期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
期号：MULTICON
页码：321
出版社：S&S Publications
摘要：In web search, there are many techniques used extensively for effective retrieval of information from theweb server. A user query entered into the search engine may return large number of web page results and thus, itbecomes extremely important to rank these results in such a manner that it returns accurate and more relevant webresults. These tasks of prioritizing the results are performed by ranking algorithms. But the search interest of every userdiffers with every other user uniquely. In existing system, the search engine that return results for a given user query isnot uniquely based on their earlier searching behavior. Hence there may be return of web page results that are least usedor accessed by the user. These results need to be filtered or less prioritized by the ranking algorithm. In our proposedsystem, the personalization of user search activities is taken to find search interest of each user. This personalization ofuser search behavior is done by storing user activities and analyzing web log by clustering frequently accessed tasks bysemantic task clustering algorithm and dynamically ranks web results. In this project we can also extend our workinclude web image search with personalization and remove duplication keywords. It can be achieved using imagefeatures approach and top k answering techniques. Implement this approach in real time search engine environment.
