Error cause analysis method based on graph neural network

Abstract

The invention provides a fault cause analysis method based on a graph neural network. According to the method, interpretable error cause information possibly existing in homework or test paper is collected; therefore, a corresponding preset interpretable error cause information set is formed; generating a preset error cause solution set matched with the preset interpretable error cause informationset and a corresponding error cause graph neural network model; collecting the current error cause information according to the actual situation of the current error cause information; finding interpretable error cause information with the highest correlation degree from the preset interpretable error cause information set through an error cause graph neural network model; and searching a preseterror cause solution matched with the preset error cause solution set from the preset error cause solution set, thereby realizing quick positioning and searching of interpretable error cause information actually appearing in homework or test paper and accurately and efficiently determining a proper interpretable error cause solution.

Description

technical field [0001] The invention relates to the technical field of information error cause analysis and solution, in particular to an error cause analysis method based on a graph neural network. Background technique [0002] At present, in the teaching process, it is usually necessary to judge homework or test papers, and with the increase in the number of students and teaching tasks, the amount of homework and test papers that teachers need to judge also increases, relying only on manual review and judgment by teachers, It is not possible to quickly, comprehensively and accurately review and judge all assignments or test papers one by one, which is not conducive to teachers' in-depth understanding of different students' mastery of different knowledge points, but also affects teaching progress and teaching quality. It can be seen that there is an urgent need in the prior art for a method capable of effectively analyzing the explainable error causes in assignments or test...

AI Technical Summary

Problems solved by technology

[0002] At present, in the teaching process, it is usually necessary to judge homework or test papers, and with the increase in the number of students and teaching tasks, the amount of homework and test papers that teachers need to judge also increases, relying only on manual review and judgment by teachers, It is not possible to quickly, comprehensively and accurately review and judge all assignments or test papers one by one, which is not conducive to teachers' in-depth understanding of different students' mastery of different knowledge points, but also affects teaching progress and teaching quality

Images