ARCHITECTURE AND PERFORMANCE OF INTELLI-GENT SYSTEM

In this paper defined the heterogeneous agents that solve problems by sharing the knowledge retrieved from the WEB and cooperating among them for an intelligent system. The control structure of those agents is based on a general pur-pose Multi-Agent architecture based on a deliberative ap-proach. Any agent in the architecture is built by means of several interrelated modules: control module, language and communication module, skills modules, knowledge base etc. Basically the control module uses an agenda to activate and coordinate the agent skills for a best intelligent system. This agenda handles actions from both the internal goals of the agent and from other agents in the basic environment. In this paper describes how SKELETONAGENT has been used to implement different kinds of agents and a specialized for a Multi-Agent System. The implemented Multi Agent System is the specific implementation of a general WEB gathering architecture, named MAPWEB, which extends SKELETO-NAGENT. MAPWEB has been designed to solve the basic problems in WEB domains through the integration of infor-mation gathering and their resources planning techniques. The system which uses information gathered directly from several WEB sources (plane, train, and hotel Companies etc.) To solve travel problems. The proposed a architecture allows integrating the different agent’s tasks with AI tech-niques like planning to build MAS which is able to gather and integrate information retrieved from the WEB to solve problems.