Education effect evaluation method and system based on data analysis

Abstract

The invention discloses an education effect evaluation method and system based on data analysis, and is applied to the technical field of teaching evaluation. The method comprises the following steps: carrying out data analysis on all evaluation indexes, dividing the evaluation indexes into different categories, and removing the evaluation indexes which have small influence on the mastering degree of students; constructing an education effect evaluation system, and calculating an education effect score; obtaining an education effect score of the student and a corresponding student mastering degree score; constructing and training a mastery degree prediction model, taking the education effect score of the student as input data, and taking the corresponding student mastery degree score as an output result; and after the student finishes learning in an evaluation time period, comparing a mastery degree score prediction result with an actual test result, adjusting a weight value of an evaluation index, and retraining the mastery degree prediction model. The comprehensiveness and reliability of the evaluation system are ensured by analyzing the evaluation indexes, and the teaching effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching evaluation, and more particularly to an education effect evaluation method and system based on data analysis. Background Art

[0002] Evaluating teaching effectiveness can help teachers understand students' learning situation and assist teachers in adjusting subsequent teaching content and teaching methods, thereby improving teaching effectiveness. Existing teaching effectiveness evaluation schemes are still mainly based on manual evaluation. Teachers only rely on their own observations and single indicators such as test scores to evaluate teaching effectiveness, and there is a large degree of subjectivity. In addition to the above-mentioned evaluation methods, there are also some methods that use multiple indicators for quantitative scoring, such as student learning situation, teacher evaluation, etc. Although this method guarantees the objectivity of the evaluation results to a certain extent, there are many evaluation indicators, and it is difficult to determine the degree of correlation between the evaluation indicators and the results. It ignores the focus of different evaluation indicators and cannot convert the evaluation indicators into indicators for evaluating students' mastery. It can only evaluate students' daily learning situation, and the final mastery level needs to be retested. Therefore, how to provide an educational effectiveness evaluation method and system based on data analysis is a problem that technicians in this field urgently need to solve. Summary of the Invention

[0003] In view of this, the present invention provides an education effect evaluation method and system based on data analysis, which realizes a comprehensive and objective evaluation of education effect by constructing an education effect evaluation system and a mastery degree prediction model.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] An educational effect evaluation method based on data analysis includes the following steps:

[0006] S1. Evaluation indicator analysis: Analyze all evaluation indicators, classify them into different categories, and eliminate those that have little impact on students' mastery.

[0007] S2. Evaluation system construction: Build an education effectiveness evaluation system to calculate education effectiveness scores based on students' learning performance;

[0008] S3. Database construction: Obtain students' educational effect scores and corresponding student mastery scores as a database for subsequent prediction model training;

[0009] S4. Mastery prediction model construction: Build and train a mastery prediction model, taking students' educational effectiveness scores as input data and the corresponding student mastery scores as output results;

[0010] S5. Update and optimization of the mastery prediction model: After students finish studying for an assessment period, the weight values ​​of the evaluation indicators are adjusted based on the mastery prediction accuracy and the mastery prediction model is retrained.

[0011] Optionally, S1 is:

[0012] S11. Conduct correlation analysis on all evaluation indicators and classify them according to different evaluation dimensions;

[0013] S12. Conduct weight analysis on the evaluation indicators included in each evaluation dimension to determine the degree of influence of the evaluation indicators on students' mastery scores;

[0014] S13. Screen the evaluation indicators based on their impact on students' mastery scores, and eliminate evaluation indicators whose impact is less than a preset threshold.

[0015] Optionally, S12 specifically includes: for each evaluation dimension, using a subjective weighting method to assign subjective weights to all evaluation indicators, using an entropy weighting method to assign objective weights to all evaluation indicators, and combining the subjective weights and the objective weights to obtain the weight values ​​of the evaluation indicators:

[0016] w ij =αw ij1 +(1-α)w ij2

[0017] Where w ij is the weight of the jth evaluation indicator in the i-th evaluation dimension, w ij1 w ij The subjective weight, w ij2 w ij The objective weight of , α is the adjustment parameter.

[0018] Optionally, S2 is as follows: divide the evaluation indicators into five evaluation dimensions: learning ability, learning attitude, psychological state, practical ability, and comprehensive quality, and calculate the educational effect indicators for each evaluation dimension separately:

[0019]

[0020] Where, E i represents the educational effect score of the i-th evaluation dimension, w ij represents the weight of the jth evaluation indicator in the i-th evaluation dimension, a ij represents the jth evaluation indicator in the i-th evaluation dimension, N i Indicates the number of evaluation indicators in the i-th evaluation dimension, i∈[1,5], j∈[1,N i ].

[0021] Optionally, S3 specifically includes: after an evaluation time period, obtaining students' performance data in daily learning, converting the students' performance data into evaluation index data and standardizing the data, calculating students' educational effect scores under different evaluation dimensions based on the evaluation index data and the education effect evaluation system, and conducting a mastery test on students to obtain their mastery scores, and using the students' educational effect scores and corresponding mastery scores as a database for subsequent prediction model training.

[0022] Optionally, S4 is:

[0023] S41. Construct a mastery level prediction model based on Adaboost and assign the same initial weight to each training sample;

[0024] S42, iteratively training the weak classifier, updating the weights of all training samples based on the classification results of the previous round during the iteration process;

[0025] S43. All weak classifiers are combined into a strong classifier to complete the training of the mastery level prediction model.

[0026] Optionally, S5 is specifically as follows: when the student finishes studying in an evaluation time period, the educational effect score is calculated through the evaluation system constructed by S2, the mastery score of the student is expected based on the mastery prediction model, and the mastery score of the student is evaluated based on the test method, the error rate between the predicted mastery score and the test mastery score is calculated, the weight value of the evaluation indicator is adjusted to minimize the error rate, and the test mastery score and the student's educational effect score are added to the database to retrain the mastery prediction model; when the number of samples in the database reaches the first set value, whether to update the database is determined based on the change in the error rate. If the error rate decreases after adding new sample data, the new mastery prediction model is adopted, otherwise the mastery prediction model of the previous evaluation time period is adopted. When the number of samples in the database reaches the second set value, stop adding new sample data, and use the mastery prediction model trained in the last evaluation time period as the final model.

[0027] An education effect evaluation system based on data analysis, which implements the above-mentioned education effect evaluation method based on data analysis, includes:

[0028] Evaluation indicator acquisition module, used to obtain students' performance data and convert it into evaluation indicator data;

[0029] The education effect evaluation module calculates the education effect scores of students under different evaluation dimensions based on the evaluation indicator data;

[0030] The mastery level prediction module predicts students' mastery level scores based on their educational effectiveness scores under different evaluation dimensions;

[0031] Iteratively update the optimization module to optimize the mastery level prediction model based on students' educational effectiveness scores and the corresponding measured mastery levels.

[0032] It can be seen from the above technical solution that compared with the existing technology, the present invention provides an education effect evaluation method and system based on data analysis, which has the following beneficial effects: the present invention divides the evaluation indicators into different evaluation dimensions by analyzing the correlation and importance of different evaluation indicators, calculates the education effect score and predicts the mastery level based on the evaluation dimensions, simplifies the evaluation indicators while ensuring the comprehensiveness and reliability of the evaluation system; by calculating the education effects of different dimensions and predicting the mastery level, it is convenient for teachers to arrange teaching methods and content in advance according to the students' situation, thereby improving the teaching effect; the present invention is based on the construction and updating of the database, so that the mastery level prediction model can be continuously optimized, thereby improving the accuracy and versatility of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0034] Figure 1 This is a flow chart of the educational effect evaluation method of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0036] The embodiment of the present invention discloses a method for evaluating educational effects based on data analysis, such as Figure 1 As shown, the following steps are included:

[0037] S1. Evaluation indicator analysis: Analyze all evaluation indicators, classify them into different categories, and eliminate those that have little impact on students' mastery.

[0038] S2. Evaluation system construction: Build an education effectiveness evaluation system to calculate education effectiveness scores based on students' learning performance;

[0039] S3. Database construction: Obtain students' educational effect scores and corresponding student mastery scores as a database for subsequent prediction model training;

[0040] S4. Mastery prediction model construction: Build and train a mastery prediction model, taking students' educational effectiveness scores as input data and the corresponding student mastery scores as output results;

[0041] S5. Update and optimization of the mastery prediction model: After students finish studying for an assessment period, the weight values ​​of the evaluation indicators are adjusted based on the mastery prediction accuracy and the mastery prediction model is retrained.

[0042] Furthermore, S1 is specifically:

[0043] S11. Conduct correlation analysis on all evaluation indicators and classify them according to different evaluation dimensions;

[0044] S12. Conduct weight analysis on the evaluation indicators included in each evaluation dimension to determine the degree of influence of the evaluation indicators on students' mastery scores;

[0045] S13. Screen the evaluation indicators based on their impact on students' mastery scores, and eliminate evaluation indicators whose impact is less than a preset threshold.

[0046] In an embodiment of the present invention, S11 first divides all evaluation indicators into five evaluation dimensions through a clustering algorithm, and then performs fine-tuning based on manual analysis. For example, a certain indicator can be included in two evaluation dimensions at the same time.

[0047] Furthermore, S12 is specifically as follows: for each evaluation dimension, a subjective weighting method is used to assign subjective weights to all evaluation indicators, and an entropy weight method is used to assign objective weights to all evaluation indicators. The weight values ​​of the evaluation indicators are obtained by combining the subjective weights and the objective weights:

[0048] w ij =αw ij1 +(1-α)w ij2

[0049] Where w ij is the weight of the jth evaluation indicator in the i-th evaluation dimension, w ij1 w ij The subjective weight, w ij2 w ij The objective weight of , α is the adjustment parameter.

[0050] In the embodiment of the present invention, the subjective weighting method adopts expert scoring to assign weights, and an expert group including teachers and psychologists is formed to assign values ​​to all evaluation indicators through subjective scoring.

[0051] In the embodiment of the present invention, the entropy weight method is specifically:

[0052] Standardize the indicator data and calculate the information entropy:

[0053]

[0054] Where, e j is the information entropy of the jth evaluation index, k is the intermediate parameter, m is the number of samples of an index, P jl represents the proportion of the lth sample of the jth indicator;

[0055] Calculate the coefficient of variation d j :

[0056] d j =1-e j

[0057] Calculating entropy weights

[0058]

[0059] Furthermore, S2 is specifically divided into five evaluation dimensions: learning ability, learning attitude, psychological state, practical ability and comprehensive quality, and the educational effect indicators of each evaluation dimension are calculated separately:

[0060]

[0061] Where, E i represents the educational effect score of the i-th evaluation dimension, w ij represents the weight of the jth evaluation indicator in the i-th evaluation dimension, a ij represents the jth evaluation indicator in the i-th evaluation dimension, N i Indicates the number of evaluation indicators in the i-th evaluation dimension, i∈[1,5], j∈[1,N i ].

[0062] In an embodiment of the present invention, learning ability includes classroom participation, homework quality, test scores and the application of learning strategies; learning attitude includes attendance punctuality, concentration, learning time and resource utilization; psychological state includes emotion assessment scale score, anxiety index and interpersonal relationship index; practical ability includes experimental operation score, innovation ability score and project learning score; comprehensive quality includes cooperative learning ability, critical thinking, information literacy and expression and communication ability.

[0063] Furthermore, S3 is specifically as follows: after an evaluation time period, students' performance data in daily learning is obtained, the students' performance data is converted into evaluation index data and standardized, and the students' educational effect scores under different evaluation dimensions are calculated based on the evaluation index data and the education effect evaluation system. At the same time, students are tested for their mastery level to obtain their mastery level scores, and the students' education effect scores and corresponding mastery level scores are used as a database for subsequent prediction model training.

[0064] Furthermore, S4 is specifically:

[0065] S41. Construct a mastery level prediction model based on Adaboost and assign the same initial weight to each training sample;

[0066] S42, iteratively training the weak classifier, updating the weights of all training samples based on the classification results of the previous round during the iteration process;

[0067] S43. All weak classifiers are combined into a strong classifier to complete the training of the mastery level prediction model.

[0068] Furthermore, S5 is specifically as follows: when students finish studying in an evaluation time period, the educational effect score is calculated through the evaluation system constructed by S2, the mastery score of the corresponding student is expected based on the mastery prediction model, and the mastery score of the student is evaluated based on the test method, and the error rate between the predicted mastery score and the test mastery score is calculated, and the weight value of the evaluation indicator is adjusted to minimize the error rate. At the same time, the test mastery score and the student's educational effect score are added to the database to retrain the mastery prediction model; when the number of samples in the database reaches the first set value, whether to update the database is determined based on the change in the error rate. If the error rate decreases after adding new sample data, the new mastery prediction model is adopted, otherwise the mastery prediction model of the previous evaluation time period is adopted. When the number of samples in the database reaches the second set value, stop adding new sample data, and use the mastery prediction model trained in the last evaluation time period as the final model.

[0069] and Figure 1 Corresponding to the method described above, an embodiment of the present invention further discloses an education effect evaluation system based on data analysis, which executes the above-mentioned education effect evaluation method based on data analysis, including:

[0070] Evaluation indicator acquisition module, used to obtain students' performance data and convert it into evaluation indicator data;

[0071] The education effect evaluation module calculates the education effect scores of students under different evaluation dimensions based on the evaluation indicator data;

[0072] The mastery level prediction module predicts students' mastery level scores based on their educational effectiveness scores under different evaluation dimensions;

[0073] Iteratively update the optimization module to optimize the mastery level prediction model based on students' educational effectiveness scores and the corresponding measured mastery levels.

[0074] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0075] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating educational effectiveness based on data analysis, characterized in that: The following steps are involved: S1. Evaluation indicator analysis: Analyze all evaluation indicators, classify them into different categories, and eliminate those that have little impact on students' mastery. S2. Evaluation system construction: Build an education effectiveness evaluation system to calculate education effectiveness scores based on students' learning performance; S3. Database construction: Obtain students' educational effect scores and corresponding student mastery scores as a database for subsequent prediction model training; S4. Mastery prediction model construction: Build and train a mastery prediction model, taking students' educational effectiveness scores as input data and the corresponding student mastery scores as output results; S5. Update and optimization of the mastery prediction model: After students finish studying for an assessment period, the weight values ​​of the evaluation indicators are adjusted based on the mastery prediction accuracy and the mastery prediction model is retrained.

2. The method for evaluating educational effectiveness based on data analysis according to claim 1, characterized in that: S1 is specifically: S11. Conduct correlation analysis on all evaluation indicators and classify them according to different evaluation dimensions; S12. Conduct weight analysis on the evaluation indicators included in each evaluation dimension to determine the degree of influence of the evaluation indicators on students' mastery scores; S13. Screen the evaluation indicators based on their impact on students' mastery scores, and eliminate evaluation indicators whose impact is less than a preset threshold.

3. The method for evaluating educational effectiveness based on data analysis according to claim 2, characterized in that: S12 is specifically as follows: For each evaluation dimension, subjective weighting method is used to assign subjective weights to all evaluation indicators, and entropy weight method is used to assign objective weights to all evaluation indicators. Combining subjective weights and objective weights, the weight value of the evaluation indicator is obtained: w ij =αw ij1 +(1-a)w ij2 Where w ij is the weight of the jth evaluation indicator in the i-th evaluation dimension, w ij1 w ij The subjective weight, w ij2 w ij The objective weight of , α is the adjustment parameter.

4. The method for evaluating educational effectiveness based on data analysis according to claim 1, characterized in that: S2 is specifically: the evaluation indicators are divided into five evaluation dimensions: learning ability, learning attitude, psychological state, practical ability and comprehensive quality, and the educational effect indicators of each evaluation dimension are calculated separately: Where, E i represents the educational effect score of the i-th evaluation dimension, w ij represents the weight of the jth evaluation indicator in the i-th evaluation dimension, a ij represents the jth evaluation indicator in the i-th evaluation dimension, N i Indicates the number of evaluation indicators in the i-th evaluation dimension, i∈[1,5], j∈[1,N i ].

5. The method for evaluating educational effectiveness based on data analysis according to claim 1, characterized in that: S3 is specifically as follows: after an evaluation period, students’ performance data in daily learning is obtained, the students’ performance data is converted into evaluation index data and standardized, and the students’ educational effect scores under different evaluation dimensions are calculated based on the evaluation index data and the education effect evaluation system. At the same time, students are tested for their mastery level to obtain their mastery level scores, and the students’ education effect scores and corresponding mastery level scores are used as a database for subsequent prediction model training.

6. The method for evaluating educational effectiveness based on data analysis according to claim 1, characterized in that: S4 is specifically: S41. Construct a mastery level prediction model based on Adaboost and assign the same initial weight to each training sample; S42, iteratively training the weak classifier, updating the weights of all training samples based on the classification results of the previous round during the iteration process; S43. All weak classifiers are combined into a strong classifier to complete the training of the mastery level prediction model.

7. The method for evaluating educational effectiveness based on data analysis according to claim 1, characterized in that: S5 is specifically as follows: when students finish studying in an evaluation time period, the education effect score is calculated through the evaluation system constructed by S2, the mastery score of the corresponding student is expected based on the mastery prediction model, and the mastery score of the student is evaluated based on the test method, and the error rate between the predicted mastery score and the test mastery score is calculated, and the weight value of the evaluation indicator is adjusted to minimize the error rate. At the same time, the test mastery score and the student's education effect score are added to the database to retrain the mastery prediction model; when the number of samples in the database reaches the first set value, whether to update the database is determined based on the change in the error rate. If the error rate decreases after adding new sample data, the new mastery prediction model is adopted, otherwise the mastery prediction model of the previous evaluation time period is adopted. When the number of samples in the database reaches the second set value, stop adding new sample data, and use the mastery prediction model trained in the last evaluation time period as the final model.

8. An education effect evaluation system based on data analysis, characterized in that: Executing the method for evaluating educational effectiveness based on data analysis according to any one of claims 1 to 7, comprising: Evaluation indicator acquisition module, used to obtain students' performance data and convert it into evaluation indicator data; The education effect evaluation module calculates the education effect scores of students under different evaluation dimensions based on the evaluation indicator data; The mastery level prediction module predicts students' mastery level scores based on their educational effectiveness scores under different evaluation dimensions; Iteratively update the optimization module to optimize the mastery level prediction model based on students' educational effectiveness scores and the corresponding measured mastery levels.

Images