网络灰色信息智能获取与分析

发布时间：2018-06-17 10:21

本文选题：灰色信息 + 智能获取　；参考：《中国人民公安大学学报(自然科学版)》2016年02期

【摘要】：网络灰色信息多属于互联网上离散分布的半公开化潜在数据资源,通过总结网络灰色信息的价值性与综合特征可知,依靠常规搜索引擎较难获得可用性高的灰色信息资源集。为获取更宽泛的网络灰色信息存在轨迹,提出了以广度优先搜索为主的信息爬取技术架构并建立索引数据库,在此基础上,将语义相似度与置信度约束融入主题关联二次搜索,以获得理想挖掘结果;网络信息流强度概念的引入,揭示出网络媒体资源对社会决策的影响程度,并在股票涨跌幅与网络关注度的关联实例中得到验证。
[Abstract]:The grey information of the network mostly belongs to the semi-open potential data resources of the discrete distribution on the Internet. By summarizing the value and comprehensive characteristics of the grey information on the network, it is difficult to obtain the highly available grey information resource set by relying on the conventional search engine. In order to obtain a broader network gray information track, this paper puts forward an information crawling architecture based on breadth-first search and establishes an index database. On this basis, the semantic similarity and confidence constraints are incorporated into the topic association quadratic search. With the introduction of the concept of network information flow intensity, the degree of influence of network media resources on social decision-making is revealed, which is verified by an example of the correlation between the stock price and decline and the network concern.
【作者单位】：中国人民公安大学网络安全保卫学院;
【基金】：中国人民公安大学2015年度中央高校基本科研业务费项目“网络灰色信息智能分析技术及相关法律问题研究”(2015JKF01113)
【分类号】：TP391.3

【相似文献】