Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method and device for identifying abnormal data of monitoring index data

A technology of index data and data anomalies, applied in the field of operation and maintenance, can solve problems such as large number of alarms, high maintenance costs, and easy complaints, etc., to achieve the effect of reducing data errors, improving accuracy, and increasing real-time performance

Pending Publication Date: 2020-11-24
CHINANETCENT TECH
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the verification period of the above method is long, the maintenance cost is high, and it leads to a large number of alarms and false alarms, which makes the accuracy and coverage of monitoring and early warning low, and it is impossible to find and solve faults in time, and it is easy to generate complaints. Therefore, there is an urgent need for a A method for identifying abnormal data of monitoring index data, which improves the accuracy of alarms and reduces the amount of alarms

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
  • Method and device for identifying abnormal data of monitoring index data
  • Method and device for identifying abnormal data of monitoring index data
  • Method and device for identifying abnormal data of monitoring index data

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0112] Such as image 3 as shown, image 3 An exemplary schematic diagram showing a method for identifying abnormal data of monitoring index data, the specific steps are as follows:

[0113] Step 301, delete outliers.

[0114] Obtain historical indicator data from 15:1 to 15:10 every day in the 28 days before the current moment, with a total of 280 samples. Then, for the 10 historical index data of each day, the outliers in the 10 sample data of each day are deleted by the Gaussian function.

[0115] In step 302, a sample set is determined.

[0116] Calculate the average of the daily historical index data after removing outliers to obtain the daily sample data, and then determine that there are 28 sample sets J.

[0117] Step 303, judging whether there is periodicity, if so, go to step 304, otherwise go to step 305.

[0118] Step 304, generating predicted values.

[0119] For a periodic sample set J, the sample set J is input into the LSTM training model to obtain the pr...

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 invention discloses a method and a device for identifying abnormal data of monitoring index data. The method comprises the steps of: obtaining index data at a current moment, determining the prediction interval of the index data according to the historical index data in a preset period, and determining the fluctuation value of the index data according to the prediction interval and the index data at the current moment; when the fluctuation value does not accord with a fluctuation threshold, determining that the index data is problem data, the fluctuation threshold being obtained by comparing the index data with historical index data in a first time period before the current moment; and if the index data at the current moment is stable, determining the problem data as abnormal data. Theindex data at the current moment is identified according to the historical index data, and the alarm accuracy is improved; and the problem data is determined as abnormal data according to the stability of the index data at the current moment, so that the accuracy of identifying the abnormal data is improved, and false alarms caused by data increment or data cutting are reduced.

Description

technical field [0001] The invention relates to the field of operation and maintenance, in particular to a method and device for identifying abnormal data of monitoring index data. Background technique [0002] In the existing technology, the scale of operation and maintenance data is large, explosive growth, and the types of monitoring indicators increase, such as: system indicators (such as memory usage overload, etc.), business indicators, but the indicator features are many and complicated, and the content included in the indicator features is becoming more and more abundant , such as: stable trend, periodic changes, large fluctuations, etc. [0003] In terms of technology for monitoring indicators, the existing technology is to set thresholds through traditional manual experience to monitor indicator data, and to notify users by generating alarms when thresholds are exceeded. [0004] However, the verification period of the above method is long, the maintenance cost is...

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 Applications(China)
IPC IPC(8): G06F11/30G06N3/04G06N3/08
CPCG06F11/3037G06F11/3051G06F11/3072G06N3/049G06N3/08G06N3/045
Inventor 蒋龙威
Owner CHINANETCENT TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products