Visual sports classroom teaching method

Abstract

The invention relates to the technical field of physical education, and provides a visual physical education class teaching method. The method comprises the following steps: S1, decomposing a target teaching action into different key action elements, establishing an action hierarchical model, and marking feature parameters of each element; s2, constructing a standard action model by using a 3D modeling technology, and generating a teaching video; s3, collecting motion data of the student through wearable multi-sensor equipment, and collecting real-time data; and S4, comparing the action data of the students with the standard action data through the teacher terminal, analyzing the action deviation of the students, and generating a difference analysis result. Through a multi-view standard action demonstration video generated through 3D modeling, students can clearly observe details of target actions from different angles such as the front side, the side surface and the top view. And in combination with the slow action and the feature annotation, students can intuitively understand the essentials of the action, so that the difficulty of oral teaching is reduced, and the learning accuracy is improved.

Description

Technical Field

[0001] The invention relates to the technical field of physical education teaching, and in particular to a visual physical education classroom teaching method. Background Art

[0002] In existing physical education, traditional teaching methods mainly rely on teachers' verbal explanations and simple action demonstrations, and students need to master complex sports skills through repeated imitation and practice. However, this traditional teaching method has many limitations, especially in sports with complex movements and high detail requirements, it is difficult for students to accurately understand and master the movements through a single demonstration and imitation. In addition, the traditional teaching method lacks real-time action data feedback, and it is difficult for teachers to accurately evaluate students' action performance and provide targeted correction suggestions, resulting in poor teaching results.

[0003] Existing visual teaching systems usually focus on single action demonstrations and lack multi-angle and multi-level action decomposition and data feedback support. In addition, current technical solutions still focus on simple qualitative descriptions in action evaluation and fail to make full use of motion data collected by multiple sensors for refined difference analysis and personalized feedback optimization.

[0004] Therefore, the present invention provides a visual physical education classroom teaching method. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a visual physical education classroom teaching method, which solves the problem that there is a lack of multi-angle action display, real-time data feedback and personalized guidance in physical education classroom teaching, which makes it difficult for students to accurately master complex sports movements.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a visual physical education classroom teaching method, comprising the following steps; S1. Decompose the target teaching action into different key action elements, establish an action hierarchical model, and mark the characteristic parameters of each element; S2, use 3D modeling technology to build standard action models and generate teaching videos; S3, collect students' sports data through wearable multi-sensor devices and collect real-time data; S4, comparing the student's movement data with the standard movement data through the teacher terminal, analyzing the student's movement deviation, and generating a difference analysis result; S5. Based on the difference analysis results, provide correction suggestions to students through the device; S6. Record students’ movement improvements, generate visual progress reports, and provide students with self-assessment functions; S7. Based on students’ historical training data, dynamically adjust training tasks and goals to achieve personalized progress management and training optimization.

[0007] Preferably, the action hierarchical model in step S1 includes: Basic layer: basic form and overall coherence of movements; Detail layer: specific details such as joint angle changes, force direction, muscle activity, etc. Strategic level: flexible use of actions and situational adaptation.

[0008] Preferably, the teaching video in step S2 includes standard action demonstrations from multiple perspectives, and the multiple perspectives include a front perspective, a side perspective, and a top perspective.

[0009] Preferably, the multi-sensor device in step S3 includes an accelerometer, a gyroscope, a heart rate sensor and an electromyography sensor to collect students' movement speed, force direction, heart rate and muscle activity data.

[0010] Preferably, the difference analysis result in step S4 is based on the comparison of multi-dimensional parameters, including multi-dimensional evaluation of angle deviation, speed difference, force direction and muscle activity deviation.

[0011] Preferably, in the difference analysis, a machine learning algorithm is used to automatically identify errors and deviations between student movements and standard movements, and to generate a difference heat map.

[0012] Preferably, the correction suggestion in step S5 generates personalized visual feedback and real-time voice guidance through the smart terminal device, and combines with the vibration feedback device to provide tactile feedback signals to help students correct their movements in time.

[0013] Preferably, the progress report in step S6 displays the student's improvement in the form of a radar chart, a line chart and a dynamic comparison chart, and generates a trend analysis report.

[0014] Preferably, the dynamic adjustment of the training tasks in step S7 includes automatically adjusting the complexity and difficulty of the training content according to the student's historical data and current training performance.

[0015] Preferably, in the step S7, the progress management and training optimization generates a personalized training plan for the student through the teacher terminal, and regularly updates it according to changes in the training data to improve the overall performance of the student.

[0016] The present invention provides a visual physical education classroom teaching method, which has the following beneficial effects: 1. The present invention generates multi-view standard action demonstration videos through 3D modeling, so that students can clearly observe the details of the target action from different angles such as front, side and top view. Combined with slow motion and feature annotation, students can intuitively understand the key points of the action, which reduces the difficulty of oral teaching and improves the accuracy of learning.

[0017] 2. The present invention uses a wearable multi-sensor device to collect students' motion data, including speed, force direction, joint angle, heart rate, etc. This real-time monitoring method enables teachers to detect students' movement deviations in a timely manner and provide personalized correction suggestions through terminal devices.

[0018] 3. The present invention uses a difference analysis algorithm to identify specific deviations in students' movements, such as subtle differences in angle, force and speed. The generated difference heat map and visual feedback provide students with intuitive improvement directions, making corrections more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Example: Please refer to the attached Figure 1 , an embodiment of the present invention provides a visual physical education classroom teaching method, comprising the following steps; S1. Decompose the target teaching action into different key action elements, establish an action hierarchical model, and mark the characteristic parameters of each element; Specifically, the target teaching movement is decomposed into multiple key elements, including the overall posture of the basic movement, the force direction of the movement, the angle of movement of the joints, the transfer position of the center of gravity, etc. Each element is labeled according to its importance to the overall movement, and the characteristic parameters are determined. The action hierarchical model consists of a basic layer, a detail layer, and a strategy layer. The basic layer describes the basic form and overall coherence of the movement, such as the gait and stride in running; the detail layer details the angle changes, force direction, and muscle activity of each joint; the strategy layer involves the flexible use of the movement in specific situations. By decomposing the movement into multiple levels, it helps students gradually understand the key points of the movement, and thus gradually establish the correct concept of the movement. This method can provide different teaching content for different levels of movements, helping students to master skills step by step in the process of learning complex movements; S2, use 3D modeling technology to build standard action models and generate teaching videos; Specifically, 3D modeling software is used to accurately model the key elements of the target action and generate a standard three-dimensional dynamic model. The model includes multiple perspectives such as the front, side and top view of the action, which can clearly show the details of the action. Teaching videos are generated based on standard actions of 3D modeling. Feature annotations are added to the video, and slow motion and decomposition demonstration functions are provided. Students can choose different perspectives to watch and observe different details of the action. By learning from multi-perspective videos, students can understand the key points of the action more clearly and intuitively see the changes in the action from different perspectives. The slow-motion playback function allows students to carefully observe the execution of key elements, thereby improving the accuracy of action imitation; S3, collect students' sports data through wearable multi-sensor devices and collect real-time data; Specifically, students wear a variety of sensor devices, such as accelerometers, gyroscopes, heart rate sensors, and electromyography sensors. Accelerometers and gyroscopes are used to collect data such as movement speed and joint angle changes. Heart rate sensors monitor heart rate changes during exercise. Electromyography sensors record muscle activity. Sensor devices collect students' movement data in real time and transmit the data to the teacher's terminal device via a wireless network. Teachers can view students' movement data in real time. Real-time data collection enables teachers to fully understand students' sports performance and conduct all-round monitoring from multiple aspects such as speed, strength, angle, and heart rate. This real-time data collection can promptly detect students' movement deviations and provide a basis for subsequent difference analysis and correction suggestions. S4, comparing the student's movement data with the standard movement data through the teacher terminal, analyzing the student's movement deviation, and generating a difference analysis result; Specifically, the teacher's terminal compares the student's real-time data with the standard action data, and uses the difference calculation algorithm to analyze the deviation of the action, including angle deviation, speed difference, force direction and muscle activity difference. The machine learning algorithm automatically identifies the errors between the student's action and the standard action, and generates the difference analysis results; S5. Based on the difference analysis results, provide correction suggestions to students through the device; Specifically, the improvement of students' movements is recorded and a visual progress report is generated. The progress report shows the improvement of students at different training stages and the changes in key indicators in the form of radar charts, line charts and dynamic comparison charts. Based on the difference analysis results, corrective suggestions are provided to students through smart terminal devices. Corrective suggestions are conveyed in the form of visual, auditory and tactile feedback, such as visual feedback, voice guidance and vibration prompts on tablet terminals; S6. Record students’ movement improvements, generate visual progress reports, and provide students with self-assessment functions; Specifically, the system analyzes students' historical training data, identifies improvement trends and weak areas in training, and dynamically adjusts the difficulty and goals of training tasks. Through time series analysis, it compares students' training performance at different stages, gradually optimizes training content, and provides a self-assessment function. Students can reflect on their progress reports and record their feelings and improvement suggestions during training in the system. The system generates subsequent training plans based on students' self-assessment results; S7. Based on students’ historical training data, dynamically adjust training tasks and goals to achieve personalized progress management and training optimization; Specifically, the system analyzes students' historical training data, identifies improvement trends and weak areas in training, and dynamically adjusts the difficulty and goals of training tasks. Through time series analysis, it compares students' training performance at different stages, gradually optimizes training content, and generates personalized training plans based on students' current performance and historical data. The system adjusts the intensity, rhythm, and content of training based on students' progress to ensure that each student receives adaptive training.

[0022] Embodiment 1; This embodiment discloses a visual physical education classroom teaching method for physical training of teenagers; it improves teenagers' understanding and mastery of complex sports movements through visualization means, and enables teenagers to achieve significant improvements in sports skills and physical fitness through step-by-step teaching, real-time data feedback and personalized training plans.

[0023] S1. Action decomposition and stratification: For physical training for teenagers, such as the sprint start action, the target action is broken down into different key elements. The basic layer focuses on the coordination of the forward leaning posture and leg movements; the detail layer marks the joint angle, force direction and speed change; the strategy layer covers the reaction speed and posture adjustment skills when starting. The characteristic parameters of the action are marked to ensure that teenagers can understand the key points of the action; S2. 3D modeling and teaching video generation: Use 3D modeling technology to generate a standard starting action model, and combine it with high-frame-rate video equipment to produce teaching videos with different perspectives. The videos also mark the key points of the action, such as the force point of the push-off action, the angle of the arm swing, etc. The video combines slow motion and still marking functions, so that young people can clearly observe and imitate each action element; S3, Multi-sensor data collection: Through smart insole sensors, bracelets, heart rate monitoring devices and IMU devices, multi-dimensional data such as teenagers' stride, ground pushing force, arm swing, center of gravity transfer, heart rate, etc. are collected in real time. These data will be automatically recorded and transmitted to the teacher's terminal during each training of the teenagers to form a training file; S4. Difference analysis: The teacher terminal compares the teenagers’ data with the standard data, calculates the angle deviation, force direction and speed difference, and generates a difference heat map to show the areas where the teenagers need to improve. Corrective suggestions are conveyed to the teenagers in the form of visual, voice and vibration prompts through smart bracelets and tablet terminals; S5. Corrective suggestions; The system provides detailed visual feedback through the tablet terminal, combined with the voice assistant to give real-time correction suggestions, while the smart bracelet reminds students through vibration signals; S6. Personalized training plan generation: Based on the difference analysis report and progress record generated by the system, a personalized training plan is generated for teenagers. The plan will adjust the training content, time and intensity according to each student's weaknesses and progress, recommend specific reinforcement exercises and movement improvement goals, and gradually improve the training effect of teenagers; S7, Progress Report and Dynamic Optimization: After the training, the system automatically generates a progress report for each teenager, showing the changing trends of various training indicators through radar charts, line charts and dynamic comparison charts. Teachers can further optimize the training content based on the progress report; Summarize: This embodiment enables young people to clearly understand and gradually improve their sprinting movements through scientific movement decomposition and multi-sensory feedback, and continuously improve their physical fitness and technical level through dynamic personalized training programs.

[0024] Embodiment 2: This embodiment discloses a visual physical education classroom teaching method for rehabilitation training for the elderly; through detailed motion analysis and dynamic feedback, it helps the elderly gradually restore their walking ability, improve their balance and gait stability, and improve their daily quality of life.

[0025] S1. Action decomposition and stratification: For rehabilitation training of the elderly, the actions are decomposed into basic layer, detail layer and strategy layer. The characteristic parameters of each element are marked, such as the knee bending angle, the landing point of the sole of the foot, etc., to help the elderly understand the key points of walking actions; S2. 3D modeling and teaching video generation: Generate a standard gait model through 3D modeling technology and make a teaching video, including front and side demonstrations. The key points of focus shift are specially marked in the video, and combined with visual annotations of action decomposition, making it easier for the elderly to imitate and understand; S3, Multi-sensor data collection: Wearing footstep sensors, waistband IMU and heart rate monitors, real-time gait data such as stride length, step frequency, joint angles, center of gravity movement and heart rate changes are collected. These data are transmitted to the teacher terminal via wireless network for real-time monitoring and analysis; S4. Difference analysis and feedback: The teacher compares the elderly's gait data with the standard data through the terminal and generates a difference analysis report. Based on information such as stride difference and joint angle deviation, the system provides guidance on pace and center of gravity control through the voice assistant, and the bracelet vibrates to remind the elderly to maintain gait balance; S5. Real-time training guidance and safety monitoring: During rehabilitation training, the system monitors the elderly's heart rate, gait and posture in real time to ensure training safety. If excessive fatigue or abnormal heart rate is detected, the system will promptly remind and suspend training; S6. Personalized rehabilitation training plan generation: The system develops a personalized rehabilitation plan for each elderly person based on their training data and analysis reports. The plan will dynamically adjust the walking stride, step frequency, and intensity of balance exercises to gradually improve their gait stability; S7. Progress report and training optimization: Generate progress reports and use radar charts and trend charts to show the improvement of the elderly in terms of stride length, stride frequency, center of gravity stability, etc. Teachers can further optimize the rehabilitation training content based on the report; Summarize: This embodiment enables the elderly to gradually restore their walking ability and gain more confidence in the rehabilitation process through accurate data analysis, dynamic personalized training and safety monitoring.

[0026] Embodiment three; This embodiment discloses a method for teaching athletes' specialized training in a visualized physical education classroom. Through a visualized teaching method, especially through detailed analysis of movements, data collection, and real-time feedback, specialized sports skills are refined and improved, and technical movements are optimized.

[0027] S1. Action decomposition and stratification: The shooting action is decomposed into the basic layer, detail layer and strategy layer. The basic layer focuses on the posture of the hands and feet to ensure the stability of the basic action; the detail layer includes the angle change of the joints, the order of arm force, the adjustment of footsteps, etc.; the strategy layer emphasizes the instantaneous decision-making reaction on the court and the adaptation to different situations; S2. 3D modeling and teaching video generation: Generate a standard shooting action model through 3D modeling, shoot multi-angle video demonstrations, wrist swing, footwork, body center of gravity changes, etc. Combined with the slow motion function, athletes can deeply understand the details of the action and focus on learning through the marked key nodes; S3. Multi-sensor data collection: Athletes wear electromyographic sensors during training to collect real-time muscle activity, joint angles, and force transfer. Electromyographic sensors monitor the strength of athletes to ensure the scientificity and safety of training; S4. Difference analysis and correction suggestions: The system analyzes the collected data to identify deviations in shooting movements, such as uneven force and insufficient angle changes, and generates a difference report. The difference heat map intuitively displays the problem areas, and combined with virtual reality equipment to provide an immersive training experience, athletes can correct their movements in the virtual arena; S5. Personalized training plan generation: Based on the difference report, the system generates a personalized training plan for each athlete, adjusts the training intensity and content, and makes suggestions for strengthening weaknesses, such as wrist swing angle, footwork adjustment, etc., to improve the overall technical level; S6. Progress report generation: The system generates progress reports for athletes, showing the changing trends of shooting movements through radar charts and line charts, helping coaches and athletes understand training results and determine further training goals; S7. Dynamic optimization and continuous feedback: The system continuously optimizes training content based on progress reports and game feedback to match training tasks with athletes’ technical needs, ensuring athletes achieve their best performance on the field.

[0028] Summarize: This embodiment helps professional athletes improve their special skills and achieve better performance in actual competitions through refined data analysis and personalized training plans.

[0029] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A visual physical education classroom teaching method, characterized in that: The steps include: S1. Decompose the target teaching action into different key action elements, establish an action hierarchical model, and mark the characteristic parameters of each element; S2, use 3D modeling technology to build standard action models and generate teaching videos; S3, collect students' sports data through wearable multi-sensor devices and collect real-time data; S4, comparing the student's movement data with the standard movement data through the teacher terminal, analyzing the student's movement deviation, and generating a difference analysis result; S5. Based on the difference analysis results, provide correction suggestions to students through the device; S6. Record students’ movement improvements, generate visual progress reports, and provide students with self-assessment functions; S7. Based on students’ historical training data, dynamically adjust training tasks and goals to achieve personalized progress management and training optimization.

2. A visual physical education classroom teaching method according to claim 1, characterized in that: The action hierarchical model in step S1 includes: Basic layer: basic form and overall coherence of movements; Detail layer: specific details such as joint angle changes, force direction, muscle activity, etc. Strategic level: flexible use of actions and situational adaptation.

3. A visual physical education classroom teaching method according to claim 1, characterized in that: The teaching video in step S2 includes standard action demonstrations from multiple perspectives, and the multiple perspectives include a front perspective, a side perspective, and a top perspective.

4. A visual physical education classroom teaching method according to claim 1, characterized in that: The multi-sensor device in step S3 includes an accelerometer, a gyroscope, a heart rate sensor and an electromyography sensor to collect students' movement speed, force direction, heart rate and muscle activity data.

5. A visual physical education classroom teaching method according to claim 1, characterized in that: The difference analysis results in step S4 are based on the comparison of multi-dimensional parameters, including multi-dimensional evaluation of angle deviation, speed difference, force direction and muscle activity deviation.

6. A visual physical education classroom teaching method according to claim 1, characterized in that: In the difference analysis, a machine learning algorithm is used to automatically identify errors and deviations between student movements and standard movements, and generate a difference heat map.

7. A visual physical education classroom teaching method according to claim 1, characterized in that: The correction suggestion in step S5 generates personalized visual feedback and real-time voice guidance through the smart terminal device, and combines with the vibration feedback device to provide tactile feedback signals to help students correct their movements in time.

8. A visual physical education classroom teaching method according to claim 1, characterized in that: The progress report in step S6 displays the student's improvement in the form of a radar chart, a line chart and a dynamic comparison chart, and generates a trend analysis report.

9. A visual physical education classroom teaching method according to claim 1, characterized in that: The dynamic adjustment of the training tasks in step S7 includes automatically adjusting the complexity and difficulty of the training content according to the student's historical data and current training performance.

10. A visual physical education classroom teaching method according to claim 1, characterized in that: In the step S7, the progress management and training optimization generates a personalized training plan for the student through the teacher terminal, and regularly updates it according to the changes in the training data to improve the overall performance of the student.

Images