Application of user behavior recognition based on edge computing resource allocation in English online teaching

In recent years, task offloading and resource allocation schemes in edge computing systems have received extensive attention from scholars, but many of them only focus on static offloading schemes without considering long-term performance. In order to optimize the long-term average performance, the randomness of task arrival, the dynamic changes of wireless channels and the dynamics of terminals, making the research on dynamic unloading and resource allocation full of challenges. In order to improve the accuracy of user behavior identification, this paper summarizes the theory of mobile edge computing, discusses the technical theory of task loading in MEC systems, and further expands the research on MEC servers. This paper proposes a deep learning system based on SDAL-DNM, which uses edge computing to generate user behavior data and target user behavior data in the same space, constantly narrowing the distance between the characteristics of user behavior data, and the deep network adjusts itself to be as close to user behavior data as possible, and improves the accuracy of user behavior. Therefore, the resource allocation method of mobile edge computing in this paper summarizes the background and importance of user behavior recognition in the application of English online teaching, and then introduces several specific examples of online teaching platforms. Therefore, this paper summarizes the guiding ideology of the design of a network English teaching platform.