Adaptive learning support device and method based on deep knowledge tracking

Abstract

According to the adaptive learning support device and method based on deep knowledge tracking provided by the invention, through an improved knowledge tracking model, the current knowledge state of a learner is tracked in real time in a relatively accurate and practical manner. The device comprises an improved deep knowledge tracking model, a mastered knowledge point topic recommendation module and a knowledge level transition resource recommendation module. According to the invention, learning behaviors of students are fused into a knowledge tracking model, and an improved knowledge tracking model is provided based on an MANN. According to the method, the knowledge mastering degree of the student can be obtained based on the knowledge tracking model, and based on the trained knowledge tracking model, unfinished questions associated with mastered knowledge points are recommended to the student, and resources based on a knowledge level transition trajectory are recommended. According to the invention, the accuracy of the knowledge tracking model is improved, and the purpose of recommending learning resources for students based on collaborative filtering is achieved.

Description

Technical field [0001] The present invention relates to the field of knowledge and technology track, in particular, to an improved apparatus and method for tracking model based on knowledge to provide adaptive learning for students. Background technique [0002] Track knowledge (Knowledge Tracing) is the knowledge of the students grasp the situation according to circumstances answer student's past modeling to give a technical knowledge of the current state of student representation. Knowledge track to capture the current real needs of learners, the learner is the core task modeling. Reasons but because of the diversity and complexity of the knowledge of the human brain, the human learning process is complex, which is very difficult to track knowledge. [0003] In recent years, with the popularization and development of the Internet, online teaching has been widely used. Small-scale limiting online courses (Small Private Online Course, SPOC) for learners provides an interactive le...

AI Technical Summary

Problems solved by technology

However, the input of the DKT model only includes the learners' answers to the questions. Some researchers believe that only considering the knowledge components of the questions and ignoring other information will have a negative impact on the knowledge tracking effect, and the DKT model cannot explicitly extract students' knowledge. Knowledge point vector representation of status and topic, lack of interpretability

[0006] Dynamic key-value pair memory network (DKVMN) adds an external memory module on the basis of DKT to extract the knowledge points of students and the vector representation of knowledge points of the topic, but it still does not take into account the impact of other information such as students' learning behavior on students' knowledge. Effects of Mastery Status

[0007] Attention-based models such as self-attentional knowledge tracking (SAKT) and context-based attentional knowledge tracking (AKT) can extract important features, capture long-distance dependencies, and train faster than recurrent neural networks. Fast, but none of the current models can explicitly extract the knowledge status of students, lacking interpretability

Images