-
公开(公告)号:US20230245424A1
公开(公告)日:2023-08-03
申请号:US18159976
申请日:2023-01-26
Applicant: Samsung Electronics Co., Ltd.
Inventor: Seohyun BACK , Taeho KIL , Gyubin SON , Hyunsoo CHOI
IPC: G06V10/764 , G06V10/82 , G06V10/77 , G06V10/26
CPC classification number: G06V10/765 , G06V10/82 , G06V10/7715 , G06V10/26
Abstract: A server for classifying an image and a method of operating the server are provided. The method includes obtaining classification probability values of the image, by applying the image to an image classification model including a plurality of parallel multi-layer perceptron (MLP) layers, and classifying the image, based on the classification probability values, wherein each of the plurality of parallel MLP layers includes a first MLP and a second MLP, an operation using the first MLP and an operation using the second MLP are performed in parallel, and dimensions of data before and after an operation of each of the plurality of parallel MLP layers are same by combining an operation result of the first MLP with an operation result of the second MLP.
-
公开(公告)号:US20190180747A1
公开(公告)日:2019-06-13
申请号:US16211973
申请日:2018-12-06
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Seohyun BACK , Doohwa HONG , Jongyoub RYU , Jiyeon HONG , Eunkyoung KIM , Sungja CHOI , Jaewon LEE , Sathish INDURTHI
Abstract: The disclosure relates to a voice recognition apparatus for analyzing a user input based on content and generating and outputting an answer and an operation method thereof, the operation method including receiving an audio signal and performing voice recognition on the audio signal; acquiring content information of content being executed; analyzing a user input based on the content information from a voice recognized by performing the voice recognition; generating an answer based on the analyzed user input and the content information; and outputting the answer.
-
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
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:US20220231979A1
公开(公告)日:2022-07-21
申请号:US17675632
申请日:2022-02-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Seohyun BACK , Taeho KIL , Kyungsu KIM , Sungjin KIM , Hojin JUNG
IPC: H04L51/10 , H04L51/224 , G06V10/422 , G06V10/74
Abstract: Provided are a device and method for providing a notification message related to content. The method includes: recognizing an action related to at least one object in the image content by applying the image content to a first artificial intelligence model for identifying the action of the at least one object; determining target images for identifying the at least one object in the image content; obtaining identification information of the at least one object in the target images by applying the target images to at least one second artificial intelligence model for identifying the at least one object; and generating the notification message describing the image content by applying, to a third artificial intelligence model, an identification value indicating the action and the identification information of the at least one object.
-
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
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:US20220223141A1
公开(公告)日:2022-07-14
申请号:US17670992
申请日:2022-02-14
Applicant: Samsung Electronics Co., Ltd.
Inventor: Seohyun BACK , Taeho KIL , Kyungsu KIM , Daehun KIM , Sungjin KIM , Younguk KIM , Hyunhan KIM , Gyubin SON , Hojin JUNG
Abstract: An electronic apparatus is provided. The electronic apparatus includes a communication interface, a memory storing at least one instruction, and a processor, wherein the processor is configured to acquire a user command from the user and control the communication interface to transmit the user command to a plurality of external devices, receive, from the plurality of external devices, information on a first question generated based on the user command and information on first response to the generated first question acquired from users of each of the plurality of external devices, identify whether there a conflict between each first response occurs by analyzing the received information on the first response based on identification that the conflict occurs, acquire information on a subject to be re-questioned based on the generated information on the first question and the received information on the first response, control the communication interface to transmit information on the conflict to at least one external device identified based on the information on the subject to be re-questioned, receive, from the identified at least one external device, information on a second response to a second question generated based on the information on the conflict, and acquire a final response based on the information on the first response and the information on the second response and output the final response.
-
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
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.
-
8.
公开(公告)号:US20200233639A1
公开(公告)日:2020-07-23
申请号:US16718672
申请日:2019-12-18
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor: Seohyun BACK , Seunghak YU , Huiwon YUN , Hojin JUNG
Abstract: Provided are an artificial intelligence (AI) system that mimics cognitive functions, such as recognition and determination, of the human brain using a machine learning algorithm such as deep learning and an application thereof. A method of providing feedback information in response to a user input including determining a user's intention, determining a variation in a number of candidates for an operation to be determined to correspond to the intention based on information input by the user, generating feedback information based on the determined variation, and providing the generated feedback information to the user is provided.
-
-
-
-
-
-
-