Personal Voice-Based Information Retrieval System

Abstract

The present invention relates to a system for retrieving information from a network such as the Internet. A user creates a user-defined record in a database that identifies an information source, such as a web site, containing information of interest to the user. This record identifies the location of the information source and also contains a recognition grammar based upon a speech command assigned by the user. Upon receiving the speech command from the user that is described within the recognition grammar, a network interface system accesses the information source and retrieves the information requested by the user.

1 - 2 . (canceled)  
   
   
       3 . A method for retrieving information via a phone in an audio format from a pre-defined portion of a pre-selected web site, said method comprising the steps of: 
 providing a server operatively connected to the Internet and said phone, said server being operatively connected to a speech recognition engine and to a speech synthesis engine;    providing at least one instruction set stored on said server for identifying the pre-defined portion of a pre-selected web site containing the information to be retrieved from the web site, each said instruction set comprising: 
 a uniform resource locator address for said web site; and  
 a content descriptor of said web site, said content descriptor defining the portion of said web site from which said information is to be retrieved; and  
 a named object associated with the content of the information to be retrieved;  
   providing a speech command to said speech recognition engine, said speech command corresponding to said instruction set;    said speech recognition engine assigning said speech command to a recognition grammar, said speech command and said recognition grammar corresponding to each said instruction set;    transmitting said speech command to said speech recognition engine;    said speech recognition engine receiving said speech command and selecting the corresponding recognition grammar;    said server retrieving each said instruction set corresponding to said recognition grammar;    said server accessing said pre-defined portion of said pre-selected web site defined by said instruction set and retrieving said information defined by said instruction set when the requested information is found in the pre-defined portion of the pre-selected web site;    said server searching said pre-selected website when the requested information is not found in the pre-defined portion of the pre-selected web site;    said speech synthesis engine converting the retrieved information from said pre-selected web site into an audio message; and    said speech synthesis engine transmitting said audio message to said user.