Personalized Learning Pathway Generation for Online Education Through Image Recognition

Abstract

The development of online education has driven a profound transformation in the teaching mode of vocational education, with the generation of personalized learning paths as one of the key factors in improving the learning effectiveness of learners. However, current online learning platforms still face a series of challenges in personalized teaching practices. Especially in terms of accurately capturing and understanding learner behavior and emotions, existing systems have not fully met the personalized learning needs of learners. This study aims to explore a novel mechanism for generating personalized learning paths for learners through image recognition technology. Firstly, by combining migration learning and dual stream convolutional networks, this study proposes a recognition method that can adapt to the behavioral characteristics of different groups of learners. Secondly, using graph convolutional neural networks (GCNNs) for deep recognition of learner micro-expressions to accurately capture the learner's emotional state, making the generation of learning paths more detailed and adaptable. This study addresses the shortcomings of existing systems in processing multimodal data integration and real-time feedback dynamic adaptation, and improves the accuracy and practicality of personalized learning path generation for learners. The research results not only promote the progress of personalized learning path generation in online education for learners technically, but also provide learners with a more customized learning experience.