A Knowledge Graph Exploration Method with No Prior Knowledge

Abstract

Various sectors now widely adopt knowledge graphs to describe and share their organizational knowledge bases. Unfortunately, the majority of knowledge-sharing systems are designed for domain experts. Making it extremely difficult for a non-expert to understand the content and explore the graph. A solution to this issue is using a machine-assisted knowledge graph exploration approach. This research introduces a knowledge exploration method to systematically and efficiently navigate a knowledge graph. First, we modeled the knowledge graphs based on the existing common schema. Second, we created a search tree technique to navigate the knowledge graph efficiently. The algorithm solves the problem by determining the path of knowledge graph exploration. We evaluated the method using a knowledge base of morphological characteristics of Capsicum. The goal of graph exploration was to identify a Capsicum species correctly. As a result, the proposed mechanism can achieve high precision, even when the search’s starting point is unknown beforehand.