Knowledge Graph Construction for Supply Chain Management in Manufacturing Industry.

Knowledge graph technology is crucial in enhancing supply chain management (SCM) in the manufacturing industry. However, the existing SCM ontology knowledge suffers from coarse granularity, leading to reduced accuracy of knowledge extraction and making knowledge graph construction more challenging. A novel construction method for the SCM event logic knowledge graph (ELKG) is proposed to overcome these challenges. The proposed method includes constructing an event logic ontology and annotating the SCM dataset based on the ontology. Meanwhile, a knowledge joint extraction model FIBGN based on Bidirectional Graph Convolutional Network (BiGCN) and feature interaction between different spaces (BiGCN) is proposed. Experimental results show that this method can improve the effect of event argument entity and relation joint extraction and is better than other methods. Finally, the event logic knowledge graph of supply chain management in large-scale manufacturing fields is established, which provides decision support for the supply chain system.