Distributed Agents to Retrieve Web Intelligence     E-mail     HOME                 Registration        | About us  | Alliances  | Contact us |  Attractions    Bibliography    Classified Papers    Search    Infomaps    Site Map    i-Web    Images Bank    White Papers   Login Area  User:   Password: Forgot your password? Register Agents Tour | AI-Lab | Darwin Tour | Faq | News | Newsletter | Pag's | Press Releases | Search Tutorial Darwin-FIRST Faq Where from FIRST extracts information? Obviously from the Web, via their agents that use the classical search engines. The FIRST Information Retrieval Methodology was transferred to agents which are continuously tuned up through the FIRST Desktop. This task is not easy even for expert people in Web content search and analysis. For this reason agents are programmed to look over all the possible “dimensions” of the Web space. The Web space grows continuously storing today (April 2003) nearly 4,000 million of documents, and only 1 million of them could be considered real Authorities. Then, how could the agents aid us to locate them efficiently?. That’s the core of the IR, Information Retrieval problem!. We know that much valuable information is “hidden”, not seen as valuable by classical search engines. To “rank high”, to be on top of search engines answers, there are a myriad of ethic and non-ethic procedures at Website owners’ hands. To locate real authorities is like an interception game where we need smart agents tuned up by smart humans. For each Major Subject and even for each “competitive” subject (the ones that induce owners to fight hard to rank high) within them, smart humans must study carefully the above mentioned ethic and non ethic procedures in order to tune up FIRST agents. Back to the last page Copyright © 2002-2006 Darwin! Inc. All rights reserved.