公开(公告)号：US20240330688A1

公开(公告)日：2024-10-03

申请号：US18737604

申请日：2024-06-07

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Kyungsu KIM ,  Chang Dong YOO ,  Junyeong KIM ,  Minuk MA

IPC: G06N3/084 ,  G06N3/08 ,  G06V10/766 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V40/16

CPC classification number: G06N3/084 ,  G06N3/08 ,  G06V10/766 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V40/165 ,  G06V40/171

Abstract: Provided are an artificial intelligence (AI) system using a machine learning algorithm such as deep learning, and applications thereof. A method, performed by an electronic apparatus, of processing images includes obtaining a plurality of training image sets corresponding to a plurality of types of target objects, wherein training images in the training image sets are labeled with feature points forming a preset structure, generating a first artificial intelligence (AI) model for determining a standard structure based on the labeled feature points, by using the training images in the training image sets, identifying a face in a training image transformed based on the standard structure, and training a second AI model for verifying the first AI model, based on an image regressed from the transformed training image, and the training image before being transformed.

公开(公告)号：US20230221049A1

公开(公告)日：2023-07-13

申请号：US18124335

申请日：2023-03-21

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Munsub KIM ,  Hyunwuk KANG ,  Jiho BAEK ,  Hyeongjoon SEO ,  Duhan JUNG ,  Jaewoo CHOI ,  Junyeong KIM ,  Taeryong SEONG ,  Sunghee LEE

IPC: F25B41/40 ,  F25B40/02 ,  F16L55/02

CPC classification number: F25B41/40 ,  F25B40/02 ,  F16L55/02 ,  F25B2500/13 ,  F25B2400/075

Abstract: An air conditioner is disclosed. The air conditioner comprises: a compressor for compressing a refrigerant; a discharge pipe for guiding the refrigerant discharged from the compressor; an accumulator for storing the refrigerant flowing into the compressor from an outdoor heat exchanger or an indoor heat exchanger; a suction pipe for guiding the refrigerant discharged from the accumulator to the compressor; a subcooler disposed in a pipe between the outdoor heat exchanger and the indoor heat exchanger so as to secure a degree of subcooling of the refrigerant; an injection pipe for guiding a refrigerant superheated in the subcooler to the compressor; and a fixing member provided for fixing the discharge pipe, the suction pipe, and the injection pipe together.

公开(公告)号：US20240302057A1

公开(公告)日：2024-09-12

申请号：US18665903

申请日：2024-05-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Munsub KIM ,  Hyunwuk KANG ,  Junyeong KIM ,  Taeryong SEONG ,  Jaewoo CHOI ,  Duhan JUNG

IPC: F24F1/12 ,  F04B39/00

CPC classification number: F24F1/12 ,  F04B39/0033

Abstract: Various embodiments of the present disclosure relate to a side felt structure applied to reduce noise emitted from a compressor in an air conditioner. To this end, a device for reducing noise of an air conditioner may comprise: a terminal block disposed to protrude from the outer peripheral surface of a compressor; a side felt disposed to encompass the compressor, and including an opening allowing the terminal block to be seen from the outside; and a terminal block cover felt extending from one side of the opening formed in the side felt, so as to open/close at least a portion of the opening.

公开(公告)号：US20220114836A1

公开(公告)日：2022-04-14

申请号：US17427471

申请日：2020-01-30

Applicant: SAMSUNG ELECTRONICS CO., LTD. ,  KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Kyungsu KIM ,  Chang Dong YOO ,  Junyeong KIM ,  Minuk MA

IPC: G06V40/16 ,  G06V10/776 ,  G06V10/774 ,  G06N3/08 ,  G06V10/82

Abstract: Provided are an artificial intelligence (AI) system using a machine learning algorithm such as deep learning, and applications thereof. A method, performed by an electronic apparatus, of processing images includes obtaining a plurality of training image sets corresponding to a plurality of types of target objects, wherein training images in the training image sets are labeled with feature points forming a preset structure, generating a first artificial intelligence (AI) model for determining a standard structure based on the labeled feature points, by using the training images in the training image sets, identifying a face in a training image transformed based on the standard structure, and training a second AI model for verifying the first AI model, based on an image regressed from the transformed training image, and the training image before being transformed.