Teaching assistance method, system and device and server

Abstract

The invention provides a teaching assistance method, system and device and a server, and the method is applied to the server, and comprises the steps: obtaining body data which comprises data collected by a sensor; and teaching auxiliary information is determined according to the body data and the teaching field priori knowledge. In the implementation process of the scheme, the body data of the students and priori knowledge in the teaching field are collected in real time in combination with the sensors, teaching suggestions such as teaching auxiliary information can be generated according to individuation of each student user, and due to the fact that the body data are the data collected by the sensors in real time, the teaching suggestions are more accurate. The real-time performance that the body data is used for teaching students is effectively ensured. Therefore, in combination with the body data collected by the sensor in real time and prior knowledge in the teaching field, the balance between individuation and real-time performance of teaching for students can be effectively considered.

Description

Technical Field

[0001] The present application relates to the technical fields of human-computer interaction, computer data processing and intelligent education, and more specifically, to a teaching assistance method, system, device and server. Background Art

[0002] In the current teaching process, a unified teaching plan is usually used for guidance. Although this standardized teaching method helps to ensure the consistency and structure of the course, it is difficult to fully take into account the individual needs of each student, which may result in some students not being able to achieve the best learning results. Although some auxiliary means such as taking photos and punching in, online activity records and test scores can be used to monitor and promote the learning progress of these students, most of these auxiliary means rely on indirect indicators such as students' online classroom exercise scores, course grade rankings, number of extracurricular activities or test scores of sports events. These indirect indicators lack real-time performance and cannot immediately reflect students' learning situation in actual teaching, nor can they adjust teaching strategies according to students' real-time status. Therefore, it is difficult for current teaching auxiliary methods to strike a balance between personalized and real-time teaching for students. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a teaching assistance method, system, device and server for improving the problem of balancing the personalization and real-time nature of teaching for students.

[0004] In the first aspect, the embodiment of the present application provides a teaching assistance method, which is applied to a server, including: obtaining body data, the body data including data collected by sensors; determining teaching assistance information according to body data and prior knowledge in the teaching field. In the implementation process of the above scheme, by combining the real-time collection of students' body data and prior knowledge in the teaching field by sensors, teaching suggestions such as teaching assistance information can be generated for each student user, and since the body data is data collected by sensors in real time, the real-time nature of the body data used for teaching students is effectively guaranteed. High personalization requires more dimensional data and more complex algorithm models, resulting in more processing time, which will affect the real-time nature of the system response, while better real-time nature requires less data and simpler algorithm models, but it is difficult to meet the needs of more personalized information. Therefore, by combining the body data collected by sensors in real time and introducing "prior knowledge in the teaching field", a balanced choice is made between the needs of high personalization and the needs of better real-time nature, so that the balance between personalization and real-time nature of teaching for students can be effectively taken into account.

[0005] In an optional implementation of the first aspect, the body data includes: basic body data and data collected by wearable devices during exercise, and the teaching auxiliary information includes: fatigue level and / or recovery time; determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field includes: determining the fatigue level and / or recovery time in the teaching auxiliary information based on the basic body data, data collected by wearable devices and prior knowledge in the teaching field. In the implementation process of the above scheme, by comprehensively analyzing the changing trends of the basic body data and the exercise data collected in real time by the wearable device, the student's fatigue level and / or the recovery time required for the current state can be more accurately evaluated based on this changing trend and prior knowledge in the teaching field, which effectively improves the evaluation accuracy of the fatigue level and / or recovery time.

[0006] In an optional implementation of the first aspect, the body data includes: sweat biomarker parameters collected by the wearable device, and the teaching auxiliary information includes: physical health status; determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field includes: determining the physical health status in the teaching auxiliary information based on the sweat biomarker parameters and prior knowledge in the teaching field. In the implementation process of the above scheme, by combining sweat biomarkers and other body data (such as heart rate, blood pressure, etc.), as well as prior knowledge in the teaching field, the system can perform a more comprehensive and multi-dimensional assessment, thereby improving the accuracy of the physical health status.

[0007] In an optional implementation of the first aspect, the body data includes: data collected by the wearable device during exercise, and the teaching auxiliary information includes: after-class recovery recommendation information; the teaching auxiliary information is determined according to the body data and the prior knowledge of the teaching field, including: determining the after-class recovery recommendation information in the teaching auxiliary information according to the data collected by the wearable device, the sports course information and the prior knowledge of the teaching field, and the after-class recovery recommendation information includes: stretching action recommendation information, medicine package recommendation information and / or dietary recommendation information. In the implementation process of the above scheme, according to the data collected by the wearable device during each student's exercise and the sports course information, the system can generate personalized after-class recovery recommendation information according to the prior knowledge of the teaching field, so as to ensure that the after-class recovery measures are highly matched with the actual needs, for example, by analyzing the muscle use during exercise, the most effective stretching action can be recommended to help relieve muscle tension and fatigue, thereby improving the recovery efficiency after class. In addition, combined with the recommendation of medicine packages (such as hot compress packs, cold compress packs, Chinese medicine packs, etc.), specific usage methods and time can be provided to accelerate the muscle recovery process, and suitable meals can be recommended according to the intensity of exercise and the calories consumed to ensure that students get enough nutritional supplements, further improving the recovery efficiency after class.

[0008] In an optional implementation of the first aspect, the above-mentioned body data includes: data collected by wearable devices during exercise, and the teaching auxiliary information includes: after-class homework recommendation information; the teaching auxiliary information is determined according to the body data and prior knowledge in the teaching field, including: determining the after-class homework recommendation information in the teaching auxiliary information according to the data collected by the wearable device, the sports course information and the prior knowledge in the teaching field, and the after-class homework recommendation information is the training content recommended specifically for the individual student's sports performance in the sports class. In the implementation process of the above scheme, according to the specific performance of each student in the sports course, the system can generate highly targeted and personalized training content as after-class homework recommendation information, so that students can conduct targeted training after class to make up for poor or enhance their advantageous sports performance, which effectively improves the student's participation and the personalization of the training content recommendation.

[0009] In an optional implementation of the first aspect, the body data includes: data collected by wearable devices during the teaching process; determining teaching auxiliary information based on the body data and prior knowledge in the teaching field, including: determining the learning status in the learning activity based on the data collected by the wearable device and prior knowledge in the teaching field; determining the target time when the learning status is not good, and determining the target content from the teaching audio / video according to the target time; wherein the target content is the content that individual students need targeted tutoring; the teaching audio / video is obtained by recording the teacher's teaching process. In the implementation of the above scheme, according to the time period when the learning status is not good, the system can extract the teaching content that the student needs targeted tutoring from the teaching audio / video, thereby serving as targeted tutoring materials for the student, which effectively improves the student's participation in the teaching process and the personalization of targeted tutoring.

[0010] In an optional implementation of the first aspect, the body data includes: basic body data, data collected by wearable devices during exercise, and the teaching auxiliary information includes: sports course recommendation information; the teaching auxiliary information is determined based on the body data and prior knowledge in the teaching field, including: determining the sports ability index based on the basic body data and the data collected by the wearable device; determining the sports course recommendation information in the teaching auxiliary information based on the sports ability index and prior knowledge in the teaching field. In the implementation process of the above scheme, the sports course most suitable for the student is recommended through the specific physical conditions in the basic body data of each student and the sports ability index determined by the sports performance data collected by the wearable device, ensuring that the training content is highly matched with the individual ability, thereby improving the personalization of the course recommendation. Furthermore, by analyzing the sports ability index, the strengths and weaknesses of the student can be effectively identified, so as to recommend targeted training course information for the strengths and weaknesses respectively, to help students make up for their weaknesses and strengthen their strengths, thereby comprehensively improving the students' sports ability.

[0011] In an optional implementation of the first aspect, the body data includes: basic body data, data collected by wearable devices during exercise, and the teaching auxiliary information includes: sports course recommendation information; determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field, including: determining the sports ability index based on the basic body data and the data collected by the wearable device; determining the psychological data index during exercise based on the data collected by the wearable device; determining the sports course recommendation information in the teaching auxiliary information based on the sports ability index, the psychological data index and the prior knowledge in the teaching field. In the implementation process of the above scheme, by not only considering the basic body data and the physiological data such as the collected sports ability index, but also combining the psychological data index for comprehensive evaluation, a more comprehensive and personalized sports course recommendation is generated, so that the most suitable sports course can be recommended, ensuring that the training content is highly matched with the personal situation, and effectively improving the personalization of the course recommendation information. Further, based on the psychological data index, the system can recommend sports courses that help relieve stress and improve emotions, not only focusing on the physical performance of students, but also focusing on the psychological state of students, so as to recommend sports courses that can both improve quality and improve mental health, while improving the training effect and mental health.

[0012] In an optional implementation of the first aspect, the basic body data includes information about poor physical condition, and the sports course recommendation information in the teaching auxiliary information is information about sports courses that are targeted to improve poor physical condition, and / or nutritional diet information that is targeted to improve poor physical condition. In the implementation of the above scheme, by combining the basic body data including poor physical condition information with the data collected by wearable devices during exercise, determining the sports ability index based on these data and prior knowledge in the teaching field, and recommending sports courses that are targeted to improve poor physical condition, the accuracy of physical health management can be achieved, and the multi-dimensionality and comprehensiveness of health management can be comprehensively improved.

[0013] In an optional implementation of the first aspect, the body data includes: data collected by wearable devices, and the teaching auxiliary information includes: course recommendation information; the teaching auxiliary information is determined based on the body data and prior knowledge in the teaching field, and also includes: obtaining the evaluation results of the student user, and determining the pleasure state score of the student user based on the data collected by the wearable device, the evaluation results characterizing the emotional and intellectual state of the student user; determining the course recommendation information in the teaching auxiliary information based on the evaluation results and the pleasure state score. In the implementation process of the above scheme, the course recommendation information is determined by comprehensively considering the user's evaluation results and the multiple dimensions of the pleasure state, which effectively improves the comprehensiveness and personalization of the course recommendation.

[0014] In an optional implementation of the first aspect, the evaluation results include: emotion evaluation scores and / or intelligence evaluation scores; obtaining the evaluation results of the student user includes: receiving a question answering request sent by the student user through a terminal device, the question answering request includes: the age parameter of the student user; searching for test questions corresponding to the age parameter in a social adaptability question library and / or a behavioral activity question library; sending the test questions corresponding to the age parameter to the terminal device so that the student user completes and returns the test answers corresponding to the test questions; and evaluating the emotion evaluation score and / or intelligence evaluation score of the student user according to the test answers corresponding to the test questions. In the implementation process of the above scheme, by receiving the age parameters of the students and matching the corresponding test questions, the emotional and intellectual states of the student users of a specific age group can be evaluated more accurately, and the personalization level of the evaluation can be improved. In addition, by corresponding the test questions to the age of the students, it is ensured that the test content is suitable for the students' cognitive development stage, thereby improving the effectiveness and reliability of the test.

[0015] In an optional implementation of the first aspect, the pleasure state score of the student user is determined based on data collected by the wearable device, including: determining the emotional state of the student user in multiple attendances of preset type courses based on the data collected by the wearable device; determining the pleasure state score of the student user for the preset type course based on the proportion of the number of times characterized as a pleasure state in the multiple attendances; wherein the preset type of course includes: at least one of a cultural course, a sports course, an art course, and a practical course. In the implementation of the above scheme, the emotional state of the students in different courses is monitored in real time through wearable devices to provide a continuous data stream, which enables the system to capture the students' immediate reactions in specific courses and improves the accuracy of the pleasure state score assessed by the emotional state.

[0016] In an optional implementation of the first aspect, the body data includes: data collected by a wearable device; the teaching auxiliary information is determined based on the body data and prior knowledge in the teaching field, including: determining the emotional state of the student user within a preset time period based on the data collected by the wearable device; determining the pleasure state score of the student user within the preset time period based on the proportion of the number of times the emotional state is characterized as a pleasure state in the preset time period. In the implementation of the above scheme, the emotional state of students in different courses is monitored in real time through wearable devices to provide a continuous data stream, which enables the system to capture the immediate reaction of students in a specific course and improves the accuracy of the pleasure state score assessed by the emotional state.

[0017] In an optional implementation of the first aspect, the body data includes: data collected by the wearable device during the teaching process, and the teaching auxiliary information includes: a teaching intervention plan; determining the teaching auxiliary information according to the body data and prior knowledge in the teaching field, including: determining the psychological data index curve according to the data collected by the wearable device; determining the teaching intervention plan in the teaching auxiliary information according to the psychological data index curve and prior knowledge in the teaching field. In the implementation process of the above scheme, the body data (such as students' heart rate, heart rate variability HRV, skin galvanic response GSR and other physiological indicators) monitored in real time by the wearable device can instantly generate a psychological data index curve, thereby realizing a real-time emotion monitoring function, and then, according to each student's psychological data index curve, provide personalized teaching intervention suggestions to help teachers conduct targeted teaching according to the emotional state of different students. For students with large emotional fluctuations, the system can recommend specific intervention measures, thereby effectively improving the personalization of student education. Further, by monitoring and adjusting the emotional state of students, the system can help create a more positive and supportive learning environment, thereby improving the overall learning effect, and also relieve students' anxiety and stress through teaching intervention suggestions, so that students can focus more on learning tasks and improve learning efficiency.

[0018] In an optional implementation of the first aspect, the body data includes: sports homework videos uploaded by student users, and the teaching auxiliary information includes: evaluation results of sports homework videos; determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field, including: identifying key action video units from the sports homework videos, the key action video units are video frames or video clips; analyzing the key action video units based on prior knowledge in the teaching field, and determining the evaluation results of the sports homework videos in the teaching auxiliary information, the evaluation results include whether they are qualified and / or action correction and improvement suggestions. In the implementation process of the above scheme, by automatically analyzing the key actions in the video and providing instant evaluation results and improvement suggestions, the manual evaluation time of the teacher is greatly reduced, and according to the key action video units of each student, it helps students to improve their skills in a targeted manner, thereby improving the personalization of the evaluation results and improvement suggestions. Further, through the analysis of a large amount of video data, the system can discover common problems and trends among students, provide data support for teaching improvement, and can continuously optimize the teaching content (such as action correction and improvement suggestions) based on the data analysis results, and improve the personalization of teaching quality.

[0019] In an optional implementation of the first aspect, the prior knowledge in the teaching field includes: standard action videos, and the teaching auxiliary information includes: action correction and improvement suggestions; the key action video units are analyzed according to the prior knowledge in the teaching field to determine the evaluation results of the sports homework video, including: extracting human body key points from the sports homework video; comparing the human body key points with the key points in the standard action video to obtain comparison results; generating action correction and improvement suggestions in the teaching auxiliary information according to the comparison results. In the implementation process of the above scheme, by automatically extracting human body key points (such as joint positions, body postures, etc.) from the students' sports videos and comparing them with the key points in the standard action videos, the accuracy of the action analysis is improved, and through the precise comparison of key points, a very detailed and accurate comparison result of the action evaluation can be provided, and according to the comparison results of the specific performance of each student, personalized action correction and improvement suggestions are provided for each student, which effectively improves the pertinence, effectiveness and personalization of the action correction and improvement suggestions.

[0020] In an optional implementation of the first aspect, the body data includes a sports video; determining the teaching auxiliary information based on the body data and the prior knowledge of the teaching field includes: decomposing the sports video into multiple key action video units based on the prior knowledge of the teaching field, the key action video unit is a video frame or a video clip; the above-mentioned teaching auxiliary method also includes: receiving an operation request for multiple key action video units, the operation request includes: a screening request and / or a note request; in response to the operation request, performing corresponding operations on the multiple key action video units. In the implementation process of the above-mentioned scheme, by automatically decomposing the sports video into multiple key action video units, each unit represents a specific action or technical point, the user (such as a coach) can request to filter out specific key action video units, for example, only view all clips of a certain action, or only view the parts that need to be improved, and annotate the key points of the demonstration action and the improvement suggestions for the student's action for these specific key action video units, thereby improving the interactivity between students and coaches. Furthermore, students can selectively view and learn specific movements according to their needs and interests to improve the pertinence and efficiency of learning. At the same time, students can also add notes to key movement video units to record personal observations, improvement suggestions or other important information, thereby effectively improving student participation.

[0021] In an optional implementation of the first aspect, the body data includes: basic body data and data collected by wearable devices during exercise, and the teaching auxiliary information includes: exercise volume target; the teaching auxiliary information is determined based on the body data and prior knowledge in the teaching field, including: determining the completed exercise volume based on the data collected by the wearable device during exercise; determining the exercise volume target for the next stage based on the basic body data, the completed exercise volume and prior knowledge in the teaching field. In the implementation process of the above scheme, the exercise volume target for the next stage that best suits each student is recommended based on their specific physical conditions and the amount of exercise they have completed, thereby increasing the personalization of the exercise plan, and combined with the prior knowledge in the teaching field, the system can scientifically plan the amount of exercise, avoid overtraining or undertraining, and thus improve the overall training effect. Furthermore, by continuously monitoring and adjusting the exercise volume target, the system can help students gradually improve their athletic ability and training effect.

[0022] In an optional implementation of the first aspect, the physical data includes: information on the current sports test and / or sports competition; after obtaining the physical data, it also includes: storing the sports test and / or sports competition information in a sports growth archive. In the implementation process of the above scheme, a complete sports growth archive is formed by long-term storage of students' sports test and competition information, thereby helping students, parents and coaches understand the students' sports development at different stages. Furthermore, by analyzing the students' sports growth archives, the system can identify the students' strengths and weaknesses and provide personalized training suggestions.

[0023] In an optional implementation of the first aspect, prior knowledge in the teaching field includes: the school's historical admission score and the number of students enrolled; teaching auxiliary information is determined based on physical data and prior knowledge in the teaching field, including: determining the recommended schools to be applied for based on the level certificates, cultural scores, sports scores in sports project tests, sports specialties in sports competition information, school history admission score lines and enrollment numbers uploaded by student users. In the traditional volunteer filling scenario, the recommendation process for students to go to school or enter professional sports training mainly relies on the inquiries and on-site inquiries of parents and students themselves, and lacks a systematic evaluation and recommendation mechanism. In the implementation process of the above scheme, by determining the recommended schools to be applied for based on the level certificates, cultural scores, sports scores in sports project tests, sports specialties in sports competition information, school history admission score lines and enrollment numbers uploaded by student users, the gap in the lack of systematic and automated recommendation mechanisms in the prior art is filled, and the most suitable school for each student user is recommended, which effectively improves the personalization of the recommendation of the school to be applied for. Furthermore, based on the historical data of the school's historical admission scores and enrollment numbers and the specific circumstances of the current students (such as academic performance, physical education performance, grade certificates, and sports specialties, etc.), the system can provide more accurate school recommendations and improve the admission success rate.

[0024] In an optional implementation of the first aspect, after storing the sports event test and / or sports competition information in the sports growth archive, it also includes: extracting the student user's physical test result data, body shape data, physiological data, motion data and the completion status of exercise homework from the sports growth archive; determining the student user's quality ability value and development potential value based on the student user's physical test result data, body shape data, physiological data, motion data and the completion status of exercise homework.

[0025] In an optional implementation of the first aspect, after determining the quality and ability value and development potential value of the student user, it also includes: if the quality and ability value of the student user is greater than the preset quality threshold, and the development potential value of the student user is greater than the preset potential value, then send a permission request message for recommending talents to the student user or the guardian user of the student user. In the implementation process of the above scheme, a comprehensive and detailed evaluation can be carried out by comprehensively analyzing the students' physical test results, body shape, physiological data, exercise data and homework completion status, and based on multi-dimensional data, students with high quality and ability and development potential can be more accurately identified, thereby improving the accuracy of talent identification.

[0026] In an optional implementation of the first aspect, after determining the quality and ability value and development potential value of the student user, it also includes: visually displaying the quality and ability value and / or development potential value of the student user. In the implementation process of the above scheme, the visual display can help users quickly identify the performance trends of students in different time periods. For example, a line chart can clearly show the progress or regression of students over a period of time, so that students can better understand their strengths and weaknesses through the visual display, and thus see their progress and achievements in certain aspects, which can greatly motivate students to continue working hard. The positive feedback in the visual display can enhance students' self-confidence and learning motivation.

[0027] In an optional implementation of the first aspect, the quality, ability and / or development potential value of the student user is visualized, including: obtaining the quality, ability and / or development potential value of the student user at a first time point and the quality, ability and / or development potential value at a second time point, the first time point being different from the second time point; comparing and analyzing the quality, ability and / or development potential value at the first time point with the quality, ability and / or development potential value at the second time point to obtain a comparative analysis result, which is used for visual display. In the implementation of the above scheme, by comparing data at different time points, the changing trends of students' quality, ability and development potential can be clearly identified. At the same time, teachers, parents and students can also quickly understand the development trajectory of students through visual charts without having to read a large amount of data in detail, thereby effectively improving the efficiency of information transmission.

[0028] In an optional implementation of the first aspect, the quality ability value and / or development potential value of the student user is visualized, including: obtaining the average quality ability value of the group to which the student user belongs, and comparing and analyzing the quality ability value of the student user with the average quality ability value to obtain a comparative analysis result, which is used for visual display; and / or, obtaining the average development potential value of the group to which the student user belongs, and comparing and analyzing the development potential value of the student user with the average development potential value to obtain a comparative analysis result, which is used for visual display. In the implementation process of the above scheme, by comparing the quality ability value and / or development potential value data of the student with the average level, the current status of the student in terms of quality ability and / or development potential can be clearly identified. At the same time, teachers, parents and students can also quickly understand the development trajectory of students through visual charts without having to read a large amount of data in detail, thereby effectively improving the efficiency of information transmission.

[0029] In an optional implementation of the first aspect, after determining the quality and ability value and development potential value of the student user, it also includes: screening out candidate athletes from the student competition list whose quality and ability value difference with the quality and ability value of the student user is less than a first preset threshold; pairing the candidate athletes as competitors of the student user. In the implementation of the above scheme, by matching competitors with similar qualities and abilities, the participation and viewing of the competition can be ensured. By competing with opponents with similar qualities and abilities, students can discover their own shortcomings in each competition and gradually improve them. This continuous progress is conducive to the all-round development of students.

[0030] In an optional implementation of the first aspect, after determining the quality and ability value and development potential value of the student user, it also includes: screening out candidate athletes from the student competition list whose quality and ability value and the quality and ability value of the student user have a difference value less than a second preset threshold; sending partner invitation information to the candidate athletes, the partner invitation information is used to invite the candidate athletes to be the student user's competition partner. In the implementation process of the above scheme, through accurate quality and ability value comparison, it is possible to more effectively find a competition partner that matches the student user's ability, improve the overall competitiveness of the team, and because the partners have similar abilities, it is helpful to establish a more harmonious team collaboration relationship and improve the communication and collaboration efficiency within the team, thereby reducing the probability of re-matching partners due to unpleasant cooperation between partners, thereby improving the collaboration rate and success rate of event organization.

[0031] In an optional implementation of the first aspect, it also includes: counting the average quality and ability value of the first organization group and the average quality and ability value of the second organization group, the group identification of the first organization group is different from the group identification of the second organization group; judging whether the average quality and ability value of the first organization group and the average quality and ability value of the second organization group are less than a preset ability threshold; if so, pairing the first organization group as a competitor of the second organization group, and the first organization group and the second organization group are both class representative teams or school representative teams. In the implementation process of the above scheme, by pairing organization groups with similar average quality and ability values, the participation and viewing of the competition can be ensured, which allows each team to have the opportunity to demonstrate their abilities and progress under relatively equal conditions, thereby reducing the probability of re-matching due to conflicts between organization groups due to excessive differences in abilities, thereby improving the matching efficiency of organization groups.

[0032] In an optional implementation of the first aspect, it also includes: for each school participating in the school-level league, a school team is selected from multiple class teams of the school; and / or, for each region participating in the district-level league, a district team is selected from multiple school teams in the region; and / or, for each province participating in the provincial league, a provincial team is selected from multiple district teams in the province. In the implementation of the above scheme, by adopting this layer-by-layer screening method to form teams of different levels, it is ensured that the teams of each level are selected through competition. In order to represent the class, school or region in the competition, students will have a stronger motivation to improve their skills and performance, thereby increasing the enthusiasm of students to participate in the league.

[0033] In an optional implementation method of the first aspect, it also includes: receiving a query request sent by a terminal device, the query request includes: the student identification being queried; querying the user role type logged in on the terminal device from the user database; if the user role type logged in on the terminal device is a class teacher type, then sending the physiological data, body shape data, motion data, completion status of exercise homework, sports project test and / or sports game information corresponding to the student identification to the terminal device; if the user role type logged in on the terminal device is a coach type, then sending the motion data, motion homework, completion status of exercise homework, sports project test and / or sports game information corresponding to the student identification to the terminal device; if the user role type logged in on the terminal device is a parent type, then sending the motion data, motion homework, completion status of exercise homework, sports project test and / or sports game information corresponding to the student identification to the terminal device; if the user role type logged in on the terminal device is a school representative type, then sending the motion data, motion homework, completion status of exercise homework, sports project test and / or sports game information corresponding to the student identification to the terminal device. In the implementation of the above solution, data access rights are controlled according to the user's role type (such as class teacher, coach, parent or school representative, etc.), and different functions are provided for different roles to ensure that sensitive information is only visible to authorized personnel, thereby realizing refined data management functions. Through strict permission management, students' privacy and data security can be effectively protected, unauthorized access can be prevented, and data security is effectively improved.

[0034] In an optional implementation method of the first aspect, it also includes: receiving a query request sent by a terminal device, the query request includes: the group identifier being queried; if the user role type logged in to the terminal device is a class teacher type, then sending the physiological data, exercise data, completion status of exercise homework, sports project tests and / or sports competition information of all students in the class corresponding to the group identifier to the terminal device; if the user role type logged in to the terminal device is a coach type, then sending the physiological data, exercise data, exercise homework, completion status of exercise homework, sports project tests and / or sports competition information of all students in the class corresponding to the group identifier to the terminal device; if the user role type logged in to the terminal device is a parent type, then sending the average exercise data, average completion status of exercise homework, sports project tests and / or sports competition information corresponding to the group identifier to the terminal device; if the user role type logged in to the terminal device is a school representative type, then sending the sports compliance rate, qualified proportion of posture data, qualified proportion of physical health status and / or qualified proportion of psychological data indicators of all students in the school corresponding to the group identifier to the terminal device. In the process of implementing the above solution, the most relevant and useful data is provided according to the user's role type (such as class teacher, coach, parent or school representative, etc.), thereby improving the practicality and utilization efficiency of information. Since users with different roles only need to view data related to their responsibilities, information overload and redundancy are avoided.

[0035] In the second aspect, an embodiment of the present application provides a teaching assistance system, including: an intelligent monitoring device and a server, the intelligent monitoring device is communicatively connected to the server; the intelligent monitoring device is used to collect body data; the server is used to determine teaching assistance information based on the body data and prior knowledge in the teaching field.

[0036] In an optional implementation of the second aspect, the intelligent monitoring device includes: a photoelectric sensor, an electrode sensor and / or a piezoelectric film PVDF sensor, which is used to collect physiological data.

[0037] In an optional implementation of the second aspect, the intelligent monitoring device includes: a flexible sweat sensor for collecting potassium ion concentration and sodium ion concentration.

[0038] In an optional implementation of the second aspect, the intelligent monitoring device includes: a flexible pressure sensor, a tension sensor and / or a piezoelectric film PVDF sensor, which is used to collect mechanical data.

[0039] In an optional implementation of the second aspect, the server includes: a business logic server for receiving and classifying physical data; and / or a data processing server for determining teaching auxiliary information based on physical data and prior knowledge in the teaching field; and / or a data storage server for storing data content such as physical data, auxiliary teaching lesson plans and / or videos.

[0040] In an optional implementation of the second aspect, the teaching auxiliary system further includes: a terminal device; an application program APP software running on the terminal device, and / or a mini program running on the APP software.

[0041] In a third aspect, an embodiment of the present application provides a teaching auxiliary device, applied to a server, comprising: a body data acquisition module, used to acquire body data, the body data including data collected by sensors; an auxiliary information determination module, used to determine teaching auxiliary information based on body data and prior knowledge in the teaching field.

[0042] In a fourth aspect, an embodiment of the present application provides a server, including: a processor and a memory, the memory storing machine-readable instructions executable by the processor, and the machine-readable instructions executing the method described above when executed by the processor.

[0043] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described above is executed.

[0044] In a sixth aspect, an embodiment of the present application provides a computer program product, including: a computer program or a computer instruction, which executes the method described above when the computer program or the computer instruction is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 A schematic diagram showing a flow chart of a teaching assistance method provided in an embodiment of the present application is shown;

[0047] Figure 2 A schematic diagram showing a visualization of the quality and capability values ​​provided in an embodiment of the present application is shown;

[0048] Figure 3 A schematic diagram of the structure of the teaching assistance system provided by an embodiment of the present application is shown;

[0049] Figure 4 A schematic diagram of the structure of a teaching auxiliary device provided in an embodiment of the present application is shown;

[0050] Figure 5A schematic diagram of the structure of a server provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0051] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. It should be understood that the drawings in the embodiment of the present application only serve the purpose of explanation and description, and are not used to limit the protection scope of the embodiment of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in the embodiment of the present application shows the operation implemented according to some embodiments of the embodiment of the present application. It should be understood that the operation of the flowchart can be implemented out of order, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the embodiment of the present application, or remove one or more operations from the flowchart.

[0052] It is understandable that the "first" and "second" in the embodiments of the present application are used to distinguish similar objects. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity and execution order, and the words "first" and "second" do not necessarily limit the difference. In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that there may be three relationships, such as A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship. The term "multiple" refers to more than two (including two), and similarly, "multiple groups" refers to more than two groups (including two groups).

[0053] It should be noted that the teaching assistance method provided in the embodiment of the present application can be executed by a server, and the above-mentioned server refers to a virtual device that provides services by a cluster composed of many server nodes, or a physical device that provides computing services through a network. Among them, the above-mentioned virtual devices are, for example: cloud servers of Elastic Compute Service (ECS), virtual servers that provide ECS services using virtualization technology (such as XEN, KVM, HyperV or VMware), or virtual machines running in a server cluster, etc. The servers of the above-mentioned physical devices are, for example: x86 servers and non-x86 servers, and non-x86 servers include: mainframes, minicomputers and UNIX servers.

[0054] See also Figure 1 The flowchart of the teaching assistance method provided by the embodiment of the present application is shown; the embodiment of the present application provides a teaching assistance method, including:

[0055] Step S100: Acquire body data, where the body data includes data collected by sensors.

[0056] Physical data refers to data related to the human body, which can be data collected by sensors during human movement (such as physical education courses and / or activity practice courses) and / or non-movement processes (such as cultural courses or art courses), or data that has been collected by sensors, such as basic physical data such as height and weight in physical examination reports or medical examination report data, etc. The above-mentioned sensors can be sensors set on wearable devices, such as piezoelectric film PVDF sensors for monitoring blood pressure and pulse or global positioning system (Global Positioning System, GPS) sensors for positioning, or sensors set in learning environments or sports environments, such as cameras for capturing and analyzing students' action videos, or pressure pads placed on the ground, in which piezoelectric film PVDF sensors can also be provided to measure the force distribution and gait pattern of footsteps contacting the ground. It should be noted that the process implemented in the embodiment of the present application is collected in strict compliance with relevant laws, regulations and ethical norms, and with the consent of the student himself or the guardian. The role of collecting physical data in the embodiment of the present application is to enhance the training effect that the student himself or the guardian wants to achieve in the field of teaching.

[0057] The implementation methods of the above-mentioned step S100 include: a first implementation method, when the sensor sends the collected data directly to the server, the server at this time can directly receive the data collected by the sensor through the application programming interface (Application Programming Interface, API); a second implementation method, when the server has received the data collected by the sensor, the sensor data can be directly read from the hard disk or memory; a third implementation method, the data collected by the sensor can be temporarily or permanently stored on a third-party server (such as a server of a cooperative company) or a third-party cluster, such as an object storage service (Object Storage Service, OSS) cluster, and the body data can be directly obtained from the OSS of the third-party server or the third-party cluster.

[0058] Step S200: Determine teaching auxiliary information based on body data and prior knowledge of the teaching field.

[0059] Prior knowledge in the teaching field refers to the professional experience knowledge that has been established in the field of physical exercise teaching. This experience knowledge is based on the research results of multiple disciplines such as education, exercise physiology, cognitive neurology and / or psychology that have been analyzed on long-term accumulated physical data. The above-mentioned prior knowledge in the teaching field can specifically include two types of knowledge: expert rule knowledge and domain knowledge of artificial intelligence (AI) models. Expert rule knowledge is a clear guiding principle summarized through the experience and research results accumulated by sports coaches, sports scientists and experts in related fields over the years. This type of knowledge can be stored by experts in the form of rules or guidelines (such as the principle of progressive overload, the principle of individual differences and avoiding overtraining, etc.), and then written into server-running code by programmers based on the content of the rules or guidelines. The domain knowledge of the AI ​​model is a knowledge system generated after training a large amount of historical physical data and / or other data based on artificial intelligence (AI) algorithms (such as deep learning models or generative AI models), which can be specifically reflected as parameters of the AI ​​model. The domain knowledge of this AI model can be learned by a pre-trained large model during the fine-tuning process, or it can be a vectorized representation stored in a vector database or knowledge vector library.

[0060] Teaching assistance information refers to status information or result information used to assist teaching, and may specifically include: physical status information used to assist in determining teaching effectiveness, and learning guidance information used to assist in personalized teaching. The above-mentioned physical status information includes, for example, physical health status, fatigue level and / or recovery time, etc.; the above-mentioned learning guidance information includes, for example, after-class recovery recommendation information, after-class homework recommendation information, exercise course recommendation information, course recommendation information, teaching intervention plan, evaluation results of exercise homework videos, action correction suggestions in videos, key action video units, exercise volume goals, rehabilitation Chinese medicine packages, nutritious diet recipes and / or schools that can be applied for, etc.

[0061] It is understandable that the above implementation method for determining teaching auxiliary information can be determined based on the type, quantity, installation location and / or specific application scenario of the sensor, as well as the type, quantity, usage method and / or application scenario of prior knowledge in the teaching field. Of course, the above implementation method for determining teaching auxiliary information can also be determined not only based on sensor data, but also based on other body data (such as basic body data, uploaded sports videos, sports project tests and / or sports competition information, etc.), and can also be determined in combination with data collected by sensors and other body data. Therefore, there are also many implementation methods for determining teaching auxiliary information, such as: obtaining teaching auxiliary information based on expert rule-based knowledge mapping and calculating teaching auxiliary information based on AI models (such as generative pre-trained large language models, multimodal models, and image classification models, etc.), etc., which are described below by way of example.

[0062] In the implementation process of the above scheme, by combining the real-time physical data collected by sensors during exercise and prior knowledge in the teaching field, teaching suggestions such as teaching auxiliary information can be generated for each student user. Moreover, since the physical data is the data collected by sensors in real time during exercise, the real-time nature of the physical data used in physical education is effectively guaranteed. High personalization requires more dimensional data and more complex algorithm models, resulting in more processing time, which will affect the real-time response of the system. However, better real-time performance requires less data and simpler algorithm models, but it is difficult to meet the needs of more personalized information. Therefore, by combining the real-time physical data collected by sensors and introducing "prior knowledge in the teaching field", a balanced choice can be made between the needs of high personalization and the needs of better real-time performance, so that the balance between personalization and real-time performance of physical education can be effectively taken into account.

[0063] As an optional implementation of the above method, the above body data may include: basic body data and data collected by wearable devices during exercise, and the teaching auxiliary information may include: fatigue level and / or recovery time; the above implementation method of determining the teaching auxiliary information based on body data and prior knowledge in the teaching field may include:

[0064] Step S201: Determine the fatigue degree and / or recovery time according to basic body data, data collected by wearable devices and prior knowledge in the teaching field.

[0065] Wearable devices refer to devices that can be worn on the human body and are equipped with sensors for collecting data, such as smart bracelets, smart watches, shoes with smart monitoring insoles, smart helmets or smart hats, etc. The data collected by the above wearable devices may include: (1) Wearable devices can be equipped with physiological sensors, which can monitor students' vital signs in real time, including heart rate data, respiratory rate, body temperature, blood pressure data and blood oxygen saturation, etc.; (2) Wearable devices can also be equipped with motion sensors, which can detect students' exercise volume, such as steps, acceleration, angle, etc. These data are helpful for analyzing students' activity volume and exercise intensity; (3) Wearable devices can also be equipped with bioinformatics sensors, which can detect students' skin electrical activity, brain wave information, heart rate variability, etc.

[0066] Basic physical data refers to basic physical examination data in the physical examination report, such as height, weight, blood pressure, joint flexibility, body mass index (BMI), pH value, etc., and functional data in hospital test items. This basic physical data can be the indicator data filled in online by students or coaches and uploaded to the server, or it can be the basic data in the physical examination report sent to the server synchronously by the cooperative hospital or cooperative physical examination institution.

[0067] There are many types of data collected by the above-mentioned wearable devices, such as smart watches, smart bracelets, EMG sensors and other devices collecting heart rate, HRV value, electromyography signal, accelerometer data, etc., and some sweat biomarker data, such sweat biomarker data includes: electrolyte (sodium, potassium, magnesium) ion concentration, pH value and / or lactic acid, etc.

[0068] The implementation method of the above step S201 is, for example: on the one hand, it can be analyzed and determined from the expert rule-type knowledge in the prior knowledge of the teaching field, and the fatigue degree and / or recovery time in the teaching auxiliary information can be determined according to the basic body data (such as heart rate data), the data collected by the wearable device (such as electromyography EMG signal) and the prior knowledge of the teaching field (for example, the higher the heart rate variability HRV value analyzed from the heart rate data, and the more the EMG signal amplitude value decreases, the more fatigued the muscle is). Assume that the fatigue degree is divided into several levels: if the HRV value is less than the variability threshold (such as 0.5ms), and the EMG signal amplitude value is higher than the amplitude threshold (such as 10μV), it is determined to be the first level of fatigue, and / or the recommended recovery time is 24 hours. If the HRV value is less than the variability threshold, and the EMG signal amplitude value is lower than the amplitude threshold, it is determined to be the second level of fatigue, and / or the recommended recovery time is 48 hours. If the HRV value is greater than the variability threshold and the EMG signal amplitude value is lower than the amplitude threshold, it is determined to be level 3 fatigue, and / or the recommended recovery time is 72 hours. On the other hand, the domain knowledge of AI models such as multi-classification models can be used to determine the degree of fatigue, for example, the output layer in the deep neural network (DNN) is replaced with a Softmax layer, and the heart rate variability HRV value obtained by analyzing the data collected by the above wearable device (such as electromyography EMG signals) and heart rate data is used to determine the level of the above fatigue levels and / or the recovery time.

[0069] As an optional implementation of the above method, the above body data may also include: sweat biomarker parameters collected by a wearable device, and the teaching auxiliary information includes: physical health status; the above implementation method of determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field may include:

[0070] Step S202: determining the health status of the body according to the sweat biomarker parameters and prior knowledge in the teaching field.

[0071] Among them, sweat biomarker parameters are biomarker data in sweat collected through wearable devices or portable sweat sensors, which may include but are not limited to: electrolyte (sodium, potassium, magnesium) ion concentration, pH value and / or lactic acid, etc.

[0072] In some embodiments of step S202, on the one hand, some physical health conditions of students can be determined by analyzing biomarker parameters in sweat and combining prior knowledge in the teaching field. Among them, the expert rule-based knowledge in the above-mentioned prior knowledge in the teaching field is, for example: if the sodium ion concentration in sweat is lower than the normal range (e.g., 130mmol / L), and the potassium ion concentration is higher than the normal range (e.g., 5.0mmol / L), the physical health state can be determined as electrolyte imbalance, and it is recommended to supplement an appropriate amount of electrolyte solution. For another example: if the lactic acid concentration in sweat is higher than a threshold value (e.g., 8mmol / L), the physical health state can be determined as the accumulation of metabolites after high-intensity exercise, and it is recommended to increase the rest time to promote recovery.

[0073] In some embodiments of step S202, on the other hand, a multi-classification model such as an AI model can be used to determine the degree of fatigue, for example, the output layer in the deep neural network (DNN) is replaced with a Softmax layer, and the collected sweat biomarker parameters are standardized, and then divided into a training set, a validation set, and a test set, and the DNN is trained to obtain a trained DNN. Finally, the DNN is used to predict the health status of the body based on the sweat biomarker parameters (sodium potassium ion concentration and / or lactic acid), for example: the sweat biomarker parameters collected in real time are input into the trained DNN model, the probability of each health indicator category is output, and the category with the highest probability is selected as the final health status in the teaching auxiliary information.

[0074] There are many other implementation methods for combining the above steps S201 and S202. The above implementation methods for determining teaching auxiliary information based on body data and prior knowledge in the teaching field include the following:

[0075] In a first implementation, the physical health status, fatigue level and / or recovery time in the teaching auxiliary information are determined based on basic physical data, sweat biomarker parameters collected by wearable devices and prior knowledge in the teaching field.

[0076] A second implementation method is to determine the fatigue degree and / or recovery time in the teaching auxiliary information based on basic body data, sweat biomarker parameters collected by wearable devices and prior knowledge in the teaching field, and determine the physical health status based on the fatigue degree and / or recovery time.

[0077] A third implementation method is to determine the fatigue level and / or recovery time in the teaching auxiliary information based on the basic body data, sweat biomarker parameters collected by wearable devices, and prior knowledge in the teaching field, and determine the physical health status in the teaching auxiliary information based on the basic body data, sweat biomarker parameters, prior knowledge in the teaching field, the fatigue level and / or recovery time.

[0078] A fourth implementation method is to determine the physical health status in the teaching auxiliary information based on the basic body data, sweat biomarker parameters collected by the wearable device and prior knowledge in the teaching field, and to determine the fatigue degree and / or recovery time in the teaching auxiliary information based on the physical health status, basic body data, sweat biomarker parameters collected by the wearable device and prior knowledge in the teaching field.

[0079] Since there are many combination implementations of step S201 and step S202, they are not listed here one by one, and the combination implementation of step S201 and step S202 is similar to the implementation of step S201 and step S202 above. Therefore, its combination implementation can refer to the implementation of step S201 and step S202 above, and will not be repeated here.

[0080] As an optional implementation of the above method, the above body data may include: data collected by a wearable device during exercise, and the teaching auxiliary information includes: after-class recovery recommendation information; the above implementation method of determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field may include:

[0081] Step S203: determining after-class recovery recommendation information in the teaching auxiliary information according to the data collected by the wearable device, the sports course information and the prior knowledge in the teaching field, wherein the after-class recovery recommendation information includes: stretching action recommendation information, medicine package recommendation information and / or dietary recommendation information.

[0082] The above-mentioned sports course information is sports-related course information, including: course type, training type, intensity, duration and / or specific sports parts, etc. Among them, course types include: football class, basketball class, track and field class, and different after-class recovery recommendation information can be recommended according to different course types. For example, training types include: aerobic training, anaerobic training, strength training, flexibility training and / or speed training, etc., and different after-class recovery recommendation information can also be recommended according to different training types.

[0083] In some implementations of step S203, it is possible to analyze and determine from the expert rule knowledge in the prior knowledge of the teaching field, and by analyzing the data collected by the wearable device, the sports course information, and combining the prior knowledge in the teaching field, the recommended information for students' after-class recovery can be determined. The above-mentioned expert rule knowledge includes stretching action recommendation information, medicine package recommendation information and / or dietary recommendation information, wherein the expert rule knowledge of stretching action recommendation information includes: if it is determined based on the data collected by the wearable device and the sports course information that high-intensity strength training (such as squats and deadlifts) has been performed, it is recommended to perform static stretching of the legs and back, and each action is maintained for 20-30 seconds; if it is determined based on the data collected by the wearable device and the sports course information that a long-term aerobic training (such as long-distance running) has been performed, it is recommended to perform full-body dynamic stretching, and each action is repeated 10-15 times. Expert rule-based knowledge of medicine package recommendation information includes: If the HRV value is low and the lactate concentration is high according to the data collected by the wearable device, it is recommended to use a recovery medicine package containing electrolytes and vitamin C to promote the removal of metabolites; if the muscle fatigue level is high (such as a large decrease in the amplitude value of the EMG signal) according to the data collected by the wearable device, it is recommended to use a recovery medicine package containing amino acids and proteins to promote muscle repair. Expert rule-based knowledge of dietary recommendation information includes: If high-intensity training is determined according to the data collected by the wearable device, it is recommended to consume high-protein foods (such as chicken breast, fish) and carbohydrates (such as oats, rice) to replenish energy and repair muscles; if long-term aerobic training is determined according to the data collected by the wearable device, it is recommended to consume foods rich in antioxidants (such as blueberries and broccoli) to reduce oxidative stress.

[0084] In some other embodiments of step S203, a pre-trained large language model (e.g., ChatGPT) can be used to determine after-class recovery recommendation information based on data collected by wearable devices (e.g., heart rate, HRV value, electromyography signal, accelerometer data collected by devices such as smart watches, smart bracelets, EMG sensors, etc.), sports course information, and prior knowledge in the teaching field. Specifically, the wearable device data, sports course information, and prior knowledge in the teaching field are integrated and organized into a text description in JSON format, and then, an executable program written in a programming language is used to convert the text description in JSON format into a natural language text, and the natural language text converted according to the above-mentioned input is input into a prompt template (Prompt Template) to obtain a prompt engineering text (Prompt Engineering Text), and finally the prompt engineering text is input into a pre-trained large language model (e.g., ChatGPT) to obtain after-class recovery recommendation information. Among them, the above-mentioned after-class recovery recommendation information can be a search expression, and then the search expression is used to retrieve the stretching action recommendation information, medicine package recommendation information, and / or dietary recommendation information to be recommended in the recommendation database. Of course, you can also directly use the fine-tuned pre-trained large language model to recommend stretching exercise recommendations, medicine package recommendations, and / or dietary recommendations. In this case, you do not search the recommendation database, but directly send the model output content.

[0085] In some other embodiments of step S203, the after-class recovery recommendation information to be recommended can also be determined in combination with the course type and / or training type in the above-mentioned sports course information. For example, the corresponding after-class recovery recommendation information is filtered out in the recommendation information database according to the course type and / or training type in the above-mentioned sports course information, wherein the course types include: football class, basketball class, track and field class, and the training types include: aerobic training, anaerobic training, strength training, flexibility training and / or speed training, etc.

[0086] In some other embodiments of step S203, the amount of exercise can be determined first according to the data collected by the wearable device, and then the recommended after-class recovery recommendation information to be recommended can be determined according to different amounts of exercise, for example: by using wearable devices such as smart watches, chest straps, EMG sensors, etc., to collect wearable device data such as heart rate, HRV value, electromyography signal, accelerometer data, etc., combined with course type (such as football class, basketball class, track and field class), training type (such as aerobic training or anaerobic training), intensity, duration, specific sports parts and other sports course information, the corresponding after-class recovery recommendation information can be screened out from the recommendation information database. Specifically, the above different data can be weighted to calculate the amount of exercise, for example: the time of football class and the time of track and field class are weighted to calculate the total amount of exercise, and a threshold range is set for different amounts of exercise to distinguish between light exercise, moderate exercise and heavy exercise. Assuming that the total amount of exercise belongs to moderate exercise, the whole body stretching action recommendation information including static stretching of the posterior leg muscle group, calf muscle, anterior thigh muscle group, back and shoulder can be pushed.

[0087] In some other implementations of step S203, the after-class recovery recommendation information to be recommended can also be determined in combination with the above-mentioned specific sports parts, for example: the corresponding after-class recovery recommendation information is filtered out in the recommendation information database according to the specific sports parts. Among them, the above-mentioned specific sports parts can be determined based on the data collected by the wearable device. For example, the student is located at the table tennis court through GPS, which means that the specific sports parts of the student are concentrated in the arm part. Of course, the above-mentioned specific sports parts can also be determined based on the sports course information. For example, if it is found in the sports course information table that a student should train in the morning is a football class, then the legs and feet can be determined as the specific sports parts to be recommended. For example, if it is found in the sports course information table of a student in the morning that the teaching point to be taught is the hand movements of the basketball class, then the hands can be determined as the specific sports parts to be recommended.

[0088] As an optional implementation of the above method, the above body data may include: data collected by a wearable device during exercise, and the above teaching auxiliary information may also include: after-class homework recommendation information; the above implementation method of determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field may include:

[0089] Step S203a: Determine homework recommendation information in the teaching auxiliary information according to the data collected by the wearable device, the sports course information and the prior knowledge of the teaching field.

[0090] Among them, the above-mentioned homework recommendation information is the training content recommended for the student's sports performance in sports class, and the form of the homework recommendation information can be video, picture, audio and / or text. It is understandable that the above-mentioned sports performance is different according to different sports course types (such as basketball, table tennis, badminton or swimming, etc.), and can be sports intensity, reaction speed, sports posture, explosive power and / or physical endurance, etc. Here, basketball is used as an example for explanation, and the above-mentioned sports performance can include: dribbling skills, positioning skills, dunking posture, shooting skills and / or shooting hit rate, etc., specifically for example: according to the performance of a student in sports class, specifically, the shooting hit rate in basketball class is 60%, which is lower than the class average, and the dribbling skills are higher than the class average, the physical fitness is very strong and the teamwork ability is outstanding. In this case, the shooting skills and other training contents can be specifically recommended to the student as homework recommendation information. The shooting accuracy can be calculated by using computer vision analysis technology (such as target recognition, image classification or video classification technology to determine whether the shot is successful), or by using traditional sensor technology (such as installing infrared sensors in the basket). The above homework recommendation information can be understood as auxiliary content that needs to be enhanced after class for problems found in sports class.

[0091] As an optional implementation of the above method, the above body data may include: data collected by a wearable device during the teaching process; the above implementation of determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field may include:

[0092] Step S203b: Determine the learning status in the learning activity based on the data collected by the wearable device and prior knowledge in the teaching field; determine the target time when the learning status is not good, and determine the target content from the teaching audio / video based on the target time.

[0093] Among them, the above target content is the content that individual students need targeted tutoring; the teaching audio / video is obtained by recording the teacher's teaching process.

[0094] The implementation method of the above step S203b is, for example: using the state analysis model trained by prior knowledge in the teaching field and data collected by wearable devices (such as physiological data and / or biochemical data), analyzing the data collected by the wearable devices, thereby obtaining the learning state of students in learning activities (such as emotional state and / or concentration). It can be understood that since the above state analysis model is obtained by training using prior knowledge in the teaching field and data collected by wearable devices, the state analysis model can learn characteristic patterns related to the learning state. For example, in emotion recognition and concentration judgment, the state analysis model constructed using a neural network can analyze physiological signals such as heart rate, skin conductance, and brain waves, thereby inferring the student's emotional state and concentration level and other learning states.

[0095] Optionally, in the above analysis to obtain the learning state, a statistical analysis method can also be used to analyze the data (such as physiological data and / or biochemical data) collected by the wearable device, so as to obtain the learning state of the student in the learning activity. For example, the physiological data collected by the above wearable device can be analyzed to determine the learning state of the student in the learning activity. This process may include: (1) extracting the heart rate characteristics in the learning activity from the heart rate data; the heart rate characteristics include the heart rate statistics, heart rate change rate, heart rate variability and / or heart rate spectrum characteristics within the course time corresponding to the learning activity. (2) According to the heart rate characteristics and the pre-trained state analysis model, the learning state in the learning activity is obtained, which can be specifically input into the above-trained state analysis model, and the learning state in the learning activity is output through the model. The above-mentioned learning state includes emotional state or concentration. The state analysis model can be obtained by training based on the sample heart rate characteristics, or it can be obtained by training based on the sample heart rate data and the sample derivative data.

[0096] Among them, the above-mentioned heart rate statistics may include average heart rate, maximum heart rate or minimum heart rate. The average heart rate value reflects the overall heart rate level of the student during the entire course time; the maximum heart rate reflects the maximum load of the student during the course time; the minimum heart rate may occur during the activity interval or rest period. The heart rate change rate includes the heart rate rise rate or the heart rate fall rate. For example, the heart rate rise rate is obtained by calculating the increase in heart rate from one moment to another and dividing it by the time interval. The heart rate fall rate is obtained by calculating the decrease in heart rate from a peak moment to a subsequent moment and dividing it by the time interval. Heart rate variability includes heart rate standard deviation or heart rate variability index. For example, the standard deviation of heart rate data is calculated, and the heart rate standard deviation reflects the degree of fluctuation of heart rate at different time points. A larger standard deviation indicates a higher heart rate variability, which may mean that the student's heart is more adaptable to activities or there are larger physiological fluctuations. The heart rate variability index is calculated by more complex algorithms (such as time series analysis, frequency domain analysis, etc.) to more accurately quantify the volatility and stability of heart rate. The heart rate spectrum feature refers to the spectrum analysis of heart rate data to decompose the heart rate signal into the superposition of different frequency components. By analyzing the distribution and intensity of these frequency components, the heart rate spectrum characteristics can be extracted.

[0097] Optionally, the teaching assistance software system can also use a trained state analysis model to analyze the student's attention state based on the data collected by the wearable device, and recommend the above target content as key content during the time period when the student's attention is concentrated, so as to help students better absorb and understand the knowledge points in the above target content.

[0098] In the process of implementing the above scheme, according to the time period when the student's learning status is not good, the system can extract the teaching content that the student needs targeted tutoring from the teaching audio / video, and use it as targeted tutoring materials for the student. This effectively improves the student's participation in the teaching process and the personalization of targeted tutoring.

[0099] As an optional implementation of the above method, the above body data may also include: basic body data, data collected by wearable devices during exercise, and the above teaching auxiliary information may also include: sports course recommendation information; the above implementation method of determining teaching auxiliary information based on body data and prior knowledge in the teaching field may include:

[0100] Step S204: determining the athletic ability index according to the basic body data and the data collected by the wearable device.

[0101] Athletic ability indicators are data indicators that reflect human athletic ability, including: muscle strength, explosive power and / or endurance, etc. Muscle strength can be determined by electromyography signal data collected by wearable devices, and of course it can also be roughly determined by a simple grip strength test. Similarly, explosive power can be determined by short-distance running speed (such as a 50-meter sprint) collected by a lightweight wearable device, or by the vertical jump height collected by a sensor camera. Similarly, endurance can be determined by long-distance running results (such as 10 kilometers) collected by lightweight wearable devices, or it can be evaluated by recovery after long-term exercise (such as heart rate recovery rate).

[0102] Some implementation methods of the above step S204 are as follows: assuming that the students' athletic ability indicators are classified into elementary, intermediate and advanced levels, and the basic physical data of a certain student is intermediate (i.e., the indicators are all within the normal range), then, by obtaining the sprint speed collected by the lightweight wearable device through a 50-meter sprint test, it can be determined that the student's explosive power is at an intermediate level, and by obtaining the long-distance running results collected by the lightweight wearable device through a 10-kilometer running test, it can be determined that the endurance is at an advanced level. The specific determination method can be analyzed and determined using expert rule-based knowledge in the prior knowledge of the teaching field, or it can be determined using an AI model such as a multi-classification model, for example: replacing the output layer in the deep neural network (DNN) with a Softmax layer, and using the above multi-classification model to classify the data and basic physical data of a certain student collected by the wearable device during exercise to obtain the student's athletic ability indicators.

[0103] Step S205: determining the sports course recommendation information in the teaching auxiliary information according to the sports ability index and the prior knowledge of the teaching field.

[0104] For example, the implementation method of the above step S205 is as follows: if a student's explosive athletic ability index is at a medium level, combined with the prior knowledge in the teaching field, it can be determined that explosive power-enhancing training should be pushed to the student, such as box jumps and fast weightlifting, 3-4 times a week; if the student's explosive athletic ability index is at an elementary level, combined with the prior knowledge in the teaching field, it can be determined that basic explosive training should be pushed to the student, such as jumping exercises, 2-3 times a week; if the student's explosive athletic ability index is at an advanced level, combined with the prior knowledge in the teaching field, it can be determined that speed training or strength training should be pushed to the student, or professional-level explosive training, such as Olympic weightlifting, 4-5 times a week, can continue to be pushed to the student. Similarly, the above-mentioned muscle strength and / or endurance athletic ability index and the prior knowledge in the teaching field determine the sports course recommendation information in the teaching auxiliary information, which is also a similar implementation method, so it will not be repeated.

[0105] As an optional implementation of the above method, the above body data may include: basic body data, data collected by wearable devices during exercise; the above implementation of determining teaching auxiliary information based on body data and prior knowledge in the teaching field may include:

[0106] Step S206: determining the athletic ability index according to the basic body data and the data collected by the wearable device.

[0107] The implementation of step S206 is the same as the implementation of step S204 above. If there is any unclear point in the implementation of step S206, please refer to the implementation of step S204 above.

[0108] Step S207: Determine the psychological data index during exercise based on the data collected by the wearable device.

[0109] Psychological data indicators refer to psychological data indicators of the human body during exercise, which may include: learning status and / or stress level, etc.; among which, the learning status may include the emotional state (such as a happy state) or concentration during the learning activity, etc.

[0110] Some implementation methods of the above step S207, for example, are as follows: Taking the psychological data indicator of determining the learning state as an example, the physiological data collected by the wearable device can be analyzed to obtain the emotional state or concentration of the students in the learning activities. The above-mentioned method of analyzing the physiological data includes: using a trained state analysis model for analysis or using a statistical analysis method for analysis. Among them, the state analysis model can identify the characteristic patterns related to the learning state by learning a large amount of physiological data. For example, in emotion recognition and concentration judgment, the state analysis model constructed using a neural network can analyze physiological signals such as heart rate, skin conductance, brain waves, etc., so as to infer the students' emotional state and concentration and other learning states.

[0111] The above-mentioned statistical analysis methods, such as descriptive statistics, variance analysis, correlation analysis, and regression analysis, can quantitatively describe physiological data, compare the differences in physiological indicators under different learning states, explore the relationship between physiological data and learning states, and predict the changing trend of physiological data under different learning states. Taking emotional state as an example, changes in heart rate can reflect the student's tension or excitement. In positive emotions, the heart rate may rise slightly; while in anxiety or fear, the heart rate may increase significantly. Therefore, the student's emotional state and emotional changes can be determined by calculating the change in heart rate data, which can be used as a learning state. Heart rate variability refers to the change in the heartbeat interval, which can reflect the activity of the autonomic nervous system. High HRV usually indicates a state of relaxation and recovery, while low HRV may reflect a state of tension or stress. High HRV may indicate that students remain calm and focused when studying, while low HRV may indicate stress, fatigue, or distraction.

[0112] Some other implementations of the above step S207 are, for example: in some scenarios, a student has tried several courses, but he is not sure which sports courses he likes, or because the student is too young, the words he expresses are not clear enough, and he expresses that he likes course A, but according to the data collected by the wearable device, the student actually likes course B more than course A. Or in other scenarios, because the student is too young, the words he expresses are not clear enough, and he expresses that he likes course A, and he may really like course A, but the coach analyzes the data collected by the wearable device and finds that the student is more suitable for course B and not for course A. In these scenarios, the emotional state in the above psychological data indicators is determined based on the heart rate, body temperature, accelerometer and other data collected by the wearable device, and the stress level in the above psychological data indicators is determined based on the HRV value, galvanic skin response (GSR) and other data collected by the wearable device.

[0113] Step S208: determining the sports course recommendation information in the teaching auxiliary information according to the sports ability index, the psychological data index and the prior knowledge of the teaching field.

[0114] Some implementations of the above step S208 are as follows: Here, the psychological data indicator of learning state is still used as an example for explanation. After determining the learning state, the sports course recommendation information can be determined according to the sports ability indicator, the learning state and the prior knowledge of the teaching field. The above prior knowledge of the teaching field is as follows: if the learning state is the emotional state of the student, the emotional state of the student is good, and the sports ability indicator exceeds the average level of the students in the class, then the student has a high degree of acceptance of the sports project, which means that the sports project is more effective and the training effect of the student is more significant. At this time, the sports course in the sports course database with a similarity greater than the preset threshold value to the sports course can be used as the sports course recommendation information to be recommended, and the sports course recommendation information is sent to the terminal device of the student to improve the training effect of the student for the related projects of similar sports courses. On the contrary, if the student's emotional state is not good, then the student may not have a good training effect on the sports project, and may need to reflect on and improve the sports project. At this time, the sports course in the sports course database with a similarity less than the preset threshold value to the sports course can be used as the sports course recommendation information to be recommended, and the sports course recommendation information is sent to the terminal device of the student to find the sports project with a more effective training effect for the student, thereby quickly improving the efficiency of the training effect.

[0115] In some implementations of step S208, in combination with the athletic ability index in step S204 and the psychological data index in step S207, and by utilizing the prior knowledge in the teaching field, a more personalized and scientific sports course recommendation can be formulated for the student, and the sports course recommendation information here is one of the information in the teaching auxiliary information. For example, in some scenarios, a student participated in several basic test activities, all of which included exercises of different body parts, and the student himself could not determine which sports activities he liked, or, because the student was too young to express his meaning, he expressed that he liked activity A, but according to the data collected by the wearable device, the student actually liked activity B more than activity A. Or in other scenarios, because the student was too young to express his meaning, he expressed that he liked activity A, and he might really like activity A, but the coach analyzed the data collected by the wearable device and found that the student was not suitable for activity A, but more suitable for activity B. In these scenarios, the sports course recommendation information related to activity A and activity B can be pushed alternately at the same time, rather than just pushing the sports course recommendation information related to activity A.

[0116] As an optional implementation of the above-mentioned teaching auxiliary method, the above-mentioned basic physical data may include poor physical information, which refers to the existence of certain basic diseases in the body itself, resulting in poor basic physical constitution, making it unsuitable for certain sports, for example: the presence of scoliosis makes it unsuitable for high-impact sports, long-term fixed-position sports and asymmetric sports, etc. Among them, high-impact sports may put too much pressure on the spine, such as football, basketball, volleyball and high jump, etc., long-term fixed-position sports may aggravate scoliosis, such as cycling, rowing, etc., and asymmetric sports such as tennis, baseball pitching, etc. may cause uneven development on both sides of the spine.

[0117] The sports course recommendation information in the above-mentioned teaching auxiliary information is information about sports courses that are targeted at improving poor physical conditions. Specifically, for the above-mentioned scoliosis situation, sports course recommendation information that can improve this poor physical condition can be recommended, such as: corrective symmetry training sports courses, flexibility training courses, and posture correction training courses, etc. Among them, the corrective symmetry training sports course is a symmetrical exercise selected or designed to help restore symmetrical strength to balance muscle development, such as breaststroke or freestyle. Flexibility training is to reduce muscle tension and stiffness through stretching and flexibility exercises, especially for the muscles on one side of the scoliosis. The posture correction training course is to teach the correct sitting, standing and sleeping postures to reduce the probability of worsening scoliosis.

[0118] For the case of flat feet, sports course recommendation information that can improve such flat feet can be recommended. For example: the condition of flat feet makes it unsuitable for long-distance running, the high-impact sports mentioned above, and barefoot sports, such as long-distance running or marathons, which require long-term use of the feet. For the case of flat feet, sports course recommendation information that can improve this physical condition can be recommended, such as: muscle strengthening exercise courses (such as foot flexion and extension, picking up small objects, arch lifting, etc.), flexibility training courses (such as stretching exercises, increasing the range of motion of the foot, etc.) and functional training courses (such as jumping, quick turns, etc.), etc.

[0119] In addition to information about sports courses that are targeted to improve poor physical condition, the sports course recommendation information in the above-mentioned teaching auxiliary information can also be targeted nutritional dietary information to improve poor physical condition. That is to say, the above-mentioned sports course recommendation information is information about sports courses that are targeted to improve poor physical condition, and / or, targeted nutritional dietary information to improve poor physical condition. For example: suppose that a student's basic physical data shows that the student has some poor physical information, including: a body mass index (BMI) of 28, which is overweight; high blood lipid levels, and there is a risk of cardiovascular disease; low bone density, and there is a risk of osteoporosis. Due to the high BMI, in order to help the student lose weight, in addition to pushing sports course recommendation information such as aerobic exercise plans, nutritional dietary information for low-fat diets can also be recommended, such as: reducing the intake of fried foods and high-fat meats, and increasing foods rich in unsaturated fatty acids, such as fish, nuts and olive oil.

[0120] As an optional implementation of the above teaching assistance method, the above body data may also include: data collected by a wearable device, and the above teaching assistance information may also include: course recommendation information; the above implementation of determining the teaching assistance information based on body data and prior knowledge in the teaching field may also include:

[0121] Step S208a: Obtain the evaluation result of the student user, and determine the pleasure state score of the student user based on the data collected by the wearable device.

[0122] Among them, the above-mentioned evaluation results characterize the emotional and intellectual state of the student user, such as emotional evaluation scores and / or intelligence evaluation scores. The above-mentioned emotional evaluation scores can be evaluated by real-time monitoring of students' emotional states in cultural courses or art courses through technologies such as facial expression recognition and voice analysis, and of course, they can also be evaluated through questionnaires. Correspondingly, the intelligence evaluation score can be evaluated through questionnaires, or the score obtained after manual evaluation can be filled in the teaching auxiliary software system.

[0123] Step S208b: Determine course recommendation information based on the evaluation results and the pleasure status score.

[0124] It is understandable that in the specific practice process, the course recommendation information can also be determined by combining physical data (such as heart rate, exercise intensity, etc.), evaluation results and pleasure status scores. The teaching auxiliary software system running in the server can have a more comprehensive understanding of the overall situation of the students, making the course recommendation more accurate and better meeting the needs of the students. In addition, the teaching auxiliary software system running in the server can also be dynamically adjusted according to the performance and status of the students in different time periods.

[0125] As an optional implementation of the above step S208a, the above evaluation results include: emotion evaluation scores and / or intelligence evaluation scores; the above implementation of obtaining the evaluation results of the student user may include:

[0126] Step S208c: The server receives a question answering request sent by the student user via the terminal device, where the question answering request includes: an age parameter of the student user.

[0127] It is understandable that the age parameter of the student user is set in the answer request, so that suitable test questions can be selected according to students of different age groups, ensuring that the assessment content matches the students' cognitive level and development stage, which makes the assessment results more accurate and meaningful.

[0128] Step S208d: Searching for test questions corresponding to the age parameter in the social adaptability question library and / or the behavioral activity question library.

[0129] Furthermore, by designing different test questions for different age groups, the teaching assistance software system can more accurately capture the emotional and intellectual characteristics of students at a specific stage of development, thereby providing more targeted teaching suggestions.

[0130] Step S208e: The server sends the test questions corresponding to the age parameters to the terminal device, so that the student user can complete and return the test answers corresponding to the test questions.

[0131] It is understandable that the way of sending test questions and receiving answers through terminal devices increases the user's interactivity and participation, and students will feel more engaged and interesting in the process of completing the test. The teaching auxiliary software system can provide test results and feedback instantly, so that students can immediately understand their performance. This instant feedback mechanism can increase students' enthusiasm and motivation to learn.

[0132] Step S208f: Evaluate the emotion assessment score and intelligence assessment score of the student user according to the test answers corresponding to the test questions.

[0133] Optionally, after evaluating the student user's emotion assessment score and intelligence assessment score, the teaching assistance software system can also record the student's test results (such as emotion assessment scores and intelligence assessment scores) at different time points, and generate long-term development trend reports, which will help teachers and parents understand the student's emotional and intellectual development changes, identify potential problems in a timely manner and take corresponding measures. In addition, based on the emotion assessment score, the system can provide mental health advice and support. For example, for students with low moods, the system can recommend mindfulness meditation or emotion regulation techniques. Of course, the system can also combine the physical data, emotion assessment scores, intelligence assessment scores, and pleasure state scores collected by wearable devices to conduct multi-dimensional data analysis and provide a more comprehensive student health and development report.

[0134] As an optional implementation of the above step S208a, determining the pleasure state score of the student user according to the data collected by the wearable device includes:

[0135] Step S208g: Determine the emotional state of the student user during multiple attendances at a preset type of course based on data collected by the wearable device.

[0136] It is understandable that by using wearable devices to monitor students' emotional states in different courses in real time to provide a continuous data stream, the teaching assistance software system can capture students' immediate reactions in specific courses, thereby making a more accurate assessment of their emotional states. In addition, by using data collected by wearable devices to determine the emotional state when taking courses, the teaching assistance software system can assess the emotional state based on objective physiological indicators (such as heart rate, skin conductance, etc.), reducing the subjective bias of human determination of emotions.

[0137] Step S208h: Determine the student user's score of pleasure for a preset type of course based on the proportion of times the student user's emotional states are characterized as pleasure among the multiple times of participation.

[0138] Among them, the preset type courses include: at least one of cultural courses, sports courses, art courses and practical courses.

[0139] After determining the student user's pleasure score for a preset type of course, the teaching assistance software system can recommend the most suitable course type for them based on the student's pleasure score. For example, if the student's pleasure score in sports courses is high, the system can recommend more related sports courses. In addition, the system can dynamically adjust according to the student's performance and emotional state in different time periods. For example, if the system detects that the student's pleasure state in a certain type of course is continuously low, it can suggest that the teacher adjust the teaching method or content to increase the student's interest and participation.

[0140] As an optional implementation of the above teaching assistance method, the above body data may include: data collected by a wearable device; and the implementation of determining the teaching assistance information based on the body data and prior knowledge in the teaching field may include:

[0141] Step S208i: Determine the emotional state of the student user within a preset time period based on the data collected by the wearable device.

[0142] An implementation of the above step S208i is, for example: using a state analysis model trained with prior knowledge in the teaching field and data collected by wearable devices (such as physiological data and / or biochemical data), analyzing the data collected by the wearable devices, thereby obtaining the emotional state of the student user within a preset time period. It can be understood that since the above state analysis model is trained using prior knowledge in the teaching field and data collected by wearable devices, the state analysis model can learn characteristic patterns related to the learning state. For example, in emotion recognition and concentration judgment, the state analysis model constructed using a neural network can analyze physiological signals such as heart rate, skin conductance, and brain waves, thereby inferring the emotional state of the student.

[0143] Another implementation of the above step S208i is as follows: in the process of analyzing and obtaining the emotional state above, a statistical analysis method can also be used to analyze the data collected by the wearable device (such as physiological data and / or biochemical data), so as to obtain the emotional state of the student user within a preset time period. Specifically, it includes: (1) extracting heart rate features within the learning activity from the heart rate data; the heart rate features include heart rate statistics, heart rate change rate, heart rate variability and / or heart rate spectrum features within the course time corresponding to the learning activity. (2) According to the heart rate features and a pre-trained state analysis model, the emotional state of the student user within a preset time period is obtained. The specific implementation method is similar to the implementation method of the above step S203b, so it will not be repeated here.

[0144] After determining the emotional state of the student user within a preset time period, the teaching assistance software system can also provide mental health advice and support based on the emotional state data. For example, for students with large emotional fluctuations, the system can recommend mindfulness meditation or emotional regulation techniques. Furthermore, the system can identify the emotional changes of students in different courses through data collected by wearable devices, and recommend corresponding emotional management courses or activities. For example, if the student's state of pleasure in cultural courses is low, the system can recommend relaxation training or psychological counseling.

[0145] Step S208j: Determine the score of the student user's pleasure state within the preset time period according to the proportion of the number of times the emotional state is characterized as a pleasure state within the preset time period.

[0146] An example of an implementation of the above step S208i is: assuming that emotional states can be divided into several categories, such as "happy", "calm", "anxious", "depressed", etc., and the preset time period is four classes in a day, and the emotional states in the four classes are "happy", "calm", "depressed" and "happy", then it is obvious that the number of times the happy state occurs in this day accounts for 50%. If it is a percentage system, then it can be determined that the student user's happiness state score for this day is 50 points.

[0147] In addition, the teaching assistance software system can also provide rewards and incentives based on the student's happiness score. For example, for students who are happy within a preset time period, points or badges can be given to increase their enthusiasm and participation. Furthermore, the system can also recommend some interesting course content and gamification elements to students who are not so happy within the preset time period to make the learning process more interesting and attractive. For example, the system can recommend teamwork games or challenges to increase students' participation and interest. The above preset time period can include: the day, week or month.

[0148] As an optional implementation of the above method, the above body data may also include: data collected by wearable devices during teaching, and the teaching auxiliary information includes: teaching intervention plan; the above implementation method of determining the teaching auxiliary information based on body data and prior knowledge in the teaching field may include:

[0149] Step S209: Determine a psychological data index curve based on the data collected by the wearable device.

[0150] The implementation method of the above step S209 is, for example: using wearable devices (such as smart watches, health trackers, etc.) to monitor students' physiological data in real time, such as heart rate, skin conductance, respiratory rate, activity level, etc., and cleaning and preprocessing the collected data to remove noise and outliers, and obtain preprocessed data to ensure the accuracy and reliability of the data. Then, using data analysis techniques such as time series analysis and statistical analysis, psychological data indicators such as heart rate variability (HRV) and stress level are extracted from the preprocessed data, and the changes of the extracted psychological data indicators over time are plotted into psychological data indicator curves to facilitate the observation and analysis of the trend of changes in students' psychological states.

[0151] Step S210: Determine the teaching intervention plan in the teaching auxiliary information according to the psychological data indicator curve and prior knowledge in the teaching field.

[0152] The implementation method of the above step S210 is, for example: using a machine learning algorithm (such as a time series analysis algorithm) to analyze the changes in the student's psychological data index curve, it is possible to identify changes in the student's psychological state, such as anxiety, lack of concentration, overexcitement, etc. Then, using the prior knowledge in teaching fields such as pedagogy and psychology, the changes in the psychological data index curve are analyzed, so as to determine whether the student needs dynamic teaching intervention or static teaching intervention based on the analysis results. Among them, specific intervention measures include: adjusting teaching content, changing teaching methods, providing psychological support, etc., to help students improve their psychological state. Finally, the formulated teaching intervention plan can also be put into practice, the intervention effect can be monitored, and adjustments can be made according to actual conditions. Moreover, after a period of intervention, the psychological data index curve can be re-collected to evaluate the effect of the intervention plan.

[0153] The above-mentioned dynamic teaching intervention plan is a teaching adjustment based on real-time monitoring of students' emotional states (such as depression, confusion, etc.). By analyzing the psychological curves of students during the learning process, the system can timely detect students' negative emotions and take corresponding intervention measures to help students adjust their mentality and better complete learning tasks. For example, a specific dynamic teaching intervention process: suppose a student is studying a sports course or a cultural course. The system has stored an emotion recognition algorithm, which can capture students' facial expressions and voice analysis through a camera to evaluate their emotional state. In a certain class, the system detects that the student shows obvious confusion and frustration, such as frowning and confused eyes. At this time, the system can send an encouraging message to the student, such as: "It looks like you have encountered some difficulties, don't worry, we will solve it together!" In addition, the difficulty of the current task can be automatically adjusted (for example, reducing the training volume of sports courses or the difficulty of exercises in cultural courses, etc.), providing simpler questions or step-by-step guided problem-solving steps to help students rebuild their confidence. After the student completes the current simpler question, the system gives a small reward, such as points, badges or virtual items, to enhance the student's enthusiasm. Through these intervention measures, students can adjust their mindsets in a timely manner, continue to study in a better mental state, and improve their learning efficiency and quality.

[0154] The above-mentioned static teaching intervention plan does not rely on real-time emotion monitoring, but is based on a fixed reward mechanism after students complete specific course goals. It aims to motivate students to continue learning and achieve set goals by setting clear goals and rewards. For example, a specific static teaching intervention process is as follows: suppose a student sets several key goals in a semester study plan. After the key goals (such as the amount of training in each chapter or each stage) are completed, the system will give a pre-set number of points or badges. Each time the key goal reaches a certain score, the system will unlock new learning resources or virtual items. Actively participate in discussions and answer questions in class to get additional points or rewards. In addition, some side quests can be set. When students complete these side quests, the system will automatically issue corresponding rewards, such as virtual items or privileges that can be exchanged in the system and displayed in the honor wall to increase the sense of achievement. In this way, students can get immediate positive feedback after completing each small goal, thereby maintaining their motivation and interest in learning.

[0155] In addition, the above-mentioned dynamic teaching intervention plan and static teaching intervention plan can be combined to generate a more comprehensive teaching intervention plan, which can achieve more comprehensive and effective teaching support. This comprehensive plan can not only respond to students' emotional changes in real time, but also motivate students to continue learning through a fixed reward mechanism. A specific comprehensive teaching intervention plan is as follows: suppose a student encounters difficulties in the learning process, and the system detects his low mood through emotion recognition technology. The system immediately initiates dynamic intervention measures, such as reducing the difficulty of the current task, sending encouraging messages, etc. At the same time, the system also sets up a static reward mechanism. Even if the difficulty of the task is reduced, the corresponding points or badges can still be obtained after completing the task. For each major goal (such as a unit of learning), the system will issue a larger reward, such as unlocking advanced functions or obtaining special badges. Through this combined approach, students can not only get timely support and encouragement when they encounter difficulties, but also get continuous positive feedback after completing each small goal, so as to maintain a positive learning attitude and motivation.

[0156] As an optional implementation of the above method, the above body data may also include: sports homework videos uploaded by student users, and the teaching auxiliary information includes: evaluation results of the sports homework videos; the above implementation method of determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field may include:

[0157] Step S211: identifying key action video units from the sports operation video, where the key action video units are video frames or video clips.

[0158] An implementation example of the above step S211 is: assuming that the sports homework video uploaded by the student user is a basketball sports homework video, the student asks others to record and upload the basketball sports homework video to the server through a mobile phone or a camera. The server can automatically perform preprocessing operations such as format conversion and resolution adjustment on the uploaded video to obtain a preprocessed video, and then use the action recognition algorithm in computer vision and machine learning (such as convolutional neural network CNN, recurrent neural network RNN, etc.) to identify key action video units from the preprocessed video. The key action video units are video frames or video clips, such as: the posture of holding the ball to prepare for shooting (video frame), the action process of jumping and shooting (video clip), the moment when the basketball leaves the hand (video frame), etc.

[0159] Another implementation of the above-mentioned step S211 is, for example: using a human posture estimation algorithm (such as OpenPose, AlphaPose or HRNet, etc.) to extract human key points from the sports work video, using an optimization algorithm (such as the SMPL model) to calibrate the key points to obtain more accurate key point positions, and identifying key action video units from the sports work video based on the more accurate key point positions. For example, if the density between the key point positions in at least one video frame is greater than a density threshold, then at least one video frame is determined as a video frame or video clip in the key action video unit.

[0160] Step S212: Analyze the key action video units according to the prior knowledge in the teaching field, and determine the evaluation results of the sports homework videos in the teaching auxiliary information, the evaluation results including whether they are qualified and / or action correction and improvement suggestions.

[0161] An implementation method of the above step S212 is, for example: the above-mentioned prior knowledge in the teaching field can also include the teaching standard specification of basketball shooting. In the scene of the basketball sports homework video, the identified key action video unit can also be analyzed in detail according to the teaching standard specification of basketball shooting in the prior knowledge in the teaching field. The content of the analysis can include shooting posture, arm force method, accuracy, fluency, strength and skills of shooting action, etc., to obtain the analysis result. Then, according to the analysis result, it is determined whether the student's shooting action meets the qualified standard. For example, if the student's shooting posture is correct, the strength is moderate, and the shooting is accurate, it can be determined to be qualified, otherwise, it can be determined to be non-compliant. In addition, specific action correction and improvement suggestions can be proposed for unqualified or action correction and improvement. If the student's arm force is incorrect when shooting, the improvement suggestion can include the specific way to adjust the arm posture and the specific force method of taking off and shooting. Guidance suggestions; for example: the student's arm is not straight enough when shooting, it is recommended to strengthen arm strength training before shooting, and ensure that the arm is fully straight when shooting.

[0162] Another implementation of the above step S212 is, for example: the above teaching field prior knowledge may include: target detection model, image segmentation model, image classification model and / or latent space knowledge of pre-trained large language model. Specifically, the target detection model (such as YOLO, SSD and Faster R-CNN, etc.) may be used to detect at least one video frame in the key action video unit, and then the image segmentation model may perform semantic segmentation on the detected human body to obtain the segmented foreground area image and background area image containing the human body. Then, the image classification model may be used to predict the evaluation result of the foreground area image containing the human body, so as to obtain the evaluation result of the sports operation video, and the evaluation result may include whether the image category is qualified, and / or, a pre-trained large language model or a multimodal model may be used to generate action correction improvement suggestions based on the above evaluation results, the foreground area image containing the human body and the background area image.

[0163] As an optional implementation of the above method, the prior knowledge in the teaching field may also include: standard action videos, and the teaching auxiliary information may include: action correction and improvement suggestions; the above implementation of determining the evaluation results of the sports homework video may include:

[0164] Step S213: extracting key points of the human body from the sports task video.

[0165] An implementation example of the above step S213 is: a student completes a badminton swing, and asks others to record a video using a smartphone or camera, and uploads the video to a server after the recording is completed. The server can use a convolutional neural network (CNN) combined with a human posture estimation algorithm (such as OpenPose, AlphaPose or HRNet, etc.) to extract human key points from the sports operation video, including wrists, elbows, shoulders, waist, knees and ankles, etc. Optionally, an optimization algorithm (such as the SMPL model) can also be used to calibrate the key points to obtain more accurate human key points.

[0166] Step S214: Compare the key points of the human body with the key points in the standard action video to obtain a comparison result.

[0167] The implementation method of the above step S214 is, for example: comparing the key points of the human body with the key points in the standard action video (such as a pre-recorded standard badminton swing action video) in the prior knowledge of the teaching field to obtain a comparison result; wherein the annotated action video includes: key point data of the standard action. Specifically, the key point data extracted from the student video and the key point data of the standard action can be aligned in time series to obtain aligned key video frames; then, the differences between the aligned key video frames in the two videos are analyzed, and the differences between the aligned key video frames are determined as the comparison results, where the comparison results include, for example, the position, angle, and motion trajectory of the key points.

[0168] Step S215: Generate action correction and improvement suggestions in the teaching auxiliary information based on the comparison results.

[0169] An implementation method of the above step S215 is, for example, to input a prompt template according to the comparison results of the position, angle, and motion trajectory of the key points to obtain a prompt engineering text, for example: "The comparison results show that the student's wrist was not correctly bent during the swing, resulting in insufficient swing force". Then, the prompt engineering text is input into the pre-trained large language model so that the pre-trained large language model generates action correction and improvement suggestion content in the teaching auxiliary information, and the action correction and improvement suggestion content is, for example: "When swinging, please note that the wrist should be kept bent to increase the speed and power of the racket face. Please refer to the swing demonstration at 3 minutes and 20 seconds in the standard action video."

[0170] Alternatively, another optional implementation of the above-mentioned teaching assistance method can use a multimodal model to directly generate action correction and improvement suggestions for the sports homework video without comparing the key points in the standard action video. This implementation, for example, directly inputs the sports homework video and the problem content uploaded by the student into the multimodal model (for example, using a Vision Transformer model, a model developed based on contrastive language image pre-training CLIP, etc.), so that the multimodal model generates action correction and improvement suggestions for the sports homework video based on the sports homework video and the problem content uploaded by the student.

[0171] As an optional implementation of the above method, the above body data may also include sports videos; the above implementation of determining teaching auxiliary information based on body data and prior knowledge in the teaching field may include:

[0172] Step S216: Decompose the motion video into a plurality of key action video units according to prior knowledge in the teaching field, where the key action video units are video frames or video clips.

[0173] For example, the above-mentioned prior knowledge in the teaching field may include: the action conversion features of each sport (such as swimming, specifically butterfly stroke) for dividing or decomposing the uploaded sports video. The sports video uploaded by (students or coaches) may be decomposed into multiple key action video units according to the action conversion features of the key points of butterfly stroke in the prior knowledge in the teaching field, and the key action video units are video frames or video clips such as entering the water, pulling the water, pushing the water and exiting the water.

[0174] The implementation method of the above teaching auxiliary method, after decomposing the sports video into a plurality of key action video units, may further include:

[0175] Step S217: receiving operation requests for multiple key action video units, the operation requests including: screening requests and / or remark requests.

[0176] Step S218: In response to the operation request, corresponding operations are performed on multiple key action video units.

[0177] In some implementations of the above-mentioned steps S217 and S218, the above-mentioned teaching auxiliary information may also include: teaching materials made by the coach based on the key action video units in the video uploaded by the coach. Such teaching materials may be made based on the sports video uploaded by the coach himself, and the specific production process includes: the server first decomposes the sports video uploaded by the coach himself into multiple key action video units based on the prior knowledge of the teaching field, and then sends the video frames or video clips in the multiple key action video units to the coach's terminal device. After the coach sees multiple video frames or video clips on his terminal device, he finds that some video frames or video clips are not required for making teaching materials, and can filter multiple video frames or video clips. Therefore, the coach's terminal device sends a screening request to the server, and the screening request includes deleting useless video unit identifiers and / or selecting useful video unit identifiers. Wherein, the video unit identifier (ID) is a field used to uniquely identify the key action video unit, which can be implemented using a universally unique identifier (Universally Unique Identifier, UUID), or using a snowflake algorithm (Snowflake Algorithm) to generate the video unit identifier. The server can respond to the screening operation request and delete multiple key action video units according to the video unit identifier in the screening request, or perform operations such as retaining marks on multiple key action video units according to the video unit identifier in the screening request. Similarly, after the coach sees multiple video frames and / or video clips on his terminal device, he finds that some video frames and / or video clips need remark content, so that the remark content, video frames and / or video clips can be made into teaching materials. At this time, the coach's terminal device sends a remark request to the server, and the remark request includes the video unit identifier to be remarked and the remark content. The server can respond to the remark operation request and correspondingly associate the remark content, video frame and / or video clip to save. In addition, similarly, after receiving the production request, the server can generate teaching materials according to the remark content, video frame and / or video clip (for example, fill the remark content, video frame and / or video clip into the teaching template selected in advance by the coach), and return the teaching materials to the coach's terminal device.

[0178] In other embodiments of the above-mentioned steps S217 and S218, the above-mentioned teaching auxiliary information may also include: the comment material made by the coach according to the key action video unit in the video uploaded by the student. This comment material can be made by the coach for the sports video uploaded by the student, and its specific production process includes: the server first decomposes the sports video uploaded by the student into multiple key action video units according to the prior knowledge of the teaching field, and then sends the video frames or video clips in the multiple key action video units to the terminal device of the coach. After the coach sees multiple video frames or video clips in his terminal device, he finds that some actions are not standard and needs to comment on them so that the comment content, video frame and / or video clip are made into comment material. Therefore, at this time, the terminal device of the coach sends a comment and note request to the server, and the comment and note request includes the video unit identification to be commented and the comment and note content. The server can respond to the comment and note operation request and correspondingly associate and save the comment and note content, video frame and / or video clip. In addition, similarly, after receiving the completion request, the server can generate review materials based on the review notes, video frames and / or video clips (for example, filling the review content, video frames and / or video clips into the review template selected in advance by the coach), and return the review materials to the coach's terminal device, and / or, return them to the student's uploading device.

[0179] As an optional implementation of the above method, the above body data may include: basic body data and data collected by wearable devices during exercise, and the above teaching auxiliary information may also include: exercise volume target; the above implementation method of determining the teaching auxiliary information based on the body data and prior knowledge in the teaching field may include:

[0180] Step S219: Determine the amount of exercise completed based on the data collected by the wearable device during the exercise.

[0181] The data collected by the wearable device during the above-mentioned exercise process may be data collected from students while they are exercising during class, or data collected from students while they are doing their exercise homework after class.

[0182] In some implementations of step S219, the student's wearable device (such as a smart bracelet) can monitor and collect data during exercise and upload it to the server, and the server analyzes and calculates the data collected by the wearable device to calculate the amount of exercise completed by the student in this stage of exercise homework. For example, the server will calculate the student's average heart rate of 150 beats / minute, the exercise duration of 30 minutes, and the consumption of about 300 calories based on the data monitored and collected by the wearable device (such as a smart bracelet).

[0183] Step S220: Determine the exercise target for the next stage based on basic physical data, completed exercise volume, and prior knowledge in the teaching field.

[0184] In some embodiments of step S220, classification can be performed first based on basic physical data and completed exercise volume, and then the exercise volume target for the next stage corresponding to the classification result is determined according to prior knowledge in the teaching field. For example, if the basic physical data is lower than the data average and the completed exercise volume is also lower than the exercise volume average, the classification result of this stage is determined as primary, and the exercise volume target for the next stage corresponding to the primary stage is determined according to prior knowledge in the teaching field to be primary aerobic training (for example, increasing the number of steps to 3,000 steps, 4 times a week, 20-45 minutes each time) and primary strength training (for example, using light weight equipment for exercise, 2-3 times a week), etc. If the basic physical data is higher than the data average and the completed exercise volume is lower than the exercise volume average, the classification result of this stage is determined as intermediate, or if the basic physical data is lower than the data average and the completed exercise volume is higher than the exercise volume average, the classification result of this stage is determined as intermediate, and the exercise volume target of the next stage corresponding to the intermediate is determined according to the prior knowledge of the teaching field to be intermediate aerobic training (for example, increasing the number of steps to 6,000, 5 times a week, 30-50 minutes each time) and intermediate strength training (for example, using medium weight equipment for exercise, 3-4 times a week), etc. If the basic physical data is higher than the data average and the completed exercise volume is higher than the exercise volume average, the classification result of this stage is determined as advanced, and the exercise volume target of the next stage corresponding to the advanced is determined according to the prior knowledge of the teaching field to be advanced aerobic training (for example, increasing the number of steps to 9,000, 6 times a week, 60-80 minutes each time) and advanced strength training (for example, using heavy weight equipment for exercise, 4-5 times a week), etc. Among them, the implementation method of determining the exercise volume target for the next stage based on the prior knowledge in the teaching field is, for example: basic body data, completed exercise volume, classification results and prior knowledge in the teaching field are integrated and organized into a text description in JSON format, and then, an executable program written in a programming language is used to convert the text description in JSON format into natural language text, and the natural language text converted above is input into a prompt template to obtain a prompt engineering text, and finally the prompt engineering text is input into a pre-trained large language model (such as ChatGPT) to obtain the exercise volume target for the next stage.

[0185] As an optional implementation of the above method, the above physical data may also include: information about the sports test and / or sports competition currently participated in; after obtaining the physical data, it also includes:

[0186] Step S221: storing the sports event test and / or sports competition information in the sports growth archive.

[0187] In some implementations of step S221, all sports test and / or sports competition information that students have participated in since childhood can be stored in a sports growth archive, where the sports growth archive can use a relational database such as MySQL, PostgreSQL, Microsoft SQL Server or Oracle, or a NoSQL database such as MongoDB, Cassandra or Redis. Of course, in the specific implementation process, a hybrid database (such as Firebase real-time database) can also be used, which combines the advantages of a relational database and a NoSQL database, and is therefore called a hybrid database, also known as a globally distributed database.

[0188] As an optional implementation of the above method, the prior knowledge in the teaching field includes: the school's historical admission score and the number of students enrolled; the auxiliary teaching information is determined based on the physical data and the prior knowledge in the teaching field, including:

[0189] Step S222: Determine the schools to be recommended for application based on the grade certificates, academic performance, sports performance in sports tests, sports specialties in sports competition information, school historical admission scores and number of admissions uploaded by the student user.

[0190] Among them, the level certificates uploaded by student users include: sports level certificates (also known as sports technical level certificates) and / or athlete level certificates. That is to say, the level certificates uploaded by student users can be sports level certificates (such as level certifications for coaches and referees), athlete level certificates issued based on performance and technical level in specific sports, or sports level certificates and athlete level certificates.

[0191] In some embodiments of step S222, the prior knowledge of the teaching field learned in a pre-trained large language model (e.g., ChatGPT) can be used to determine the recommended schools in the teaching auxiliary information based on the level certificates (e.g., sports level certificates and / or athlete level certificates) uploaded by the student users, cultural performance, sports performance in sports tests, athlete level certificates, sports specialties in sports competition information, school historical admission scores and enrollment numbers. Specifically, the grade certificates (such as sports grade certificates and / or athlete grade certificates), cultural achievements (such as test scores in Chinese, mathematics, English, etc.), sports scores in sports project tests (such as specific scores in track and field, basketball, football, etc.), athlete grade certificates (such as national grade certificates), sports specialties in sports competition information (such as awards and personal bests, etc.), school historical admission scores (such as the admission scores of School A and School B in the past few years) and enrollment numbers (such as the annual enrollment plan numbers of School A and School B) uploaded by student users are integrated together and organized into a text description in JSON format. Then, an executable program written in a programming language is used to convert the text description in JSON format into natural language text, and the natural language text converted above is input into a prompt template (Prompt Template) to obtain a prompt engineering text (Prompt Engineering Text). Finally, the prompt engineering text is input into a pre-trained large language model (such as ChatGPT) to obtain the recommended schools for application in the teaching auxiliary information.

[0192] As an optional implementation of the above method, after storing the sports test and / or sports competition information in the sports growth archive, the following may also be included:

[0193] Step S223: extracting the student user's physical test result data, body shape data, physiological data, exercise data and completion status of exercise homework from the physical growth archive.

[0194] An implementation method of the above-mentioned step S223 is, for example: using SQL language or other database query languages ​​to extract the student user's physical test results data, body shape data, physiological data, exercise data, completion status of exercise homework, and other data from the sports growth archive. After querying these data, relevant data can also be obtained through the application programming interface API.

[0195] Step S224: Determine the quality ability value and development potential value of the student user based on the student user's physical test result data, body shape data, physiological data, exercise data and completion status of exercise homework.

[0196] The implementation method of the above step S224 is, for example: after obtaining the relevant data of the student user's physical test result data, posture data, physiological data, exercise data and the completion of the exercise homework through the API interface, the physical test result data, posture data, physiological data, exercise data and the completion of the exercise homework can also be scored respectively to obtain the scores of each item each year, including: physical test result data, posture score, physiological score, exercise score and the completion score of the exercise homework. Use the formula y1=w1×p+w2×b+w3×d+w4×s+w5×c to estimate the quality and ability of the physical test result score, posture score, physiological score, exercise score and the completion score of the exercise homework each year to obtain the quality and ability value. Among them, y1 represents the quality ability value, p represents the score of the physical test result, w1 represents the weight corresponding to the physical test result score, b represents the body shape score, w2 represents the weight corresponding to the body shape score, d represents the physiological score, w3 represents the weight corresponding to the physiological score, s represents the exercise score, w4 represents the weight corresponding to the exercise score, c represents the completion score of the exercise homework, and w5 represents the weight corresponding to the completion score of the exercise homework. In addition, the annual improvement trend can be analyzed based on the physical test result score, body shape score, physiological score, exercise score and the completion score of the exercise homework, and the development potential value of the student user can be determined based on the annual improvement trend. Specifically, using the formula y2=(p ′ +b′+d′+s′+c′) / h calculates the change trend of the physical test result score, posture score, physiological score, exercise score and the completion score of the exercise homework to obtain the development potential value of the student user. Among them, y2 represents the development potential value of the student user, p ′ represents the trend of the physical test results, b′ represents the trend of the posture score, d′ represents the trend of the physiological score, s′ represents the trend of the exercise score, and c′ represents the trend of the completion score of the exercise homework. The coefficient of the considered dimension that represents the development potential value.

[0197] As an optional implementation of the above teaching auxiliary method, after determining the quality, ability and development potential value of the student user, it also includes:

[0198] Step S224a: If the quality and ability value of the student user is greater than the preset quality threshold, and the development potential value of the student user is greater than the preset potential value, a permission request message for recommending talents is sent to the student user or the guardian user of the student user.

[0199] An implementation example of the above step S224a is: assuming that the quality and ability threshold is 85, and the development potential threshold is 80, if the student's quality and ability value (for example, 91) is greater than the preset quality threshold (i.e., 85), and the development potential value (for example, 86) is greater than the preset potential threshold (i.e., 80), the recommendation condition is met, and the server can send a permission request information for recommending talents to the student user or the guardian user of the student user.

[0200] It is understandable that the main purpose of the above steps S223 to S224a is to evaluate the quality, ability and development potential of student users by comprehensively analyzing the students' physical test results, body shape data, physiological data, exercise data and the completion of exercise homework, and send permission request information for recommended talents to students or their guardians when certain conditions are met. Specifically, the quality, ability and development potential of students are comprehensively evaluated through multi-dimensional data, and permission request information for recommended talents is sent to students or their guardians based on the quality, ability and development potential, informing them that the students have the potential to become excellent athletes, and seeking their consent for further talent training plans. In addition, personalized training and development suggestions can be provided to students based on their development situation, and long-term development plans and goal setting can be provided based on the students' development trends to support students' continuous progress and help them achieve better results in their sports careers.

[0201] See also Figure 2 A schematic diagram of a visualization display of the quality and ability values ​​provided by an embodiment of the present application is shown; as an optional implementation of the above teaching auxiliary method, after determining the quality and ability values ​​and development potential values ​​of the student user, it also includes:

[0202] Step S225: Visually display the quality ability value and / or development potential value of the student user.

[0203] It can be understood that there are many ways to display visualization. It can be displayed according to the type of display chart, for example: radar chart, bar chart, pie chart or line chart, etc.; it can also be displayed according to the time dimension, for example: comparative analysis of quality ability values ​​and / or development potential values ​​at different time points; it can also be displayed according to the student dimension, for example: comparative analysis of the current student's quality ability value and / or development potential value with the average level of the student's class; it can also be displayed according to the regional dimension, for example: comparative analysis of the current student's quality ability value and / or development potential value with the average level of the student's province (or other provinces).

[0204] It is understandable that through charts, graphs and other visualization tools, students, parents and teachers can more intuitively understand students' qualities, abilities and development potential. This intuitive display makes complex data easy to understand. In addition, visual display can help users quickly identify the performance trends of students in different time periods. For example, a line chart can clearly show the progress or regression of students over a period of time.

[0205] As an optional implementation of the above step S225, the above implementation of visually displaying the quality ability value and / or development potential value of the student user may include:

[0206] Step S225a: Obtain the quality and ability value and / or development potential value of the student user at a first time point and the quality and ability value and / or development potential value at a second time point, where the first time point is different from the second time point.

[0207] It is understandable that by comparing data at different time points, the changing trends in students' qualities, abilities and development potential can be clearly identified. For example, a line graph or bar graph can show the progress or regression of students over a period of time.

[0208] Step S225b: Compare and analyze the quality and ability values ​​and / or development potential values ​​at the first time point with the quality and ability values ​​and / or development potential values ​​at the second time point to obtain a comparative analysis result, which is used for visual display.

[0209] Optionally, teachers can more accurately identify students' needs based on the results of comparative analysis and provide personalized teaching and coaching. For example, if the data shows that a student has significantly improved in a certain skill, the teacher can continue to strengthen training in this area; if a certain skill has not improved, the teacher can adjust the teaching method. In addition, with the real-time updated comparative analysis results, teachers can also adjust teaching strategies in a timely manner to adapt to students' changes and development needs.

[0210] As an optional implementation of the above step S225, the above implementation of visually displaying the quality ability value and / or development potential value of the student user may include:

[0211] Step S225c: Obtain the average quality and ability value of the group to which the student user belongs, and compare and analyze the quality and ability value of the student user with the average quality and ability value to obtain a comparative analysis result, which is used for visual display.

[0212] It is understandable that parents can compare and analyze the results of the student user's quality and ability values ​​with the average quality and ability values, thereby visually displaying a clear understanding of their child's performance and development in school, which increases the transparency of the education process and enhances parents' trust in the school.

[0213] And / or, as an optional implementation of the above step S225, the above implementation of visually displaying the quality ability value and / or development potential value of the student user may include:

[0214] Step S225d: Obtain the average development potential value of the group to which the student user belongs, and compare and analyze the development potential value of the student user with the average development potential value to obtain a comparative analysis result, which is used for visual display.

[0215] Understandably, visualized data provides a concrete basis for communication between parents and teachers. Parents can discuss their children's performance with teachers based on the data and jointly develop support plans. For example, if the data shows that the child's progress in a certain subject is slow, parents and teachers can jointly explore solutions. In addition, school management can evaluate the overall teaching quality and curriculum effectiveness through the results of comparative analysis. For example, if the data shows that multiple students generally perform poorly in a certain subject, the school can take measures to improve the teaching methods of the subject. Furthermore, based on the results of comparative analysis, the school can allocate educational resources more reasonably to ensure that every student can receive appropriate support and help. For example, if the data shows that some students have higher development potential in a certain aspect, the school can provide more relevant resources and opportunities.

[0216] As an optional implementation of the above teaching auxiliary method, after determining the quality, ability and development potential value of the student user, it also includes:

[0217] Step S225e: Select candidate athletes from the student competition list whose quality and ability values ​​differ from the quality and ability value of the student user by less than a first preset threshold.

[0218] It is understandable that by matching competitors with similar qualities and abilities, the participation and viewing experience of the competition can be ensured, which gives every student the opportunity to demonstrate his or her abilities and progress under relatively equal conditions.

[0219] Step S225f: Pairing the candidate athletes as competitors of the student user.

[0220] It is understandable that by matching with opponents with similar qualities and abilities, students' sense of competition and enterprising spirit can be stimulated, and students will work harder to train and improve themselves in order to achieve better results. Furthermore, students can conduct more targeted training based on the characteristics of the matched competitors. For example, if the competitors are strong in a certain aspect, students can strengthen the training in that aspect to improve their overall level. By competing with opponents with similar qualities and abilities, students can discover their shortcomings in each competition and gradually improve them. This continuous improvement helps students develop in an all-round way.

[0221] As an optional implementation of the above teaching auxiliary method, after determining the quality, ability and development potential value of the student user, it also includes:

[0222] Step S225g: Select candidate athletes from the student competition list whose quality and ability values ​​differ from the quality and ability value of the student user by less than a second preset threshold.

[0223] Optionally, the second preset threshold is adjusted according to historical data. For example, by collecting and analyzing the performance data of different students in the competition, the system can continuously optimize the matching algorithm to make the pairing more accurate. For example, the system can adjust the preset threshold according to historical data to better reflect the actual ability of the students. Competing with opponents with similar qualities and abilities can reduce the psychological pressure of students. Students will not feel frustrated because their opponents are too strong, nor will they lose motivation because their opponents are too weak. By competing with different but similar opponents, students can gradually adapt to various competition environments and improve their psychological adaptability.

[0224] Step S225h: sending partner invitation information to the candidate athlete, where the partner invitation information is used to invite the candidate athlete to be the competition partner of the student user.

[0225] It is understandable that by pairing students with similar qualities and abilities into competition partners, teamwork is promoted. This pairing method helps students learn to collaborate and communicate and cultivate team spirit. Because students with similar qualities and abilities are more likely to resonate with each other, they can learn and improve from each other through communication and sharing of experiences. This interaction helps to form a good learning atmosphere.

[0226] As an optional implementation of the above teaching auxiliary method, the above teaching auxiliary method also includes:

[0227] Step S225i: Count the average quality and capability value of the first organization group and the average quality and capability value of the second organization group, where the group identifier of the first organization group is different from the group identifier of the second organization group.

[0228] Step S225j: Determine whether the average quality and capability value of the first organization group and the average quality and capability value of the second organization group are less than a preset capability threshold.

[0229] It is understandable that by pairing groups of organizations with similar average quality and ability values, the participation and viewing value of the competition can be ensured, which gives each team the opportunity to demonstrate their abilities and progress under relatively equal conditions.

[0230] Step S225k: If the average quality and capability value of the first organization group and the average quality and capability value of the second organization group are less than a preset capability threshold, the first organization group is paired as a competitor of the second organization group.

[0231] It is understandable that by pairing organizational groups with similar average quality and ability values, they can compete with opponents with similar quality and ability, which can stimulate the competitive awareness and enterprising spirit of team members. The team will work harder to train and improve themselves in order to achieve better results. Among them, the first organizational group and the second organizational group are both class representative teams or school representative teams.

[0232] As an optional implementation method of the above teaching assistance method, the representative teams can be selected at multiple levels from school level, district level to provincial level. This solution can not only ensure the competitiveness of leagues at all levels, but also include:

[0233] Step S2251: For each school participating in the school-level league, select a school representative team from multiple class representative teams of the school.

[0234] Optionally, by collecting and analyzing data from teams at different levels (such as quality and ability values, game performance, etc.), the system can continuously optimize the screening algorithm to make the selection more accurate. For example, the system can adjust the screening criteria based on historical data to better reflect the actual capabilities of the team. Based on data-driven decision-making, coaches can more accurately understand the ability distribution and needs of each team, thereby formulating more scientific training plans and strategies.

[0235] And / or, step S225m: for each region participating in the district league, select a district team from multiple school teams in the region.

[0236] It is understandable that the multi-level selection process can promote exchanges and cooperation between different regions. Through the competition, teams from different regions can learn from each other and enhance understanding. At the same time, teams from different regions can share resources and experience and promote common development. For example, excellent training methods and teaching resources can be spread among different teams.

[0237] And / or, step S225n: for each province participating in the provincial league, select a provincial team from multiple district-level teams in the province.

[0238] It is understandable that from class to school, to regional and provincial level, each step is strictly screened to ensure that the final selected representative team is the best team at each level. This layer-by-layer optimization method can gradually improve the overall competitive level. Furthermore, the screening process at each level is based on objective data and standards, ensuring the transparency of the selection, which helps to improve the trust and enthusiasm of the participants.

[0239] As an optional implementation of the above method, a student information query function on a personal side is also included, and the implementation of the function includes:

[0240] Step S226: The server receives the query request sent by the terminal device, where the query request includes: the student ID being queried.

[0241] The implementation method of the above step S226 is, for example: the head teacher or coach sends a query request to the server through the Internet via a terminal device (such as a mobile phone, a tablet computer or a personal computer), and the query request contains the student identifier (such as a student number or a unique ID) to be queried. Then, the server receives the query request sent by the terminal device and parses the student identifier to be queried from the query request.

[0242] Step S227: Query the user role type of the user who logs in to the terminal device from the user database.

[0243] For example, the implementation of the above step S227 is as follows: the server can also obtain the user identification logged in at the terminal device, and the user identification can be confirmed during the interaction between the server and the terminal device. For example, after the user logs in, the server can store the user identification in the local session, and the user identification can be obtained from the local session at this time; for another example, after the user logs in, the server can also store the user identification in the browser cookie of the terminal device. At this time, the query request contains the browser cookie by default, and the user identification can be obtained from the browser cookie in the query request. Then, the user role type of the user logged in at the terminal device is queried from the user database according to the user identification.

[0244] Step S228: If the user role type logged in by the terminal device is a class teacher type, the physiological data, body shape data, exercise data, completion status of exercise homework, sports project test and / or sports competition information corresponding to the student ID are sent to the terminal device.

[0245] Step S229: If the user role type logged into the terminal device is a coach type, the sports data, exercise homework, completion status of the exercise homework, sports project tests and / or sports competition information corresponding to the student ID are sent to the terminal device.

[0246] It is understandable that both the head teacher and the coach can view the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information of each student in the managed class on their personal APP or mini program. In this case, the server can send the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information corresponding to the student ID in the managed class to the terminal device according to the user role type.

[0247] Step S230: If the user role type logged in by the terminal device is a parent type or a guardian type, the physiological data, body shape data, exercise data, completion status of exercise homework, sports project tests and / or sports competition information corresponding to the student ID are sent to the terminal device.

[0248] It is understandable that if the user role logged in to the terminal device is the parent or guardian of the student, such as the student's parent, the physiological data, body shape data, exercise data, completion status of exercise homework, sports test and / or sports competition information and other personal information corresponding to the student ID can be sent directly to the parent's terminal device, but the personal information of other students in the class cannot be sent, so as to achieve better privacy protection and enhance the security of privacy data protection.

[0249] Step S230a: If the user role type logged in by the terminal device is a school representative type, the exercise data, exercise homework, completion status of the exercise homework, sports test and / or sports competition information corresponding to the student ID are sent to the terminal device.

[0250] It is understandable that the school representative can also view the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information of each student in the managed class on the APP or applet on his / her personal end. In this case, the server can send the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information corresponding to the student ID in the managed class to the terminal device according to the user role type.

[0251] As an optional implementation of the above teaching auxiliary method, a group management function is also included. The implementation of the query operation processing of the group management function includes:

[0252] Step S231: the server receives a query request sent by a terminal device, where the query request includes: an identifier of a group to be queried.

[0253] The implementation method of the above step S231 is, for example: the head teacher or coach sends a query request for a specific class to the server through the Internet via a terminal device (such as a mobile phone, a tablet computer or a personal computer), and the query request contains the group identifier to be queried (such as the class number or the unique ID of the class, or the school identifier or the school ID, etc.). Then, the server receives the query request sent by the terminal device and parses the group identifier to be queried from the query request.

[0254] Step S232: Query the user role type of the user who logs in to the terminal device from the user database.

[0255] The implementation of step S232 is the same as the implementation of step S227 above. If there is any unclear point in the implementation of step S232, please refer to the implementation of step S227 above.

[0256] Step S233: If the user role type logged in by the terminal device is a class teacher type, the physiological data, exercise data, completion status of exercise homework, sports project tests and / or sports competition information of all students in the class corresponding to the group identifier are sent to the terminal device.

[0257] Step S234: If the user role type logged in by the terminal device is a coach type, the physiological data, exercise data, exercise homework, completion status of exercise homework, sports project tests and / or sports competition information of all students in the class corresponding to the group identifier are sent to the terminal device.

[0258] It is understandable that both the head teacher and the coach can be assigned group management authority, so they can see the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports game information of each student in the managed class. In this case, the server can send the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports game information corresponding to all student identifiers in the managed class to the terminal device according to the user role type.

[0259] Step S235: If the user role type logged into the terminal device is a parent type, the average exercise data corresponding to the group identifier, the average completion status of the exercise homework, the sports project test and / or the sports competition information are sent to the terminal device.

[0260] It is understandable that the parent type is not assigned group management permissions, but can see the average level information in the class to understand the comparison information of the students with the average level, such as: average exercise data, average completion of exercise homework, etc., and can also see the information of sports tests and / or sports competitions that can be participated in on a regular basis, etc.

[0261] Step S236: If the user role type logged in by the terminal device is a school representative type, the sports compliance rate, the qualified proportion of body data, the qualified proportion of physical health status and / or the qualified proportion of psychological data indicators of all students in the school corresponding to the group identifier are sent to the terminal device.

[0262] It is understandable that the school representative is more concerned about the sports compliance rate of all students in the school, the qualified proportion of body data, the qualified proportion of physical health status and / or the qualified proportion of psychological data indicators, etc. Therefore, the indicator information that the school representative is concerned about and / or the relevant indicator information that needs to be evaluated is sent to the school representative first. In addition, the average sports data corresponding to the group identifier, the average completion of the exercise homework, sports project tests and / or sports competition information can also be sent to the school representative, and the physiological data, sports data, completion of the exercise homework, sports project tests and / or sports competition information of all students in the class can also be sent to the school representative.

[0263] In the process of implementing the above solution, the most relevant and useful data is provided according to the user's role type (such as class teacher, coach, parent or school representative, etc.), thereby improving the practicality and utilization efficiency of information. Since users with different roles only need to view data related to their responsibilities, information overload and redundancy are avoided.

[0264] See also Figure 3 The structural diagram of the teaching assistance system provided in the embodiment of the present application is shown; the embodiment of the present application provides a teaching assistance system 300, including: an intelligent monitoring device 310 and a server 320, and the intelligent monitoring device 310 is communicatively connected with the server 320.

[0265] The smart monitoring device 310 is used to collect body data, which includes data collected by sensors. The above-mentioned smart monitoring device refers to a device equipped with a sensor, such as a smart watch or smart bracelet equipped with a piezoelectric film PVDF sensor and / or a flexible sweat sensor, or a shoe with a smart monitoring insole, a smart helmet or a smart hat.

[0266] The server 320 is used to determine teaching auxiliary information based on the physical data and prior knowledge of the teaching field.

[0267] It is understandable that the above-mentioned implementation method of collecting body data is the same as the step execution method in the above-mentioned teaching auxiliary method. Similarly, the above-mentioned implementation method of determining teaching auxiliary information based on body data and prior knowledge in the teaching field is the same as the step execution method in the above-mentioned teaching auxiliary method. Therefore, it will not be repeated here.

[0268] As an optional embodiment of the above system, the intelligent monitoring device includes: a photoelectric sensor, an electrode sensor and / or a piezoelectric film PVDF sensor for collecting physiological data. That is to say, the intelligent monitoring device includes: at least one of a photoelectric sensor, an electrode sensor and a piezoelectric film PVDF sensor. Among them, the sensors used in the above intelligent monitoring device may include: a sensor made of polyvinylidene fluoride PVDF material, also known as a piezoelectric film PVDF sensor, or simply a PVDF sensor. Due to the small size of this PVDF sensor, it is not only easy to be woven, but also easy to hide in, for example, the strap of a smart watch or the wristband of a smart bracelet. Since the PVDF material has a very high piezoelectric coefficient, which means that it is very sensitive to small pressure changes, this high sensitivity enables the PVDF sensor to capture subtle pulse waveforms and blood pressure changes, providing more accurate data.

[0269] As an optional embodiment of the above system, the intelligent monitoring device may also include: a flexible sweat sensor, which is used to collect potassium ion concentration and / or sodium ion concentration. When this flexible sweat sensor collects the biochemical ion concentration of sweat, the potential signal data caused by the change in this concentration. The above-mentioned sweat biochemical ion concentration is, for example, sodium ion concentration or potassium ion concentration. After the concentration of either of these two ions changes, the signal processing circuit in the flexible sweat sensor fiber can convert the potential difference analog signal caused by the change in ion concentration into a digital signal. Then, the flexible sweat sensor can send the digital signal to the intelligent monitoring device (such as a smart watch or a smart bracelet).

[0270] Optionally, the flexible sweat sensor can be designed as a filament sensor, such as a flexible sweat sensor fiber. Since the flexible sweat sensor fiber is very thin, it is easy to weave and make it into a smart watch strap or a smart bracelet wristband. Of course, it can also be woven with other natural fiber lines (such as cotton fiber lines or wool fiber lines, etc.) and / or artificial chemical fiber lines (such as polyester and nylon) and made into a smart watch strap or a smart bracelet wristband.

[0271] As an optional implementation of the above system, the above intelligent monitoring device may include: a flexible pressure sensor, a tension sensor and / or a piezoelectric film PVDF sensor for collecting mechanical data. That is to say, the intelligent monitoring device includes: at least one of a flexible pressure sensor, a tension sensor and / or a piezoelectric film PVDF sensor to collect mechanical data. For ease of understanding and explanation, only the tension sensor is used as an example for explanation here. For example: a tension sensor is installed on a sports equipment (such as a pull rod or a handle), and the tension value of the arm can be collected when the student or athlete uses the sports equipment for training, which can be used to determine whether the strength of the left arm and the strength of the right arm are trained sufficiently balanced.

[0272] Optionally, after obtaining the arm pulling force value, it is also possible to determine whether the arm pulling force value reaches an absolute value, and use this as a standard for whether a student or athlete can conduct a certain training activity or a certain training stage. For example, weightlifting training requires strong arm and shoulder strength. If the minimum arm pulling force value required for primary weightlifting training is 300N, the intermediate training is 500N, and the advanced training is 700N. If a student wants to conduct weightlifting training activities, he can first conduct a pulling force assessment. After the absolute value of the pulling force exceeds 300N, he can conduct weightlifting training activities and become an athlete at the primary stage. Similarly, if the athlete wants to enter the intermediate stage from the primary stage, he can first conduct a pulling force assessment. After the absolute value of the pulling force exceeds 500N, he can enter the intermediate stage training.

[0273] As an optional implementation of the above system, the server includes: a business logic server, which is used to receive and classify the physical data. The business logic server extracts the physical data of indicators such as heart rate, number of steps, and sleep quality from the received data packets, and stores these data packets to a local disk, a database server, a dedicated storage server and / or an OSS cluster, etc.

[0274] And / or, a data processing server is used to determine teaching auxiliary information based on body data and prior knowledge in the teaching field. The implementation method of determining teaching auxiliary information based on body data and prior knowledge in the teaching field is the same as the step execution method in the above teaching auxiliary method. Therefore, it will not be repeated here.

[0275] And / or, a data storage server is used to store data content such as physical data, auxiliary teaching lesson plans and / or videos.

[0276] As an optional implementation of the above system, the teaching assistance system also includes: terminal devices; terminal devices such as personal computers, tablet computers and / or smart phones, etc., these computers, tablet computers and / or smart phones can run application APP software, and / or the APP software on these computers, tablet computers and / or smart phones can run mini-programs.

[0277] See also Figure 4 The structural diagram of the teaching auxiliary device provided in the embodiment of the present application is shown; the embodiment of the present application provides a teaching auxiliary device 400, including:

[0278] The body data acquisition module 410 is used to acquire body data, where the body data includes data collected by sensors.

[0279] The auxiliary information determination module 420 is used to determine teaching auxiliary information based on body data and prior knowledge of the teaching field.

[0280] It should be understood that the device corresponds to the above-mentioned teaching auxiliary method embodiment and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be referred to in the above description, and the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or solidified in the operating system (OS) of the device.

[0281] See also Figure 5 A server 900 provided in an embodiment of the present application includes: a processor 910 and a memory 920, wherein the memory 920 stores machine-readable instructions executable by the processor 910, and when the machine-readable instructions are executed by the processor 910, the above method is executed.

[0282] The embodiment of the present application also provides a computer-readable storage medium 930, on which a computer program is stored, and the computer program is executed by the processor 910 to execute the above method. Among them, the computer-readable storage medium 930 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk.

[0283] The embodiment of the present application also provides a computer program product, including: a computer program or a computer instruction, and the computer program or the computer instruction executes the method described above when executed by a processor.

[0284] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0285] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed device and method can also be implemented in other ways. The device embodiments described above are only schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible implementation architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, a program segment or a code, and a part of a module, a program segment or a code includes one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also be different from the order of occurrence marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which is mainly determined by the functions involved.

[0286] In addition, the functional modules of each embodiment in the embodiments of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. In addition, in the description of this specification, the description of reference terms "one embodiment", "some embodiments", "example", "specific example", "some examples", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples without contradiction.

[0287] The above description is only an optional implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiments of the present application, which should be covered within the protection scope of the embodiments of the present application.

Claims

1. A teaching auxiliary method, characterized in that: Applicable to servers, including: Acquiring body data, wherein the body data includes data collected by a sensor; Teaching auxiliary information is determined based on the physical data and prior knowledge of the teaching field.

2. The method according to claim 1, characterized in that The body data includes: basic body data and data collected by wearable devices during exercise; the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: The fatigue degree and / or recovery time are determined according to the basic body data, the data collected by the wearable device and the prior knowledge in the teaching field.

3. The method according to claim 1, characterized in that The body data includes: sweat biomarker parameters collected by the wearable device; the teaching auxiliary information is determined according to the body data and prior knowledge in the teaching field, including: The body health status is determined based on the sweat biomarker parameters and the prior knowledge in the teaching field.

4. The method according to claim 1, characterized in that: The body data includes: data collected by the wearable device during exercise; the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: After-class recovery recommendation information is determined based on the data collected by the wearable device, the sports course information and the prior knowledge of the teaching field, and the after-class recovery recommendation information includes: stretching action recommendation information, medicine package recommendation information and / or dietary recommendation information.

5. The method according to claim 1, characterized in that The body data includes: data collected by the wearable device during exercise; the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: The after-class homework recommendation information is determined according to the data collected by the wearable device, the sports course information and the prior knowledge of the teaching field. The after-class homework recommendation information is training content specifically recommended for the sports performance of individual students in sports classes.

6. The method according to claim 1, characterized in that The body data includes: data collected by the wearable device during the teaching process; the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: Determining a learning state in a learning activity based on data collected by the wearable device and prior knowledge in the teaching field; Determine a target time when the learning status is not good, and determine the target content from the teaching audio / video according to the target time; wherein the target content is the content that the individual students need to take targeted tutoring; the teaching audio / video is obtained by recording the teacher's teaching process.

7. The method according to claim 1, characterized in that The body data includes: basic body data and data collected by wearable devices during exercise; the teaching auxiliary information determined based on the body data and prior knowledge in the teaching field includes: Determining a sports ability index according to the basic body data and the data collected by the wearable device; The sports course recommendation information is determined according to the sports ability index and the prior knowledge of the teaching field.

8. The method according to claim 1, characterized in that The body data includes: basic body data and data collected by wearable devices during exercise; the teaching auxiliary information determined based on the body data and prior knowledge in the teaching field includes: Determining a sports ability index according to the basic body data and the data collected by the wearable device; Determining psychological data indicators during exercise based on the data collected by the wearable device; The sports course recommendation information is determined according to the sports ability index, the psychological data index and the prior knowledge of the teaching field.

9. The method according to claim 7 or 8, characterized in that: The basic physical data includes information about poor physical condition, and the exercise course recommendation information is information about exercise courses that are targeted at improving poor physical condition, and / or nutritional diet information that is targeted at improving poor physical condition.

10. The method according to claim 1, characterized in that The body data includes: data collected by a wearable device; the teaching auxiliary information is determined based on the body data and prior knowledge in the teaching field, and also includes: Obtaining the evaluation results of the student user, and determining the happiness state score of the student user according to the data collected by the wearable device; The course recommendation information is determined according to the evaluation result and the pleasure state score.

11. The method according to claim 10, characterized in that The evaluation results include: emotion evaluation scores and / or intelligence evaluation scores; the evaluation results of the student users are obtained, including: Receiving a question answering request sent by a student user through a terminal device, the question answering request including: an age parameter of the student user; Searching for test questions corresponding to the age parameter in a social adaptability question bank and / or a behavioral activity question bank; Sending a test question corresponding to the age parameter to the terminal device, so that the student user completes and returns a test answer corresponding to the test question; The emotion assessment score and / or intelligence assessment score of the student user is evaluated according to the test answers corresponding to the test questions.

12. The method according to claim 10, characterized in that Determining the pleasure state score of the student user according to the data collected by the wearable device includes: Determining the emotional state of the student user during multiple attendances at a preset type of course based on the data collected by the wearable device; Determine the student user's score of pleasure for the preset type of course according to the proportion of times of pleasure in the multiple emotional states; The preset type courses include at least one of cultural courses, sports courses, art courses and practical courses.

13. The method according to claim 1, characterized in that The body data includes: data collected by a wearable device; the teaching auxiliary information is determined based on the body data and prior knowledge in the teaching field, including: Determining the emotional state of the student user within a preset time period based on the data collected by the wearable device; The pleasure state score of the student user in the preset time period is determined according to the proportion of the number of times the emotional state in the preset time period is characterized as a pleasure state.

14. The method according to claim 1, characterized in that The body data includes: data collected by the wearable device during the teaching process; the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: Determining a psychological data index curve based on the data collected by the wearable device; A teaching intervention plan is determined according to the psychological data indicator curve and the prior knowledge of the teaching field.

15. The method according to claim 1, characterized in that The body data includes: sports homework videos uploaded by student users, and the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: Identify key action video units from the sports operation video, where the key action video units are video frames or video clips; The key action video unit is analyzed according to the prior knowledge of the teaching field to determine the evaluation result of the sports homework video, and the evaluation result includes whether it is qualified and / or action correction and improvement suggestions.

16. The method according to claim 15, characterized in that The prior knowledge in the teaching field includes: standard action videos; the analysis of the key action video units according to the prior knowledge in the teaching field to determine the evaluation results of the sports homework videos includes: Extracting key points of a human body from the sports operation video; Comparing the key points of the human body with the key points in the standard action video to obtain a comparison result; The action correction and improvement suggestions in the teaching auxiliary information are generated according to the comparison results.

17. The method according to claim 1, characterized in that The body data includes a sports video; the determining of teaching auxiliary information based on the body data and prior knowledge in the teaching field includes: Decomposing the sports video into a plurality of key action video units according to the prior knowledge of the teaching field, wherein the key action video units are video frames or video clips; The teaching auxiliary method further includes: receiving an operation request for the plurality of key action video units, the operation request comprising: a screening request and / or a remark request; In response to the operation request, corresponding operations are performed on the multiple key action video units.

18. The method according to claim 1, characterized in that The body data includes: basic body data and data collected by wearable devices during exercise; the teaching auxiliary information determined according to the body data and prior knowledge in the teaching field includes: Determining the amount of exercise completed based on data collected by the wearable device during the exercise; The exercise target for the next stage is determined based on the basic body data, the completed exercise volume and the prior knowledge in the teaching field.

19. The method according to claim 1, characterized in that The physical data includes: the current sports test and / or sports competition information; after obtaining the physical data, it also includes: The sports event test and / or the sports competition information is stored in a sports growth archive.

20. The method according to claim 19, characterized in that The prior knowledge in the teaching field includes: the school's historical admission score and enrollment number; the teaching auxiliary information determined based on the physical data and prior knowledge in the teaching field includes: The schools to be recommended for application are determined based on the level certificates, academic performance, sports performance in the sports test, sports specialties in the sports competition information, the school's historical admission score line and the number of admissions uploaded by the student user.

21. The method according to claim 19, characterized in that After storing the sports event test and / or the sports game information in the sports growth archive, the method further includes: Extracting the student user's physical test result data, body shape data, physiological data, exercise data and completion status of exercise homework from the physical growth archive; The quality ability value and development potential value of the student user are determined according to the physical test result data, body shape data, physiological data, exercise data and completion status of exercise homework of the student user.

22. The method according to claim 21, characterized in that After determining the quality, ability and development potential value of the student user, the method further includes: If the quality and ability value of the student user is greater than the preset quality threshold, and the development potential value of the student user is greater than the preset potential value, a permission request message for recommending talents is sent to the student user or the guardian user of the student user.

23. The method according to claim 21, characterized in that After determining the quality, ability and development potential value of the student user, the method further includes: The quality and ability value and / or development potential value of the student user is displayed visually.

24. The method according to claim 23, characterized in that The visual display of the quality ability value and / or development potential value of the student user includes: Obtaining the quality ability value and / or development potential value of the student user at a first time point and the quality ability value and / or development potential value at a second time point, wherein the first time point is different from the second time point; The quality and ability value and / or development potential value at the first time point is compared and analyzed with the quality and ability value and / or development potential value at the second time point to obtain a comparative analysis result, and the comparative analysis result is used for visual display.

25. The method according to claim 23, characterized in that The visual display of the quality ability value and / or development potential value of the student user includes: Obtaining the average quality and ability value of the group to which the student user belongs, and performing comparative analysis on the quality and ability value of the student user and the average quality and ability value to obtain comparative analysis results, which are used for visual display; And / or, obtaining the average development potential value of the group to which the student user belongs, and performing comparative analysis on the development potential value of the student user and the average development potential value to obtain comparative analysis results, which are used for visual display.

26. The method according to claim 21, characterized in that After determining the quality, ability and development potential value of the student user, the method further includes: Screening out candidate athletes from the student competition list whose quality and ability values ​​have a difference with the quality and ability value of the student user that is less than a first preset threshold; The candidate athletes are paired as competitors for the student user.

27. The method according to claim 21, characterized in that After determining the quality, ability and development potential value of the student user, the method further includes: Screening out candidate athletes from the student competition list whose quality and ability values ​​have a difference with the quality and ability value of the student user that is less than a second preset threshold; Send partner invitation information to the candidate athlete, where the partner invitation information is used to invite the candidate athlete to serve as a competition partner of the student user.

28. The method according to any one of claims 1 to 27, characterized in that: Also includes: Counting the average quality and capability value of a first organization group and the average quality and capability value of a second organization group, wherein the group identifier of the first organization group is different from the group identifier of the second organization group; Determining whether the average quality and capability value of the first organization group and the average quality and capability value of the second organization group are less than a preset capability threshold; If so, the first organization group is paired as a competitor of the second organization group, and both the first organization group and the second organization group are class representative teams or school representative teams.

29. The method according to claim 28, characterized in that Also includes: For each school participating in the school-level league, select the school representative team from multiple class representative teams of the school; and / or, For each region participating in the district league, select a district team from among the multiple school teams in that region; and / or, For each province participating in the provincial league, a provincial team is selected from multiple district-level teams in that province.

30. The method according to any one of claims 1 to 27, characterized in that: Also includes: Receiving a query request sent by a terminal device, the query request including: an identification of a student to be queried; Querying the user role type logged in at the terminal device from the user database; If the user role type logged in by the terminal device is a class teacher type, sending the physiological data, body shape data, exercise data, completion status of exercise homework, sports project test and / or sports competition information corresponding to the student ID to the terminal device; If the user role type logged in by the terminal device is a coach type, the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information corresponding to the student ID are sent to the terminal device; If the user role type logged in by the terminal device is a parent type, the sports data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information corresponding to the student ID are sent to the terminal device; If the user role type logged in by the terminal device is a school representative type, the sports data, exercise homework, completion status of the exercise homework, sports project tests and / or sports competition information corresponding to the student ID are sent to the terminal device.

31. The method according to any one of claims 1 to 27, characterized in that: Also includes: Receiving a query request sent by a terminal device, the query request including: an identifier of a group to be queried; If the user role type logged in by the terminal device is a class teacher type, the physiological data, exercise data, completion status of exercise homework, sports project test and / or sports competition information of all students in the class corresponding to the group identifier are sent to the terminal device; If the user role type logged in by the terminal device is a coach type, sending the physiological data, exercise data, exercise homework, completion status of exercise homework, sports project test and / or sports competition information of all students in the class corresponding to the group identifier to the terminal device; If the user role type logged in by the terminal device is a parent type, sending the average exercise data, average completion status of exercise homework, sports project test and / or sports competition information corresponding to the group identifier to the terminal device; If the user role type logged in by the terminal device is a school representative type, the sports compliance rate, the qualified proportion of body shape data, the qualified proportion of physical health status and / or the qualified proportion of psychological data indicators of all students in the school corresponding to the group identifier are sent to the terminal device.

32. A teaching assistance system, characterized in that: include: An intelligent monitoring device and a server, wherein the intelligent monitoring device is communicatively connected with the server; The intelligent monitoring device is used to collect body data; The server is used to determine teaching auxiliary information based on the body data and prior knowledge of the teaching field.

33. The system according to claim 32, characterized in that The intelligent monitoring device includes: a photoelectric sensor, an electrode sensor and / or a piezoelectric film PVDF sensor, which are used to collect physiological data.

34. The system according to claim 32, characterized in that The intelligent monitoring device includes: a flexible sweat sensor for collecting potassium ion concentration and sodium ion concentration.

35. The system according to claim 32, characterized in that The intelligent monitoring device includes: a flexible pressure sensor, a tension sensor and / or a piezoelectric film PVDF sensor, which are used to collect mechanical data.

36. The system according to claim 32, characterized in that The server includes: a business logic server, configured to receive and sort the body data; and / or, a data processing server for determining teaching auxiliary information based on the body data and prior knowledge of the teaching field; And / or, a data storage server for storing physical data, auxiliary teaching lesson plans and / or video data content.

37. The system according to claim 32, characterized in that The teaching auxiliary system also includes: a terminal device; an application program APP software and / or a small program running on the APP software are running on the terminal device.

38. A teaching auxiliary device, characterized in that: Applicable to servers, including: A body data acquisition module, used to acquire body data, wherein the body data includes data collected by sensors; The auxiliary information determination module is used to determine the teaching auxiliary information according to the body data and prior knowledge of the teaching field.

39. A server, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the machine-readable instructions are executed by the processor to perform any method according to claims 1 to 31.

40. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 31 is executed.

41. A computer program product, characterized in that include: A computer program or a computer instruction, wherein when the computer program or the computer instruction is executed by a processor, the method according to any one of claims 1 to 31 is executed.

Images