Systems and methods for interactively accessing hosted services using voice communications

Abstract

Systems and methods for an interactive voice response system are described herein. In one embodiment, the system may include a voice recognition module, a session manager, and a voice generator module. An utterance received at the voice recognition module may be converted into one or more structures using a lexicon tied to an ontology. Concepts in the utterance may then be identified. If sufficient information has been provided to identify a relevant service, corresponding text responses associated with that service may then be converted into voice messages by the voice generator.

What is claimed is: 
     
         1 . A method implemented using a device, comprising:
 receiving, from a user, an utterance in a human language;   identifying at least one concept based on the utterance, where each of the at least one concept is redefined with a plurality of associated lexemes and at least a portion of the associated lexemes match at least some lexemes associated with the utterance;   identifying a message based on the at least one concept; and   providing the message.   
     
     
         2 . The method of  claim 1 , wherein the at least a portion of the associated lexemes are in a first order, the at least some lexemes associated with the utterance are in a second order that is not the same as the first order. 
     
     
         3 . The method of  claim 1 , wherein the associated lexemes of the at least one concept is in the human language and the at least one concept is further associated with lexemes of a different human language. 
     
     
         4 . The method of  claim 1 , wherein the human language is one or a plurality of human languages in which the device accepts the utterance. 
     
     
         5 . The method of  claim 1 , wherein providing the message comprises providing the message in a different human language. 
     
     
         6 . The method of  claim 5 , wherein the human language and the different human language are two of a plurality of languages in which the device is capable of providing the message. 
     
     
         7 . The method of  claim 1 , wherein the at least one concept s part of a plurality of concepts predefined associating with a service. 
     
     
         8 . The method of  claim 1 , wherein the identifying the at least one concept is further based on at least one condition that is required to be present or absent, 
     
     
         9 . The method of  claim 1 , wherein the identifying the at least one concept is further based on a ranking with at least one other concept. 
     
     
         10 . A device comprising a voice recognition module, a voice generator, and a storage, the device is configured to perform:
 receiving, from a user, an utterance in a human language;   identifying at least one concept based on the utterance, where each of the at least one concept is redefined with a plurality of associated lexemes and at least a portion of the associated. lexemes match at least some lexemes associated with the utterance;   identifying a message based on the at least one concept; and   providing the message.   
     
     
         11 . The method of  claim 10 , wherein the at least a portion of the associated lexemes are in a first order, the at least some lexemes associated with the utterance are in a second order that is not the same as the first order. 
     
     
         12 . The method of  claim 10 , wherein the associated lexemes of the at least one concept is in the human language and the at least one concept is further associated with lexemes of a different human language. 
     
     
         13 . The method of  claim 10 , wherein the human language is one or a plurality of human languages in which the device accepts the utterance. 
     
     
         14 . The method of  claim 10 , wherein providing the message comprises providing the message in a different human language. 
     
     
         15 . The method of  claim 14 , wherein the human language and the different human language are two of a plurality of languages in which the device is capable of providing the message. 
     
     
         16 . The method of  claim 10 , wherein the at least one concept is part of a plurality of concepts predefined associating with a service. 
     
     
         17 . The method of  claim 10 , wherein the identifying the at least one concept is further based on at least one condition that is required to be present or absent. 
     
     
         18 . The method of  claim 10 , wherein the identifying the at least one concept is further based on a ranking with at least one other concept. 
     
     
         19 . A non-transitory computer readable medium having stored therein computer executable instructions for:
 receiving, from a user, an utterance in a. human language;   identifying at least one concept based on the utterance, where each of the at least one concept is redefined with a plurality of associated lexemes and at least a portion of the associated lexemes match at least some lexemes associated with the utterance;   identifying a message based on the at least one concept; and   providing the message.   
     
     
         20 . The computer readable medium of  claim 19 , wherein the at least a portion of the associated lexemes are in a first order, the at least some lexemes associated with the utterance are in a second order that is not the same as the first order; and wherein the associated lexemes of the at least one concept is in the human language and the at least one concept is further associated. with lexemes of a different human language.