In order to intelligently meet the business requirements of the SG-CIM model designed by the State Grid Corporation of China and improve the quality and sharing of the graph data, this paper proposes a graph structure mapping model based on gaph attention network(GAT). First of all, using the data of SG-CIM model, an SG-CIM knowledge graph and a database table knowledge graph are constructed. The entities embedding in each graph are learned separately through the GAN, which are then embeded into a unified vector space. Finally, the graph structure mapping results of the two graphs are obtained after calculating the similarities based on the distances between the entity vectors. Experiments show that the proposed model achieves good results in automatic mapping of SG-CIM model.

SG-CIM model  /  knowledge graph  /  graph attention network  /  knowledge graph mapping