Model-independent adaptive test method

Abstract

The invention discloses a model-independent adaptive test method which is characterized by comprising the following steps: estimating the cognitive state of an examinee according to the historical answer record of the examinee so as to predict the answer probability of the examinee to each question in an untested question set, and through a model-independent information amount evaluation function,quantifying the information amount of each question in the untested question set, and selecting the top KC questions according to the information amount to form a high-quality candidate set; and quantifying the diversity of a tested question set through a model-independent question set diversity evaluation function in combination with importance weights of knowledge points in questions, and selecting the question with the maximum boundary gain of the diversity from a high-quality candidate set to serve as a final result of question selection this time. The method is advantaged in that dependence of the algorithm on model underlying details is stripped, the method is suitable for all existing cognitive diagnosis models, coupling of the adaptive test system is reduced, and flexibility of the adaptive test system is improved.

Description

technical field [0001] The invention relates to the technical fields of machine learning, artificial intelligence and intelligent education, in particular to a model-independent adaptive testing method. Background technique [0002] In intelligent education, testing and diagnosing candidates' knowledge mastery is a basic task. In this task, how to choose the appropriate topic for candidates is a core challenge. [0003] Since the traditional paper-based test cannot select individualized questions according to the cognitive state of each examinee, educational psychology research is currently focusing on an adaptive test form, that is, in the test process, according to the current performance of the examinee, through cognitive The cognitive diagnosis model dynamically estimates the cognitive state of candidates, and then designs a topic selection strategy to adaptively select the next step according to their cognitive state. [0004] Existing topic selection strategies try t...

AI Technical Summary

Problems solved by technology

However, these works rely more on the details and principles of the representation of the knowledge level of candidates by the cognitive diagnostic model, resulting in the design of topic selection strategies that are only applicable to specific models

This strong correlation between strategies and models leads to high coupling and low flexibility of the adaptive test system, and makes researchers have to consider too many low-level details when designing strategies, instead of simply considering the cognitive ability of candidates

Images