Knowledge tracking method and device and storage medium

Abstract

The invention discloses a knowledge tracking method and device based on a multi-head attention mechanism long-term and short-term memory network and a storage medium. A knowledge tracking model basedon a multi-head attention mechanism long-term and short-term memory network is constructed and used for knowledge tracking, and the model has better prediction performance; wherein the multi-head attention mechanism can capture more dependency relationships, including long-distance dependency relationships, among the input sequence data, so that the internal structure of the input sequence data can be obtained; in the aspect of calculation, attention calculation is carried out in parallel, calculation at the previous moment is not depended on, and the calculation speed is higher; the input sequence data is processed in parallel by using the long-short-term memory network, the information of the input sequence data can be obtained, a multi-head attention mechanism is combined with the long-short-term memory network, better prediction can be provided, and intelligent tutoring, personalized homework arrangement, learning plan generation, evaluation report generation and the like can be performed by using knowledge tracking. The method is widely applied to the field of knowledge tracking.

Description

technical field [0001] The present invention relates to the field of knowledge tracking, in particular to a knowledge tracking method, device and storage medium based on a multi-head attention mechanism long-short-term memory network. Background technique [0002] In the field of education, it is of great significance to effectively track students' knowledge status scientifically and pertinently. According to the historical learning trajectory of students, the interaction process between students and exercises can be modeled. On this basis, it can automatically track the knowledge status of students at each stage, and then predict student performance, realizing personalized guidance and adaptive learning. [0003] With the rapid development of Internet education, platforms such as Intelligent Tutoring System (ITS) and Massive Open Online Course (MOOC) are becoming more and more popular, which provides the possibility for students to learn independently and assist teaching. ...

AI Technical Summary

Problems solved by technology

In many cases, knowledge tracking tries to predict the probability that students will answer the question correctly in the next time step, that is, P(at+1=1|qt+1,Xt); due to the importance of knowledge tracking to the learning process, the industry has emerged Many related models, such as Bayesian knowledge tracing (Bayesian knowledge tracing, BKT), recurrent neural network (Recurrent Neural Network, RNN), etc.; among them, RNN is applied to a method called deep knowledge tracing (Deep knowledge tracing, DKT) Among the methods, the experimental results show that the DKT method is superior to the traditional method without the need to manually select a large number of features; however, the DKT method still has some shortcomings: (1) The model cannot reconstruct the current input results, resulting in even Students' good performance in the previous knowledge state will also lead to the failure of the prediction of the knowledge state; (2) In the time series, the students' mastery of the knowledge points is not continuous, but fluctuating, resulting in knowledge across time steps. The prediction performance of the state is inconsistent; the root cause of these deficiencies is that the DKT method cannot handle long sequence input problems well

Images