Exercise physiological data monitoring method

Abstract

The invention relates to the field of human body physiological data monitoring, in particular to an exercise physiological data monitoring method which comprises a monitoring system, and the monitoring system comprises an acquisition module, a conveying module, a storage display module, a data processing module and a customized training module. The monitoring system comprises an acquisition module, a conveying module, a storage display module, a data processing module and a customized training module which are electrically connected with one another, the acquisition module monitors the heart rate of a monitored person in real time through the sports bracelet, personalized training suggestions are provided for athletes or sports enthusiasts through accurate physiological data monitoring and analysis, and the monitoring effect is good. According to the exercise physiological data processing and analysis method, training plans are optimized, the exercise performance is improved, the exercise injury risk is reduced, the health conditions of individuals are monitored through the exercise physiological data, potential health problems are found in the early stage, scientific exercise and diet plans are made, chronic diseases are prevented, and development of related technologies is promoted through research on the exercise physiological data processing and analysis method.

Description

Technical Field

[0001] The invention relates to the technical field of sports physiological data monitoring, in particular to a sports physiological data monitoring method. Background Art

[0002] In today's society, people are paying more and more attention to health and physical exercise. As a discipline that studies the changes in human physiological functions during exercise, the research results of exercise physiology have important practical significance for improving exercise effects, preventing sports injuries, and promoting health. With the advancement of science and technology, especially the rapid development of wearable devices and biosensor technology, the collection and analysis of exercise physiological data has become increasingly convenient and accurate.

[0003] Current sports physiological data monitoring can only collect data when the athlete is exercising, and cannot adjust the training intensity according to the trainee's real-time sports physiological data during the collection. Moreover, the monitoring data can only be obtained during exercise, which results in the trainee needing to maintain the same intensity for training all the time, and cannot flexibly adjust the training intensity according to the monitoring data at any time, thereby effectively changing the training. Therefore, it is necessary to propose a sports physiological data monitoring method. Summary of the invention

[0004] In view of the problems in the prior art, the present invention provides a method for monitoring sports physiological data.

[0005] The technical solution adopted by the present invention to solve the technical problem is: a method for monitoring sports physiological data, comprising a monitoring system, the monitoring system comprising a collection module, a conveying module, a storage and display module, a data processing module and a customized training module; the monitoring system comprising the collection module, the conveying module, the storage and display module, the data processing module and the customized training module are electrically connected to each other; The acquisition module monitors the monitor's heart rate, blood pressure, blood oxygen and lactic acid generated by exercise in real time through a sports bracelet, which is convenient for subsequent transmission.

[0006] The transmission module transmits the sports physiological data collected by the collection module losslessly via Bluetooth or WIFI, which is convenient for storage and processing.

[0007] The storage and display module receives the data transmitted by the conveying module through the mobile terminal, packages and stores the data as a whole, and can view the data in real time through the mobile terminal.

[0008] The data processing module includes a preprocessing module, a feature extraction module and an analysis module; The data preprocessing module is the first step in the processing and analysis of sports physiological data. Its purpose is to improve the data quality and make the data more suitable for statistical analysis and machine learning. It cleans, filters and denoises the stored data to eliminate interference in the data collection process. The analysis stage evaluates the athlete's physiological state and athletic ability by analyzing physiological parameters such as heart rate, blood pressure, and respiratory rate. The feature extraction module identifies the most useful information from the original data and constructs a new feature set to improve the model performance. The information extracted by the preprocessing module is used as a basis, and then a database is built through the feature extraction module to continuously cooperate with the model training. The selection of the analysis module depends on the research purpose and data type. Cluster analysis, correlation analysis and time series analysis are performed based on the constructed data model and operation set. The analysis of this sports physiological data is carried out in combination with random forests, gradient boosting decision trees and neural networks. The processed data is deeply studied and interpreted to explore the relationship between athletes' physiological parameters and sports performance, providing guidance for sports training and health management.

[0009] The preprocessing module includes a data cleaning module, a data normalization module, a data encoding module and a data segmentation module; The data cleaning module processes missing values, abnormal values ​​and duplicate values ​​in the data; for missing values, a filling strategy can be adopted, such as the mean, median and most frequent value; for abnormal values, they can be identified and processed through methods such as box plots and standard deviations; for duplicate values, they are deleted and data cleaning is performed; The data normalization module converts the data into a uniform scale to facilitate comparison between different features. Standardization usually scales the data to a range with a mean of 0 and a standard deviation of 1; normalization scales the data to a specific interval, such as [0, 1] or [0, 100], so that the data can be quickly located in different intervals for analysis.

[0010] The data encoding module converts the category data into a numerical form that can be processed by the machine learning algorithm. Common encoding methods include label encoding and one-hot encoding. Through the above operation, the collected data is centrally encoded and distinguished, and the encoded data is extracted and used; The data segmentation module divides the data set into a training set and a test set to facilitate the training and verification of the model; the data set is used as the whole of the model training area for continuous training, and the test set is used for testing during debugging to increase the overall efficiency of use.

[0011] The feature extraction module includes a feature selection module and a feature collection module; The feature selection module selects the most useful features for the model from the original features of the data to reduce the complexity of the model and the risk of overfitting; the commonly used feature selection methods include filtering, packaging and embedding; the filtering method is used to filter and screen the repetitions in the data, the packaging method is used to supplement the missing data in the sports physiological data, and the embedding method is used to embed the male and female data sets for operation, and the data set module is used to continuously perform calculations; The feature collection module synthesizes new features from the original data to better express the inherent laws of the data, and can extract the characteristics of physiological changes during exercise through time series analysis.

[0012] After the customized training module collects data through the acquisition module, the overall data is cleaned, split, extracted and classified through the data processing module, so as to facilitate the setting of tailor-made training plans for different types, and modify the training intensity at any time according to the monitored sports physiological data.

[0013] A method for using a sports physiological data monitoring method comprises the following steps: S1: When it is necessary to monitor the athlete's sports physiological data, first wear the sports bracelet on the monitoring personnel, determine the physiological parameters to be monitored, select the appropriate collection equipment, and debug and calibrate the equipment; S2: During exercise, the acquisition module will monitor and record physiological data in real time. The sports bracelet will monitor heart rate, blood pressure, blood oxygen and lactate data in real time. The data needs to be collected immediately during exercise. At this time, the collected data is transmitted to a computer or other device through Bluetooth or WiFi in the transmission module, and stored and managed. Then, the overall collected data is displayed and processed through the storage display module. S3: The collected physiological data are pre-processed by the data processing module, and then feature extraction is performed. Finally, the analysis module performs overall analysis, statistical analysis and interpretation of the collected data are performed, and the real-time changes of sports physiological parameters and physiological reactions after exercise are obtained, providing a basis for sports training and health management; S4: Through the customized training module, the athlete's plan is customized in real time according to the collected and analyzed data, and the data obtained is monitored at any time to change the training intensity to avoid athletes from being injured during training.

[0014] Beneficial effects of the present invention: The method for monitoring sports physiological data described in the present invention provides personalized training suggestions for athletes or sports enthusiasts through precise physiological data monitoring and analysis, optimizes training plans, improves sports performance, reduces the risk of sports injuries, uses sports physiological data to monitor the health status of individuals, discovers potential health problems at an early stage, formulates scientific exercise and diet plans, and prevents the occurrence of chronic diseases. The research on sports physiological data processing and analysis methods promotes the development of related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0016] Figure 1 A schematic diagram of the overall process structure of a method for monitoring sports physiological data provided by the present invention; Figure 2 A schematic diagram of the structure of a preprocessing module in a method for monitoring sports physiological data provided by the present invention; Figure 3 A schematic diagram of the structure of a feature extraction module in a sports physiological data monitoring method provided by the present invention. DETAILED DESCRIPTION

[0017] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0018] like Figure 1-Figure 3 As shown, a method for monitoring sports physiological data of the present invention includes a monitoring system, wherein the monitoring system includes a collection module, a conveying module, a storage and display module, a data processing module and a customized training module; the monitoring system includes the collection module, the conveying module, the storage and display module, the data processing module and the customized training module are electrically connected to each other; The acquisition module monitors the monitor's heart rate, blood pressure, blood oxygen and lactic acid generated by exercise in real time through a sports bracelet, which is convenient for subsequent transmission.

[0019] The transmission module transmits the sports physiological data collected by the collection module losslessly via Bluetooth or WIFI, which is convenient for storage and processing.

[0020] The storage and display module receives the data transmitted by the conveying module through the mobile terminal, packages and stores the data as a whole, and can view the data in real time through the mobile terminal.

[0021] The data processing module includes a preprocessing module, a feature extraction module and an analysis module; The data preprocessing module is the first step in the processing and analysis of sports physiological data, and its purpose is to improve the data quality and make the data more suitable for statistical analysis and machine learning; The stored data is cleaned, filtered and denoised to eliminate interference during data collection. The analysis phase evaluates the athlete's physiological state and athletic ability by analyzing physiological parameters such as heart rate, blood pressure, and respiratory rate. The feature extraction module identifies the most useful information from the original data and constructs a new feature set; To improve the performance of the model, the information extracted by the preprocessing module is used as the basis, and then the database is built through the feature extraction module to continuously cooperate with the model training; The selection of the analysis module depends on the research purpose and data type, and cluster analysis, correlation analysis and time series analysis are performed according to the constructed data model and operation set; The analysis of this sports physiological data is carried out in combination with random forests, gradient boosting decision trees and neural networks. The processed data is deeply studied and interpreted to explore the relationship between athletes' physiological parameters and sports performance, providing guidance for sports training and health management.

[0022] The preprocessing module includes a data cleaning module, a data normalization module, a data encoding module and a data segmentation module; The data cleaning module processes missing values, abnormal values ​​and duplicate values ​​in the data; For missing values, you can use filling strategies, such as mean, median and most frequent value; for outliers, you can identify and process them through box plots, standard deviation and other methods; for duplicate values, delete them and perform data cleaning; The data normalization module converts the data into a uniform scale to facilitate comparison between different features. Normalization usually scales the data to a range with a mean of 0 and a standard deviation of 1. Normalization scales the data to a specific interval, such as [0,1] or [0,100], so that the data can be quickly located in the interval for analysis.

[0023] The data encoding module converts the category data into a numerical form that can be processed by the machine learning algorithm. Common encoding methods include label encoding and one-hot encoding. Through the above operation, the collected data is centrally encoded and distinguished, and the encoded data is extracted and used; The data segmentation module divides the data set into a training set and a test set to facilitate the training and verification of the model; the data set is used as the whole of the model training area for continuous training, and the test set is used for testing during debugging to increase the overall efficiency of use.

[0024] The feature extraction module includes a feature selection module and a feature collection module; The feature selection module selects the most useful features for the model from the original features of the data to reduce the complexity and overfitting risk of the model; Commonly used feature selection methods include filtering, packaging and embedding. The filtering method is used to filter and screen the repetitions in the data, the packaging method is used to supplement the missing data in the sports physiological data, and the embedding method is used to embed the male and female data sets and run them in conjunction with the data set module to continuously perform calculations. The feature collection module synthesizes new features from the original data to better express the inherent laws of the data, and can extract the characteristics of physiological changes during exercise through time series analysis.

[0025] After the customized training module collects data through the acquisition module, the overall data is cleaned, split, extracted and classified through the data processing module, so as to facilitate the setting of tailor-made training plans for different types, and modify the training intensity at any time according to the monitored sports physiological data.

[0026] Specific use: When it is necessary to monitor the physiological data of athletes, first wear the sports bracelet on the monitoring personnel, determine the physiological parameters that need to be monitored, select the appropriate acquisition equipment, and debug and calibrate the equipment; during exercise, the acquisition module will monitor and record physiological data in real time, and monitor heart rate, blood pressure, blood oxygen and lactate data in real time through the sports bracelet, which needs to be collected immediately during exercise; at this time, the collected data is transmitted to the computer or other devices through the Bluetooth or WiFi in the transmission module, and stored and managed, and then the storage and display module is used to display and process the collected overall data; the data processing module pre-processes the collected physiological data separately, then extracts features, and finally analyzes the whole data through the analysis module, performs statistical analysis and interpretation on the collected data, and obtains the real-time changes of sports physiological parameters and physiological reactions after exercise, which provides a basis for sports training and health management; through the customized training module, the athlete's plan is customized in real time according to the collected and analyzed data, and the obtained data is monitored at any time to change the training intensity to avoid damage to the athlete's training.

[0027] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for using a method for monitoring sports physiological data, characterized in that: The following steps are involved: Step 1: When it is necessary to monitor the athlete's sports physiological data, first wear the sports bracelet on the monitoring personnel, determine the physiological parameters that need to be monitored, select the appropriate collection equipment, and debug and calibrate the equipment; Step 2: During exercise, the acquisition module will monitor and record physiological data in real time. The sports bracelet will monitor heart rate, blood pressure, blood oxygen and lactate data in real time. The data needs to be collected immediately during exercise. At this time, the collected data is transmitted to a computer or other device through Bluetooth or WiFi in the transmission module, and stored and managed. Then, the overall collected data is displayed and processed through the storage display module. Step 3: The collected physiological data are pre-processed by the data processing module, and then feature extraction is performed. Finally, the analysis module is used to analyze the collected data as a whole, and statistical analysis and interpretation are performed on the collected data to obtain the real-time changes of sports physiological parameters and physiological reactions after exercise, providing a basis for sports training and health management; Step 4: Customize the training plan for athletes in real time based on the collected and analyzed data through the customized training module, monitor the data at any time to change the training intensity and avoid damage to the athlete during training.

2. A method for monitoring sports physiological data, characterized in that: The monitoring system comprises a collection module, a conveying module, a storage and display module, a data processing module and a customized training module; the monitoring system comprises a collection module, a conveying module, a storage and display module, a data processing module and a customized training module which are electrically connected to each other; The acquisition module monitors the monitor's heart rate, blood pressure, blood oxygen and lactic acid generated by exercise in real time through a sports bracelet, which is convenient for subsequent transmission.

3. A method for monitoring sports physiological data according to claim 2, characterized in that: The transmission module transmits the sports physiological data collected by the collection module losslessly via Bluetooth or WIFI, which is convenient for storage and processing.

4. The method for monitoring sports physiological data according to claim 2, characterized in that: The storage and display module receives the data transmitted by the conveying module through the mobile terminal, packages and stores the data as a whole, and can view the data in real time through the mobile terminal.

5. The method for monitoring sports physiological data according to claim 2, characterized in that: The data processing module includes a preprocessing module, a feature extraction module and an analysis module; The data preprocessing module is the first step in the processing and analysis of sports physiological data. Its purpose is to improve the data quality and make the data more suitable for statistical analysis and machine learning. It cleans, filters and denoises the stored data to eliminate interference in the data collection process. The analysis stage evaluates the athlete's physiological state and athletic ability by analyzing physiological parameters such as heart rate, blood pressure, and respiratory rate. The feature extraction module identifies the most useful information from the original data and constructs a new feature set to improve the model performance. The information extracted by the preprocessing module is used as a basis, and then a database is built through the feature extraction module to continuously cooperate with the model training. The selection of the analysis module depends on the research purpose and data type. Cluster analysis, correlation analysis and time series analysis are performed based on the constructed data model and operation set. The analysis of this sports physiological data is carried out in combination with random forests, gradient boosting decision trees and neural networks. The processed data is deeply studied and interpreted to explore the relationship between athletes' physiological parameters and sports performance, providing guidance for sports training and health management.

6. A method for monitoring sports physiological data according to claim 5, characterized in that: The preprocessing module includes a data cleaning module, a data normalization module, a data encoding module and a data segmentation module; The data cleaning module processes missing values, abnormal values ​​and duplicate values ​​in the data; for missing values, a filling strategy can be adopted, such as the mean, median and most frequent value; for abnormal values, they can be identified and processed through methods such as box plots and standard deviations; for duplicate values, they are deleted and data cleaning is performed; The data normalization module converts the data into a unified scale to facilitate comparison between different features. Standardization usually scales the data to a range with a mean of 0 and a standard deviation of 1; normalization scales the data to a specific interval, such as [0, 1] or [0, 100], so as to quickly locate the data through the interval for analysis; The data encoding module converts the category data into a numerical form that can be processed by the machine learning algorithm. Common encoding methods include label encoding and one-hot encoding. Through the above operation, the collected data is centrally encoded and distinguished, and the encoded data is extracted and used; The data segmentation module divides the data set into a training set and a test set to facilitate the training and verification of the model; The data set is used as the whole of the model training area for continuous training, and the test set is used for testing during debugging to increase the overall efficiency of use.

7. The method for monitoring sports physiological data according to claim 5, characterized in that: The feature extraction module includes a feature selection module and a feature collection module; The feature selection module selects the most useful features for the model from the original features of the data to reduce the complexity of the model and the risk of overfitting; the commonly used feature selection methods include filtering, packaging and embedding; the filtering method is used to filter and screen the repetitions in the data, the packaging method is used to supplement the missing data in the sports physiological data, and the embedding method is used to embed the male and female data sets for operation, and the data set module is used to continuously perform calculations; The feature collection module synthesizes new features from the original data to better express the inherent laws of the data, and can extract the characteristics of physiological changes during exercise through time series analysis.

8. The method for monitoring sports physiological data according to claim 2, characterized in that: After the customized training module collects data through the acquisition module, the overall data is cleaned, split, extracted and classified through the data processing module, so as to facilitate the setting of tailor-made training plans for different types, and modify the training intensity at any time according to the monitored sports physiological data.

Images