首页 | 本学科首页   官方微博 | 高级检索  
     检索      

P2P网络资源搜索中的用户行为模型
引用本文:钱宁,胡永东,吴国新.P2P网络资源搜索中的用户行为模型[J].东南大学学报(自然科学版),2011,41(4):706-710.
作者姓名:钱宁  胡永东  吴国新
作者单位:东南大学计算机网络和信息集成教育部重点实验室,南京210096;东南大学计算机科学与工程学院,南京210096
基金项目:国家高技术研究发展计划(863计划)资助项目(2007AA01Z422)
摘    要:为了改善P2P网络的搜索性能,提出应用马尔可夫链预测用户兴趣集合的方法.根据用户的历史查询行为,对关键词进行聚类,得到相关的兴趣类;应用马尔可夫链,建立用户行为模型,描述用户兴趣的时序变化;根据极限概率,预测用户达到平稳状态时的兴趣集合;给出根据模型进行预测的方法.实验表明,模型的命中率受查询序列分布的影响较大,增加兴...

关 键 词:P2P网络  用户行为  马尔可夫链  极限概率

User behavior model for search in peer-to-peer networks
Qian Ning,Hu Yongdong,Wu Guoxin.User behavior model for search in peer-to-peer networks[J].Journal of Southeast University(Natural Science Edition),2011,41(4):706-710.
Authors:Qian Ning  Hu Yongdong  Wu Guoxin
Institution:Qian Ning Hu Yongdong Wu Guoxin(Key Laboratory of Computer Network and Information Integration of Ministry of Education,Southeast University,Nanjing 210096,China)(School of Computer Science and Engineering,China)
Abstract:To improve search performance in P2P networks,a novel method based on Markov chain is proposed to predict interests of peers.Firstly,based on past queries,Key words are clustered and interests related to peers are obtained.Then,a user behavior model is established using Markov chain to describe the changes of user's interests over time.Finally,limiting probability is employed to predict user's interests in the future.The predicting method based on this model is also presented.Experimental results demonstrat...
Keywords:peer-to-peer networks  user behavior  Markov chain  limiting probability  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号