Application of Graph Convolutional Network in the Construction of Knowledge Graph for Higher Mathematics Teaching

Abstract

In this study, we first perform data preprocessing using higher mathematics textbooks and network resources to complete the construction of the dataset extracted from the knowledge of this mathematical discipline in order to study the application of a graph neural network in the knowledge graph (KG) of higher mathematics. Then, the graph convolutional network (GCN) and attention mechanism are introduced, and the relationship extraction model based on attention-guided GCN and the text classification model based on GCN are established, whereby the automatic extraction of higher mathematical knowledge can be realized. Finally, sensors are used to collect data from students' classroom responses, the data layer construction of a subject KG is realized, and the database is used to realize the storage visualization of triples. The results show that on the basis of the text classification model of GCN, higher mathematical knowledge classification is set, providing a reference example for the application of GCN in higher education. The constructed higher mathematics atlas has a total of 2580 triples, which can be used on the higher mathematics visual query platform. The self-built recognizer recognition test set obtains a P-value of 89.16% in the higher mathematics theorem law entity and a P-value of 97.73% in the test question of higher mathematics. Therefore, the GCN model established here can be effective in the construction of higher mathematical KGs.