Method for controlling artificial intelligence system that performs multilingual processing

Abstract

This specification relates to a method for controlling an artificial intelligence system which performs a multilingual processing based on artificial intelligence technology. The method for controlling an artificial intelligence system which performs a multilingual processing includes: receiving voice information through a microphone; determining a language of the voice information, based on a preset reference; selecting a specific voice recognition server from a plurality of voice recognition servers which process different languages, based on a result of the determination; and transmitting the voice information to the selected specific voice recognition server.

What is claimed is: 
     
         1 . A method for controlling a multilingual audio processing system, the method comprising:
 receiving voice information via a microphone;   determining a first language of the received voice information,   transmitting the received voice information to a first voice recognition server for determining an intent of the received voice information, wherein the first voice recognition server is associated with the first language;   receiving intent information from the first voice recognition server, wherein the intent information indicates that the received voice information comprises a request to translate a portion of the voice information to a second language;   transmitting the portion of the voice information to a second voice recognition server associated with the second language;   receiving translation information of the portion of the voice information from the second voice recognition server; and   outputting an output corresponding to the received translation information.   
     
     
         2 . The method of  claim 1 , wherein the output is in the form of an audio output. 
     
     
         3 . The method of  claim 1 , wherein the output is visually displayed on a display of a terminal associated with the system. 
     
     
         4 . The method of  claim 1 , wherein the first voice recognition server is selected based on the determination that the received voice information is in the first language. 
     
     
         5 . The method of  claim 4 , wherein a different server is selected as the first voice recognition server for a different language from the first language. 
     
     
         6 . The method of  claim 1 , wherein the output corresponds to a response to a request included in the portion of the voice information. 
     
     
         7 . A method for controlling a multilingual audio processing system, the method comprising:
 receiving voice information via a microphone;   determining a first language of the received voice information;   determining that the received voice information comprises a request to translate a portion of the received voice information to a second language;   transmitting the portion of the received voice information to a first voice recognition server associated with the first language;   receiving translated information from the first voice recognition server, wherein the translated information corresponds to a translation of the portion of the received voice information translated to the second language;   transmitting the translated information to a second voice recognition server for processing; and   outputting a processing result received from the second voice recognition server.   
     
     
         8 . The method of  claim 7 , wherein the processing result is output in the form of an audio output. 
     
     
         9 . The method of  claim 7 , wherein the processing result is visually output on a display of a terminal associated with the system. 
     
     
         10 . The method of  claim 7 , wherein the first voice recognition server is selected based on the determination that the received voice information is in the first language. 
     
     
         11 . The method of  claim 10 , wherein a different server is selected as the first voice recognition server for a different language from the first language. 
     
     
         12 . The method of  claim 7 , wherein the processing result corresponds to a response to a request included in the portion of the voice information.