煤矿安全知识图谱构建及智能查询方法研究  

Coalmine Safety:Knowledge Graph Construction and Its QA Approach

作　　者：刘鹏 叶帅 舒雅 鹿晓龙 刘明明 LIU Peng;YE Shuai;SHU Ya;LU Xiaolong;LIU Mingming(National and Local Joint Engineering Laboratory of Internet Application Technology of Mines,Xuzhou,Jiangsu 221008,China;NetPosa Technologies Co.Ltd.,Wuhan,Hubei 430070,China;School of Information and Control Engineering,China University of Mining and Technology,Xuzhou,Jiangsu 221116,China;School of Intelligent Manufacturing,Jiangsu Vocational Institute of Architectural Technology,Xuzhou,Jiangsu 221008,China)

机构地区：[1]矿山互联网应用技术国家地方联合工程实验室,江苏徐州221008 [2]东方网力科技股份有限公司,湖北武汉430070 [3]中国矿业大学信息与控制工程学院,江苏徐州221116 [4]江苏建筑职业技术学院智能制造学院,江苏徐州221008

出　　处：《中文信息学报》2020年第11期49-59,共11页Journal of Chinese Information Processing

基　　金：十三五国家重点研发计划(2017YFCO804401);国家自然科学基金(61801198);江苏省自然科学基金(BK20180174);淄矿智慧矿山开放基金(2019lh10)。

摘　　要：煤矿企业正从信息化建设向智能化迈进,以大数据、人工智能为代表的网络新技术已促进了矿山领域的智能化发展。但是由于煤矿领域数据信息的繁杂性,难以对其进行统一而高效地收集、信息挖掘,进而促进深一步的特定领域研究和应用。将知识图谱技术初步引入煤矿安全领域,对相关知识概念分类建模,并基于图数据库存储,用实体关系图的方式直观地描述各类概念及概念之间的关系,然后基于初步构建的知识图谱,提出了一种自然语言知识查询方法。实验证明,该文提出的方法具有较高的查全率和查准率,基于Spark的并行朴素贝叶斯问题分类方法可以在保证准确率的同时,显著提升训练效率。该文工作为煤矿安全知识图谱构建及智能查询做了初步有益探索。Coal mining enterprises are developing beyond information construction into intelligence era,motivated by new network technologies like big data and artificial intelligence.In this paper,knowledge graph is introduced into the domain of coalmine safety.The domain knowledge concept is first classified,stored in the graph database,and visually presented for its concept relations.Then,to facilitate the query search over this knowledge graph,a question classification approach is implemented to identify the best query types for a specific question.The experiment results show that the proposed entity extraction method has higher scores on recall and precision,and the Spark-based parallel question classification algorithm significantly improves efficiency while ensuring the accuracy.

关 键 词：煤矿安全 知识图谱 实体识别 知识查询 SPARK 朴素贝叶斯 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]