Knowledge tracking method based on heterogeneous structure

Abstract

A knowledge tracking method based on a heterogeneous structure comprises the following steps: obtaining practice history logs of students and knowledge points investigated by each exercise; obtaininga heterogeneous knowledge structure formed by relationships among the knowledge points; processing score logs of the students into a plurality of answering sequences arranged according to a time sequence, wherein each answering sequence comprises a series of answering results of the specific students at specific time; based on graph structure properties of knowledge, applying two different publicity models to track influences along different relationships, including a synchronous publicity method and an asynchronous publicity method; adopting a cascade influence publicity unit to jointly establish a model for the time effect and the space effect of the model, with the heterogeneous knowledge structure and the answering sequence of the students as input, and enabling the cascade influence publicity unit to extract the time sequence influence of each learning on the knowledge points from the answering situation at each moment; and updating the knowledge state of the students by adoptinga gating function to synthesize the comprehensive effect of the time sequence influence and the space sequence influence.

Description

technical field [0001] The invention relates to the technical field of machine learning and educational data mining, in particular to a knowledge tracking method based on a heterogeneous structure. Background technique [0002] Knowledge Tracing (KT) is a technology that accurately tracks students' dynamically changing knowledge status based on their past practice performance. In recent years, the research and application of online education systems have flourished, and many well-known educational websites have adopted online education systems. These systems can not only help teachers give targeted guidance according to students' personalities, but also help students realize their own learning progress in a timely manner. Knowledge tracking, which plays a crucial role in online education systems, is a fundamental but challenging task. Pedagogy theory has proved that when students are learning a knowledge point, not only the degree of mastery of the knowledge point being le...

AI Technical Summary

Problems solved by technology

However, traditional knowledge tracking mainly utilizes time information, that is, students' answer records, while ignoring the relationship between different knowledge points, that is, the influence of "knowledge structure" on the state of knowledge

Although some recent studies have considered the influence of "knowledge structure", they have ignored the different forms of dissemination between knowledge points, such as similar relations (undirected, influence can be transmitted in both directions) and predecessor-successor relations (directed, influence can only propagate in the same direction)

Images