Prediction method and device for alarm in service operation and maintenance and electronic equipment

Abstract

The embodiment of the invention provides an alarm prediction method and device in service operation and maintenance and electronic equipment, and the method comprises the steps: obtaining a given number of historical alarm data of a target network element object before a current alarm period, and forming a historical alarm sequence; based on the historical alarm sequence, performing alarm prediction on the target network element object by using a trained hidden Markov prediction model, wherein the trained hidden Markov prediction model is obtained by performing initialization construction in advance by analyzing relationship information of a network element object, a network element fault and a network element alarm in a fault management system, and performing training by utilizing an original data sample selected according to the relationship information. According to the embodiment of the invention, the accuracy of alarm prediction in service operation and maintenance can be effectively improved, so that faults are effectively avoided or the influence caused by the faults is reduced.

Description

technical field [0001] The present invention relates to the technical field of IT operation and maintenance, and more specifically, to a method, device and electronic equipment for predicting alarms in business operation and maintenance. Background technique [0002] In the field of IT operation and maintenance, a complete operation and maintenance system includes a system with fault management capabilities, which is usually called a fault management system. Traditional fault management systems generally have functions such as equipment alarm monitoring, business indicator monitoring, fault response, and fault location. [0003] Traditional fault management systems are "behindsight" about equipment alarm monitoring. That is, after the relevant collection tool obtains the data, it finds that the data triggers the corresponding rules before generating an alarm and reviewing the dispatch. Usually, the shorter the process from alarm discovery to order dispatch, the less impact...

AI Technical Summary

Problems solved by technology

However, since this method is only a regular summary of the existing alarm data, it cannot truly reflect the status of the equipment, resulting in low accuracy of alarm prediction for specific equipment

Images