一种冷启动跨课程的知识追踪方法和系统
By constructing a sequence neural network model and a knowledge component prototype alignment mechanism, zero-sample cross-course knowledge tracing is achieved using source course data, solving the knowledge transfer problem in cold start scenarios and improving the accuracy and stability of knowledge tracing.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA UNIV OF MINING & TECH
- Filing Date
- 2026-06-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to achieve cross-course knowledge tracking when student interaction data for the target course is lacking, especially in cold start scenarios where knowledge states cannot be effectively transferred.
A sequence neural network model is constructed, and a training sample set is built using the student answer sequence of the source course. Through stage-aware state modeling and knowledge component prototype alignment mechanism, the knowledge state representation of the source course is directly transferred to the target course, realizing zero-shot cross-course knowledge tracking.
This allows for direct application to the target course without using any student interaction data, solving the problem of traditional methods being unable to transfer knowledge across courses and improving the accuracy and stability of knowledge tracking.
Smart Images
Figure CN122415293A_ABST