TRAFFIC ABNORMALITY DETECTION METHOD, AND MODEL TRAINING METHOD AND APPARATUS

Title:

TRAFFIC ABNORMALITY DETECTION METHOD, AND MODEL TRAINING METHOD AND APPARATUS

Document Type and Number:

WIPO Patent Application WO/2021/027697

Kind Code:

A1

Abstract:

Provided is a traffic abnormality detection method. The method comprises: acquiring a target time sequence comprising N elements; according to the target time sequence, acquiring a target parameter of the target time sequence, with the target parameter comprising a periodic factor and/or a jitter density, wherein the periodic factor represents a wave-shaped variation, presented in the target time sequence, regarding a long-term trend, and the jitter density represents the deviation of an actual value of the target time sequence in a target time from a target value; according to the target parameter, determining, from among a plurality of types, a first type of the target time sequence, wherein each of the plurality of types corresponds to one parameter set, and the target parameter belongs to the parameter set corresponding to the first type; and according to a first-type determination model corresponding to the first type, detecting the abnormality of the target time sequence, wherein each of the plurality of types corresponds to one type of determination model. By means of the technical solution, the precision of traffic abnormality detection can be improved.

Inventors:

ZHANG YANFANG (CN)
LI GANG (CN)
XUE LI (CN)
LIN WEI (CN)

Application Number:

PCT/CN2020/107627

Publication Date:

February 18, 2021

Filing Date:

August 07, 2020

Export Citation:

Click for automatic bibliography generation Help

Assignee:

HUAWEI TECH CO LTD (CN)

International Classes:

H04L12/24; H04L12/26

Foreign References:

CN110266552A	2019-09-20
CN109862129A	2019-06-07
CN106685750A	2017-05-17
CN109783876A	2019-05-21
CN106095655A	2016-11-09
US20170011299A1	2017-01-12
US20190102276A1	2019-04-04
CN201910752193A	2019-08-15

Other References: