摘要
个性化搜索力求为用户提供最贴切的搜索结果,当前个性化搜索的挑战在于无法搜集足够的用户信息.对于用户信息不足的问题,一个有效的方法是利用具有相同搜索目的的其他用户的数据.通过挖掘搜狗提供的搜索日志,研究各种群组.提出了一种基于对IP地址聚类来扩充目的用户信息的个性化搜索算法,在提高搜索体验方面做了有效的工作.对应于传统的"个性化搜索",称之为"群体搜索".通过对用户的搜索行为进行分析验证,本算法在提高个性化搜索的效果方面是可行的、高效的.
Personalized search ought to provide its user the most suitable search results.However,the current challenge of personalized search algorithm is that the search engine can not collect users＇ information as much as possible.The insufficient information for users becomes a problem,so an effective method is used to search the data of other people who have the same search purpose.From mining search log provided by Sogou,all kinds of groups are studied,then a novel personalized search algorithm based on the use of clustering IP address is proposed,which can augment enough information to the end user from other people who share the same query intent.A lot of work has done for improving the users＇ search experience.Corresponding to the trodational ＂Personalized Search＂,it also called ＂Groupization Search＂.By analysing the users＇ search behaviors and performing experiments,it showed that the method is available and effective for improving the personalized search results.
出处
《河南理工大学学报（自然科学版）》
CAS
2010年第1期131-134,共4页
Journal of Henan Polytechnic University（Natural Science）
关键词
个性化搜索
IP地址聚类
群组
群体搜索
personalized search
IP address clustering
group
groupization search
