一种用于辅助知识学习的方法及装置
By combining three-level coordinate mapping and OCR models with subject knowledge graphs, the system achieves precise alignment and correction of paper assignments and projected content in intelligent tutoring devices. By adopting a deconstructive teaching strategy, it solves the problems of positional misalignment and eye strain in homework tutoring, thereby improving the user experience and training effectiveness of the devices.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 北京爱宾果科技有限公司
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing smart tutoring devices have problems in homework tutoring scenarios, such as eye strain caused by blue light radiation from the screen, low efficiency due to the separation of paper and correction content, and misalignment of the projection correction position, resulting in a poor user experience.
The paper assignments and projected content are precisely aligned using a three-level pixel-level coordinate mapping technology. An OCR model is used for grading and a deconstructive teaching strategy is employed. Personalized training is conducted by combining subject knowledge graphs and propagation probability models to generate electronic test papers.
It solves the problems of projector misalignment, eye strain, and rigid teaching methods, improves the systematicness and effectiveness of homework tutoring, takes into account both homework correction and thinking development, and achieves accurate identification of weak knowledge points and personalized training.
Smart Images
Figure CN122415294A_ABST