一种异步教学评价与自适应干预方法
By constructing a global incomplete observation vector and a graph Laplace matrix, and combining stochastic dynamics models and chaotic game optimization, the problem of teaching evaluation and resource allocation under asynchronous assessment data was solved, realizing an efficient adaptive teaching strategy and improving teaching quality and resource utilization efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- OCEAN UNIV OF CHINA
- Filing Date
- 2026-04-27
- Publication Date
- 2026-07-17
AI Technical Summary
Existing educational evaluation methods are unable to accurately estimate students' learning status and plan optimal teaching interventions when faced with asynchronous and non-uniform assessment data, resulting in large data errors, unreasonable resource allocation, and traditional algorithms are prone to getting trapped in local optima.
A global incomplete observation vector is constructed, a graph Laplace matrix is generated, a continuous-time stochastic dynamic evolution model is established, and an adaptive variable-dimensional mask observation matrix and a chaotic game optimization algorithm are combined to achieve cross-time domain calibration of the global state vector and output of the optimal intervention strategy.
It achieves unbiased estimation of asynchronous incomplete sampling, breaks the local optimum deadlock in educational resource scheduling, provides efficient adaptive teaching decisions, and improves teaching effectiveness and resource utilization.
Smart Images
Figure CN122222469B_ABST