Physical data real-time monitoring and abnormity early warning system for volleyball athletes

Abstract

The invention discloses a volleyball player physical ability data real-time monitoring and abnormity early warning system, and relates to the field of physical ability monitoring, and the system comprises a physical ability management platform which comprises a multi-source data acquisition module, a multi-source data management module, a multi-source data analysis module, a physical ability monitoring and evaluation module and a physical ability early warning analysis module; the multi-source data acquisition module is used for acquiring historical multi-source motion data and real-time multi-source motion data; the multi-source data management module is used for constructing a comprehensive physical ability analysis map according to historical multi-source motion data; the multi-source data analysis module is used for generating a personalized physical ability analysis map corresponding to the corresponding user; the physical ability monitoring and evaluation module analyzes the real-time multi-source motion data through the personalized physical ability analysis atlas to obtain real-time physical ability evaluation data; the physical ability early warning analysis module is used for judging whether the physical ability data of the athlete is abnormal or not according to the real-time physical ability evaluation data The accuracy in the physical ability data testing process of different volleyball athletes is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of physical fitness monitoring, and particularly to a real-time monitoring and abnormal warning system for the physical fitness data of volleyball players. Background Art

[0002] Volleyball is a sport featuring high intensity, fast pace, and frequent physical confrontations. Therefore, volleyball players need to continuously maintain a high level of physical fitness output during competitions and training. With the continuous improvement of modern volleyball competition levels and the increasing number of games, athletes are facing greater physical fitness pressure. In this context, it has become an urgent need to timely understand the physical fitness status of athletes and prevent sports injuries caused by over-fatigue or physical exhaustion, in order to protect the physical health of athletes and improve their competitive performance.

[0003] After retrieval, the invention patent with the Chinese patent number CN117084646B discloses a training injury monitoring and warning method and system based on electronic sensing, which relates to the technical field of data processing. By obtaining the user's real-time exercise heart rate set based on the exercise heart rate monitoring instruction and traversing and comparing the real-time exercise heart rate set to generate an exercise heart rate warning instruction; obtaining the user's peak exercise heart rate set based on the recovery heart rate monitoring instruction and comparing it with the exercise recovery heart rate set in multiple rounds to generate a recovery heart rate warning instruction. It solves the technical problem that the formulation of the physical fitness training plan in the prior art depends on manual experience, which is not suitable for the physical functions of the training participants, resulting in easy occurrence of training injuries and even sports sudden death accidents. It achieves the technical effect of obtaining the user's physical fitness status from the dimensions of exercise heart rate monitoring and exercise recovery heart rate monitoring, providing a reference for timely and effectively adjusting the training intensity and training volume adaptively, thereby effectively avoiding the occurrence of training injuries caused by training, reducing the probability of user sports sudden death, and protecting the physical and mental health of the training participants.

[0004] Compared with the prior art, the invention patent with the Chinese patent number CN117084646B can analyze and process the exercise heart rates of different athletes, and set corresponding peak exercise heart rate sets and exercise recovery heart rate sets according to the exercise heart rate sets of different athletes, thereby improving the accuracy of user monitoring and warning.

[0005] However, in the actual use process of the above system, only using the peak heart rate data during the movement of relevant personnel as the evaluation standard, there is a situation where the monitoring and warning results are inaccurate due to the problem of data simplification to a certain extent. Moreover, during the movement of athletes, the heart rate data is affected differently according to different personal physical qualities, exercise durations, and exercise movements. Therefore, only monitoring and warning the physical fitness data during the movement of athletes through heart rate data may have the problem of insufficient accuracy. Summary of the Invention

[0006] The object of the present invention is to solve the problems of insufficient accuracy and low personalization in the prior art, and a real-time monitoring and abnormal warning system for the physical fitness data of volleyball players is proposed.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: A real-time monitoring and abnormal warning system for the physical fitness data of volleyball players, including a physical fitness management platform, which includes a multi-source data acquisition module, a multi-source data management module, a multi-source data analysis module, a physical fitness monitoring and evaluation module, and a physical fitness warning analysis module; The multi-source data acquisition module is used to collect historical multi-source motion data and real-time multi-source motion data of volleyball players during the motion process in the physical fitness monitoring volleyball court, including motion environment data, motion image data, and motion physiological data; The multi-source data management module is used to decompose the historical multi-source motion data obtained in the platform in sequence, generate corresponding comprehensive links according to the decomposition results, perform correlation analysis on the obtained comprehensive links, and construct a comprehensive physical fitness analysis map; The multi-source data analysis module is used to extract features from the historical multi-source motion data corresponding to the corresponding volleyball players, perform comparative analysis based on the feature extraction results and the comprehensive physical fitness analysis map, and generate a personalized physical fitness analysis map according to the comparative analysis results; The physical fitness monitoring and evaluation module is used to analyze and process the real-time multi-source motion data corresponding to the corresponding users according to the personalized physical fitness analysis map, and obtain real-time physical fitness evaluation data; The physical fitness warning analysis module is used to perform warning analysis based on the real-time physical fitness evaluation data obtained by the user, and judge whether there is physical fitness abnormality in the corresponding athlete.

[0008] The above technical solution further includes: The process of collecting historical multi-source motion data and real-time multi-source motion data includes: Set an information entry window, and enter user collection information and historical multi-source motion data through the information entry window; Set an environment collection unit, an image collection unit, and a physiological collection unit, and respectively obtain the motion environment data, motion image data, and motion physiological data of the corresponding volleyball players during the motion process in the physical fitness monitoring volleyball court according to the corresponding user collection information. The collected data is uniformly referred to as real-time multi-source motion data, and the corresponding real-time multi-source motion data is marked according to the collection time.

[0009] Further, the process of decomposing the historical multi-source motion data obtained in the platform in sequence to obtain the corresponding comprehensive link includes: Obtain the motion environment data, motion image data, and motion physiological data corresponding to the historical multi-source motion data in the physical fitness management platform, and set the corresponding environment nodes, image nodes, and physiological nodes respectively; The environment node and the physiological node respectively set the corresponding environment sub-nodes and physiological sub-nodes in sequence according to the different data types corresponding to the motion environment data and the motion physiological data. The image node analyzes and processes the motion image data, obtains the standard key features of the corresponding actions and the trajectory feature data during the volleyball motion process, obtains the corresponding action types according to the standard key features, sets the corresponding image sub-nodes according to the action types, constructs a mechanical analysis model according to the trajectory feature data, and sets the trajectory sub-nodes; Mark and process the corresponding types of motion environment data, motion physiological data, and motion image data through the corresponding environment sub-nodes, physiological sub-nodes, image sub-nodes, and trajectory sub-nodes respectively, and set the corresponding longitudinal environment number axis, longitudinal physiological number axis, longitudinal action number axis, and longitudinal force application number axis; The environment node, the image node, and the physiological node are respectively connected and processed according to the corresponding longitudinal environment number axis, longitudinal physiological number axis, longitudinal action number axis, and longitudinal force application number axis to generate an environment comprehensive link, an image comprehensive link, and a physiological comprehensive link.

[0010] Furthermore, the process of constructing the comprehensive physical fitness analysis atlas includes: Connect the generated environment comprehensive link, image comprehensive link, and physiological comprehensive link in sequence; Set the corresponding fuzzy intervals respectively according to the data types corresponding to the longitudinal number axes in each environment comprehensive link and image comprehensive link, and traverse and combine the data information obtained in the corresponding longitudinal number axes according to the corresponding fuzzy intervals to generate the corresponding independent variable data set; Obtain the corresponding motion physiological data according to the motion environment data and motion image data corresponding to the independent variable data set, and generate the corresponding dependent variable data set; Analyze the multi-source motion data in the obtained independent variable data set X and dependent variable data set Y, set the to-be-evaluated parameters corresponding to the corresponding data types, perform a correlation evaluation on the independent variable data set and the dependent variable data set according to the corresponding to-be-evaluated parameters to obtain the physical fitness evaluation data, and compare and analyze the obtained physical fitness evaluation data with the preset evaluation limit value to determine whether the corresponding independent variable data set and the dependent variable data set are associated; Adjust and analyze the corresponding to-be-evaluated parameters according to the association result until there is an association, and mark the corresponding to-be-evaluated parameters as association evaluation parameters; Connect and associate the longitudinal number axes corresponding to the independent variable data set and the dependent variable data set according to the corresponding association evaluation parameters to construct a comprehensive physical fitness analysis atlas.

[0011] Further, the process of feature extraction for the corresponding historical multi-source motion data of volleyball players includes: Obtain the historical multi-source motion data of the corresponding volleyball players, traverse and match the multi-source motion data sequentially along the vertical number axis of the corresponding data type in the comprehensive physical fitness analysis map, obtain the characteristic attributes of the vertical number axis to which the multi-source motion data belongs, set the matching results as the characteristic data of the historical multi-source motion data corresponding to the corresponding volleyball players, and set the characteristic data set.

[0012] Further, the process of setting up the personalized physical fitness analysis map includes: Set the physical fitness monitoring time axis according to the collection time of the historical multi-source motion data, map the characteristic data sets corresponding to the multi-source motion data to the corresponding positions in the physical fitness monitoring time axis according to the corresponding collection time, connect each characteristic data set according to the unit time of the physical fitness monitoring time axis to generate a physical fitness monitoring data storage chain, and integrate the physical fitness monitoring data storage chains corresponding to multiple historical multi-source motion data to generate a user physical fitness comprehensive data set; Set the segmentation processing period according to the corresponding unit time, adjust the associated evaluation parameters in the comprehensive physical fitness analysis map according to the characteristic data of the corresponding unit time in the user physical fitness comprehensive data set within the corresponding segmentation processing period, and obtain the corresponding segmented evaluation parameters according to the adjustment results; Arrange the corresponding segmented evaluation parameters in the user physical fitness comprehensive data set according to the segmentation processing period order, and adjust and integrate the comprehensive physical fitness analysis map respectively according to the sequential arrangement results to generate a personalized physical fitness analysis map.

[0013] Further, the process of obtaining real-time physical fitness evaluation data includes: Obtain the personalized physical fitness analysis map, and map the real-time multi-source motion data obtained by the volleyball players in the physical fitness monitoring volleyball court to the personalized physical fitness analysis map; Obtain the corresponding predicted exercise physiological data according to the segmented evaluation parameters of the personalized physical fitness analysis map, compare and analyze the real-time multi-source motion data with the predicted exercise physiological data according to the corresponding data types, and obtain the physical fitness deviation data; Set up a physical fitness analysis storage library according to the corresponding data types, input the physical fitness deviation curve into the physical fitness analysis library for real-time evaluation, obtain the physiological evaluation data of the corresponding data types, and integrate according to the corresponding physiological evaluation data to generate real-time physical fitness evaluation data.

[0014] Further, construct physical fitness monitoring models and anomaly warning models for the corresponding data types based on deep learning algorithms; Obtain real-time physical fitness assessment data, input the physiological assessment data of corresponding data types in the real-time physical fitness assessment data into the corresponding physical fitness monitoring models respectively, and obtain the monitoring feedback results of the corresponding data types; Integrate the monitoring feedback results corresponding to the physiological assessment data of each data type to generate a comprehensive feedback set, input the comprehensive feedback set into the anomaly warning model, perform analysis and processing through the anomaly warning model, output the anomaly analysis results, and determine whether there is a physical fitness anomaly in the corresponding volleyball player according to the output anomaly analysis results.

[0015] The present invention has the following beneficial effects: 0. In the present invention, by obtaining multi-source motion data of volleyball players during the movement process, a comprehensive physical fitness analysis map is set for the correlation relationship between the motion environment data, motion image data, and motion physiological data in the multi-source motion data. Based on the comprehensive physical fitness analysis map, most of the correlation situations during the movement process of volleyball players are obtained as a basis. Through comparative analysis between the historical multi-source motion data of the corresponding user and the comprehensive physical fitness analysis map, a corresponding personalized physical fitness analysis map is obtained, so as to perform personalized adjustment according to the physical fitness and movement habit skills of the corresponding volleyball player, thereby improving the personalized difference in the monitoring process of the physical fitness data of the corresponding volleyball player to a certain extent and improving the accuracy in the data monitoring process.

[0016] 1. In the present invention, by setting corresponding vertical number axes for different data situations corresponding to different data types in the corresponding motion environment data, motion image data, and motion physiological data in the multi-source motion data, the corresponding multi-source motion data is integrally marked and processed through the corresponding vertical number axes to obtain the corresponding independent variable data set and dependent variable data set. The corresponding real-time multi-source motion data is evaluated and processed through the correlation relationship between the independent variable data set and the dependent variable data set, thereby avoiding to a certain extent the situation of reduced accuracy in the data processing process caused by data missing.

[0017] 2. In the present invention, different types of motion physiological data are obtained, and the anomaly assessment is carried out through the change situation of different types of motion physiological data during the movement process of volleyball players, thereby avoiding to a certain extent the situation of insufficient accuracy of the monitoring and warning results caused by data simplification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic structural diagram of a real-time monitoring and anomaly warning system for the physical fitness data of volleyball players proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, for the convenience of description, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] Embodiment 1 As Figure 1 shown, the real-time monitoring and abnormal warning system for the physical fitness data of volleyball players proposed by the present invention includes a physical fitness management platform, and the physical fitness management platform includes a multi-source data acquisition module, a multi-source data management module, a multi-source data analysis module, a physical fitness monitoring and evaluation module, and a physical fitness warning analysis module; In this embodiment, the physical fitness management platform is used to monitor the physical fitness data of volleyball players in daily volleyball training and volleyball competitions in real time, and feedback the real-time monitoring results to the corresponding volleyball players, so as to facilitate volleyball players to adjust their states in a timely manner during daily volleyball sports, and provide a reference direction for the physical fitness monitoring of volleyball players. The specific implementation process includes: The multi-source data acquisition module is used to collect multi-source motion data of volleyball players during volleyball sports. The multi-source motion data includes motion environment data, motion image data, and motion physiological data. The specific implementation process includes: Set up an environment acquisition unit, an image acquisition unit, and a physiological acquisition unit; An information entry window is set in the multi-source data acquisition module; The information entry window is used to enter the corresponding user acquisition information and historical multi-source motion data. The user acquisition information includes various data information such as the basic information of volleyball players, the historical motion data of athletes, and the informed consent form, etc.; verify the corresponding user acquisition information, and send the user acquisition information that has completed the verification process to the corresponding acquisition unit respectively, and the corresponding acquisition unit collects the motion data of the corresponding volleyball player. The historical multi-source motion data includes the multi-source motion data corresponding to the user number in the corresponding physical fitness monitoring volleyball court and the physical fitness monitoring result data; The environment acquisition unit is connected to the environment monitoring sensors corresponding to the physical fitness monitoring volleyball court, and obtains the motion environment data corresponding to the physical fitness monitoring volleyball court through the environment monitoring sensors. The environment monitoring sensors include corresponding meteorological monitoring sensors, light sensors, etc.; the motion environment data includes environmental temperature data, environmental humidity data, environmental wind speed data, environmental wind direction data, and light intensity distribution data, etc.; The image acquisition unit is used to collect the motion image data of the corresponding volleyball players during the movement. A physical fitness monitoring volleyball court is set up, and multiple high-definition cameras are installed at different positions and heights within the physical fitness monitoring volleyball court. The obtained high-definition cameras are interconnected with the corresponding image acquisition units to obtain the motion image data of each volleyball player within the physical fitness monitoring volleyball court; Analyze and process the motion image data obtained within the physical fitness monitoring volleyball court. Based on the user's collected information, set the visual feature information of the corresponding volleyball players. Use the obtained visual feature information and target detection algorithms to perform athlete positioning processing on the motion image data obtained within the physical fitness monitoring volleyball court. Based on the athlete positioning processing results, continuously track the athletes using motion tracking algorithms to obtain the motion image data corresponding to the corresponding volleyball players; The physiological acquisition unit is interconnected with the corresponding physiological monitoring sensors. The physiological monitoring sensors include various types such as wearable devices, adhesive sensors, and laboratory monitoring equipment. Through the physiological monitoring sensors, obtain the exercise physiological data corresponding to the corresponding volleyball players. The exercise physiological data includes various physiological index data such as heart rate data, movement trajectory data, muscle electrical activity data, blood oxygen saturation data, hemoglobin data, and lactic acid data; Unify the obtained motion environment data, motion image data, and motion physiological data and label them as the multi-source motion data of the corresponding volleyball players during the volleyball movement process, and send them to the multi-source data management module.

[0021] The multi-source data management module is used to sequentially analyze and process the multi-source motion data obtained within the platform, construct a comprehensive physical fitness analysis map, and perform real-time update and storage on the comprehensive physical fitness analysis map. The specific implementation process includes: Set up a decomposed data management unit and a comprehensive data management unit; Through the decomposed data management unit, obtain the historical multi-source motion data obtained within the platform, and perform decomposition processing on the historical multi-source motion data respectively. Set up a single monitoring data processing link. The specific implementation process includes: Obtain the motion environment data, motion image data, and motion physiological data corresponding to the historical multi-source motion data, and set the corresponding environment nodes, image nodes, and physiological nodes respectively according to the motion environment data, motion image data, and motion physiological data; Analyze and process the corresponding motion environment data, motion image data, and motion physiological data through the environment node, image node, and physiological node respectively; The environmental node and the physiological node respectively obtain the motion environment data and motion physiological data corresponding to the corresponding physical fitness monitoring volleyball court, set environmental sub-nodes in sequence according to different data types in the motion environment data, and set physiological sub-nodes in sequence according to different data types in the motion physiological data; The corresponding environmental sub-nodes and physiological sub-nodes respectively analyze and process the corresponding types of motion environment data and motion physiological data, and set the corresponding vertical environmental number axis and vertical physiological data. The environmental sub-nodes map the corresponding types of motion environment data to the corresponding positions within the vertical environmental number axis, and the physiological sub-nodes map the corresponding types of motion physiological data to the corresponding positions within the vertical physiological number axis; Respectively obtain the environmental standard data and physiological standard data corresponding to different types of motion environment data and motion physiological data within the corresponding physical fitness monitoring volleyball court, and set the corresponding reference center points for the vertical environmental number axis corresponding to each environmental sub-node and the vertical physiological number axis corresponding to each physiological sub-node according to the environmental standard data and physiological standard data; Connect the reference center points corresponding to the vertical environmental number axes corresponding to different types of motion environment data to set an environmental comprehensive link; Connect the reference center points corresponding to the vertical physiological data corresponding to different types of motion physiological data to set a physiological comprehensive link; The imaging node obtains the motion image data corresponding to all athletes within the physical fitness monitoring volleyball court, analyzes and processes the motion image data, and obtains athlete motion data and volleyball motion data; Set the obtained motion image data within the platform as a motion image data set, perform feature extraction on the motion image data set to obtain the standard key features of the corresponding actions. The corresponding actions include various types such as the ready position, movement mode, serving action, passing action, setting action, spiking action, and blocking action, and set the corresponding action types as imaging sub-nodes respectively; The corresponding imaging sub-nodes analyze and process the standard key features, and comprehensively sort the occurrence probabilities of the corresponding action types according to the position roles of the corresponding volleyball players; Vertically sort the imaging sub-nodes corresponding to the corresponding action types according to the comprehensive sorting results to generate an action independent variable link; Analyze and process the volleyball motion data, obtain the volleyball monitoring data within the corresponding physical fitness monitoring volleyball court in the motion image data, obtain the corresponding volleyball motion trajectory data according to the volleyball monitoring data, and obtain the corresponding trajectory feature data corresponding to the volleyball at the corresponding moment. The trajectory feature data includes various types of data information such as but not limited to initial velocity data, height data, and direction data; Set the trajectory feature data corresponding to the corresponding volleyball movement trajectory data as the trajectory feature set, and preprocess the corresponding data information in the trajectory feature set; Obtain the corresponding trajectory feature set, perform analysis and processing on the trajectory feature set, obtain the force application degree data corresponding to the corresponding movement trajectory, and obtain the corresponding force application data set; Correspond the trajectory feature set with the corresponding force application data set, set the corresponding training set, train the corresponding training set with a multi-layer perceptron based on a machine learning algorithm, construct a mechanical analysis model, and associate the obtained mechanical analysis model with the trajectory sub-nodes; Set the corresponding force application degree as the longitudinal force application number axis, connect the action independent variable link with the longitudinal force application number axis, and generate an image comprehensive link; Mark the obtained environment comprehensive link, image comprehensive link, and physiological comprehensive link as single monitoring data processing links, and send the corresponding comprehensive links and marking results to the comprehensive data management unit; Obtain the single monitoring data processing link corresponding to the multi-source motion data obtained by the decomposition data management unit through the comprehensive data management unit, perform analysis and processing according to the single monitoring data processing link, and set the corresponding comprehensive physical fitness analysis map. The specific implementation process includes: Obtain the single monitoring data processing link corresponding to the multi-source motion data, and connect the environment comprehensive link, image comprehensive link, and physiological comprehensive link in sequence; Obtain the motion environment data type corresponding to the corresponding environment sub-node in the environment comprehensive link and the athlete action class corresponding to the image sub-node and the force application degree data corresponding to the corresponding longitudinal force application number axis in the image comprehensive link; Set the fuzzy interval according to the corresponding data type, and traverse and combine and extract the data information obtained in the corresponding longitudinal number axis according to the corresponding fuzzy interval to generate the corresponding independent variable data set. The independent variable data set includes the fuzzy reference intervals corresponding to the data types of the corresponding longitudinal number axes; Select the corresponding historical multi-source motion data in the platform according to the fuzzy reference intervals corresponding to the data types in the corresponding independent variable data set, map the motion physiological data in the obtained multi-source motion data to the corresponding positions in the corresponding longitudinal number axis in the physiological comprehensive link, and obtain the corresponding dependent variable data set; Comprehensively analyze the multi-source motion data in the obtained independent variable data set X and dependent variable data set Y, where, X = x1, x2, …, x i 、…、x n , Y = y1, y2, …, y i 、…、y n ; According to the corresponding sample data points (x i , y i ) in the independent variable data set X and the dependent variable data set Y, they are respectively mapped into the high-dimensional feature space, and each sample data point in the high-dimensional feature space is analyzed and processed. Corresponding parameters to be evaluated β0, β1, β2, …, β j , is the error term, where j is the number of data type quantities on the corresponding vertical number axis, where: ; , ; According to the corresponding parameters to be evaluated, the correlation between the independent variable data set and the dependent variable data set is evaluated, and the balanced evaluation coefficient is set, and the preset physical fitness evaluation data TP, where: , is the preset evaluation influence factor; The preset evaluation limit PX and the associated limit GX are set, and the error comparison analysis is carried out between the physical fitness evaluation data TP and the corresponding evaluation limit PX to judge whether the corresponding independent variable data set and the dependent variable data set conform to the association; If PX < , there is an association; if PX ≥ , there is no association. The parameters to be evaluated corresponding to the independent variable data set and the dependent variable data set without association are adjusted and analyzed until there is an association, and the corresponding parameters to be evaluated are marked as association evaluation parameters; Each independent variable data set and dependent variable data set are analyzed and processed in turn to judge the relationship between the corresponding motion environment data, motion image data and motion physiological data; According to the relationship between the corresponding motion environment data, motion image data and motion physiological data, an association is made, a comprehensive physical fitness analysis atlas is set, and it is sent to the multi-source data analysis module.

[0022] The multi-source data analysis module is used to compare and analyze the multi-source motion data corresponding to the corresponding volleyball players and the corresponding comprehensive physical fitness analysis atlas, and set a personalized physical fitness analysis atlas. The specific implementation process includes: Obtain and analyze the historical multi-source motion data obtained by the corresponding volleyball players in the corresponding physical fitness monitoring volleyball court, and obtain the acquisition time corresponding to the corresponding multi-source motion data; Set the physical fitness monitoring time axis according to the acquisition time of the historical multi-source motion data, and map the corresponding motion environment data, motion image data and motion physiological data in the obtained multi-source motion data into the comprehensive physical fitness analysis atlas; Traverse the multi-source motion data in sequence along the vertical number axis of the corresponding data type in the comprehensive physical fitness analysis atlas for comparative analysis, obtain the characteristic attributes of the vertical number axis to which the multi-source motion data belongs, and divide the corresponding characteristic attributes into independent variable characteristic data and dependent variable characteristic data; Set the obtained independent variable characteristic data and dependent variable characteristic data as a characteristic data set, map the characteristic data set corresponding to the multi-source motion data to the corresponding position in the physical fitness monitoring time axis according to the corresponding acquisition time, and set up a physical fitness monitoring data storage chain according to the characteristic data set corresponding to the corresponding position of the physical fitness monitoring time axis; Integrate the obtained physical fitness monitoring data storage chains to obtain a comprehensive user physical fitness data set; Analyze and process the comprehensive user physical fitness data set, correspond the acquisition time according to the corresponding start time, set the corresponding unit time, and map the corresponding independent variable characteristic data and dependent variable characteristic data to the comprehensive physical fitness analysis atlas according to the unit time; Obtain the distribution of the independent variable characteristic data and dependent variable characteristic data of the corresponding unit time on the corresponding vertical number axis in the comprehensive physical fitness analysis atlas respectively, and integrate according to the distribution of each characteristic data in the physical fitness monitoring data storage chain; Analyze and process each user's comprehensive physical fitness data set in the physical fitness monitoring data storage chain according to the force data within the unit time; Set a segmented processing period according to the corresponding unit time, and analyze and process according to the positions of the independent variable characteristic data and dependent variable characteristic data of the corresponding unit time within the segmented processing period in the comprehensive physical fitness analysis atlas; Adjust the associated evaluation parameters within the comprehensive physical fitness analysis atlas corresponding to the characteristic data of the corresponding unit time in the user's comprehensive physical fitness data set according to the corresponding segmented processing period, and obtain the corresponding segmented evaluation parameters within the corresponding comprehensive physical fitness analysis atlas for the corresponding segmented processing period according to the adjustment results; Store the user's comprehensive physical fitness data set according to the segmented evaluation parameters of the comprehensive physical fitness analysis atlas corresponding to the corresponding segmented processing period; Arrange the corresponding segmented evaluation parameters in the user's comprehensive physical fitness data set according to the order of the segmented processing periods, perform personalized adjustments on the comprehensive physical fitness analysis atlas respectively according to the arranged results in order, integrate the comprehensively physically fitness analysis atlas after completing the personalized adjustment according to the order of the segmented processing periods, generate a personalized physical fitness analysis atlas corresponding to the corresponding user, and send the personalized physical fitness analysis atlas to the physical fitness monitoring and evaluation module.

[0023] The physical fitness monitoring and evaluation module is used to analyze and process the multi-source motion data corresponding to the corresponding user according to the personalized physical fitness analysis atlas to obtain real-time physical fitness evaluation data. The specific implementation process includes: Obtain a personalized physical fitness analysis map, and map the multi-source motion data obtained by volleyball players in the physical fitness monitoring volleyball court to the personalized physical fitness analysis map; Obtain the corresponding segmented evaluation parameters in the personalized physical fitness analysis map according to the acquisition time of the multi-source motion data. Map the multi-source motion data to the corresponding longitudinal number axis in the personalized physical fitness analysis map according to the segmented evaluation parameters. According to the position information of the longitudinal number axis of the motion environment data and the motion image data, obtain the predicted exercise physiological data according to the personalized physical fitness analysis map; Set up a two-dimensional space coordinate system corresponding to the time information of the exercise physiological data corresponding to the corresponding data type, and map the predicted exercise physiological data and the exercise physiological data corresponding in the multi-source motion data to the corresponding positions in the two-dimensional space coordinate system according to the corresponding acquisition time; Conduct a comparative analysis on the predicted exercise physiological data and the corresponding exercise physiological data in the multi-source motion data of the corresponding data type in the two-dimensional space coordinate system. Obtain the corresponding physical fitness deviation data according to the comparative analysis result, and mark the obtained physical fitness deviation data according to the corresponding acquisition time; Obtain the physical fitness deviation data corresponding to the corresponding data type within the corresponding acquisition time, and set a physical fitness deviation curve for the physical fitness deviation data of the corresponding data type according to the corresponding acquisition time; Set up a physical fitness analysis storage library according to the corresponding data type, input the physical fitness deviation curve into the physical fitness analysis library for real-time evaluation, and obtain the physiological evaluation data of the corresponding data type; It should be further noted that in the specific implementation process, the physical fitness analysis library is the characteristic data preset for evaluating the change process corresponding to different exercise physiological data in the corresponding physical fitness management platform. Compare the exercise physiological data with the characteristic data of the corresponding change process to obtain the corresponding physiological evaluation data; Integrate the physiological evaluation data of each exercise physiological data corresponding to the corresponding data type within the corresponding acquisition time to obtain real-time physical fitness evaluation data, and send the obtained real-time physical fitness evaluation data to the physical fitness warning analysis module.

[0024] The physical fitness warning analysis module is used to conduct a warning analysis based on the real-time physical fitness evaluation data obtained by the user, judge whether there is a physical fitness abnormality in the corresponding athlete, and conduct a warning process on the data with physical fitness abnormalities. Its specific implementation process includes: Based on the deep learning algorithm, construct a physical fitness monitoring model and an abnormal warning model for the corresponding data type respectively, where: The physical fitness monitoring model is used to analyze and process the physiological evaluation data of the corresponding data type to judge whether there is an abnormal situation type involved by the athlete in the corresponding physiological evaluation data; The abnormal warning model is used to integrate the judgment results corresponding to each physiological assessment data, and determine whether the physiological assessment data of other data types conforms when an abnormal situation type exists, so as to determine the physical fitness abnormal situation type of the corresponding volleyball player during the movement process; Obtain real-time physical fitness assessment data, input the physiological assessment data of the corresponding data type in the real-time physical fitness assessment data into the corresponding physical fitness monitoring model respectively, and obtain the monitoring feedback results of the corresponding data type; Integrate the monitoring feedback results corresponding to the physiological assessment data of each data type to generate a comprehensive feedback set, and input the comprehensive feedback set into the abnormal warning model. Through analysis and processing by the abnormal warning model, output the abnormal analysis result, and judge whether the corresponding volleyball player has physical fitness abnormalities according to the output abnormal analysis result. If there are physical fitness abnormalities, give a warning for the data with physical fitness abnormalities.

[0025] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring and abnormal warning system for the physical fitness data of volleyball players, including a physical fitness management platform, characterized in that, The physical fitness management platform includes a multi-source data collection module, a multi-source data management module, a multi-source data analysis module, a physical fitness monitoring and evaluation module, and a physical fitness early warning analysis module; The multi-source data collection module is used to collect historical multi-source motion data and real-time multi-source motion data of volleyball players during the motion process in the physical fitness monitoring volleyball court, including motion environment data, motion image data, and motion physiological data; The multi-source data management module is used to decompose and process the historical multi-source motion data obtained in the platform in sequence, generate corresponding comprehensive links according to the decomposition and processing results, perform correlation analysis on the obtained comprehensive links, and construct a comprehensive physical fitness analysis map; The multi-source data analysis module is used to extract features from the historical multi-source motion data corresponding to the corresponding volleyball players, perform comparative analysis based on the feature extraction results and the comprehensive physical fitness analysis map, and generate a personalized physical fitness analysis map according to the comparative analysis results; The physical fitness monitoring and evaluation module is used to analyze and process the real-time multi-source motion data corresponding to the corresponding user according to the personalized physical fitness analysis map to obtain real-time physical fitness evaluation data; The physical fitness early warning analysis module is used to perform early warning analysis based on the real-time physical fitness evaluation data obtained by the user to determine whether there is physical fitness abnormality in the corresponding athlete.

2. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 1, characterized in that, The process of collecting historical multi-source motion data and real-time multi-source motion data includes: Set up an information entry window, and enter user collection information and historical multi-source motion data through the information entry window; Set up an environment collection unit, an image collection unit, and a physiological collection unit, and respectively obtain the motion environment data, motion image data, and motion physiological data of the corresponding volleyball players during the motion process in the physical fitness monitoring volleyball court according to the corresponding user collection information. The collected data is uniformly referred to as real-time multi-source motion data, and the corresponding real-time multi-source motion data is marked according to the collection time.

3. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 2, characterized in that, The process of decomposing and processing the historical multi-source motion data obtained in the platform in sequence to obtain the corresponding comprehensive link includes: Obtain the motion environment data, motion image data, and motion physiological data corresponding to the historical multi-source motion data in the physical fitness management platform, and respectively set corresponding environment nodes, image nodes, and physiological nodes; The environment node and the physiological node respectively set corresponding environment sub-nodes and physiological sub-nodes according to different data types corresponding to the motion environment data and the motion physiological data. The image node analyzes and processes the motion image data, obtains the standard key features of the corresponding actions and the trajectory feature data during the volleyball motion process, obtains the corresponding action types according to the standard key features, respectively sets corresponding image sub-nodes according to the action types, constructs a mechanical analysis model according to the trajectory feature data, and sets a trajectory sub-node; Mark and process the corresponding types of motion environment data, motion physiological data, and motion image data through the corresponding environment sub-nodes, physiological sub-nodes, image sub-nodes, and trajectory sub-nodes, and set corresponding longitudinal environment number axes, longitudinal physiological number axes, longitudinal action number axes, and longitudinal force number axes; The environmental node, the image node, and the physiological node are respectively connected according to the corresponding longitudinal environmental number axis, longitudinal physiological number axis, longitudinal motion number axis, and longitudinal force application number axis to generate an environmental comprehensive link, an image comprehensive link, and a physiological comprehensive link.

4. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 3, characterized in that, The process of constructing a comprehensive physical fitness analysis atlas includes: Connect the generated environmental comprehensive link, image comprehensive link, and physiological comprehensive link in sequence; Set corresponding fuzzy intervals according to the data types corresponding to the longitudinal number axes in each environmental comprehensive link and image comprehensive link, and traverse and combine the data information obtained in the corresponding longitudinal number axes according to the corresponding fuzzy intervals to generate corresponding independent variable data sets; Obtain corresponding exercise physiological data according to the exercise environment data and exercise image data corresponding in the independent variable data set to generate corresponding dependent variable data sets; Analyze the multi-source exercise data in the obtained independent variable data set X and dependent variable data set Y, preset the evaluation parameters corresponding to the corresponding data types, evaluate the correlation between the independent variable data set and the dependent variable data set according to the corresponding evaluation parameters to obtain physical fitness evaluation data, and compare and analyze the obtained physical fitness evaluation data with the preset evaluation limit values to determine whether the corresponding independent variable data set and dependent variable data set are associated; Adjust and analyze the corresponding evaluation parameters according to the association result until there is an association, and mark the corresponding evaluation parameters as association evaluation parameters; Connect and associate the longitudinal number axes corresponding to the independent variable data set and the dependent variable data set according to the corresponding association evaluation parameters to construct a comprehensive physical fitness analysis atlas.

5. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 4, characterized in that The process of extracting features from the historical multi-source exercise data corresponding to the corresponding volleyball players includes: Obtain the historical multi-source exercise data of the corresponding volleyball players, traverse and match the multi-source exercise data with the longitudinal number axes of the corresponding data types in the comprehensive physical fitness analysis atlas to obtain the characteristic attributes of the longitudinal number axes to which the multi-source exercise data belongs, set the matching results as the characteristic data of the historical multi-source exercise data corresponding to the corresponding volleyball players, and set a characteristic data set.

6. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 5, characterized in that, The process of setting a personalized physical fitness analysis atlas includes: Set a physical fitness monitoring time axis according to the collection time of the historical multi-source exercise data, map the characteristic data set corresponding to the multi-source exercise data to the corresponding position in the physical fitness monitoring time axis according to the corresponding collection time, connect each characteristic data set according to the unit time of the physical fitness monitoring time axis to generate a physical fitness monitoring data storage chain, and integrate the physical fitness monitoring data storage chains corresponding to multiple historical multi-source exercise data to generate a user physical fitness comprehensive data set; Set a segmented processing period according to the corresponding unit time, adjust the association evaluation parameters in the comprehensive physical fitness analysis atlas according to the characteristic data of the corresponding unit time in the user physical fitness comprehensive data set within the corresponding segmented processing period, and obtain corresponding segmented evaluation parameters according to the adjustment results; Arrange the segmented evaluation parameters corresponding in the user physical fitness comprehensive data set according to the segmented processing period order, and adjust and integrate the comprehensive physical fitness analysis atlas according to the order arrangement results to generate a personalized physical fitness analysis atlas.

7. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 6, characterized in that The process of obtaining real-time physical fitness assessment data includes: Obtaining a personalized physical fitness analysis map and mapping the real-time multi-source motion data obtained by volleyball players in the physical fitness monitoring volleyball court to the personalized physical fitness analysis map; Obtaining corresponding predicted exercise physiological data according to the segmented assessment parameters of the personalized physical fitness analysis map, comparing and analyzing the real-time multi-source motion data with the predicted exercise physiological data according to the corresponding data types, and obtaining physical fitness deviation data; Setting up a physical fitness analysis repository according to the corresponding data types, inputting the physical fitness deviation data into the physical fitness analysis repository for real-time assessment, obtaining physiological assessment data of the corresponding data types, and integrating according to the corresponding physiological assessment data to generate real-time physical fitness assessment data.

8. The real-time monitoring and abnormal warning system for the physical fitness data of volleyball players according to claim 7, characterized in that, The process of determining whether a corresponding athlete has physical fitness abnormalities includes: Based on deep learning algorithms, respectively construct physical fitness monitoring models and abnormal warning models for corresponding data types; Obtain real-time physical fitness assessment data, input the physiological assessment data of the corresponding data types in the real-time physical fitness assessment data into the corresponding physical fitness monitoring models respectively, and obtain monitoring feedback results of the corresponding data types; Integrate the monitoring feedback results corresponding to the physiological assessment data of each data type to generate a comprehensive feedback set, input the comprehensive feedback set into the abnormal warning model, perform analysis and processing through the abnormal warning model, output an abnormal analysis result, and determine whether the corresponding volleyball player has physical fitness abnormalities according to the output abnormal analysis result.

Images