Since feed has a significant relationship between production and quality in cattle breeding, ICT systems are used for precise management and design. However, the feed names differ depending on the competent authority and feed information, and it is not easy to integrate and data between systems. This paper proposes and develops an ontology for cattle feed that becomes the guideline for data integration between farm ICT systems.

In this study, in order to support the construction of domain ontologies, we propose a methodology for extracting target domain concepts from a large-scale public Linked Open Data (LOD) system. In the proposed method, we obtain the class-related hierarchy of the domain concept by the occurrences of common upper entities and the chain of those path relationships. As an example of class hierarchy extraction from LOD, we describe the construction of a domain ontology for polymeric materials using Wikidata.

In the world of knowledge graphs, only the written word is considered to be a fact. However, many knowledge graphs expressed in RDF are incomplete, and knowledge graph embedding and graph neural networks are used to compensate for the incompleteness. In this paper, we propose a query language, TranSPARQL, which is an extension of SPARQL to enable RDF fuzzy search using these neural network-based link predictions. One predictor can be described by a variable in the pattern of subject, property and object in TranSPARQL. And we describe two implementations, one using TransE for link prediction and the other a hybrid implementation using both TransE and graph neural networks.