Root cause positioning method and system based on machine learning

Abstract

The invention discloses a root cause positioning method based on machine learning, and the method comprises the steps: obtaining call chain data composed of data of a call process in a micro-service application system, and obtaining business index data, container indexes, middleware indexes, host indexes and database index data of the micro-service application system; and inputting the timestamp, the average calling time, the business volume, the success quantity and the success rate in the acquired business index data into a trained support vector machine (SVM) network to obtain a detection result, judging whether the detection result is abnormal or not, performing root cause detection on the obtained detection result if the detection result is abnormal, and if the detection result is abnormal, performing root cause detection on the obtained detection result. Therefore, the node with the fault and the performance index causing the fault are obtained. The technical problem that an existing root cause detection method based on static threshold setting is low in accuracy can be solved, and the technical problem that an existing root cause detection method based on a sliding window is difficult to recognize periodic characteristics of actual data indexes can be solved.

Description

technical field [0001] The invention belongs to the technical field of intelligent operation and maintenance, and more specifically relates to a root cause location method and system based on machine learning. Background technique [0002] Large-scale Internet companies jointly provide external services through service clusters, and at the same time, business services will become bloated with the increase in product demand, and the structure will be split. Large-scale services will be split into small independent services, and each small service will be run by an independent process. To manage to provide services to the outside world, this is "microservices". [0003] Microservices applications use a microservices architecture to build applications as independent components and run each application process as a service. These services communicate through well-defined interfaces using lightweight APIs. These services are built around business functions, and each service ind...

AI Technical Summary

Problems solved by technology

[0007] In view of the above defects or improvement needs of the prior art, the present invention provides a root cause location method and system based on machine learning, the purpose of which is to solve the technical problem of low accuracy of the existing root cause detection method based on static threshold setting , and the technical problem that the existing root cause detection method based on sliding window is difficult to identify the periodic characteristics of the actual data index, and the technical problem that can only identify a single index anomaly without good interpretability

Images