AI-driven personalised English learning path planning algorithm and blended learning platform construction

Abstract

In response to the contradiction between algorithm recommendation precision and learner autonomy in personalised English learning path planning and the problem of weak personalisation of blended learning platforms, this paper focuses on the AI-driven personalised English learning path planning algorithm and the construction of a blended learning platform. First, a knowledge graph is used to model the structure of English learning content and achieve semantic associations between knowledge points. Subsequently, a multi-dimensional learner profile is constructed by combining bidirectional encoder representations from transformers (BERT) and light gradient boosting machine (LightGBM) to precisely capture learning behaviours and characteristics. Finally, a deep Q-network (DQN) algorithm is applied to dynamically generate personalised learning paths based on learner status. At the same time, a blended learning system is built based on the Open EdX open source platform, and combined with the AI-driven personalised English learning path planning algorithm proposed in this paper, online AI and offline teaching are organically integrated. Experimental verification shows that this solution increases learner engagement by 55.45% compared to traditional teaching methods and improves overall autonomous learning ability by an average of 12.7%, meeting personalised needs and providing a new path for English teaching reform.