Physical fitness test auxiliary method and system for sports athletes

Abstract

The invention discloses a physical fitness test assisting method and system for sports athletes, and belongs to the field of physical fitness test assisting.The physical fitness test assisting method comprises the steps that real-time data streams of different physical fitness test devices are obtained, and a preset device interface protocol is adopted to convert the real-time data streams into data of a unified format through a data format conversion module; for the test data in the unified format, adopting a preset data cleaning rule to remove abnormal values and repeated data to obtain a standardized physical fitness test data set; according to age and gender information in the athlete identity information, selecting a corresponding evaluation standard from a pre-established physical fitness evaluation model, and analyzing the standardized physical fitness test data set; and matching the preliminary physical fitness evaluation result with a pre-established training suggestion library through a preset rule engine to obtain a personalized training suggestion scheme.

Description

Technical Field

[0001] The present invention belongs to the field of physical fitness test assistance, and in particular relates to a physical fitness test assistance method and system for athletes. Background Art

[0002] During athlete fitness testing, efficiently and accurately collecting and analyzing athlete fitness data is a key technical challenge. Traditional manual recording and analysis methods are inefficient and prone to errors. While some automated fitness testing equipment is available, they typically only measure a single fitness metric and fail to comprehensively assess an athlete's overall fitness level. Furthermore, the data formats and interface specifications collected by different fitness testing devices are not standardized, making data integration and analysis difficult.

[0003] To address these issues, a standardized fitness test data collection and analysis system is urgently needed. This system should be compatible with different types of fitness test equipment, automatically identify and record athlete identification information, and collect athletes' fitness test data in real time using a unified data format. The system should also have intelligent data analysis capabilities, automatically generating personalized fitness assessment reports and training recommendations based on factors such as the athlete's age, gender, and sport. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a physical fitness test auxiliary method for athletes, comprising:

[0005] Acquire real-time data streams from different fitness test devices, and convert the real-time data streams into data in a unified format through a data format conversion module using a preset device interface protocol;

[0006] Extracting the athlete number from the data in the unified format according to a preset athlete identification rule, and matching it with a pre-established athlete information database to obtain the athlete identity information;

[0007] removing outliers and duplicate data from the data in the unified format to obtain a standardized physical fitness test data set;

[0008] Based on the athlete's identity information, selecting an evaluation standard model from a preset physical fitness evaluation standard model library, inputting the standardized physical fitness test data set into the evaluation standard model for calculation, and obtaining a comprehensive physical fitness evaluation result of the athlete;

[0009] A personalized training recommendation program is constructed based on the comprehensive physical fitness assessment results.

[0010] Preferably, the process of acquiring real-time data streams from different fitness test devices, using a preset device interface protocol, and converting the real-time data streams into data in a unified format through a data format conversion module includes:

[0011] Acquire real-time heterogeneous data from fitness test equipment, use the preset device interface protocol for data collection, and obtain original heterogeneous data;

[0012] According to the data format characteristics of heterogeneous data, key data elements are obtained through feature extraction;

[0013] For key data elements, a data format conversion module is used to convert them into a unified data format;

[0014] If the converted data format meets the preset data quality standard, it will be stored in the unified format database; otherwise, feature extraction will be performed again to obtain the data in the unified format.

[0015] Preferably, the process of obtaining the athlete's identity information includes:

[0016] According to the preset athlete identification rules, the athlete number information is extracted from the data in a unified format, and the athlete number is identified and extracted using a regular expression matching method;

[0017] Matching the extracted athlete number with the number field in a pre-established athlete information database, and obtaining the athlete identity information corresponding to the number through a database query operation;

[0018] If the athlete number has the corresponding identity information found in the database, the identity information is associated with the number to obtain a number-identity information matching result.

[0019] Preferably, the process of obtaining a standardized physical fitness test data set includes:

[0020] Performing outlier detection on the data in the unified format, and if outliers exist, removing the outliers to obtain a first data set;

[0021] For the first data set, a data deduplication algorithm is used to remove duplicate data to obtain a second data set;

[0022] Performing standardization processing on the second data set according to a preset data standardization rule to obtain a processed physical fitness test data set;

[0023] Calculating data distribution characteristics of the processed physical fitness test data set to obtain statistical characteristics of the data;

[0024] Based on the statistical characteristics of the data, determine whether the data set meets the preset data quality requirements. If it meets the requirements, determine the standardized physical fitness test data set as the final data set.

[0025] Preferably, the process of obtaining the athlete's comprehensive physical fitness assessment result includes:

[0026] Selecting an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information;

[0027] Input the standardized physical fitness test data set into the selected evaluation standard model, and score and grade each physical fitness indicator data according to the evaluation rules and thresholds set in the model;

[0028] Based on the evaluation results of various physical fitness indicators, a weighted average algorithm is used to calculate the athlete's comprehensive physical fitness evaluation score and level;

[0029] The athlete's comprehensive physical fitness evaluation result is obtained based on the athlete's comprehensive physical fitness evaluation score and grade.

[0030] Preferably, the process of selecting an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information includes:

[0031] Obtain the identity information of athletes, extract sports features, construct feature vectors, and generate feature data sets;

[0032] Dividing the feature data set into a training set and a test set according to the features of the sports event;

[0033] A decision tree model is constructed based on the athlete identity information. After the decision tree model is trained using the training set, the decision tree model is tested using the test set until the loss function no longer converges and is output to obtain the evaluation standard model.

[0034] Preferably, the process of constructing a personalized training recommendation program based on the comprehensive physical fitness assessment results includes:

[0035] Based on the comprehensive physical fitness assessment results, screening out training suggestions that match the user's physical fitness level from a pre-established training suggestion library;

[0036] If there are multiple matching suggestions in the training suggestion library, a decision tree algorithm is used to further screen based on the user's personal attributes and health data to obtain the best personalized training suggestion;

[0037] Conduct content analysis on the selected personalized training suggestions, extract key features, and use clustering algorithms to group similar suggestions into one category;

[0038] Based on the clustering results, an association rule mining algorithm is used to discover the correlations between different types of training suggestions and form a complete training plan;

[0039] The generated personalized training suggestion plan is output, and the training content is dynamically adjusted based on user feedback to continuously optimize the training effect.

[0040] On the other hand, the present invention also provides a physical fitness test auxiliary system for athletes, comprising:

[0041] A data acquisition module is used to obtain real-time data streams from different fitness test devices, and convert the real-time data streams into data in a unified format through a data format conversion module using a preset device interface protocol;

[0042] A data conversion module is used to extract the athlete number from the data in the unified format according to a preset athlete identification rule, and match it with a pre-established athlete information database to obtain the athlete identity information;

[0043] an identity recognition module, configured to remove outliers and duplicate data from the data in the unified format to obtain a standardized physical fitness test data set;

[0044] An evaluation standard selection module is used to select an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information, input the standardized physical fitness test data set into the evaluation standard model for calculation, and obtain the athlete's comprehensive physical fitness evaluation result;

[0045] The classification evaluation module is used to construct a personalized training recommendation plan based on the comprehensive physical fitness evaluation results.

[0046] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method is implemented when the processor executes the computer program.

[0047] On the other hand, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein the computer program implements the method when executed by a processor.

[0048] Compared with the prior art, the present invention has the following advantages and technical effects:

[0049] The present invention discloses a physical fitness test assistance method for athletes. The method collects real-time data streams from different devices, converts heterogeneous data into a unified format, and performs data cleaning and standardization. Subsequently, the present invention extracts the athlete number and matches the identity information according to preset rules, and selects appropriate evaluation criteria in combination with age and gender. Taking into account the characteristics of the sports event, the standardized data is classified and evaluated to generate preliminary physical fitness evaluation results. Finally, the present invention uses a rule engine to match the evaluation results with a training suggestion library to generate a personalized training plan. This method realizes the full process automation from heterogeneous data collection to personalized training suggestions, improves the efficiency and accuracy of physical fitness tests, and provides athletes with scientific and personalized training guidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0051] Figure 1 A schematic diagram of a basketball offensive agility test according to an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a basketball defensive agility test according to an embodiment of the present invention;

[0053] Figure 3 This is a schematic diagram of a football player's agility test according to an embodiment of the present invention;

[0054] Figure 4 This is a flow chart of a physical fitness test auxiliary method for athletes according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0056] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0057] Example 1

[0058] This embodiment provides a physical fitness test assistance method for athletes, including:

[0059] In this embodiment, the process of the basketball player agility test includes:

[0060] like Figure 1 As shown, the offensive agility test is 11 meters long. The test route is Y-shaped and requires four timing gates and a light stimulus. Timing Gate 1 is the starting point and ends at Gates 3 or 4. Timing Gate 2 is co-located with the stimulus sensor and located 2 meters before the change of direction. Timing begins when the athlete accelerates from a standstill and passes through Timing Gate 1, 0.5 meters from the starting point. When the athlete passes through Timing Gate 2, the first time period (T1) is recorded and the stimulus sensor is triggered. The light stimulus displays an arrow symbol on the left or right. The athlete changes direction according to the arrow and passes through Timing Gate 3 or 4, the finish line. The timer records the second time period (T2) and the total time (T1 + T2).

[0061] like Figure 2 As shown, the Defensive Agility Test is 10 meters long. The test route is arrow-shaped and requires four timing gates and a light stimulus. Gate 1 is the starting point and Gates 3 or 4 are the endpoints. Gate 2 is co-located with the stimulus sensor and is located 2 meters before the change of direction. Timing begins when the athlete accelerates from a standstill 0.5 meters from the starting point and passes Gate 1. When the athlete passes Gate 2, the first time interval (T1) is recorded and the stimulus sensor is triggered. The light stimulus displays an arrow symbol on the left or right. The athlete changes direction according to the arrow and passes Gate 3 or 4 at the finish line. The timer records the second time interval (T2) and the total time (T1 + T2).

[0062] The hardware system includes:

[0063] Infrared sensor timing door:

[0064] The height of the timing gate is adjustable. The timing gate is connected to the controller, and the distance between two timing gates can be calculated through infrared sensing. At the same time, multiple timing gates can be connected to each other to perform segmented timing between multiple timing gates. Take this experiment as an example:

[0065] The four timing gates are interconnected, and ultimately three times need to be recorded: the first time period from Gate 1 to Gate 2 (T1), the second time period from Gate 2 to Gate 3 or Gate 4 (T2), and the total time from Gate 1 to Gate 3 or Gate 4 (T1 + T2).

[0066] Stimulus sensor:

[0067] The sensor is height-adjustable and portable, and can be connected to a light display. When someone passes through the sensor, the light display will immediately respond with information. Furthermore, the sensor can also be connected to a timing system to record the time someone passes through the sensor.

[0068] Stimulus display:

[0069] Light off display: The light off display can display eight direction arrows (as shown in the figure), namely up, down, left, right, upper left, lower left, upper right and lower right. The display of the arrows in each direction on the display is controlled by the control system, and the response of the light source sensor is used to activate the display of relevant information.

[0070] Audio playback: The display can play the start command and is connected to the timer. The playback of the audio command can be controlled by the experimenter. The command playback can also start the timer and can be connected to the timing gate to stop the timing. (The audio command playback function can be turned off and not participate in the test)

[0071] Software main control system;

[0072] Device connection;

[0073] The hardware device can be started by a switch, wirelessly connected to the software main control system and controlled by the main control system.

[0074] Parameter recording;

[0075] Record the time between each moving distance, the total moving distance, and the time from the voice command to the first timing gate. (Time recording results are accurate to 0.001);

[0076] Control of stimulus sources;

[0077] Setting of light off information;

[0078] Single response mode: The stimulus sensor needs to be triggered once during the entire test process, and the direction indicated by the arrow can be predetermined by the experimenter;

[0079] Multiple response mode: The entire test process requires triggering the stimulus source sensor multiple times, and the direction indicated by the arrow each time can be predetermined by the experimenter;

[0080] Voice control command settings;

[0081] The sound command is activated by the experimenter by pressing a button, and the timer can be activated after the sound command is issued;

[0082] In this embodiment, the process of the football player agility test includes:

[0083] Preparation before the test:

[0084] Selected subjects (elementary school to high school age - adolescent population);

[0085] The subjects' age, height, weight, BMI, and field position (forward, midfielder, defender) were recorded;

[0086] Perform a standardized 15-minute warm-up, including two 800-meter laps of jogging, accelerations in various directions, directional changes, lateral movements, 10 push-ups and squats, and dynamic stretching of the lower extremities. Follow the warm-up with 2-3 minutes of active rest.

[0087] Inform the subjects to avoid strenuous exercise and high-intensity cognitive activities 24 hours before the experiment to prevent affecting the experimental results.

[0088] After the warm-up, each subject had two chances to try in order to familiarize themselves with the experimental process.

[0089] After becoming familiar with the experimental process, the subjects began the formal experiment. Each subject had three test opportunities, with a 1-minute interval between each test. The best score was taken, and the completion time was rounded to two decimal places.

[0090] The test route for each subject is randomly selected according to a pre-set procedure. The sensitive test route map is as follows: Figure 3 As shown;

[0091] The subject starts 50 cm from the starting line (to prevent premature contact with the infrared light of the electronic timing gate due to starting posture). After hearing the start command, they run a 4-meter shuttle run back and forth at maximum speed. Then, after returning to the starting line, they accelerate in a straight line to the No. 2 electronic timing gate, triggering the stimulus source sensor. They slow down and brake before reaching intersection O. At this time, there are four directions ahead: A, B, C, and D. The subject needs to react quickly and make the correct judgment based on the arrow signals indicating the direction given by the light stimulus source 3 meters in front of them. Then, they accelerate in a straight line to the end of the direction indicated by the signal light, and then run back to the starting line. The subject needs to complete the test in four directions in one test, and the final completion time is recorded to two decimal places.

[0092] Notes:

[0093] During the test, the subjects need to step on or exceed the starting line and the dotted lines set in the four directions of the finish line to ensure that the infrared rays of the electronic timing gate are triggered and the results are valid. If the electronic timing gate is not triggered, the results will be cancelled and there will be one opportunity to retake the test.

[0094] If the subject fails to make the correct judgment and choose the correct test route during the test, the test will be stopped immediately without retesting. This test will be recorded as the basis for the accuracy of the subject's decision-making.

[0095] The subjects are required to start from a stationary state at the starting line and are not allowed to start with a run-up. If this requirement is violated, the test results will not be recorded and there will be one opportunity to retake the test.

[0096] The direction of the signal light stimulus source in each test is composed of a pre-determined experimental program. There are 8 experimental programs in total, which are connected to the computer and randomly selected by the tester before the subject is formally tested.

[0097] When the subject passes through electronic timing gate No. 2 and triggers the stimulus source sensor, if he exceeds point O due to inertia, the test will continue and the test results will be recorded. No retest will be conducted.

[0098] like Figure 4 As shown, in this embodiment, a physical fitness test auxiliary method for athletes specifically includes:

[0099] Step S101 , obtaining real-time data streams of different physical fitness test devices, and using a preset device interface protocol to convert the heterogeneous data into data in a unified format through a data format conversion module.

[0100] Acquire real-time heterogeneous data from fitness test equipment, use the preset device interface protocol for data collection, and obtain raw heterogeneous data; obtain key data elements through data cleaning and feature extraction based on the data format characteristics of the heterogeneous data; use the data format conversion module to convert the key data elements into a unified data format;

[0101] Specifically, real-time heterogeneous data collection from fitness testing equipment is the foundation of fitness assessment. Taking a treadmill as an example, raw data such as speed, heart rate, and slope can be obtained through a preset interface protocol. During data cleaning, outliers such as records with a heart rate of 0 or exceeding 250 can be eliminated, and key data elements such as maximum heart rate and average pace can be extracted. The data format conversion module unifies data from different devices into a standard format, such as unifying heart rate data into beats per minute. Data quality standards may include aspects such as completeness and accuracy. If the converted data does not meet the standards, such as if more than 30% of the heart rate data is missing, data cleaning must be performed again. Data that meets the standards is stored in a unified format database, laying the foundation for subsequent analysis.

[0102] Step S102: extracting the athlete number from the data in the unified format according to a preset athlete identification rule, and matching it with a pre-established athlete information database to obtain the athlete identity information.

[0103] According to preset athlete identification rules, athlete number information is extracted from uniformly formatted data. Regular expression matching is used to identify and extract the athlete numbers. The extracted athlete numbers are matched against the number field in a pre-established athlete information database. A database query is performed to obtain the athlete identity information corresponding to the numbers. If the athlete number matches the corresponding identity information in the database, the identity information is associated with the number to obtain a number-identity information match result. If no corresponding identity information is found, the number is marked as unidentified. Athlete numbers marked as unidentified are manually verified and supplemented in the athlete information database, and steps 2 and 3 are repeated until all numbers are matched to corresponding identity information. Based on the matching results, a number-identity information mapping table is constructed and stored in a key-value pair data structure for rapid subsequent access and retrieval. During the athlete identification process, if the same number corresponds to multiple identity information, a similarity algorithm is used to compare other athlete information, such as name and age, to determine the final identity match result. The log data during the identification and matching process is recorded and stored, including the extracted athlete numbers, matched identity information, unidentified numbers, etc., so as to facilitate subsequent statistical analysis and optimization of identification rules.

[0104] Specifically, athlete identification is a key step in analyzing physical fitness test data. First, athlete numbers are extracted from uniformly formatted data. Regular expression matching can be used. For example, if the number format is "letters + numbers," such as "A001," the regular expression "[AZ]\d{3}" can be used to match it. This method quickly and accurately identifies numbers that meet the requirements. After extracting the numbers, they are matched against a pre-established athlete information database. This database may contain basic athlete information such as name, age, and event. By querying the database, detailed identity information corresponding to the number can be obtained. For example, the number "A001" may correspond to the information "Zhang San, male, 20 years old, sprinter." If a match is successful, an association is established between the number and the identity information. This association can help improve the accuracy of subsequent data analysis, such as analyzing the physical performance of athletes in specific age groups. If a match is unsuccessful, the number is marked as unidentified for subsequent manual verification. Manual verification may reveal that newly added athlete information has not yet been entered into the database. By supplementing and improving the information, the accuracy and completeness of the identification can be improved. Construct a mapping table between numbers and identity information, storing it in a key-value data structure. This structure facilitates fast access and recall, improving data processing efficiency. For example, a hash table can be used, with the key being the number and the value being the corresponding identity information. This allows for quick access to athlete information in subsequent data analysis simply by number. During the recognition process, the same number may correspond to multiple identities. In this case, a similarity algorithm can be used to compare other information to determine the final match. For example, an edit distance algorithm can be used to compare name similarity, or a comprehensive assessment can be made by combining information such as age and specialty. This approach effectively resolves identity confusion caused by data redundancy or entry errors. Log data from the recognition and matching process is recorded and stored, including extracted numbers, matching results, and unrecognized numbers. This log data can be used for subsequent statistical analysis, such as calculating recognition success rates and analyzing the reasons for unrecognized numbers.

[0105] Step S103 : For the test data in the unified format, a preset data cleaning rule is used to remove outliers and duplicate data to obtain a standardized physical fitness test data set.

[0106] According to the preset data cleaning rules, a physical fitness test data set in a unified format is obtained, and outlier detection is performed on the data set. If outliers exist, the outliers are removed to obtain a first data set; a data deduplication algorithm is used on the first data set to remove duplicate data to obtain a second data set; according to the preset data standardization rules, the second data set is standardized to obtain a standardized physical fitness test data set; a data exploration algorithm is used on the standardized physical fitness test data set to analyze the distribution characteristics of the data and obtain the statistical characteristics of the data; based on the statistical characteristics of the data, it is determined whether the data set meets the preset data quality requirements. If it meets the requirements, the standardized physical fitness test data set is determined as the final data set;

[0107] Specifically, physical fitness test data cleaning is a key step in ensuring data quality. First, obtain a dataset in a unified format according to pre-set rules, such as unifying data from different sources into a CSV format. Next, detect outliers using boxplots or Z-score methods. For example, if an athlete's 100-meter run time is 5 seconds, significantly below the norm, it should be considered an outlier and removed. Data deduplication is crucial to prevent duplicate records from impacting analysis results. A hash-based deduplication algorithm can be used to convert each record into a unique hash value for comparison. If two athletes have identical data across all test items, it's likely a duplicate entry, and only one should be retained. Normalization can eliminate the effects of different dimensions. Common methods include Z-score and Min-Max normalization. For example, for the standing long jump, raw data may range from 150 to 300 cm. After Min-Max normalization, all data is mapped to a range of 0 to 1, facilitating comprehensive evaluation with other events. Data exploratory analysis can help gain a deeper understanding of data characteristics. Statistics such as mean, median, and standard deviation can be calculated, and visualizations such as histograms and boxplots can be created. For example, if a bimodal distribution is observed in the data for a particular project, this may indicate significant differences in performance across the subject population. Data quality assessment ensures the reliability of subsequent analysis. Standards can be set, such as a maximum of 5% missing values ​​and a maximum of 1% outliers. If these standards are not met, data should be re-acquired or the cleaning strategy adjusted.

[0108] Step S104 , selecting corresponding evaluation criteria from a pre-established physical fitness evaluation model based on the age and gender information in the athlete's identity information, and analyzing the standardized physical fitness test data set.

[0109] Obtain the athlete's age and gender information, and based on these identity characteristics, select the corresponding evaluation standard model from the preset physical fitness evaluation standard model library. Conduct standardized physical fitness tests on the athletes, collect test data for various physical fitness indicators, and obtain a standardized physical fitness test data set. Input the standardized physical fitness test data set into the selected evaluation standard model, and score and grade each physical fitness indicator data according to the evaluation rules and thresholds set in the model. Based on the evaluation results of each physical fitness indicator, use weighted average or other comprehensive evaluation algorithms to calculate the athlete's comprehensive physical fitness evaluation score and grade. Compare the athlete's comprehensive physical fitness evaluation results with the normative data of their age and gender groups to determine the relative position and advantages and disadvantages of the athlete's physical fitness level among people of the same age and gender.

[0110] Specifically, during the physical fitness assessment process, the athlete's age and gender information must first be obtained. This information is crucial for selecting an appropriate assessment model. For example, a 20-year-old male athlete and a 35-year-old female athlete clearly require different assessment criteria. Based on these identity characteristics, the appropriate assessment model can be selected from a pre-set model library. Standardized physical fitness testing is crucial for ensuring the comparability of assessment results. Test items may include cardiorespiratory endurance, muscular strength, flexibility, and other aspects. For example, a cardiorespiratory endurance test might include a 12-minute run test, recording the distance the athlete runs within 12 minutes. Muscular strength tests might include push-ups and sit-ups, recording the number of reps completed within a specified time. After inputting the test data into the selected assessment model, the model will score and rank each indicator based on pre-set rules and thresholds. For example, in a 12-minute run test, a 20-year-old male athlete who runs over 3,000 meters might be rated as excellent, while a 35-year-old female athlete might qualify as excellent at 2,500 meters. A weighted average approach can be used for comprehensive assessment. For example, cardiorespiratory endurance accounts for 40%, muscular strength for 30%, flexibility for 20%, and body composition for 10%. This approach yields a comprehensive fitness assessment score and grade. By comparing the assessment results with normative data for people of the same age and gender, the athlete's relative position within the population can be determined. For example, if an athlete's overall score is 85, compared to the normative data, this score places them in the top 15% of their peers, indicating a relatively high level of fitness. Based on the assessment results, the system can automatically generate personalized training recommendations. For example, if an athlete's cardiorespiratory endurance is weak, a recommendation might be made to increase the proportion of aerobic training; if upper body strength is deficient, targeted strength training programs might be recommended. Regular retesting and evaluation are crucial for tracking fitness trends. By comparing test results over time, it's possible to clearly identify improvements or declines in various indicators, allowing for timely adjustments to training plans. For example, if an athlete's flexibility has significantly improved over the past three months, but strength gains have been slow, training priorities can be adjusted accordingly to achieve comprehensive and balanced fitness improvement. This systematic and personalized physical fitness assessment and training method can help coaches and athletes grasp the training direction more accurately, improve training efficiency, and ultimately achieve the goal of continuously improving physical fitness levels.

[0111] Obtaining athlete identification information is the starting point for physical fitness assessment. For example, a 20-year-old male basketball player's identification characteristics include age, gender, and sport. This information forms a feature vector, providing the basis for subsequent assessment. The feature vector might include [20, 1, 2], representing age, gender (1 for male), and sport (2 for basketball), respectively. Standardizing physical fitness test data is a key step in eliminating dimensional differences between different metrics. For example, suppose the original data includes height (cm), weight (kg), and vertical jump (cm). Standardization converts these metrics to the same scale, such as between 0 and 1. This allows for fair comparison of the performance of different metrics. Dividing the dataset based on sport characteristics improves model specificity. For example, in basketball, metrics such as vertical jump and sprint speed might be prioritized. The training set might contain 80% of the data for model learning, while the test set contains 20% for model validation. When training a classification model using the decision tree algorithm, different splitting criteria can be selected, such as information gain or the Gini coefficient. For example, the model might first classify based on vertical jump height and then consider sprint speed. This hierarchical decision-making process is similar to the evaluation method used by human experts and is highly interpretable. Preliminary fitness assessment results are obtained by using the trained decision tree model to predict the test set data. For example, the model may categorize athletes into four levels: "Excellent," "Good," "Fair," and "Needs Improvement." If the model's accuracy on the test set reaches a preset threshold (e.g., 85%), the model performance is considered acceptable. If the accuracy falls short, the model parameters need to be adjusted. Possible adjustments include changing the tree depth or adjusting the minimum number of sample splits. This process may require multiple iterations until the optimal parameter combination is found. Finally, the optimized decision tree model is applied to the athletes' standardized fitness test data to obtain the final assessment results. For example, for a 20-year-old male basketball player, the model might give a "Good" rating, noting that his vertical jump performance is excellent but that he needs to improve his endurance. Storing the assessment results associated with the athlete's identity information facilitates long-term tracking of the athlete's development.

[0112] Step S105 , matching the preliminary fitness assessment result with a pre-established training suggestion library through a preset rule engine to obtain a personalized training suggestion plan.

[0113] The user's fitness assessment results are analyzed to determine their fitness level. Training suggestions that match the user's fitness level are screened from a pre-established library of training suggestions. If multiple matching suggestions exist in the library, a decision tree algorithm is used to further filter them based on the user's personal attributes and health data to obtain the optimal personalized training suggestion. Content analysis is performed on the selected personalized training suggestions to extract key features, and similar suggestions are grouped together using a clustering algorithm. Based on the clustering results, an association rule mining algorithm is used to discover the correlations between different types of training suggestions, forming a complete training plan. The generated personalized training suggestion plan is output, and the training content is dynamically adjusted based on user feedback to continuously optimize training results.

[0114] Specifically, the process of generating personalized training recommendations involves multiple steps and technical topics. First, the user's preliminary fitness assessment results and personal health data are obtained as input. This data may include fitness metrics such as cardiorespiratory function, muscle strength, and flexibility, as well as health information such as age, gender, and medical history. For example, a 30-year-old male user's fitness assessment results show good cardiorespiratory function but slightly insufficient muscle strength. The user's fitness assessment results are analyzed based on pre-set assessment criteria to determine a fitness level. This step may use a multi-dimensional scoring system that comprehensively considers the weighting of various indicators. For example, the user's fitness level may be divided into beginner, intermediate, and advanced levels, each of which is further divided into low, medium, and high sub-levels. Matching recommendations are then selected from a pre-established library of training recommendations. The library may contain a variety of training plans tailored to different fitness levels and goals. For this user, a training recommendation may be selected that focuses on strengthening muscle strength while also maintaining cardiorespiratory function. If multiple matching recommendations are found, a decision tree algorithm is used for further screening. The nodes of the decision tree may include factors such as the user's age, occupation, and available training time. Through layer-by-layer screening, the most suitable personalized training recommendations for the user are ultimately obtained. The selected recommendations are subjected to content analysis to extract key features, and then categorized using a clustering algorithm. For example, training recommendations may be divided into categories such as aerobic exercise, strength training, and flexibility exercises. Clustering algorithms can use methods such as K-means or hierarchical clustering to group training recommendations based on similarity in content. Association rule mining algorithms are used to discover correlations between different types of training recommendations. This step can use the Apriori algorithm or FP-growth algorithm to analyze the matching patterns between different types of training. For example, it may be found that flexibility exercises after strength training can better promote recovery. Finally, the generated personalized training recommendation plan is output and dynamically adjusted based on user feedback. This may involve a feedback loop system that regularly collects users' training results and subjective feelings, and continuously optimizes the training plan through machine learning algorithms.

[0115] On the other hand, this embodiment also provides a physical fitness test auxiliary system for athletes, including:

[0116] A data acquisition module is used to obtain real-time data streams from different fitness test devices, and convert the real-time data streams into data in a unified format through a data format conversion module using a preset device interface protocol;

[0117] A data conversion module is used to extract the athlete number from the data in the unified format according to a preset athlete identification rule, and match it with a pre-established athlete information database to obtain the athlete identity information;

[0118] an identity recognition module, configured to remove outliers and duplicate data from the data in the unified format to obtain a standardized physical fitness test data set;

[0119] An evaluation standard selection module is used to select an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information, input the standardized physical fitness test data set into the evaluation standard model for calculation, and obtain the athlete's comprehensive physical fitness evaluation result;

[0120] The classification evaluation module is used to construct a personalized training recommendation plan based on the comprehensive physical fitness evaluation results.

[0121] On the other hand, this embodiment further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method is implemented when the processor executes the computer program.

[0122] On the other hand, this embodiment further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and is characterized in that the method is implemented when the computer program is executed by a processor.

[0123] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A physical fitness test auxiliary method for athletes, characterized in that: include: Acquire real-time data streams from different fitness test devices, and convert the real-time data streams into data in a unified format through a data format conversion module using a preset device interface protocol; Extracting the athlete number from the data in the unified format according to a preset athlete identification rule, and matching it with a pre-established athlete information database to obtain the athlete identity information; removing outliers and duplicate data from the data in the unified format to obtain a standardized physical fitness test data set; Based on the athlete's identity information, selecting an evaluation standard model from a preset physical fitness evaluation standard model library, inputting the standardized physical fitness test data set into the evaluation standard model for calculation, and obtaining a comprehensive physical fitness evaluation result of the athlete; A personalized training recommendation program is constructed based on the comprehensive physical fitness assessment results.

2. The method according to claim 1, characterized in that The process of obtaining real-time data streams from different fitness test devices and converting the real-time data streams into data in a unified format through a data format conversion module using a preset device interface protocol includes: Acquire real-time heterogeneous data from fitness test equipment, use the preset device interface protocol for data collection, and obtain original heterogeneous data; According to the data format characteristics of heterogeneous data, key data elements are obtained through feature extraction; For key data elements, a data format conversion module is used to convert them into a unified data format; If the converted data format meets the preset data quality standard, it will be stored in the unified format database; otherwise, feature extraction will be performed again to obtain the data in the unified format.

3. The method according to claim 1, characterized in that The process of obtaining the athlete's identity information includes: According to the preset athlete identification rules, the athlete number information is extracted from the data in a unified format, and the athlete number is identified and extracted using a regular expression matching method; Matching the extracted athlete number with the number field in a pre-established athlete information database, and obtaining the athlete identity information corresponding to the number through a database query operation; If the athlete number has the corresponding identity information found in the database, the identity information is associated with the number to obtain a number-identity information matching result.

4. The method according to claim 1, wherein The process of obtaining a standardized physical fitness test data set includes: Performing outlier detection on the data in the unified format, and if outliers exist, removing the outliers to obtain a first data set; For the first data set, a data deduplication algorithm is used to remove duplicate data to obtain a second data set; Performing standardization processing on the second data set according to a preset data standardization rule to obtain a processed physical fitness test data set; Calculating data distribution characteristics of the processed physical fitness test data set to obtain statistical characteristics of the data; Based on the statistical characteristics of the data, determine whether the data set meets the preset data quality requirements. If it meets the requirements, determine the standardized physical fitness test data set as the final data set.

5. The method according to claim 1, characterized in that The process of obtaining the athlete's comprehensive physical fitness evaluation results includes: Selecting an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information; Input the standardized physical fitness test data set into the selected evaluation standard model, and score and grade each physical fitness indicator data according to the evaluation rules and thresholds set in the model; Based on the evaluation results of various physical fitness indicators, a weighted average algorithm is used to calculate the athlete's comprehensive physical fitness evaluation score and level; The athlete's comprehensive physical fitness evaluation result is obtained based on the athlete's comprehensive physical fitness evaluation score and grade.

6. The method according to claim 1, characterized in that The process of selecting an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information includes: Obtain the identity information of athletes, extract sports features, construct feature vectors, and generate feature data sets; Dividing the feature data set into a training set and a test set according to the features of the sports event; A decision tree model is constructed based on the athlete identity information. After the decision tree model is trained using the training set, the decision tree model is tested using the test set until the loss function no longer converges and is output to obtain the evaluation standard model.

7. The method according to claim 1, characterized in that The process of constructing a personalized training recommendation plan based on the comprehensive fitness assessment results includes: Based on the comprehensive physical fitness assessment results, screening out training suggestions that match the user's physical fitness level from a pre-established training suggestion library; If there are multiple matching suggestions in the training suggestion library, a decision tree algorithm is used to further screen based on the user's personal attributes and health data to obtain the best personalized training suggestion; Conduct content analysis on the selected personalized training suggestions, extract key features, and use clustering algorithms to group similar suggestions into one category; Based on the clustering results, an association rule mining algorithm is used to discover the correlations between different types of training suggestions and form a complete training plan; The generated personalized training suggestion plan is output, and the training content is dynamically adjusted based on user feedback to continuously optimize the training effect.

8. A physical fitness test auxiliary system for athletes, characterized in that: include: A data acquisition module is used to obtain real-time data streams from different fitness test devices, and convert the real-time data streams into data in a unified format through a data format conversion module using a preset device interface protocol; A data conversion module is used to extract the athlete number from the data in the unified format according to a preset athlete identification rule, and match it with a pre-established athlete information database to obtain the athlete identity information; an identity recognition module, configured to remove outliers and duplicate data from the data in the unified format to obtain a standardized physical fitness test data set; An evaluation standard selection module is used to select an evaluation standard model from a preset physical fitness evaluation standard model library based on the athlete's identity information, input the standardized physical fitness test data set into the evaluation standard model for calculation, and obtain the athlete's comprehensive physical fitness evaluation result; The classification evaluation module is used to construct a personalized training recommendation plan based on the comprehensive physical fitness evaluation results.

9. An electronic device comprising a memory, a processor, and a computing program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images