Distant supervision knowledge extraction and knowledge graph construction method for supply chain management domain

Abstract

As the core competitiveness of the national industry, large-scale equipment such as ships, high-speed rail and nuclear power equipment, their production process involves in-depth personalization. It includes complex processes and long manufacturing cycles. In addition, the equipment’s supply chain management is extremely complex. Therefore, the development of a supply chain management knowledge graph is of significant strategic significance. It not only enhances the synergistic effect of the supply chain management but also upgrades the level of intelligent management. This paper proposes a distant supervision knowledge extraction and knowledge graph construction method in the supply chain management of large equipment manufacturing, which achieves digital and structured management and efficient use of supply chain management knowledge in the industry. This paper presents an approach to extract entity-relation knowledge using limited samples. We achieve this by establishing a distant supervision model. Furthermore, we introduce a fusion gate mechanism and integrate ontology information, thereby enhancing the model’s capability to effectively discern sentence-level semantics. Subsequently, we promptly modify the weights of input features using the gate mechanism to strengthen the model’s resilience and address the issue of vector noise diffusion. Finally, an inter-bag sentence attention mechanism is introduced to integrate different sentence bag information at the sentence bag level, which achieves more accurate entity-relation knowledge extraction. The experimental results prove that compared with the latest distant supervision method, the accuracy of relation extraction is improved by 2.8%, and the AUC value is increased by 3.9%, effectively improving the quality of knowledge graph in supply chain management.