Research on construction of personalized English learning path optimization system based on MVO-CNN

With the progress of globalization, English learning has become an important topic in education. However, the traditional teaching mode makes it difficult to meet individualized learning needs, resulting in uneven learning effects. Therefore, this study aims to build a personalized English learning path optimization system based on MVO-CNN (multiverse optimization-convolutional neural networks) to improve learning efficiency and effectiveness. There are some problems in English learning, such as scattered resources and single methods, which are difficult to adapt to the characteristics and needs of different learners. As an advanced artificial intelligence technology, MVO-CNN can effectively process complex learning data and provide strong support for personalized learning. In the system construction process, we first collected English learning data, including learners’ basic information, study habits, and achievement records. Then, MVO-CNN is used to mine and analyze the data deeply to identify the key factors affecting the learning effect. Based on these factors, the system generates personalized learning paths for each learner, including recommended learning resources, learning plans and learning methods. We conducted a 3-month experiment with 500 learners participating to verify the system’s effectiveness. The experimental results show that learners who use personalized learning paths have an average improvement of 15% in English scores, a 20% reduction in learning time and a 30% increase in learning satisfaction. In addition, the system’s recommendation accuracy rate reaches 85%, better than the 60% of the traditional teaching mode. The personalized English learning path optimization system based on MVO-CNN can improve learners’ English level and learning efficiency and has broad application value.