基于用户兴趣与隐私保护的网络信息资源个性化推荐技术  

The Personalized Recommendation Technique of Network Information Resources Based on User Interests and Privacy Protection

作　　者：付达杰[1] 张小波[1] 

机构地区：[1]江西财经职业学院信息工程系,江西九江332000

出　　处：《景德镇学院学报》2015年第6期42-45,共4页Journal of JingDeZhen University

基　　金：江西省自然科学基金项目--网络信息资源个性化推荐若干关键技术研究(20142BAB207030)

摘　　要：在网络信息资源个性化推荐技术当中,协同过滤算法是使用最广泛的,但传统的协同过滤算法在对用户的兴趣数据集的选取上不够有效,而且对于用户的隐私兴趣没有给予相应的保护。针对传统协同过滤算法的不足,本文对其做出了改进,引入公共集过滤噪音数据,结合k-匿名方法,隐匿隐私数据。最终的实验数据表明了改进后的算法在提高推荐准确率的基础上,用户的隐私得到了一定的保护。Among the personalized recommendation techniques of network information resources,collaborative filtering algorithm is the most popular. However,the traditional collaborative filtering algorithm lacks an effective method to choose the data set of user interests. And there is nothing to do with the user privacy protection. Aiming at the shortcomings of the traditional collaborative filtering algorithm,this paper has made an improvement to it. The paper introduces public set to filter noise data,combined with k- anonymous methods to hide privacy data. The experimental data show that the improved algorithm has protected user privacy on the basis of improving the accuracy of recommendation.

关 键 词：协同过滤 个性化推荐 隐私保护 噪音数据 

分 类 号：TP393.6[自动化与计算机技术—计算机应用技术]