计算机科学与探索

• 学术研究 •    

融合决策蕴涵的知识图谱推理方法

翟岩慧,何煦,李德玉,张超   

  1. 1.山西大学计算机与信息技术学院 太原 030006
    2.山西大学 计算智能与中文信息处理教育部重点实验室 太原 030006

Knowledge Graph Inference Method Combining with Decision Implication

ZHAI Yanhui, HE Xu, LI Deyu, ZHANG Chao   

  1. 1.School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China
    2.Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006, China

摘要: 决策蕴涵是形式概念分析中的决策知识表示和推理工具。本文提出了一种基于决策蕴涵的知识图谱关系补全方法。首先,基于知识图谱构建对应的决策背景,证明决策蕴涵可以等价表示知识图谱推理中的规则;为了快速挖掘决策蕴涵,对具有较高复杂度的决策背景进行多次约简,证明约简后的决策背景也可以获取知识图谱推理中的规则;设计了从简化后的决策背景中获取决策蕴涵的算法,给出了使用决策蕴涵进行关系补全的步骤;最后通过实验验证了上述方法的有效性。该研究为完成知识图谱关系补全任务提供了新的思路,也为融合推理提供了一个新的选择。

关键词: 形式概念分析, 决策蕴涵, 对象约简, 知识图谱, 关系补全

Abstract: Decision implication is a tool of decision knowledge representation and reasoning in Formal Concept Analysis.This paper proposed a relationship completion method for knowledge graph based on decision implication.To this end,we first constructed the corresponding decision context for a knowledge graph and proved that decision implications are able to equivalently represent the rules in knowledge graph inference.In order to efficiently extract decision implications, we reduce the decision contexts by many strategies and proved that the reduced decision contexts also contain the rules in knowledge graph inference.We also designed an algorithm to extract decision implications from the reduced decision contexts and provided the steps to perform relationship completion by applying decision implications. Finally, experiments verify the effectiveness of the proposed method. This study provides a new idea for completing knowledge graph relationship, as well as a new choice for fusion inference.

Key words: Formal concept analysis, decision implication, object reduction, knowledge graph, relation ship completion