Research on the Model of Adaptive Learning Path Planning Based on Artificial Intelligence in English Education

This paper aims to build an adaptive learning path planning model based on artificial intelligence to improve the personalized learning effect in English education. First, this paper introduces the dynamic knowledge tracking (DKT) algorithm, which adjusts the learning path in real time through dynamic analysis of learners' historical learning behavior and knowledge mastery, thereby optimizing the learning experience. The model combines students' cognitive characteristics, learning preferences, and the dependencies between knowledge points to ensure that learners receive the most targeted teaching content at the right time. In the model simulation part, this paper verifies the effectiveness of the adaptive learning path planning model by conducting simulation experiments on a large number of students' learning data. The results show that compared with the traditional fixed learning path, the model based on dynamic knowledge tracking significantly improves learning efficiency and knowledge mastery. The model has an accuracy rate of 85% in predicting students' next learning content, an optimization rate of learning path improvement of 30%, and a student learning effect improvement rate of up to 25%.