公开(公告)号：US20230351117A1

公开(公告)日：2023-11-02

申请号：US17925732

申请日：2020-06-25

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Kyo Joong Oh ,  Ho Jin Choi

IPC: G06F40/35 ,  G06F16/332 ,  G06Q10/0633

CPC classification number: G06F40/35 ,  G06F16/3329 ,  G06Q10/0633

Abstract: A conversation intention real-time analysis method is provided. The conversation intention real-time analysis method includes the steps of: determining, by a natural language conversation understanding unit, conversation information regarding a response and a response policy depending on whether a refined sentence refined by a natural language conversation preprocessing unit for determining a question to be answered by analyzing a sentence; outputting, a conversation context, and extracting a response; collecting, by a situation information collection unit, situation information by standardizing a field situation, user information, business information, and domain information; detecting, by a field-directed type response management unit, a refined response according to situation information generated by the situation information collection unit from among the conversation information; and transmitting, by a response providing unit, a final response to a portable device by detecting the final response from the refined response detected by the field-directed type response management unit.

公开(公告)号：US20230206661A1

公开(公告)日：2023-06-29

申请号：US17920067

申请日：2020-12-28

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Ho Jin Choi ,  Seung Ho Han

IPC: G06V20/70 ,  G06F40/166 ,  G06V10/82

CPC classification number: G06V20/70 ,  G06F40/166 ,  G06V10/82

Abstract: An apparatus for automatically generating a domain-specific image caption using a semantic ontology is provided. The apparatus includes a caption generator configured to generate an image caption in the form of a sentence describing an image provided from a client, in which the client includes a user device, and the caption generator includes a server connected to the user device through a wired/wireless communication method.

公开(公告)号：US20230177854A1

公开(公告)日：2023-06-08

申请号：US17925354

申请日：2020-06-16

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Seung Ho Han ,  Ho Jin Choi

IPC: G06V20/70 ,  G06T7/90 ,  G06V10/44 ,  G06F40/44

CPC classification number: G06V20/70 ,  G06F40/44 ,  G06T7/90 ,  G06V10/44 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/07

Abstract: apparatus and method for automatically generating an image caption is provided capable of giving an explanation by using Bayesian inference and an image area-word mapping module on the basis of a deep learning algorithm. An apparatus for automatically generating an image caption, according to one embodiment of the present invention, includes: an automatic caption generation module for creating a caption by applying a deep learning algorithm to an image received from a client; a caption basis generation module for creating a basis for the caption by mapping a partial area in the image received from the client with respect to important words in the caption received from the automatic caption generation module; and a visualization module for visualizing the caption received from the automatic caption generation module and the basis for the caption received from the caption basis generation module to return same to the client.