Registered DANGEROUS SITUATION DETECTION METHOD AND APPARATUS USING TIME SERIES ANALYSIS OF USER BEHAVIORS

Inventors

Kim Hyo Jin, Park Hyunho, Lee Yong Tae, Kwon Eun Jung, Byon Sungwon, Jung Eui Suk

Application No.

16387327 (2019.04.17)

Publication No.

20190325728 (2019.10.24)

Registration No.

10810856 (2020.10.20)

Country

UNITED STATES

Project Code

18HR1800, Platform Development of Multi-log based Multi-Modal Data Convergence Analysis and Situational Response, Lee Yong Tae

Abstract

The present invention relates to dangerous situation detection method and apparatus using a time series analysis of user behaviors. The dangerous situation detection method and apparatus using a time series analysis of user behaviors according to the present invention includes recognizing user behaviors in a time series manner using sensor sensing data, setting stability interval periods and reflecting stability factors on the user behaviors recognized in the time series manner for each of the stability interval periods to set a stability level, and determining a danger level on the basis of the recognized user behaviors and the set stability level.

KSP Keywords

Detection Method, Sensing data, Set stability, Situation Detection, Stability interval, Time Series Analysis(TSA), Time series, User Behavior

Family

 

패밀리 특허 목록

Status	Patent	Country	KIPRIS
Registered	사용자 행동의 시계열 분석을 활용한 위험 상황 인지 방법 및 장치	KOREA	KIPRIS