Serialized student cognition diagnosis method

Abstract

The invention discloses a serialized student cognition diagnosis method. The method comprises the steps of obtaining historical question-answering information of multiple students; performing modeling by using a serialized cognition diagnosis method according to the obtained historical question-answering information, and obtaining ability vectors and a test question-knowledge point correlation matrix subjected to partial order limitation; and predicting an ability value and a score of a student in the next time period according to the ability vectors and the test question-knowledge point correlation matrix subjected to the partial order limitation. According to the method, by performing continuous and long-time analysis processing on test question information and question-answering conditions of the students, the overall ability levels and knowledge mastery degrees of the students in different time periods can be accurately analyzed.

Description

technical field [0001] The invention relates to the technical field of educational data mining, in particular to a time-series cognitive diagnosis method for students. Background technique [0002] Cognitive diagnosis is an improvement and perfection of traditional examination and evaluation. Educational tests in general, especially large scale ones, only provide test scores. However, from a single score, we can neither get the conclusion of what knowledge the student has or has not mastered, nor can we get the reason why the student did the wrong test questions for remediation; for students with the same score, it is impossible to get the knowledge that may exist between them Differences in state and cognitive structure. The information provided by traditional examinations is no longer suitable for the needs of students' development. The main task of cognitive diagnosis is to dig out more cognitive processing information according to the differences of students. Cognitiv...

AI Technical Summary

Problems solved by technology

[0011] In the above-mentioned cognitive diagnosis method, although the ability value diagnosis and knowledge mastery diagnosis based on a single moment can accurately obtain the student's ability value or knowledge mastery degree at a specific moment, this method is static and can only analyze the data of one exam. analysis, cannot be applied to the dynamic assessment of students' long-term learning

Based on the ability value diagnosis method at multiple moments, although the ability value of the student at different moments can be obtained and the student's score at the next moment can be accurately predicted, the ability value has no practical significance, let alone explain how the student's ability value changes , a single-dimensional ability value is of little practical value because of the lack of explanatory significance. This method can only diagnose the improvement or decline of the student's ability value at different moments, but it cannot know which aspect of the student's knowledge needs to be strengthened. , which aspects are already proficient enough and do not require additional training

Therefore, using the existing cognitive diagnostic methods, it is difficult to accurately capture the changes in students' mastery of various knowledge points during the long-term learning process, and to explain what factors lead to the changes in students, such as learning a new a knowledge point, or the time interval is too long to forget, etc.

Images