Alarm processing method, system and device and storage medium

Abstract

The invention provides an alarm processing method, system and device and a storage medium, and the method comprises the steps: obtaining historical alarm information from a historical database; sequentially carrying out feature processing and clustering processing on the historical alarm information; and processing the processed historical alarm information according to a preset expert processingmethod. According to the alarm processing method provided by the invention, the alarm is converged based on feature extraction and clustering, the processing dimension is reduced, and meanwhile, differences between manufacturers and systems are shielded through structured processing, clustering processing, classification processing and the like. In combination with domain expert operation and maintenance experience, intelligent alarm processing is realized, so that the fault processing efficiency is improved, and the pressure of operation and maintenance personnel is reduced. Besides, the method supports intelligent creation of ITSM event lists and change lists for various fault scenes and intelligent notification of related personnel so that the process risk can be reduced and audit can be avoided.

Description

technical field [0001] The present invention relates to the field of computer technology, and more specifically, to an alarm processing method, system, device and storage medium based on feature extraction and clustering. Background technique [0002] With the rapid expansion of the operation and maintenance scale of the data center, the alarm information volume of various operation and maintenance systems has increased sharply. Taking the data center as an example, there are nearly a thousand major alarms per day on average. For each major alarm, it needs to go through: Notification→login device→view information document (optional)→professional operation and maintenance knowledge judgment and a series of professional manual processing procedures, this processing process currently has the following three major problems: [0003] (1) The efficiency of alarm handling is extremely low. At present, most of the alarms in the alarm information are false alarms, which can be judged...

AI Technical Summary

Problems solved by technology

[0003] (1) The efficiency of alarm handling is extremely low. At present, most of the alarms in the alarm information are false alarms, and it can be judged that there is no need to deal with them after simply logging in to the device. However, even so, it is necessary to check one by one, which wastes a lot of operation and maintenance manpower;

[0004] (2) The professional skills of operation and maintenance personnel are highly required. Operation and maintenance needs to quickly judge each alarm scenario, and quickly deal with it according to various disposal methods. to great risk;

[0005] (3) The data center has strict monitoring and management requirements, and the notification to relevant personnel is not timely, the processing is not timely, and various manual links such as filling in wrong information in the work order will bring greater audit risks

Images