Self-healing rule mining method and device based on big data

Abstract

The embodiment of the invention provides a self-healing rule mining method and device based on big data, and the method comprises the steps: collecting business data, performance data and log data assample data; preprocessing the sample data, and converting the sample data into a form suitable for data mining; association rule mining is carried out on the preprocessed sample data to obtain a certain number of strong association rules, wherein each strong association rule at least comprises service data and performance data; and verifying the strong association rule, and if the strong association rule inevitably corresponds to an abnormal phenomenon, taking the strong association rule as a self-healing rule. According to the embodiment of the invention, the dependence on human experience is greatly reduced, the energy investment of professionals is reduced, and a large amount of manpower is saved.

Description

technical field [0001] The present invention relates to the technical field of data mining, and more specifically, to a method and device for mining self-healing rules based on big data. Background technique [0002] In order to adapt to the increasing number of users and the continuous expansion of business types in the telecommunications industry, the design of the business acceptance system has also developed accordingly, showing the characteristics of complex architecture relationships, large node scale, and frequent system updates. In the face of such a complex, large and changeable "super" system, it is a huge challenge for the operation and maintenance personnel to maintain the goal of abnormally fast recovery. How to quickly locate subtle anomalies in a complex, large, and changeable system and quickly solve them? The current mainstream solution is to realize it through operation and maintenance automation. Driven by automated processes, the basis for judging self-h...

AI Technical Summary

Problems solved by technology

This solution cannot radiate other problems beyond the scope of this fault. The individuality of each rule makes it unable to quickly adapt to system changes, and the rules can easily become invalid. From the perspective of the use effect of the rules, as the system changes, the accuracy of the rules sex is not guaranteed

[0006] To sum up, the existing technical solutions have serious deficiencies, and cannot meet the self-healing needs of current system maintenance in terms of the scope of application of rules, the efficiency of rule output, and the effect of rule use.

Images