公开(公告)号：US20200327155A1

公开(公告)日：2020-10-15

申请号：US16845725

申请日：2020-04-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hannam KIM ,  Eunchung NOH ,  Kwanho LEE ,  Yeseul LEE ,  Jisun CHOI ,  Namkoo LEE

IPC: G06F16/33 ,  G06F40/40

Abstract: An electronic device is provided. The electronic device includes an output device, at least one processor operatively connected to the output device, and a memory operatively connected to the at least one processor. The memory may store instructions that cause at least one processor to output a natural language response based on main information selected from raw data depending on a context. Other various embodiments as understood from the specification are also possible.

公开(公告)号：US20230197079A1

公开(公告)日：2023-06-22

申请号：US18094694

申请日：2023-01-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kichul KIM ,  Seolhee KIM ,  Sungbin JIN ,  Jisun CHOI ,  Eunchung NOH ,  Sunghwan BAEK ,  Jaeyung YEO ,  Changyong JEONG

IPC: G10L15/22 ,  G10L15/30 ,  G10L15/18

CPC classification number: G10L15/22 ,  G10L15/30 ,  G10L15/1815 ,  G10L2015/223

Abstract: An electronic device is disclosed that, in response to at least one of an utterance intent and a control target device not being identified from utterance data, classifies a situation factor based on the utterance data, determines one or more external devices that match the classified situation factor, and generates and presents to the user terminal one or more action scenarios for one or more external devices determined for the classified situation factor.

公开(公告)号：US20220027574A1

公开(公告)日：2022-01-27

申请号：US17311559

申请日：2019-12-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Eunchung NOH

IPC: G06F40/35 ,  H04L12/58 ,  G06F40/166 ,  G06F40/253 ,  G06N3/08

Abstract: An electronic device according to various embodiments of the present invention may include a memory, and at least one processor, wherein the at least one processor may be configured to obtain a sentence based on a user input, based on obtaining the sentence, determine at least one persona, convert the sentence to at least one sentence having a style corresponding to the at least one persona, using a neural network, and provide the converted at least one sentence.