“Online + Offline” Hybrid Teaching Model in the Post Epidemic Era Based on Deep Reinforcement Learning

• Published in: Multimedia Technology and Enhanced Learning Vol. 446; pp. 112 - 126
• Main Authors: Liang, Shaolin, Su, Pei
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer 2022; Springer Nature Switzerland
• Series: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
• Subjects: Deep reinforcement learning; Domain knowledge unit; Learner unit; Mixed teaching model; Online + offline; Post epidemic era
• ISBN: 3031181220; 9783031181221
• ISSN: 1867-8211; 1867-822X
• DOI: 10.1007/978-3-031-18123-8_9

In order to achieve students’ in-depth understanding of the teaching content, in the post-epidemic era, an “online + offline” hybrid teaching model based on deep reinforcement learning has been designed. First, the basic data is preprocessed to remove interfering data and convert it into a form that can be directly used by the model. In the domain knowledge unit of the model, on the basis of determining the composition of the domain knowledge elements and their associated relationships, a structure in which the superordinate relationship and the subordinate relationship, the predecessor relationship and the successor relationship coexist is constructed; in the learner unit of the model, the deep reinforcement determines Based on the learning source, a block-based data management mechanism is established to jointly promote the operation of the model. The experimental results show that the “Online + offline” hybrid teaching model in the post epidemic era based on deep reinforcement learning has good performance and can achieve good teaching results.