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

Method and device for automatic detection of network element abnormal behavior

An anomaly and behavioral technology, applied in the field of communication, to achieve the effect of effective detection

Active Publication Date: 2019-03-05
CHINA UNITED NETWORK COMM GRP CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the prior art lacks an automatic and effective method for detecting the abnormal behavior of network elements

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 automatic detection of network element abnormal behavior
  • Method and device for automatic detection of network element abnormal behavior
  • Method and device for automatic detection of network element abnormal behavior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] figure 1 It is a flowchart of a method for automatically detecting abnormal network element behavior provided by an embodiment of the present invention. The embodiment of the present invention provides an automatic detection method for network element abnormal behaviors in view of the lack of effective detection methods for network element abnormal behaviors in the prior art. The specific steps of the method are as follows:

[0030] Step S101, acquiring a historical data set corresponding to a key performance indicator of the communication network, the historical data set includes a multi-dimensional historical data set and a one-dimensional historical data set;

[0031] Obtain the historical data set corresponding to the Key Performance Indicator (KPI) of the communication network. The key performance indicator includes a multi-dimensional historical data set and a one-dimensional historical data set. The multidimensional historical dataset and the one-dimensional his...

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 embodiment of the invention provides an automatic network element abnormal behavior detection method and device. The method includes the steps that a historical data set corresponding to the key performance index of a communication network is obtained; clustering processing is conducted on a multidimensional historical data set or a multidimensional historical data set composed of multiple one-dimensional historical data, a characteristic mode library is obtained, and the characteristic mode library is subjected to classification processing, and a characteristic classification model is obtained; a multidimensional predication value corresponding to the key performance index at the next moment is predicted according to the multidimensional historical data set; a predication characteristic mode to which the multidimensional predication value belongs is judged according to the characteristic classification model, and an observation characteristic mode to which a multidimensional observation value corresponding to the key performance index at the next moment belongs is judged; the predication characteristic mode and the observation characteristic mode are compared, and whether the network element behavior is abnormal or not is judged. By means of the method and device, the network element abnormal behavior is automatically detected effectively.

Description

technical field [0001] Embodiments of the present invention relate to the field of communication technologies, and in particular to a method and device for automatically detecting abnormal behavior of network elements. Background technique [0002] With the development of mobile communication technology, the structure of the mobile communication network becomes more and more complex, the number of network elements in the mobile communication network continues to increase, and the polymorphism of network elements continues to increase. [0003] If a network element is abnormal, it is necessary to diagnose or repair the network element. Therefore, it is necessary to detect the behavior of the network element at all times to discover the abnormal behavior of the network element in time and reduce the workload of manual network abnormality monitoring. However, the prior art lacks a method for automatically and effectively detecting the abnormal behavior of network elements. Co...

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): H04L29/06H04L12/24
CPCH04L41/145H04L41/147H04L63/1416H04L63/1425
Inventor 曾柏森韩振东
Owner CHINA UNITED NETWORK COMM GRP CO LTD