一种虚拟现实环境下的学习投入度评估方法
By constructing a learning engagement assessment model in a virtual reality environment and utilizing posture behavior, lip movement, and eye movement trajectory recognition algorithms, the difficulty of assessing learning engagement in a virtual reality environment is solved. This achieves accurate assessment in a natural state without affecting learners' interactive operations and provides multi-dimensional visual representation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING NORMAL UNIVERSITY
- Filing Date
- 2023-11-02
- Publication Date
- 2026-07-17
AI Technical Summary
In virtual reality environments, existing technologies struggle to assess learning engagement in real time without disrupting learners' interactive operations, especially due to the challenges of assessment caused by wearing VR headsets and using physiological data collection devices.
By constructing a learning engagement assessment model, combining posture behavior recognition, lip movement recognition, and eye movement trajectory recognition algorithms, and employing a hybrid attention Transformer network, cascaded convolutional neural network, and 1DCNN-BiLSTM network, the model identifies learners' body movements, lip movements, and eye movement trajectories in the VR environment, and calculates behavioral engagement, emotional engagement, and cognitive engagement.
It enables accurate assessment of learning engagement in a natural state without affecting learners' interactive operations, eliminates the impact of wearing VR headsets, and provides multi-dimensional visual representations of behavioral, emotional, and cognitive engagement.
Smart Images
Figure CN117593156B_ABST