公开(公告)号：US12175979B2

公开(公告)日：2024-12-24

申请号：US18210696

申请日：2023-06-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jina Ham ,  Kangwook Lee ,  Soofeel Kim ,  Yewon Park ,  Wonjong Choi

IPC: G10L15/22 ,  G06V40/16 ,  G10L15/02 ,  G10L15/18 ,  G10L15/197 ,  G10L15/25 ,  G10L15/30

Abstract: A method, performed by an electronic device, of providing a conversational service includes: receiving an utterance input; identifying a temporal expression representing a time in a text obtained from the utterance input; determining a time point related to the utterance input based on the temporal expression; selecting a database corresponding to the determined time point from among a plurality of databases storing information about a conversation history of a user using the conversational service; interpreting the text based on information about the conversation history of the user, the conversation history information being acquired from the selected database; generating a response message to the utterance input based on a result of the interpreting; and outputting the generated response message.

公开(公告)号：US11710481B2

公开(公告)日：2023-07-25

申请号：US16797339

申请日：2020-02-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jina Ham ,  Kangwook Lee ,  Soofeel Kim ,  Yewon Park ,  Wonjong Choi

IPC: G10L15/22 ,  G10L15/30 ,  G10L15/02 ,  G10L15/197 ,  G10L15/18 ,  G10L15/25 ,  G06V40/16

CPC classification number: G10L15/22 ,  G06V40/172 ,  G10L15/02 ,  G10L15/1815 ,  G10L15/197 ,  G10L15/25 ,  G10L15/30 ,  G10L2015/025 ,  G10L2015/223

Abstract: A method, performed by an electronic device, of providing a conversational service includes: receiving an utterance input; identifying a temporal expression representing a time in a text obtained from the utterance input; determining a time point related to the utterance input based on the temporal expression; selecting a database corresponding to the determined time point from among a plurality of databases storing information about a conversation history of a user using the conversational service; interpreting the text based on information about the conversation history of the user, the conversation history information being acquired from the selected database; generating a response message to the utterance input based on a result of the interpreting; and outputting the generated response message.

公开(公告)号：US10887454B2

公开(公告)日：2021-01-05

申请号：US16545307

申请日：2019-08-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Soofeel Kim ,  Wonjong Choi ,  Jina Ham

IPC: H04M3/42 ,  H04M1/27453 ,  G06N3/08

Abstract: A method of controlling an electronic apparatus is provided. The method includes obtaining a name referring to a user of another electronic apparatus in a chat with the user of the other electronic apparatus using an artificial intelligence (AI) model trained by an AI algorithm while conducting the chat with the user of the other electronic apparatus using the electronic apparatus; and storing the obtained name in association with contact information of the user of the other electronic apparatus. At least some of the control method of the disclosure may use an AI model trained according to at least one of machine learning, neural network, or deep learning algorithm.

公开(公告)号：US12010074B2

公开(公告)日：2024-06-11

申请号：US17578088

申请日：2022-01-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jina Ham ,  Wonjong Choi ,  Soofeel Kim ,  Yewon Park

IPC: H04L51/02 ,  G06F16/33 ,  G06F16/332 ,  G06F16/35

CPC classification number: H04L51/02 ,  G06F16/3329 ,  G06F16/334 ,  G06F16/35

Abstract: An electronic apparatus includes a memory storing instructions, a plurality of chat-bots for responding to a plurality of questions, and a question classification model trained to identify a chat-bot among the plurality of chat-bots for responding to an input question, and a processor configured to execute the instructions to input the input question into the question classification model, the question classification model outputting a first chat-bot among the plurality of chat-bots for responding to the input question, acquire a first response for the input question, through the outputted first chat-bot, based on the acquired first response comprising information of a function that can be performed at the electronic apparatus, generate a question requesting to perform the function, and input the generated question into the question classification model, the question classification model outputting a second chat-bot among the plurality of chat-bots for responding to the generated question.

公开(公告)号：US11575783B2

公开(公告)日：2023-02-07

申请号：US17139093

申请日：2020-12-31

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Soofeel Kim ,  Wonjong Choi ,  Jina Ham

IPC: H04M3/42 ,  H04M1/27453 ,  G06N3/08

Abstract: A method of controlling an electronic apparatus is provided. The method includes obtaining a name referring to a user of another electronic apparatus in a chat with the user of the other electronic apparatus using an artificial intelligence (AI) model trained by an AI algorithm while conducting the chat with the user of the other electronic apparatus using the electronic apparatus; and storing the obtained name in association with contact information of the user of the other electronic apparatus. At least some of the control method of the disclosure may use an AI model trained according to at least one of machine learning, neural network, or deep learning algorithm.

公开(公告)号：US11348588B2

公开(公告)日：2022-05-31

申请号：US16545511

申请日：2019-08-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wonjong Choi ,  Soofeel Kim ,  Jina Ham

IPC: G10L17/22 ,  G10L17/00 ,  G10L17/06 ,  G06F40/295 ,  G10L15/22

Abstract: An electronic device for performing speech recognition and a method therefor are provided. The method includes detecting a first text, which is preset for performing speaker recognition, by performing speech recognition on a first speech signal, performing speaker recognition on a second speech signal acquired after the first speech signal, based on the first text being detected, and executing a voice command obtained from the second speech signal, based on a result of performing the speaker recognition on the second speech signal indicating that a speaker of the second speech signal corresponds to a first speaker who registered the first text.

公开(公告)号：US20210065705A1

公开(公告)日：2021-03-04

申请号：US16797339

申请日：2020-02-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jina Ham ,  Kangwook Lee ,  Soofeel Kim ,  Yewon Park ,  Wonjong Choi

IPC: G10L15/22 ,  G10L15/30 ,  G10L15/02 ,  G10L15/197 ,  G10L15/25 ,  G06K9/00 ,  G10L15/18

Abstract: A method, performed by an electronic device, of providing a conversational service includes: receiving an utterance input; identifying a temporal expression representing a time in a text obtained from the utterance input; determining a time point related to the utterance input based on the temporal expression; selecting a database corresponding to the determined time point from among a plurality of databases storing information about a conversation history of a user using the conversational service; interpreting the text based on information about the conversation history of the user, the conversation history information being acquired from the selected database; generating a response message to the utterance input based on a result of the interpreting; and outputting the generated response message.

公开(公告)号：US12277390B2

公开(公告)日：2025-04-15

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：US12211510B2

公开(公告)日：2025-01-28

申请号：US17551421

申请日：2021-12-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Soofeel Kim ,  Jina Ham ,  Yewon Park ,  Wonjong Choi

IPC: G10L17/18 ,  G06F3/16 ,  G06F40/216 ,  G06F40/30 ,  G06F40/35 ,  G06N3/045 ,  G06N3/08 ,  G10L15/16 ,  G10L15/22 ,  G10L17/04 ,  G10L17/22 ,  G11B20/10 ,  G10L15/18 ,  G10L15/26 ,  G10L17/00

Abstract: An electronic device is provided. The electronic device includes a memory storing recording data including a content of a conversation and at least one instruction, and a processor configured, by executing the at least one instruction, to input first data corresponding to a first voice in the content of the conversation into a first neural network model and acquire category information of the first data, and acquire category information of second data corresponding to a second voice in the content of the conversation. The processor is configured to, based on the category information of the first data and the category information of the second data being different, train the first neural network model based on the category information of the second data and the first data.

公开(公告)号：US11889152B2

公开(公告)日：2024-01-30

申请号：US17609669

申请日：2020-06-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jina Ham ,  Wonjong Choi ,  Soofeel Kim ,  Yewon Park

IPC: H04N21/472 ,  H04N21/422 ,  H04N21/488 ,  G06F3/16

CPC classification number: H04N21/47202 ,  G06F3/167 ,  H04N21/42203 ,  H04N21/4884

Abstract: An electronic device and a control method thereof are provided. The electronic device includes a camera, a microphone, a display, a communicator including circuitry, a memory, and a processor configured to capture an image of an external device through the camera and obtain information on the external device, based on a user's voice for requesting for solution information for solving a problem regarding the external device being input through the microphone while obtaining the information on the external device, control the communicator to transmit the input user's voice and the information on the external device to a server, receive a content related to the solution information from a content of a device related to the external device from the server via the communicator, and control the display to provide the content related to the solution information along with the captured image.