Hybrid teaching effect evaluation method and system and storage medium

Abstract

The invention discloses a hybrid teaching effect evaluation method and system and a storage medium, and relates to the technical field of index evaluation, and the method comprises the steps: determining the evaluation result of a teaching effect according to the teaching content of a teacher and the teaching score of a student, the types of the teaching content comprise the historical teaching content and the current teaching content, and the types of the teaching content comprise the historical teaching content and the current teaching content; the types of the teaching scores include historical teaching scores and current teaching scores, an evaluation result determined according to the historical teaching content and the historical teaching scores is a first evaluation result, and an evaluation result determined according to the current teaching content and the current teaching scores is a second evaluation result; comparing the first evaluation result with the second evaluation result, and determining the improvement condition of the teaching effect; and evaluating the teaching effect of the teacher based on the promotion condition. According to the invention, multiple teaching acquisition is carried out, and the teaching content and the learning ability are separately evaluated, so that the teaching ability of the teacher is comprehensively judged, and the evaluation of the teaching effect of the teacher is more accurate.

Description

Technical Field

[0001] The present application relates to the technical field of indicator evaluation, and in particular to a hybrid teaching effect evaluation method, system and storage medium. Background Art

[0002] In current education assessment technology, the common practice is to measure the teaching effectiveness of teachers by evaluating and statistically analyzing the teaching performance of teachers in the classroom and the test scores of students. However, this assessment method has certain limitations, and its main problem is that it is not very controllable.

[0003] Because there are significant differences in learning ability among individual students, even if the same course is taught by the same teacher using different lesson plans, different students will have different degrees of absorption and understanding during the learning process, which may lead to deviations in the evaluation results, making it difficult to accurately reflect the teacher's teaching level and teaching effect. This single evaluation system is difficult to comprehensively and objectively evaluate the teacher's teaching effect. In order to improve the accuracy and fairness of the evaluation, it is necessary to optimize and adjust the existing evaluation system. Summary of the invention

[0004] The main purpose of this application is to provide a hybrid teaching effectiveness evaluation method, system and storage medium, aiming to solve the technical problem of how to improve the accuracy of teacher teaching effectiveness evaluation.

[0005] To achieve the above objectives, this application proposes a hybrid teaching effect evaluation method, which includes: Determine the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the teaching content includes historical teaching content and current teaching content, the teaching performance includes historical teaching performance and current teaching performance, and the evaluation result includes a first evaluation result determined according to the historical teaching content and the historical teaching performance, and a second evaluation result determined according to the current teaching content and the current teaching performance; Comparing the first evaluation result with the second evaluation result to determine the improvement of the teaching effect; The teaching effectiveness of the teacher is evaluated based on the improvement status.

[0006] In one embodiment, the step of determining the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance includes: Determine the corresponding teaching knowledge points according to the teacher's teaching content, and perform relevance evaluation on the teaching knowledge points to obtain content evaluation data; Classifying the students' classes based on their teaching performance to obtain class grade data, and classifying each student in any grade class based on the historical teaching performance and the class grade data to obtain student grade data; Counting the number of students at each level in the student level data, obtaining a level data value of the corresponding level, and comparing the level data value with a preset standard data value as ability assessment data, wherein the degree of fit between the teaching content and the students is positively correlated with the ability assessment data; An evaluation result of the teaching effect is calculated based on the content evaluation data and the ability evaluation data.

[0007] In one embodiment, the step of determining the corresponding teaching knowledge points according to the teacher's teaching content, and performing relevance evaluation on the teaching knowledge points to obtain content evaluation data includes: Identify the knowledge points of the teacher's teaching content to obtain the corresponding teaching knowledge point data, and identify the knowledge points of the preset teaching syllabus to obtain the corresponding knowledge point range; Comparing the teaching knowledge point data with the knowledge point range, and canceling the step of determining the evaluation result of the teaching effect when the teaching knowledge point data is outside the knowledge point range; In the case where the teaching knowledge point is within the knowledge point range, determining the attribute category of each knowledge point in the teaching knowledge point data based on the teaching syllabus, and for each knowledge point of any attribute category, determining the teaching time of each knowledge point based on the teaching content; The continuity of each knowledge point is evaluated at each teaching moment to obtain the first content evaluation sub-data, and the progressiveness of the difficulty of each knowledge point is evaluated at each teaching moment to obtain the second content evaluation sub-data; Based on the first content-evaluation sub-data and the second content-evaluation sub-data, content-evaluation data is calculated.

[0008] In one embodiment, after the step of evaluating the continuity of each knowledge point according to each teaching moment, the step further includes: In the case where the teaching moments corresponding to the knowledge points are not continuous, determining the interspersed knowledge points that interrupt the continuity of the knowledge points and the correlation between the knowledge points to obtain correlation data; The association data is adjusted based on the progressive difficulty between the interspersed knowledge points and subsequent knowledge points, wherein the subsequent knowledge points are knowledge points that are adjacent to the interspersed knowledge points at the teaching time and are located after the interspersed knowledge points; The first content-evaluation sub-data is determined based on the adjusted relevance data.

[0009] In one embodiment, the step of evaluating the progressive difficulty of each knowledge point according to each teaching moment to obtain the second content evaluation sub-data includes: Determine the teaching duration and teaching sequence of each knowledge point based on each teaching moment, and perform teaching difficulty evaluation on each knowledge point based on each teaching duration to obtain first difficulty evaluation data, and perform teaching difficulty evaluation on each knowledge point based on the teaching sequence to obtain second difficulty evaluation data; Comparing the collection of teaching time and teaching sequence of each teacher for each knowledge point, determining the correlation between the teaching time and teaching sequence of each knowledge point, and performing teaching difficulty evaluation on each knowledge point based on the correlation to obtain third difficulty evaluation data; Based on the first difficulty evaluation data, the second difficulty evaluation data and the third difficulty evaluation data, the difficulty data of each knowledge point is calculated, and the second content evaluation sub-data is determined according to the progressiveness of each difficulty data.

[0010] In one embodiment, the first evaluation result and the second evaluation result are both numerical values, and the step of comparing the first evaluation result and the second evaluation result to determine the improvement of the teaching effect includes: Determining a difference relationship between the first evaluation result and the second evaluation result; In the case where the difference relationship is that the second evaluation result is less than the first evaluation result, determining a first achievement degree of the first evaluation result relative to a preset standard teaching effect, and determining an improvement status of the teaching effect according to the first achievement degree and a preset standard fluctuation range; When the difference relationship is that the second evaluation result is greater than or equal to the first evaluation result, the second achievement degree of the second evaluation result relative to the preset standard teaching effect is determined, and the improvement status of the teaching effect is determined based on the second achievement degree and the preset standard fluctuation range.

[0011] In one embodiment, the first evaluation result and the second evaluation result are both numerical values, and the step of evaluating the teaching effect of the teacher based on the improvement status includes: When the improvement condition is that there is improvement, comparing the improvement condition with a preset standard teaching effect; When the improvement condition is within the standard fluctuation range preset for the standard teaching effect, the first evaluation result and the second evaluation result are respectively subjected to difference calculation with the numerical values ​​corresponding to the standard teaching effect to obtain a first evaluation difference and a second evaluation difference; The teaching effectiveness of the teacher is determined according to the ratio of the first evaluation difference to the second evaluation difference.

[0012] In one embodiment, after the step of evaluating the teaching effect of the teacher based on the improvement status, the step further includes: Comparing the capability assessment data in the second assessment result with the preset standard capability data to obtain corresponding capability matching data; Comparing the content evaluation data in the second evaluation result with the preset standard teaching effect to obtain corresponding teaching data; The ability matching data, the teaching data and the teaching effect are output in association.

[0013] In addition, to achieve the above purpose, the present application also proposes a hybrid teaching effect evaluation system, the hybrid teaching effect evaluation system comprising: An analysis module, used to determine the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the teaching content includes historical teaching content and current teaching content, the teaching performance includes historical teaching performance and current teaching performance, and the evaluation result includes a first evaluation result determined according to the historical teaching content and the historical teaching performance, and a second evaluation result determined according to the current teaching content and the current teaching performance; A comparison module, used to compare the first evaluation result with the second evaluation result to determine the improvement of the teaching effect; An evaluation module is used to evaluate the teaching effect of the teacher based on the improvement status.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the hybrid teaching effect evaluation method described above are implemented.

[0015] One or more technical solutions proposed in this application have at least the following technical effects: The present application first determines the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the teaching content includes historical teaching content and current teaching content, the teaching performance includes historical teaching performance and current teaching performance, and the evaluation result includes a first evaluation result determined according to the historical teaching content and the historical teaching performance, and a second evaluation result determined according to the current teaching content and the current teaching performance, so as to divide the evaluation of the teaching effect into the evaluation of the teaching content and the evaluation of the student's learning outcomes, so as to separate the teacher's teaching content and the student's learning ability, thereby making the evaluation of the teacher's teaching effect more accurate, and taking the previous teaching result as the basis for judging this teaching, thereby effectively reducing uncontrollable variables; then compare the first evaluation result with the second evaluation result to determine the improvement of the teaching effect, so as to compare the results of the two evaluations with each other to determine whether the teacher's grasp of the student's learning situation has improved; finally, the teaching effect of the teacher is evaluated based on the improvement status to obtain a more accurate teaching effect evaluation result.

[0016] In summary, this application conducts multiple teaching collections, evaluates the teacher's teaching content and the students' learning ability separately, and then compares the results of the two evaluations. In this way, a comprehensive judgment is made on the teacher's teaching ability based on the teacher's grasp of the students' learning situation, making the evaluation of the teacher's teaching effectiveness more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0019] Figure 1 A flow chart of the first embodiment of the hybrid teaching effect evaluation method provided in this application; Figure 2 A flow chart of the second embodiment of the hybrid teaching effect evaluation method provided in this application; Figure 3 A flow chart of the third embodiment of the hybrid teaching effect evaluation method provided in this application; Figure 4 A brief flowchart of the hybrid teaching effect evaluation method provided in Example 3 of the present application; Figure 5 This is a schematic diagram of the module structure of the hybrid teaching effect evaluation system of the present application embodiment; DETAILED DESCRIPTION It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0020] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0021] The main solution of the embodiment of the present application is: determine the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the teaching content includes historical teaching content and current teaching content, the teaching performance includes historical teaching performance and current teaching performance, and the evaluation result includes a first evaluation result determined according to the historical teaching content and the historical teaching performance, and a second evaluation result determined according to the current teaching content and the current teaching performance; compare the first evaluation result with the second evaluation result to determine the improvement status of the teaching effect; and evaluate the teaching effect of the teacher based on the improvement status.

[0022] Because there are significant differences in learning ability among individual students, even if the same course is taught by the same teacher using different lesson plans, different students will have different degrees of absorption and understanding during the learning process, which may lead to deviations in the evaluation results, making it difficult to accurately reflect the teacher's teaching level and teaching effect. This single evaluation system is difficult to comprehensively and objectively evaluate the teacher's teaching effect. In order to improve the accuracy and fairness of the evaluation, it is necessary to optimize and adjust the existing evaluation system.

[0023] This application provides a solution, which collects teaching data for multiple times, evaluates the teacher's teaching content and the student's learning ability separately, and then compares the results of the two evaluations. In this way, a comprehensive judgment can be made on the teacher's teaching ability based on the teacher's understanding of the student's learning situation, making the evaluation of the teacher's teaching effect more accurate.

[0024] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device that can realize the above functions. The following takes an electronic device as an example to illustrate this embodiment and the following embodiments.

[0025] Based on this, the present application embodiment provides a hybrid teaching effect evaluation method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the hybrid teaching effect evaluation method of the present application.

[0026] In this embodiment, the hybrid teaching effect evaluation method includes steps S10 to S30: Step S10, determining the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the teaching content includes historical teaching content and current teaching content, the teaching performance includes historical teaching performance and current teaching performance, and the evaluation result includes a first evaluation result determined according to the historical teaching content and the historical teaching performance, and a second evaluation result determined according to the current teaching content and the current teaching performance; It should be noted that teaching content refers to the knowledge system, teaching materials, course design and implementation process taught by teachers in class, including specific teaching elements such as course objectives, knowledge point distribution, teaching methods, and teaching activities; history teaching content refers to the course design, knowledge point arrangement and teaching strategy used by teachers in the previous teaching cycle (such as the previous class, etc.); current teaching content refers to the teaching plan currently being implemented by teachers, including the latest course adjustments, knowledge point updates or teaching method improvements; teaching performance refers to the quantitative results obtained by students through tests, homework, classroom performance, etc. after course learning, reflecting the students' mastery of teaching content; history teaching performance refers to students' performance data in the past teaching cycle (such as the test score of the previous class, etc.); current teaching performance refers to students' real-time performance data in the current teaching cycle (such as the latest test results); evaluation results are quantitative or qualitative indicators obtained after comprehensive analysis of teaching content and teaching performance, which are used to measure teachers' teaching effectiveness; the first evaluation result is the evaluation result based on history teaching content and history teaching performance, reflecting the teacher's past teaching level; the second evaluation result is the evaluation result based on current teaching content and current teaching performance, reflecting the teacher's current teaching level.

[0027] It is understandable that, due to the great limitation of the traditional evaluation method that only relies on single data (such as current teaching performance or current assessment results), step S10 is performed to build a multi-dimensional evaluation model by integrating historical and current teaching content and performance data. This can avoid misjudgment of teacher ability caused by isolated evaluation. For example, poor performance of a class may be caused by weak students' foundation rather than the level of the teacher, that is, it ignores the problem of individual differences among students and dynamic changes in teaching content. This provides teaching ability tracking in the time dimension, enhances the longitudinal comparison ability of the evaluation, and provides an effective basis for more accurately locating teaching problems (such as unreasonable knowledge point design leading to a decline in performance).

[0028] For example, we first collect the teacher's teaching plans, lesson plans, courseware and other teaching materials in two consecutive times, as well as the corresponding students' test scores and homework scores in two consecutive times. Then, by analyzing these historical and current teaching contents and scores, we use statistical analysis methods such as regression analysis or variance analysis to calculate the teaching effect scores of the two stages, namely the first evaluation results and the second evaluation results. These evaluation results will be quantified based on the key knowledge points taught by the teacher and the students' mastery.

[0029] In a feasible implementation, step S10 may include steps S11 to S14: Step S11, determining corresponding teaching knowledge points according to the teacher's teaching content, and performing relevance evaluation on the teaching knowledge points to obtain content evaluation data; It should be noted that content evaluation data refers to the data obtained by evaluating the interrelationships between various knowledge points in the teacher's teaching content. This data reflects the logical relationship between knowledge points and the systematic nature of the teaching content.

[0030] It is understandable that since the teaching knowledge points set by teachers in the teaching process often have strong or weak correlations, this has a great impact on the scientific degree of teaching and the degree of learning difficulty of students. Therefore, performing step S11 can avoid ignoring the problem that the teaching content may lack systematicity and logic, resulting in poor learning effects for students. By evaluating the correlation between knowledge points in the teaching content, the evaluation of the teaching content is included in the evaluation scope, so as to improve the comprehensiveness and accuracy of the evaluation of the teacher's teaching effect.

[0031] For example, by constructing a concept map or knowledge map to visualize the connections between knowledge points, these connections are then quantitatively scored to form content evaluation data. For example, if knowledge point A is the basis of knowledge point B, then the correlation between A and B will be given a higher score. The higher the score, the more reasonable the design of the teaching content, and the more positive the content evaluation data.

[0032] In a feasible implementation, step S11 may include steps S111 to S115: Step S111, performing knowledge point recognition on the teacher's teaching content to obtain corresponding teaching knowledge point data, and performing knowledge point recognition on the preset teaching syllabus to obtain the corresponding knowledge point range; For example, through natural language processing technology and a knowledge base based on the knowledge of experts in the field of education, text analysis is performed on teaching materials such as lesson plans, handouts or courseware provided by teachers to identify and extract teaching knowledge points and form a teaching knowledge point data set. At the same time, the same processing is performed on the teaching syllabus to identify and determine the scope of knowledge points specified in the syllabus. This process may involve technologies such as keyword extraction and semantic analysis to ensure the consistency of teaching knowledge points with the syllabus.

[0033] It should be noted that knowledge point recognition can be performed by a pre-trained large language model to improve recognition accuracy. The large language model is trained by a preset deep learning model. The training process of the deep learning model includes: obtaining a teaching text set, wherein the teaching text set is annotated with knowledge point information, and the teaching text set includes a training set and a verification set; inputting the training set into the deep learning model to train the deep learning model to obtain a candidate large language model; evaluating the candidate large language model according to the verification set to obtain a model evaluation result; if the model evaluation result does not meet the preset indicators, fine-tune the model parameters of the candidate large language model according to the model evaluation result, and return to execute the step of inputting the training set into the deep learning model to train the deep learning model based on the fine-tuned candidate large language model; if the model evaluation meets the preset indicators, use the candidate large language model as the large language model.

[0034] Step S112, comparing the teaching knowledge point data with the knowledge point range, and in the case where the teaching knowledge point data is outside the knowledge point range, canceling the step of determining the evaluation result of the teaching effect; It is understandable that since teachers often provide some additional teaching content during the teaching process, performing step S112 can avoid evaluating invalid teaching content that does not conform to the teaching syllabus, as well as the impact of invalid teaching content on normal evaluation, thereby improving the efficiency and accuracy of effective evaluation.

[0035] Exemplarily, the identified teaching knowledge point data is compared with the knowledge point range specified in the teaching syllabus. If it is found that the teacher's teaching content contains additional knowledge points outside the syllabus, or lacks necessary knowledge points required by the syllabus, the system will automatically cancel the subsequent teaching effectiveness evaluation steps, thereby avoiding the evaluation of teaching content that does not meet the syllabus requirements.

[0036] Step S113, when the teaching knowledge point is within the knowledge point range, determining the attribute category of each knowledge point in the teaching knowledge point data based on the teaching syllabus, and for each knowledge point of any attribute category, determining the teaching time of each knowledge point based on the teaching content; It should be noted that the attribute category of each knowledge point refers to the category into which the knowledge point is divided in the teaching syllabus, such as basic knowledge, advanced concepts, etc.; the teaching time of each knowledge point refers to the specific time period arranged in the teaching process.

[0037] It is understandable that in order to classify knowledge points according to the syllabus and consider whether the teacher arranges reasonable teaching time according to the categories, step S113 is performed, which can avoid ignoring the problems of misalignment or omissions of teachers in the teaching process, thereby providing an effective and comprehensive evaluation basis for subsequent evaluation.

[0038] For example, after confirming that the teaching knowledge point data meets the syllabus scope, each knowledge point is classified into attribute categories according to the teaching syllabus, such as basic knowledge, advanced knowledge, practical skills, etc. Then, the teaching time of each knowledge point is determined according to the arrangement record of the teaching content, that is, the specific teaching time point in the teaching plan.

[0039] Step S114, evaluating the continuity of each knowledge point according to each teaching moment to obtain first content evaluation sub-data, and evaluating the progressiveness of the difficulty of each knowledge point according to each teaching moment to obtain second content evaluation sub-data; It should be noted that the first content evaluation sub-data refers to the evaluation results of the continuity and logical sequence of knowledge points in the teaching process; the second content evaluation sub-data refers to the evaluation results of the progressive difficulty of knowledge points in the teaching process.

[0040] It is understandable that since teachers often have problems with coherence and unreasonable arrangement of difficulty levels during the teaching process, performing step S114 can avoid ignoring the lack of logic in the teaching content and improper setting of the difficulty level of the teaching content during the evaluation process. It makes it possible to include whether the teaching content is coherent and whether the progressive difficulty level is reasonably arranged within the scope of the evaluation, thereby further improving the comprehensiveness and accuracy of the evaluation of the teaching effectiveness of teachers.

[0041] Exemplarily, the continuity of knowledge points of the same category is evaluated according to the teaching moments to find out whether the teaching sequence between knowledge points of the same category is reasonable, thereby obtaining the first content evaluation sub-data. For example, when the teaching moments corresponding to each knowledge point are continuous, that is, when the teaching sequence corresponding to each knowledge point of the same attribute category is not interrupted, the preset standard content evaluation value is used as the first content evaluation sub-data, and the standard content evaluation value is used to indicate that the evaluation result of the first content evaluation sub-data is an ideal result. At the same time, the progressive difficulty of the knowledge points in the teaching process will also be evaluated to find out whether the difficulty of the teaching content is gradually increased, thereby obtaining the second content evaluation sub-data. These evaluations are usually carried out by data analysis methods.

[0042] Step S115: calculating content evaluation data based on the first content evaluation sub-data and the second content evaluation sub-data.

[0043] Exemplarily, the first content evaluation sub-data and the second content evaluation sub-data are combined, and comprehensive content evaluation data is calculated through weight distribution, which reflects the overall quality of the teaching content, including the continuity of knowledge points and the progressive difficulty level.

[0044] In this implementation, by identifying knowledge points in the teacher's teaching content and comparing them with the teaching syllabus, the compliance of the teaching content is ensured; by determining the attribute categories and teaching moments of the knowledge points, the systematic and logical consideration of the teaching content is guaranteed; by evaluating the continuity and difficulty progression of the knowledge points, content evaluation sub-data are obtained; finally, the content evaluation data calculated based on these sub-data avoids problems such as the inability to identify deviations of teaching content from the teaching syllabus, incomplete coverage of knowledge points, unreasonable teaching sequence, and inappropriate difficulty of teaching content, and achieves a comprehensive and objective evaluation of the quality and suitability of the teaching content, thereby improving the accuracy and comprehensiveness of the teaching effectiveness evaluation.

[0045] Step S12, classifying the students' classes based on their teaching performance to obtain class grade data, and classifying each student in any grade class based on the historical teaching performance and the class grade data to obtain student grade data; It should be noted that class grade data refers to data that divides classes into different grades based on students' teaching performance, which is used to indicate the overall learning level of the class; student grade data refers to data that divides classes into different grades based on students' teaching performance within each class, which is used to indicate students' individual learning level.

[0046] It is understandable that when the same teacher teaches a better class and a worse class, he or she cannot directly apply the teaching method of the better class to the worse class. Similarly, for students in the same class, the content that the same teacher cannot explain can only be understood by the better students in the class, but not by the worse students. Therefore, step S12 is performed to grade classes and students accordingly, so as to avoid ignoring whether the teacher ignores the differences between classes, resulting in a one-size-fits-all teaching strategy, which is not conducive to teaching students in accordance with their aptitude, and whether the teacher cannot identify individual differences among students, which is not conducive to providing personalized learning support for students. Therefore, an evaluation basis is constructed based on complex environmental distribution factors in a real environment to improve the comprehensiveness and accuracy of the evaluation of teacher teaching effectiveness.

[0047] For example, firstly, students' teaching performance, such as test scores, homework completion, etc., are collected, and then, based on these performances, statistical methods such as average scores or medians are used to divide the classes into different levels, such as excellent classes, ordinary classes, and remedial classes, so as to obtain class grade data. Then, for each class, students are further divided into different levels, such as excellent students, ordinary students, and remedial students, according to their teaching performance, so as to obtain student grade data. The role of class grade data in this division process is not to uniformly divide student grades according to specific grade values. For example, 80 points may be a poor student in a better class, but may be an excellent student in an ordinary class.

[0048] Step S13, counting the number of students at each level in the student level data, obtaining the level data value of the corresponding level, and comparing the level data value with the preset standard data value as the ability evaluation data, wherein the fit between the teaching content and the students is positively correlated with the ability evaluation data; It should be noted that ability assessment data refers to the assessment results obtained by comparing the number of students of each level in the class with the preset standard data values, which is used to measure the overall learning ability of the class.

[0049] It can be understood that in order to evaluate the overall learning ability of the class and compare it with the expected standard, step S13 is performed, which can avoid the problem of lack of accurate quantitative evaluation of the overall learning ability of the class, thereby accurately quantifying the learning ability of the class, and further providing effective key indicators for accurately and comprehensively evaluating the teaching effect.

[0050] For example, the grade data of students in each class are counted, and the number of students in each grade (such as excellent students, ordinary students and tutored students) is calculated to obtain the grade data value. Then these grade data values ​​are compared with the pre-set standard data values. Finally, the comparison results are used as ability assessment data, which reflects the degree of fit between the teaching content and the students' learning ability. For example, if 90% of the students scored 80 points and 10% of the students scored full marks, it means that the teaching content meets the requirements in terms of extended content, but is insufficient in terms of advanced content and basic content, resulting in students with medium learning ability not achieving full learning and obtaining a medium-level ability assessment data value; if 100% of the people scored 80 and no one scored full marks, it means that the extended content in the teaching content is too difficult, and the advanced content and basic content are not distinguished enough, resulting in students with medium and excellent learning abilities not achieving full learning, and also obtaining a medium-level ability assessment data value, and so on, and then infer the teacher's grasp of the students' learning status.

[0051] Step S14, calculating the evaluation result of the teaching effect according to the content evaluation data and the ability evaluation data.

[0052] It is understandable that in order to comprehensively consider the quality of teaching content and students' learning ability and obtain a comprehensive teaching effectiveness evaluation, step S14 is performed to avoid the problem that a single-dimensional evaluation cannot fully reflect the teaching effect, resulting in biased evaluation results. Through comprehensive evaluation, a more accurate and comprehensive teaching effectiveness evaluation can be obtained.

[0053] Exemplarily, the obtained content evaluation data and ability evaluation data are comprehensively analyzed. For example, a weighted average or other complex algorithm can be used to combine the data of these two dimensions to obtain a comprehensive teaching effect evaluation score or grade. This evaluation result not only considers the rationality and systematicness of the teaching content, but also considers the degree of match between the teaching content and the actual learning ability of the students, thereby providing a comprehensive teaching effect evaluation.

[0054] In this implementation, by evaluating the relevance of teaching knowledge points and obtaining content evaluation data, the effectiveness and consistency of teaching content are ensured; by grading the students' classes and individual students, class grade data and student grade data are obtained, which can more accurately reflect the students' actual learning level; by statistically analyzing the student grade data and comparing it with the preset standard data value, ability evaluation data is obtained, which reflects the fit between the teaching content and the students' learning ability. Finally, the teaching effect evaluation results calculated by combining the content evaluation data and the ability evaluation data achieve the technical effect of comprehensively, objectively and systematically evaluating the teaching effect of teachers, and provide a scientific basis for teaching improvement.

[0055] Step S20, comparing the first evaluation result and the second evaluation result to determine the improvement of the teaching effect; It is understandable that in order to quantify the improvement or decline trend of teachers' teaching effectiveness rather than just focusing on absolute values, step S20 is performed. By analyzing the differences between historical and current evaluation results, it is possible to avoid ignoring the problem of dynamic changes in teachers' teaching abilities, achieve a relative evaluation based on the extent of teachers' own progress, and reduce external factors to accurately identify whether teachers have the ability to make continuous improvements.

[0056] Exemplarily, the first evaluation result and the second evaluation result are compared and analyzed. This can be done by creating a comparison table or using statistical software to calculate the difference between the two evaluation results. For example, if the second evaluation result is higher than the first evaluation result by a certain percentage, it can be considered that the teaching effect has improved; conversely, if the second evaluation result is lower than the first evaluation result, it indicates that the teaching effect may have declined. Through this comparison, the degree of improvement in the teaching effect can be quantified.

[0057] In a feasible implementation, step S20 may include steps S21 to S23: Step S21, determining a difference relationship between the first evaluation result and the second evaluation result; It is understandable that in order to compare the teaching effect evaluation results at two different time points to determine the changing trend of the teaching effect, step S21 is performed, which can avoid the problem of not being able to accurately judge whether the teaching effect has improved or declined, thereby realizing the quantification of the change in teaching effect.

[0058] Exemplarily, the numerical values ​​of the first evaluation result and the second evaluation result are first obtained, which may be a set of scores, percentages or other quantitative indicators, and then the difference relationship is determined by calculating the difference between the two numerical values, that is, subtracting the first evaluation result from the second evaluation result.

[0059] Step S22, when the difference relationship is that the second evaluation result is less than the first evaluation result, determining a first achievement degree of the first evaluation result relative to a preset standard teaching effect, and determining an improvement status of the teaching effect according to the first achievement degree and a preset standard fluctuation range; It should be noted that the first achievement degree refers to the degree of achievement between the first evaluation result and the preset standard teaching effect. This value is a ratio or percentage, which indicates the degree of closeness between the actual teaching effect and the standard effect. The standard fluctuation range refers to the allowable fluctuation range of the evaluation results in the teaching effect evaluation, which is used to judge the stability of the teaching effect.

[0060] It is understandable that in order to evaluate whether the teaching effect has been improved, step S22 is performed, which can avoid the problem of being unable to reasonably judge the improvement of the teaching effect, thereby achieving the effect of identifying and confirming the degree of improvement of the teaching effect.

[0061] Exemplarily, when it is found that the second evaluation result is lower than the first evaluation result, the first evaluation result is first compared with the preset standard teaching effect, and the first achievement degree is calculated, which is usually a ratio obtained by dividing the first evaluation result by the standard teaching effect. Then, according to the preset standard fluctuation range, that is, an allowable fluctuation range of the evaluation result, it is judged whether the first achievement degree indicates that the teaching effect has been significantly improved. For example, the standard teaching effect is 10 and the standard fluctuation range is 1. The value corresponding to the first evaluation result is 5. If the value corresponding to the second evaluation result is 4, it indicates that the teacher's mastery of the students has decreased, and since the data with a larger data value is 5 of the first evaluation data, and 5 is less than 9, it can be directly judged that the second teaching result has not been improved; and if the value corresponding to the first evaluation is 9 and the value corresponding to the second evaluation is 8, then since 9>8, it indicates that the teacher's mastery of the students has decreased, but since the result of the first teaching is 9, it belongs to the standard fluctuation range, so it indicates that the teacher's mastery of the students' learning status is in a standard state, so it is judged that the reason for the decrease in the second evaluation result is normal teaching fluctuation, and the difference between 9 and 8 is used as the teaching improvement.

[0062] Step S23, when the difference relationship is that the second evaluation result is greater than or equal to the first evaluation result, determine the second achievement degree of the second evaluation result relative to the preset standard teaching effect, and determine the improvement status of the teaching effect based on the second achievement degree and the preset standard fluctuation range.

[0063] It should be noted that the second achievement degree refers to the degree of achievement between the second evaluation result and the preset standard teaching effect. This value is a ratio or percentage, indicating the degree of closeness between the actual teaching effect and the standard effect.

[0064] It is understandable that in order to evaluate whether the teaching effect remains stable or decreases, step S23 is performed, which can avoid the problem of being unable to effectively identify whether the teaching effect is stable or decreasing, thereby achieving the effect of accurately judging the changing trend of the teaching effect.

[0065] Exemplarily, when the second evaluation result is not lower than the first evaluation result, the second evaluation result is compared with the standard teaching effect to calculate the second achievement degree. This step involves converting the second evaluation result into a ratio with the standard teaching effect. Then, the second achievement degree is judged according to the standard fluctuation range whether it indicates that the teaching effect remains stable or has declined. If the second achievement degree is within the standard fluctuation range, it is considered that the teaching effect remains stable; if it exceeds the range, it may indicate that the teaching effect has declined. For example, if the value corresponding to the first evaluation is 8 and the value corresponding to the second evaluation is 9, since 8 < 9, it indicates that the teacher's mastery of the student's learning status has improved. Since the value corresponding to the second evaluation is 9 within the standard fluctuation range, it indicates that the teacher's mastery of the student's learning status is in the standard state, so the value 9 corresponding to the second evaluation is directly used as the improvement of the teaching effect; and if the value corresponding to the first evaluation is 5 and the value corresponding to the second evaluation is 6, since the value corresponding to the second evaluation is 6 beyond the standard fluctuation range, it indicates that the teacher's mastery of the student's learning status is lower than the standard state, so the improvement of the teaching effect is determined to be 9-8=1.

[0066] In this embodiment, by comparing the second evaluation data with the first evaluation data, the size relationship between the second evaluation data and the first evaluation data is determined. If the second evaluation data is less than the first evaluation data, it indicates that the teacher's mastery of the student's learning status is reduced. Therefore, by comparing the first evaluation data with a higher mastery with the built-in standard teaching effect, the reason for the decline in mastery is determined. When the first achievement is within the standard fluctuation range, it indicates that the teacher's mastery of the student's learning status has reached the standard state during the first teaching, so the second evaluation data of the second teaching is used as the fluctuation in the teaching process; on the contrary, when the first achievement exceeds the standard fluctuation range, it indicates that the teacher's mastery of the student's learning status is low, and because the second evaluation data is less than the first evaluation data, it is determined that the teacher has not made progress in the second teaching based on the first teaching. Similarly, when the second evaluation data is greater than the first evaluation data, it indicates that the teaching effect of the second teaching is better than that of the first teaching. Therefore, by comparing the second evaluation data with the standard teaching effect, it is clear whether the second teaching has reached the standard state, and a corresponding judgment is made according to the achievement state, thereby ensuring the effectiveness of the judgment on the improvement of the teaching effect.

[0067] Step S30: Evaluate the teaching effect of the teacher based on the improvement status.

[0068] For example, based on the determined teaching effect improvement status, combined with multi-dimensional data such as teachers' teaching behavior, student feedback and peer evaluation, a comprehensive evaluation of the teacher's teaching effect is conducted. For example, if the improvement status shows that the teaching effect has been significantly improved, then the teacher can be given a positive evaluation and the specific aspects of his teaching improvement can be pointed out in the teacher evaluation report. If the improvement status is not obvious or has declined, it is necessary to further analyze the reasons and put forward targeted improvement suggestions accordingly to help teachers improve the quality of teaching.

[0069] In a feasible implementation, step S30 may include steps A31 to A33: Step A31, when the improvement condition is improvement, comparing the improvement condition with a preset standard teaching effect; It is understandable that in order to quantify the degree of improvement in teaching effectiveness and determine whether such improvement reaches or exceeds the preset standard, step A31 is performed. This can avoid the problem of being unable to reasonably judge whether the teaching effect is truly improved. By comparing the improvement status with the preset standard, the degree of improvement in teaching effectiveness can be accurately measured.

[0070] Step A32, when the improvement status is within the standard fluctuation range preset for the standard teaching effect, performing difference calculation between the first evaluation result and the second evaluation result and the numerical values ​​corresponding to the standard teaching effect, respectively, to obtain a first evaluation difference and a second evaluation difference; It should be noted that the first evaluation difference refers to the difference between the numerical value corresponding to the first evaluation result and the standard teaching effect, and the second evaluation difference refers to the difference between the numerical value corresponding to the second evaluation result and the standard teaching effect.

[0071] It is understandable that in order to analyze the changes in teaching effects more carefully, even if the improvement condition is within the standard fluctuation range, it is necessary to understand the specific numerical differences. Therefore, performing step A32 can avoid the problem of ignoring small but potentially important changes in teaching effects, thereby achieving an in-depth understanding of the changing trends in teaching effects and providing more accurate data support for teaching improvements.

[0072] Step A33, determining the teaching effect of the teacher according to the ratio of the first evaluation difference to the second evaluation difference.

[0073] It should be noted that the ratio of the first evaluation difference to the second evaluation difference reflects the relative change in the teacher's teaching effectiveness between the two evaluations and is an important indicator for measuring the improvement in the teacher's teaching effectiveness.

[0074] It can be understood that since the stability or degree of improvement of the teacher's teaching effect can be evaluated by comparing the ratio of the two evaluation differences, performing step A33 can avoid judging the teacher's teaching effect based on only a single evaluation result, which may lead to problems of subjectivity and randomness in the evaluation, thereby objectively and systematically evaluating the teacher's teaching effect.

[0075] Exemplarily, after calculating the ratio of the first evaluation difference and the second evaluation difference, the teaching effect of the teacher is judged according to the preset evaluation standard or ratio range. For example, if the ratio is 1 or close to 1, it may indicate that the teaching effect of the teacher is stable during the two evaluations; if the ratio is greater than 1, it may indicate that the teaching effect of the teacher has improved; if the ratio is less than 1, it may indicate that the teaching effect has declined. The teaching effect evaluation process can be implemented by an algorithm that corresponds the ratio to different teaching effect levels and outputs the final evaluation result. For example, the calculation formula of the teaching effect data is y=a+kx, where y is the authorized effect data, a is the data value corresponding to the second evaluation result, k is the weighting coefficient, and x is the ratio of the first evaluation difference to the second evaluation difference.

[0076] In this implementation, by performing data comparison and difference analysis, the subjectivity and lack of quantitative indicators in traditional evaluation are avoided, and the technical effect of accurately and objectively evaluating the teaching effect of teachers is achieved. Specifically, this method compares the actual improvement status with the preset standard teaching effect, and calculates the difference of the evaluation results within the standard fluctuation range, thereby avoiding the subjective bias of the evaluation and the contingency of a single evaluation result, thereby ensuring the reliability and fairness of the evaluation results, and then effectively monitoring and evaluating the teaching quality.

[0077] In another feasible implementation, step S30 may further include step B31: Step B31, when the improvement status is no improvement, taking the second evaluation result as the teaching effect of the teacher.

[0078] It is understandable that when the teacher's teaching fails to bring about obvious improvement, a direct evaluation result based on the most recent data is needed to reflect the teacher's teaching effectiveness. Therefore, performing step B31 can avoid the problem of trying to determine the teacher's teaching effectiveness through complex comparisons and ratio calculations when the teacher's teaching effectiveness has not improved. This reduces unnecessary calculations and possible misunderstandings, simplifies the evaluation process, and quickly provides feedback on the teacher's teaching effectiveness, so that education administrators can take corresponding measures based on the latest evaluation results.

[0079] This embodiment provides a hybrid teaching effectiveness evaluation method, which collects teaching data for multiple times, evaluates the teacher's teaching content and the student's learning ability separately, and then compares the results of the two evaluations. In this way, a comprehensive judgment is made on the teacher's teaching ability based on the teacher's understanding of the student's learning situation, making the evaluation of the teacher's teaching effectiveness more accurate.

[0080] In a feasible implementation manner, after the step of evaluating the continuity of each knowledge point according to each teaching moment in step S114, steps S401 to S403 may also be included: Step S401, when the teaching moments corresponding to the knowledge points are not continuous, determining the correlation between the interspersed knowledge points that interrupt the continuity of the knowledge points and the knowledge points, and obtaining correlation data; It should be noted that interspersed knowledge points refer to knowledge points of different attribute categories that exist between knowledge points of the same attribute category. The teaching of this knowledge point may help to master subsequent knowledge points; correlation data refers to quantitative information that describes the logical relationship between interspersed knowledge points and other knowledge points.

[0081] It is understandable that during the teaching process, some knowledge points may not have type consistency due to teaching arrangements or content characteristics, and it is necessary to specifically identify the logical relationship between these interspersed knowledge points and the remaining knowledge points. Therefore, performing step S401 can avoid the problem of inaccurate teaching content evaluation caused by lack of category consistency between knowledge points, thereby ensuring the comprehensiveness and accuracy of teaching content evaluation and better understanding the intrinsic connection between knowledge points.

[0082] Exemplarily, when the teaching moments corresponding to each knowledge point are not continuous, that is, when the teaching sequence corresponding to each knowledge point of the same attribute category is interrupted, the knowledge points of different attribute categories between the knowledge points of the same attribute category are identified, that is, interspersed knowledge points. For example, the order of knowledge points in this teaching content is knowledge point 1, knowledge point 2, knowledge point 3, knowledge point 4, knowledge point 5, which indicates that the knowledge points corresponding to category A: knowledge point 1, knowledge point 3, are not continuous, so the interspersed knowledge point: knowledge point 2 is judged for relevance. By constructing a knowledge graph or using a correlation analysis algorithm, the relevance between these interspersed knowledge points and other knowledge points is quantified to generate relevance data, which may include dependencies, logical sequences, or conceptual similarities between knowledge points.

[0083] Step S402, adjusting the association data based on the progressive difficulty between the interspersed knowledge point and the subsequent knowledge point, wherein the subsequent knowledge point is a knowledge point that is adjacent to the interspersed knowledge point at the teaching time and is located after the interspersed knowledge point among the knowledge points; It should be noted that the progressive difficulty level refers to the gradual increase or decrease in the learning difficulty of knowledge points; subsequent knowledge points refer to the knowledge points that follow the interspersed knowledge points in the teaching sequence and are adjacent to them in time.

[0084] It is understandable that since the progressive difficulty of knowledge points will affect students' learning outcomes and understanding levels, the correlation data needs to be adjusted according to this progressiveness. Therefore, performing step S402 can avoid the problem of biased evaluation results caused by not considering the progressive difficulty of knowledge points, thereby more accurately reflecting the logical relationship and learning difficulty between knowledge points, so as to optimize the teaching content and sequence.

[0085] For example, it is necessary to first determine the adjacent knowledge points after each interspersed knowledge point, that is, the subsequent knowledge points, and then determine the difficulty progression between the interspersed knowledge points and the subsequent knowledge points based on the preset difficulty coefficients of each knowledge point. Then, according to this progression, the previously obtained association data is adjusted. For example, if there is a correlation between the interspersed knowledge point 2 and category A, and the difficulty coefficient is low, that is, the difficulty progression is increasing, it means that the knowledge point 2 plays an auxiliary role in the understanding of the knowledge point 3, and the corresponding association data is increased; on the contrary, if the difficulty coefficient is greater than or equal to the difficulty coefficient of the knowledge point 3, that is, the difficulty progression is decreasing, then the corresponding association data is reduced. This adjustment can be achieved through an algorithm, which will modify the weight of the association data according to a preset rule or model.

[0086] Step S403: determining the first content evaluation sub-data based on the adjusted relevance data.

[0087] It is understandable that, since the adjusted correlation data is needed to evaluate the effectiveness and suitability of the teaching content, performing step S403 can avoid ignoring the importance of the correlation between knowledge points and the rationality of the setting of interspersed knowledge points in content evaluation, thereby providing a more accurate and targeted teaching content evaluation.

[0088] Exemplarily, the adjusted relevance data is used as input, and the evaluation model is used to calculate the first content evaluation sub-data, thereby providing a quantitative basis for the overall teaching content evaluation. Specifically, the evaluation model can combine the relevance data with indicators such as teaching objectives and student learning outcomes, and output the first content evaluation sub-data through a series of algorithm processing. The data may include a comprehensive consideration of the importance of knowledge points, the expected value of teaching effects, and students' perception of learning difficulty.

[0089] In this implementation, by analyzing the correlation of knowledge points and adjusting relevant data based on the progressive degree of difficulty, the problem of inaccurate teaching content evaluation and neglect of logical relationships between knowledge points due to discontinuous teaching moments of knowledge points is avoided, and the effects of accurately identifying and evaluating the correlation between knowledge points in teaching content and optimizing the teaching sequence and content design are achieved. Specifically, this method determines the correlation between interspersed knowledge points and other knowledge points, and adjusts the correlation data by considering the progressive degree of difficulty between knowledge points, thereby ensuring the comprehensiveness and effectiveness of teaching content evaluation, and then helping to better understand and optimize the teaching structure and improve teaching quality.

[0090] In a feasible implementation manner, the step of evaluating the progressive difficulty of each knowledge point according to each teaching moment to obtain the second content evaluation sub-data in step S114 may include steps S410 to S430: Step S410, determining the teaching duration and teaching sequence of each knowledge point based on each teaching moment, and performing a teaching difficulty evaluation on each knowledge point based on each teaching duration to obtain first difficulty evaluation data, and performing a teaching difficulty evaluation on each knowledge point based on the teaching sequence to obtain second difficulty evaluation data; It should be noted that the first difficulty assessment data refers to the assessment result of the difficulty of the knowledge point based on the teaching time, and the second difficulty assessment data refers to the assessment result of the difficulty of the knowledge point based on the teaching sequence.

[0091] It is understandable that in order to quantify the difficulty of each knowledge point in the teaching process and consider the impact of teaching time and sequence on the difficulty, step S410 is performed to avoid the problem of being unable to accurately assess the objective difficulty of the knowledge points, thereby more accurately assessing the teaching difficulty of each knowledge point and providing effective and reliable data support for subsequent evaluations.

[0092] Exemplarily, firstly, the teaching time data of each knowledge point at the beginning and end are collected, the teaching time of each knowledge point is calculated, and then the teaching order of each knowledge point is determined according to the teaching content. Then, the relationship between the teaching time and the difficulty of the knowledge point is analyzed using a statistical model to generate the first difficulty assessment data, wherein the longer the teaching time, the higher the difficulty of the corresponding knowledge point. At the same time, by analyzing the correlation between the teaching order and the difficulty of the knowledge point, the second difficulty assessment data is generated, wherein the later the teaching order, the higher the difficulty of the corresponding knowledge point.

[0093] Step S420, comparing the collection of teaching durations and teaching sequences of each teacher for each knowledge point, determining the correlation between the teaching duration and the teaching sequence of each knowledge point, and performing teaching difficulty evaluation on each knowledge point based on the correlation to obtain third difficulty evaluation data; It should be noted that the correlation between the teaching duration and teaching sequence of each knowledge point refers to the consistency or difference in the duration and sequence arrangement of knowledge points by different teachers in actual teaching; the third difficulty assessment data refers to the assessment result of the difficulty of the knowledge points based on this correlation.

[0094] It is understandable that in order to analyze the differences in teaching time and sequence of knowledge points among different teachers, and the impact of these differences on teaching difficulty, step S420 is performed. This can avoid the problem of ignoring the impact of teaching differences among teachers on difficulty assessment. By comparing teaching methods, the impact of teaching time and sequence on teaching difficulty is revealed, thereby promoting teaching standardization.

[0095] Exemplarily, based on the big data model, the teaching time and teaching sequence of each teacher on each knowledge point in the same category are collected and counted, and the collection of teaching time and teaching sequence of different teachers on each knowledge point is obtained. The teaching time set and the teaching sequence set are compared with each other to determine the mutual correlation between the teaching time and teaching sequence of each knowledge point of the same attribute category. For example, when each teacher teaches the knowledge points of this category, the teaching time of a certain knowledge point will be longer, and the teaching sequence will be earlier. Then, the teaching situation of this knowledge point is determined to meet the teaching demand, so the difficulty of this knowledge point is processed so that the difficulty is between two adjacent knowledge points.

[0096] Step S430, calculating the difficulty data of each knowledge point based on the first difficulty assessment data, the second difficulty assessment data and the third difficulty assessment data, and determining the second content assessment sub-data according to the progressiveness of each difficulty data.

[0097] It is understandable that in order to integrate multiple data sources to comprehensively evaluate the difficulty of knowledge points, step S430 is performed. By providing a multi-dimensional teaching difficulty assessment model, the problem of incomplete assessment caused by a single assessment dimension can be avoided, and a comprehensive evaluation of the difficulty of knowledge points can be achieved, providing a more scientific basis for the adjustment and optimization of teaching content.

[0098] Exemplarily, the first difficulty assessment data, the second difficulty assessment data, and the third difficulty assessment data are input into a comprehensive assessment model, which combines the three sets of data and calculates the comprehensive difficulty data of each knowledge point by weighted average or other synthesis methods, and then determines the second content assessment sub-data based on the progressiveness of these difficulty data, that is, the trend of the knowledge point difficulty gradually increasing. This process can be achieved by an algorithm that can output the difficulty score of each knowledge point according to preset weights and standards.

[0099] Exemplarily, after step S420, the teaching difficulty of each knowledge point can also be evaluated through a pre-trained difficulty evaluation model to obtain fourth difficulty evaluation data, so as to calculate the difficulty data of each knowledge point based on the first difficulty evaluation data, the second difficulty evaluation data, the third difficulty evaluation data and the fourth difficulty evaluation data, and determine the second content evaluation sub-data according to the progressiveness of each difficulty data. Wherein, the pre-trained difficulty evaluation model is obtained by training a preset deep learning model, and the training process of the deep learning model includes: obtaining a teaching assessment text set, wherein any teaching assessment text in the teaching assessment text set includes knowledge point annotations and the correctness judgment results corresponding to the knowledge point annotations; inputting the teaching assessment text set into the deep learning model, so as to learn the distribution of wrong questions of each knowledge point based on the knowledge point annotations and the corresponding correctness judgment results in the teaching assessment text set through the deep learning model, and obtain the pre-trained difficulty evaluation model. Therefore, the process of the pre-training difficulty assessment model performing teaching difficulty assessment on each of the knowledge points, that is, the pre-training difficulty assessment model performs teaching difficulty assessment on each of the knowledge points according to the learned distribution of wrong questions. For example, if a certain knowledge point accounts for a higher proportion in the learned distribution of wrong questions, then the teaching difficulty assessment result of the knowledge point corresponds to a more difficult knowledge point; if a certain knowledge point accounts for a smaller proportion or does not exist in the learned distribution of wrong questions, then the teaching difficulty assessment result of the knowledge point corresponds to a simpler knowledge point.

[0100] In this implementation, by determining the teaching duration and sequence, and conducting difficulty assessments separately, and combining the teaching differences between teachers, multi-dimensional difficulty assessment data is obtained. This avoids the problem of judging the difficulty of knowledge points based solely on subjective experience and ignoring the impact of teaching duration and sequence on difficulty in traditional teaching, and achieves a quantitative, objective and comprehensive assessment of the difficulty of knowledge points, thereby ensuring the accuracy and comprehensiveness of the assessment results.

[0101] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 After step S30, the hybrid teaching effect evaluation method further includes steps S40 to S60: Step S40, comparing the capability assessment data in the second assessment result with preset standard capability data to obtain corresponding capability matching data; It should be noted that standard ability data refers to the degree of match between the teacher's teaching content and the students' learning ability, which is pre-set according to education standards or curriculum requirements; ability fit data refers to the degree of match between the teaching content and the students' learning ability.

[0102] It is understandable that in order to quantify the degree of match between the teacher's relevant ability level and the preset standard, step S40 is performed, which can avoid the problem of being unable to objectively identify the degree of match between the teacher's teaching content and the students' learning ability, and achieve an objective evaluation of the teacher's ability.

[0103] Exemplarily, the ability assessment data in the second assessment result is that the number of better students accounts for 20%, the number of average students accounts for 60%, and the number of poor students accounts for 20%. The built-in standard ability data is that the number of better students accounts for 20%, the number of average students accounts for 60%, and the number of poor students accounts for 20%. By comparing the ability assessment data with the built-in standard data value, since the ability assessment data and the standard data value are the same, it is determined that the teaching content is consistent with the students' learning ability, and the corresponding ability match data is 1. Otherwise, the ratio of the corresponding items is calculated to determine the corresponding ability match data.

[0104] Step S50, comparing the content evaluation data in the second evaluation result with a preset standard teaching effect to obtain corresponding teaching data; It should be noted that teaching data refers to the comparison results between teachers’ actual teaching results and preset standard teaching results.

[0105] It is understandable that in order to evaluate the gap between the teacher's teaching content and the expected teaching effect, step S50 is performed, which can avoid the problem of lack of quantitative indicators in teaching effect evaluation, thereby providing a method to measure the effectiveness of teachers' teaching content, which helps to optimize teaching design and improve teaching effects.

[0106] For example, if the content evaluation data in the second evaluation result is 8, and the built-in standard teaching effect is 10, the corresponding teaching data is 8÷10=0.8.

[0107] Step S60, associating and outputting the ability matching data, the teaching data and the teaching effect.

[0108] It is understandable that in order to combine the teacher's ability assessment, content assessment and teaching effectiveness to obtain a comprehensive teaching evaluation result, step S60 is performed to avoid the problem of scattered and unsystematic evaluation results, thereby achieving a comprehensive evaluation of the teacher's comprehensive teaching level, and then providing a comprehensive teaching evaluation report to help education managers make more comprehensive and accurate decisions.

[0109] For example, the ability fit data, teaching data, and teaching effectiveness data are integrated into a comprehensive evaluation report. This process can be achieved through a data management platform, which brings together data from different evaluation dimensions and presents them through visualization tools. For example, the platform may generate a report containing charts and key indicators to show the teacher's ability fit, the effectiveness of the teaching content, and the overall teaching effectiveness.

[0110] In this embodiment, by implementing a multi-dimensional teaching evaluation program, the ability evaluation data is compared with the standard ability data to obtain ability fit data, the content evaluation data is compared with the standard teaching effect to obtain teaching data, and these data are associated with the teaching effect and output, thereby avoiding the problem of relying only on a single indicator or subjective judgment in traditional evaluation, ensuring the accuracy and completeness of the evaluation results, and achieving a comprehensive, objective and quantitative evaluation of teachers' teaching abilities, thereby helping education administrators to better understand teachers' teaching performance, optimize teacher training plans, and improve overall teaching quality.

[0111] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those of the above-mentioned embodiments 1 and 2 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S402 may further include steps S01 to S03: Step S01, when the difficulty level between the interspersed knowledge point and the subsequent knowledge point is progressively decreasing, performing the step of determining the first content evaluation sub-data based on the adjusted relevance data based on the relevance data; It is understandable that when the interspersed knowledge points and the subsequent knowledge points show "decreasing difficulty" (for example, first teaching advanced calculus and then returning to basic algebra), there is no need to adjust the correlation data, so step S01 is performed, and by not adjusting the correlation data, objective reflection of the correlation data between the interspersed knowledge points and the remaining knowledge points is achieved.

[0112] Step S02, when the difficulty level between the interspersed knowledge point and the subsequent knowledge point is progressively increasing or equal, matching the interspersed knowledge point with the teacher's history teaching content collection; Step S03, if the interspersed knowledge point does not exist in the history teaching content collection, then based on the relevance data, the step of determining the first content evaluation sub-data based on the adjusted relevance data is performed; It is understandable that when the difficulty of the interspersed knowledge points increases or remains the same as that of the subsequent knowledge points (such as the transition from basic algebra to geometric proofs), and the interspersed knowledge points have never appeared in history teaching, there is no need to adjust the correlation data, so step S03 is performed, and by not adjusting the correlation data, objective reflection of the correlation data between the interspersed knowledge points and the remaining knowledge points is achieved.

[0113] Step S04: if the interspersed knowledge points exist in the history teaching content collection, weighted adjustment is performed on the correlation data based on a preset interference coefficient.

[0114] It is understandable that, since the interspersed knowledge point has appeared in history teaching, it is necessary to additionally consider that the interspersed knowledge point is easier to understand for students, so step S04 is performed. By making corresponding adjustments to the related data when the interspersed knowledge point has appeared in history teaching, it is possible to avoid evaluation bias caused by inaccurate grasp of the interspersed knowledge points, thereby achieving accurate grasp of the impact of the interspersed knowledge points on the evaluation of teaching content.

[0115] For example, if the interspersed knowledge point exists in the collection of history teaching content, indicating that the interspersed knowledge point exists in the history teaching situation, then the difficulty coefficient of the interspersed knowledge point for students in the current state is reduced, thereby making the interspersed knowledge point play an auxiliary role in the understanding of subsequent knowledge points, thereby increasing the corresponding correlation data.

[0116] In this embodiment, by only adjusting the correlation data between the interspersed knowledge points and the remaining knowledge points when the difficulty level between the interspersed knowledge points and the subsequent knowledge points is increasing or remaining the same, and the interspersed knowledge points have appeared in history teaching, so as to reasonably reflect the impact of the interspersed knowledge points on the evaluation of teaching content, thereby further improving the accuracy and comprehensiveness of the evaluation of teachers' teaching effectiveness.

[0117] For example, to help understand the implementation process of the hybrid teaching effect evaluation method obtained by combining the above-mentioned embodiments 1, 2 and 3, please refer to Figure 4 , Figure 4 A brief flow chart of the hybrid teaching effect evaluation method is provided, specifically: The teaching content and teaching results are collected twice, namely the history teaching content and history teaching results obtained in the first collection, and the current teaching content and current teaching results obtained in the second collection. For the first collection process, the history teaching content is continuously evaluated to obtain the first content evaluation sub-data, and the history teaching content is progressively evaluated in terms of difficulty to obtain the second content evaluation sub-data, and then the first content evaluation sub-data and the second content evaluation sub-data are combined to obtain the content evaluation data. The history teaching results are divided and evaluated by class and individual to obtain the ability evaluation data. Finally, the evaluated content evaluation data and ability evaluation data are combined to obtain the first evaluation result corresponding to the first collection process. In the figure, the process of the current teaching content and the current teaching results in the second collection process is represented by a dotted line, which means that the process is consistent with the data processing process of the first collection process, and the second evaluation result is finally obtained, so it is not repeated. Then the first evaluation result and the second evaluation result are compared to obtain the improvement of the teaching effect, and the teaching effect of the teacher is evaluated based on the improvement. In addition, based on the ability assessment data and content assessment data in the second assessment result, corresponding ability fit data and teaching data are generated, and the teaching effect, ability fit data and teaching data are output together.

[0118] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the hybrid teaching effect evaluation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0119] This application also provides a hybrid teaching effect evaluation system, please refer to Figure 5 , the hybrid teaching effect evaluation system includes: The analysis module 10 is used to determine the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the type of the teaching content includes historical teaching content and current teaching content, the type of the teaching performance includes historical teaching performance and current teaching performance, the evaluation result determined according to the historical teaching content and the historical teaching performance is the first evaluation result, and the evaluation result determined according to the current teaching content and the current teaching performance is the second evaluation result; A comparison module 20, used to compare the first evaluation result with the second evaluation result to determine the improvement of the teaching effect; The evaluation module 30 is used to evaluate the teaching effect of the teacher based on the improvement status.

[0120] Optionally, the analysis module 10 is further used for: Determine the corresponding teaching knowledge points according to the teacher's teaching content, and perform relevance evaluation on the teaching knowledge points to obtain content evaluation data; Classifying the classes to which the students belong based on their teaching performance to obtain class grade data, and classifying each student in any grade class based on the teaching performance of each student and the class grade data of the grade class to obtain student grade data; Counting the number of students at each level in the student level data, obtaining a level data value of the corresponding level, and using a comparison result of each level data value with a preset standard data value as ability assessment data, wherein the conformity of the comparison result is positively correlated with the ability assessment data; An evaluation result of the teaching effect is calculated based on the content evaluation data and the ability evaluation data.

[0121] Optionally, the analysis module 10 is further used for: Identify the knowledge points of the teacher's teaching content to obtain the corresponding teaching knowledge point data, and identify the knowledge points of the preset teaching syllabus to obtain the corresponding knowledge point range; Comparing the teaching knowledge point data with the knowledge point range, and canceling the step of determining the evaluation result of the teaching effect when the teaching knowledge point data is outside the knowledge point range; In the case where the teaching knowledge point is within the knowledge point range, determining the attribute category of each knowledge point in the teaching knowledge point data based on the teaching syllabus, and for each knowledge point of any attribute category, determining the teaching time of each knowledge point based on the teaching content; The continuity of each knowledge point is evaluated at each teaching moment to obtain the first content evaluation sub-data, and the progressiveness of the difficulty of each knowledge point is evaluated at each teaching moment to obtain the second content evaluation sub-data; Based on the first content-evaluation sub-data and the second content-evaluation sub-data, content-evaluation data is calculated.

[0122] Optionally, the analysis module 10 is further used for: In the case where the teaching moments corresponding to the knowledge points are not continuous, determining the interspersed knowledge points that interrupt the continuity of the knowledge points and the correlation between the knowledge points to obtain correlation data; The association data is adjusted based on the progressive difficulty between the interspersed knowledge points and subsequent knowledge points, wherein the subsequent knowledge points are knowledge points that are adjacent to the interspersed knowledge points at the teaching time and are located after the interspersed knowledge points; The first content-evaluation sub-data is determined based on the adjusted relevance data.

[0123] Optionally, the analysis module 10 is further used for: Determine the teaching duration and teaching sequence of each knowledge point based on each teaching moment, and perform teaching difficulty evaluation on each knowledge point based on each teaching duration to obtain first difficulty evaluation data, and perform teaching difficulty evaluation on each knowledge point based on the teaching sequence to obtain second difficulty evaluation data; Comparing the collection of teaching time and teaching sequence of each teacher for each knowledge point, determining the correlation between the teaching time and teaching sequence of each knowledge point, and performing teaching difficulty evaluation on each knowledge point based on the correlation to obtain third difficulty evaluation data; Based on the first difficulty evaluation data, the second difficulty evaluation data and the third difficulty evaluation data, the difficulty data of each knowledge point is calculated, and the second content evaluation sub-data is determined according to the progressiveness of each difficulty data.

[0124] Optionally, the comparison module 20 is further used for: Determining a difference relationship between the first evaluation result and the second evaluation result; In the case where the difference relationship is that the second evaluation result is less than the first evaluation result, determining a first achievement degree of the first evaluation result relative to a preset standard teaching effect, and determining an improvement status of the teaching effect according to the first achievement degree and a preset standard fluctuation range; When the difference relationship is that the second evaluation result is greater than or equal to the first evaluation result, the second achievement degree of the second evaluation result relative to the preset standard teaching effect is determined, and the improvement status of the teaching effect is determined based on the second achievement degree and the preset standard fluctuation range.

[0125] Optionally, the evaluation module 30 is further configured to: When the improvement condition is that there is improvement, comparing the improvement condition with a preset standard teaching effect; When the improvement condition is within the standard fluctuation range preset for the standard teaching effect, the first evaluation result and the second evaluation result are respectively subjected to difference calculation with the numerical values ​​corresponding to the standard teaching effect to obtain a first evaluation difference and a second evaluation difference; The teaching effectiveness of the teacher is determined according to the ratio of the first evaluation difference to the second evaluation difference.

[0126] Optionally, the evaluation module 30 is further configured to: Comparing the capability assessment data in the second assessment result with the preset standard capability data to obtain corresponding capability matching data; Comparing the content evaluation data in the second evaluation result with the preset standard teaching effect to obtain corresponding teaching data; The ability matching data, the teaching data and the teaching effect are output in association.

[0127] Optionally, the analysis module 10 is further used for: In the case where the difficulty level between the interspersed knowledge points and the subsequent knowledge points is progressively decreasing, performing the step of determining the first content evaluation sub-data based on the adjusted relevance data based on the relevance data; In the case where the difficulty level between the interspersed knowledge points and the subsequent knowledge points is progressively increasing or equal, matching the interspersed knowledge points with the teacher's history teaching content collection; If the interspersed knowledge point does not exist in the history teaching content collection, then performing the step of determining the first content evaluation sub-data based on the adjusted relevance data based on the relevance data; If the interspersed knowledge points exist in the history teaching content collection, the correlation data is weighted and adjusted based on a preset interference coefficient.

[0128] The hybrid teaching effect evaluation system provided by the present application adopts the hybrid teaching effect evaluation method in the above embodiment, which can solve the technical problem of how to improve the accuracy of the evaluation of the teacher's teaching effect. Compared with the prior art, the beneficial effects of the hybrid teaching effect evaluation system provided by the present application are the same as the beneficial effects of the hybrid teaching effect evaluation method provided by the above embodiment, and other technical features of the hybrid teaching effect evaluation system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0129] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the hybrid teaching effect evaluation method in the above-mentioned embodiment.

[0130] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above.

[0131] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: determines the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the type of the teaching content includes historical teaching content and current teaching content, and the type of the teaching performance includes historical teaching performance and current teaching performance, the evaluation result determined according to the historical teaching content and the historical teaching performance is the first evaluation result, and the evaluation result determined according to the current teaching content and the current teaching performance is the second evaluation result; compares the first evaluation result with the second evaluation result to determine the improvement status of the teaching effect; and evaluates the teaching effect of the teacher based on the improvement status.

[0132] Computer program code for performing operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​and conventional procedural programming languages.

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of a code, which contains one or more executable instructions for implementing a specified logical function.

[0134] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned hybrid teaching effect evaluation method, and can solve the technical problem of how to improve the accuracy of the evaluation of the teacher's teaching effect. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the hybrid teaching effect evaluation method provided in the above-mentioned embodiment, and will not be repeated here.

Claims

1. A hybrid teaching effect evaluation method, characterized in that: The hybrid teaching effect evaluation method includes: Determine the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the types of the teaching content include historical teaching content and current teaching content, the types of the teaching performance include historical teaching performance and current teaching performance, the evaluation result determined according to the historical teaching content and the historical teaching performance is the first evaluation result, and the evaluation result determined according to the current teaching content and the current teaching performance is the second evaluation result; Comparing the first evaluation result with the second evaluation result to determine the improvement of the teaching effect; The teaching effectiveness of the teacher is evaluated based on the improvement status.

2. The hybrid teaching effect evaluation method according to claim 1, characterized in that: The step of determining the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance includes: Determine the corresponding teaching knowledge points according to the teacher's teaching content, and perform relevance evaluation on the teaching knowledge points to obtain content evaluation data; Classifying the classes to which the students belong based on their teaching performance to obtain class grade data, and classifying each student in any grade class based on the teaching performance of each student and the class grade data of the grade class to obtain student grade data; Counting the number of students at each level in the student level data, obtaining a level data value of the corresponding level, and using a comparison result of each level data value with a preset standard data value as ability assessment data, wherein the conformity of the comparison result is positively correlated with the ability assessment data; An evaluation result of the teaching effect is calculated based on the content evaluation data and the ability evaluation data.

3. The hybrid teaching effect evaluation method according to claim 2, characterized in that: The step of determining the corresponding teaching knowledge points according to the teacher's teaching content, and performing relevance evaluation on the teaching knowledge points to obtain content evaluation data includes: Identify the knowledge points of the teacher's teaching content to obtain the corresponding teaching knowledge point data, and identify the knowledge points of the preset teaching syllabus to obtain the corresponding knowledge point range; Comparing the teaching knowledge point data with the knowledge point range, and canceling the step of determining the evaluation result of the teaching effect when the teaching knowledge point data is outside the knowledge point range; In the case where the teaching knowledge point is within the knowledge point range, determining the attribute category of each knowledge point in the teaching knowledge point data based on the teaching syllabus, and for each knowledge point of any attribute category, determining the teaching time of each knowledge point based on the teaching content; The continuity of each knowledge point is evaluated at each teaching moment to obtain first content evaluation sub-data, and the progressiveness of the difficulty of each knowledge point is evaluated at each teaching moment to obtain second content evaluation sub-data; Based on the first content-evaluation sub-data and the second content-evaluation sub-data, content-evaluation data is calculated.

4. The hybrid teaching effect evaluation method according to claim 3 is characterized in that: After the step of evaluating the continuity of each knowledge point according to each teaching moment, the following step is further included: In the case where the teaching moments corresponding to the knowledge points are not continuous, determining the interspersed knowledge points that interrupt the continuity of the knowledge points and the correlation between the knowledge points to obtain correlation data; The association data is adjusted based on the progressive difficulty between the interspersed knowledge points and subsequent knowledge points, wherein the subsequent knowledge points are knowledge points that are adjacent to the interspersed knowledge points at the teaching time and are located after the interspersed knowledge points; The first content-evaluation sub-data is determined based on the adjusted relevance data.

5. The hybrid teaching effect evaluation method according to claim 3, characterized in that: The step of evaluating the progressive difficulty of each knowledge point according to each teaching moment to obtain the second content evaluation sub-data includes: Determine the teaching duration and teaching sequence of each knowledge point based on each teaching moment, and perform teaching difficulty evaluation on each knowledge point based on each teaching duration to obtain first difficulty evaluation data, and perform teaching difficulty evaluation on each knowledge point based on the teaching sequence to obtain second difficulty evaluation data; Comparing the collection of teaching time and teaching sequence of each teacher for each knowledge point, determining the correlation between the teaching time and teaching sequence of each knowledge point, and performing teaching difficulty evaluation on each knowledge point based on the correlation to obtain third difficulty evaluation data; Based on the first difficulty evaluation data, the second difficulty evaluation data and the third difficulty evaluation data, the difficulty data of each knowledge point is calculated, and the second content evaluation sub-data is determined according to the progressiveness of each difficulty data.

6. The hybrid teaching effect evaluation method according to claim 1, characterized in that: The first evaluation result and the second evaluation result are both numerical values, and the step of comparing the first evaluation result and the second evaluation result to determine the improvement of the teaching effect includes: Determining a difference relationship between the first evaluation result and the second evaluation result; In the case where the difference relationship is that the second evaluation result is less than the first evaluation result, determining a first achievement degree of the first evaluation result relative to a preset standard teaching effect, and determining an improvement status of the teaching effect according to the first achievement degree and a preset standard fluctuation range; When the difference relationship is that the second evaluation result is greater than or equal to the first evaluation result, the second achievement degree of the second evaluation result relative to the preset standard teaching effect is determined, and the improvement status of the teaching effect is determined based on the second achievement degree and the preset standard fluctuation range.

7. The hybrid teaching effect evaluation method according to claim 1, characterized in that: The first evaluation result and the second evaluation result are both numerical values, and the step of evaluating the teaching effect of the teacher based on the improvement status includes: When the improvement condition is that there is improvement, comparing the improvement condition with a preset standard teaching effect; When the improvement condition is within the standard fluctuation range preset for the standard teaching effect, the first evaluation result and the second evaluation result are respectively subjected to difference calculation with the numerical values ​​corresponding to the standard teaching effect to obtain a first evaluation difference and a second evaluation difference; The teaching effectiveness of the teacher is determined according to the ratio of the first evaluation difference to the second evaluation difference.

8. The hybrid teaching effect evaluation method according to claim 1, characterized in that: After the step of evaluating the teaching effect of the teacher based on the improvement status, the method further includes: Comparing the capability assessment data in the second assessment result with the preset standard capability data to obtain corresponding capability matching data; Comparing the content evaluation data in the second evaluation result with the preset standard teaching effect to obtain corresponding teaching data; The ability matching data, the teaching data and the teaching effect are output in association.

9. A hybrid teaching effect evaluation system, characterized in that: The hybrid teaching effect evaluation system comprises: An analysis module, used to determine the evaluation result of the teaching effect according to the teacher's teaching content and the student's teaching performance, wherein the types of the teaching content include historical teaching content and current teaching content, the types of the teaching performance include historical teaching performance and current teaching performance, the evaluation result determined according to the historical teaching content and the historical teaching performance is the first evaluation result, and the evaluation result determined according to the current teaching content and the current teaching performance is the second evaluation result; A comparison module, used to compare the first evaluation result with the second evaluation result to determine the improvement of the teaching effect; An evaluation module is used to evaluate the teaching effect of the teacher based on the improvement status.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the hybrid teaching effect evaluation method according to any one of claims 1 to 8 are implemented.

Images