To further construct the structure of MGED-KG, terms classification was first achieved. Materials category labels were assigned to each term entity determined by the catalog of ‘Material Dictionary’. The terminology classification is hierarchical in three levels, with a total of 235 category labels.
MGED-KG was used to complete and standardize user input automatically, and significantly improve the user experience when retrieving material term. It analyzes the user's query and utilizes relevant semantics, context, or other related information to automatically recommend or provide additional query terms or terms.
The terminology recommendation feature aims to enhance information retrieval and knowledge acquisition in the materials domain. This feature leverages the material terminology knowledge graph, which we have constructed, to automatically complete and standardize user input and provide a list of related terms.
MGED-KG has been embedded into National Materials Data Management and Service platform (NMDMS) to construct the correlation between data instances, which help realize the data recommendation during data retrieval and accelerate the valuable data discovery efficiently.