Learning trajectory-oriented fine-grained knowledge tracking method

Abstract

The invention relates to the field of education big data mining and knowledge tracking, and provides a learning track-oriented fine-grained knowledge tracking method, which comprises the following steps of: (1) constructing a learning track-oriented fine-grained knowledge tracking framework; (2) obtaining a historical potential knowledge state of the learner through historical interaction in the learning track; (3) obtaining the current potential ability representation of the learner through the current interaction in the learning track; and (4) predicting the fine granularity of the current reaction state. According to the method, the learning track of the learner is modeled by using technical methods such as a multi-head self-attention network, multi-task prediction and time sequence modeling, the knowledge state of the learner is tracked, the future performance of the learner is predicted, and the development of precise teaching and personalized learning is assisted.

Description

technical field [0001] The invention relates to the fields of education big data mining and knowledge tracking, in particular to a fine-grained knowledge tracking method oriented to learning trajectory. Background technique [0002] The development of artificial intelligence technology is conducive to the development of personalized and precise teaching models. Knowledge tracking can analyze the changes of the learner's knowledge state during the learning process by modeling the trajectory and results of the learners' answering questions, and predict the performance of the learners' answering questions in the future. [0003] The current deep knowledge tracking models can be roughly divided into three categories according to the models used: knowledge tracking based on long short-term memory network, knowledge tracking based on attention network, and knowledge tracking based on custom neural network. [0004] The state-of-the-art among knowledge tracking methods based on lo...

AI Technical Summary

Problems solved by technology

Existing studies only focus on coarse-grained response results, which cannot effectively explore the fine-grained changes in learners' knowledge status during the answering process.

Images