Abnormal state detection method and system, storage medium, program and server

Abstract

The invention belongs to the technical field of server fault processing, and discloses an abnormal state detection method and system, a storage medium, a program and a server, being characterized in that unsupervised learning is performed on LSTM1, and supervised learning is performed on LSTM2 and server faults are quickly solved by utilizing log information; an LSTM1 recurrent neural network is adopted to predict the log information with the time sequence characteristic, and an alarm is given out by identifying abnormal occurrence of the log information, and operation and maintenance personnel are assisted in checking fault reasons; and the LSTM2 gives out a fault reason causing the current situation through log information in a period of time before the fault occurs. According to the abnormal state detection method, a machine learning method is adopted, and an applicable model is learned through data automation; and deep learning is adopted, and a data structure accepted by a bit neural network is converted, and a recurrent neural network is adopted, and long-term and short-term dependency relationships in log relationships are mined. In supervised learning, the potential relationship between the log sequence and the fault cause can be found.

Description

technical field [0001] The invention belongs to the technical field of server failure processing, and in particular relates to an abnormal state detection method, system, storage medium, program and server. Background technique [0002] The normal operation of the server is crucial to every enterprise or other organization. Once the server fails, the possible losses are immeasurable. Server failures are usually divided into hardware failures and software failures. About 70% of the failures are caused by software, which may cause server downtime in severe cases. For troubleshooting, there are many commercial software, such as: IBM Tivoli software allows customers to spend less time diagnosing problems and deploying solutions, and spend more time effectively managing their own business; splunk is a managed log file management tool that requires significant skill and domain knowledge to use. CA Spectrum is an industry-leading infrastructure and fault management solution tha...

AI Technical Summary

Problems solved by technology

[0004] Through the above analysis, the existing problems and defects of the existing technology are: the scale and complexity of the server continue to increase, resulting in the diversity of server software failures; the failure to issue early warning information for possible problems in the future

Images