Auotmatic generation of voice content for a voice response system

Abstract

In one embodiment, the invention provides a method for building a voice response system. The method comprises developing voice content for the voice response system, the voice content including prompts and information to be played to a user; and integrating the voice content with logic to define a voice user-interface that is capable of interacting with the user in a manner of a conversation in which the voice user-interface receives an utterance from the user and presents a selection of the voice content to the user in response to the utterance.

1 . A method for building a voice response system the method comprising: 
 automatically generating text elements based on an analysis of text in the text document;    marking up the text document with tags that can be interpreted by a mark-up language interpreter.    
   
   
       2 . The method of  claim 1 , wherein the text elements comprise subject topics and the analysis comprises analysis of a frequency of occurrence of nouns in the text document.  
   
   
       3 . The method of  claim 1 , further comprising grouping the subject topics based on a similarity and a difference between the subject topics.  
   
   
       4 . The method of  claim 3  further comprising determining at least one mutually exclusive keyword between the subject topics in each group.  
   
   
       5 . The method of  claim 4 , wherein automatically generating the text elements comprises generating navigation elements comprising at least one disambiguating question based on the mutually exclusive keywords.  
   
   
       6 . The method of claim  3 S further comprising determining the similarity between the subject topics.  
   
   
       7 . The method of  claim 6 , wherein determining the similarity between the subject topics comprises computing a dot product between normalized keyword frequency vectors associated with keywords in the text document.  
   
   
       8 . The method of  claim 6 , wherein determining the similarity between the subject topics comprises performing a Bayesian probability analysis on the subject topics.  
   
   
       9 . A device, comprising: 
 a processor; and    a memory coupled to the processor, the memory storing instructions which when executed by the processor cause the device to perform a method comprising:    automatically generating text elements based on an analysis of text in the text document;    marking up the text document with tags that can be interpreted by a mark-up language interpreter.    
   
   
       10 . The device of  claim 9 , wherein the text elements comprise subject topics and the analysis comprises analysis of a frequency of occurrence of nouns in the text document.  
   
   
       11 . The device of  claim 9 , wherein the method further comprises grouping the subject topics based on a similarity and a difference between the subject topics.  
   
   
       12 . The device of  claim 11  wherein the method further comprises determining at least one mutually exclusive keyword between the subject topics in each group.  
   
   
       13 . The device of  claim 12  wherein automatically generating the text elements comprises generating navigation elements comprising at least one disambiguating question based on the mutually exclusive keywords.  
   
   
       14 . The device of  claim 11 , wherein the method further comprises determining the similarity between the subject topics.  
   
   
       15 . The device of  claim 14 , wherein determining the similarity between the subject topics comprises by performing a Bayesian probability analysis on the subject topics, or computing a dot product between normalized keyword frequency vectors associated with keywords in the text document.  
   
   
       16 . A computer readable medium having stored thereon a sequence of instructions which when executed by a computer cause the computer to perform a method comprising: 
 automatically generating text elements based on an analysis of text in the text document;    marking up the text document with tags that can be interpreted by a mark-up language interpreter.    
   
   
       17 . The computer readable medium of  claim 16 , wherein the text elements comprise subject topics and the analysis comprises analysis of a frequency of occurrence of nouns in the text document.  
   
   
       18 . The computer readable medium of  claim 16 , wherein the method further comprises grouping the subject topics based on a similarity and a difference between the subject topics.  
   
   
       19 . The computer readable medium of  claim 18 , wherein the method further comprises determining at least one mutually exclusive keyword between the subject topics in each group.  
   
   
       20 . The computer readable medium of  claim 19 , wherein automatically generating the text elements comprises generating navigation elements comprising at least one disambiguating question based on the mutually exclusive keywords.  
   
   
       21 . The computer readable medium of  claim 19 , wherein the method further comprises determining the similarity between the subject topics by computing a dot product between normalized keyword frequency vectors associated with keywords in the text document.