公开(公告)号：US11989658B2

公开(公告)日：2024-05-21

申请号：US16929975

申请日：2020-07-15

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyunseok Kim ,  Myung Eun Kim ,  Seonghyun Kim ,  Young Sung Son ,  Jongkwon Son ,  Soonyong Song ,  Donghun Lee ,  Ingook Jang ,  Jin Chul Choi

IPC: G06N3/092 ,  G06N20/00 ,  G06N7/00

CPC classification number: G06N3/092 ,  G06N20/00 ,  G05B2219/32334 ,  G05B2219/33056 ,  G05B2219/34082 ,  G05B2219/40499 ,  G06N7/00

Abstract: A method and an apparatus for exclusive reinforcement learning are provided, comprising: collecting information of states of an environment through the communication interface and performing a statistical analysis on the states using the collected information; determining a first state value of a first state among the states in a training phase and a second state value of a second state among the states in an inference phase based on analysis results of the statistical analysis; performing reinforcement learning by using one reinforcement learning unit of a plurality of reinforcement learning unit which performs reinforcement learnings from different perspectives according to the first state value; and selecting one of actions determined by the plurality of reinforcement learning unit based on the second state value and applying selected action to the environment.

公开(公告)号：US11763179B2

公开(公告)日：2023-09-19

申请号：US16922310

申请日：2020-07-07

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Myung Eun Kim ,  Seonghyun Kim ,  Hyunseok Kim ,  Young Sung Son ,  Jongkwon Son ,  Soonyong Song ,  Donghun Lee ,  Ingook Jang ,  Jin Chul Choi

IPC: G06Q30/00 ,  G06N5/04 ,  G06N20/00

CPC classification number: G06N5/04 ,  G06N20/00

Abstract: An apparatus and method for abnormal situation detection are disclosed. An abnormal situation detection apparatus can map first sensor data among sensor data transmitted from a plurality of sensors into a vector value, convert it into first situation information in the form of an image pattern, and generate a learning model using the first situation information and an abnormal situation reference range. In addition, the abnormal situation detection apparatus can convert second sensor data among sensor data transmitted from a plurality of sensors into a form that can be input to the learning model, and determine whether an abnormal situation occurs by applying the converted second data to the learning model.