A Hybrid Reasoning Method of Knowledge Graph for On-line Arts Education based on Reinforcement Learning

Abstract

With the popularization of online education mode, online arts education has entered the public field of vision. However, due to the non-systematic and non-standard art teaching at home and abroad, there is still a huge room for improvement in its scale and knowledge system. In this paper, a hybrid reasoning method of knowledge graph based on Reinforcement Learning - Multi relational GCN reasoning combined with reinforcement learning (RL-URGCN) is introduced, which uses the knowledge reasoning technology to mine the knowledge standardization. The scattered knowledge can be formed into a relational and structured knowledge system, so as to improve the learning efficiency and promote the teaching process in the process of art education.