Interactive physical training evaluation method and system

Abstract

The invention relates to the technical field of physical training, and discloses an interactive physical training evaluation method which comprises the following steps: acquiring exercise data of a trainee in real time by using wearable equipment; the collected data is preprocessed; a machine learning algorithm is used for deeply analyzing the preprocessed data, the physical ability level, the exercise performance and the training effect of the trainee are evaluated, and personalized training suggestions and improvement schemes are generated in combination with the personal target and the physical condition of the trainee; according to a data analysis result, training feedback is provided for the trainee in real time through the intelligent equipment; the exercise data of the trainee is deeply analyzed through a machine learning algorithm, a highly personalized training suggestion and an improved scheme can be generated in combination with personal targets and physical conditions, meanwhile, a personalized training plan is automatically generated based on an optimization algorithm, the trainee is allowed to perform custom adjustment, and the training effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sports training, and particularly to an interactive sports training evaluation method and system. Background Art

[0002] In the traditional sports training evaluation system, coaches or experts usually rely on manual observation and recording to evaluate the training effect and physical condition of athletes. Although this method can reflect the training situation of athletes to a certain extent, it is limited by the subjective judgment and experience level of observers, and there are often problems of strong subjectivity and inaccurate data. In addition, the manual recording method is not only inefficient, but also difficult to give athletes effective feedback in a timely manner, thus affecting the improvement of training effect. With the rapid development of information technology and the popularization of intelligent devices, more and more advanced technologies have been introduced into the field of sports training, aiming to improve the efficiency and effect of training. For example, through high-precision sensors and intelligent devices, key sports data such as the heart rate, speed, and strength of athletes can be collected in real time, providing a more objective and accurate basis for training evaluation. However, there are still many deficiencies in the application of existing intelligent sports training systems. On the one hand, most of these systems stay at the data collection stage and lack in-depth analysis and mining of data. Just collecting data without effective analysis and utilization is tantamount to wasting data resources. On the other hand, the formulation of personalized training plans is also a major shortcoming of existing systems. The physical conditions, training goals, and exercise habits of different athletes are different. Therefore, formulating personalized training plans is crucial for improving training effect. However, existing intelligent sports training systems are still insufficient in formulating personalized training plans and are difficult to meet the diverse needs of athletes. Summary of the Invention

[0003] The present invention proposes an interactive sports training evaluation method and system to solve the problem that existing systems cannot formulate personalized training plans.

[0004] To achieve the above object, the present invention provides the following technical solution: An interactive sports training evaluation method, comprising the following steps:

[0005] S1: Using wearable devices to collect the exercise data of the trainer in real time;

[0006] S2: Preprocessing the collected data;

[0007] S3: Using machine learning algorithms to deeply analyze the preprocessed data, evaluate the physical fitness level, sports performance and training effect of the trainer, and generate personalized training suggestions and improvement plans in combination with the personal goals and physical conditions of the trainer;

[0008] S4: Based on the data analysis results, provide training feedback to the trainer in real time through intelligent devices, and the feedback forms include but are not limited to vision, audition or touch;

[0009] S5: Based on the trainer's personal goals, physical condition and historical training data, automatically generate a personalized training plan using an optimization algorithm, and allow the trainer to make custom adjustments according to the actual situation;

[0010] S6: Provide a social interaction platform, allow the trainer to share training achievements, challenge records and training experiences, and recommend relevant training content, friend dynamics and community activities through intelligent recommendation algorithms;

[0011] Preferably, the motion data includes heart rate, speed, strength, and position information.

[0012] Preferably, the S2 includes the steps of:

[0013] S21: Identify and remove outliers or noise;

[0014] S22: Calibrate the collected data according to the calibration parameters of the sensor;

[0015] S23: Convert the original data into a format suitable for subsequent analysis.

[0016] Preferably, the S3 includes the steps of:

[0017] S31: Extract key features from the preprocessed data that can reflect the trainer's physical fitness level, sports performance and training effect;

[0018] S32: Use historical training data and expert evaluation results to train a machine learning model to evaluate the trainer's physical fitness level and predict the training effect;

[0019] S33: Based on the trainer's personal goals and physical condition, and combined with the evaluation results of the machine learning model, generate personalized training suggestions and improvement plans.

[0020] Preferably, the S4 specifically includes the steps of:

[0021] S41: Provide real-time feedback to the trainer in the form of vision, audition or touch through wearable devices;

[0022] S42: The feedback content includes training status, training effect evaluation, and improvement suggestions.

[0023] Preferably, in the S33, the personal goals include improving endurance and enhancing strength, and the physical condition includes age, gender, and health status.

[0024] Preferably, in S42, the training status includes the current heart rate and current speed, the training effect evaluation includes whether the current training has achieved the expected goal, and the improvement suggestions include adjusting the exercise intensity and rhythm.

[0025] Preferably, in S5, the optimization algorithms include genetic algorithms and particle swarm optimization algorithms.

[0026] An interactive sports training evaluation system, comprising:

[0027] A data acquisition module, configured to collect the motion data of the trainer in real time;

[0028] A data processing and analysis module, configured to preprocess and analyze the collected data, and evaluate the exercise performance and training effect of the trainer;

[0029] A real-time feedback module, configured to provide training feedback to the trainer in real time according to the analysis results;

[0030] A training plan formulation module: configured to automatically generate a personalized training plan according to the personal goals and physical conditions of the trainer;

[0031] A social interaction and sharing module: providing a social interaction platform, allowing the trainer to share training results and experiences.

[0032] Preferably, the data acquisition module includes a smart watch, a smart bracelet, and smart earphones.

[0033] In the above technical solution, the technical effects and advantages provided by the present invention:

[0034] By deeply analyzing the motion data of the trainer through machine learning algorithms, combined with personal goals and physical conditions, highly personalized training suggestions and improvement plans can be generated. At the same time, a personalized training plan is automatically generated based on optimization algorithms, and the trainer is allowed to make custom adjustments, so as to better meet the diverse needs of the trainer, improve the training effect, and provide training feedback to the trainer in real time through smart devices, which not only improves the interactivity of the training process, but also enables the trainer to timely understand their training status, effect evaluation, and improvement suggestions. This kind of instant feedback helps the trainer adjust the training strategy and maintain the training motivation. The provided social interaction platform not only enhances the interaction and communication among trainers, but also can recommend relevant training content, friend dynamics, and community activities to the trainer through intelligent recommendation algorithms. This kind of social interaction helps to stimulate the interest of the trainer. Description of the Drawings

[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0036] Figure 1 This is the flowchart of the present invention. Specific embodiments

[0037] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0038] As Figure 1 shown, the present invention provides the following embodiments: Specific embodiment one:

[0040] Data collection:

[0041] S11: The trainer wears a smart watch, a smart bracelet and smart headphones for training.

[0042] S12: The smart watch monitors data such as heart rate and speed, the smart bracelet records strength data, and the smart headphones capture position information through built-in sensors (such as by connecting to the GPS function of the mobile phone).

[0043] Data preprocessing:

[0044] S21: The system identifies and removes outliers caused by equipment failures or environmental factors.

[0045] S22: According to the calibration parameters of each sensor, the data is accurately calibrated to ensure the accuracy of the data.

[0046] S23: Convert the original data into a unified format for subsequent analysis.

[0047] Data analysis and evaluation:

[0048] S31: Extract key features from the preprocessed data, such as heart rate intervals, speed changes, strength peaks, etc.

[0049] S32: Use historical training data and expert evaluation results to train a machine learning model to classify and evaluate the physical fitness level of the trainer and predict future training effects.

[0050] S33: Based on the personal goals of the trainee (such as improving endurance to a certain level) and physical conditions (such as age, gender, health status), combined with the evaluation results of the machine learning model, generate personalized training suggestions and improvement plans.

[0051] Real-time feedback:

[0052] S41: Display current heart rate, speed and other information through the screen of the smart watch, the smart bracelet vibrates to remind the power output situation, and the smart earphone broadcasts the training status and effect evaluation through voice.

[0053] S42: The feedback content includes whether the current heart rate is in the optimal training range, whether the speed meets the standard, whether the power output is sufficient, and improvement suggestions such as whether it is necessary to adjust the exercise intensity or rhythm.

[0054] Training plan formulation:

[0055] S51: The system optimizes the training plan according to the personal goals, physical conditions and historical training data of the trainee by using the genetic algorithm to ensure that the plan is both scientific and efficient.

[0056] S52: The trainee can view and customize the training plan on the smart device, such as increasing or decreasing the number of training days, adjusting the training intensity, etc.

[0057] Social interaction and sharing:

[0058] S61: The trainee shares training achievements, challenge records and experiences through the built-in social interaction platform of the system.

[0059] S62: The system uses intelligent recommendation algorithms to recommend relevant friend dynamics, community activities and training tutorials according to the trainee's preferences and training content. Specific implementation method two:

[0061] Data collection:

[0062] S11: Before the training starts, the trainee ensures that all wearable devices are correctly worn and connected to the mobile phone or cloud server.

[0063] S12: During the training process, the device collects heart rate, speed, strength and position information in real time and automatically uploads it to the cloud for storage and analysis.

[0064] Data preprocessing:

[0065] S21: The system automatically detects and filters out abnormal data caused by device mis-touch or signal interference.

[0066] S22: According to the calibration information provided by the device, accurately calibrate the original data to ensure the accuracy of the data.

[0067] S23: The data is converted into a format suitable for processing by machine learning algorithms, such as time series data or feature vectors.

[0068] Data analysis and evaluation:

[0069] S31: The system uses deep learning algorithms to deeply analyze the preprocessed data and extract key features.

[0070] S32: The physical fitness level of the trainer is dynamically evaluated by comparing historical training data and expert evaluation results.

[0071] S33: According to the trainer's personal goals and physical conditions, personalized training suggestions and improvement plans are generated, including specific training actions, intensities, and durations, etc.

[0072] Real-time feedback:

[0073] S41: The wearable device provides real-time feedback to the trainer through various means such as vision (e.g., screen display), audition (e.g., voice broadcast), and touch (e.g., vibration reminder).

[0074] S42: The feedback content includes the current training status, effect evaluation, and personalized improvement suggestions based on machine learning.

[0075] Training plan formulation:

[0076] S51: The system uses the particle swarm optimization algorithm to automatically generate a personalized training plan according to the trainer's personal goals, physical conditions, and historical training data.

[0077] S52: The trainer can view the training plan on the intelligent device and make fine-tuning according to their actual situation, such as increasing rest time or reducing training intensity, etc.

[0078] Social interaction and sharing:

[0079] S61: The trainer shares training results and experiences with other users through the built-in social interaction platform of the system.

[0080] S62: The system recommends relevant training content, friend dynamics, and community activities according to the trainer's preferences and interests to promote interaction and communication among trainers. Specific implementation method three:

[0082] Data collection:

[0083] S11: The trainer wears a smart watch, a smart bracelet, and smart earphones for training, and the devices collect heart rate, speed, strength, and position information in real time.

[0084] S12: The data is transmitted to the cloud server via wireless means such as Bluetooth or Wi-Fi for storage and analysis.

[0085] Data preprocessing:

[0086] S21: The system conducts preliminary cleaning on the collected data to remove invalid or abnormal values.

[0087] S22: Calibrate the original data according to the calibration parameters of the sensor to ensure the accuracy of the data.

[0088] S23: Convert the data into a format suitable for subsequent analysis and evaluation.

[0089] Data analysis and evaluation:

[0090] S31: The system uses machine learning algorithms to conduct in-depth analysis on the preprocessed data, extract key features and evaluate the physical fitness level of the trainer.

[0091] S32: Predict and evaluate the training effect of the trainer by comparing historical training data and expert evaluation results.

[0092] S33: Generate personalized training suggestions and improvement plans according to the personal goals and physical conditions of the trainer, including the selection of training actions, the adjustment of training intensity, and the arrangement of training time, etc.

[0093] Real-time feedback:

[0094] S41: The wearable device provides real-time feedback to the trainer through various means such as vision (such as screen display), audition (such as voice broadcast), and touch (such as vibration reminder).

[0095] S42: The feedback content includes the current training status (such as heart rate, speed, etc.), the evaluation of training effect (such as whether the expected goal is achieved), and improvement suggestions (such as adjusting the exercise intensity or rhythm).

[0096] Training plan formulation:

[0097] S51: The system automatically generates a personalized training plan according to the personal goals, physical conditions and historical training data of the trainer by using optimization algorithms (such as genetic algorithm or particle swarm optimization algorithm).

[0098] S52: The trainer can view and customize the training plan on the intelligent device to meet their actual needs and preferences.

[0099] Social interaction and sharing:

[0100] S61: The trainer shares training achievements, challenge records and experiences with other users through the built-in social interaction platform of the system.

[0101] S62: The system uses intelligent recommendation algorithms to recommend relevant training content, friend dynamics, and community activities based on the preferences and interests of the trainers, promoting interaction and communication among the trainers. At the same time, the system can also provide online competition and challenge opportunities for the trainers, increasing the fun and challenge of training. Specific Embodiment 4:

[0103] An interactive sports training evaluation method includes the following steps:

[0104] S1: Use wearable devices to collect the motion data of the trainers in real time;

[0105] S2: Preprocess the collected data;

[0106] S3: Use machine learning algorithms to deeply analyze the preprocessed data, evaluate the physical fitness level, sports performance, and training effect of the trainers, and generate personalized training suggestions and improvement plans in combination with the personal goals and physical conditions of the trainers;

[0107] S4: According to the data analysis results, provide training feedback to the trainers in real time through intelligent devices, and the feedback forms include but are not limited to vision, audition, or touch;

[0108] S5: Based on the personal goals, physical conditions, and historical training data of the trainers, use optimization algorithms to automatically generate personalized training plans, and allow the trainers to make custom adjustments according to the actual situation;

[0109] S6: Provide a social interaction platform, allowing the trainers to share training achievements, challenge records, and training experiences, and recommend relevant training content, friend dynamics, and community activities through intelligent recommendation algorithms;

[0110] Preferably, the motion data includes heart rate, speed, strength, and position information.

[0111] Preferably, the S2 includes the steps of:

[0112] S21: Identify and remove outliers or noise;

[0113] S22: Calibrate the collected data according to the calibration parameters of the sensors;

[0114] S23: Convert the original data into a format suitable for subsequent analysis.

[0115] Preferably, the S3 includes the steps of:

[0116] S31: Extract key features from the preprocessed data that can reflect the physical fitness level, sports performance, and training effect of the trainers;

[0117] S32: Use historical training data and expert evaluation results to train a machine learning model to evaluate the physical fitness level of the trainer and predict the training effect;

[0118] S33: Based on the personal goals and physical conditions of the trainer, and combined with the evaluation results of the machine learning model, generate personalized training suggestions and improvement plans.

[0119] Preferably, the S4 specifically includes the steps of:

[0120] S41: Provide real-time feedback to the trainer in the form of vision, audition, or touch through wearable devices;

[0121] S42: The feedback content includes training status, training effect evaluation, and improvement suggestions.

[0122] Preferably, in the S33, the personal goals include improving endurance and enhancing strength, and the physical conditions include age, gender, and health status.

[0123] Preferably, in the S42, the training status includes the current heart rate and the current speed, the training effect evaluation includes whether the current training reaches the expected goal, and the improvement suggestions include adjusting the exercise intensity and rhythm.

[0124] Preferably, in the S5, the optimization algorithms include genetic algorithms and particle swarm optimization algorithms.

[0125] An interactive sports training evaluation system, comprising:

[0126] A data acquisition module, configured to collect the motion data of the trainer in real time;

[0127] A data processing and analysis module, configured to preprocess and analyze the collected data, and evaluate the motion performance and training effect of the trainer;

[0128] A real-time feedback module, configured to provide training feedback to the trainer in real time according to the analysis results;

[0129] A training plan formulation module: configured to automatically generate a personalized training plan according to the personal goals and physical conditions of the trainer;

[0130] A social interaction and sharing module: providing a social interaction platform, and allowing the trainer to share training results and experiences.

[0131] Preferably, the data acquisition module includes a smart watch, a smart bracelet, and smart earphones.

[0132] Through the above various specific implementation manners, we can provide a more comprehensive, personalized, safe, and interesting interactive sports training evaluation method for trainers, helping them better achieve their training goals.

[0133] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An interactive sports training evaluation method, characterized in that: It includes the following steps: S1: Use wearable devices to collect the trainer's motion data in real time; S2: Preprocess the collected data; S3: Apply machine learning algorithms to deeply analyze the preprocessed data, evaluate the trainer's physical fitness level, sports performance and training effect, and generate personalized training suggestions and improvement plans in combination with the trainer's personal goals and physical conditions; S4: According to the data analysis results, provide training feedback to the trainer in real time through intelligent devices, and the feedback forms include but are not limited to vision, audition or touch; S5: Based on the trainer's personal goals, physical conditions and historical training data, use optimization algorithms to automatically generate personalized training plans, and allow the trainer to make custom adjustments according to the actual situation; S6: Provide a social interaction platform, allowing trainers to share training results, challenge records and training experiences, and recommend relevant training content, friend dynamics and community activities through intelligent recommendation algorithms.

2. The interactive sports training evaluation method according to claim 1, characterized in that: The motion data includes heart rate, speed, strength, and position information.

3. An interactive sports training and evaluation method according to claim 1, characterized in that: The S2 includes the steps: S21: Identify and remove outliers or noise; S22: Calibrate the collected data according to the calibration parameters of the sensor; S23: Convert the original data into a format suitable for subsequent analysis.

4. An interactive sports training and evaluation method according to claim 1, characterized in that: The S3 includes the steps: S31: Extract key features from the preprocessed data that can reflect the trainer's physical fitness level, sports performance and training effect; S32: Use historical training data and expert evaluation results to train a machine learning model to evaluate the trainer's physical fitness level and predict the training effect; S33: Based on the trainer's personal goals and physical conditions, and combined with the evaluation results of the machine learning model, generate personalized training suggestions and improvement plans.

5. The interactive sports training evaluation method according to claim 1, characterized in that: The S4 specifically includes the steps: S41: Provide real-time feedback to the trainer in the form of vision, audition or touch through wearable devices; S42: The feedback content includes training status, training effect evaluation, and improvement suggestions.

6. The interactive sports training and evaluation method according to claim 4, characterized in that: In the S33, the personal goals include improving endurance and enhancing strength, and the physical conditions include age, gender, and health status.

7. An interactive sports training evaluation method according to claim 5, characterized in that: In the S42, the training status includes the current heart rate and current speed, the training effect evaluation includes whether the current training reaches the expected goal, and the improvement suggestions include adjusting the exercise intensity and rhythm.

8. An interactive sports training evaluation method according to claim 1, characterized in that: In the S5, the optimization algorithms include genetic algorithms and particle swarm optimization algorithms.

9. An interactive sports training evaluation system, characterized in that, It includes: A data collection module for collecting the trainer's motion data in real time; A data processing and analysis module for preprocessing and analyzing the collected data and evaluating the trainer's sports performance and training effect; A real-time feedback module for providing training feedback to the trainer in real time according to the analysis results; A training plan formulation module: for automatically generating a personalized training plan according to the trainer's personal goals and physical conditions; A social interaction and sharing module: providing a social interaction platform for allowing trainers to share training results and experiences.

10. An interactive sports training and evaluation system according to claim 9, characterized in that: The data collection module includes smart watches, smart bracelets, and smart earphones.

Images