Auxiliary teaching method, device and electronic equipment based on digital avatar

Abstract

The present application provides an auxiliary teaching method, device and electronic equipment based on digital avatars, which relate to the field of data processing. In this method, the target training type of the learner is obtained; according to the target training type, the digital avatar corresponding to the learner and the preset training data corresponding to the digital avatar are matched; the real-time training data of the learner during training in the training field is obtained; the real-time training data is compared with the preset training data to obtain the difference results; the difference results are marked on the digital avatar to obtain the digital avatar to be displayed; the digital avatar to be displayed is displayed to the teacher through AR glasses, and the teacher wears AR glasses. The implementation of the technical solution provided by the present application facilitates the teacher's teaching of the learner.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to an auxiliary teaching method, device and electronic equipment based on a digital avatar. Background Art

[0002] In today's society, with the continuous improvement of people's health awareness and living standards, sports have become an indispensable part of people's pursuit of a healthy life. From children to adults, from amateurs to professional athletes, the group participating in sports is growing, and sports teaching has also ushered in unprecedented development opportunities.

[0003] At present, the traditional teaching observation method mostly relies on the teacher's naked eye observation and experience judgment. This method is not only inefficient, but also easily affected by subjective factors, resulting in inaccurate and biased observation results. Therefore, the above method is not conducive to the teacher's teaching of the students.

[0004] Therefore, there is an urgent need for an auxiliary teaching method, device and electronic equipment based on digital avatar. Summary of the invention

[0005] The present application provides an auxiliary teaching method, device and electronic equipment based on a digital avatar, which facilitates the teaching of the teacher to the students.

[0006] In a first aspect of the present application, an auxiliary teaching method based on a digital avatar is provided, the method comprising: obtaining a target training type of a learner; matching a digital avatar corresponding to the learner and preset training data corresponding to the digital avatar according to the target training type; obtaining real-time training data of the learner during training in a training field; comparing the real-time training data with the preset training data to obtain a difference result; marking the difference result to the digital avatar to obtain a digital avatar to be displayed; and displaying the digital avatar to be displayed to a teacher through AR glasses, wherein the teacher wears the AR glasses.

[0007] By adopting the above technical solution, by comparing the real-time training data with the preset training data, the teacher can immediately obtain feedback on the training situation of the taught person, without waiting for the end of the training to review or evaluate. This instant feedback helps the teacher to adjust the teaching strategy in time and ensure the efficient teaching. The digital and automated comparison process reduces the subjectivity of human judgment, making the teaching evaluation more objective and accurate. The teacher can guide the taught person based on the specific data differences, avoiding misjudgment caused by personal bias or lack of experience. By displaying the digital avatar with the difference results marked by AR glasses, the teacher can intuitively see the specific problems and improvement points of the taught person in the training. This intuitive display method helps the taught person better understand the teaching intention and improve the enthusiasm and participation in learning. According to the target training type of different taught persons, the corresponding digital avatar and preset training data are matched to realize personalized teaching. The teacher can formulate a more targeted training plan according to the specific situation of the taught person to improve the teaching effect. Therefore, it is convenient for the teacher to teach the taught person.

[0008] Optionally, matching the digital avatar corresponding to the learner and the preset training data corresponding to the digital avatar according to the target training type specifically includes: searching for the learner in a preset database, the preset database pre-stores preset learners and preset digital avatars, one preset learner corresponds to one preset digital avatar, and the preset digital avatar is pre-constructed; if it is determined that the learner exists among multiple preset learners, obtaining the preset digital avatar corresponding to the preset learner, and using the preset digital avatar as the digital avatar corresponding to the learner; determining the preset training data corresponding to the digital avatar according to the target training type, the target training type includes track and field event types and ball game event types, and the preset training data includes movement posture data, speed output data, strength output data and training performance data.

[0009] By adopting the above technical solution, the system can accurately match a personalized digital avatar for each student through the correspondence between the preset taught person and the preset digital avatar stored in the preset database. This personalized matching ensures the pertinence and effectiveness of the subsequent teaching process. According to the target training type of the student, the system can further determine the preset training data corresponding to the digital avatar. These preset training data include movement posture, speed output, power output, training results and other aspects, providing customized training references and standards for the students. The process of searching and matching the student and his digital avatar in the preset database is automated, which greatly improves the matching efficiency. The teacher does not need to manually create or adjust the digital avatar, saving valuable time and energy. Once the match is successful, the system can provide rich preset training data for the teacher to use. These data have been preprocessed and sorted, and the teacher no longer needs to collect and analyze the data by himself, thereby improving the convenience of teaching. The entire matching process and data preparation are based on the objective data in the preset database, reducing the interference of human factors and the influence of subjective judgment. This data-driven approach makes the teaching process more scientific and accurate. By comparing the real-time training data of the students with the preset training data, the system can provide accurate feedback results. These feedback results not only help the instructor understand the training status of the students, but also provide the students with specific improvement suggestions and directions.

[0010] Optionally, the acquiring of real-time training data of the person being taught during training at the training ground specifically includes: receiving original training data sent by a wearable device and a field sensor device, the person being taught wearing the wearable device, and the training ground being installed with the field sensor device; preprocessing the original training data to obtain the real-time training data, the preprocessing including denoising, filtering, feature classification and normalization.

[0011] By adopting the above technical solution, the system can obtain all-round information of the students during the training process by receiving the original training data sent by the wearable device and the field sensor device. The wearable device provides the students' physiological indicators and motion status data, while the field sensor device provides real-time feedback of the training environment. This multi-source data acquisition method ensures the comprehensiveness and accuracy of the data. The original training data often contains noise, redundant information or inconsistent formats. By performing pre-processing steps such as denoising, filtering, feature classification and normalization on these data, the system can effectively improve the data quality, reduce errors and interference, and lay a solid foundation for subsequent data analysis and comparison. Since the system can receive and process the students' training data in real time, the teacher can immediately obtain the students' training status and performance feedback. This real-time nature not only helps the teacher to adjust the teaching strategies and methods in time, but also stimulates the enthusiasm and participation of the students and improves the training effect. By continuously receiving and processing real-time training data, the system can dynamically monitor and evaluate the students' training process. This dynamic nature enables the teacher to have a more comprehensive understanding of the students' training progress and changing trends, so as to formulate a more scientific and reasonable training plan.

[0012] Optionally, comparing the real-time training data with the preset training data to obtain a difference result specifically includes: obtaining a real-time motion trajectory according to the real-time training data within a preset time period, and the preset time period is set based on the complete training action corresponding to the real-time training data; obtaining a preset motion trajectory according to the preset training data within the preset time period; comparing the trajectory difference between the real-time motion trajectory and the preset motion trajectory within the preset time period, and the trajectory difference includes a speed difference and a strength difference; if it is determined that the trajectory difference is greater than a preset threshold, determining the difference area in the complete training action according to the skeleton point positioning algorithm to obtain the difference result, and the difference result includes the difference area.

[0013] By adopting the above technical solution, the accuracy of the comparison process is ensured by setting a preset time period to match the complete training movements in the real-time training data and the preset training data. This method of refining the time range can reduce the errors introduced by time asynchrony or incomplete movements. Not only the speed difference is compared, but also the strength difference is considered, which makes the evaluation of the difference results more comprehensive and multi-dimensional. Speed ​​and strength are key indicators of sports performance. By comparing the trajectory differences of these two dimensions at the same time, the deficiencies and deviations of the learners in training can be more accurately reflected. After determining that the trajectory difference is greater than the preset threshold, the difference area in the complete training movement is further determined by the skeleton point positioning algorithm. This precise positioning method helps teachers quickly find the specific movement links that the learners need to improve, thereby providing more targeted guidance and suggestions. The instant comparison of real-time training data with preset training data enables teachers to obtain training feedback from the learners immediately. This immediacy not only improves teaching efficiency, but also stimulates the enthusiasm and participation of the learners, because they can immediately see their performance and room for improvement in training. The entire comparison process, including the generation of trajectories, the calculation of differences, and the determination of difference areas, can be completed automatically, reducing the need for human intervention and manual operation. This not only improves processing efficiency, but also reduces the possibility of human error.

[0014] Optionally, marking the difference results onto the digital twin to obtain the digital twin to be displayed specifically includes: obtaining a central positioning point and multiple edge positioning points corresponding to the difference area according to the difference area; determining a limb part to be marked according to the central positioning point; determining the affected range of the limb part to be marked according to the multiple edge positioning points and in combination with the physiological movement laws of the human body; marking the digital twin according to the limb part to be marked and the affected range to obtain the digital twin to be displayed.

[0015] By adopting the above technical solution, by determining the central positioning point and multiple edge positioning points of the difference area, the system can accurately identify the deficiencies and deviations of the taught person in training. This precise positioning provides an accurate basis for subsequent labeling work. The difference results are directly marked on the digital twin, so that the teacher and the taught person can intuitively see the problem. This intuitive display method is more vivid and easy to understand than text or digital descriptions, which helps to quickly identify and solve problems. In the labeling process, not only the central positioning point of the difference area is considered, but also the physiological movement law of the human body is combined to determine the scope of influence. This processing method makes the labeling results more detailed and comprehensive, and can reflect the degree of influence of the problem on the entire movement or limb. Labeling the digital twin according to the limb part to be labeled and the scope of influence can ensure that the problem is displayed from multiple angles and levels. This multi-angle labeling method helps the teacher and the taught person to understand the problem more comprehensively, so as to formulate a more comprehensive improvement plan. Through the intuitive labeling display, the teacher can quickly point out the problem of the taught person and give specific improvement suggestions. This efficient feedback mechanism helps save teaching time and improve teaching efficiency. The intuitive annotation display helps the students to more clearly understand their own problems and motivate them to improve. At the same time, the annotation results can also be used as a reference and basis for subsequent training, helping the students to train and improve more targetedly.

[0016] Optionally, after comparing the real-time training data with the preset training data to obtain a difference result, the method further includes: sending the difference result to the wearable device to control the wearable device to provide real-time prompts to the person being taught, wherein the real-time prompts include voice prompts, text prompts and vibration prompts.

[0017] By adopting the above technical solution, the method ensures the real-time feedback by instantly comparing the real-time training data with the preset training data and generating the difference results immediately. This immediacy is crucial for the skill learning or training process because it allows the learner to realize the problem almost at the same time as the error occurs, so that he can immediately adjust his behavior or method to improve learning efficiency. Since the feedback is based on individual real-time performance, it provides a highly personalized learning experience. The learning progress, difficulties and errors of each learner are unique. This method can give accurate feedback and guidance according to each person's specific situation, which helps to accelerate the learning process and reduce ineffective efforts. Providing multiple feedback methods such as voice prompts, text prompts and vibration prompts greatly enriches the diversity and flexibility of feedback. Different people may have different sensitivities and preferences for different types of feedback. Diverse prompt methods can ensure that feedback information can be effectively conveyed to the learner, improving user experience and learning effects.

[0018] Optionally, the method further includes: if it is determined that the target training type is sprinting, generating a video stream digital avatar according to the preset training data, and the video stream digital avatar performs sprinting training together with the person being taught; and displaying the video stream digital avatar to the teacher through the AR glasses.

[0019] By adopting the above technical solutions, the video stream digital twin shows the standard movements, rhythm and skills of sprinting in a highly simulated form, providing an intuitive visual reference for the learners. This dynamic demonstration can attract the learners' attention more than static pictures or text descriptions, helping them to better understand and imitate the correct sprinting movements. By generating a digital twin that trains with the learners, a certain degree of personalized teaching can be achieved. Although the twin is created based on preset training data, it can be adjusted to a certain extent according to the specific situation of the learners, such as speed, cadence, etc., to better adapt to and guide them. The application of AR glasses enables teachers to observe the interaction between the learners and the digital twin in real time, so as to more accurately evaluate the learners' learning progress and existing problems. Teachers can give guidance and suggestions in time based on the observed situation, enhancing the interactivity and pertinence of teaching. The combination of digital twin and AR technology adds fun and a sense of technology to sprint training, which helps to enhance the learners' interest and motivation in learning. When the learners see their performance compared with the digital twin, it may stimulate their competitiveness and curiosity, prompting them to train harder.

[0020] In a second aspect of the present application, an auxiliary teaching device based on a digital avatar is provided, the auxiliary teaching device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire the target training type of the learner; the processing module is used to match the digital avatar corresponding to the learner and the preset training data corresponding to the digital avatar according to the target training type; the acquisition module is also used to acquire the real-time training data of the learner during training in a training field; the processing module is also used to compare the real-time training data with the preset training data to obtain a difference result; the processing module is also used to mark the difference result to the digital avatar to obtain a digital avatar to be displayed; the processing module is also used to display the digital avatar to be displayed to the teacher through AR glasses, and the teacher wears the AR glasses.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0024] By comparing real-time training data with preset training data, teachers can immediately get feedback on the training situation of the taught, without waiting for the end of training to review or evaluate. This instant feedback helps teachers adjust teaching strategies in a timely manner to ensure efficient teaching. The digital and automated comparison process reduces the subjectivity of human judgment, making teaching evaluation more objective and accurate. Teachers can guide the taught based on specific data differences, avoiding misjudgments caused by personal bias or lack of experience. By displaying the digital avatar with the difference results marked by AR glasses, teachers can intuitively see the specific problems and improvement points of the taught in training. This intuitive display method helps the taught to better understand the teaching intention and improve the enthusiasm and participation of learning. According to the target training type of different taught, the corresponding digital avatar and preset training data are matched to achieve personalized teaching. Teachers can formulate more targeted training plans according to the specific situation of the taught to improve the teaching effect. Therefore, it is convenient for teachers to teach the taught. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart of an auxiliary teaching method based on a digital avatar provided in an embodiment of the present application.

[0026] Figure 2 Another flowchart of an auxiliary teaching method based on a digital avatar provided in an embodiment of the present application.

[0027] Figure 3 A module schematic diagram of a digital avatar-based auxiliary teaching device provided in an embodiment of the present application.

[0028] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0029] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0030] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0031] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0032] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0033] In today's society, with the significant increase in public health awareness and the continuous improvement of quality of life, sports have become an indispensable part of the pursuit of a healthy lifestyle. This trend has crossed age boundaries, from young children to mature adults, from pure amateurs to skilled professional athletes, all of whom are actively participating in the craze for sports. This extensive and in-depth participation has brought unprecedented prosperity and development opportunities to the field of sports teaching.

[0034] However, one of the major challenges facing physical education today is that traditional teaching observation methods are highly dependent on teachers’ intuitive feelings and accumulated experience. This method is not only inefficient and difficult to cope with large-scale or high-frequency teaching needs, but is also easily interfered by personal subjective biases, resulting in inaccurate or even misleading observation results. This limitation is obviously not conducive to teachers accurately grasping students’ learning status, which in turn affects the optimization and improvement of teaching results.

[0035] In order to solve the above technical problems, the present application provides an auxiliary teaching method based on digital avatar, referring to Figure 1 , Figure 1 A flowchart of an auxiliary teaching method based on a digital avatar provided in an embodiment of the present application. The auxiliary teaching method is applied to a server and includes steps S110 to S160, which are as follows:

[0036] S110. Obtain the target training type of the learner.

[0037] Specifically, in this scenario, the server is one of the core components of the entire teaching system, responsible for processing, storing and distributing various teaching resources and data. The taught (such as students, athletes, etc.) input or select their target training type to the system in some way (such as through a web page, application or wearable device). This target training type may be a specific sport (such as sprinting, basketball, swimming, etc.), or it may be a more detailed skill area (such as three-point shooting in basketball, dribbling skills in football, etc.). After receiving the input from the taught, the server will parse and identify the target training type, and then prepare corresponding teaching resources, training plans or feedback mechanisms based on this type.

[0038] S120. According to the target training type, a digital avatar corresponding to the person being taught and preset training data corresponding to the digital avatar are matched.

[0039] Specifically, in a digital teaching server, a digital avatar is usually a highly simulated virtual image that can simulate various human movements and postures. According to the target training type of the learner, the server will select or generate a matching digital avatar from a pre-built digital avatar library. This avatar will serve as the learner's representative in the virtual environment and participate in training, simulated competitions and other activities. Preset training data refers to a series of teaching resources, action models, motion parameters, etc. prepared in advance to support a specific type of training. These data are compiled based on expert experience, scientific research or actual training data, and are intended to provide standardized and scientific training guidance for learners. According to the learner's target training type, the server will retrieve the corresponding preset training data from the database and associate it with the matching digital avatar.

[0040] In a possible implementation, according to the target training type, a digital avatar corresponding to the taught person and preset training data corresponding to the digital avatar are matched, specifically including: searching for the taught person in a preset database, the preset database pre-stores preset taught persons and preset digital avatars, one preset taught person corresponds to one preset digital avatar, and the preset digital avatar is pre-constructed; if it is determined that the taught person exists among multiple preset taught persons, then the preset digital avatar corresponding to the preset taught person is obtained, and the preset digital avatar is used as the digital avatar corresponding to the taught person; according to the target training type, the preset training data corresponding to the digital avatar is determined, the target training types include track and field event types and ball game event types, and the preset training data include motion posture data, speed output data, strength output data and training performance data.

[0041] Specifically, the preset database is a database that stores preset taught persons and their corresponding digital avatars. Each preset taught person has a unique identifier in the database and is associated with a pre-built digital avatar. These digital avatars may be constructed based on scanned data of real people, 3D modeling technology or other methods, and have high simulation and personalized characteristics. When the server receives the target training type of the taught person, it will first search the preset database for records of the taught person. This step is to confirm whether the taught person has been registered in the server and has a corresponding digital avatar. If the record of the taught person is found in the preset database, the server will obtain the preset digital avatar corresponding to the taught person. This digital avatar will be used as a virtual representative of the taught person in subsequent training.

[0042] Next, the server will determine the preset training data required for the digital avatar based on the target training type of the person being taught. These preset training data may include action posture data (such as videos or 3D models of standard actions), speed output data (such as running speed, shooting speed, etc.), strength output data (such as shooting strength, weightlifting weight, etc.) and training performance data (such as historical training results, progress curves, etc.). These data are compiled based on expert experience, scientific research or actual training data, and are intended to provide standardized and scientific training guidance for the person being taught. The target training type refers to the specific project or field that the person being taught wishes to train in. The track and field event types and ball game event types mentioned here are two common training types. Different training types require different training data and guidance methods.

[0043] For example, suppose the learner is a track and field athlete, and his target training type is "100-meter sprint". The server searches for the record of the track and field athlete in the preset database. Assume that he has registered in the server and has a corresponding digital avatar. The server obtains the preset digital avatar corresponding to the track and field athlete. This digital avatar may be a highly simulated image of a track and field athlete, with a body shape, muscle lines and movement characteristics similar to those of a real athlete. According to the training type of "100-meter sprint", the server retrieves the relevant preset training data from the database. These data may include: Action posture data: video or 3D model of the standard starting posture, mid-running posture and sprinting posture of the 100-meter sprint. Speed ​​output data: running speed recommendations and acceleration curves at different stages. Strength output data: explosive power requirements at the start, strength distribution during mid-running, etc. Training performance data: historical 100-meter sprint results, progress curves, competitor data, etc. During the training process, the learner can watch the digital avatar perform a demonstration of the 100-meter sprint through devices such as AR glasses. At the same time, the server will analyze and provide feedback on the student's running movements in real time based on the preset training data, point out the problems and provide suggestions for improvement. For example, the server may prompt the student to adjust the starting posture, increase acceleration, optimize force distribution, etc. Through this process, the server can provide a customized digital avatar and preset training data based on the student's target training type, thereby helping him train more effectively and improve his skills.

[0044] S130: Acquire real-time training data of the learner during training at the training ground.

[0045] Specifically, in this scenario, the server plays a core role. It is not only responsible for storing and managing training data, but also for collecting, processing and analyzing this data in real time. The server obtains real-time training data by connecting to various sensors, wearable devices or video monitoring servers. Real-time training data includes various performance indicators of the trainees during training, such as speed, strength, posture, heart rate, cadence, movement trajectory, etc. These data are collected in real time through various sensors (such as speed sensors, force sensors, accelerometers, gyroscopes, heart rate monitors, etc.) and monitoring equipment (such as high-definition cameras). When the trainee is training on the training ground, the sensors he wears or the surrounding monitoring equipment will continuously transmit real-time data to the server. After receiving this data, the server will quickly process and analyze it to extract useful information. This information may be used for real-time feedback, training effect evaluation, training plan adjustment, etc.

[0046] In a possible implementation, real-time training data of a learner training at a training ground is obtained, specifically including: receiving original training data sent by a wearable device and a field sensor device, the learner wears a wearable device, and the training ground is equipped with a field sensor device; preprocessing the original training data to obtain real-time training data, the preprocessing including denoising, filtering, feature classification, and normalization.

[0047] Specifically, when the trainee is training on the training ground, the wearable device he / she wears (such as heart rate monitor, accelerometer, gyroscope, GPS tracker, etc.) and the field sensor equipment installed on the training ground (such as pressure sensor, camera, microphone, etc.) will collect various data in real time. These data are collectively referred to as raw training data, which directly reflect the training status and training environment of the trainee. Wearable devices send data to servers or data collection devices via Bluetooth, Wi-Fi or other wireless technologies, and field sensor devices can be connected to the data center via wired or wireless means.

[0048] Since the original training data may contain noise, redundant information or inconsistent formats, preprocessing is required to extract useful information and prepare it for subsequent analysis. The preprocessing process usually includes the following steps: Denoising: Remove noise from the data, which may come from errors in the equipment itself, environmental interference, etc. Denoising can be achieved through various filtering techniques, such as low-pass filtering, high-pass filtering, band-pass filtering, etc. Filtering: In a broader sense, filtering also includes the process of denoising, but it may also include other types of signal processing, such as smoothing to reduce data fluctuations, or sharpening to highlight data features. Feature classification: Extract specific features from the preprocessed data, which can reflect the training status or performance of the learner. For example, features such as cadence and step length are extracted from accelerometer data; features such as heart rate variability are extracted from heart rate monitors. Normalization: Scale the data according to certain rules so that it falls within a specific numerical range. Normalization helps to eliminate the dimensional differences between different data, so that data from different sources or different scales can be compared and analyzed.

[0049] For example, suppose the person being taught is a runner who is doing speed training on the track and field. The athlete wears a smart bracelet with an accelerometer and a heart rate monitor. The accelerometer can record the athlete's cadence, stride length, acceleration and other information in real time; the heart rate monitor can record the athlete's heart rate changes. Pressure sensors are installed on the track and field to record the distribution of the athlete's footsteps when they land; at the same time, there may also be cameras to capture the athlete's running posture and movements. These devices send the raw training data collected in real time to the server wirelessly. After the server receives the raw training data, it first performs denoising to remove noise caused by equipment errors or environmental interference. Then, filtering is performed to smooth the accelerometer data to reduce data fluctuations, making features such as cadence and stride length more accurate. Then, feature classification is performed to extract motion features such as cadence and stride length from the accelerometer data; and physiological features such as heart rate variability are extracted from the heart rate monitor. Finally, normalization is performed to scale all feature data to the same numerical range according to certain rules for subsequent comparison and analysis. Through this process, the server can obtain the real-time training data of the trainees on the training ground, and obtain more accurate and useful information after preprocessing, providing support for the evaluation and improvement of training effects.

[0050] S140: Compare the real-time training data with the preset training data to obtain a difference result.

[0051] Specifically, as mentioned above, real-time training data is data generated in real time by the learner during the training process, which reflects the learner's current training status and performance. These data may include various indicators such as speed, strength, posture, heart rate, and cadence. Preset training data is a pre-defined data set representing an ideal or standard training state. These data may be compiled based on expert experience, scientific research, or historical training data, and are used to provide training guidance and reference standards for the learner. The server compares the real-time training data with the preset training data item by item or comprehensively. The content of the comparison may include the value, change trend, and distribution range of each training indicator. The purpose of the comparison is to evaluate whether the training effect of the learner meets the preset standard and to find the difference between the two. Through the comparison, the server generates difference results. These results may be presented in the form of values, charts, reports, etc., detailing the differences between the real-time training data and the preset training data. Difference results may include positive differences (such as real-time data is better than preset data, indicating that the learner performs well) and negative differences (such as real-time data is lower than preset data, indicating that the learner has deficiencies or needs improvement).

[0052] In one possible implementation, the real-time training data is compared with the preset training data to obtain a difference result, which specifically includes: obtaining a real-time motion trajectory according to the real-time training data within a preset time period, and the preset time period is set based on the complete training action corresponding to the real-time training data; obtaining a preset motion trajectory according to the preset training data within the preset time period; comparing the trajectory difference between the real-time motion trajectory and the preset motion trajectory within the preset time period, the trajectory difference includes the speed difference and the strength difference; if it is determined that the trajectory difference is greater than a preset threshold, determining the difference area in the complete training action according to the skeleton point positioning algorithm to obtain a difference result, and the difference result includes the difference area.

[0053] Specifically, this time period is set based on the complete training action corresponding to the real-time training data. In other words, in order to accurately compare the real-time training data with the preset training data, it is necessary to select a sufficiently long time period to ensure that the complete training action is included in the time period. For example, if the training action is a basketball shot, the preset time period should start from the shooting preparation action and end when the basketball leaves the finger. During this preset time period, based on the real-time training data (such as acceleration, angular velocity, position and other information collected by the wearable device), the server can reconstruct the real-time motion trajectory of the person being taught. This trajectory reflects the actual motion path and speed change of the person being taught when completing the training action. Also within the preset time period, the server generates a preset motion trajectory based on the preset training data (these data may be based on expert experience, simulation data or historical excellent training data). This trajectory represents an ideal or standard training action path.

[0054] Next, the server compares the difference between the real-time motion trajectory and the preset motion trajectory over a preset time period. This difference may include speed difference and force difference (although force is usually not directly reflected by the trajectory, it can be indirectly inferred through kinematic analysis). Speed ​​difference refers to the difference between the speed of each point on the real-time motion trajectory and the corresponding point on the preset trajectory; while force difference may need to be indirectly evaluated in combination with other data (such as acceleration data). If the trajectory difference is greater than the preset threshold (this threshold is used to determine whether the difference is significant), the server will further analyze the specific location of the difference. This is usually achieved through a bone point positioning algorithm that can identify the key bone points of the human body during movement and determine which areas (such as arms, legs, torso, etc.) have significant differences in motion trajectories from the preset trajectory. These difference areas are areas that need improvement or attention. Finally, the server will generate a difference result report that details the difference area, the degree of difference, and possible improvement suggestions. This report is very valuable for both coaches and students because it can directly point out the deficiencies in training and provide targeted improvement directions.

[0055] S150: Mark the difference results on the digital twin to obtain the digital twin to be displayed.

[0056] Specifically, the difference results refer to the inconsistencies or areas for improvement found after comparing the real-time training data with the preset training data. These differences may include deviations in movement posture, insufficient speed and strength, errors in technical details, etc. The process of marking the difference results is to present these differences in a visual way on the digital twin. This usually involves adding highlights, marks, arrows or text descriptions to the corresponding parts of the digital twin to intuitively show the differences. The digital twin is a dynamic and updateable virtual image. During the training process, with the continuous collection and processing of real-time data, the digital twin can reflect the movements and status of the taught person in real time or near real time. When the difference results are marked on the digital twin, the digital twin is updated and becomes an object to be displayed that contains training feedback and improvement suggestions. The digital twin marked with the difference results is now an object to be displayed that contains rich training information. It can be used in a variety of scenarios, such as online teaching, remote guidance, self-assessment, etc. The digital twin to be displayed can not only help the taught person intuitively see their training effects and problems, but also serve as a tool for coaches to conduct remote guidance and evaluation, thereby improving the pertinence and efficiency of training.

[0057] In a possible implementation, the difference results are marked on the digital twin to obtain the digital twin to be displayed, specifically including: according to the difference area, obtaining the central positioning point and multiple edge positioning points corresponding to the difference area; according to the central positioning point, determining the limb part to be marked; according to the multiple edge positioning points, combined with the physiological movement laws of the human body, determining the scope of the limb part to be marked; marking the digital twin according to the limb part to be marked and the scope of influence to obtain the digital twin to be displayed.

[0058] Specifically, first, the difference area is determined according to the difference result. The difference area refers to the body part or area where there is a significant difference between the real-time training data and the preset training data. In the difference area, a central positioning point and multiple edge positioning points are found. The central positioning point is usually the point with the most significant or core difference, while the edge positioning points are distributed around the central positioning point and are used to define the boundary of the difference area. According to the position of the central positioning point, the corresponding limb part to be annotated is determined. This limb part is the part that needs to be highlighted and annotated in the difference result. For example, if the central positioning point is on the arm, the limb part to be annotated is the arm. Next, according to multiple edge positioning points and the physiological movement law of the human body, the scope of the limb part to be annotated is determined. The scope of the impact refers to the range of adjacent or related body parts that may be affected by the existence of the difference area. The physiological movement law of the human body refers to the interaction and coordination relationship between various parts of the human body when exercising. By analyzing these laws, the possible impact of the difference area on other body parts can be inferred. Finally, according to the limb part to be annotated and the impact range, corresponding annotations are made on the digital clone. Annotation may include highlighting, adding arrows or marks, displaying text descriptions, etc., so as to intuitively display the difference results. The purpose of annotation is to allow observers (e.g. coaches, students, etc.) to quickly identify the differences and understand the impact they may have on other parts of the body.

[0059] For example, suppose the person being taught is a swimmer who is doing freestyle training. By comparing the real-time training data with the preset training data, it is found that the angle of entry of the athlete's right arm in the stroke is significantly different from the standard action. The central positioning point of the difference area is determined to be the entry point of the right arm, and multiple edge positioning points around this point are found, such as the starting position, highest point and end position of the right arm. According to the position of the central positioning point, the limb part to be marked is determined to be the right arm. Considering the coordination and interaction of various parts of the body during swimming, it is analyzed that the deviation of the right arm's entry angle may affect the body's rotation, the kicking action of the legs, and the breathing rhythm. Therefore, the affected range is determined to include the body's rotation axis, legs, and breathing area. On the digital clone, the right arm is highlighted, and an arrow or mark is added at the entry point to indicate the direction and degree of the deviation. At the same time, in the affected range of the body's rotation axis, legs, and breathing area, corresponding annotations or instructions are added to show the possible impact of the difference results on other parts of the body. Through this marking process, coaches and students can intuitively see the differences and their impact on other parts of the body, so that they can conduct training and adjustments more specifically.

[0060] S160. Displaying the digital avatar to be displayed to the teacher through the AR glasses, where the teacher wears the AR glasses.

[0061] Specifically, AR glasses are a wearable device that combines augmented reality technology. It can superimpose virtual information on the real world, thereby providing users with a richer and more intuitive visual experience. In this scenario, AR glasses, as a medium for displaying digital avatars, can display the digital avatar content processed by the server in a three-dimensional form in the teacher's field of vision. By displaying the digital avatar with marked difference results through AR glasses, the teacher can intuitively see the specific problems and improvement points of the taught in the training. This intuitive display method helps the taught to better understand the teaching intentions and improve the enthusiasm and participation in learning. According to the target training types of different taught, the corresponding digital avatars and preset training data are matched to achieve personalized teaching. The teacher can formulate a more targeted training plan according to the specific situation of the taught to improve the teaching effect. Therefore, it is convenient for the teacher to teach the taught.

[0062] In a possible implementation, after comparing the real-time training data with the preset training data to obtain a difference result, the method further includes: sending the difference result to a wearable device to control the wearable device to provide real-time prompts to the person being taught, and the real-time prompts include voice prompts, text prompts, and vibration prompts.

[0063] Specifically, after completing the comparison between the real-time training data and the preset training data, the system will obtain a series of difference results. These results reflect the difference between the performance of the learner in the training and the standard or expectation. In order for the learner to understand these differences in a timely manner, the system needs to convey the difference results to them in some form. Here, wearable devices are used as a medium to convey the difference results. Wearable devices, such as smart watches, smart bracelets or special training auxiliary equipment, are lightweight and portable, can fit closely to the learner's body, and provide real-time feedback. In this scenario, the wearable device receives the difference results from the system and generates corresponding real-time prompts based on these results. Voice prompts: Play voice messages to the learner through the built-in speakers of the wearable device or connected peripherals (such as headphones), directly informing them of the differences or areas that need to be adjusted. Text prompts: Display text messages on the display screen of the wearable device, such as "arm angle is too low", "pay attention to breathing rhythm", etc., so that the learner can receive feedback visually. Vibration prompts: Use the vibration function of the wearable device to prompt the learner to pay attention to certain specific actions or states through vibrations of different modes or intensities.

[0064] In one possible implementation, refer to Figure 2 , Figure 2Another flow chart of an auxiliary teaching method based on a digital avatar provided for an embodiment of the present application includes steps S210 to S220, and the above steps are as follows: S210, if the target training type is determined to be sprinting, a video stream digital avatar is generated according to preset training data, and the video stream digital avatar performs sprint training together with the person being taught; S220, the video stream digital avatar is displayed to the teacher through AR glasses.

[0065] Specifically, in this scenario, it is first clarified that the training goal is sprinting. As a specific sport, sprinting has its own unique training requirements and skills. Based on the preset data of sprinting training (these data may include standard starting posture, cadence, stride, acceleration method, finish line sprinting skills, etc.), the system uses computer graphics technology and animation technology to generate a video stream digital avatar. This avatar is a virtual sprinter, whose behavior and movements are simulated based on the preset data of sprinting training. During the actual training process, this video stream digital avatar will appear on the training ground with the person being taught (i.e., the real sprinter). Although the avatar is virtual, it will move according to the preset sprinting training mode, forming a contrast or demonstration with the person being taught. It should be noted that "training together" here does not mean that the avatar will physically run side by side with the person being taught, but that the avatar's movements and training process will be displayed synchronously with the person being taught, forming a visual accompaniment effect. After the teacher wears AR glasses, he can see a virtual scene superimposed on the real world, which includes the video stream digital avatar that is training with the person being taught. AR glasses use augmented reality technology to combine virtual digital avatars with real training scenarios, providing teachers with a more intuitive and comprehensive training observation perspective.

[0066] The present application also provides an auxiliary teaching device based on a digital avatar, referring to Figure 3 , Figure 3 An auxiliary teaching device based on a digital avatar is provided in an embodiment of the present application. The auxiliary teaching device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the target training type of the learner; the processing module 32 matches the digital avatar corresponding to the learner and the preset training data corresponding to the digital avatar according to the target training type; the acquisition module 31 acquires the real-time training data of the learner during training in the training ground; the processing module 32 compares the real-time training data with the preset training data to obtain a difference result; the processing module 32 marks the difference result to the digital avatar to obtain a digital avatar to be displayed; the processing module 32 displays the digital avatar to be displayed to the teacher through AR glasses, and the teacher wears AR glasses.

[0067] In a possible implementation, the processing module 32 matches the digital avatar corresponding to the taught person and the preset training data corresponding to the digital avatar according to the target training type, specifically including: the processing module 32 searches for the taught person in a preset database, the preset database pre-stores preset taught persons and preset digital avatars, one preset taught person corresponds to one preset digital avatar, and the preset digital avatar is pre-constructed; if the processing module 32 determines that the taught person exists among multiple preset taught persons, it obtains the preset digital avatar corresponding to the preset taught person, and uses the preset digital avatar as the digital avatar corresponding to the taught person; the processing module 32 determines the preset training data corresponding to the digital avatar according to the target training type, the target training type includes track and field event types and ball game event types, and the preset training data includes movement posture data, speed output data, strength output data and training performance data.

[0068] In a possible implementation, the acquisition module 31 acquires real-time training data of the student during training at the training ground, specifically including: the acquisition module 31 receives original training data sent by wearable devices and field sensor devices, the student wears a wearable device, and the training ground is installed with field sensor devices; the processing module 32 preprocesses the original training data to obtain real-time training data, and the preprocessing includes denoising, filtering, feature classification and normalization.

[0069] In one possible implementation, the real-time training data is compared with the preset training data to obtain a difference result, which specifically includes: the processing module 32 obtains a real-time motion trajectory according to the real-time training data within a preset time period, and the preset time period is set based on the complete training action corresponding to the real-time training data; the processing module 32 obtains a preset motion trajectory according to the preset training data within the preset time period; the processing module 32 compares the trajectory difference between the real-time motion trajectory and the preset motion trajectory within the preset time period, and the trajectory difference includes a speed difference and a strength difference; if the processing module 32 determines that the trajectory difference is greater than a preset threshold, the difference area in the complete training action is determined according to the skeleton point positioning algorithm to obtain a difference result, and the difference result includes the difference area.

[0070] In a possible implementation, the difference results are marked on the digital twin to obtain the digital twin to be displayed, which specifically includes: the processing module 32 obtains the central positioning point and multiple edge positioning points corresponding to the difference area according to the difference area; the processing module 32 determines the limb part to be marked according to the central positioning point; the processing module 32 determines the scope of the limb part to be marked according to the multiple edge positioning points and the physiological movement law of the human body; the processing module 32 marks the digital twin according to the limb part to be marked and the scope to obtain the digital twin to be displayed.

[0071] In a possible implementation, after the processing module 32 compares the real-time training data with the preset training data and obtains the difference result, it also includes: the processing module 32 sends the difference result to the wearable device to control the wearable device to give real-time prompts to the person being taught, and the real-time prompts include voice prompts, text prompts and vibration prompts.

[0072] In a possible implementation, if the processing module 32 determines that the target training type is sprinting, it generates a video stream digital avatar based on preset training data, and the video stream digital avatar performs sprinting training with the person being taught; the processing module 32 displays the video stream digital avatar to the teacher through AR glasses.

[0073] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0074] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0075] The communication bus 42 is used to realize the connection and communication between these components.

[0076] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0077] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0078] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0079] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for an auxiliary teaching method based on a digital avatar.

[0080] exist Figure 4In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program stored in the memory 45 for an auxiliary teaching method based on a digital avatar. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.

[0081] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0082] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0083] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0087] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0088] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An auxiliary teaching method based on digital avatar, characterized in that: The method comprises: Obtain the target training type of the learner; According to the target training type, matching is performed to obtain the digital twin corresponding to the person being taught and the preset training data corresponding to the digital twin; Acquiring real-time training data of the person being taught during training at the training ground; Comparing the real-time training data with the preset training data to obtain a difference result; Marking the difference results on the digital twin to obtain a digital twin to be displayed; Displaying the digital avatar to be displayed to a teacher through AR glasses, wherein the teacher wears the AR glasses; The matching according to the target training type to obtain the digital twin corresponding to the taught person and the preset training data corresponding to the digital twin specifically includes: Searching for the taught person in a preset database, wherein the preset database pre-stores preset taught persons and preset digital twins, one preset taught person corresponds to one preset digital twin, and the preset digital twin is pre-constructed; If it is determined that the taught person exists among the plurality of preset taught persons, obtaining a preset digital twin corresponding to the preset taught person, and using the preset digital twin as the digital twin corresponding to the taught person; According to the target training type, the preset training data corresponding to the digital avatar is determined, the target training type includes track and field event types and ball game event types, and the preset training data includes movement posture data, speed output data, strength output data and training performance data.

2. The auxiliary teaching method based on digital avatar according to claim 1 is characterized in that: The obtaining of the real-time training data of the person being taught during training at the training ground specifically includes: Receiving original training data sent by a wearable device and a field sensor device, wherein the wearable device is worn by the person being taught and the field sensor device is installed in the training field; The original training data is preprocessed to obtain the real-time training data, wherein the preprocessing includes denoising, filtering, feature classification and normalization.

3. The auxiliary teaching method based on digital avatar according to claim 1 is characterized in that: The comparing the real-time training data with the preset training data to obtain a difference result specifically includes: A real-time motion trajectory is obtained according to the real-time training data within a preset time period, wherein the preset time period is set based on a complete training action corresponding to the real-time training data; Within the preset time period, obtaining a preset motion trajectory according to the preset training data; Comparing the real-time motion trajectory with the preset motion trajectory within the preset time period, the trajectory difference includes a speed difference and a force difference; If it is determined that the trajectory difference is greater than a preset threshold, the difference area in the complete training action is determined according to the skeleton point positioning algorithm to obtain the difference result, which includes the difference area.

4. The auxiliary teaching method based on digital avatar according to claim 3 is characterized in that: The step of marking the difference result on the digital twin to obtain the digital twin to be displayed specifically includes: According to the difference area, a central positioning point and a plurality of edge positioning points corresponding to the difference area are obtained; Determine the limb part to be marked according to the central positioning point; According to the plurality of edge positioning points and in combination with the physiological movement law of the human body, determining the range of the limb part to be marked; The digital avatar is labeled according to the body part to be labeled and the affected range to obtain the digital avatar to be displayed.

5. The auxiliary teaching method based on digital avatar according to claim 2 is characterized in that: After comparing the real-time training data with the preset training data to obtain a difference result, the method further includes: The difference result is sent to the wearable device to control the wearable device to give real-time prompts to the person being taught, wherein the real-time prompts include voice prompts, text prompts, and vibration prompts.

6. The auxiliary teaching method based on digital avatar according to claim 1 is characterized in that: The method further comprises: If it is determined that the target training type is sprinting, a video stream digital twin is generated according to the preset training data, and the video stream digital twin performs sprinting training together with the person being taught; The digital avatar of the video stream is displayed to the instructor through the AR glasses.

7. An auxiliary teaching device based on digital avatar, characterized in that: The auxiliary teaching device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to acquire the target training type of the learner; The processing module (32) is used to match and obtain the digital twin corresponding to the person being taught and the preset training data corresponding to the digital twin according to the target training type; The acquisition module (31) is also used to acquire the real-time training data of the learner during training at the training ground; The processing module (32) is further used to compare the real-time training data with the preset training data to obtain a difference result; The processing module (32) is further used to mark the difference result on the digital twin to obtain the digital twin to be displayed; The processing module (32) is further used to display the digital avatar to be displayed to the teacher through AR glasses, and the teacher wears the AR glasses; The processing module (32) is also used to match the digital twin corresponding to the taught person and the preset training data corresponding to the digital twin according to the target training type, specifically comprising: searching for the taught person in a preset database, wherein the preset taught person and the preset digital twin are pre-stored, one preset taught person corresponds to one preset digital twin, and the preset digital twin is pre-constructed; if it is determined that the taught person exists among a plurality of the preset taught persons, obtaining the preset digital twin corresponding to the preset taught person, and using the preset digital twin as the digital twin corresponding to the taught person; determining the preset training data corresponding to the digital twin according to the target training type, wherein the target training type includes track and field event types and ball game event types, and the preset training data includes action posture data, speed output data, strength output data, and training performance data.

8. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 6 is performed.

Images