语义扩展技术在敏感数据识别中的应用研究
|
摘要
为了解决用户在敏感内容检测时给定关键词较少的问题,在此提出一种基于语义扩展技术识别敏感数据的方法。主要是通过对用户给定的关键词,进行基于搜索引擎、百度百科以及搜索引擎结果页面三种模式的语义扩展,然后借助少量人工方式整体评价,得到用户所需的扩展词。实验结果表明,与语义扩展之前相比,语义扩展之后敏感数据识别的准确率P、召回率R和评价值F均有所提高,说明该方法能够有效地提高敏感数据识别结果的全面性和准确性。
To solve the problem of less key words given in sensitive content inspection,a sensitive data identification method based on semantic extension approach is proposed. The semantic extension based on three forms of search engine,Baidu Encyclopedia and results page of searching is performed through the keywords given by users,by which the extension words is obtained through the overall evaluation in a manual way. The experimental result shows that,with the three forms of semantic extension,the accuracy P,recall R and evaluation value F of sensitive data identification have all been improved,which illustrates that the approach can effectively improve the comprehensiveness and accuracy of sensitive data identification.
To solve the problem of less key words given in sensitive content inspection,a sensitive data identification method based on semantic extension approach is proposed. The semantic extension based on three forms of search engine,Baidu Encyclopedia and results page of searching is performed through the keywords given by users,by which the extension words is obtained through the overall evaluation in a manual way. The experimental result shows that,with the three forms of semantic extension,the accuracy P,recall R and evaluation value F of sensitive data identification have all been improved,which illustrates that the approach can effectively improve the comprehensiveness and accuracy of sensitive data identification.
引文
[1]李伟伟,张涛,林为民,等.基于文本内容的敏感数据识别方法研究与实现[J].计算机工程与设计,2013,34(4):1202-1206.
[2]林臻彪.基于数据流分析的防文件网络泄露关键技术研究[D].郑州:解放军信息工程大学,2009.
[3]付义军.语义扩展的认知机制[J].青春岁月,2013(15):121.
[4]黄名选,严小卫,张师超.查询扩展技术进展与展望[J].计算机应用与软件,2007,24(11):1-4.
[5]FRANZEN K,KARLGREN J.Verbosity and interface design[R].Sweden:Swedish Institute of Computer Science(SICS),2000.
[6]徐建斌,施亚东.基于概念的文本自动分类研究的综述[J].福建电脑,2005(2):2-4.
[7]汪晨,邓松,张涛,等.智能电网环境下用户行为可信数据安全交换研究[J].现代电子技术,2014,37(1):75-79.
[2]林臻彪.基于数据流分析的防文件网络泄露关键技术研究[D].郑州:解放军信息工程大学,2009.
[3]付义军.语义扩展的认知机制[J].青春岁月,2013(15):121.
[4]黄名选,严小卫,张师超.查询扩展技术进展与展望[J].计算机应用与软件,2007,24(11):1-4.
[5]FRANZEN K,KARLGREN J.Verbosity and interface design[R].Sweden:Swedish Institute of Computer Science(SICS),2000.
[6]徐建斌,施亚东.基于概念的文本自动分类研究的综述[J].福建电脑,2005(2):2-4.
[7]汪晨,邓松,张涛,等.智能电网环境下用户行为可信数据安全交换研究[J].现代电子技术,2014,37(1):75-79.