公开(公告)号：US20250139188A1

公开(公告)日：2025-05-01

申请号：US18889622

申请日：2024-09-19

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Jeong Heo ,  Oh Woog Kwon ,  Jihee Ryu ,  Young-Ae Seo ,  Jin SEONG ,  Jong Hun Shin ,  Ki Young Lee ,  Yo Han Lee ,  Soojong Lim

IPC: G06F17/11 ,  G06F40/205 ,  G06F40/40 ,  G06V10/86

Abstract: A method for problem inference based on multi-modal generative artificial intelligence includes receiving question information including an image and text, generating formal languages by parsing the image and text of the question information, respectively, based on a pre-constructed problem solving template, generating text-based intermediate inference information for the question information by inputting the generated formal language to a formal language inference unit, generating image-based inference information by inputting the text-based intermediate inference information, the text included in the question information (hereinafter referred to as “text question information”), and the image included in the question information (hereinafter referred to as “image question information”) to a multi-modal image generation model, and generating text-based inference information by inputting the text-based intermediate inference information, the image-based inference information, and the text question information to a multi-modal text generation model.

公开(公告)号：US11663479B2

公开(公告)日：2023-05-30

申请号：US15896409

申请日：2018-02-14

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yo Han Lee ,  Young Kil Kim

IPC: H04N19/187 ,  H04N19/33 ,  G06N3/082 ,  G06N3/08 ,  G06F40/10 ,  G06F40/40 ,  G06F40/44 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06N3/082 ,  G06F40/10 ,  G06F40/40 ,  G06F40/44 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

Abstract: Provided is a method of constructing a neural network translation model. The method includes generating a first neural network translation model learning a feature of source domain data used in an unspecific field, generating a second neural network translation model learning a feature of target domain data used in a specific field, generating a third neural network translation model learning a common feature of the source domain data and the target domain data; and generating a combiner combining translation results of the first to third neural network translation models.

公开(公告)号：US11544479B2

公开(公告)日：2023-01-03

申请号：US16751764

申请日：2020-01-24

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Yo Han Lee ,  Young Kil Kim

IPC: G06F40/58 ,  G06N3/08 ,  G06F17/16 ,  G06F16/901 ,  G06F17/18 ,  G06F40/44

Abstract: Provided are a method and apparatus for constructing a compact translation model that may be installed on a terminal on the basis of a pre-built reference model, in which a pre-built reference model is miniaturized through a parameter imitation learning and is efficiently compressed through a tree search structure imitation learning without degrading the translation performance. The compact translation model provides translation accuracy and speed in a terminal environment that is limited in network, memory, and computation performance.

公开(公告)号：US20190114545A1

公开(公告)日：2019-04-18

申请号：US15896409

申请日：2018-02-14

Applicant: Electronics and Telecommunications Research Institute

Inventor： Yo Han Lee ,  Young Kil Kim

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/21 ,  G06F17/28

Abstract: Provided is a method of constructing a neural network translation model. The method includes generating a first neural network translation model learning a feature of source domain data used in an unspecific field, generating a second neural network translation model learning a feature of target domain data used in a specific field, generating a third neural network translation model learning a common feature of the source domain data and the target domain data; and generating a combiner combining translation results of the first to third neural network translation models.