Cognitive diagnosis method and system based on learning behaviors

Abstract

The embodiment of the invention provides a cognitive diagnosis method and system based on learning behaviors, and the method comprises the steps: determining student numbers and answer numbers to be subjected to cognitive diagnosis, and enabling the student numbers and the answer numbers to be in one-to-one correspondence with student answers and corresponding video records contained in learning courses; inputting the student number to be subjected to cognitive diagnosis and the answer number into a diagnosis model to obtain a student cognitive diagnosis result output by the diagnosis model, wherein the diagnosis model is obtained by training on the basis of test question samples, corresponding knowledge point marks, corresponding video samples and corresponding video marks; the diagnosis model is used for constructing a course diagram based on the test question samples, the corresponding knowledge point marks, the corresponding video samples and the corresponding video marks, and performing corresponding student cognitive diagnosis on the learning course to be subjected to cognitive diagnosis after node information updating is performed on the course diagram through a graph neural network. According to the embodiment of the invention, the knowledge level of the student is effectively predicted.

Description

technical field [0001] The invention relates to the technical field of intelligent education, in particular to a cognitive diagnosis method and system based on learning behavior. Background technique [0002] Cognitive diagnosis is an important task proposed for the online education scene. It aims to diagnose the knowledge level of students by using the behavior of students on the online education website. One of the key technologies of path planning). [0003] The usual cognitive diagnosis method relies on students’ record of doing questions on the online learning platform. After obtaining each student’s question sequence and scores, both students and test questions are modeled. During the modeling process, students and test questions are modeled and analyzed. The student's answering result is predicted, and the student's answering question is predicted to be a binary classification problem. The model gradually optimizes the parameters during the classification process, an...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a cognitive diagnosis method and system based on learning behavior, which is used to solve some or all of the above-mentioned problems in the cognitive diagnosis method of the existing online education system

Images