Abstract: Web search is considered the mainly valuable place for information retrieval and knowledge discovery. Web is ever more used not only to find answers to specific information needs but also to carry out various tasks, attractive the capability of current web search engines with effective and resourceful techniques for web service retrieval and selection becomes an important issue. Existing web search result based on keyword matching in single search engine only it will not give accurate result of the query. The Proposed system efficient multiple web search results based on probability clustering system that enhances search results performance (i) multi search engine method is lists of web results returned by user queries to search engines. Ii) Probability k means cluster using search results term based cluster based on this approach, in this system, a mechanism is being proposed that provides ordered results in the form of likelihood based clusters in agreement with users query. An efficient cluster method is also proposed that orders the results according to both the relevancy and the importance of web results. Web search result clustering has been emerged as a method which overcomes this problem of conventional information retrieval (IR) machine. It is the probability clustering of results returned by the search engines into meaningful, thematic groups. This paper gives a succinct overview and categorizes various techniques that have been used in clustering of web search results.

Keywords: web mining; Information Retrieval (IR); Clustering; Ranking; Text mining; web search engine.