Page 230 - 《爆炸与冲击》2026年第5期
P. 230

第 46 卷    第 5 期                   爆    炸    与    冲    击                       Vol. 46, No. 5
                2026 年 5 月                    EXPLOSION AND SHOCK WAVES                          May, 2026

               DOI:10.11883/bzycj-2025-0329


                                   意外爆炸毁伤知识图谱研究                                     *


                                         王继民 ,姜    灿 ,韩    斌 ,王    幸 ,张    磊  2,3
                                                       1
                                                                      2,3
                                               1
                                                              1
                                        (1. 河海大学计算机与软件学院,江苏 南京 211100;
                                       2. 目标易损性评估全国重点实验室,河南 洛阳 471023;
                                   3. 军事科学院国防工程研究院工程防护研究所,河南 洛阳 471023)

                  摘要: 利用具有多源、异构、重叠等特征的爆炸事故调查报告建立意外爆炸毁伤知识图谱,对进行数据驱动的爆
               炸评估以及溯源具有重要作用。针对意外爆炸事故调查数据中存在重叠和嵌套事件的特点,采用以事件联合抽取为
               核心的知识图谱构建方法以及爆炸调查报告构建了意外爆炸毁伤知识图谱;通过余弦相似度在知识图谱中检索类似
               爆炸事件并采用贝叶斯分类方法进行分类,较准确地实现了对贝鲁特港口爆炸事故爆炸源物资种类的确定。知识图
               谱构建结果表明,在意外爆炸毁伤语料库上的事件分类以及事件元素分类分析表明,相较于现有抽取模型,提出的基
               于动态掩码的事件联合抽取方法的             F 1 值分别提高至少    2%  和  5.4%。溯源分析表明,基于知识图谱的溯源与传统的人
               工溯源相比,其速度和准确性都有较大的提高。
                  关键词: 意外爆炸;知识图谱;事件抽取;爆炸溯源
                  中图分类号: O389   国标学科代码: 13035   文献标志码: A

                     Research on the knowledge graph of accidental explosion damage


                                                               1
                                                                           2,3
                                                      1
                                           1
                               WANG Jimin , JIANG Can , HAN Bin , WANG Xing , ZHANG Lei 2,3
                    (1. College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, Jiangsu, China;
                           2. State Key Laboratory of Target Vulnerability Assessment, Luoyang 471023, Henan, China;
                            3. Institution of Engineering Protection, IDE, AMS, PLA, Luoyang 471023, Henan, China)
               Abstract:  Constructing a knowledge graph for accidental explosion damage using investigation reports of explosion accident
               characterized by multi-source, heterogeneous, and overlapping information plays a significant role in data-driven explosion
               assessment and traceability analysis. To address the overlapping and nested events in accidental explosion investigation data, a
               knowledge  graph  construction  method  centered  on  event  joint  extraction  was  employed,  utilizing  explosion  investigation
               reports  to  build  the  accidental  explosion  damage  knowledge  graph.  By  retrieving  similar  explosion  events  within  the
               knowledge  graph  using  cosine  similarity  and  applying  a  Bayesian  classification  method,  the  type  of  explosive  materials

               involved in the Beirut port explosion incident was identified with relatively high accuracy. The knowledge graph construction
               results  demonstrate  that  on  the  accidental  explosion  damage  corpus,  the  proposed  dynamic  masking-based  event  joint
               extraction method improved the F  scores for event classification and event element classification by at least 2% and 5.4%,
                                        1
               respectively, compared to existing extraction models. Traceability analysis indicates that knowledge graph-based traceability
               offers significant improvements in both speed and accuracy compared to traditional manual traceability methods.
               Keywords:  accidental explosion; knowledge graph; event extraction; explosion traceability




                 *   收稿日期: 2025-09-30;修回日期: 2026-02-02
                   基金项目: 国家自然科学基金(12172381)
                   第一作者: 王继民(1976- ),男,硕士,副教授,wangjimin@hhu.edu.cn
                   通信作者: 张 磊(1974- ),男,博士,研究员,ustczhanglei@163.com


                                                         051444-1
   225   226   227   228   229   230   231   232   233   234   235