Unlock instant, AI-driven research and patent intelligence for your innovation.

A time series anomaly detection method based on unsupervised learning

An unsupervised learning, time series technology, applied in the field of anomaly detection, which can solve problems such as difficulty in obtaining anomalous data

Active Publication Date: 2020-10-02
TONGJI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, anomaly detection is mainly divided into supervised methods and unsupervised methods. The supervised method requires a large amount of abnormally marked data for model training. However, anomalies are often sporadic, so it is difficult to obtain them in real life. large amount of abnormal data

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A time series anomaly detection method based on unsupervised learning
  • A time series anomaly detection method based on unsupervised learning
  • A time series anomaly detection method based on unsupervised learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is carried out on the premise of the technical solution of the present invention, and detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0055] A time series anomaly detection method based on unsupervised learning, which mainly includes two steps: model training and anomaly detection, such as figure 1 shown, including:

[0056] Segment the time series data at the position where it changes significantly, and fill each segmented data segment to a set length; in order to achieve the above requirements, the flow chart of the model training steps of the present invention is as follows figure 2 shown. The data preprocessing includes two steps:

[0057] Data segmentation: first find all the extreme points of the sequence,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention involves a time sequence abnormal detection method based on unsupervised learning, including: cutting time sequence data in its significant changes, and filling the data segment after each divisionThe time sequence sequence is divided into and filled in multiple data segments in the state training a neural network for abnormal detection; multiple data segments that will be divided by the time sequence to be detected will be detectedOutput abnormal scores; judging whether the abnormal score exceeds the threshold, if it is, it is judged that the abnormalities occur, otherwise, the judgment is not abnormal.Compared with the existing technology, the invention has the advantages of unreasonable abnormal data, no loss of data information, and excellent performance.

Description

technical field [0001] The invention relates to an anomaly detection method, in particular to a time series anomaly detection method based on unsupervised learning. Background technique [0002] Anomaly Detection (Anomaly Detection) is a means of detecting anomalies in data. "Anomaly" refers to patterns that do not conform to normal behaviors. For example, in the field of network traffic analysis, normal patterns refer to normal network access behaviors, and abnormal patterns are Refers to the behavior of network intruders. Anomaly detection is used in many fields, such as medical and health fields, network security fields, financial security fields, system maintenance fields, and so on. [0003] Time series (Time Series) refers to a series of data in the form of <time stamp, data>. Time series are often used to record data such as system operation status and human health data in real time. By analyzing time series data, it is possible to judge the status of the syste...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L29/06G06F21/55G06K9/62G06N3/04
CPCH04L63/1425G06F21/552G06N3/044G06N3/045G06F18/214
Inventor 杨恺刘音希窦绍瑜
Owner TONGJI UNIV