Abstract:

In the classroom， student state changes are subtle and key features are difficult to capture. Therefore， a real-time collection and dynamic analysis method based on hybrid intelligence is proposed to detect abnormal learning states in a timely manner. By using image enhancement technology to preprocess and collect images， the enhanced images are input into a convolutional neural network. After convolutional processing， deep level feature maps and key feature maps are extracted， and further input into a long short-term memory network to achieve dynamic analysis and recognition of the learning status of classroom students. Through experimental verification， this method can provide real-time feedback on the learning status of students， with good recognition effect and high stability. With the help of this method， students' academic performance can be effectively improved based on the correction of relevant academic personnel， and it has certain application value.

Key words: hybrid intelligence, real-time acquisition of learning status, dynamic analysis, image enhancement technology, convolutional neural network, long short-term memory network