Design and Application of English Smart Classroom Teaching Based on Deep Learning

As a product of the era of smart teaching, smart classrooms provide unlimited possibilities and potential for the development of teaching and have gradually become popular. In the context of educational informatization 2.0, how to stimulate students’ intrinsic motivation for self-learning and thus improve their deep learning ability has become an important direction for teaching practice exploration. Therefore, this study applies deep learning and smart classroom-related learning theories to smart classroom teaching to improve teaching effects. This paper explores how to use artificial intelligence technology to help teachers monitor the learning behavior status of learners in smart classrooms. First, through literature analysis, a classification system of learning behaviors in smart classrooms is summarized, which are nine types of learning behaviors: looking down at books, looking down at writing, looking up at lectures, raising hands to speak, standing up to answer, turning to look at others, abnormal behavior, group discussion, and teacher guidance. We use the DeepSORT algorithm to track the target and use the YOLOv5 target detection algorithm to train the labeled student behavior dataset to obtain a target detection model for detecting student behavior. The experimental results show that we use the YOLOv5 target detection algorithm for training to achieve good recognition results, with an average accuracy of 87.5% and 99%, respectively.