Experiment teaching system and teaching method

Abstract

The invention provides an experiment teaching system and a teaching method, and relates to the technical field of medicine production teaching experiments, and the experiment teaching system comprises a basic setting module, a theory learning module, a GMP simulation module and an entity experiment module. The basic setting module is used for setting basic information such as learning direction; the theory learning module provides learning materials and automatically generates comprehensive test questions according to learning conditions of students; the GMP simulation module constructs a GMP workshop simulation environment by using VR and AR technologies, carries out following experiment simulation practice and independent experiment simulation practice, and evaluates a practice result; and after the theoretical test score and the virtual training score reach the standard, the entity experiment module allows the students to carry out practical operation, and records and evaluates the practical operation process and result. According to the experiment teaching method, teaching processes are implemented in sequence according to the system modules.

Description

Technical Field

[0001] The invention relates to the technical field of pharmaceutical production experiment teaching, and in particular to an experiment teaching system and a teaching method. Background Art

[0002] Under the traditional professional teaching model, there are many deficiencies in experimental teaching, which seriously restricts the teaching effect and the cultivation of students' abilities. It is difficult for students to effectively connect with actual work scenarios during the basic subject learning stage, especially in highly specialized environments such as GMP workshops, resulting in their lack of intuitive and in-depth understanding. At the same time, due to the high cost of GMP workshop equipment and the need for large-scale installation, many colleges and universities are limited by funding and site conditions and can only partially or completely set up corresponding teaching facilities. This not only fails to meet the needs of standardized and unified professional teaching, but also seriously hinders the comprehensive cultivation of students' practical skills.

[0003] At the experimental teaching level, the teaching and assessment functions of the existing model are still imperfect, and it is difficult to accurately evaluate the comprehensive ability level of students. In addition, the teaching content is seriously out of touch with the future employment needs of higher vocational students, the requirements of vocational skills competitions, and the standards for obtaining relevant certificates, resulting in vague learning goals for students and a significant reduction in their employment competitiveness. More importantly, the content of experimental teaching is often limited to the scope of knowledge in a single subject, and there is a lack of necessary integration and coordination mechanisms between experiments in various subjects, which makes students face huge challenges in building a comprehensive and systematic knowledge system. The teaching methods are also too old, mainly based on one-way lectures by teachers, lacking innovation and interactivity, and it is difficult to stimulate students' interest in learning and desire to explore. At the same time, teaching resources are scattered and underutilized, and there is a lack of organic linkage between on-campus laboratories, training bases, and off-campus enterprise resources, resulting in a serious disconnection between teaching and actual production and scientific research activities.

[0004] In view of the above problems, the present invention proposes a new experimental teaching system and teaching method, which aims to solve the various deficiencies in traditional experimental teaching and improve students' practical ability and employment competitiveness by combining intelligence, simulation and entity. Summary of the invention

[0005] In view of the defects in the prior art, the present invention provides an experimental teaching system and teaching method, which greatly improves the effect of experimental teaching and the practical ability of students by combining intelligence, simulation and entity.

[0006] In a first aspect, the present invention provides an experimental teaching system, the system comprising:

[0007] A basic setting module, used to set basic information, including setting a learning direction;

[0008] Theoretical learning module, used to provide learning materials according to the learning direction, automatically generate comprehensive test questions according to the students' learning situation to conduct theoretical tests on students, and obtain theoretical test scores;

[0009] The GMP simulation module is used to build a GMP workshop simulation environment using VR and AR technologies to conduct follow-up experiment simulation exercises and independent experiment simulation exercises, and evaluate the results of independent experiment simulation exercises to obtain virtual training scores;

[0010] The physical experiment module is used to allow practical operation when the theoretical test score and the virtual training score are both greater than the set value, record the practical operation process and the practical operation results, evaluate the practical operation process and the practical operation results, and obtain the physical training score.

[0011] Preferably, the learning directions include conventional directions, job competency directions, professional skills competition directions, and professional certificate directions.

[0012] Preferably, comprehensive test questions are automatically generated according to the students' learning situation to conduct theoretical tests on the students, including:

[0013] Calculate the knowledge mastery index according to the student's learning situation, wherein the learning situation includes the total number of questions answered, the number of correct questions answered, the number of incorrect questions answered, the time between questions answered, and the total time spent answering questions for each knowledge point;

[0014] Determine strong knowledge points and weak knowledge points according to the knowledge mastery index;

[0015] Considering the correlation between strong knowledge points and weak knowledge points and the correlation between weak knowledge points, calculating the correction factor of the weak knowledge point, and correcting the knowledge mastery index of the weak knowledge point according to the correction factor of the weak knowledge point;

[0016] The question ratio and question difficulty are determined according to the corrected knowledge mastery index, and comprehensive test questions are automatically generated according to the question ratio and question difficulty.

[0017] Preferably, the calculation formula of the knowledge mastery is:

[0018]

[0019] Among them, K represents the degree of knowledge mastery, T, C, U, T s , Var(I) respectively represent the variance of the total number of questions, the number of correct questions, the number of incorrect questions, the total time for answering questions, and the time interval between answering questions corresponding to the knowledge point. α and δ are both constants.

[0020] Preferably, the calculation formula of the weak knowledge point correction factor is:

[0021]

[0022] Among them, F w represents the weak knowledge point correction factor of weak knowledge point w, r ws represents the correlation between weak knowledge point w∈W and strong knowledge point s∈S, K s represents the knowledge mastery index of strong knowledge points, S and n represent the set of strong knowledge points S and the number of strong knowledge points in the set, respectively, and r ww' represents the association between a weak knowledge point w∈W and all other weak knowledge points w'∈W\{w}, K w' represents the knowledge mastery index of other weak knowledge points w'∈W\{w}, W and m represent the set of weak index points and the number of other weak knowledge points in the set respectively, and A is a constant.

[0023] As a preferred method, the formula for determining the question ratio and question difficulty according to the corrected knowledge mastery index is:

[0024]

[0025] D i,i∈H =D base,i ×(1-K' i ) γ γ

[0026] Among them, P i,i∈H represents the difficulty of the question for knowledge point i, K i 'Represents the corrected knowledge mastery index of knowledge point i, K' j represents the corrected knowledge mastery index of knowledge point j, m+n represents the total number of knowledge points, and D i,i∈H Indicates the difficulty of the question, D base,i represents the basic difficulty coefficient of knowledge point i, and γ represents the adjustment factor.

[0027] As a preferred method, VR and AR technologies are used to construct a GMP workshop simulation environment for follow-up experimental simulation exercises and independent experimental simulation exercises, including:

[0028] Determine a prompting method for following the experiment, and perform an experiment demonstration according to the prompting method so that students can perform simulation exercises for following the experiment;

[0029] Obtaining the number of simulation exercises for the follow-up experiment and the duration of a single exercise, and calculating a follow-up exercise score according to the number of simulation exercises for the follow-up experiment, the duration of a single exercise, and the number of errors in the follow-up exercise;

[0030] When the follow-up practice score is greater than the set follow-up practice score, the independent experiment simulation practice is opened.

[0031] Preferably, the results of the independent experimental simulation exercises are evaluated to obtain a virtual training score, including:

[0032] The number of independent experiment simulation exercises, the duration of a single exercise, the number of successful exercises, the number of failed exercises, and the failure nodes are obtained, and the independent exercise score is calculated according to the number of independent experiment simulation exercises, the duration of a single exercise, the number of successful exercises, the number of failed exercises, and the failure nodes;

[0033] Calculate the average independent practice score of multiple consecutive successful independent experimental simulation exercises, and use the average independent practice score as the virtual training score.

[0034] Preferably, the practical operation process and the practical operation results are evaluated to obtain the entity training score including:

[0035] Acquire video data of the practical operation process; extract key frames of the practical operation process to obtain a key frame sequence and a key time sequence, compare the key frame sequence with a standard key frame sequence to obtain a similarity sequence, input the key time sequence and the similarity sequence into a pre-built process evaluation model to obtain a process score;

[0036] Obtaining quantitative data of practical operation results, and determining a result score according to the quantitative data of the practical operation results;

[0037] The entity training score is calculated based on the process score and the result score.

[0038] In a second aspect, the present invention provides an experimental teaching method, the system comprising:

[0039] Step 1: Set basic information, including setting learning direction;

[0040] Step 2, providing learning materials according to the learning direction, automatically generating comprehensive test questions according to the student's learning situation to conduct a theoretical test on the student, and obtaining a theoretical test score;

[0041] Step 3: Use VR and AR technologies to build a GMP workshop simulation environment to conduct follow-up experiment simulation exercises and independent experiment simulation exercises, and evaluate the results of independent experiment simulation exercises to obtain virtual training scores;

[0042] Step 4: When the theoretical test score and the virtual training score are both greater than the set values, practical operation is allowed, the practical operation process and the practical operation results are recorded, and the practical operation process and the practical operation results are evaluated to obtain the entity training score.

[0043] The beneficial effects of the present invention are:

[0044] 1) Improve teaching effect and students' practical ability: Through the combination of intelligence, simulation and entity, the present invention effectively solves the problem of traditional experimental teaching being out of touch with actual work scenes, and improves students' practical ability and employment competitiveness.

[0045] 2) Optimize resource allocation: The GMP workshop simulation environment built using VR and AR technology reduces the high equipment costs and large-scale installation requirements, allowing more colleges and universities to set up corresponding teaching facilities to meet the standardized and unified professional teaching needs.

[0046] 3) Improve teaching and assessment functions: The experimental teaching system and method provided by the present invention can accurately evaluate the comprehensive ability level of students, ensure that the teaching content is closely connected with the future employment needs of higher vocational students, the requirements of vocational skills competitions and the standards for obtaining relevant certificates. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0048] Figure 1 A schematic diagram of the structure of an experimental teaching system provided by one embodiment of the present invention;

[0049] Figure 2 A flowchart of an experimental teaching method provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0051] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0052] Example 1

[0053] like Figure 1 As shown, an experimental teaching system, the system comprises:

[0054] The basic setting module is used to set basic information, and the basic information includes setting the learning direction.

[0055] This module is responsible for initializing the system, including entering user information (such as name, student ID, major, etc.) and setting the direction of study. The choice of study direction is not limited to the preset general options, but also supports user customization to meet different learning backgrounds and needs.

[0056] Specifically, the learning directions include general direction, job competency direction, vocational skills competition direction, and vocational certificate direction. Job competency direction: customized learning for the skills and abilities required for specific occupations to improve the user's employment competitiveness. Vocational skills competition direction: targeted learning and training are provided according to the requirements of various vocational skills competitions to help users improve their competition level. Vocational certificate direction: learning paths and test question banks are designed according to the content and requirements of various vocational certificate examinations to help users pass the examinations smoothly.

[0057] Furthermore, the basic setting module connects with the enterprise job database to obtain basic job information, and determines the theoretical knowledge, professional skills, job certificates and other information required by students based on the basic job information, thereby realizing customized learning for the job.

[0058] The basic setting module and its learning direction setting function in the present invention provide an effective solution to the problem that the future employment needs of higher vocational students, professional skills competitions and related certificate examinations are not closely connected.

[0059] The theoretical learning module is used to provide learning materials according to the learning direction, automatically generate comprehensive test questions according to the students' learning situation to conduct theoretical tests on students, and obtain theoretical test scores.

[0060] According to the learning direction selected by the user, the system intelligently pushes relevant learning materials, including video tutorials, graphic materials, online courses, etc. At the same time, the system automatically adjusts the difficulty and type of test questions according to the user's learning progress and answering situation, ensuring that the test content is in line with the user's current knowledge level and can effectively test their theoretical mastery.

[0061] Specifically, comprehensive test questions are automatically generated according to the students' learning situation to conduct a theoretical test on the students, including: calculating a knowledge mastery index according to the students' learning situation, wherein the learning situation includes the total number of questions corresponding to each knowledge point, the number of correct questions, the number of incorrect questions, the time interval between questions, and the total time for answering questions; determining strong knowledge points and weak knowledge points according to the knowledge mastery index; calculating a correction factor for weak knowledge points, taking into account the correlation between strong knowledge points and weak knowledge points and the correlation between weak knowledge points, and correcting the knowledge mastery index of the weak knowledge points according to the weak knowledge point correction factor; determining a question ratio and a question difficulty according to the corrected knowledge mastery index, and automatically generating comprehensive test questions according to the question ratio and the question difficulty.

[0062] More specifically, the calculation formula for the knowledge mastery is:

[0063]

[0064] Among them, K represents the degree of knowledge mastery, T, C, U, Ts , Var(I) respectively represent the variance of the total number of questions, the number of correct questions, the number of incorrect questions, the total time for answering questions, and the time interval between answering questions corresponding to the knowledge point. α and δ are both constants.

[0065] The higher the correlation between weak knowledge points and strong knowledge points, the lower the knowledge mastery index is. This is because the related knowledge points should be better learned but students do not have better mastery. The higher the correlation between weak knowledge points and weak knowledge points, the lower the knowledge mastery is. This is because the mastery of related knowledge points is low, which will have a superimposed effect.

[0066] Based on the above reasons, the calculation formula of the weak knowledge point correction factor provided by the embodiment of the present invention is:

[0067]

[0068] Among them, F w represents the weak knowledge point correction factor of weak knowledge point w, r ws represents the correlation between weak knowledge point w∈W and strong knowledge point s∈S, K s represents the knowledge mastery index of strong knowledge points, S and n represent the set of strong knowledge points S and the number of strong knowledge points in the set, respectively, and r ww' represents the association between a weak knowledge point w∈W and all other weak knowledge points w'∈W\{w}, K w' represents the knowledge mastery index of other weak knowledge points w'∈W\{w}, W and m represent the set of weak index points and the number of other weak knowledge points in the set respectively, and A is a constant.

[0069] The present invention can calculate the correction factor of the weak knowledge point and correct the knowledge mastery index of the weak knowledge point according to the correction factor, which helps to more accurately evaluate the learning situation of students and generate targeted test questions.

[0070] The difficulty of the questions should match the students' mastery of the knowledge points, which should be able to test the students' true level and avoid inaccurate evaluation caused by too difficult or too easy questions. In the embodiment of the present invention, a basic difficulty coefficient is set for each knowledge point, and this coefficient can be determined according to the complexity and importance of the knowledge point. Then, the difficulty coefficient is adjusted according to the corrected knowledge mastery index.

[0071] Specifically, the formula for determining the question ratio and question difficulty based on the revised knowledge mastery index is:

[0072]

[0073] D i,i∈H =D base,i ×(1-K' i ) γ γ

[0074] Among them, P i,i∈H represents the difficulty of the question for knowledge point i, K i 'Represents the corrected knowledge mastery index of knowledge point i, K' j represents the corrected knowledge mastery index of knowledge point j, m+n represents the total number of knowledge points, and D i,i∈H Indicates the difficulty of the question, D base,i represents the basic difficulty coefficient of knowledge point i, and γ represents the adjustment factor, which is used to control the sensitivity of the difficulty coefficient to the change of mastery level. When γ is large, a small decrease in mastery level will lead to a large increase in the difficulty coefficient; when γ is small, this change is relatively gentle.

[0075] The embodiment of the present invention formulates a more scientific and reasonable question-setting strategy based on the revised knowledge mastery index, thereby more effectively evaluating students' learning situation and promoting their learning progress, and providing data support for subsequent entity experiments.

[0076] The GMP simulation module is used to build a GMP workshop simulation environment using VR and AR technologies to conduct follow-up experiment simulation exercises and independent experiment simulation exercises, and evaluate the results of independent experiment simulation exercises to obtain virtual training scores;

[0077] In the process of drug production, the operational standardization and efficiency of the GMP workshop are crucial. In order to improve students' practical skills and understanding of the GMP workshop process, this example uses VR and AR technology to build a GMP workshop simulation environment. Through following experimental simulation exercises and independent experimental simulation exercises, students can learn and master the operation process of the GMP workshop more intuitively.

[0078] Specifically, the system intelligently pushes simulation experiment-related materials based on the learning direction selected by the user.

[0079] In this embodiment, VR and AR technologies are used to construct a GMP workshop simulation environment for follow-up experiment simulation exercises and independent experiment simulation exercises, including: determining a follow-up experiment prompt method, and performing an experiment demonstration according to the prompt method for students to perform follow-up experiment simulation exercises; obtaining the number of follow-up experiment simulation exercises and the duration of a single exercise, and calculating a follow-up exercise score based on the number of follow-up experiment simulation exercises, the duration of a single exercise, and the number of follow-up exercise errors; when the follow-up exercise score is greater than the set follow-up exercise score, opening an independent experiment simulation exercise.

[0080] Among them, the prompt methods include voice prompts, text prompts, etc.

[0081] Since it is a follow-up exercise, this embodiment assumes that each follow-up exercise is successful. This is because the system will automatically record the wrong exercise nodes and reset the wrong exercise nodes during the follow-up exercise. At this time, the key factors of the follow-up exercise process are the duration of each exercise and the number of follow-up exercises, and the follow-up exercise score is calculated based on the two.

[0082] Obviously, the number of reset times of the erroneous practice node can also be considered, and the reset influence coefficient can be calculated based on the number of reset times of the erroneous practice node and the reset influence function, wherein the reset influence function includes the weight of the practice node, and the weight is determined based on the depth of the practice node. The depth includes sequence depth and duration depth. The later the practice sequence is, the higher the sequence depth is. The greater the difference between the correct duration and the standard duration from the start time of the practice to the erroneous practice node is, the greater the duration depth is. The depth of the practice node is calculated based on the weights of the two. The reset influence function also includes the number exponent. As the number of resets increases, the influence coefficient increases exponentially.

[0083] In this embodiment, the results of independent experimental simulation exercises are evaluated to obtain a virtual training score, including: obtaining the number of independent experimental simulation exercises, the duration of a single exercise, the number of successful exercises, the number of failed exercises, and the failure nodes, and calculating the independent exercise score based on the number of independent experimental simulation exercises, the duration of a single exercise, the number of successful exercises, the number of failed exercises, and the failure nodes; calculating the average independent exercise score of multiple consecutive successful independent experimental simulation exercises, and using the average independent exercise score as the virtual training score.

[0084] Specifically, the independent practice score is calculated by weighted summation, considering factors such as the number of follow-up experimental simulation exercises, the duration of a single exercise, and the number of successful exercises.

[0085] When following the experimental simulation practice, let N be the number of following experimental simulation practice, T be the average length of a single practice, R be the number of resets of the error node, W be the weight of the error node, calculated according to the depth of the practice node (sequential depth and duration depth), E be the number index, and the influence coefficient increases exponentially with the number of resets. The basic score B is B score =a*N+b*T, where a and b are weight coefficients, which need to be adjusted according to actual conditions. The impact coefficient is reset to Reset impact =W*E^R.

[0086] Further, the final follow-up exercise score considering the reset effect is Follow score =B score -Reset impact .

[0087] When the follow-up practice score threshold is set to Threshold follow , when Follow score>Threshold follow Independent experimental simulation exercises are only available when the

[0088] When performing independent experimental simulation exercises, let M be the number of independent experimental simulation exercises, S be the number of successful exercises, F be the number of failed exercises, P be the set of nodes (or error types) that failed each time, and each node (or error type) has a corresponding weight w f , K is the number of consecutive successful independent experimental simulation exercises, Ind scorej is the score of the jth consecutive successful independent experimental simulation exercise, and the independent exercise score is Ind score =c*Md*max(0,AvgTime-T)-e*Σ f＝Q (w f *f f )+f*Sg*F, where c, d, e, f and g are weight coefficients, AvgTime represents the average single practice time, T represents the ideal average single practice time threshold, and f f is the number of occurrences of the fth error node (or error type); the mean score of consecutive successful exercises is Mean indscore =Σ(Ind scorej ) / K, virtual training score is Virtual trainingscore =Mean_ indscore .

[0089] Specifically, weak knowledge points in theoretical learning automatically trigger targeted experimental simulation exercises in the simulation module. For example, if a student has weak knowledge of "aseptic operation", the system will push GMP workshop aseptic process simulation exercises. The difficulty of the exercises can be determined based on the knowledge mastery index or knowledge mastery.

[0090] Furthermore, the GMP simulation module also includes a competition simulation module, which can simulate the real competition environment, including time-limited operation requirements and judges' scoring rules. By introducing the AI ​​referee system, it can provide real-time feedback on the standardization of students' operations and help students adapt to the rhythm and scoring standards of the competition. At the same time, it automatically records the students' historical scores in the competition simulation and generates a competition ability radar chart to intuitively display the students' performance in various skills. By analyzing these data, students can quickly identify their skill shortcomings and formulate targeted improvement plans accordingly.

[0091] A competition performance score is added to the virtual training score, which comprehensively considers the student's independent experiment success rate, operation efficiency, standardization and other aspects to form an evaluation system that comprehensively reflects the student's competition ability. This helps students understand their competition strength more clearly and make full preparations for future competitions. It should be noted that the competition performance score can be set according to different competition rules, which will not be repeated in this embodiment.

[0092] In order to increase the reliability of the virtual training score, the final virtual training score can be obtained by weighted summing the independent practice score and the competition performance score.

[0093] The physical experiment module is used to allow practical operation when the theoretical test score and the virtual training score are both greater than the set value, record the practical operation process and the practical operation results, evaluate the practical operation process and the practical operation results, and obtain the physical training score.

[0094] In this embodiment, the practical operation process and the practical operation results are evaluated to obtain an entity training score, which includes: obtaining video data of the practical operation process; extracting key frames of the practical operation process to obtain a key frame sequence and a key time sequence, comparing the key frame sequence with a standard key frame sequence to obtain a similarity sequence, and inputting the key time sequence and the similarity sequence into a pre-built process evaluation model to obtain a process score; obtaining quantitative data of the practical operation results, and determining a result score based on the quantitative data of the practical operation results; and calculating the entity training score based on the process score and the result score.

[0095] Specifically, the process evaluation model is a bidirectional LSMT model, which can better learn the association information in the similarity sequence and the key time series.

[0096] At the beginning of the practice, start the camera to record until the end of the practice. Ensure that the recorded video is of good quality, without obstructions or blur. Store the recorded video data on a designated server or local storage device for subsequent processing.

[0097] After the practical operation, various quantitative data generated during the experiment, such as experimental parameters, experimental result values, etc., are collected and sorted to ensure the accuracy and completeness of the data.

[0098] The video data of the practical operation process is processed by using video processing software or algorithms to parse the recorded video, extract the image data of each frame, and use the image recognition algorithm to identify the key frames in the practical operation process. Among them, the key frames include the start, end or important turning points of the experimental steps. Compare the extracted key frame sequence with the preset standard key frame sequence to calculate the similarity. The similarity can be calculated by image matching algorithms (such as SIFT, SURF, etc.) or deep learning algorithms (such as convolutional neural networks). Record the time point corresponding to each key frame to generate a key time series. At the same time, arrange the calculated similarity values ​​in chronological order to generate a similarity sequence.

[0099] In another preferred embodiment, the consistency of the practical results and the practical process also needs to be considered.

[0100] Specifically, according to the obtained practical operation result image, the historical key frame corresponding to the historical practical operation process video data matching the practical operation process image is obtained, and the similarity between the key frame and the historical key frame is calculated. When the similarity is less than a set value, an image recognition algorithm is replaced to extract the key frame. Replacing an image recognition algorithm includes extracting image frames on both sides of the key frame with a certain time parameter, and using the average of the similarities between the extracted image frames and the standard key frame as the similarity sequence of the key frame with the standard key frame. The lower the similarity, the smaller the time parameter.

[0101] By obtaining the actual operation result image, it is possible to trace back to the historical actual operation process video data that matches the actual operation process image. This helps to find historical records similar to the current actual operation process and provide a reference for subsequent similarity calculations. For each key frame in the current actual operation process, calculate its similarity with the corresponding historical key frame in the historical actual operation process video data. This helps to evaluate the consistency between the current actual operation process and the historical records, thereby discovering possible differences or errors. When the similarity between a key frame and a historical key frame is less than the set value, it indicates that the current image recognition algorithm may not be able to accurately identify the key frame. At this time, the system will choose to replace another image recognition algorithm to re-extract the key frame. In order to more accurately evaluate the similarity between the key frame and the standard key frame, the system will extract the image frames on both sides of the key frame with a certain time parameter, and calculate the average similarity between these image frames and the standard key frame. This helps to reduce the similarity calculation error caused by inaccurate recognition of a single key frame.

[0102] Conduct quantitative evaluation of the practical results, check the practical results, such as product manufacturing quality, accuracy of experimental data, etc., compare them with expected results, evaluate the degree of conformity of the practical results, and give corresponding scores based on the degree of conformity of the practical results. Give high scores for results that fully conform to expected results; for cases with deviations or errors, deduct points based on the degree of deviation.

[0103] According to the process score and the result score, the entity training score is calculated according to a certain weight ratio (such as 60% for the process score and 40% for the result score). The weight ratio can be formulated according to the specific requirements or goals of the experiment. The entity training score, process score and result score are output to students or teachers to understand the overall performance of the practical operation.

[0104] It should be noted that the entity training module of the present invention is also provided with an alarm device, which detects the operation specifications in real time through a camera during the actual operation and can issue an alarm according to the abnormal level of the operation specifications.

[0105] In some embodiments, a comprehensive score of the user may be obtained by calculating the weighted sum of the theoretical test score, the virtual training score, and the physical training score, and talents may be intelligently recommended to the enterprise based on the comprehensive score.

[0106] The embodiment of the present invention also takes into account the learning progress tracking and visualization display functions so that students can intuitively understand their learning progress. A learning dashboard is added to the system, which can display the student's learning status in real time, including but not limited to the progress of knowledge point mastery, virtual training scoring trends, and practical evaluation reports. Through intuitive charts and data analysis, students can clearly see their mastery of various knowledge points and the changes in learning effects over time. In addition, the learning dashboard also incorporates intelligent tutoring functions, which can provide students with real-time learning suggestions and help, and provide targeted guidance for students' weak links, thereby further improving learning effects.

[0107] Furthermore, the experimental teaching system also includes a learning report module, which can generate personalized reports based on students' learning situation and clearly point out the direction of personal skill improvement, such as "it is recommended to strengthen professional skills in the field of quality inspection" or "it is necessary to improve time management ability in competitions." This function helps students accurately locate their own growth points;

[0108] Secondly, the module closely integrates the actual operating standards of the enterprise to ensure that the recommendations in the report are highly consistent with industry needs, laying a solid foundation for students' future career development. In terms of the evaluation mechanism, the learning report module adopts a "dual-track evaluation" model, which combines the system's automatic scoring with the remote professional review of the enterprise mentor to improve the comprehensiveness and authority of the evaluation results. The system can summarize the students' comprehensive performance in theoretical learning, virtual training and actual operation, and compare and analyze it with industry standards, competition requirements and certificate standards, and generate intuitive visual reports, such as "The current skill level matches the target position requirements by 80%" or "There is still a 15% gap from the gold medal standard of the competition."

[0109] In addition, the module can intelligently recommend suitable internships or jobs based on students' skill profiles and competitiveness analysis, and mark the specific matching degree, such as "a pharmaceutical production technician position in a well-known pharmaceutical company, with a matching degree of up to 92%." At the same time, it will also recommend internship opportunities in related companies based on students' interests and career plans, providing strong support for students' career development paths.

[0110] Example 2

[0111] like Figure 2 As shown, the present invention provides an experimental teaching method, the system comprising:

[0112] Step 1: Set basic information, including setting learning direction;

[0113] Step 2, providing learning materials according to the learning direction, automatically generating comprehensive test questions according to the student's learning situation to conduct a theoretical test on the student, and obtaining a theoretical test score;

[0114] Step 3: Use VR and AR technologies to build a GMP workshop simulation environment to conduct follow-up experiment simulation exercises and independent experiment simulation exercises, and evaluate the results of independent experiment simulation exercises to obtain virtual training scores;

[0115] Step 4: When the theoretical test score and the virtual training score are both greater than the set values, practical operation is allowed, the practical operation process and the practical operation results are recorded, and the practical operation process and the practical operation results are evaluated to obtain the entity training score.

[0116] It should be understood that an experimental teaching method provided in an embodiment of the present invention and an experimental teaching system provided in the above embodiment are based on the same inventive concept. For more specific implementation processes of each step in the embodiment of the present invention, reference can be made to the above embodiment and will not be repeated in this embodiment.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. An experimental teaching system, characterized in that: include: A basic setting module, used to set basic information, including setting a learning direction; Theoretical learning module, used to provide learning materials according to the learning direction, automatically generate comprehensive test questions according to the students' learning situation to conduct theoretical tests on students, and obtain theoretical test scores; The GMP simulation module is used to build a GMP workshop simulation environment using VR and AR technologies to conduct follow-up experiment simulation exercises and independent experiment simulation exercises, and evaluate the results of independent experiment simulation exercises to obtain virtual training scores; The physical experiment module is used to allow practical operation when the theoretical test score and the virtual training score are both greater than the set value, record the practical operation process and the practical operation results, evaluate the practical operation process and the practical operation results, and obtain the physical training score.

2. The system according to claim 1, characterized in that The learning directions include general direction, job ability direction, professional skills competition direction, and professional certificate direction.

3. The system according to claim 1, characterized in that Automatically generate comprehensive test questions based on students' learning situation to test students' theory, including: Calculate the knowledge mastery index according to the student's learning situation, wherein the learning situation includes the total number of questions answered, the number of correct questions answered, the number of incorrect questions answered, the time between questions answered, and the total time spent answering questions for each knowledge point; Determine strong knowledge points and weak knowledge points according to the knowledge mastery index; Considering the correlation between strong knowledge points and weak knowledge points and the correlation between weak knowledge points, calculating the correction factor of the weak knowledge point, and correcting the knowledge mastery index of the weak knowledge point according to the correction factor of the weak knowledge point; The question ratio and question difficulty are determined according to the corrected knowledge mastery index, and comprehensive test questions are automatically generated according to the question ratio and question difficulty.

4. The system according to claim 2, characterized in that The calculation formula of the knowledge mastery is: Among them, K represents the degree of knowledge mastery, T, C, U, T s , Var(I) respectively represent the variance of the total number of questions, the number of correct questions, the number of incorrect questions, the total time for answering questions, and the time interval between answering questions corresponding to the knowledge point. α and δ are both constants.

5. The system according to claim 3, characterized in that The calculation formula of the weak knowledge point correction factor is: Among them, F w represents the weak knowledge point correction factor of weak knowledge point w, r ws represents the correlation between weak knowledge point w∈W and strong knowledge point s∈S, K s represents the knowledge mastery index of strong knowledge points, S and n represent the set of strong knowledge points S and the number of strong knowledge points in the set, respectively, and r ww' Represents the difference between a weak knowledge point w∈W and all other weak knowledge points The association degree of the recognition point w'∈W\{w}, Kw ' represents the knowledge mastery index of other weak knowledge points w'∈W\{w}, W and m represent the set of weak index points and the number of other weak knowledge points in the set respectively, and A is a constant.

6. The system according to claim 4, characterized in that The formula for determining the proportion and difficulty of questions based on the revised knowledge mastery index is: D i,i∈H =D base,i ×(1-K i ') γ c Among them, P i,i∈H represents the difficulty of the question for knowledge point i, K i 'Represents the corrected knowledge mastery index of knowledge point i, K' j represents the corrected knowledge mastery index of knowledge point j, m+n represents the total number of knowledge points, and D i,i∈H Indicates the difficulty of the question, D base,i represents the basic difficulty coefficient of knowledge point i, and γ represents the adjustment factor.

7. The system according to claim 1, characterized in that Use VR and AR technology to build a GMP workshop simulation environment for follow-up experiment simulation exercises and independent experiment simulation exercises, including: Determine a prompting method for following the experiment, and perform an experiment demonstration according to the prompting method so that students can perform simulation exercises for following the experiment; Obtaining the number of simulation exercises for the follow-up experiment and the duration of a single exercise, and calculating a follow-up exercise score according to the number of simulation exercises for the follow-up experiment, the duration of a single exercise, and the number of errors in the follow-up exercise; When the follow-up practice score is greater than the set follow-up practice score, the independent experiment simulation practice is opened.

8. The system according to claim 7, characterized in that Evaluate the results of independent experimental simulation exercises to obtain virtual training scores, including: The number of independent experiment simulation exercises, the duration of a single exercise, the number of successful exercises, the number of failed exercises, and the failure nodes are obtained, and the independent exercise score is calculated according to the number of independent experiment simulation exercises, the duration of a single exercise, the number of successful exercises, the number of failed exercises, and the failure nodes; Calculate the average independent practice score of multiple consecutive successful independent experimental simulation exercises, and use the average independent practice score as the virtual training score.

9. The system according to claim 8, characterized in that Evaluate the practical process and results, and get the entity training score including: Acquire video data of the practical operation process; extract key frames of the practical operation process to obtain a key frame sequence and a key time sequence, compare the key frame sequence with a standard key frame sequence to obtain a similarity sequence, input the key time sequence and the similarity sequence into a pre-built process evaluation model to obtain a process score; Obtaining quantitative data of practical operation results, and determining a result score according to the quantitative data of the practical operation results; The entity training score is calculated based on the process score and the result score.

10. An experimental teaching method, characterized in that: include: Step 1: Set basic information, including setting learning direction; Step 2, providing learning materials according to the learning direction, automatically generating comprehensive test questions according to the student's learning situation to conduct a theoretical test on the student, and obtaining a theoretical test score; Step 3: Use VR and AR technologies to build a GMP workshop simulation environment to conduct follow-up experiment simulation exercises and independent experiment simulation exercises, and evaluate the results of independent experiment simulation exercises to obtain virtual training scores; Step 4: When the theoretical test score and the virtual training score are both greater than the set values, practical operation is allowed, the practical operation process and the practical operation results are recorded, and the practical operation process and the practical operation results are evaluated to obtain the entity training score.

Images