A method for searching a corpus of documents, such as the World Wide Web, includes defining a knowledge domain and identifying a set of reference documents in the corpus pertinent to the domain. Upon inputting a query, the corpus is searched using the set of reference documents to find one or more of...http://www.google.fr/patents/US20080147644?utm_source=gb-gplus-shareBrevet US20080147644 - Information search using knowledge agents
Numéro de demande: 11/923,676 Numéro de publication: US 2008/0147644 A1 Date de dépôt: 10 déc. 2007 Brevet délivré: US7809708 ( Date de délivrance 5 oct. 2010)
