Network Fault Diagnosis Method

Abstract

The invention discloses a network fault diagnosis method and medium, wherein the method comprises: obtaining a real-time sequence flow of KPI indicators, and performing window truncation processing on the real-time sequence flow of KPI indicators to obtain a real-time sequence vector of KPI indicators; The real-time sequence vector of the KPI index and the normal attribute vector of the pre-trained KPI index are tested by K-S distribution to judge whether the real-time sequence vector of the KPI index is distributed normally; when the real-time sequence vector distribution of any KPI index in all KPI indicators is abnormal , the deviation values ​​of all KPI indicators in the K-S distribution test are arranged in order to form a deviation value vector; a new type of gravity clustering model is used to obtain the network fault category with the highest similarity to the deviation value vector according to the deviation value vector, and The network fault category is used as the result of network fault diagnosis; thus, the network fault diagnosis process can be realized without manual intervention, which greatly improves the efficiency and convenience of network intelligent operation and maintenance.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a network fault diagnosis method. Background technique [0002] With the rapid development of information technology, the scale of the network system continues to expand, and the complexity is getting higher and higher. Although the existing diagnosis of network faults can use machines to monitor dynamic indicators, once a network fault is found, manual analysis is still required. Processing to confirm the network fault type is not only time-consuming and laborious, but also greatly reduces the efficiency of network fault diagnosis. Contents of the invention [0003] The present invention aims to solve one of the technical problems in the above-mentioned technologies at least to a certain extent. For this reason, an object of the present invention is to propose a network fault diagnosis method. By monitoring the KPI indicators in the communication network in real time, when ...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of information technology, the scale of the network system continues to expand, and the complexity is getting higher and higher. Although the existing diagnosis of network faults can use machines to monitor dynamic indicators, once a network fault is found, manual analysis is still required. Processing to confirm the type of network fault is not only time-consuming and laborious, but also greatly reduces the efficiency of network fault diagnosis

Images