Teaching quality comprehensive evaluation system and method based on teaching sequence visual angle

Abstract

The invention relates to the technical field of teaching quality evaluation, and particularly discloses a teaching quality comprehensive evaluation system and method based on a teaching sequence perspective, and the system comprises a data management module, a learning sequence analysis module, a teaching sequence analysis module, a teaching quality evaluation module, a feedback improvement module, and a decision support module. The data management module is used for collecting data generated in an education and teaching process, including learning sequence data of students and teaching sequence data of teachers, and performing arrangement and standardization processing on the collected data; the learning sequence analysis module is used for analyzing learning sequence data of the students through a data mining technology; according to the invention, by integrating the student learning sequence data and the teacher teaching sequence data and combining a data mining technology and a deep learning algorithm, key factors influencing the teaching quality are accurately identified, the teaching quality is objectively evaluated in a data-driven manner, the deviation of manual evaluation is avoided, and the teaching quality is accurately evaluated. And the transparency and fairness of teaching quality evaluation are enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of teaching quality evaluation, and specifically relates to a teaching quality comprehensive evaluation system and method based on a teaching sequence perspective. Background Art

[0002] Teaching quality is a direct factor affecting the quality of talent training, and teaching quality evaluation is a measure of the quality of teaching interaction between teachers and students. It is of great significance for discovering excellent teaching methods, guiding the teaching process and building a style of study. Through teaching quality evaluation, we can comprehensively improve and improve teaching work, optimize teaching methods, and thus improve the overall teaching level and promote the standardized management of schools. Therefore, the evaluation of teaching quality must be scientific and adapted to reality to ensure the actual fit of the final evaluation results and avoid subsequent teaching adjustment deviations.

[0003] At present, the most practical methods for evaluating the teaching quality of individual teachers in schools are still listening to classes and holding discussions. The listening methods here are divided into attending classes in person and listening to classes remotely via video without entering the classroom. However, listening to classes and holding discussions collect more subjective information and less objective information. It is usually possible to promote teaching through evaluation, but it is more difficult to promote learning through evaluation. Existing teaching quality evaluation methods usually rarely consider the sequence of students' learning process and the coverage of knowledge points based on the learning sequence, which are direct methods of teaching quality evaluation. The coverage of knowledge points is usually tested based on exercises. Exercise-based tests, on the one hand, are an assessment of students' mastery of knowledge points, and on the other hand, they can also examine students' thinking methods, thinking quality, and the worldview and values ​​that students develop.

[0004] Therefore, it is necessary to propose a comprehensive teaching quality evaluation system and method based on the teaching sequence perspective to solve the problem that there is little teaching quality evaluation in the existing technology in terms of students' learning process sequence and teachers' teaching sequence.

[0005] The above information disclosed in this background technology is only used to increase the understanding of the background technology of the present invention and therefore, it may include information that does not constitute the prior art known to ordinary technicians in this field. Summary of the invention

[0006] The purpose of the present invention is to provide a teaching quality comprehensive evaluation system and method based on the teaching sequence perspective to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A comprehensive teaching quality evaluation system based on the teaching sequence perspective, including: data management module, learning sequence analysis module, teaching sequence analysis module, teaching quality evaluation module, feedback improvement module, decision support module

[0009] The data management module is used to collect data generated during the education and teaching process, including students' learning sequence data and teachers' teaching sequence data, and to organize and standardize the collected data;

[0010] The learning sequence analysis module is used to analyze the learning sequence data of the students through data mining technology, to mine the learning rules and understand the learning situation of the students;

[0011] The teaching sequence analysis module is used to analyze the teacher's teaching sequence data using a deep learning algorithm to evaluate whether the teacher's teaching method is effective;

[0012] The teaching quality evaluation module is used to comprehensively analyze the learning sequence data and the teacher's teaching sequence data, and give a comprehensive evaluation of the teaching quality through an evaluation model;

[0013] The feedback improvement module is used to obtain feedback information based on the above comprehensive evaluation and build an interactive communication channel between teachers and students;

[0014] The decision support module is used to predict teaching quality based on big data and machine learning and provide decision suggestions.

[0015] Preferably, the data management module is also used to collect students' attendance, activity level, and classroom participation data in real time through IoT devices and sensors; perform sentiment analysis and text classification on the collected text data through natural language processing technology; and use data integration technology to integrate data from different platforms through an API interface.

[0016] Preferably, the learning sequence analysis module is also used to discover potential associations between students' learning behavior data through association rule mining and evaluate their learning habits; cluster students according to the learning behavior data in combination with the K-means algorithm to identify different student groups; use LSTM to analyze the learning sequence data, predict students' future learning status, and identify key factors affecting students' learning progress.

[0017] Preferably, the teaching sequence analysis module is also used to analyze the teaching sequence data using LSTM, capture teaching content, student reactions and progress changes, and evaluate the effectiveness of teaching methods; analyze the teaching sequence data through the Transformer model to identify key behavior patterns in teaching; and apply Shapley values ​​in LSTM and Transformer models to evaluate the contribution of each feature to the teaching effect.

[0018] Preferably, the teaching quality assessment module is also used to extract features based on the analysis process using a multivariate indicator joint analysis method to construct an evaluation index system; to calculate the importance of each indicator and determine its weight using a hierarchical analysis method in combination with the Shapley value; to establish the evaluation model through a fuzzy comprehensive evaluation method, to score the teaching quality, and to obtain a scoring result.

[0019] Preferably, the feedback improvement module is also used to display the evaluation results and teaching sequence data analysis to teachers, point out problems in teaching, and generate targeted improvement suggestions; display the evaluation results and learning sequence data analysis to students, and provide personalized learning suggestions; and provide school administrators with teaching improvement plans based on the above data analysis according to the evaluation results.

[0020] Preferably, the decision support module is also used to predict the changing trend of teaching quality using a machine learning algorithm based on the evaluation results, generate decision opinions and send them to the school administrators; and recommend corresponding learning resources and paths to students through the Internet in combination with the above-mentioned personalized learning suggestions.

[0021] The comprehensive evaluation method of teaching quality based on the teaching sequence perspective includes:

[0022] Step 1: Collect comprehensive education and teaching data, including student data, teacher data, course data, and classroom feedback data, and clean and integrate the collected data;

[0023] Step 2: Use data mining technology and deep learning algorithm to analyze the student data, teacher data, course data and classroom feedback data respectively to obtain analysis results;

[0024] Step 3: According to the analysis results, a fuzzy comprehensive evaluation method is selected to construct a model to conduct a multi-dimensional evaluation of the teaching quality to obtain the evaluation results;

[0025] Step 4: Calculate the comprehensive score of each teacher and each course according to the evaluation results, diagnose the comprehensive score, and identify problems in teaching;

[0026] Step 5: Generate a comprehensive report on teaching quality and improvement suggestions based on the evaluation results and problems, present the evaluation results in a visual way, and recommend teaching resources to teachers through the Internet based on the improvement suggestions.

[0027] Preferably, the missing values ​​of all collected data are filled, abnormal data is detected and corrected, and data format is converted; principal component analysis is used to reduce the dimension of the data and reduce noise; and data fusion algorithms are used to fuse data from multiple data sources to generate comprehensive data.

[0028] Preferably, the applied reinforcement learning adjusts the teaching content and learning path by continuously interacting with students; predicts the changing trend of teaching quality through machine learning algorithms, and makes forward-looking decisions.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention integrates student learning sequence data and teacher teaching sequence data, combines data mining technology and deep learning algorithms, accurately identifies the key factors affecting teaching quality, objectively evaluates teaching quality in a data-driven manner, avoids the bias of human judgment, enhances the transparency and fairness of teaching quality evaluation, builds an interactive communication channel between teachers and students, obtains teaching quality evaluation feedback, and reduces possible misunderstandings and deviations between teachers and students in the teaching and learning process, thereby more accurately formulating policies and measures and improving the efficiency and effectiveness of education management.

[0031] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a framework diagram of the teaching quality comprehensive evaluation system based on the teaching sequence perspective of the present invention;

[0033] Figure 2 This is a flow chart of the comprehensive teaching quality evaluation method based on the teaching sequence perspective of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Embodiment 1:

[0036] See also Figure 1 As shown, the comprehensive teaching quality evaluation system based on the teaching sequence perspective includes: data management module, learning sequence analysis module, teaching sequence analysis module, teaching quality evaluation module, feedback improvement module, and decision support module;

[0037] The data management module is used to collect data generated in the process of education and teaching, including students' learning sequence data and teachers' teaching sequence data, and to organize and standardize the above collected data;

[0038] The learning sequence analysis module is used to analyze students' learning sequence data through data mining technology, dig out learning rules, and understand students' learning situation;

[0039] The teaching sequence analysis module is used to analyze the teacher's teaching sequence data using a deep learning algorithm to evaluate whether the teacher's teaching method is effective;

[0040] The teaching quality evaluation module is used to comprehensively analyze the learning sequence data and the teacher's teaching sequence data, and give a comprehensive evaluation of the teaching quality through the evaluation model;

[0041] The feedback improvement module is used to obtain feedback information based on the above comprehensive evaluation and build an interactive communication channel between teachers and students;

[0042] The decision support module is used to predict teaching quality based on big data and machine learning and provide decision recommendations.

[0043] The learning sequence data of students include their grades, learning progress, learning behavior, classroom feedback, attendance rate, etc. The teaching sequence data of teachers include course data, teaching data, classroom feedback data, and data on communication records between teachers and students.

[0044] The data management module is also used to collect students' attendance, activity level, and classroom participation data in real time through IoT devices and sensors; perform sentiment analysis and text classification on the collected text data through natural language processing technology; and use data integration technology to integrate data from different platforms (such as grade management systems, student information systems, student learning platforms, etc.) through API interfaces.

[0045] The learning sequence analysis module is also used to discover potential associations between students' learning behavior data through association rule mining and evaluate their learning habits; combine the K-means algorithm to cluster students according to their learning behavior data to identify different student groups; use LSTM to analyze learning sequence data, predict students' future learning status, and identify key factors that affect students' learning progress.

[0046] The teaching sequence analysis module is also used to analyze teaching sequence data using LSTM, capture teaching content, student reactions and progress changes, and evaluate the effectiveness of teaching methods (such as lectures, discussions, experiments, etc.); analyze teaching sequence data through the Transformer model to identify key behavior patterns in teaching; and apply Shapley values ​​in LSTM and Transformer models to evaluate the contribution of each feature to teaching effectiveness.

[0047] The teaching quality assessment module is also used to extract features based on the analysis process using a multivariate indicator joint analysis method to construct an evaluation index system; to use a hierarchical analysis method in combination with the Shapley value to calculate the importance of each indicator and determine its weight; to establish an evaluation model through a fuzzy comprehensive evaluation method, to score the teaching quality, and to obtain the scoring results.

[0048] The fuzzy comprehensive evaluation method can take into account the subjectivity of the data generated in the above-mentioned education and teaching process and the objectivity of the evaluation results. Therefore, the fuzzy comprehensive evaluation method is selected to establish an evaluation model, and the data generated in the above-mentioned education and teaching process is used as the data source to score the teaching quality. The specific steps are as follows:

[0049] (1) Establish a comprehensive evaluation factor set: U = {u1,u2,…,u n}, where u i (i=1,2,…,n) is the evaluation factor, n is the number of indicators at the same level;

[0050] (2) Establish a comprehensive evaluation set of comments: V = {v1, v2, ..., v m}, where v j (j=1,2,…,m) is the evaluation level standard, j is the level number, and m is the number of evaluation levels; each indicator is evaluated independently by a number of experienced teachers and experts, and the proportion of comments that agree with the indicator is taken as the membership degree, V=[V1,V2,V3,V4]=[excellent, good, medium, poor];

[0051] (3) Establish fuzzy evaluation matrix:

[0052]

[0053] In the formula, r ij Factor u i The membership degree of the j-th level comment;

[0054] (4) Determine the weight vector of the evaluation factors, and use the hierarchical analysis method in combination with the Shapley value to calculate the importance of each indicator and determine its weight, and determine the factor u i Weight coefficients are normalized before synthesis;

[0055] W=(a1,a2,…,a n )

[0056] In the formula, a n Factor u i The weight of each indicator above;

[0057] (5) Synthesize the fuzzy comprehensive evaluation result vector: synthesize the weight vector W of the evaluation factor with the R of each evaluated object to obtain the fuzzy comprehensive evaluation vector B of each evaluated object.

[0058]

[0059] Where b j Indicates that the thing being evaluated is positive from the overall perspective. j The degree of membership of hierarchical fuzzy subsets.

[0060] The feedback improvement module is also used to display evaluation results and teaching sequence data analysis to teachers, point out problems in teaching, and generate targeted improvement suggestions; display evaluation results and learning sequence data analysis to students, and provide personalized learning suggestions; and provide school administrators with teaching improvement plans based on the above data analysis according to the evaluation results.

[0061] The decision support module is also used to predict the changing trend of teaching quality based on the evaluation results using machine learning algorithms, generate decision opinions and send them to school administrators; combined with the above personalized learning suggestions, the corresponding learning resources and paths are recommended to students through the Internet.

[0062] Embodiment 2:

[0063] See also Figure 2 As shown in the figure, the comprehensive evaluation method of teaching quality based on the teaching sequence perspective includes:

[0064] Step 1: Collect comprehensive education and teaching data, including student data, teacher data, course data, and classroom feedback data, and clean and integrate the collected data;

[0065] Step 2: Use data mining technology and deep learning algorithms to analyze student data, teacher data, course data, and classroom feedback data to obtain analysis results;

[0066] Step 3: According to the analysis results, the fuzzy comprehensive evaluation method is selected to construct a model to evaluate the teaching quality in multiple dimensions and obtain the evaluation results;

[0067] Step 4: Calculate the comprehensive score of each teacher and each course based on the evaluation results, diagnose the comprehensive score and identify problems in teaching;

[0068] Step 5: Generate a comprehensive report on teaching quality and improvement suggestions based on the evaluation results and problems, present the evaluation results in a visual way, and recommend teaching resources to teachers through the Internet based on the improvement suggestions.

[0069] Student data collection: collect students’ grades, learning progress, study habits, class feedback, attendance rate, etc.

[0070] Course data collection: including course teaching plan, syllabus, course resources (such as courseware, teaching materials), examination and assessment forms, etc.

[0071] Teacher data collection: teachers’ teaching records, teaching methods, classroom interactions, evaluation criteria, etc.

[0072] Classroom feedback collection: Collect students’ evaluation of course content, teaching methods, and teacher performance through student feedback, classroom surveys, etc.

[0073] All collected data are used to fill missing values, detect and correct abnormal data, and convert data formats; principal component analysis is used to reduce data dimensionality and reduce noise; data fusion algorithms are used to fuse data from multiple data sources (teachers, students, grade management systems, student information systems, etc.) to generate comprehensive data.

[0074] Understand the students' knowledge mastery through changes in their grades at different time points; analyze their study time, study frequency, and homework submission to evaluate their study habits; and comprehensively evaluate students' learning outcomes through their test scores, regular grades, and class participation data.

[0075] Check the completion of the teaching plan and the teaching progress of the course content, and evaluate whether the design of the teaching content is reasonable; analyze the teaching methods used by teachers in class and their interactions with students, as well as analyze the teacher's management ability in class and the way they evaluate student learning (homework answers, in-class tests, grading standards, etc.).

[0076] Conduct multi-dimensional scoring of teaching quality. By comparing the teaching quality scores of different classes, teachers, and students, inefficient teaching activities or learning paths can be detected, and adjustments and optimizations can be made. Combined with comprehensive evaluation, qualitative analysis and improvement suggestions can be provided to teachers and schools.

[0077] Applied reinforcement learning adjusts teaching content and learning paths through continuous interaction with students; predicts changing trends in teaching quality through machine learning algorithms and makes forward-looking decisions.

[0078] From the above, it can be seen that the present invention integrates student learning sequence data and teacher teaching sequence data, combines data mining technology and deep learning algorithms, accurately identifies the key factors affecting teaching quality, objectively evaluates teaching quality in a data-driven manner, avoids the bias of human judgment, enhances the transparency and fairness of teaching quality evaluation, builds an interactive communication channel between teachers and students, obtains teaching quality evaluation feedback, and reduces possible misunderstandings and deviations between teachers and students in the teaching and learning process, thereby more accurately formulating policies and measures and improving the efficiency and effectiveness of education management.

[0079] Embodiment 3:

[0080] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above-mentioned teaching quality comprehensive evaluation system embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0081] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0082] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a program, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A way to specify functions in one or more boxes.

[0083] In the drawings of the embodiments disclosed in the present invention, only the structures involved in the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0084] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0085] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive teaching quality evaluation system based on the teaching sequence perspective, characterized by: include: Data management module, learning sequence analysis module, teaching sequence analysis module, teaching quality assessment module, feedback improvement module, decision support module; The data management module is used to collect data generated during the education and teaching process, including students' learning sequence data and teachers' teaching sequence data, and to organize and standardize the collected data; The learning sequence analysis module is used to analyze the learning sequence data of the students through data mining technology, to mine the learning rules and understand the learning situation of the students; The teaching sequence analysis module is used to analyze the teacher's teaching sequence data using a deep learning algorithm to evaluate whether the teacher's teaching method is effective; The teaching quality evaluation module is used to comprehensively analyze the learning sequence data and the teacher's teaching sequence data, and give a comprehensive evaluation of the teaching quality through an evaluation model; The feedback improvement module is used to obtain feedback information based on the above comprehensive evaluation and build an interactive communication channel between teachers and students; The decision support module is used to predict teaching quality based on big data and machine learning and provide decision suggestions.

2. The teaching quality comprehensive evaluation system based on the teaching sequence perspective according to claim 1 is characterized in that: The data management module is also used for: Collect student attendance, activity levels, and class participation data in real time through IoT devices and sensors; Perform sentiment analysis and text classification on the collected text data through natural language processing technology; Use data integration technology to integrate data from different platforms through API interfaces.

3. The teaching quality comprehensive evaluation system based on the teaching sequence perspective according to claim 2 is characterized in that: The learning sequence analysis module is also used for: Discover potential associations between students’ learning behavior data through association rule mining and evaluate their learning habits; Clustering students according to the learning behavior data using the K-means algorithm to identify different student groups; LSTM is used to analyze the learning sequence data, predict students' future learning status, and identify key factors that affect students' learning progress.

4. The teaching quality comprehensive evaluation system based on the teaching sequence perspective according to claim 3 is characterized in that: The teaching sequence analysis module is also used for: LSTM is used to analyze the teaching sequence data, capture teaching content, student reactions and progress changes, and evaluate the effectiveness of teaching methods; Analyze the teaching sequence data through the Transformer model to identify key behavior patterns in teaching; The Shapley value is applied in LSTM and Transformer models to evaluate the contribution of each feature to the teaching effect.

5. The teaching quality comprehensive evaluation system based on the teaching sequence perspective according to claim 4 is characterized in that: The teaching quality assessment module is also used to: Based on the analysis process, a multivariate index joint analysis method is used to extract features and construct an evaluation index system; Combined with the Shapley value, the hierarchical analysis method is used to calculate the importance of each indicator and determine its weight; The evaluation model is established through the fuzzy comprehensive evaluation method, and the teaching quality is scored to obtain the scoring result.

6. The teaching quality comprehensive evaluation system based on the teaching sequence perspective according to claim 5 is characterized in that: The feedback improvement module is also used to: Show the evaluation results and teaching sequence data analysis to teachers, point out problems in teaching, and generate targeted improvement suggestions; Present the assessment results and learning sequence data analysis to students and provide personalized learning suggestions; According to the evaluation results, a teaching improvement plan based on the above data analysis is provided to school administrators.

7. The teaching quality comprehensive evaluation system based on the teaching sequence perspective according to claim 6 is characterized in that: The decision support module is also used to: Based on the evaluation results, a machine learning algorithm is used to predict the trend of changes in teaching quality, and a decision opinion is generated and sent to the school administrator; In combination with the above-mentioned personalized learning suggestions, corresponding learning resources and paths are recommended to students through the Internet.

8. A comprehensive evaluation method of teaching quality based on the teaching sequence perspective is characterized by: include: Step 1: Collect comprehensive education and teaching data, including student data, teacher data, course data, and classroom feedback data, and clean and integrate the collected data; Step 2: Use data mining technology and deep learning algorithm to analyze the student data, teacher data, course data and classroom feedback data respectively to obtain analysis results; Step 3: According to the analysis results, a fuzzy comprehensive evaluation method is selected to construct a model to conduct a multi-dimensional evaluation of the teaching quality to obtain the evaluation results; Step 4: Calculate the comprehensive score of each teacher and each course according to the evaluation results, diagnose the comprehensive score, and identify problems in teaching; Step 5: Generate a comprehensive report on teaching quality and improvement suggestions based on the evaluation results and problems, present the evaluation results in a visual way, and recommend teaching resources to teachers through the Internet based on the improvement suggestions.

9. The comprehensive evaluation method of teaching quality based on the teaching sequence perspective according to claim 8 is characterized in that: The cleaning and integration of the above-collected data includes: Fill missing values, detect and correct abnormal data, and convert data formats for all collected data; Use principal component analysis to reduce the dimension of the data and reduce noise; Data fusion algorithms are used to fuse data from multiple data sources to generate comprehensive data.

10. The comprehensive evaluation method of teaching quality based on the teaching sequence perspective according to claim 9 is characterized in that: The comprehensive report and improvement suggestions on teaching quality are generated based on the evaluation results and problems, including: Applied reinforcement learning adjusts teaching content and learning paths by continuously interacting with students; Use machine learning algorithms to predict changing trends in teaching quality and make forward-looking decisions.

Images