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：US20250148223A1

公开(公告)日：2025-05-08

申请号：US19013494

申请日：2025-01-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yonghyun RYU ,  Jiho SHIN

IPC: G06F40/58 ,  G06F40/279 ,  G06F40/30

Abstract: An electronic device is disclosed. The electronic device comprises: a memory storing a first translation model configured to translate using a first translation method and a second translation model configured to translate using a second translation method; and at least one processor, comprising processing circuitry, individually and/or collectively, is configured to: based on original text and a translation intention being input, identify whether a word corresponding to the translation intention exists in learning data; based on a word corresponding to the translation intention existing in the learning data, generate first translated text of the original text based on the first translation model and the translation intention; and, based on a word corresponding to the translation intention not existing in the learning data, generate second translated text of the original text based on the second translation model and the translation intention.

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.