Research Of Multi-Agent Coordination In Topic-Specific Search Engine

With the fast development of computer technology, artificial intelligence and computer network technology, computer has quickly turned into opened, network distributed and coordinative working. In the recent ten years, intelligent Agent and Multi-Agent System (MAS), which come of Distributed Artificial Intelligence (DAI), have become a hotspot in the field of Artificial Intelligence. The advent of intelligent Agent and Multi-Agent System broke a new path for integration, analysis, realization and application of the Distributed Artificial Intelligence; it also further promoted the growth of Artificial Intelligence and software engineering.Nowadays, intelligent Agent technology has been widely applied to the filed of electronic commerce, air traffic control, workflow management, transportation systems, and information retrieve, among others. This paper focuses on the related issues, which apply intelligent Agent to topic-specific search engines.Topic-specific search engines use Agents to collect Web pages from the Internet by choosing to gather only particular pages related to specific topic therefore could efficiently collect pages that are more relevant to users. Comparing with the general search engines, it can effectively decrease the amount of retrieval documents, can profoundly analyze the useful topic and retrieve more high quality information for users. Therefore, topic-specific search has become a hotspot in the search field. However, in the topic-specific search field, most researchers focus on the single Agent how to crawl on the Web; they neglect the coordinative issues among multi-Agents. Therefore, this paper concentrated on the coordination among multi-Agent in topic-specific search engine. The main contents of this paper can be summarized in the following three aspects:Structure of multi-Agent in topic-specific search engine:To achieve the coordination among multi-Agent, it must make sure that Agents can communicate normally and immediately. Therefore, a structure is firstly proposed for the Multi-Agent in Topic-specific Search engine; it realizes the communication among Agents.Structure of intelligent Agent in topic-specific search engine:In this paper, the topic-Specific search Agents is divided into two types: F-Agent and C-Agent. The former makes task plans, manages the C-Agents as well as deals with the communications among TSSA, whereas the latter crawls on the Web for retrieving the relevant pages. This paper concretely discusses function and architecture of the two Agents respectively.The negotiation protocols among multi-Agent in topic-specific search engine: This paper discusses the cooperation and competition among the multi-agent intopic-specific search engine in more detail. Based on the contract net and auction theory, two negotiation protocols are proposed to control the cooperation and competition among C-Agents. Finally, by the experiment, the two negotiation protocols are ulteriorly explained, and it can draw the conclusion: In the topic-specific search engine, the negotiation among Agents is necessary. It can evidently improve the efficiency and increase the executive ability of Agent.