基于RDF重写的航空安全事件因果关系查询方法研究  

Research on aviation security event causality query method based on RDF rewriting

作　　者：王红[1] 杨蓉 郭静 WANG Hong;YANG Rong;GUO Jing(School of Computer Science and Technology,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]中国民航大学计算机科学与技术学院

出　　处：《现代电子技术》2019年第16期149-153,158,共6页Modern Electronics Technique

基　　金：国家自然科学基金资助项目：基于跨媒体网络大数据的民航突发事件应急决策语义服务关键技术研究(U1633110)~~

摘　　要：针对航空安全事件RDF图数据因果关系查询中低匹配和无匹配的问题,提出一种基于语义相似度和RDFS规则的重写方法。该方法首先采用基于词向量的语义相似度计算方法将用户RDF三元组转换为领域本体RDF三元组,然后依据RDFS规则对领域本体RDF三元组进行关系扩展重写,最后将该方法应用于航空安全事件因果关系的查询。实验结果表明,该方法在查全率和查准率方面取得明显效果,能够改善因果关系查询中低匹配和无匹配的问题,为解决航空安全事件因果关系的查询问题提供了方法支持。A rewriting method based on semantic similarity and RDFS rules is proposed to solve the low matching and no matching problems existing in the causality query of RDF graph data in aviation security events.In this method,the semantic similarity calculation method based on word vector is used to convert the user RDF triple into domain ontology RDF triple,and then relationship extension and rewriting of the domain ontology RDF triple are conducted according to the RDFS rules.Finally,the method is applied to causality query in aviation security events.The experimental results show that the method has achieved obvious results in the aspects of recall rate and precision rate,and can solve the problems of low matching and no matching in causality query,which provides approach support for solving the problem of causality query in aviation security events.

关 键 词：因果关系查询 关系重写 航空安全事件 语义相似度计算 查询效果分析 查询语句扩展 

分 类 号：TN919-34[电子电信—通信与信息系统] TP391.1[电子电信—信息与通信工程]