A learning strategy recommendation method based on a knowledge graph and dynamic evaluation

By combining student ability vectors and knowledge graph dependencies, a personalized learning path is dynamically evaluated and generated. Adjustments are made through real-time verification and feedback, which solves the problem of rigid learning strategies in existing technologies and achieves continuous adaptive optimization and efficiency improvement of the learning path.

CN121834064BActive Publication Date: 2026-06-16浙江海亮科技有限公司
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
浙江海亮科技有限公司
Filing Date
2026-03-12
Publication Date
2026-06-16

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve continuous adaptive optimization of personalized learning strategies, fail to dynamically adapt to students' changing learning states and abilities in real time, and ignore the inherent prerequisite dependencies of knowledge graphs, resulting in rigid and inefficient recommended learning paths.

Method used

By integrating student ability vectors, knowledge status, and knowledge graph dependencies for dynamic evaluation, personalized learning paths are generated, and adjustments are made through real-time verification and feedback to ensure the scientific nature and adaptability of the learning paths.

Benefits of technology

It enables continuous adaptive optimization of learning paths, improves the accuracy and efficiency of learning strategies, ensures a precise match between learning content and students' abilities and the controllability of learning progress, and adapts to changes in students' learning status.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121834064B_ABST
    Figure CN121834064B_ABST
Patent Text Reader

Abstract

The application discloses a learning strategy recommendation method based on a knowledge graph and dynamic evaluation, and belongs to the field of recommendation. A learning ability vector and a comprehensive knowledge state matrix are defined, an initial to-be-learned queue is generated, and preliminary knowledge point integrity checking and topological sorting are performed, then, a basic learning path is individually adjusted based on the learning ability vector, and suitable learning materials are matched for each knowledge point in the individualized learning path; finally, a daily learning task is generated based on a daily learning time budget. After the daily learning task is completed, suitable test questions are pushed, the comprehensive knowledge state matrix is updated according to the test results, and an instant adjustment strategy based on a single knowledge point test result and an overall adjustment strategy based on a learning trend are executed; a next-day learning task is generated according to the adjusted strategy, and the process is repeated until a preset learning goal is achieved. The application realizes continuous self-adaptive optimization of learning path and resource recommendation, thereby significantly improving the accuracy and efficiency of individualized learning.
Need to check novelty before this filing date? Find Prior Art