A pediatric TCM acupoint massage teaching and training system and method

Abstract

The present invention relates to the field of massage teaching and training technology, and in particular to a pediatric Chinese medicine acupoint massage teaching and training system and method. The system comprises: generating a personalized learning plan based on learning data, generating a virtual child anatomical model based on the personalized learning plan, acquiring the operation data of the trainees in operation at the same time, and performing annotation processing in the virtual child anatomical model to obtain the annotation result; generating the operation evaluation result through recursive hierarchical error feedback and adaptive adjustment algorithm, and further calculating the operation adjustment amount of the trainees by using the recursive adjustment mechanism; generating real-time improvement suggestions based on the operation adjustment amount of the trainees; adjusting the learning content according to the real-time improvement suggestions to obtain the latest personalized learning plan; and training according to the latest personalized learning plan until the training is completed. The system solves the problems of insufficient personalization of the learning plan and inaccurate and incomplete adjustment of the trainees' operation in the teaching and training of pediatric Chinese medicine acupoint massage.

Description

Technical Field

[0001] The present invention relates to the technical field of massage teaching and training, and in particular to a pediatric Chinese medicine acupoint massage teaching and training system and method. Background Art

[0002] In the teaching of TCM acupoint massage, especially the massage technique training for children, students need to master complex skills in the learning process, including accurate positioning of acupoints, proper control of strength, and correct use of techniques. However, traditional teaching methods have significant limitations in the following aspects: first, the teaching method is mainly based on direct guidance by teachers; second, the traditional operation evaluation method is mainly based on manual observation; third, it is impossible to achieve flexible adjustment of learning progress and goals. Therefore, a teaching and training method for pediatric TCM acupoint massage for personalized teaching came into being. Summary of the invention

[0003] The present invention provides a pediatric TCM acupoint massage teaching and training system and method, so as to solve the problems of insufficient personalization of learning plans and inaccurate and incomplete adjustment of trainees' operations in pediatric TCM acupoint massage teaching and training.

[0004] The present invention provides a pediatric TCM acupoint massage teaching and training system and method, which specifically includes the following technical solutions:

[0005] A pediatric TCM acupoint massage teaching and training method comprises the following steps:

[0006] S1. After the student logs in, the student's learning data is obtained, and a personalized learning plan is generated based on the learning data using dynamic state feedback and a nonlinear adaptive learning plan generation algorithm, and an interactive virtual child anatomical model is generated based on the personalized learning plan. At the same time, the student's operation data is obtained during operation, and the operation data is annotated in the virtual child anatomical model to obtain the annotation result;

[0007] S2. Comprehensively evaluate the student's operation data through recursive hierarchical error feedback and adaptive adjustment algorithm to generate operation evaluation results; based on the operation evaluation results, use the recursive adjustment mechanism to adjust the student's operation to obtain the student's operation adjustment amount; based on the student's operation adjustment amount, generate real-time improvement suggestions; adjust the learning content according to the real-time improvement suggestions to obtain the latest personalized learning plan; train according to the latest personalized learning plan until the training is completed.

[0008] Preferably, the S1 specifically includes:

[0009] When a student logs in, the user information table stored in the database is queried to check the matching of the user name and password, verify the permissions and load the corresponding learning data; the learning data includes historical learning records, current progress, operation evaluation results and real-time improvement suggestions.

[0010] Preferably, the S1 specifically includes:

[0011] In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, the student's learning state model is constructed. The student's learning state includes four dimensions: mastering accuracy, operation deviation, learning progress and feedback response ability. After constructing the student's learning state model, a nonlinear feedback model is introduced to simulate the student's feedback mechanism in the learning process, reflecting the student's feedback response and learning progress. The specific formula is:

[0012]

[0013] in, is the student’s feedback response, indicating that The degree to which feedback and adjustments are made to students’ learning status; Indicates the accuracy of students’ mastery of acupoints or techniques; Indicates the deviation of trainees in the operation process; Indicates the learning progress of students; is the weighting coefficient of feedback; is the adjustment coefficient, which is used to control the intensity of the nonlinear impact of the operation deviation on the feedback; is the adjustment coefficient, which is used to control the periodic effect of learning progress on feedback; It is the adjustment coefficient, which is used to control the impact of students’ mastering accuracy on learning feedback.

[0014] Preferably, the S1 specifically includes:

[0015] In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, a fuzzy reasoning mechanism is introduced to dynamically adjust the learning tasks according to the difference between the students' current learning progress and the target learning progress. The specific implementation process of the fuzzy reasoning mechanism is as follows: calculate the error between the target learning progress and the students' current learning progress to obtain the learning progress error value; adjust the students' learning tasks based on the learning progress error value to obtain the learning plan adjustment amount.

[0016] Preferably, the S1 specifically includes:

[0017] In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, a weighted error optimization algorithm is used to calculate the operation error compared with the standard method after each operation of the trainee.

[0018] Preferably, the S1 specifically includes:

[0019] In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, the quantitative index of the learning plan is defined; the formula of the quantitative index of the learning plan is expressed as:

[0020]

[0021] in, It's time Quantitative indicators of the learning plan; It's time The study plan The learning status of a task; It is the students at the time For the study plan Feedback response for each task; It's time The study plan The amount of adjustment for each task; It's time The study plan The error of the task; , , , represents weight; It is the total number of tasks in the learning plan; according to the quantitative indicators of the learning plan, adjust the priority of the tasks; based on the priority of the tasks, allocate different times for each task; and obtain the task content and learning goals from the real-time improvement suggestions to generate a personalized learning plan including task priority, time allocation, task content and learning goals.

[0022] Preferably, the S2 specifically includes:

[0023] In the process of implementing the recursive hierarchical error feedback and adaptive adjustment algorithm, the student operation data is standardized with an attenuation factor to obtain the standardized student operation data; based on the standardized student operation data, a nonlinear weighted error calculation method is introduced to calculate the error between the student operation data and the standard technique operation data from the standard technique database. The specific formula is as follows:

[0024]

[0025] in, The data of students' operation and the data of standard operation at the time The weighted error of is the index adjustment factor; It is the students’ operation data after standardization; Manipulate data using standard techniques; is a control parameter used to control the speed of exponential decay; is the time weight factor, and the formula is: , is the time decay factor; It is the benchmark time for evaluating trainees’ operational performance;

[0026] By replacing the standardized student operation data and the corresponding standard technique operation data in the nonlinear weighted error calculation method with path, time, and force operation data, the path error, time error, and force error of the student operation are obtained.

[0027] Preferably, the S2 specifically includes:

[0028] In the process of implementing the recursive hierarchical error feedback and adaptive adjustment algorithm, a hierarchical error feedback mechanism is introduced based on path error, time error, and force error to calculate the student's overall operation error value and obtain the student's error feedback; the student's overall operation error value is used as the operation evaluation result, and the operation evaluation result is displayed dynamically.

[0029] Preferably, the S2 specifically includes:

[0030] In the process of implementing the recursive hierarchical error feedback and adaptive adjustment algorithm, the recursive adjustment mechanism is used to adjust the student's operation according to the student's error feedback, and the student's operation adjustment amount is calculated; the formula is as follows:

[0031]

[0032] in, It is the students at the time The amount of operational adjustment; is the adjustment scale factor; is the overall operation error value of the trainees, indicating error feedback; is the nonlinear growth coefficient;

[0033] Based on the error feedback and the trainee's operational adjustments, real-time improvement suggestions are generated for the trainee; and the operational evaluation results and real-time improvement suggestions are stored in the database.

[0034] A pediatric TCM acupoint massage teaching and training system, comprising the following parts:

[0035] User management module, virtual human interaction module, dynamic learning module, force sensing feedback module, AI intelligent guidance module;

[0036] The user management module is the entrance to the system and is responsible for managing the student's identity information, historical learning records, and initialization of the learning plan. After the student logs in, a personalized learning plan is generated based on the historical learning record, current learning progress, operation evaluation results, and real-time improvement suggestions, and the personalized learning plan is passed to the virtual human interaction module;

[0037] The virtual human interaction module generates an interactive virtual child anatomical model according to the personalized learning plan provided by the user management module, and receives the trainee operation data provided by the force sensing feedback module in real time; the standard manipulation operation data is marked in green on the virtual anatomical model, and the trainee operation data is marked in red to obtain the marking results; the standard manipulation operation data comes from the standard manipulation database; the marking results are sent to the dynamic learning module;

[0038] The dynamic learning module receives and displays the annotation results provided by the virtual human interaction module in real time. At the same time, it dynamically displays the operation evaluation results provided by the AI ​​intelligent guidance module and dynamically adjusts the learning content according to the real-time improvement suggestions provided by the AI ​​intelligent guidance module until the training is completed.

[0039] The force sensing feedback module is used to capture the trainee's operation data during operation, and transmit the trainee's operation data to the virtual human interaction module in real time for annotation processing, and at the same time transmit the trainee's operation data to the AI ​​intelligent guidance module;

[0040] The AI ​​intelligent guidance module conducts a comprehensive evaluation of the students' operation data through recursive hierarchical error feedback and adaptive adjustment algorithms to generate operation evaluation results; based on the operation evaluation results, the recursive adjustment mechanism is used to obtain the students' operation adjustment amounts; based on the operation evaluation results and the students' operation adjustment amounts, real-time improvement suggestions are generated; the operation evaluation results and real-time improvement suggestions are passed to the dynamic learning module, and at the same time, the operation evaluation results and real-time improvement suggestions are stored in the database.

[0041] The beneficial effects of the technical solution of the present invention are:

[0042] 1. Generate personalized learning plans based on students’ historical learning records, current learning progress, recent operation evaluation results, and real-time improvement suggestions through dynamic state feedback and nonlinear adaptive learning plan generation algorithms. Personalized learning plans include learning task priorities, time allocation, task content, and learning goals to ensure that learning content is highly consistent with students’ abilities and learning progress, avoiding the inefficiency and waste of resources that may be caused by traditional static learning plans.

[0043] 2. Adopt a hierarchical error feedback mechanism, comprehensively consider path error, time error, and force error, and generate operation evaluation results. Compared with the traditional single-dimensional scoring, the hierarchical error feedback mechanism is more comprehensive and can identify more subtle deficiencies in the students' operations, thereby providing more accurate improvement suggestions, thereby improving the overall operation level of the students. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a structural diagram of a pediatric TCM acupoint massage teaching and training system according to the present invention;

[0045] Figure 2 The present invention provides a flow chart of a pediatric TCM acupoint massage teaching and training method. DETAILED DESCRIPTION

[0046] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0048] The specific scheme of a pediatric TCM acupoint massage teaching and training system and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0049] Refer to the attached Figure 1 , which shows a structural diagram of a pediatric TCM acupoint massage teaching and training system provided by an embodiment of the present invention, the system includes the following parts:

[0050] User management module, virtual human interaction module, dynamic learning module, force sensing feedback module, AI intelligent guidance module;

[0051] The user management module is the entrance to the system and is responsible for managing the student's identity information, historical learning records, and initialization of the learning plan. After the student logs in, a personalized learning plan is generated based on the historical learning record, current learning progress, recent operation evaluation results, and real-time improvement suggestions. The acupoints to be learned and related operation goals are specified, and the personalized learning plan is passed to the virtual human interaction module.

[0052] The virtual human interaction module generates an interactive virtual child anatomical model according to the personalized learning plan provided by the user management module, and receives the trainee operation data provided by the force sensing feedback module in real time; the standard manipulation operation data is marked in green on the virtual anatomical model, and the trainee operation data is marked in red to obtain the marking results; the standard manipulation operation data comes from the standard manipulation database; the marking results are sent to the dynamic learning module;

[0053] The dynamic learning module receives and displays the annotation results provided by the virtual human interaction module in real time. At the same time, it dynamically displays the operation evaluation results provided by the AI ​​intelligent guidance module and dynamically adjusts the learning content according to the real-time improvement suggestions provided by the AI ​​intelligent guidance module until the training is completed.

[0054] The force sensing feedback module is used to capture the trainee's operation data during operation, and transmit the trainee's operation data to the virtual human interaction module in real time for annotation processing, and at the same time transmit the trainee's operation data to the AI ​​intelligent guidance module;

[0055] The AI ​​intelligent guidance module conducts a comprehensive evaluation of the students' operation data through recursive hierarchical error feedback and adaptive adjustment algorithms to generate detailed operation evaluation results; based on the operation evaluation results, the module uses a recursive adjustment mechanism to adaptively adjust the students' operations to obtain the students' operation adjustment amounts; based on the operation evaluation results and the students' operation adjustment amounts, it generates real-time improvement suggestions; the operation evaluation results and real-time improvement suggestions are passed to the dynamic learning module, and at the same time, the operation evaluation results and real-time improvement suggestions are stored in the database.

[0056] Refer to the attached Figure 2 , which shows a flow chart of a pediatric TCM acupoint massage teaching and training method provided by an embodiment of the present invention, the method comprising the following steps:

[0057] S1. After the student logs in, the student's learning data is obtained, and a personalized learning plan is generated based on the learning data using dynamic state feedback and a nonlinear adaptive learning plan generation algorithm, and an interactive virtual child anatomical model is generated based on the personalized learning plan. At the same time, the student's operation data is obtained during operation, and the operation data is annotated in the virtual child anatomical model to obtain the annotation result;

[0058] First, when the student logs in, the user information table stored in the database is queried to check the match between the username and password to identify the student information, verify the authority and load the corresponding learning data, and extract the student's learning data from the existing database, including historical learning records, current learning progress, recent operation evaluation results and real-time improvement suggestions, to provide a basis for generating a learning plan. The technologies used in the above process are all existing technologies and will not be elaborated here.

[0059] Furthermore, based on the students' learning data, a personalized learning plan is generated using dynamic state feedback and nonlinear adaptive learning plan generation algorithms. The dynamic state feedback and nonlinear adaptive learning plan generation algorithms dynamically model the students' learning status and gradually adjust the learning plan by combining nonlinear relationships and fuzzy reasoning. By introducing nonlinear feedback models, fuzzy reasoning mechanisms and weighted error optimization, the training effect and learning progress of students can be greatly improved. The specific contents include:

[0060] First, we construct a student's learning status model. The student's learning status is described by multiple dimensions, which reflect the student's specific performance in each learning link. The student's learning status is defined as a four-dimensional vector , which includes four dimensions: mastering accuracy, operation deviation, learning progress and feedback responsiveness. Each dimension can be quantified through specific operation data: It indicates the accuracy of students’ mastery of acupoints or techniques, which is specifically evaluated by the accuracy of the techniques, that is, the average value of the errors of all the techniques that have been trained; Indicates the deviation of students during the operation process, used to measure the deviation of students in terms of strength, angle, etc. when performing the technique; Indicates the learning progress of students, that is, the proportion of completed learning tasks; It represents the trainee's feedback response ability, that is, the trainee's ability to absorb and implement real-time improvement suggestions, which is measured by the reduction in the technique error caused by the trainee's execution of the improvement suggestions. The variables of each dimension in the above four-dimensional vector are defined by expert experience method.

[0061] Therefore, the student's learning state can be expressed as a four-dimensional vector:

[0062]

[0063] After constructing the student's learning status model, a nonlinear feedback model is introduced to simulate the feedback mechanism of the student in the learning process. The errors and deviations of each student in the operation process will affect their learning progress and learning status, so the feedback mechanism must be able to adjust the student's learning plan in real time. The nonlinear feedback model reflects the student's feedback response and learning progress. The nonlinear feedback model can be expressed as:

[0064]

[0065] in, is the student’s feedback response, indicating that The degree to which feedback is provided to the learner’s learning status. Feedback response combines the three dimensions of operational deviation, learning progress, and mastery accuracy, with the goal of providing dynamic adjustments during the learner’s learning process; It is the weighted coefficient of feedback, which indicates the influence of different dimensions on feedback. It is dynamically adjusted according to the individual differences of trainees using the expert experience method. is the adjustment coefficient, which is used to control the intensity of the nonlinear impact of the operation deviation on the feedback; is the adjustment coefficient, which is used to control the periodic effect of learning progress on feedback; It is an adjustment coefficient, which is used to control the impact of students’ mastery accuracy on learning feedback. By performing a logarithmic transformation on students’ mastery accuracy, the growth rate of students’ learning progress can be effectively slowed down.

[0066] Furthermore, in order to make the learning plan more adaptable to the individual needs of students, a fuzzy reasoning mechanism is introduced. The role of the fuzzy reasoning mechanism is to make the learning plan more personalized according to the current learning progress of the students. The difference between the target learning progress and the student’s current learning progress can be expressed as:

[0067]

[0068] in, It is the target progress set by the teaching and training system; It is the learning progress error value, which is used to measure the deviation of the students’ learning progress from the target learning progress.

[0069] Furthermore, the student's learning task is adjusted based on the learning progress error value to determine whether the learning progress needs to be accelerated or slowed down. The specific formula is:

[0070]

[0071] in, It is the learning plan adjustment amount, which indicates the specific amount by which the student's learning progress needs to be adjusted; and It is the degree of membership between lagging and advancing, which is used to reflect the direction and intensity of learning plan adjustment when the student's learning progress lags behind or advances ahead. If the student's learning progress lags behind, the degree of membership will be higher, prompting accelerated learning; and Respectively represent the adjustment amount when the student's learning progress lags behind or is ahead; , , It is a fixed adjustment factor, which is set by expert experience according to the course difficulty or the individual needs of the students; It is a fixed reduction factor, which is determined by the course design or the students' learning situation using expert experience.

[0072]

[0073]

[0074] in, is the maximum learning progress error value, that is, when the learning progress error value exceeds At this time, it is considered that the students’ progress can no longer be considered as “lagging behind”.

[0075] In order to further optimize the students' learning process, especially to adjust the deviations in the students' operations, a weighted error optimization algorithm is used. After each operation of the students, the operation error compared with the standard method is calculated. The error calculation formula is:

[0076]

[0077] in, is the total error, indicating that the student The total error generated when performing all operations. The total error is obtained by weighting the errors to reflect the overall accuracy of the student's operations; is the weighted coefficient of each error term, indicating the contribution of different operation terms to the total error, which is determined according to the expert experience method; It is The actual value of the operation indicates that the student Specific values ​​of the techniques or movements performed in this training (such as angle, strength, etc.); Indicated in Specific values ​​(such as angle, force, etc.) when performing standard techniques in training; is the total number of operations.

[0078] Finally, through the above process, a personalized learning plan for the student will be generated. Specifically, a quantitative indicator of a learning plan is defined to describe and generate a personalized learning plan. The quantitative indicator of the learning plan is a comprehensive measure of the tasks and goals that the student should complete in the current learning stage. The size and nature of the quantitative indicator of the learning plan can help generate the time arrangement and priority of the learning tasks. The formula for the quantitative indicator of the learning plan is expressed as:

[0079]

[0080] in, It's time Quantitative indicators of the learning plan; It's time The study plan The learning status of a task; It is the students at the time For the study plan Feedback response for each task; It's time The study plan The amount of adjustment for each task; It's time The study plan The error of the task; , , , Represents the weight, which is used to reflect the importance in generating the learning plan; is the total number of tasks in the learning plan.

[0081] Furthermore, according to the calculated quantitative indicators of the learning plan, adjust the priority of the task:

[0082] Task priority adjustment formula:

[0083]

[0084] in, It's time The study plan The larger the value, the higher the priority of the task.

[0085] Different time is allocated to each task according to its priority. The total time allocation for learning tasks will be dynamically adjusted based on their priority and complexity. For example, tasks with higher priority and greater difficulty will be allocated more learning time, while tasks with lower priority and less difficulty will be allocated relatively less time.

[0086] Task time allocation formula:

[0087]

[0088] in, It's time The study plan Time allocation for tasks, It's time The total time available for students to study.

[0089] Furthermore, the task content and learning objectives can be obtained from real-time improvement suggestions.

[0090] After the above processing, the generated personalized learning plan includes task priority, time allocation, task content and learning objectives.

[0091] Based on the personalized learning plan, the existing 3D modeling, virtual reality and other technologies are used to generate an interactive virtual child anatomical model. At the same time, the operation data of the trainees in operation is obtained, and the data is annotated in the virtual child anatomical model to obtain the annotation results.

[0092] S2. Comprehensively evaluate the student's operation data through recursive hierarchical error feedback and adaptive adjustment algorithm to generate operation evaluation results; based on the operation evaluation results, adjust the student's operation using the recursive adjustment mechanism to obtain the student's operation adjustment amount; generate real-time improvement suggestions based on the student's operation adjustment amount; adjust the learning content according to the real-time improvement suggestions to obtain the latest personalized learning plan; train according to the latest personalized learning plan until the training is completed.

[0093] Through the recursive hierarchical error feedback and adaptive adjustment algorithm, the student's operation data is comprehensively evaluated, and the student's operation data is compared item by item with the operation data of the standard method to generate detailed operation evaluation results. The recursive hierarchical error feedback and adaptive adjustment algorithm accurately evaluates the student's operation performance and generates personalized improvement suggestions through real-time and dynamic error analysis. At the same time, by associating the error feedback of each operation with the student's operation performance, a dynamic learning mechanism with recursive adjustment capabilities is established. The specific implementation process is as follows:

[0094] Remember the moment The student operation data is , the standard method operation data is ; Among them, the standard manipulation data comes from the standard manipulation database. Since the distribution and magnitude of the student manipulation data may be different from the standard manipulation data, the student manipulation data is standardized with an attenuation factor to make it have the same distribution and magnitude as the standard manipulation data. The formula is as follows:

[0095]

[0096] in, It is the students’ operation data after standardization; It is the mean of the students’ operation data, reflecting the students’ average operation performance over a period of time. It is obtained by averaging the students’ operation data over a period of time. is the decay factor, which represents the time decay control parameter and is used to control the rate of time decay; Indicates time point; It is the current moment or the most recent assessment time point, which serves as the benchmark time for evaluating trainees’ operational performance.

[0097] In order to capture the multi-dimensional characteristics of the operation and the time-varying nature of the student's operation performance, a nonlinear weighted error calculation method is introduced to calculate the error between the student's operation data and the standard method operation data. The nonlinear weighted error calculation formula is as follows:

[0098]

[0099] in, The data of students' operation and the data of standard operation at the time The weighted error, i.e., the error value between the student's operation data and the standard operation data, indicates the comprehensive deviation between the student's current operation data and the standard operation data, and is the core indicator of dynamic error feedback. is an exponential adjustment factor used to control the sensitivity of the operating deviation to the error value and is set according to the expert experience method; is a control parameter used to control the speed of exponential decay; is the time weight factor, which is used to indicate the degree of dynamic adjustment of the error value at the current moment. It is generated by the time decay formula: , is the time decay factor.

[0100] The errors in the path error, time error, force error, etc. of the student's operation are calculated in the same way as the weighted error. It is only necessary to add the standardized student operation data in the calculation formula And the corresponding standard technique operation data can be replaced with path, time, strength and other operation data.

[0101] In order to further improve the accuracy of the evaluation, the error feedback is divided into multiple levels, taking into account the impact of multiple dimensions such as path error, time error, force error, etc. A hierarchical error feedback mechanism is introduced, in which different error feedback dimensions are weighted and combined, and the formula is as follows:

[0102]

[0103] in, It is the quantitative result of the student's overall operation error, that is, the student's overall operation error value, which represents error feedback and integrates the errors of multiple operation dimensions (path, time, and force), reflecting the overall performance of the student's operation; , , They represent path error, time error and force error respectively; , , They are the weight coefficients of path error, time error, and force error, respectively, reflecting the impact of the error in each operation dimension on the overall error.

[0104] Furthermore, a recursive adjustment mechanism is used to continuously adjust the student's operation so that it gradually approaches the standard technique. The recursive adjustment mechanism adaptively adjusts the student's operation according to the student's error feedback, and calculates the student's error at time Operation adjustment , the formula is as follows:

[0105]

[0106] in, It is the students at the time The amount of operational adjustment; It is the adjustment proportional coefficient, which is used to control the overall amplitude of the operation adjustment. It determines the sensitivity of the error feedback to the operation adjustment. The larger the value, the larger the amplitude of the adjustment, and the more significant the change of the trainee's operation; the smaller the value, the more conservative the adjustment amplitude; is a nonlinear growth coefficient used to control the sensitivity of the effect of error feedback on the operation adjustment amount.

[0107] Keep students at all times The overall operation error value is taken as the operation evaluation result. Based on the above error feedback and the trainees’ The system calculates the amount of operation adjustment and finally generates real-time improvement suggestions for the trainees, providing the dimensions that need to be improved for each operation step (such as path, strength, time, etc.), and gives the specific amount of operation. For example, the trainee may get the following improvement suggestions: "Reduce the strength to a certain value" or "Adjust the path to make it conform to the standard technique". At the same time, the operation evaluation results and real-time improvement suggestions are stored in the database.

[0108] Through the above process, trainees can receive accurate error feedback and real-time improvement suggestions in each operation, thereby effectively improving operation accuracy and quickly approaching standard techniques.

[0109] Furthermore, on the virtual anatomical model, use green to mark the standard technique operation data and use red to mark the trainee operation data to obtain the marking results; at the same time, the operation evaluation results are presented on the screen in real time to achieve dynamic display. At the same time, the learning content is adjusted according to the adjustment amount in the real-time improvement suggestions to obtain the latest personalized learning plan, and training is carried out according to the latest personalized learning plan until the training is completed.

[0110] In summary, a pediatric TCM acupoint massage teaching and training system and method have been completed.

[0111] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0112] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0113] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A teaching and training method for pediatric TCM acupoint massage, characterized in that: The following steps are involved: S1. After the student logs in, the student's learning data is obtained, and a personalized learning plan is generated based on the learning data using the dynamic state feedback and nonlinear adaptive learning plan generation algorithm. In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, the student's learning state model is constructed. The student's learning state includes four dimensions: mastering accuracy, operation deviation, learning progress and feedback response ability. After the student's learning state model is constructed, a nonlinear feedback model is introduced to simulate the student's feedback mechanism in the learning process, reflecting the student's feedback response and learning progress. The specific formula is: ， in, is the student’s feedback response, indicating that The degree to which feedback and adjustments are made to students’ learning status; Indicates the accuracy of students’ mastery of acupoints or techniques; Indicates the deviation of trainees in the operation process; Indicates the learning progress of students; is the weighting coefficient of feedback; is the adjustment coefficient, which is used to control the intensity of the nonlinear impact of the operation deviation on the feedback; is the adjustment coefficient, which is used to control the periodic effect of learning progress on feedback; is the adjustment coefficient, which is used to control the impact of students’ mastering accuracy on learning feedback; Introducing fuzzy reasoning mechanism to dynamically adjust learning tasks according to the difference between students’ current learning progress and target learning progress; And define the quantitative indicators of the learning plan; the formula for the quantitative indicators of the learning plan is: ， in, It's time Quantitative indicators of the learning plan; It's time The study plan The learning status of a task; It is the students at the time For the study plan Feedback response for each task; It's time The study plan The amount of adjustment for each task; It's time The study plan The error of the task; , , , represents weight; is the total number of tasks in the learning plan; adjust the priority of tasks according to the quantitative indicators of the learning plan; allocate different time for each task based on the priority of the task; and obtain the task content and learning objectives from the real-time improvement suggestions to generate a personalized learning plan including task priority, time allocation, task content and learning objectives; Generate an interactive virtual child anatomical model based on the personalized learning plan, obtain the operation data of the trainees in operation, and perform annotation processing on the virtual child anatomical model to obtain the annotation results; S2. Comprehensively evaluate the student's operation data through recursive hierarchical error feedback and adaptive adjustment algorithm to generate operation evaluation results; based on the operation evaluation results, adjust the student's operation using the recursive adjustment mechanism to obtain the student's operation adjustment amount; generate real-time improvement suggestions based on the student's operation adjustment amount; adjust the learning content according to the real-time improvement suggestions to obtain the latest personalized learning plan; train according to the latest personalized learning plan until the training is completed.

2. The pediatric TCM acupoint massage teaching and training method according to claim 1, characterized in that: The S1 specifically includes: When a student logs in, the user information table stored in the database is queried to check the matching of the user name and password, verify the permissions and load the corresponding learning data; the learning data includes historical learning records, current progress, operation evaluation results and real-time improvement suggestions.

3. The teaching and training method of pediatric TCM acupoint massage according to claim 1, characterized in that: The S1 specifically includes: In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, the specific implementation process of the fuzzy reasoning mechanism is as follows: calculate the error between the target learning progress and the student's current learning progress to obtain the learning progress error value; adjust the student's learning task based on the learning progress error value to obtain the learning plan adjustment amount.

4. The teaching and training method of pediatric TCM acupoint massage according to claim 1, characterized in that: The S1 specifically includes: In the dynamic state feedback and nonlinear adaptive learning plan generation algorithm, a weighted error optimization algorithm is used to calculate the operation error compared with the standard method after each operation of the trainee.

5. The teaching and training method of pediatric TCM acupoint massage according to claim 1, characterized in that: The S2 specifically includes: In the process of implementing the recursive hierarchical error feedback and adaptive adjustment algorithm, the student operation data is standardized with an attenuation factor to obtain the standardized student operation data; based on the standardized student operation data, a nonlinear weighted error calculation method is introduced to calculate the error between the student operation data and the standard technique operation data from the standard technique database. The specific formula is as follows: ， in, The data of students' operation and the data of standard operation at the time The weighted error of is the index adjustment factor; It is the students’ operation data after standardization; Manipulate data using standard techniques; is a control parameter used to control the speed of exponential decay; is the time weight factor, and the formula is: , is the time decay factor; It is the benchmark time for evaluating trainees’ operational performance; By replacing the standardized student operation data and the corresponding standard technique operation data in the nonlinear weighted error calculation method with path, time, and force operation data, the path error, time error, and force error of the student operation are obtained.

6. The teaching and training method of pediatric TCM acupoint massage according to claim 5, characterized in that: The S2 specifically includes: In the process of implementing the recursive hierarchical error feedback and adaptive adjustment algorithm, a hierarchical error feedback mechanism is introduced based on path error, time error, and force error to calculate the student's overall operation error value and obtain the student's error feedback; the student's overall operation error value is used as the operation evaluation result, and the operation evaluation result is displayed dynamically.

7. The teaching and training method of pediatric TCM acupoint massage according to claim 6, characterized in that: The S2 specifically includes: In the process of implementing the recursive hierarchical error feedback and adaptive adjustment algorithm, the recursive adjustment mechanism is used to adjust the student's operation according to the student's error feedback, and the student's operation adjustment amount is calculated; the formula is as follows: ， in, It is the students at the time The amount of operational adjustment; is the adjustment scale factor; is the overall operation error value of the trainees, indicating error feedback; is the nonlinear growth coefficient; Based on the error feedback and the trainee's operational adjustments, real-time improvement suggestions are generated for the trainee; and the operational evaluation results and real-time improvement suggestions are stored in the database.

8. A pediatric TCM acupoint massage teaching and training system, applied to the pediatric TCM acupoint massage teaching and training method as claimed in claim 1, characterized in that: Includes the following parts: User management module, virtual human interaction module, dynamic learning module, force sensing feedback module, AI intelligent guidance module; The user management module is the entrance to the system and is responsible for managing the student's identity information, historical learning records, and initialization of the learning plan. After the student logs in, a personalized learning plan is generated based on the historical learning record, current learning progress, operation evaluation results, and real-time improvement suggestions, and the personalized learning plan is passed to the virtual human interaction module; The virtual human interaction module generates an interactive virtual child anatomical model according to the personalized learning plan provided by the user management module, and receives the trainee operation data provided by the force sensing feedback module in real time; Use green to mark the standard manipulation data on the virtual anatomical model, and use red to mark the trainee manipulation data to obtain the marking results; The standard manipulation operation data comes from the standard manipulation database; the annotation results are sent to the dynamic learning module; The dynamic learning module receives and displays the annotation results provided by the virtual human interaction module in real time. At the same time, it dynamically displays the operation evaluation results provided by the AI ​​intelligent guidance module and dynamically adjusts the learning content according to the real-time improvement suggestions provided by the AI ​​intelligent guidance module until the training is completed. The force sensing feedback module is used to capture the trainee's operation data during operation, and transmit the trainee's operation data to the virtual human interaction module in real time for annotation processing, and at the same time transmit the trainee's operation data to the AI ​​intelligent guidance module; The AI ​​intelligent guidance module uses recursive hierarchical error feedback and adaptive adjustment algorithms to comprehensively evaluate the students' operation data and generate operation evaluation results. Based on the operation evaluation results, the recursive adjustment mechanism is used to obtain the students' operation adjustment amount. Generate real-time improvement suggestions based on the operation evaluation results and the trainees' operation adjustments; The operation evaluation results and real-time improvement suggestions are passed to the dynamic learning module, and at the same time, the operation evaluation results and real-time improvement suggestions are stored in the database.

Images