. After each training round, the feature generation model is tested according to the test set, and the prediction error is calculated; based on the prediction error, the error change value is calculated; the error change value is compared with a preset change threshold. If the error change value is greater than or equal to the change threshold, the training continues; if the error change value is less than the change threshold, the training is stopped and the construction of the feature generation model is completed; the change threshold is pre-set by a person skilled in the art according to actual conditions.

[0096] The method for calculating the prediction error is as follows: for each data in the actual feature analysis data corresponding to each group of training data in the test set, subtract the corresponding data in the corresponding predicted feature analysis data, and square them to obtain the square of the data difference corresponding to each group of training data; preset a weight set, the weight set includes the weight coefficient corresponding to each data in the feature analysis data, and the weight set is pre-set by technical personnel in this field according to actual conditions; multiply the square of the data difference corresponding to each group of training data by the corresponding weight coefficient in the weight set to obtain the data difference weight; add the data difference weights corresponding to each group of training data in sequence to obtain the error value corresponding to each group of training data; add the error values ​​of each group of training data in sequence to obtain the prediction error.

[0097] The error change value is calculated by subtracting the prediction error calculated after the previous training round from the prediction error calculated after the current training round to obtain the error change value.

[0098] Methods for constructing feature generation models for deficiency maps include:

[0099] According to the personnel information set of each sports and arts personnel, the density clustering algorithm is used to cluster all sports and arts personnel to obtain clusters, is an integer greater than 1; mark the sports and arts personnel corresponding to the insufficient graph as missing personnel, obtain the cluster corresponding to the missing personnel, and mark it as a supplementary cluster; use the similarity measurement method to calculate the similarity between each sports and arts personnel in the supplementary cluster and the missing personnel in turn, and mark the sports and arts personnel with the greatest similarity as a supplementary personnel; add the prediction threshold to , get the quantity threshold; subtract the number of nodes from the quantity threshold to get the insufficient quantity; take the end point corresponding to the insufficient graph as the insufficient starting point, and The empty node of the node is used as the insufficient end point. The empty node is the node that does not actually store data. =The number of insufficient personnel; mark the development trajectory map corresponding to the supplementary personnel as the supplementary map, and mark the node with the same time field as the insufficient starting point as the supplementary starting point, and mark the node with the same time field as the insufficient end point as the supplementary end point; obtain all the data between the supplementary starting point and the supplementary end point, and mark them as supplementary data. The supplementary data does not include the data corresponding to the supplementary starting point and the data corresponding to the supplementary end point; divide all the data in the insufficient map and the supplementary data into Different sets of build data, and according to A set of different construction data is used to construct a feature generation model; The method of constructing feature generation model based on different construction data is different from The method of constructing feature generation models for different sets of training data is consistent. To predict the threshold; it should be noted that the density clustering algorithm and the similarity measurement method are both existing technologies, and the specific process will not be described in detail here.

[0100] The technical evaluation module is used to conduct quantitative analysis of personnel characteristic information and evaluate the special technical capabilities of different sports and arts personnel.

[0101] The steps for evaluating the specific technical abilities of individuals in different sports arts include:

[0102] Step S101: Training characteristics, event characteristics, and physical characteristics are used as technical characteristic data; multiple fuzzy sets are constructed for each data in the technical characteristic data; for example, the fuzzy sets corresponding to training frequency are low training frequency, medium training frequency, high training frequency, etc., and the fuzzy sets corresponding to the number of event participations are high number of participations, medium number of participations, low number of participations, etc.;

[0103] Step S102: The technical characteristic data of each sports and arts personnel are converted into the membership of each corresponding fuzzy set through fuzzification technology. Fuzzification technology is the process of converting precise numerical values ​​into the membership corresponding to the fuzzy set. Fuzzification technologies include triangular membership function and trapezoidal membership function. For example, if the value of training frequency is low, it is inferred that the membership of low training frequency is 0.9, the membership of medium training frequency is 0.2, and the membership of high training frequency is 0.1.

[0104] Step S103: defining fuzzy rules, which are defined based on expert knowledge or relevant literature; for example, if the training frequency is high, the number of competitions is high, the performance trend is rising, and the endurance is rising, then it is inferred that the corresponding sports and arts personnel's special technical ability is at the advanced level, with a high membership degree; if the training frequency is medium, the number of competitions is small, the performance trend is stable, and the endurance is stable, then it is inferred that the corresponding sports and arts personnel's special technical ability is at the intermediate level, with a high membership degree;

[0105] Step S104: Match each set of fuzzified technical feature data with fuzzy rules respectively, and perform fuzzy reasoning using a fuzzy reasoning method (such as the Mamdani fuzzy reasoning model, the Sugeno fuzzy reasoning model, etc.) to obtain a fuzzy reasoning result corresponding to each sports and arts personnel. The fuzzy reasoning result is the membership degree of each special technical ability level, which includes advanced, intermediate, and low levels. For example, the fuzzy reasoning result has a membership degree of 0.3 for the advanced level, 0.8 for the intermediate level, and 0.5 for the advanced level.

[0106] Step S105: Set the scoring space. The range of the scoring space is , is an integer greater than 1; the scoring space is evenly divided into three level spaces, and the level spaces correspond to the levels of special technical capabilities one by one; among them, the level space corresponding to the advanced level is , the intermediate level space is , the level space corresponding to the low level is ; Add the maximum value of each level space to the corresponding minimum value and divide by 2 to obtain the mean value of each level space;

[0107] Step S106: Multiply the degree of affiliation of each special technical ability level corresponding to each sports and art personnel by the mean of the corresponding level space, and then add them up in sequence to obtain the total score of each sports and art personnel; add the degree of affiliation of each special technical ability level corresponding to each sports and art personnel in sequence to obtain the total degree of affiliation; divide the total value of the score of each sports and art personnel by the corresponding total degree of affiliation to obtain the technical score value of each sports and art personnel, and use it as the evaluation result of the special technical ability.

[0108] The planning module is used to automatically formulate training plans based on special technical capabilities and combined with sports physiology principles using a multi-objective optimization algorithm.

[0109] The principles of exercise physiology usually include knowledge of body reactions, energy consumption, exercise performance, recovery patterns, etc.; the principles of exercise physiology include maximum heart rate, lactate threshold, maximum oxygen uptake, exercise recovery cycle, etc.; the principles of exercise physiology provide a scientific framework to guide the training process of sports and arts personnel, helping to determine the appropriate training intensity, training cycle, recovery period and other key factors, and design more scientific and personalized training plans to ensure that sports and arts personnel train in the best physiological state and achieve the best performance when the goals are achieved; the principles of exercise physiology are obtained through academic literature, expert knowledge, etc.

[0110] Methods for developing a training plan for a sports arts professional include:

[0111] Preset plan set, which includes Different training plans, is an integer greater than 1; the training plans in the plan set are designed by technicians in this field in a variety of ways based on the principles of exercise physiology and different exercise goals, training methods, intensity, frequency, recovery time and other factors; different numerical labels are set for the training plans in the plan set in increasing order and marked as plan labels. The range of plan labels is ;

[0112] Define the iterative process, which is: randomly select from the range of plan labels values, and all of them are taken as candidate solutions. , the candidate solutions correspond to the plan labels one by one; calculate the target value set corresponding to each candidate solution in turn, and Filter out the optimal solution from the candidate solutions;

[0113] Execute the iterative process. When the number of executions of the iterative process is greater than or equal to a preset number threshold, stop executing the iterative process and select the best solution from all the optimal solutions; use the training plan corresponding to the plan label of the best solution as the training plan for the corresponding sports and arts personnel; the number threshold is pre-set by technical personnel in this field according to actual conditions.

[0114] It should be noted that the method of formulating training plans for each sports and arts personnel is the same.

[0115] Methods for calculating target value sets include:

[0116] Construct a target calculation model, which includes a physical fitness calculation model, a skill calculation model and an injury calculation model. The construction method of each target calculation model is consistent with the construction method of the feature generation model, and all are deep neural network models; the evaluation results of the corresponding special technical capabilities of sports and arts personnel, the basic information of the personnel and the plan labels corresponding to the candidate solutions are used as calculation data; the calculation data are input into each target calculation model respectively to predict the corresponding prediction value set; the prediction value set includes physical fitness improvement effect, skill improvement effect and injury risk; among them, the physical fitness calculation model is used to predict the physical fitness improvement effect, the skill calculation model is used to predict the skill improvement effect, and the injury calculation model is used to predict the injury risk; the inverse of the physical fitness improvement effect, skill improvement effect and injury risk in the prediction value set is used as the target value set.

[0117] It should be understood that the physical fitness improvement effect refers to improving the physical fitness level of sports and arts personnel (such as muscle strength, cardiopulmonary endurance, etc.) through training, thereby improving the performance of sports and arts personnel in special sports; the skill improvement effect refers to the degree of improvement of sports and arts personnel in technical movements, coordination, reaction speed, etc., and the level of skill directly affects the performance and results of sports and arts personnel; injury risk refers to the possibility of sports and arts personnel being injured during training. Control of injury risk is crucial to maintaining the long-term health of sports and arts personnel. High injury risk will not only affect the training effect, but also lead to long-term inability to participate in competitions.

[0118] from Methods for selecting the optimal solution from candidate solutions include:

[0119] A preset proportion set, which includes a proportional coefficient corresponding to each target value in the target value set, is pre-set by a person skilled in the art based on actual conditions; each target value in the target value set corresponding to each candidate solution is multiplied by the corresponding proportional coefficient in the proportion set, and the results are added in sequence to obtain the total target value corresponding to each candidate solution; the total target value of each candidate solution is compared respectively, and the candidate solution with the largest total target value is taken as the optimal solution.

[0120] It should be noted that the method of selecting the best solution from all the optimal solutions is the same as that of The method of selecting the optimal solution from the candidate solutions is consistent.

[0121] The comprehensive evaluation module is used to combine personnel characteristic information and special technical capabilities, conduct multi-dimensional analysis, and quantitatively evaluate the comprehensive capabilities of different sports and arts personnel.

[0122] The steps to quantitatively assess the comprehensive abilities of individuals in different sports arts include:

[0123] Step S201: Preset search range and the division coefficient , The search interval is pre-set by those skilled in the art based on the actual setting range of comprehensive capabilities;

[0124] Step S202: randomly selecting a sports arts person who is not marked as a selected person and marking him as the current person;

[0125] Step S203: Based on the division coefficient , from the search interval Divide into two split points and ;

[0126] Step S204: Calculate two segmentation points respectively and The corresponding matching coefficient will split the points The corresponding matching coefficient is marked as the first coefficient, and the split point The corresponding matching coefficient is marked as the second coefficient;

[0127] Step S205: Compare the first coefficient with the second coefficient; if the first coefficient is greater than or equal to the second coefficient, proceed to step S206; if the first coefficient is less than the second coefficient, proceed to step S207;

[0128] Step S206: Update the maximum value of the search interval as the split point , the minimum value of the search interval remains unchanged, and the process goes to step S208;

[0129] Step S207: Update the minimum value of the search interval as the split point , the maximum value of the search interval remains unchanged, and the process goes to step S208;

[0130] Step S208: Determine whether the segmentation is completed. If the segmentation is completed, proceed to step S209. If the segmentation is not completed, update the segmentation coefficient according to the matching coefficient, and re-divide two segmentation points from the search interval according to the updated segmentation coefficient. and , and returns to step S204;

[0131] Step S209: taking the average of the maximum and minimum values ​​corresponding to the search interval as the comprehensive ability of the current person, marking the current person as a selected person, and returning to step S202;

[0132] Step S210: Loop step S202 to step S209 until all sports and arts personnel are marked as selected personnel. The loop ends and the quantitative evaluation of the comprehensive capabilities of different sports and arts personnel is completed.

[0133] In the above step S203, the segmentation points are divided The method is: subtract 1 from , and then multiply by , get the split point ; Divide the split point The method is: Multiply , get the split point ;

[0134] In step S204, the matching coefficient calculation method includes: using the numerical value corresponding to the split point, the basic characteristics, psychological characteristics, injury characteristics, and the evaluation results of the specific technical ability of the current person as matching data, inputting the matching data into a pre-built matching analysis model, and predicting the corresponding matching coefficient; the construction method of the matching analysis model is consistent with the construction method of the feature generation model, and both are deep neural network models;

[0135] In the above step S208, the method for updating the segmentation coefficient according to the matching coefficient is: presetting a matching threshold, which is pre-set by those skilled in the art according to actual conditions; comparing the matching coefficient with the matching threshold; if the matching coefficient is greater than or equal to the matching threshold, multiplying the matching coefficient by a preset first factor to obtain the first coefficient, and subtracting the adjustment coefficient from the matching coefficient to obtain the first update coefficient, and updating the segmentation coefficient according to the first update coefficient; if the matching coefficient is less than the matching threshold, multiplying the matching coefficient by a preset second factor to obtain the second coefficient, and adding the second coefficient to the matching coefficient to obtain the second update coefficient, and updating the segmentation coefficient according to the second update coefficient; both the first factor and the second factor are pre-set by those skilled in the art according to actual conditions.

[0136] This embodiment constructs a development trajectory map by integrating the basic information and professional information of different sports and arts personnel; and uses data mining technology to extract personnel characteristic information to achieve quantitative analysis and evaluation of the special technical capabilities of different sports and arts personnel; at the same time, a multi-objective optimization algorithm is used to automatically formulate personalized training plans, which helps to improve the training effect of sports and arts personnel and ensure that training is carried out in the best physiological state; in addition, through multi-dimensional analysis, the comprehensive capabilities of different sports and arts personnel can be quantitatively evaluated, providing a basis for selecting outstanding talents and optimizing resource allocation; it realizes the full life cycle intelligent management of sports and arts personnel information, can comprehensively and real-time track and manage personnel information, improve management efficiency, enhance the overall competitiveness of sports and arts projects, and meet the needs of refined and intelligent training management.

[0137] Example 2

[0138] See also Figure 2 As shown, for the parts not described in detail in this embodiment, please refer to the description of embodiment 1. A method for managing information of sports and arts personnel is provided, and the method includes:

[0139] Collect basic information of personnel in different sports and arts;

[0140] Dynamically record the professional information of different sports and arts personnel during their careers;

[0141] Based on a unified timeline, integrate basic and professional information of personnel to build a development trajectory map;

[0142] Using data mining technology, we extract features from the development trajectory map and generate personnel feature information;

[0143] Conduct quantitative analysis of personnel characteristic information and evaluate the specialized technical capabilities of personnel in different sports and arts;

[0144] Based on specific technical capabilities and combined with the principles of sports physiology, a multi-objective optimization algorithm is used to automatically formulate training plans;

[0145] Combining personnel characteristic information and special technical capabilities, and conducting multi-dimensional analysis, we can quantitatively evaluate the comprehensive capabilities of different sports and arts personnel.

[0146] Example 3

[0147] The present application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories may store computer-readable code that, when executed by the one or more processors, may execute the above-described method for managing information of sports and arts personnel.

[0148] The method or system according to the embodiments of the present application can also be implemented using the architecture of the electronic device shown in this application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. A storage device in the electronic device, such as a ROM or hard disk, can store the sports and arts personnel information management method provided in this application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in this application is merely exemplary. When implementing different devices, one or more components in the electronic device shown in this application may be omitted according to actual needs.

[0149] Example 4

[0150] One embodiment of the present application discloses a computer-readable storage medium. The computer-readable storage medium stores computer-readable instructions. When the computer-readable instructions are executed by a processor, a sports and arts personnel information management method according to an embodiment of the present application described with reference to the accompanying drawings can be executed. The storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc.

[0151] Additionally, depending on the embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions capable of being executed by a processor to execute instructions corresponding to the steps of the method provided herein, such as a method for managing information of sports and arts personnel. When this computer program is executed by a central processing unit (CPU), the functions defined in the method of the present application are performed.

[0152] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art will be able to modify the technical solutions described in the foregoing embodiments or to substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0153] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0154] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0155] In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0156] In the description of the present invention, “several” means one or more, and “a large number” means two or more.

[0157] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0158] The formulas in this manual are all dimensionless and calculated using numerical values. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field based on actual conditions.

[0159] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A sports arts personnel information management method, characterized in that: include: Collect basic information of personnel in different sports and arts; Dynamically record the professional information of different sports and arts personnel during their careers; Based on a unified timeline, integrate basic and professional information of personnel to build a development trajectory map; Using data mining technology, we extract features from the development trajectory map and generate personnel feature information; Conduct quantitative analysis of personnel characteristic information and evaluate the specialized technical capabilities of personnel in different sports and arts; Based on specific technical capabilities and combined with the principles of sports physiology, a multi-objective optimization algorithm is used to automatically formulate training plans; Combining personnel characteristic information and special technical capabilities, and conducting multi-dimensional analysis, we can quantitatively evaluate the comprehensive capabilities of different sports and arts personnel.

2. A sports arts personnel information management method according to claim 1, characterized in that: The basic information of the personnel includes identity information, contact information, physical information and project information; the professional information of the personnel includes training information, competition information, physical information, psychological information and injury information; The method for constructing a development trajectory map includes: Get the time fields corresponding to each group of personnel's basic information and professional information; Convert all time fields into a unified time format, and combine each set of personnel basic information with the corresponding personnel professional information as a set of personnel information sets, with the personnel information sets corresponding to the personnel basic information one-to-one, where each set of personnel information sets includes multiple sets of personnel professional information; Set the time granularity, that is, determine the length of the time unit; based on the set time granularity, build timelines, each of which corresponds to a set of personnel information. is the number of groups of personnel information sets; for each time unit on each time axis, a node is created; an index structure is established in each time axis; each data in each group of personnel information sets is stored in the corresponding node in the corresponding time axis in chronological order according to the corresponding time field, and a development trajectory map corresponding to each sports and arts personnel is constructed.

3. A sports arts personnel information management method according to claim 2, characterized in that: The personnel characteristic information includes basic characteristics, training characteristics, competition characteristics, physical characteristics, psychological characteristics and injury characteristics; The method for generating personnel characteristic information includes: Mark all non-numeric data in personnel basic information and personnel professional information as text data, set different numerical labels for each text data in turn, and mark them as information labels; replace the text data in each development trajectory map with the corresponding information label; Set the window length to time window, is an integer greater than 1; count the number of storage nodes in each development trajectory map and mark them as the number of nodes. The storage nodes are the nodes that actually store data; preset the prediction threshold, which is the minimum number of data groups required to train the extraction model; subtract the number of each node from Add 1 to obtain the maximum number; compare each maximum number with the prediction threshold in turn, mark the development trajectory map with a maximum number less than the prediction threshold as an insufficient map, and mark the development trajectory map with a maximum number greater than or equal to the threshold as a sufficient map; construct a corresponding feature generation model for each insufficient map and sufficient map in turn, the feature generation model corresponds to the sports and arts personnel one by one, and the feature generation model is a deep neural network model; According to the set time window, the corresponding starting point and end point are obtained from each development trajectory map. The starting point is the latest node in the time field, and the end point is all nodes with a time interval of no more than Among the nodes, the node with the earliest time field; obtain all the data between the starting point and the end point in each development trajectory map and mark them as feature analysis data; input each set of feature analysis data into the corresponding feature generation model to predict the corresponding personnel feature information.

4. A sports arts personnel information management method according to claim 3, characterized in that: Methods for constructing feature generation models for sufficient graphs include: Mark the previous node of the sufficient graph corresponding to the starting point as a training point, and divide all the data between the training point and the end point into Different sets of training data, and according to A feature generation model is constructed using a set of different training data; each set of training data includes continuous The data corresponding to each node, , is the number of nodes in the sufficient graph; right The corresponding feature analysis data are set for each set of training data in turn, and each set of training data and the corresponding feature analysis data are converted into a corresponding set of feature vectors in turn; each set of feature vectors is used as the input of the feature generation model, and the feature generation model uses a set of predicted feature analysis data corresponding to each set of training data as the output, and the actual feature analysis data corresponding to each set of training data as the prediction target, and the actual feature analysis data is the pre-set feature analysis data corresponding to the training data; Different sets of training data are divided into training sets and test sets. The feature generation model is trained according to the training set. After each training round, the feature generation model is tested according to the test set, and the prediction error is calculated. According to the prediction error, the error change value is calculated; the error change value is compared with the preset change threshold. If the error change value is greater than or equal to the change threshold, the training continues. If the error change value is less than the change threshold, the training is stopped to complete the construction of the feature generation model.

5. A sports arts personnel information management method according to claim 4, characterized in that: Methods for constructing feature generation models for deficiency maps include: According to the personnel information set of each sports and arts personnel, the density clustering algorithm is used to cluster all sports and arts personnel to obtain clusters, is an integer greater than 1; mark the sports and arts personnel corresponding to the insufficient graph as missing personnel, obtain the cluster corresponding to the missing personnel, and mark it as a supplementary cluster; use the similarity measurement method to calculate the similarity between each sports and arts personnel in the supplementary cluster and the missing personnel in turn, and mark the sports and arts personnel with the greatest similarity as a supplementary personnel; add the prediction threshold to , get the quantity threshold; subtract the number of nodes from the quantity threshold to get the insufficient quantity; take the end point corresponding to the insufficient graph as the insufficient starting point, and The empty node of the node is used as the insufficient end point. The empty node is the node that does not actually store data. =The number of insufficient personnel; mark the development trajectory map corresponding to the supplementary personnel as the supplementary map, and mark the node with the same time field as the insufficient starting point as the supplementary starting point, and mark the node with the same time field as the insufficient end point as the supplementary end point; obtain all the data between the supplementary starting point and the supplementary end point, and mark them as supplementary data. The supplementary data does not include the data corresponding to the supplementary starting point and the data corresponding to the supplementary end point; divide all the data in the insufficient map and the supplementary data into Different sets of build data, and according to A set of different construction data is used to construct a feature generation model; The method of constructing feature generation model based on different construction data is different from The method of constructing feature generation models for different sets of training data is consistent. is the prediction threshold.

6. A sports arts personnel information management method according to claim 5, characterized in that: The steps for evaluating the specific technical abilities of different sports and arts personnel include: Step S101: Taking training characteristics, competition characteristics, and physical characteristics as technical characteristic data; constructing multiple fuzzy sets for each data in the technical characteristic data; Step S102: converting the technical characteristic data of each sports artist into the membership degree of each corresponding fuzzy set through fuzzification technology; Step S103: defining fuzzy rules; Step S104: Match each set of fuzzified technical feature data with fuzzy rules respectively, and perform fuzzy reasoning using a fuzzy reasoning method to obtain the fuzzy reasoning results corresponding to each sports and arts personnel. The fuzzy reasoning results are the membership levels of each special technical ability level, which include advanced, intermediate, and low levels. Step S105: Set the scoring space. The range of the scoring space is , is an integer greater than 1; the scoring space is evenly divided into three level spaces, and the level spaces correspond to the levels of special technical capabilities one by one; the maximum value of each level space is added to the corresponding minimum value and then divided by 2 to obtain the mean value of each level space; Step S106: Multiply the degree of affiliation of each special technical ability level corresponding to each sports and art personnel by the mean of the corresponding level space, and then add them up in sequence to obtain the total score of each sports and art personnel; add the degree of affiliation of each special technical ability level corresponding to each sports and art personnel in sequence to obtain the total degree of affiliation; divide the total value of the score of each sports and art personnel by the corresponding total degree of affiliation to obtain the technical score value of each sports and art personnel, and use it as the evaluation result of the special technical ability.

7. A sports arts personnel information management method according to claim 6, characterized in that: Methods for developing a training plan for a sports arts professional include: Preset plan set, which includes Different training plans, is an integer greater than 1; different numerical labels are set for the training plans in the plan set in sequence and marked as plan labels. The range of plan labels is ; Define the iterative process, which is: randomly select from the range of plan labels values, and all of them are taken as candidate solutions. , the candidate solutions correspond to the plan labels one by one; calculate the target value set corresponding to each candidate solution in turn, and Filter out the optimal solution from the candidate solutions; Execute the iterative process. When the number of executions of the iterative process is greater than or equal to a preset number threshold, stop executing the iterative process and select the best solution from all the optimal solutions; use the training plan corresponding to the plan label of the best solution as the training plan for the corresponding sports and arts personnel; Methods for calculating target value sets include: Construct a target calculation model, which includes a physical fitness calculation model, a skill calculation model, and an injury calculation model. The construction method of each target calculation model is consistent with the construction method of the feature generation model, and all are deep neural network models; the evaluation results of the corresponding special technical capabilities of sports and arts personnel, the basic information of the personnel, and the plan labels corresponding to the candidate solutions are used as calculation data; the calculation data are input into each target calculation model respectively to predict the corresponding prediction value set; the prediction value set includes the physical fitness improvement effect, the skill improvement effect, and the injury risk; the inverse of the physical fitness improvement effect, the skill improvement effect, and the injury risk in the prediction value set is used as the target value set; from Methods for selecting the optimal solution from candidate solutions include: A preset proportion set is provided, where the proportion set includes a proportion coefficient corresponding to each target value in the target value set; each target value in the target value set corresponding to each candidate solution is multiplied by the corresponding proportion coefficient in the proportion set, and the results are added in sequence to obtain the total target value corresponding to each candidate solution; the total target value of each candidate solution is compared, and the candidate solution with the largest total target value is taken as the optimal solution.

8. A sports arts personnel information management method according to claim 7, characterized in that: The steps to quantitatively assess the comprehensive abilities of individuals in different sports arts include: Step S201: Preset search range and the division coefficient , ; Step S202: randomly selecting a sports arts person who is not marked as a selected person and marking him as the current person; Step S203: Based on the division coefficient , from the search interval Divide into two split points and ; Step S204: Calculate two segmentation points respectively and The corresponding matching coefficient will split the points The corresponding matching coefficient is marked as the first coefficient, and the split point The corresponding matching coefficient is marked as the second coefficient; Step S205: Compare the first coefficient with the second coefficient; if the first coefficient is greater than or equal to the second coefficient, proceed to step S206; if the first coefficient is less than the second coefficient, proceed to step S207; Step S206: Update the maximum value of the search interval as the split point , the minimum value of the search interval remains unchanged, and the process goes to step S208; Step S207: Update the minimum value of the search interval as the split point , the maximum value of the search interval remains unchanged, and the process goes to step S208; Step S208: Determine whether the segmentation is completed. If the segmentation is completed, proceed to step S209. If the segmentation is not completed, update the segmentation coefficient according to the matching coefficient, and re-divide two segmentation points from the search interval according to the updated segmentation coefficient. and , and returns to step S204; Step S209: taking the average of the maximum and minimum values ​​corresponding to the search interval as the comprehensive ability of the current person, marking the current person as a selected person, and returning to step S202; Step S210: Loop step S202 to step S209 until all sports and arts personnel are marked as selected personnel. The loop ends and the quantitative evaluation of the comprehensive capabilities of different sports and arts personnel is completed.

9. A sports arts personnel information management method according to claim 8, characterized in that: In step S203, the segmentation points are divided The method is: subtract 1 from , and then multiply by , get the split point ; Divide the split point The method is: Multiply , get the split point ; In step S204, the matching coefficient calculation method includes: using the numerical value corresponding to the split point, the basic characteristics, psychological characteristics, injury characteristics, and the evaluation results of the specific technical ability of the current person as matching data, inputting the matching data into a pre-built matching analysis model, and predicting the corresponding matching coefficient; the construction method of the matching analysis model is consistent with the construction method of the feature generation model, and both are deep neural network models; In step S208, the method for updating the segmentation coefficient according to the matching coefficient is as follows: presetting a matching threshold and comparing the matching coefficient with the matching threshold; if the matching coefficient is greater than or equal to the matching threshold, multiplying the matching coefficient by a preset first factor to obtain the first coefficient, subtracting the adjustment coefficient from the matching coefficient to obtain the first update coefficient, and updating the segmentation coefficient according to the first update coefficient; if the matching coefficient is less than the matching threshold, multiplying the matching coefficient by a preset second factor to obtain the second coefficient, adding the second coefficient to the matching coefficient to obtain the second update coefficient, and updating the segmentation coefficient according to the second update coefficient.

10. A sports and arts personnel information management system, implementing a sports and arts personnel information management method according to any one of claims 1 to 9, characterized in that: include: Information collection module, used to collect basic information of different sports and arts personnel; The information recording module is used to dynamically record the professional information of different sports and arts personnel during their sports careers; The information integration module is used to integrate basic and professional personnel information based on a unified timeline to construct a development trajectory map; The information extraction module is used to extract features from the development trajectory map using data mining technology to generate personnel feature information; The technical evaluation module is used to conduct quantitative analysis of personnel characteristics and evaluate the special technical capabilities of different sports and arts personnel; The planning module is used to automatically formulate training plans based on specific technical capabilities and combined with sports physiology principles using a multi-objective optimization algorithm; The comprehensive evaluation module is used to combine personnel characteristic information and special technical capabilities, conduct multi-dimensional analysis, and quantitatively evaluate the comprehensive capabilities of different sports and arts personnel.

Images