Confidence evaluation method and device for test question difficulty value and storage medium

Abstract

The invention discloses a confidence evaluation method and device for a test question difficulty value and a storage medium, and the method comprises the steps: extracting a certain number of test questions in a test question library, and forming a test question pair in pairs; obtaining test question difficulty values of test questions in the test question pair, comparing the test question difficulty values, and summarizing to obtain system evaluation result data; performing manual evaluation on the difficulty size relationship of the test questions in the test question pair to obtain manual evaluation result data; and taking the manual evaluation result data as an evaluation standard, performing result comparison with the system evaluation result data, performing statistical calculation and comparison on the proportion of the same test question pairs, and obtaining the confidence coefficient for evaluating the difficulty value information of the test questions in the test question bank. According to the method, the test question difficulty value of each specific test question is not concerned any more, and the consistent proportion of the manual evaluation result data and the system evaluation result data is counted and calculated according to the comparison result of the test question to the difficulty value size relationship, so that the confidence evaluation of the test question difficulty values is realized.

Description

technical field [0001] The present invention relates to the technical field of online education, in particular to a confidence evaluation method, device and storage medium for the difficulty value of test questions. Background technique [0002] In order to provide online services such as photo search, intelligent practice, and homework correction, online education platforms generally need to be based on a powerful test question database. For the test questions in the test question database, in order to provide users with a more comprehensive user experience, the subject, grade, area and difficulty value of the test question are often marked with test question attribute labels, among which the subject, grade, region and other test question attribute labels can be obtained from the test paper of the test question It is automatically obtained from resources, but the labeling of the difficulty value of the test questions is highly subjective. Due to the lack of evaluation stand...

AI Technical Summary

Problems solved by technology

For the test questions in the test question database, in order to provide users with a more comprehensive user experience, the subject, grade, area and difficulty value of the test question are often marked with test question attribute labels, among which the subject, grade, region and other test question attribute labels can be obtained from the test paper It is automatically obtained from resources, but the difficulty value of the test questions is highly subjective. Due to the lack of evaluation standards, the confidence of the difficulty value of the test questions cannot be evaluated

[0003] Most of the difficulty values ​​of existing test questions are marked manually by teachers. Due to the subjective factors of the difficulty value of the test questions, multiple teachers have different evaluation standards for the same test question, resulting in deviations in the labeling of the difficulty value of the same test question.

This characteristic makes it difficult to evaluate whether the difficulty value of a test question is reasonable, that is, whether the difficulty value of the test question has reference value

Images