Development of Domain Knowledge Graph: A Case Study on Flotation Process

Abstract

A growing number of researches about knowledge graph have been studied and improved recently, but they are rarely applied in industries. At present, due to the lack of data and the scattered knowledge distribution in industry, constructing industrial domain knowledge graph is expensive and of low quality. This paper proposes a domain knowledge graph construction framework based on multi-source knowledge extraction, entity disambiguation, relation completion, and assisted decision-making, taking the flotation process as a case to study. Firstly, design the ontology layer of the flotation field, obtain corpus by crawling technology according to key words, and complete knowledge extraction. Secondly, use similarity calculation to entity disambiguation. Finally, apply the domain knowledge graph to achieve industrial applications, such as intelligent recommendation and assisted-decision in the flotation process.