PERFORMANCE EVALUATION OF CLUSTERING IN WEB-LOG ANALYSIS BASED ON AGENT

Web mining is the use of data mining Technique toautomatically discover & extract information from webdocuments. When user searches for goods the managementagent receives order from graphical user interface.Management agent receives information, update agentinformation store house and feedback the mining result touser. Intelligent agent can help making computer systemeasier to use, enable finding & filtering information. Themining agent is the analytical center of whole agentsystem.It mainly adopts two kind of analytical method:related rule mining and cluster analysis. Cluster of objectsare formed so that objects with in a cluster have highsimilarity. The aim of this paper is to analyze the web logdata .To achieve this clustering tool is used. It performs intwo phases. First it captures the web-log data. Then itanalyzes the data& discovers the hidden pattern. Agentrequires an agent communication language to describe &process agent request. The future internet will use PERL toencode information with meaningful structure & semantics.