基于广告联盟的虚拟身份画像方法研究

RESEARCH ON VIRTUAL IDENTITY PORTRAIT METHOD BASED ON ADVERTISEMENT ALLIANCE

目前,网络虚拟账号繁多,大多数账号无需实名认证便可使用,这样不利于网络空间的安全维护与监管。针对这一情况,提出一种以虚拟账号为属性的网络空间身份画像方法。该方法首先利用大数据预处理技术实现从无关联的http post数据提取网络虚拟账号;然后,基于广告联盟机制,利用页面标签技术中Cookie存储用户唯一ID,将虚拟身份进行关联绑定与关联分析,进而构建虚拟身份画像原型;最后通过相似度计算方法,完成相似画像原型的重组。实验结果表明,该方法能有效刻画网络空间身份。

At present,the network virtual account is too numerous,most accounts do not need real-nameauthentication can be used. This is not conducive to the safety of network space maintenance and supervision. Aiming at this situation, this paper presents a network space identity portrait method with virtual account as attribute. The method first uses the big data preprocessing technique to extract the network virtual account from unrelated http post data; then, based on the mechanism of advertising alliance, this paper uses the cookie ID of the page tag technology to store the user unique ID, and the virtual identity is correlated with the binding analysis and then the virtual identity prototype is constructed; finally, the portrait of similar prototype is completed by the similarity calculation. The experimental results show that the method can effectively depict the identity of network space.