College computer basic knowledge problem solving method based on deep learning

• Main Authors: LIU YAOLIN, LIU RUI, LYU HONGJIN, FENG LINLIN, ZHANG JINYUAN, LIU XUHUA, HEI XINHONG, LIN HONG, ZHU LEI
• Format: Patent
• Language: Chinese; English
• Published: 28.08.2020
• Subjects: ADVERTISING; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND,DEAF OR MUTE; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; CRYPTOGRAPHY; DIAGRAMS; DISPLAY; EDUCATION; EDUCATIONAL OR DEMONSTRATION APPLIANCES; ELECTRIC DIGITAL DATA PROCESSING; GLOBES; PHYSICS; PLANETARIA; SEALS

The invention discloses a college computer basic knowledge problem solving method based on deep learning. An existing university computer basic knowledge graph and an NTN model are used for generatingan inference data set containing all basic knowledge points; then, a PCANET network and a GRU network are used for generating an incomplete knowledge graph corresponding to the problem; and then theapproximate sub-graph closest to the incomplete knowledge graph in the knowledge graph is matched by using a PSQUERY algorithm, inferring is performed to obtain a missing part in the incomplete knowledge graph by using a TransE method, and finally inferring is performed to obtain a part which is a correct result. And the manpower consumption is reduced, and the question solving efficiency is improved. The method is easy to implement, and answers can be generated in batches. According to the invention, the efficiency of students learning the class by themselves is improved, and the burden of teachers in teaching the cla