公开(公告)号：US20250131327A1

公开(公告)日：2025-04-24

申请号：US18506600

申请日：2023-11-10

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Woo Ri KO ,  Jae Hong KIM ,  Min Su JANG

IPC: G06N20/00

Abstract: The present invention relates to a method and apparatus for re-training model by recognizing uncertainty in online user behavior detection. A method for training a model related to user behavior detection according to an embodiment of the present disclosure may comprise: detecting one or more behavior instances having a type of user behavior and a time interval of the user behavior; calculating at least one of a first uncertainty value for the type of user behavior or a second uncertainty value for the time interval of the user behavior; generating a first data newly labeling the type of user behavior or a second data newly labeling the time interval of the user behavior; and training a model that recognizes the user behavior information on a frame-by-frame basis.