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

Network fault analysis method and device

A technology of network failure and analysis method, applied in the field of network maintenance, can solve the problems of low analysis efficiency and low accuracy, and achieve the effect of improving accuracy, improving efficiency and accuracy, and realizing automatic analysis.

Active Publication Date: 2020-11-17
GUANGDONG PLANNING & DESIGNING INST OF TELECOMM
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, when performing network maintenance, network failures are mainly analyzed manually: communication operators analyze communication network failures, business terminal equipment manufacturers check terminal equipment failures, and communication module manufacturers conduct communication module failures. For troubleshooting, the company's IT department conducts fault analysis on the intranet, and finally combines the above-mentioned multi-party feedback information with manual experience to confirm the cause of the network fault. However, practice has found that the analysis efficiency and accuracy of this network fault analysis method are not high.

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
  • Network fault analysis method and device
  • Network fault analysis method and device
  • Network fault analysis method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] see figure 1 , figure 1 It is a schematic flowchart of a network fault analysis method disclosed in an embodiment of the present invention. Such as figure 1 As shown, the network failure analysis method may include the following operations:

[0046] 101. Acquire a time-series data set corresponding to a service terminal in a current fault analysis period, the time-series data set includes at least one type of time-series data, and the time-series data included in the time-series data set is used to determine the network status of the service terminal.

[0047]In an optional embodiment, the time series data in the time series data set includes the data used to represent the virtual / physical server resources occupied by the AMF in the 5G slice corresponding to the service terminal, and the data used to represent the virtual / physical server resources occupied by the UPF corresponding to the service terminal. The data of physical server resources, the data used to repres...

Embodiment 2

[0147] see figure 2 , figure 2 It is a schematic flowchart of another network failure analysis method disclosed in the embodiment of the present invention. Such as figure 2 As shown, the network failure analysis method may include the following operations:

[0148] 201. Acquire a time-series data set corresponding to a service terminal in a current fault analysis period, the time-series data set includes at least one type of time-series data, and the time-series data included in the time-series data set is used to determine the network status of the service terminal.

[0149] 202. Calculate a year-on-year characteristic value corresponding to each type of time series data in the time series data set.

[0150] 203. Calculate the ring-to-chain eigenvalue corresponding to each type of time series data in the time series data set.

[0151] 204. Calculate the time-series feature value corresponding to this type of time-series data according to the year-on-year feature value ...

Embodiment 3

[0178] see image 3 , image 3 It is a schematic flowchart of a training method for a network fault discrimination model disclosed in an embodiment of the present invention. Such as image 3 As shown, the training method of the network fault discrimination model may include the following operations:

[0179] 301. Obtain multiple training data sets corresponding to service terminals in multiple training analysis cycles, one training analysis cycle corresponds to one training data set, each training data set includes at least one type of training data, and the training data set includes training The data is used to determine the network status of the service terminal.

[0180] 302. For each training data set, calculate a year-on-year feature value corresponding to each type of training data in the training data set.

[0181] 303. For each training data set, calculate the ring ratio feature value corresponding to each type of training data in the training data set.

[0182] ...

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 network fault analysis method and apparatus. The method comprises the steps of obtaining a time series data set corresponding to a service terminal in a current fault analysis period; calculating a year-on-year characteristic value and a loop ratio characteristic value corresponding to each type of time series data in the time series data set; calculating a time sequencefeature value according to the year-on-year ratio feature value and the loop ratio feature value; determining the state statistics of each global classification space resource; generating in-mold dataaccording to the time sequence characteristic value and the state statistics; and inputting the modeling data into a predetermined network fault discrimination model for analysis to obtain a networkdiscrimination result. Visibly, by implementing the method and the device, the time sequence data of the service terminal in the network can be automatically obtained, and then the judgment result ofthe network fault is obtained by analyzing based on the time sequence data, so that the automatic analysis of the network fault can be realized, the efficiency and accuracy of network fault analysis are improved, and the intellectualization of a power grid system is realized.

Description

technical field [0001] The invention relates to the technical field of network maintenance, in particular to a network fault analysis method and device. Background technique [0002] In recent years, the wide application of Internet of Things technology in the power grid system has greatly promoted the reform of the power grid system. The Internet of Things technology has gradually penetrated into all aspects of the power grid system (the Internet of Things technology has gradually been applied in power grid distribution automation, metering automation, direct reading of electric meters, etc.), which has improved the depth and breadth of information perception in each link of the power grid system. [0003] In practical applications, tens of millions of service terminals are scattered in every corner of the power grid system. These service terminals form a huge network through communication connections, and the maintenance of this network has become increasingly prominent. ...

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): H04L12/24
CPCH04L41/0631H04L41/064H04L41/065H04L41/145
Inventor 黄伟如赵仕嘉林涛李晁铭杨鹤鸣麦洪永黄贵平
Owner GUANGDONG PLANNING & DESIGNING INST OF TELECOMM