High vocational practice teaching quality evaluation method based on multi-source data fusion
By standardizing and integrating multi-source data from vocational college practical teaching and using a multi-subject integrated scoring system, combined with consistency correction factors and a comprehensive teaching quality index, the problem of insufficient utilization of multi-source data in traditional evaluation is solved, and accurate, scientific and personalized assessment of teaching quality is achieved.
Patent Information
- Application Number
- CN202511491872.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-20
- Publication Date
- 2025-11-18
AI Technical Summary
The traditional evaluation system for the quality of practical teaching in higher vocational colleges cannot make full use of multi-source data, resulting in insufficient fairness and consistency of evaluation results, difficulty in integrating the diversity and complexity of evaluation indicators, difficulty in quantifying students' nonlinear growth, neglect of the impact of the group learning environment on individual performance, and insufficient adaptability and dynamism of the graded evaluation of teaching quality.
By standardizing multi-source data, generating a fusion score using a multi-subject fusion scoring algorithm, and combining it with a consistency correction factor, a comprehensive teaching quality index is calculated. Taking into account cognitive leaps and group collaboration factors, a grading threshold is dynamically generated to achieve accurate assessment of teaching quality.
It achieves fair integration of multi-source data, ensuring the objectivity and accuracy of evaluation results. It can reflect students' non-linear growth and group influence, and the grading results are closely related to the actual quality distribution. It adapts to different teaching environments and improves the scientificity and adaptability of teaching management and student growth.
Smart Images
Figure CN120975992A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of higher vocational practice teaching quality evaluation, and particularly relates to a higher vocational practice teaching quality evaluation method based on multi-source data fusion. BACKGROUND
[0002] As an important way to cultivate high-quality technical and skilled talents for the country, higher vocational education plays a decisive role in the formation of students' professional competence and the improvement of their employment competitiveness through its practice teaching link. However, with the progress of the times, the traditional higher vocational practice teaching quality evaluation system has gradually exposed various inadaptabilities and cannot meet the needs of high-quality development of education in the era of digitization. In the current reform of teaching quality monitoring and evaluation, many colleges and universities are often limited to a single platform or a single data source, failing to fully realize the synergistic value of multi-source data. Practice teaching involves multiple subjects such as teachers, students, teaching managers, and enterprise mentors, and spans multiple links such as teaching preparation, teaching implementation, teaching evaluation, and achievement application. A large amount of structured or unstructured data is generated at each node. If these data can be effectively fused and scientifically processed, it will provide solid data support for the accurate evaluation of teaching quality. However, most colleges and universities have not yet established a systematic multi-source data collection and fusion mechanism, and cannot extract valuable information from massive data to guide teaching improvement.
[0003] Therefore, constructing a higher vocational practice teaching quality evaluation method that integrates multi-party data and realizes dynamic evaluation and precise feedback is not only a practical need to promote the modernization of vocational education, but also a key measure to implement the national education evaluation reform. A higher vocational practice teaching quality evaluation method based on multi-source data fusion can help improve the teaching management efficiency of higher vocational colleges, enhance the learning experience and ability growth of students, and also help realize the continuous improvement of talent cultivation quality and promote the deep integration and collaborative development of education and industry. In the future, with the continuous evolution of digital technology, the application scenarios of this method will be more extensive, and the intelligent degree of evaluation will also be continuously improved, ultimately realizing the scientific, precise, personalized, and intelligent evaluation of education. SUMMARY
[0004] The present application provides a higher vocational practice teaching quality evaluation method based on multi-source data fusion to solve the technical problems of insufficient fairness and consistency of multi-subject evaluation, difficulty in integrating the diversity and complexity of evaluation indicators, difficulty in quantifying the non-linear growth of students, neglect of the influence of group learning environment on individual performance, and insufficient adaptability and dynamics of teaching quality grading evaluation.
[0005] The present application provides a higher vocational practice teaching quality evaluation method based on multi-source data fusion, which specifically includes the following technical solutions: A higher vocational practice teaching quality evaluation method based on multi-source data fusion includes the following steps: S1. standardizing the collected raw score data to obtain standardized score data; and generating a fusion score of each student based on the standardized score data by using a multi-agent fusion scoring algorithm; S2. calculating a comprehensive teaching quality index based on the fusion score of each student by using a comprehensive teaching quality index calculation algorithm; and grading and evaluating the teaching quality based on the comprehensive teaching quality index.
[0006] Preferably, the S1 specifically comprises: calculating the average standardized score of all evaluation agents of each student on each evaluation index based on the standardized score data.
[0007] Preferably, the S1 specifically comprises: calculating the score variance of the evaluation agent on the evaluation index based on the standardized score data and the average standardized score of all evaluation agents on each evaluation index.
[0008] Preferably, the S1 specifically comprises: calculating a consistency correction factor by using an inverse function based on the score variance of the evaluation agent on the evaluation index.
[0009] Preferably, the S1 specifically comprises: In the multi-agent fusion scoring algorithm, the standardized score data of all evaluation indexes and evaluation agents are double-weighted and summed, each standardized score data is multiplied by the corresponding fixed evaluation index weight, agent weight and consistency correction factor, and the fusion score of each student is calculated.
[0010] Preferably, the S2 specifically comprises: calculating a comprehensive teaching quality index based on the fusion score of each student by using a comprehensive teaching quality index calculation algorithm combined with a historical benchmark score, embedding a cognitive jump factor and a group synergy factor.
[0011] Preferably, the S2 specifically comprises: calculating the difference between the current fusion score and the historical benchmark score, normalizing the difference, nonlinearly transforming the normalized difference by using a sine function, and generating a cognitive jump factor.
[0012] Preferably, the S2 specifically comprises: when the total number of students is 1, the group synergy factor is directly set to 1; and when the total number of students is greater than 1, for each student, the average difference between the fusion score and the historical benchmark score of other students except the student is calculated to generate the group synergy factor.
[0013] Preferably, the S2 specifically comprises: Generate a grading threshold based on the mean and standard deviation of the comprehensive teaching quality index; based on the comparison between the comprehensive teaching quality index and the grading threshold, the teaching quality is graded and evaluated.
[0014] The beneficial effects of the technical solutions of the present application are: 1. By using information tools or traditional tools to collect raw score data, and standardizing the score data of different evaluation subjects on different evaluation indicators, the dimensional difference is eliminated, the comparability of the score is ensured, the multi-agent fusion score algorithm is adopted, the subject weight is dynamically adjusted through the consistency correction factor, the score with large subjective bias is reduced, the fusion score of each student is generated, the fair integration of multi-source data is realized, the evaluation result is more objective and accurate, and it is suitable for the complex evaluation scene of multi-agent and multi-index in higher vocational practical teaching.
[0015] 2. By calculating the score variance of the evaluation subject on the evaluation indicator and generating a consistency correction factor, the weight of the subject with large deviation can be dynamically reduced, while the authority of the high consistency score is retained, the fixed evaluation indicator weight and the subject weight are combined, the importance of different evaluation indicators and the professionalism of the evaluation subject are fully reflected, the fairness of the evaluation is enhanced, and the scene of different student scale, evaluation indicator quantity and evaluation subject type is adapted, the flexibility is high, and it is suitable for diversified higher vocational teaching environment.
[0016] 3. Through the comprehensive teaching quality index calculation algorithm, combining the fusion score of the student, the historical benchmark score, the cognitive jump factor and the group synergy factor, the nonlinear growth behavior of the student from "passive task completion" to "active exploration and innovation" is captured, and the influence of group learning environment on individual performance is considered, which breaks through the limitation of traditional evaluation only focusing on individual linear progress, fully reflects the characteristics of higher vocational education focusing on practical ability, team cooperation and innovation breakthrough, and makes the teaching quality evaluation more scientific.
[0017] 4. Based on the comprehensive teaching quality index, the grading threshold is dynamically generated based on the mean and standard deviation, the teaching quality is divided into "excellent", "good", "qualified" and "poor" four grades, the grading method is closely related to the actual comprehensive teaching quality index distribution, avoids the limitation of fixed threshold, enhances the adaptability and pertinence of the evaluation result, and provides data support for higher vocational colleges to optimize teaching management, course design and teacher guidance. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 A flow chart of a higher vocational practical teaching quality evaluation method based on multi-source data fusion according to the present application. DETAILED DESCRIPTION
[0019] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined inventive purpose, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.
[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0021] The specific scheme of the high vocational practical teaching quality evaluation method based on multi-source data fusion provided by the present application will be specifically described below in combination with the drawings.
[0022] Referring to the drawings Figure 1 , it shows a flow chart of a high vocational practical teaching quality evaluation method based on multi-source data fusion provided by an embodiment of the present application, which comprises the following steps: S1, standardizing the collected original score data to obtain standardized score data; based on the standardized score data, using a multi-agent fusion scoring algorithm to generate a fusion score of each student; Using information tools such as teaching management systems, online scoring platforms, etc., or traditional tools such as paper scoring tables, to collect original score data.
[0023] Since high vocational practical teaching involves different evaluation agents such as teachers, students, industry and enterprise experts, etc., and contains different evaluation indexes such as skill mastery, team cooperation, innovation ability, etc., the score data of different agents may use different dimensions or ranges. In order to eliminate the dimensional difference and ensure the comparability of the score data, the original score data is standardized, such as the maximum and minimum standardization method, which is standardized to a unified range , to obtain standardized score data; Using a multi-agent fusion scoring algorithm to integrate the standardized score data of different evaluation agents on different evaluation indexes to generate a fusion score of each student; The core of the multi-agent fusion scoring algorithm is to dynamically adjust the influence weight of the evaluation agent through a consistency correction factor to ensure the fairness and objectivity of the score, and at the same time to simplify the calculation expression of the fusion score to improve the readability and implementation efficiency; Based on the standardized score data, the average standardized score of all evaluation agents of each student on each evaluation index is calculated, which reflects the overall evaluation level of different evaluation agents on a certain student on a certain evaluation index, and is used as a benchmark for subsequent consistency analysis; Based on the standardized scoring data and the average standardized score of all evaluators on each evaluation indicator, the variance of the evaluators' scores on the evaluation indicators is calculated. The larger the variance value, the more the evaluators' scores deviate from the average level, which may indicate subjective bias, such as scores that are too high or too low. Based on the variance of the ratings given by the evaluators on the evaluation indicators, a consistency correction factor is calculated using a multi-subject fusion scoring algorithm. Specifically, the consistency correction factor is generated through a reciprocal function, i.e., 1 divided by 1 plus the variance of the ratings given by the evaluators on the evaluation indicators. The value of the consistency correction factor ranges from 0 to 1. The smaller the consistency correction factor, the greater the rating deviation of the evaluators, and the lower the weight should be. The closer the value is to 1, the higher the rating consistency, and the original weight should be maintained. The calculation formula is as follows: , in, Indicates the first The evaluation subjects in the first Consistency correction factor on each evaluation indicator; Indicates the first The evaluation subjects in the first Variance of scores on each evaluation indicator.
[0024] The integrated score for each student is calculated by combining standardized scoring data, fixed evaluation indicator weights, subject weights, and a consistency correction factor. Specifically, the standardized scoring data for all evaluation indicators and subjects are doubly weighted and summed. Each standardized score is multiplied by its corresponding fixed evaluation indicator weight, subject weight, and consistency correction factor. The fixed evaluation indicator weight reflects the importance of different indicators, the subject weight reflects the authority of different evaluation subjects, and the consistency correction factor adjusts for bias. The calculation formula is as follows: , in, Indicates the first The integration score of each student; This represents the weighted sum of scores for all evaluation indicators; Indicates the number of evaluation indicators; This represents the sum of weighted scores from all evaluators. Indicates the number of evaluation subjects; Indicates the first The weight of each evaluation subject is used to reflect the importance of different evaluation subjects, and is set based on the professionalism or authority of the evaluation subjects. ,satisfy ; Indicates the first The evaluation subjects in the first A fixed evaluation index weight on an evaluation index is used to reflect the importance of different evaluation indexes, which is set based on course objectives or industry requirements, , meet ; represents the standardized score data of the th evaluation subject on the th evaluation index of the th student.
[0025] Through the consistency correction factor, the influence of the evaluation subject with large subjective bias is reduced, the scoring result is ensured to be more objective, the fairness requirement of multi-subject evaluation in higher vocational practical teaching is met, it is suitable for different student scale, evaluation index quantity and evaluation subject type scene, high flexibility, suitable for diversified higher vocational teaching environment.
[0026] S2, based on the fusion score of each student, the comprehensive teaching quality index is calculated through a comprehensive teaching quality index calculation algorithm; based on the comprehensive teaching quality index, the teaching quality is evaluated; Based on the fusion score of each student, the comprehensive teaching quality index is calculated through a comprehensive teaching quality index calculation algorithm combined with historical benchmark score, embedded with cognitive leap factor and group synergy factor, capturing the nonlinear transition behavior of students from “passive task completion” to “active exploration and innovation”, and considering the influence of group learning environment on individual performance.
[0027] For each student, the difference between the current fusion score and the historical benchmark score is calculated to reflect the progress or regression amplitude of the student. In order to avoid the result distortion caused by too large difference, the difference is normalized to control within the range of-1 to 1. The normalized difference is nonlinearly transformed by a periodic function such as sine function to generate cognitive leap factor, simulating the “leap” feature of student growth, i.e. significant progress or regression.
[0028] The group synergy factor reflects the influence of the performance of other students except itself on the individual evaluation, which is processed in two cases: single person scene, i.e. the total number of students is 1, the group synergy factor is directly set to 1, indicating no group effect; multi-person scene, i.e. the total number of students is greater than 1, for each student, the average difference between the fusion score and the historical benchmark score of other students except itself is calculated to reflect the value-added performance of the group as a whole. If the group as a whole performs well, the group synergy factor is greater than 1, which amplifies the individual score. If the group performs poorly, the group synergy factor is less than 1, which exerts negative regulation.
[0029] For each student, the fusion score, cognitive leap factor and group synergy factor of each student are multiplied to obtain the comprehensive contribution score of the student. The comprehensive contribution scores of all students are averaged to obtain the comprehensive teaching quality index, which reflects the overall teaching quality of the course, class or teacher. The calculation formula of the comprehensive teaching quality index is: , Wherein, represents the comprehensive teaching quality index; represents the number of students; represents the comprehensive contribution score of the th student; represents the historical benchmark score of the th student, which is derived from the historical evaluation data obtained from the existing database, such as the fusion score of the th student in the previous semester; represents the score increment of the th student, i.e. the difference between the fusion score and the historical benchmark score of the th student, which is used to quantify the change in individual performance of the student, with a positive value indicating progress and a negative value indicating regression; represents a mathematical constant; represents a sine function, simulating nonlinear growth; represents a cognitive leap incentive factor, which is used to control the amplification degree of the cognitive leap factor and balance the influence of nonlinear effect, and is preset by the existing teaching evaluation system, ; represents a cognitive leap factor; represents a cognitive leap adjustment term; represents the group synergy factor of the th student, and the calculation formula is: , Wherein, represents a group synergy incentive factor, which is used to control the amplification degree of the group effect and is preset by the existing teaching evaluation system, ; represents the fusion score of the th student; represents the historical benchmark score of the th student; represents the score increment of the th student, i.e. the difference between the fusion score and the historical benchmark score of the th student; represents the sum of the score increments of the students other than the th student, i.e. the difference between the fusion score and the historical benchmark score of the students other than the th student, which is used to reflect the overall performance of the group; represents the average difference between the fusion score and the historical benchmark score of the other students other than the th student; The normalized group score increment is used to normalize the range of group score increment, stabilize and adjust the influence of group effect; The normalized group score increment is used to normalize the range of group score increment, stabilize and adjust the influence of group effect; The normalized group score increment is used to normalize the range of group score increment, stabilize and adjust the influence of group effect; The comprehensive teaching quality index calculation algorithm breaks through the limitation of traditional evaluation which only focuses on individual linear progress, captures the nonlinear growth of students and the synergistic effect of groups, and meets the characteristics of higher vocational education which emphasizes practical ability, team cooperation and innovation breakthrough.
[0030] The comprehensive teaching quality index is used for grading evaluation of teaching quality. Specifically, based on the comprehensive teaching quality index, the mean and standard deviation of the comprehensive teaching quality index are calculated, and the grading threshold is dynamically generated based on the mean and standard deviation of the comprehensive teaching quality index, which is used to divide the teaching quality level, and ensures that the grading result is closely related to the actual comprehensive teaching quality index distribution. The grading threshold is set to the mean plus one standard deviation, the mean, and the mean minus one standard deviation, and is limited to not more than the maximum theoretical value 1 and not less than the minimum theoretical value 0. When the comprehensive teaching quality index is greater than or equal to the mean plus one standard deviation and less than or equal to 1, it is an excellent level, reflecting superior performance above average. When the comprehensive teaching quality index is greater than or equal to the mean and less than the mean plus one standard deviation, it is a good level, representing the average teaching quality level. When the comprehensive teaching quality index is greater than or equal to the mean minus one standard deviation and less than the mean, it is a qualified level, reflecting a performance below the average teaching quality level but still acceptable. When the comprehensive teaching quality index is greater than or equal to 0 and less than the mean minus one standard deviation, it is a qualified level.
[0031] According to the comparison of the comprehensive teaching quality index and the grading threshold, the teaching quality is divided into four levels: excellent, good, qualified and poor.
[0032] By dynamically setting the grading threshold through statistical characteristics, namely the mean and standard deviation, the fairness and adaptability of higher vocational practice teaching quality evaluation are enhanced.
[0033] In summary, a higher vocational practice teaching quality evaluation method based on multi-source data fusion is completed.
[0034] The order of the embodiments is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or can be advantageous.
[0035] Each embodiment in the specification is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.
[0036] The above examples are only used to illustrate the technical solutions of the present application, but not to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.
Claims
1. A method for evaluating the quality of practical teaching in higher vocational colleges based on multi-source data fusion, characterized in that, Includes the following steps: S1. Standardize the collected raw scoring data to obtain standardized scoring data; based on the standardized scoring data, use a multi-subject fusion scoring algorithm to generate a fusion score for each student; S2. Based on each student's integration score, calculate the comprehensive teaching quality index using the comprehensive teaching quality index calculation algorithm; based on the comprehensive teaching quality index, conduct a graded evaluation of teaching quality.
2. The method for evaluating the quality of practical teaching in higher vocational colleges based on multi-source data fusion according to claim 1, characterized in that, S1 specifically includes: Based on the standardized scoring data, the average standardized score of each student across all evaluators for each evaluation indicator is calculated.
3. The method for evaluating the quality of vocational college practical teaching based on multi-source data fusion according to claim 2, characterized in that, S1 specifically includes: Based on the standardized scoring data and the average standardized score of all evaluators on each evaluation indicator, the variance of the evaluators' scores on the evaluation indicators is calculated.
4. The method for evaluating the quality of vocational college practical teaching based on multi-source data fusion according to claim 3, characterized in that, S1 specifically includes: Based on the variance of the ratings of the evaluation subjects on the evaluation indicators, the consistency correction factor is calculated by using the reciprocal function.
5. The method for evaluating the quality of vocational college practical teaching based on multi-source data fusion according to claim 4, characterized in that, S1 specifically includes: In the multi-subject fusion scoring algorithm, the standardized scoring data of all evaluation indicators and evaluation subjects are summed with double weights. Each standardized scoring data is multiplied by the corresponding fixed evaluation indicator weight, subject weight and consistency correction factor to calculate the fusion score of each student.
6. The method for evaluating the quality of vocational college practical teaching based on multi-source data fusion according to claim 1, characterized in that, S2 specifically includes: Based on each student's integration score, the comprehensive teaching quality index is calculated by combining historical benchmark scores with a comprehensive teaching quality index calculation algorithm, and embedding cognitive leap factors and group collaboration factors.
7. The method for evaluating the quality of practical teaching in higher vocational colleges based on multi-source data fusion according to claim 6, characterized in that, S2 specifically includes: The difference between the current fusion score and the historical baseline score is calculated, the difference is normalized, and the normalized difference is nonlinearly transformed by a sine function to generate a cognitive leap factor.
8. The method for evaluating the quality of vocational college practical teaching based on multi-source data fusion according to claim 6, characterized in that, S2 specifically includes: If the total number of students is 1, the group synergy factor is set directly to 1; if the total number of students is greater than 1, for each student, the average difference between the integration score of other students (excluding the student) and the historical baseline score is calculated to generate the group synergy factor.
9. The method for evaluating the quality of practical teaching in higher vocational colleges based on multi-source data fusion according to claim 6, characterized in that, S2 specifically includes: The grading thresholds are generated based on the mean and standard deviation of the comprehensive teaching quality index; the teaching quality is then graded and evaluated based on the comparison between the comprehensive teaching quality index and the grading thresholds.