Cognitive diagnosis method and system

Abstract

The invention provides a cognitive diagnosis method and system. The method comprises the following steps of: obtaining cognitive attribute information and reaction information of a subject; determining a project attribute relationship Q matrix according to the cognitive attribute information and determining a subject reaction X matrix according to the reaction information of the subject; constructing an OR-DINA model, wherein the model comprises an error parameter and a guess parameter; estimating the error parameter and the guess parameter by utilizing an expectation maximization EM algorithm; and calculating a knowledge state of the subject according to the estimated error parameter and guess parameter. According to the cognitive diagnosis method and system provided by the invention, anoptimized cognitive diagnosis model is disclosed, so that the probability of correctly answering projects can be increased along with the increase of attribute quantity tested by projects grasped by the subject, and weak knowledge points and skill point of the subject can be accurately diagnosed.

Description

technical field [0001] The invention relates to the field of computer application technology, in particular to a cognitive diagnosis method and system. Background technique [0002] The traditional test only uses the total score of the test as the evaluation index, which seems too general and general. Now people not only require the test to be evaluated at the level of the total score, but also hope to go deep into the internal cognitive processing level of the testee. [0003] Relatively speaking, the prior art divides the subjects into two categories on each item: the mastered class and the unmastered class. The mastery category is the set of subjects who have mastered all the attributes investigated by the project; other subjects are classified into the non-mastery category, and these subjects may not have mastered any attributes, or may have mastered some attributes. Such a classification ignores the difference in the amount of attributes mastered by the subjects in the...

AI Technical Summary

Problems solved by technology

In addition, the definition of the model in the prior art is not rigorous enough. From the point of view of the function, the probability of the subject answering the item correctly does not increase with the number of attributes that the subject masters; and the interpretability of the model Poor, ideal response latent variable η ij It is unreasonable to take continuous values

at 0ij When ij Taking continuous values ​​also increases the computational complexity of parameter estimation

[0004] To sum up, the current cognitive diagnosis model lacks the ability to accurately judge the weak points and skill points of the subjects

Images