Method of Handling Frequently Asked Questions in a Natural Language Dialog Service

Abstract

A voice-enabled help desk service is disclosed. The service comprises an automatic speech recognition module for recognizing speech from a user, a spoken language understanding module for understanding the output from the automatic speech recognition module, a dialog management module for generating a response to speech from the user, a natural voices text-to-speech synthesis module for synthesizing speech to generate the response to the user, and a frequently asked questions module. The frequently asked questions module handles frequently asked questions from the user by changing voices and providing predetermined prompts to answer frequently asked questions.

We claim: 
     
         1 . A method comprising:
 developing, via a processor, a back story for a pre-synthesized voice in a plurality of pre-synthesized voices;   in response to a received utterance, selecting a prompt type associated with the pre-synthesized voice;   generating a prompt, as part of a turn-based dialog comprising the received utterance, based on the prompt type and the back story.   
     
     
         2 . The method of  claim 1 , wherein generating of the prompt is further based on a dialog history. 
     
     
         3 . The method of  claim 2 , wherein generating of the prompt is further based on a set of logical predicates. 
     
     
         4 . The method of  claim 3 , wherein generating of the prompt utilizes an interpreter tuple. 
     
     
         5 . The method of  claim 1 , wherein the back story is based on a personality trait associated with the pre-synthesized voice. 
     
     
         6 . The method of  claim 1 , wherein the prompt type is one of a pricing, a hint, a demonstration, a question, an example, an instruction, and a command. 
     
     
         7 . The method of  claim 1 , wherein the plurality of pre-synthesized voices comprises eight pre-synthesized voices. 
     
     
         8 . A system comprising:
 a processor; and   a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
 developing a back story for a pre-synthesized voice in a plurality of pre-synthesized voices; 
 in response to a received utterance, selecting a prompt type associated with the pre-synthesized voice; 
 generating a prompt, as part of a turn-based dialog comprising the received utterance, based on the prompt type and the back story. 
   
     
     
         9 . The system of  claim 8 , wherein generating of the prompt is further based on a dialog history. 
     
     
         10 . The system of  claim 9 , wherein generating of the prompt is further based on a set of logical predicates. 
     
     
         11 . The system of  claim 10 , wherein generating of the prompt utilizes an interpreter tuple. 
     
     
         12 . The system of  claim 1 , wherein the back story is based on a personality trait associated with the pre-synthesized voice. 
     
     
         13 . The system of  claim 1 , wherein the prompt type is one of a pricing, a hint, a demonstration, a question, an example, an instruction, and a command. 
     
     
         14 . The system of  claim 1 , wherein the plurality of pre-synthesized voices comprises eight pre-synthesized voices. 
     
     
         15 . A computer-readable storage device having instructions stored which, when executed by a computing device, cause the device to perform operations comprising:
 developing a back story for a pre-synthesized voice in a plurality of pre-synthesized voices;   in response to a received utterance, selecting a prompt type associated with the pre-synthesized voice;   generating a prompt, as part of a turn-based dialog comprising the received utterance, based on the prompt type and the back story.   
     
     
         16 . The computer-readable storage device of  claim 15 , wherein generating of the prompt is further based on a dialog history. 
     
     
         17 . The computer-readable storage device of  claim 16 , wherein generating of the prompt is further based on a set of logical predicates. 
     
     
         18 . The computer-readable storage device of  claim 17 , wherein generating of the prompt utilizes an interpreter tuple. 
     
     
         19 . The computer-readable storage device of  claim 15 , wherein the back story is based on a personality trait associated with the pre-synthesized voice. 
     
     
         20 . The computer-readable storage device of  claim 15 , wherein the prompt type is one of a pricing, a hint, a demonstration, a question, an example, an instruction, and a command.