航空不安全事件知识图谱构建  

Construction of Knowledge Graph for Aviation Unsafe Events

作　　者：许雅玺[1] 孟天宇 王欣 刘炳南 XU Ya-xi;MENG Tian-yu;WANG Xin;LIU Bing-nan(School of Economics and Management,Civil Aviation Flight University of China,Guanghan 618307,China;Sichuan Tengdun Technology Co.,Ltd.,Chengdu 610037,China;School of Computer Science,Civil Aviation Flight University of China,Guanghan 618307,China;Air China Limited,Chongqing 401120,China)

机构地区：[1]中国民用航空飞行学院经济与管理学院,广汉618307 [2]四川腾盾科技有限公司,成都610037 [3]中国民用航空飞行学计算机学院,广汉618307 [4]中国国际航空股份有限公司,重庆401120

出　　处：《科学技术与工程》2024年第32期13925-13934,共10页Science Technology and Engineering

基　　金：中央高校基本科研业务费专项(J2022-048);民航飞行技术与飞行安全重点实验室自主研究项目(FZ2022ZZ01)。

摘　　要：面向构建航空不安全事件知识图谱,开展知识图谱信息抽取技术研究。分析清洗航空不安全事件原始数据,构建航空不安全事件实体关系抽取数据集和领域词典。当前知识图谱中实体关系抽取的主要问题是实体边界获取困难和关系分类精度不高,鉴于此,提出融合领域词典嵌入的语义信息增强方法,进行领域实体关系联合抽取。以航空公司安全信息报告中的大量不安全事件记录为具体应用场景,对提出的知识图谱构建方法进行验证,实验分析提出的实体关系抽取算法的精确率和召回率指标,表明知识图谱构建方法的有效性。For the purpose of constructing a knowledge graph for aviation unsafe events,information extraction technologies are focused on for knowledge graph.A dataset for entity relationship extraction and a domain dictionary have been constructed by analyzing and cleaning aviation unsafe events raw data.The major challenges in entity relationship extraction for knowledge graph are determining entity boundaries and improving relationship classification accuracy.In view of this,a semantic information augmentation method that integrated domain dictionary embedding was proposed for domain entity and relationship joint extraction.The proposed knowledge graph construction method was validated for the scenario of numerous unsafe event recordings in airline safety information reports.Experiments demonstrate the effectiveness of the knowledge graph construction method by analyzing the precision and recall metrics of the proposed entity relationship extraction algorithms.

关 键 词：航空不安全事件 知识图谱 领域词典 实体关系抽取 预训练语言模型 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]