公开(公告)号：US10983808B2

公开(公告)日：2021-04-20

申请号：US16547755

申请日：2019-08-22

Applicant: Electronics and Telecommunications Research Institute

Inventor： Kyoung Ju Noh ,  Hyun Tae Jeong ,  Ga Gue Kim ,  Ji Youn Lim ,  Seung Eun Chung

IPC: G06F9/451 ,  G06F3/01

Abstract: The present invention relates to a method and apparatus for providing an emotion-adaptive user interface (UI) on the basis of an affective computing service, in which the provided service is configured with at least one of a service operation condition, a service end condition, and an emotion-adaptive UI service type on the basis of purpose information of the service, and the detailed pattern is changed and provided on the basis of the purpose information and the usefulness information of the service.

公开(公告)号：US10341461B2

公开(公告)日：2019-07-02

申请号：US15194013

申请日：2016-06-27

Applicant: Electronics and Telecommunications Research Institute ,  SOGANG UNIVERSITY RESEARCH FOUNDATION ,  DIQUEST INC. ,  Soongsil University Research Consortium techno-PARK ,  Pukyong National University Industry-University Cooperation Foundation

Inventor： Kyeong Deok Moon ,  Jong Ho Nang ,  Yun Kyung Park ,  Kyung Sun Kim ,  Chae Kyu Kim ,  Ki Ryong Kwon ,  Kyoung Ju Noh ,  Young Tack Park ,  Kwang Il Lee

IPC: G06F15/16 ,  H04L29/08 ,  G06F17/27 ,  G06F16/435 ,  G06F16/9535

Abstract: Provided are a system and method for automatically recreating personal media through fusion of multimodal features. The system includes a multimodal fusion analyzer configured to analyze semantics of personal media having various forms based on a plurality of modalities and divide the personal media into media fragments which are the smallest units having semantics, a semantic-based intelligent retriever configured to store and retrieve the divided media fragments by considering the semantics, a personal media recommender configured to learn and analyze a profile of a user through modeling the user, and select and recommend a plurality of media fragments wanted by the user among the media fragments retrieved by the semantic-based intelligent retriever, and a personal media creator configured to create new personal media using the plurality of media fragments recommended by the personal media recommender according to a scenario input by the user.

公开(公告)号：US20220207382A1

公开(公告)日：2022-06-30

申请号：US17538398

申请日：2021-11-30

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung Eun CHUNG ,  Chi Yoon JEONG ,  Hyun Tae JEONG ,  Ga Gue KIM ,  Kyoung Ju Noh ,  Jeong Muk LIM ,  Ji Youn LIM

IPC: G06N5/02 ,  G06K9/62 ,  G06N5/04

Abstract: Provided is an apparatus for refining data and improving the performance of a behavior recognition model by reflecting time-series characteristics of a behavior. The apparatus includes: a data pre-processing unit configured to receive training data and real-time data as input, identify a missing value of sensor data, and interpolate the sensor data; a behavior recognition unit configured to, through a behavior recognition model, generate a behavior recognition classification result for the preprocessed real-time data; a data refinement unit configured to correct the behavior recognition classification result to generate a refined dataset; a learning model update unit configured to analyze a similarity of the refined dataset and, based on a result of the analysis, perform learning to generate the behavior recognition model; and an information output unit configured to express a corrected behavior recognition result to a user.

公开(公告)号：US10789961B2

公开(公告)日：2020-09-29

申请号：US16219443

申请日：2018-12-13

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Kyoung Ju Noh ,  Ji Youn Lim ,  Ga Gue Kim ,  Seung Eun Chung ,  Hyun Tae Jeong

IPC: G10L17/26 ,  G06F3/00 ,  G06F9/00 ,  A61B5/053 ,  G06K9/00 ,  G10L15/22 ,  A61B5/0205 ,  H04W88/18 ,  A61B5/16

Abstract: Disclosed is technology for providing a proper UI/UX through various devices or services when occurrence of registered concerned context is predicted or recognized in order to predict or recognize the circumstances that require attention or emotion control with regard to a change in his/her biological information With this, a user designates his/her own biological information range or emotional state with regard to circumstances which catch his/her attention, and registers concerned context by selectively designating attributes of circumstantial elements. Further, a user registers feedback desired to be given and an external device/service desired to interface with when the occurrence of the concerned context is predicted or recognized. According to the attributes of the circumstances designated in the registered concerned context, points in time for collecting and managing UX data are automatically determined, thereby processing and managing the UX data as useful information.