Multipurpose teaching evaluation system and method
By using a multi-purpose teaching evaluation system that combines subject classification and weight allocation of teaching emphasis factors, the system addresses the evaluation differences between different subjects and teaching stages, achieves accurate measurement of teaching effectiveness and scientific evaluation results, and provides a quantitative basis for education quality.
Patent Information
- Application Number
- CN202511598546.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-04
- Publication Date
- 2026-03-03
AI Technical Summary
Existing teaching evaluation methods fail to fully consider the characteristics of different subjects and teaching stages, resulting in insufficient objectivity and accuracy of evaluation results, making it difficult to truly reflect teaching effectiveness and results.
A multi-purpose teaching evaluation system is adopted, which automatically assigns weight coefficients to subject classification and teaching emphasis factors, and combines text analysis and implicit sentiment recognition of teacher-student interaction data to dynamically calculate the final evaluation score, adapting to the needs of different subjects and teaching stages.
It achieves high subject adaptability and precise matching of evaluation results, provides highly objective and scientific evaluation standards, and provides quantitative basis for education quality monitoring and teacher improvement.
Smart Images
Figure CN121599276A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of teaching evaluation technology, and in particular to a multi-purpose teaching evaluation system and method. Background Technology
[0002] In the field of education, teaching evaluation is an important means of improving teaching quality. However, existing teaching evaluation methods still have many technical shortcomings, resulting in insufficient objectivity, accuracy, and applicability of evaluation results. For example: Existing teaching evaluation systems typically employ uniform evaluation indicators, failing to fully consider the teaching characteristics of different disciplines (such as science and engineering, humanities, and arts). For example, mathematics emphasizes logical reasoning ability, while language arts emphasizes language expression and critical thinking. However, traditional evaluation methods do not dynamically adjust evaluation weights according to the core competency requirements of different disciplines, resulting in evaluation results that fail to accurately reflect teaching effectiveness.
[0003] Current teaching evaluations primarily rely on expert observation and scoring or student questionnaires. These evaluations are easily influenced by subjective factors and struggle to comprehensively collect and analyze implicit feedback during student-teacher interactions (such as emotional inclinations in classroom discussions). Furthermore, traditional methods are inefficient at processing multimodal teaching data (such as classroom recordings and online discussion texts), resulting in insufficient evaluation evidence.
[0004] The teaching objectives differ significantly across different educational stages (such as primary school, secondary school, and university). For instance, primary school focuses on mastering basic knowledge, while university emphasizes cultivating innovative abilities. However, existing evaluation methods typically do not establish differentiated evaluation criteria for different educational stages, making it difficult to accurately measure the teaching effectiveness at each stage.
[0005] Therefore, it is necessary to provide a multi-purpose teaching evaluation system and method to solve the above-mentioned technical problems. Summary of the Invention
[0006] To address the aforementioned technical problems, this invention provides a multi-purpose teaching evaluation system and method to solve the problems in the prior art where the results of teaching evaluations are difficult to truly reflect teaching effectiveness, the evaluation basis is insufficient, and the evaluation results are difficult to accurately measure the teaching effectiveness at each stage.
[0007] This invention provides a multi-purpose teaching evaluation method, which includes the following steps: S1. Establish a subject classification mechanism, including: major subject categories and different sub-subject categories belonging to the major subject categories; S2. Construct an evaluation adjustment mechanism, including: assigning corresponding teaching emphasis factors to each sub-subject category, and setting corresponding evaluation weight coefficients for the teaching emphasis factors. S3. Identify the teaching subject to be evaluated and its teaching stage, and automatically assign coefficients to the teaching emphasis factors of the teaching subject to be evaluated through the evaluation adjustment mechanism to obtain the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated. S4. Obtain information on teacher-student interactions and analyze the teaching emphasis factors of the teacher's explanation and the implicit emotions of students' feedback on the teaching emphasis factors. S5. Based on the implicit emotional feedback from students on the teaching focus factors and the evaluation weight coefficients of each teaching focus factor of the subject to be evaluated, evaluate the teaching focus factors of the teacher's explanation content, and calculate the comprehensive evaluation score of the subject to be evaluated. S6. Dynamically calculate the adaptation coefficient β based on the pre-built teaching stage adaptation rule base, and calculate the final evaluation score of the subject to be evaluated in combination with the preset final evaluation score calculation formula. The final evaluation score calculation formula includes: final evaluation score = comprehensive evaluation score × β.
[0008] Preferably, step S1 includes the following steps: S101. Subjects are categorized according to the education system, and a unique identifier is assigned to each subject category. Subject categories include science and engineering, humanities, and arts. S102. Under each major subject category, specific sub-subject categories are divided. The sub-subject category identifier code inherits the major subject category code, and the hierarchical relationship between the major subject category and the sub-subject category is stored.
[0009] Preferably, step S2 includes the following specific steps: S201. By using online scoring by teaching group experts, teaching emphasis factors are pre-defined for different sub-subject categories, and weight coefficients are assigned to each teaching emphasis factor. The total weight coefficients of all sub-subject categories under the same major category are 1. S202. Based on the weight coefficients assigned to each teaching emphasis factor, store the mapping relationship between each teaching emphasis factor and the weight coefficients to construct an evaluation adjustment mechanism.
[0010] Preferably, step S3 includes the following specific steps: S301. Identify the subject to be evaluated by determining the major subject category and sub-subject category to which it belongs based on the subject classification mechanism, and at the same time identify the teaching stage to which the subject to be evaluated belongs, where the teaching stage includes primary school, secondary school or university. S302. Based on the constructed evaluation adjustment mechanism, query the teaching emphasis factors corresponding to the sub-subject categories of the teaching subject to be evaluated and the evaluation weight coefficients of each teaching emphasis factor, and obtain the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated.
[0011] Preferably, step S4 includes the following specific steps: S401. During the teaching process, collect information on interactions between teachers and students, including classroom recordings, chat logs on online teaching platforms, or posts in discussion forums; S402. Identify teacher explanation information from teacher-student interaction information, perform text analysis and content classification processing on teacher explanation information, and determine the teaching emphasis factors involved in the teacher explanation content by combining the sub-subject categories of the subject to be evaluated and its teaching emphasis factors. S403. Identify student feedback information from teacher-student interactions and analyze the student feedback information using natural language processing technology to determine the implicit emotions of students towards each teaching focus factor. Implicit emotions include positive, neutral, and negative.
[0012] Preferably, step S5 includes the following specific steps: S501. Based on the implicit emotions of students' feedback on the teaching focus factors, formulate corresponding evaluation criteria, including setting corresponding scores of high, medium and low for positive, neutral and negative feedback respectively. S502. Evaluate each teaching focus factor of the teacher's explanation content according to the established evaluation criteria, and record it as the original evaluation score of the teaching focus factor. S503. Multiply the evaluation weight coefficient of each teaching emphasis factor of the subject to be evaluated by the original evaluation score of each teaching emphasis factor to obtain the secondary evaluation score of each teaching emphasis factor. S504. Add up the secondary evaluation scores of each teaching focus factor to obtain the comprehensive evaluation score of the subject to be evaluated.
[0013] Preferably, step S6 includes the following specific steps: S601. For each teaching stage, a set of quantitative adaptation standard rules are pre-defined to build a teaching stage adaptation rule library; S602. From the interaction information between teachers and students of the subject to be evaluated, detect the specific number of adaptation standard rules in the adaptation rule base of the teaching stage, and use it as the compliance score α. S603. Calculate the final evaluation score of the subject to be evaluated according to the preset final evaluation score calculation formula. The final evaluation score calculation formula is: Final evaluation score = Comprehensive evaluation score × Fit coefficient β. The fit coefficient β is set by a preset mapping relationship. The mapping relationship specifically includes: if α=0, then β is set to 0.8; if α=1, then β is set to 0.95; if α is greater than 3, then β is set to 1.1.
[0014] A multi-purpose teaching evaluation system, the evaluation system comprising: The classification definition module is used to set up the subject classification mechanism, including: major subject categories and different sub-subject categories belonging to the major subject categories; The weight definition module is used to construct the evaluation adjustment mechanism, including: assigning corresponding teaching emphasis factors to the subjects of each sub-subject category, and setting corresponding evaluation weight coefficients for the teaching emphasis factors. The automatic adjustment module is used to identify the teaching subject to be evaluated and its teaching stage, and automatically assign coefficients to the teaching emphasis factors of the teaching subject to be evaluated through the evaluation adjustment mechanism, thereby obtaining the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated. The sentiment analysis module is used to obtain information on teacher and student interactions, and to analyze the teaching emphasis factors of the teacher's explanation content and the implicit sentiments of students' feedback on the teaching emphasis factors. The first-level calculation module is used to evaluate the teaching emphasis factors of the teacher's lecture content by combining the implicit emotional feedback of students on the teaching emphasis factors and the evaluation weight coefficients of each teaching emphasis factor of the subject to be evaluated, and to calculate the comprehensive evaluation score of the subject to be evaluated. The secondary calculation module is used to dynamically calculate the adaptation coefficient β based on the pre-built teaching stage adaptation rule base, and calculate the final evaluation score of the teaching subject to be evaluated in combination with the preset final evaluation score calculation formula. The final evaluation score calculation formula includes: final evaluation score = comprehensive evaluation score × β.
[0015] Compared with related technologies, the multi-purpose teaching evaluation system and method provided by the present invention have the following beneficial effects: This invention achieves high subject adaptability, including accurate matching of different subjects and the needs and evaluation of primary, secondary, or university stages, through hierarchical subject classification and automatic weight coefficient allocation, combined with text analysis of teacher-student interaction data, semantic recognition of implicit emotions, and big data analysis. It is highly objective and the results are scientific. Through automated weight matching and multi-level reasonable calculation, it obtains comprehensive and final evaluation scores, which fully reflect the overall situation of subject teaching and the characteristics of different teaching stages, providing standardized and scalable quantitative basis for education quality monitoring and teacher improvement. Attached Figure Description
[0016] Figure 1 This is a flowchart illustrating a multi-purpose teaching evaluation method according to the present invention; Figure 2 This is a system block diagram of a multi-purpose teaching evaluation system according to the present invention. Detailed Implementation
[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0018] Example 1 A multi-purpose teaching evaluation method includes the following steps: S1. Establish a subject classification mechanism, including: major subject categories and different sub-subject categories belonging to the major subject categories; S2. Construct an evaluation adjustment mechanism, including: assigning corresponding teaching emphasis factors to each sub-subject category, and setting corresponding evaluation weight coefficients for the teaching emphasis factors. S3. Identify the teaching subject to be evaluated and its teaching stage, and automatically assign coefficients to the teaching emphasis factors of the teaching subject to be evaluated through the evaluation adjustment mechanism to obtain the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated. S4. Obtain information on teacher-student interactions and analyze the teaching emphasis factors of the teacher's explanation and the implicit emotions of students' feedback on the teaching emphasis factors. S5. Based on the implicit emotional feedback from students on the teaching focus factors and the evaluation weight coefficients of each teaching focus factor of the subject to be evaluated, evaluate the teaching focus factors of the teacher's explanation content, and calculate the comprehensive evaluation score of the subject to be evaluated. S6. Dynamically calculate the adaptation coefficient β based on the pre-built teaching stage adaptation rule base, and calculate the final evaluation score of the subject to be evaluated in combination with the preset final evaluation score calculation formula. The final evaluation score calculation formula includes: final evaluation score = comprehensive evaluation score × β.
[0019] In the specific implementation process, step S1 includes the following steps: S101. Subject categories are divided according to the education system, and a unique identifier is assigned to each subject category. Subject categories include science and engineering, humanities, and arts.
[0020] Specifically, after dividing the disciplines into major categories, a unique identifier is assigned to each major category using either numerical or alphabetical coding to ensure that each major category is unique. This unified coding facilitates the rapid identification and management of major discipline categories and provides a foundation for the subsequent hierarchical division of sub-subject categories.
[0021] S102. Under each major subject category, specific sub-subject categories are divided. The sub-subject category identifier code inherits the major subject category code, and the hierarchical relationship between the major subject category and the sub-subject category is stored.
[0022] Specifically, within the framework of major subject categories, sub-subjects are further subdivided according to specific teaching content, course objectives, or knowledge systems. In this embodiment, the sub-subject categories of science and engineering include mathematics, physics, and computer science; humanities include history and Chinese language; and arts include music theory and fine arts. The identification code of the sub-subject category consists of the major subject category code and the sub-subject category number, and the hierarchical relationship between the major subject category and the sub-subject category is stored. It should be noted that this method can be stored using a tree structure or a relational database table.
[0023] In the specific implementation process, step S2 includes the following steps: S201. By using online scoring by teaching group experts, teaching emphasis factors are pre-defined for different sub-subject categories, and weight coefficients are assigned to each teaching emphasis factor. The total weight coefficients of all sub-subject categories under the same major category are 1.
[0024] Specifically, the teaching emphasis factor is a key dimension reflecting the core teaching objectives of a sub-subject category. Teaching emphasis factors are pre-defined for different sub-subject categories through online scoring by teaching experts. In this embodiment, the teaching experts assign importance scores to each emphasis factor online. After scoring, the allocation is based on the results and the weight coefficient of the teaching emphasis factor is calculated using the formula: weight coefficient + average score of a certain emphasis factor / sum of average scores of all emphasis factors. It should be noted that the sum of the weight coefficients of all sub-subject categories within the same major category is 1 as a constraint.
[0025] For example, in this embodiment, for the mathematics sub-subject, the emphasis factors and average scores determined online by the teaching group experts include: logical deduction emphasis factor of 8.5 points, formula application emphasis factor of 7 points, and problem modeling emphasis factor of 6.5 points; then the total score = 8.5 + 7.0 + 6.5 = 22. According to the formula for calculating the weight coefficient of the teaching emphasis factors, the weight coefficient of the logical deduction emphasis factor can be calculated as 8.5 / 22 ≈ 0.386; the weight coefficient of the formula application emphasis factor is 7.0 / 22 ≈ 0.318; and the weight coefficient of the problem modeling emphasis factor is 6.5 / 22 ≈ 0.296.
[0026] S202. Based on the weight coefficients assigned to each teaching emphasis factor, store the mapping relationship between each teaching emphasis factor and the weight coefficients to construct an evaluation adjustment mechanism.
[0027] In the specific implementation process, step S3 includes the following steps: S301. Identify the subject to be evaluated by determining its major subject category and sub-subject category based on the subject classification mechanism, and at the same time identify the teaching stage to which the subject to be evaluated belongs, where the teaching stage includes primary school, secondary school or university.
[0028] Specifically, based on the hierarchical relationship between major and sub-subject categories, the subject category and sub-subject category are determined by querying the unique identifier of the subject to be evaluated. Then, based on the specific information of the subject to be evaluated obtained from the query, and considering the teaching stages in the education system such as primary, secondary, and higher education, the teaching stage of the subject to be evaluated is determined. The specific information of the subject to be evaluated includes course number, grade level, etc.
[0029] S302. Based on the constructed evaluation adjustment mechanism, query the teaching emphasis factors corresponding to the sub-subject categories of the teaching subject to be evaluated and the evaluation weight coefficients of each teaching emphasis factor, and obtain the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated.
[0030] Specifically, the evaluation adjustment mechanism constructed in step S202 is used to query the teaching emphasis factors corresponding to the sub-subject category of the subject to be evaluated, as well as the evaluation weight coefficients of each teaching emphasis factor. For example, if the subject to be evaluated is found to be the high school mathematics sub-subject category, the weight coefficients of its teaching emphasis factors are as follows: the weight coefficient of the logical deduction emphasis factor is 0.386; the weight coefficient of the formula application emphasis factor is 0.318; and the weight coefficient of the problem modeling emphasis factor is 0.296.
[0031] In the specific implementation process, step S4 includes the following steps: S401. During the teaching process, collect information on interactions between teachers and students, including classroom recordings, chat logs on online teaching platforms, or posts in discussion forums.
[0032] Specifically, audio or video recordings of teachers' lectures and students' questions are recorded using smart devices such as recording and video recording equipment; or data such as chat logs, discussion forum posts, and homework comments are collected by accessing online teaching platforms; then, speech recognition technology (such as ASR) is used to convert the audio into text.
[0033] For example, a recording of a high school physics class shows the teacher explaining "Newton's First Law" and asking questions, which the students then answer. The text data is as follows: Teacher asks: Newton's First Law is also known as the law of inertia, which refers to... Can anyone give an example? Student A answers: When a bus suddenly brakes, people will lean forward. Student B answers: But why is it sometimes not obvious?
[0034] S402. Identify teacher explanation information from teacher-student interaction information, perform text analysis and content classification processing on teacher explanation information, and determine the teaching emphasis factors involved in the teacher explanation content by combining the sub-subject categories of the subject to be evaluated and their teaching emphasis factors.
[0035] Specifically, the teacher's explanation information is identified from the interaction between teachers and students. The text is then broken down into sentences, and each sentence is matched against a pre-built keyword database to extract keywords for the subject being evaluated. If a sentence contains keywords related to a certain teaching focus factor (such as "formula," "derivation," or "experimental steps"), then the sentence is marked as belonging to that focus factor. For example, in physics, terms such as "inertia" and "force analysis" are extracted and matched against the "phenomenon explanation ability" focus factor of the physics lesson. At the same time, each teacher's explanation content is tagged, and the coverage frequency of each focus factor is counted.
[0036] S403. Identify student feedback information from teacher-student interactions and analyze the student feedback information using natural language processing technology to determine the implicit emotions of students towards each teaching focus factor. Implicit emotions include positive, neutral, and negative.
[0037] Specifically, from teacher-student interactions, student statements are separated using speaker annotations or user IDs, and invalid data is filtered out, eliminating short responses (such as "um" or "understand"). Then, a pre-trained sentiment analysis model, such as the VADER model, from natural language processing is used to analyze student feedback, determining the implicit sentiment of each student towards each teaching focus factor, thus obtaining the student's sentiment label for each factor, including positive, neutral, or negative. The training process for the pre-trained sentiment analysis model includes: using publicly available unlabeled text, splitting the text into sentences, randomly masking some words, and having the VADER model predict the masked words as the result of implicit sentiment analysis. Through iterative optimization, the sentiment analysis model is trained and completed.
[0038] In the specific implementation process, step S5 includes the following steps: S501. Based on the implicit emotions of students' feedback on the teaching focus factors, formulate corresponding evaluation criteria, including setting corresponding scores of high, medium and low for positive, neutral and negative feedback.
[0039] Specifically, based on the implicit emotions reported by students—positive, neutral, and negative—a corresponding score is assigned to each emotion category as the benchmark for calculating the original evaluation score. In this embodiment, positive is high (3 points), neutral is medium (2 points), and negative is low (1 point).
[0040] S502. Evaluate each teaching focus factor of the teacher's explanation content according to the established evaluation criteria, and record it as the original evaluation score of the teaching focus factor.
[0041] Specifically, the average score of all student feedback under each teaching focus factor is calculated and used as the raw evaluation score for that factor.
[0042] S503. Multiply the evaluation weight coefficient of each teaching emphasis factor of the subject to be evaluated by the original evaluation score of each teaching emphasis factor to obtain the secondary evaluation score of each teaching emphasis factor.
[0043] Specifically, the original evaluation score of each teaching focus factor is multiplied by its corresponding evaluation weight coefficient to obtain the weighted secondary evaluation score. The specific calculation formula is: Secondary evaluation score = Original evaluation score × Evaluation weight coefficient.
[0044] S504. Add up the secondary evaluation scores of each teaching focus factor to obtain the comprehensive evaluation score of the subject to be evaluated.
[0045] In the specific implementation process, step S6 includes the following steps: S601. For each teaching stage, a set of quantitative adaptation standard rules are pre-defined to build a teaching stage adaptation rule library.
[0046] Specifically, in this embodiment, for the university teaching stage, the adaptation standard rules are set to 3, including: Adaptation standard rule 1: In the teacher-student interaction throughout the class, the number of "open-ended questions" or "questioning questions" raised by students is ≥3; Adaptation standard rule 2: In the discussion session, the number of times students' speeches contain keywords such as "refute", "disagreement", and "counterexample" is ≥2; Adaptation standard rule 3: In the teacher's explanation, the frequency of higher-order verbs identified by Bloom's Taxonomy such as "analyze", "evaluate", and "create" is ≥5.
[0047] S602. From the interaction information between teachers and students in the subject to be evaluated, detect the specific number of adaptation standard rules in the adaptation rule base of the teaching stage, and use it as the compliance score α.
[0048] Specifically, after collecting teacher and student interaction information in step S401, existing NLP technologies such as keyword matching and sentence pattern recognition are used to scan and count the text from the teacher and student interaction information of the subject to be evaluated, and the specific number of the text that meets the adaptation standard rules in the teaching stage adaptation rule base is detected. The value of the number is then counted as the specific value of the compliance score α.
[0049] S603. Calculate the final evaluation score of the subject to be evaluated according to the preset final evaluation score calculation formula. The final evaluation score calculation formula is: Final evaluation score = Comprehensive evaluation score × Fit coefficient β. The fit coefficient β is set by a preset mapping relationship. The mapping relationship specifically includes: if α=0, then β is set to 0.8; if α=1, then β is set to 0.95; if α is greater than 3, then β is set to 1.1.
[0050] Specifically, the fit coefficient β is set by a preset mapping relationship of the conformity score α. The mapping relationship includes: if α=0, then β is set to 0.8; if α=1, then β is set to 0.95; if α is greater than 3, then β is set to 1.1. The larger the conformity score α, the higher the matching degree between the teaching method and the characteristics of the teaching stage.
[0051] Example 2 like Figure 2 As shown, a multi-purpose teaching evaluation system applied to a multi-purpose teaching evaluation method specifically includes: The classification definition module is used to set up the subject classification mechanism, including: major subject categories and different sub-subject categories belonging to the major subject categories; The weight definition module is used to construct the evaluation adjustment mechanism, including: assigning corresponding teaching emphasis factors to the subjects of each sub-subject category, and setting corresponding evaluation weight coefficients for the teaching emphasis factors. The automatic adjustment module is used to identify the teaching subject to be evaluated and its teaching stage, and automatically assign coefficients to the teaching emphasis factors of the teaching subject to be evaluated through the evaluation adjustment mechanism, thereby obtaining the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated. The sentiment analysis module is used to obtain information on teacher and student interactions, and to analyze the teaching emphasis factors of the teacher's explanation content and the implicit sentiments of students' feedback on the teaching emphasis factors. The first-level calculation module is used to evaluate the teaching emphasis factors of the teacher's lecture content by combining the implicit emotional feedback of students on the teaching emphasis factors and the evaluation weight coefficients of each teaching emphasis factor of the subject to be evaluated, and to calculate the comprehensive evaluation score of the subject to be evaluated. The secondary calculation module is used to dynamically calculate the adaptation coefficient β based on the pre-built teaching stage adaptation rule base, and calculate the final evaluation score of the teaching subject to be evaluated in combination with the preset final evaluation score calculation formula. The final evaluation score calculation formula includes: final evaluation score = comprehensive evaluation score × β.
[0052] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.
[0053] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.
[0054] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
Claims
1. A multi-purpose teaching evaluation method, characterized in that, The evaluation method includes the following steps: S1. Establish a subject classification mechanism, including: major subject categories and different sub-subject categories belonging to the major subject categories; S2. Construct an evaluation adjustment mechanism, including: assigning corresponding teaching emphasis factors to each sub-subject category, and setting corresponding evaluation weight coefficients for the teaching emphasis factors. S3. Identify the teaching subject to be evaluated and its teaching stage, and automatically assign coefficients to the teaching emphasis factors of the teaching subject to be evaluated through the evaluation adjustment mechanism to obtain the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated. S4. Obtain information on teacher-student interactions and analyze the teaching emphasis factors of the teacher's explanations and the implicit emotions of students' feedback on the teaching emphasis factors. S5. Based on the implicit emotional feedback from students on the teaching focus factors and the evaluation weight coefficients of each teaching focus factor of the subject to be evaluated, evaluate the teaching focus factors of the teacher's explanation content, and calculate the comprehensive evaluation score of the subject to be evaluated. S6. Dynamically calculate the adaptation coefficient β based on the pre-built teaching stage adaptation rule base, and calculate the final evaluation score of the subject to be evaluated in combination with the preset final evaluation score calculation formula. The final evaluation score calculation formula includes: final evaluation score = comprehensive evaluation score × β.
2. The multi-purpose teaching evaluation method according to claim 1, characterized in that, The specific steps of step S1 include: S101. Subjects are categorized according to the education system, and a unique identifier is assigned to each subject category. Subject categories include science and engineering, humanities, and arts. S102. Under each major subject category, specific sub-subject categories are divided. The sub-subject category identifier code inherits the major subject category code, and the hierarchical relationship between the major subject category and the sub-subject category is stored.
3. The multi-purpose teaching evaluation method according to claim 1, characterized in that, The specific steps of step S2 include: S201. By using online scoring by teaching group experts, teaching emphasis factors are pre-defined for different sub-subject categories, and weight coefficients are assigned to each teaching emphasis factor. The total weight coefficients of all sub-subject categories under the same major category are 1. S202. Based on the weight coefficients assigned to each teaching emphasis factor, store the mapping relationship between each teaching emphasis factor and the weight coefficients to construct an evaluation adjustment mechanism.
4. The multi-purpose teaching evaluation method according to claim 1, characterized in that, The specific steps of step S3 include: S301. Identify the subject to be evaluated by determining the major subject category and sub-subject category to which it belongs based on the subject classification mechanism, and at the same time identify the teaching stage to which the subject to be evaluated belongs, where the teaching stage includes primary school, secondary school or university. S302. Based on the constructed evaluation adjustment mechanism, query the teaching emphasis factors corresponding to the sub-subject categories of the teaching subject to be evaluated and the evaluation weight coefficients of each teaching emphasis factor, and obtain the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated.
5. The multi-purpose teaching evaluation method according to claim 1, characterized in that, The specific steps of step S4 include: S401. During the teaching process, collect information on interactions between teachers and students, including classroom recordings, chat logs on online teaching platforms, or posts in discussion forums; S402. Identify teacher explanation information from teacher-student interaction information, perform text analysis and content classification processing on teacher explanation information, and determine the teaching emphasis factors involved in the teacher explanation content by combining the sub-subject categories of the subject to be evaluated and its teaching emphasis factors. S403. Identify student feedback information from teacher-student interactions and analyze the student feedback information using natural language processing technology to determine the implicit emotions of students towards each teaching focus factor. Implicit emotions include positive, neutral, and negative.
6. The multi-purpose teaching evaluation method according to claim 1, characterized in that, The specific steps of step S5 include: S501. Based on the implicit emotions of students' feedback on the teaching focus factors, formulate corresponding evaluation criteria, including setting corresponding scores of high, medium and low for positive, neutral and negative feedback respectively. S502. Evaluate each teaching focus factor of the teacher's explanation content according to the established evaluation criteria, and record it as the original evaluation score of the teaching focus factor. S503. Multiply the evaluation weight coefficient of each teaching emphasis factor of the subject to be evaluated by the original evaluation score of each teaching emphasis factor to obtain the secondary evaluation score of each teaching emphasis factor. S504. Add up the secondary evaluation scores of each teaching focus factor to obtain the comprehensive evaluation score of the subject to be evaluated.
7. The multi-purpose teaching evaluation method according to claim 1, characterized in that, The specific steps of step S6 include: S601. For each teaching stage, a set of quantitative adaptation standard rules are pre-defined to build a teaching stage adaptation rule library; S602. From the interaction information between teachers and students of the subject to be evaluated, detect the specific number of adaptation standard rules in the adaptation rule base of the teaching stage, and use it as the compliance score α. S603. Calculate the final evaluation score of the subject to be evaluated according to the preset final evaluation score calculation formula. The final evaluation score calculation formula is: Final evaluation score = Comprehensive evaluation score × Fit coefficient β. The fit coefficient β is set by a preset mapping relationship. The mapping relationship specifically includes: if α=0, then β is set to 0.8; if α=1, then β is set to 0.95; if α is greater than 3, then β is set to 1.
1.
8. A multi-purpose teaching evaluation system, employing a multi-purpose teaching evaluation method as described in any one of claims 1-7, characterized in that, The evaluation system includes: The classification definition module is used to set up the subject classification mechanism, including: major subject categories and different sub-subject categories belonging to the major subject categories; The weight definition module is used to construct the evaluation adjustment mechanism, including: assigning corresponding teaching emphasis factors to the subjects of each sub-subject category, and setting corresponding evaluation weight coefficients for the teaching emphasis factors. The automatic adjustment module is used to identify the teaching subject to be evaluated and its teaching stage, and automatically assign coefficients to the teaching emphasis factors of the teaching subject to be evaluated through the evaluation adjustment mechanism, thereby obtaining the evaluation weight coefficients of each teaching emphasis factor of the teaching subject to be evaluated. The sentiment analysis module is used to obtain information on teacher and student interactions, and to analyze the teaching emphasis factors of the teacher's lecture content and the implicit sentiments of students' feedback on the teaching emphasis factors. The first-level calculation module is used to evaluate the teaching emphasis factors of the teacher's lecture content by combining the implicit emotional feedback of students on the teaching emphasis factors and the evaluation weight coefficients of each teaching emphasis factor of the subject to be evaluated, and to calculate the comprehensive evaluation score of the subject to be evaluated. The secondary calculation module is used to dynamically calculate the adaptation coefficient β based on the pre-built teaching stage adaptation rule base, and calculate the final evaluation score of the teaching subject to be evaluated in combination with the preset final evaluation score calculation formula. The final evaluation score calculation formula includes: final evaluation score = comprehensive evaluation score × β.