计算机科学 ›› 2015, Vol. 42 ›› Issue (4): 156-159.doi: 10.11896/j.issn.1002-137X.2015.04.031

• 软件与数据库技术 • 上一篇    下一篇

基于PH-Tree多属性索引树的朋友推荐算法

梁俊杰,孙阳征   

  1. (湖北大学计算机与信息工程学院 武汉430062),(湖北大学计算机与信息工程学院 武汉430062)
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家发改委2012年信息安全专项(发改办高技[2013]1309号),湖北省自然科学基金重点项目(2013CFA115),武汉市科技攻关计划项目(2013012401010851)资助

Friend Recommendation Algorithm Based on PH-Tree Multi-attribute Index Tree

LIANG Jun-jie and SUN Yang-zheng   

  • Online:2018-11-14 Published:2018-11-14

摘要: 现阶段越来越多的人通过社交网络结识新朋友,如何为用户快速准确推荐朋友是考量平台服务能力的重要指标。提出了一种基于索引树的在线网络朋友推荐方法,即基于网络结构局部特性的思想将用户间的多属性相交值转换为二进制位码向量表示,利用改进后的PH-Tree将所有的向量构造成排序索引树,通过 遍历 索引树容易确定用户的最佳推荐朋友集。实验证明本方法具有较高的效率和准确率。

关键词: 社交网络,PH-Tree,索引,朋友推荐

Abstract: Nowadays,more and more people make new friends on online social networks (OSN),and it becomes an important feature for OSN to recommend friends for users rapidly and exactly.An online friend recommended algorithm was proposed using a sorted index tree based on local network structure.Multi-attribute intersection values between different users were converted into binary vectors and organized in PH-Tree.Thus a user’s best friend recommended set can be determined by travelling the index tree easily.The experiments show that our method performs efficiently and precisely.

Key words: Social networks,PH-Tree,Index,Friend recommendation

[1] Yin Z,Gupta M,Weninger T.A unified framework for link re-commendation with user attributes and graph structure [C]∥Proceedings of the 19th International Conerence on World Wide Web.New York,USA,2010,6:1200-1212
[2] Chen J,et al.Make new friends,but keep the old:Recommend ing people on social networking sites[C]∥Proceeding of the 27th International Conference on Human Factors in Computing Systems.New York:ACM,2009,2:201-210
[3] 付艳艳,张敏,冯登国,等.基于节点分割的社交网络属性隐私保护[J].软件学报,2014,5(4):768-780
[4] 余琰,邱广华.基于局部随机游走的在线社交网络朋友推荐算法[J].系统工程,2013,31(2):47-54
[5] Zaschke T,Zimmerli C,Norrie M C.The PH -Tree:A Space-Efficient Storage Structure and MultiDimen sional Index.Institute for information Systems[J].Department of Computer Science ETH Zu rich,Switzerland,2014,7:659-671
[6] Wolfe A W.Social network analysis:Methods and applications[J].Cambridge American Ethnologist,1997,24(1):210-230
[7] 印鉴,王智圣,李琪,等.基于大规模隐式反馈的个性化推荐[J].软件学报,2014,5(9):1953-1966
[8] German U,Joanis E,Larkin S.Tightly Packed Tries:How to Fit Large Models into Memory,and Make them Load Fast,Too[C]∥Proc.of the NAACLHLT Workshop.2009,8:31-39
[9] Leskovec J,Lang K J,Mahoney M.Empirical comparision of algorithms for network community detection [C]∥Proceedings of the 19th International Conference on World Wide Web.New York:ACM,2010,9:630-655
[10] 徐志明,李栋,刘挺,等.微博用户的相似性度量及其应用[J].计算机学报,2014(1):207-218
[11] 贾大文,曾承,彭智勇,等.一种基于用户偏好自动分类的社会媒体共享和推荐方法[J].计算机学报,2012(11):2381-2391
[12] 张丰,王箭,赵燕飞,等.社交网络中一种基于社区推荐的信任模型[J].计算机科学,2014,1(5):168-172
[13] 王玙,高琳.基于社交圈的在线社交网络朋友推荐算法[J].计算机学报,2014(4):801-808
[14] Alan M,Massimiliano M,Krishnap G,et al.Bhattacharjcc Bobby,Mcasurement and analysis of online social network[C]∥Proccedings of the 7th ACM SIGCOMM Conference on Internet Mcasurement.SanDiego,CA,USA,2007,5:29-45
[15] Chen Ke-han,Han Pan-pan,Wu Jian.User Clustering Based Social Network Recommentdation[J].College of Computer Science and Technology,2013,3:100-107
[16] Herlocker J.Evaluating collaborative filtering recom mendersystems[J].ACM Transactions on Information systens,2004,2(1):5-53
[17] 文俊浩,舒珊.一种改进相似性度量的协同过滤推荐算法[J].计算机科学,2014,1(5):68-71
[18] 高明,金澈清,钱卫宁,等.面向微博系统的实时个性化推荐[J].计算机学报,2014(4):963-975
[19] 海本斋,解瑞云.基于贝叶斯网络的上下文推荐算法[J].计算机科学,2014,1(7):275-278
[20] 朱宝,徐玲玉.一种个性化推荐方法[J].计算机科学,2014,1(11A):294-297

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!