Intelligent network fault diagnosis method based on knowledge graph

Abstract

The invention discloses an intelligent network fault diagnosis method based on a knowledge graph. The method comprises the following steps: constructing a network information knowledge graph, importing various types of events into the event library, and providing an API for a diagnosis program to call; selecting a time slice, and coloring the equipment generating the abnormal event on the networkinformation knowledge graph; on the basis of coloring of the abnormal network element, ignoring other normal network elements to obtain a network structure diagram only with the abnormal network element, and finding out all connected sub-diagrams in the network structure diagram to obtain all event clusters; calculating the centrality of each event cluster, sorting the event clusters from large tosmall, and taking the event clusters corresponding to the first N centralities as fault points where the root cause events are located. According to the method, the problem of cluster application downtime caused by basic network faults is effectively solved, and the high reliability and the high availability of the cluster application are improved.

Description

technical field [0001] The invention belongs to the technical field of the Internet, and in particular relates to an intelligent network fault diagnosis method. Background technique [0002] At present, people live in a society with advanced Internet information and information technology is ubiquitous. How to ensure the healthy, stable and reliable operation of application systems is very important. With the rapid development of the Internet and mobile Internet, users are becoming more and more picky, and the user experience requirements for application software are getting higher and higher. As we all know, application software is built on a large, complex, and cross-protocol layer large-scale distributed system, and the technology, software, and configuration of this distributed system usually evolve continuously and rapidly, and its software and hardware will inevitably occur. Faults, bugs, changes, unpredictable changes in user traffic, and even security attacks, and...

AI Technical Summary

Problems solved by technology

[0003] Although various operation and maintenance monitoring tools have greatly improved the visibility of system operation status, when encountering operation and maintenance failures, faced with massive monitoring data and huge responsible distributed systems, it still relies on operation and maintenance personnel to make manual work under high pressure. It is obviously unrealistic to make quick and accurate operation and maintenance decisions

Images