A knowledge tracking method and system

Abstract

The invention relates to a knowledge tracking method and system, belonging to the technical field of knowledge tracking. Including: building a DMKT model based on the DKT model; the DMKT model includes an input layer, which is used to encode the encoding vector according to the student's answer data and domain characteristics; a hidden layer, used to encode according to the encoding vector and the student's knowledge state data and domain characteristics at the previous moment Obtain the output result of the hidden layer; the output layer is used to obtain the prediction result according to the output result of the hidden layer; the multi-knowledge point mapping layer is used to obtain the multi-knowledge point mapping result according to the prediction result; obtain historical student answer data and historical field feature encoding and historical The prediction result is combined with the multi-knowledge point mapping result to train the DMKT model; the next moment prediction result is output according to the trained DMKT model. It solves the problem of lack of domain feature integration and feature reduction in the process of integration, and at the same time suppresses the occurrence of forgetting the relationship between knowledge points, and realizes accurate tracking of students' knowledge levels.

Description

technical field [0001] The present invention relates to the technical field of knowledge tracking, and in particular, to a knowledge tracking method and system. Background technique [0002] In recent years, the widespread application of online learning platforms and intelligent guidance systems has provided students with a wealth of practice questions, one of which may be related to one or more knowledge points. The probability of a student answering a question correctly depends on his state of knowledge, that is, his mastery of knowledge points. The purpose of knowledge tracking is to track students' knowledge status, and predict the probability that students will answer the next question correctly based on their answer records. However, there are existing knowledge tracking methods such as Deep Knowledge Tracing (DKT), whose input only includes question labels and correct answers, and the answer results are obviously affected by other domain features such as the number o...

AI Technical Summary

Problems solved by technology

However, there are existing knowledge tracking methods such as Deep Knowledge Tracing (DKT), whose input only includes question labels and correct answers, and the answer results are obviously affected by other domain characteristics such as the number of answers, answering time, etc.

Although some methods have tried to integrate features into the DKT model, there is a problem of low prediction accuracy. The main reason is that the key information reduction problem of features in network transmission is not considered.

[0003] In addition, the cyclic neural network in knowledge tracking itself has the problem of long-term dependency forgetting, that is, the network will forget what it has learned before, which will lead to the loss of some key information; and there are a large number of multi-knowledge point problems in knowledge tracking, and there are also problems between problems. There are complex knowledge point association relationships, and the forgetting of these relationships will cause the network to fit wrong features, resulting in wrong associations and continuous offsets of knowledge points

Images