A Clustering Knowledge Tracking Algorithm for Learners Based on Dynamic Key-Value Memory Network

Abstract

In the existing classic deep knowledge tracking model, only the correctness of the student's historical question data is concerned, but the other characteristics of the student are not paid attention to. Human learning is a process of practice. Students gradually improve their knowledge mastery through learning, but the learning ability of each student is not the same. Only a single characteristic of correctness cannot completely distinguish the learning ability of different students. The existing BKT or DKVMN algorithms assume that the learning ability of each student is the same. In order to solve the above mentioned problems, this paper divides students according to their learning ability based on the DKVMN model, and then dynamically divides students into corresponding groups according to the time interval, improves the personalized expression of the DKVMN algorithm, and makes the algorithm more reasonable predictions.