公开(公告)号：US20220237215A1

公开(公告)日：2022-07-28

申请号：US17712301

申请日：2022-04-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaehyung AN ,  Hoyoung KIM ,  Dongil YANG ,  Jiyeon LEE ,  Cheolseung JUNG

IPC: G06F16/332 ,  G06F16/33 ,  G06F40/30 ,  G06F40/289

Abstract: A method of controlling an electronic device includes, based on obtaining first text information corresponding to a user query, identifying a main query corresponding to the first text information; obtaining a plurality of responses related to the main query; identifying a plurality of phrases included in the first text information; identifying at least one first phrase corresponding to the main query among the plurality of phrases based on a similarity between the plurality of phrases and the main query; identifying, among the plurality of responses, at least one first response corresponding to a remaining second phrase, among the plurality of phrases except the at least one first phrase, based on a similarity between each of the plurality of responses and the remaining second phrase; and providing second text information corresponding to a remaining second response other than the at least one first response among the plurality of responses.

公开(公告)号：US20220094651A1

公开(公告)日：2022-03-24

申请号：US17503819

申请日：2021-10-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jiyeon LEE ,  Hoyoung KIM ,  Jaehyung AN ,  Dongil YANG ,  Cheolseung JUNG

IPC: H04L12/58 ,  G06F40/20 ,  G06F40/30

Abstract: An electronic device and a method for controlling thereof are provided. The electronic device may include: a memory and a processor configured to: input sentences input into a plurality of conversation rooms generated through a messenger application into a first model and acquire characteristic information of conversations conducted in the plurality of respective conversation rooms, based on a first sentence being input, input the first sentence and the characteristic information into a second model and acquire first scores indicating a similarity between the first sentence and the characteristics of the conversations conducted in the plurality of respective conversation rooms, input the first sentence and the sentences input into the plurality of conversation rooms into a third model and acquire second scores indicating relevance between the first sentence and the sentences input into the plurality of conversation rooms, identify a conversation room as a conversation room corresponding to the first sentence among the plurality of conversation rooms based on the characteristic information, the first scores, and the second scores, and input the first sentence into the identified conversation room.

公开(公告)号：US20230260515A1

公开(公告)日：2023-08-17

申请号：US18305652

申请日：2023-04-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seohyun BACK ,  Yonghyun RYU ,  Wonho RYU ,  Haejun LEE ,  Cheolseung JUNG ,  Sai CHETAN ,  Jiyeon HONG

IPC: G10L15/22 ,  G06T13/00 ,  G10L15/16 ,  G06N3/08 ,  G10L15/18

CPC classification number: G10L15/22 ,  G06T13/00 ,  G10L15/16 ,  G06N3/08 ,  G10L15/1815 ,  G10L2015/223

Abstract: A method of improving output content through iterative generation is provided. The method includes receiving a natural language input, obtaining user intention information based on the natural language input by using a natural language understanding (NLU) model, setting a target area in base content based on a first user input, determining input content based on the user intention information or a second user input, generating output content related to the base content based on the input content, the target area, and the user intention information by using a neural network (NN) model, generating a caption for the output content by using an image captioning model, calculating similarity between text of the natural language input and the generated output content, and iterating generation of the output content based on the similarity.

公开(公告)号：US20220245340A1

公开(公告)日：2022-08-04

申请号：US17677396

申请日：2022-02-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dongil YANG ,  Hoyoung KIM ,  Jaehyung AN ,  Jiyeon LEE ,  Cheolseung JUNG ,  Wonjong CHOI

IPC: G06F40/279 ,  G06V30/18 ,  G06V30/19

Abstract: An electronic device for providing a corrected response message according to an utterance intention of a user by using a keyword included in an input inquiry input by the user, and an operation method of the electronic device are provided. The electronic device includes receiving the input inquiry input by the user, identifying a representative inquiry according to an utterance intention of the user by analyzing the input inquiry by using a natural language understanding (NLU) model, extracting a keyword from the input inquiry by comparing a vector value of a first embedding vector of the input inquiry changed through the NLU model with a vector value of a second embedding vector of the representative inquiry, and correcting a response message mapped to correspond to the representative inquiry, by using the extracted keyword.

公开(公告)号：US20240079008A1

公开(公告)日：2024-03-07

申请号：US18503741

申请日：2023-11-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seohyun BACK ,  Yonghyun RYU ,  Wonho RYU ,  Haejun LEE ,  Cheolseung JUNG ,  Sai CHETAN ,  Jiyeon HONG

IPC: G10L15/22 ,  G06N3/08 ,  G06T13/00 ,  G10L15/16 ,  G10L15/18

CPC classification number: G10L15/22 ,  G06N3/08 ,  G06T13/00 ,  G10L15/16 ,  G10L15/1815 ,  G10L2015/223

Abstract: A method of improving output content through iterative generation is provided. The method includes receiving a natural language input, obtaining user intention information based on the natural language input by using a natural language understanding (NLU) model, setting a target area in base content based on a first user input, determining input content based on the user intention information or a second user input, generating output content related to the base content based on the input content, the target area, and the user intention information by using a neural network (NN) model, generating a caption for the output content by using an image captioning model, calculating similarity between text of the natural language input and the generated output content, and iterating generation of the output content based on the similarity.

公开(公告)号：US20210174801A1

公开(公告)日：2021-06-10

申请号：US17111734

申请日：2020-12-04

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seohyun BACK ,  Yonghyun RYU ,  Wonho RYU ,  Haejun LEE ,  Cheolseung JUNG ,  Sai CHETAN ,  Jiyeon HONG

IPC: G10L15/22 ,  G06T13/00 ,  G10L15/18 ,  G10L15/16 ,  G06N3/08

Abstract: A method of improving output content through iterative generation is provided. The method includes receiving a natural language input, obtaining user intention information based on the natural language input by using a natural language understanding (NLU) model, setting a target area in base content based on a first user input, determining input content based on the user intention information or a second user input, generating output content related to the base content based on the input content, the target area, and the user intention information by using a neural network (NN) model, generating a caption for the output content by using an image captioning model, calculating similarity between text of the natural language input and the generated output content, and iterating generation of the output content based on the similarity.

公开(公告)号：US20240161746A1

公开(公告)日：2024-05-16

申请号：US18461095

申请日：2023-09-05

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjong CHOI ,  Manun JEONG ,  Cheolseung JUNG

IPC: G10L15/22 ,  G10L15/04

CPC classification number: G10L15/22 ,  G10L15/04 ,  G10L2015/223

Abstract: A main device is provided. The main device includes a memory storing function information and importance information of each function of a first sub-device, a communication interface connected to the first sub-device, and at least one processor configured to acquire the function information and importance information of each function of a second sub-device, determine whether at least one function performed by the first sub-device exists among a plurality of functions performed by the second sub-device, determine a device to perform the at least one function based on importance of the at least one function of the second sub-device and importance of the at least one function of the first sub-device, and transmit information on the device to perform the at least one function to the first sub-device and the second sub-device.

公开(公告)号：US20220247822A1

公开(公告)日：2022-08-04

申请号：US17584967

申请日：2022-01-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoyoung KIM ,  Dongil YANG ,  Jaehyung AN ,  Jiyeon LEE ,  Cheolseung JUNG

IPC: H04L67/143 ,  H04L67/50 ,  H04L51/02 ,  H04L51/00

Abstract: An electronic apparatus and an operation method thereof for determining a session duration time according to a characteristic of a response message in a chatbot are provided. The electronic apparatus is configured to determine a default session time based on a difficulty level of the response message, determine an additional session time based on conversation history information through the chatbot prior to outputting of the response message, determine a session duration time, which is a sum of the default session time and the additional session time, and provide the session duration time.

公开(公告)号：US20220215276A1

公开(公告)日：2022-07-07

申请号：US17607702

申请日：2020-08-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Haejun LEE ,  Cheolseung JUNG

IPC: G06N5/04 ,  G06N3/08 ,  G06F16/903

Abstract: Disclosed are an electronic device and a method for controlling an electronic device. The electronic device according to the disclosure obtains text information corresponding to a user's question, obtains a plurality of keywords related to the user's question and importance values for the respective keywords by inputting the text information corresponding to the user's question to a trained first neural network model, identifies at least one search word to be input to a search engine among the plurality of keywords by inputting the plurality of keywords and the importance values to a trained second neural network model, and provides an answer to the user's question based on the at least one identified search word.