公开(公告)号：US20230186036A1

公开(公告)日：2023-06-15

申请号：US17435995

申请日：2021-08-23

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Yoonjung CHOI ,  Sangha KIM ,  Hakjung KIM ,  Yoonjin YOON ,  Seokchan AHN

IPC: G06F40/58 ,  G10L21/04 ,  G10L25/87

CPC classification number: G06F40/58 ,  G10L21/04 ,  G10L25/87

Abstract: A method is provided. The method includes receiving a speech input in a first language from a first device; obtaining, by using an artificial intelligence (AI) model, an estimated interpretation time that indicates a time expected to be required to interpret the speech input in the first language into a second language; transmitting, based on the estimated interpretation time, interpretation situation information to at least one of the first device or a second device; interpreting the speech input in the first language into the second language; and transmitting, to the second device a result of the interpreting of the speech input into the second language.

公开(公告)号：US20230359836A1

公开(公告)日：2023-11-09

申请号：US18219339

申请日：2023-07-07

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyojung HAN ,  Yoonjin YOON ,  Yoonjung CHOI ,  Sangha KIM ,  Seokchan AHN ,  Taehwan YOO ,  Beomseok LEE

IPC: G06F40/40

CPC classification number: G06F40/40

Abstract: An electronic device which obtains a first translated text in which a first phrase in an original text sequence of a first language is translated in a second language by inputting the first phrase to a translation model, determines an extent of delay in translation of the first phrase by comparing a time-point of the first phrase with a time-point of the first translated text, identifies one phrase from among the first phrase and a second phrase following the first phrase based on the extent of delay, obtains a summary text of the identified phrase by inputting the identified phrase to a summary model, obtains a second translated text in which identified phrase or the summary text is translated in the second language by inputting the identified phrase or the summary text to the translation model, and outputs the second translated text after the first translated text is output.

公开(公告)号：US20220343156A1

公开(公告)日：2022-10-27

申请号：US17432631

申请日：2021-08-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sangha KIM ,  Seokchan AHN ,  Yoonjung CHOI ,  Hakjung KIM ,  Yoonjin YOON

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063 ,  G06K9/62

Abstract: A method performed by a server is provided. The method includes, in response to input information being processed by the first model in the terminal, receiving, from the terminal, intermediate data output from a first layer included in a shared portion of the first model, obtaining the first model and a second model, which are pretrained by including the shared portion, obtaining correct answer data for the input information by inputting the intermediate data as an output of the first layer to the first layer included in the shared portion of the second model, in response to the intermediate data being input as the output of the first layer to the first layer included in the shared portion of the first model, refining the first model so that the correct answer data may be output from the first model, and transmitting information about the refined first model to the terminal.