Online Learning Concentration Analysis via Interactive Stage Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online education is hindered by distractions, making it difficult to determine key learning content that requires relearning, as existing methods rely on reverse derivation from learning results rather than real-time concentration analysis.
Innovation Solution
A method and apparatus that acquire and analyze learning feature data from different interactive stages of online learning (watching, answering, voice interaction, and movement imitation) to determine actual learning concentration, identifying non-concentration periods and targeting specific content for relearning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If prior art uses reverse derivation from learning results to determine key learning content, then the method is simple to implement, but the accuracy of identifying actual non-concentration periods is low
Solution Approach 1:
The learning process is segmented into multiple interactive stages (watching stage, online answering stage, voice interaction stage, movement imitation stage), and concentration analysis is performed separately for each stage using stage-specific feature data and analysis modes. This segmentation enables precise identification of non-concentration periods without requiring a complex unified analysis system.
Solution Approach 2:
Learning feature data serves as an intermediary between the learning process and concentration determination. The system collects feature data (face orientation, viewpoint position, answering delay, voice data, body movement) from each interactive stage, analyzes this intermediary data to determine concentration state, thereby avoiding direct complex observation of user attention while achieving high accuracy.
2Loss of time
If online learning provides comprehensive learning content, then the learning material is complete, but the time required for relearning key content increases
Solution Approach 1:
The system performs preliminary concentration analysis during the learning process itself, identifying non-concentration periods and determining key learning content in advance. This preliminary identification allows targeted relearning of only the necessary content, preventing the need to review entire learning materials and thus reducing relearning time while maintaining completeness.
Solution Approach 2:
The system provides feedback by determining actual learning concentration in real-time and identifying key learning content that requires attention. This feedback mechanism enables dynamic adjustment of learning focus, ensuring that relearning efforts are concentrated on actual gaps rather than reviewing already-mastered content, thereby optimizing both time efficiency and content completeness.
Data Source
AI summary
A method and apparatus for determining key learning content, an electronic device and a computer-readable storage medium. An implementation of the method may include: acquiring learning feature data of a user at different interactive learning stages of the online learning, where the interactive learning stage includes: at least one of a watching stage, an online answering stage, a voice interaction stage, and a movement imitation stage; analyzing learning feature data corresponding to an interactive learning stage by using a preset analysis mode corresponding to the interactive learning stage, to obtain an actual learning concentration corresponding to the interactive learning stage; and determining, according to the actual learning concentration, a target period with an actual learning concentration not meeting a preset learning concentration requirement, and determining learning content corresponding to the target period as the key learning content.