Knowledge Extraction and Application for Metal Materials Based on DBpedia

Linked data is developing very fast and becoming more and more important in different domains. As a relatively-comprehensive linked data set, DBpedia contains billions of triples, which involves knowledge from diverse domains. This paper aims to utilize the metal materials knowledge in DBpeida to provide more useful services for materials experts. A knowledge extraction algorithm is designed to extract metal materials knowledge from DBpedia into a local knowledge base. Then, we develop an experimental prototype for metal materials information recommendation based on semantic distance calculation. The experimental results show that the system can help users retrieve metal knowledge originated from DBpedia rapidly and conveniently.