面向军事领域的Web开源情报主题挖掘研究  

Study of Web Open Source Intelligence Topic Mining in Military Domain

作　　者：黄胜[1] 郭继光[1] 陆泽健[1] 陈龙[1] 潘越[1] HUANG Sheng GUO Ji-guang LU Ze-jian CHEN Long PAN Yue(China Academy of Electronics and Information Technology, Beijing 100041, China)

机构地区：[1]中国电子科学研究院,北京100041

出　　处：《中国电子科学研究院学报》2017年第4期400-405,共6页Journal of China Academy of Electronics and Information Technology

基　　金：电子信息装备体系研究国防科技重点实验室基础研究项目(DXZT-JC-ZZ-2011-015)

摘　　要：针对军事领域海量Web开源情报的有效分析和利用问题,提出了一种基于主题聚类的开源情报挖掘方法。基于网络爬虫从Web上自动搜集军事开源情报数据,通过解析Web网页内容提取重要情报要素,采用层次聚类算法自动生成情报主题。最后,通过实际Web数据对军事开源情报主题生成效果进行评估。实验结果表明该方法在情报主题聚类熵值、纯度和算法运行时间上均具有良好的表现。Aiming at the demand of effective analysis and utilization of the massive military open source intelligence on the Web,this paper proposes a topic clustering based method for automatic open source intelligence mining. The method utilizes web crawler to collect relevant military open source intelligence data from multiple Web sources,and extracts the important intelligence elements by parsing Web pages,then employs the Chameleon hierarchical clustering algorithm to generate intelligence topic automatically.At last,experimental evaluation of the effectivity and efficiency of this method using the real Web data was conducted. The experiment results demonstrated that this method has improved the entropy,purity and algorithm runtime of military open source intelligence topic generation effectively.

关 键 词：军事领域 Web开源情报 情报主题 层次聚类 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]