US 12,190,075 B2
Apparatus and method for processing voice commands
Jooyong Byeon, Suwon-si (KR); and Seolhee Kim, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on May 24, 2022, as Appl. No. 17/664,834.
Application 17/664,834 is a continuation of application No. PCT/KR2022/002142, filed on Feb. 14, 2022.
Claims priority of application No. 10-2021-0024733 (KR), filed on Feb. 24, 2021.
Prior Publication US 2022/0284197 A1, Sep. 8, 2022
Int. Cl. G10L 15/00 (2013.01); G06F 40/58 (2020.01); G10L 15/22 (2006.01)
CPC G06F 40/58 (2020.01) [G10L 15/005 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An apparatus for processing voice commands, the apparatus comprising:
a memory configured to store computer-executable instructions; and
a processor coupled to the memory and configured to execute the computer-executable instructions,
wherein the computer-executable instructions, when executed, cause the processor to perform a process of:
receiving an utterance of a user in an input language set by the user;
determining an utterance intent of the utterance by analyzing the utterance with the input language;
determining a standard utterance in the input language corresponding to the utterance of the user based on the determined utterance intent;
determining whether the input language and an output language are different languages;
in response to determining the input language and the output language are different, extracting a standard utterance in the output language corresponding to the determined standard utterance in the input language;
generating an output response in the output language based on the extracted standard utterance in the output language; and
outputting the output response,
wherein the generating of the output response in the output language comprises, when a plurality of languages are set as the output language, generating language-dependent output responses respectively for the plurality of languages, and
wherein the generating of the language-dependent output responses comprises:
requesting response information for generating the language-dependent output responses from a content provider, when content providers corresponding to respectively extracted language-dependent standard utterances are the same;
receiving the requested response information; and
generating the language-dependent output responses based on the received response information.