Analyzing an agent-based selective information retrieval

A dynamic cooperation model for different agents´ message exchanging is proposed. It is thought that the curve of surrounding words´ relevant influence approximatively fits normal distribution with a mean of 0 and a standard deviation of σ. Following those mechanisms, agent-based selective information retrieval based on topical crawling, high-performance indexing and an efficient search algorithm is implemented. The agents´ cooperation model expresses the procedure of agent organization and communication. Topical crawling based on anchor word concept analysis can guarantee a higher performance. The topical crawler makes it easy to find as many relevant pages as possible and as few irrelevant pages as possible.