An architecture for extracting information from hidden web databases using intelligent agent technology through reinforcement learning

摘要: The web contains enormous amount of information. From that information only small is visible to users and a huge portion the not users. This because traditional search engines are able index or access all which can be retrieved by following hypertext links accessed such engines. forms include login authorization process. Hidden refers part crawlers. An important problem retrieving desired good quality from hidden database how find out identify entry points databases i.e., forms, in Web. crawlers may unable retrieve deep databases. Therefore it main cause motivation for web. Issues challenges related also discussed. architecture accessing uses an intelligent agent technology through reinforcement learning proposed. experimental results show helps overcoming existing problems outperforms terms precision recall.