Root alarm analysis and recognition method based on data mining

A technology of data mining and identification methods, which is applied in the fields of electrical digital data processing, instruments, hardware monitoring, etc., to ensure the quality of operation and maintenance work, improve the efficiency of operation and maintenance work, and reduce the cost of operation and maintenance.

Inactive Publication Date: 2016-12-21
INSPUR QILU SOFTWARE IND
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in different technology networks, different manufacturers of equipment, and even different types of equipment of the same manufacturer, the alarm event tree is very different. The upgrade and transformation of the equipment network management will also have a certain impact on the alarm event tree, and the accurate and durable alarm derivation rules can be concluded. It is a difficulty and pain point in this technical field

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
  • Root alarm analysis and recognition method based on data mining
  • Root alarm analysis and recognition method based on data mining
  • Root alarm analysis and recognition method based on data mining

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] The method for analyzing and identifying root alarms based on data mining described in this embodiment includes two steps: 1) generation of alarm derivation rules by machine learning and 2) analysis of root alarms by an expert system.

[0025] In order to solve the problem of difficulty in obtaining existing alarm derivation rules, 1) the machine learning generates alarm derivation rules, fully combines the learning method of production rules in the field of machine learning with specific application practices, and performs data mining on the historical alarm database, Using the "generated" behavior strategy, learn the alarm derivation rules, store them in the knowledge base, and use them as the knowledge input for the expert system to analyze root alarms. The machine learning to generate alarm derivation rules includes three steps: a) historical alarm extraction, b) production rule matching, c) alarm derivation rule generation and d) optional manual supervision and guid...

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 root alarm analysis and identification method based on data mining, which belongs to the field of communication network operation and maintenance. An alarm group is generated by reading historical alarms and resource information from a historical alarm database and a resource database and matching them with production rules; at the same time, Optional manual supervision and guidance for setting production rules, seed alarms, and rule effective thresholds; identify the root alarm in the alarm group, generate alarm derivative rules and store them in the knowledge base; when a new alarm is received, obtain the alarm time from the real-time alarm base When an alarm is approaching, read the resource database to analyze the correlation of alarm resources; continue to search the knowledge base, and identify the alarm as a root alarm, a derived alarm, and an undetermined alarm. The present invention greatly reduces the work intensity of the operation and maintenance personnel to monitor and process massive alarms, improves the operation and maintenance work efficiency, can guarantee the operation and maintenance work quality, reduces the operation and maintenance cost, and has strong practicability.

Description

technical field [0001] The invention belongs to the field of communication network operation and maintenance, and specifically relates to a root alarm analysis and recognition method based on data mining. Background technique [0002] In recent years, the communication network operation and maintenance work has been developing in the direction of centralized communication supervision, centralized command and dispatch, and the construction of network management tools has also shown a trend of unified construction, unified push, and unified management. A large number of alarms make the work intensive and difficult. In fact, the alarms of each device are related to a certain extent. Analyzing the root alarms that O&M personnel should pay attention to and basically responding to network faults, identifying the derivative alarms that accompany the root alarms, and effectively compressing the alarms will improve the efficiency of O&M work and ensure the operation and maintenance. ...

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
IPC IPC(8): G06F11/30
CPCG06F11/3072
Inventor 王添刘益畅高磊张顺来倪腾飞
Owner INSPUR QILU SOFTWARE IND
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap