公开(公告)号：US11436215B2

公开(公告)日：2022-09-06

申请号：US16545388

申请日：2019-08-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hyungtak Choi ,  Seungsoo Kang ,  Sunhwa Ko ,  Jihie Kim ,  Hyunwoo Park ,  Haehun Yang ,  Daye Lee ,  Siddarth K M ,  Inchul Hwang

IPC: G06F16/23 ,  G06F16/22

Abstract: A server and a control method thereof are disclosed. The control method of a server includes receiving knowledge information from a first electronic device, storing the received knowledge information in a personal knowledge database corresponding to a user using the first electronic device, transmitting a response to an inquiry to obtain the knowledge information to at least one second electronic device based on the knowledge information stored in the personal knowledge database, based on the inquiry being received from the at least one second electronic device, receiving feedback information to the response from the at least one second electronic device, and storing the knowledge information in a global knowledge database based on the feedback information. At least a part of a method of allowing a server to provide a response to a user inquiry may use an artificial intelligence model learned according to at least one of machine learning, neural networks, or deep learning algorithms.

公开(公告)号：US20250048528A1

公开(公告)日：2025-02-06

申请号：US18427431

申请日：2024-01-30

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyunwoo Park ,  Jae-Hyun Kim ,  Hyunsik Kim ,  Taijong Sung ,  Young Heo

IPC: H05H1/34

Abstract: A plasma torch includes a cathode, a pilot electrode disposed on a first outer circumference of the cathode and separated from an exterior surface of the cathode, an electrode protection member disposed below the pilot electrode and including a first insulator, an anode disposed on a second outer circumference of a process space and disposed below the pilot electrode, and a discharge gas flow path coupled to a separation gap formed between the exterior surface of the cathode and an inner surface of the pilot electrode. The discharge gas flow path is configured to supply a discharge gas.

公开(公告)号：US12046243B2

公开(公告)日：2024-07-23

申请号：US17437903

申请日：2021-08-20

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jaechul Yang ,  Hyunwoo Park ,  Hyungrai Oh ,  Jongsun Abbas Lee

IPC: G10L15/26 ,  G06F40/279 ,  G10L15/06

CPC classification number: G10L15/26 ,  G06F40/279 ,  G10L15/06

Abstract: Provided herein are an electronic apparatus and a method for controlling thereof. The method for controlling an electronic apparatus may include: acquiring a voice command, performing voice recognition of the voice command and acquiring a first text, identifying a prestored indexed word among a plurality of words included in the first text, identifying a rule template among a plurality of prestored rule templates including the indexed word and slots matched to at least one word excluding the indexed word among the plurality of words, and acquiring a control command corresponding to the voice command based on the identified rule template.

公开(公告)号：US11657237B2

公开(公告)日：2023-05-23

申请号：US16966249

申请日：2019-01-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hyungtak Choi ,  Heesik Jeon ,  Jihie Kim ,  Haehun Yang ,  Inchul Hwang ,  Seungsoo Kang ,  Hyunwoo Park ,  Daye Lee

IPC: G06F17/00 ,  G06F40/30 ,  G06F40/56

CPC classification number: G06F40/30 ,  G06F40/56

Abstract: Provided in the present disclosure are an electronic device and a natural language generation method thereof. The natural language generation method of the electronic device comprises: obtaining input data with information on a plurality of slots included for generating a response; obtaining a natural language corresponding to the input data by inputting the information on the plurality of slots to one of artificial intelligence models trained for obtaining a natural language generation template and a natural language; and outputting the obtained natural language. In particular, at least a part of a method for obtaining a natural language in order to provide a response can use an artificial intelligence model having learned according at least one of machine learning, a neural network, or a deep-learning algorithm