Research on the Design of Computer-Assisted Learning System and Learning Effect Evaluation for Higher Vocational English Education

Abstract

With the deepening of globalization, there are more and more international exchanges, and English has become an important medium of communication, so how to improve the effect of higher vocational English education has become the focus of research in the field of education. To this end, the article designs a personalized recommendation system for English teaching resources based on deep learning. The system matches user features and English learning resource features through neural network to complete resource recommendation. At the same time, the article establishes a learning effect prediction model based on IGWO⁃CNN, uses the improved Gray Wolf algorithm to optimize the hyperparameters of the convolutional neural network, and finally carries out performance comparison experiments on the model. In the accuracy index comparison, this paper's algorithm grows more stable, the value is maintained between 0.2~0.3, the growth rate is not more than 0.1, that is, the learning resources recommendation algorithm proposed in this paper has high stability, the best recommendation performance, and can be good for students to recommend learning resources. This paper's algorithm optimizes the CNN network of higher vocational English teaching quality evaluation model on the test set of data evaluation error is not greater than 0.01, compared with the evaluation error of other evaluation model methods is smaller. From the experimental results, it can be concluded that the algorithm in this paper is highly accurate and less time-consuming, and can effectively evaluate the quality of English teaching in higher vocational English education.