Building and Using a Supply Chain Knowledge Graph applied to the rail transit industry

In recent years, data-driven research in specific vertical fields has gained tremendous momentum. There is a huge amount of supply chains data spread across the enterprise information systems and web that we can use to build knowledge graphs. For the rail transit industry, the knowledge graph can systematically, structure and integrate the basic facts of the rail transit field, and it is also a powerful tool for storing, querying, and processing big data. However, analyzing these data to build knowledge graphs is difficult due to the heterogeneity of the sources and scale of the amount of data. This article proposes an approach to building supply chain knowledge graph by exploiting semantic technologies to reconcile the data continuously crawled from diverse sources and to support interactive queries on the data and further assist decision-making. The graph realizes the reconstruction and storage of important data, and uses Neo4j to realize the visualization of the graph. Case studies on a realistic example have shown that the approach has major potential in building supply chain knowledge graph, therefore improving the supply chain performance of the rail transit industry.