A Semantically Enhanced Knowledge Discovery Method for Knowledge Graph Based on Adjacency Fuzzy Predicates Reasoning

Discover the deep semantics from massively structured data in knowledge graph and provide reasonable explanations are a series of important foundational research issues artificial intelligence. However, hidden between entities cannot be well expressed. Moreover, considering many predicates express fuzzy relationships, existing reasoning methods effectively deal with these interpret corresponding process. To counter above problems, this article, new interpretable schema is proposed by introducing theory. The presented method focuses on analyzing semantic related graph. By annotating features adjacency predicates, novel model designed to realize extension over evaluation, based both visualization query experiments, shows that proposal has advantages initial can discover more valid information.