Unlock instant, AI-driven research and patent intelligence for your innovation.

Information system log-based fault time space prediction method and system

An information system, downtime technology, applied in the field of data processing

Active Publication Date: 2020-10-30
STATE GRID FUJIAN ELECTRIC POWER CO LTD +3
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, fault prediction based on log data can only predict the presence or absence of faults, that is, whether faults will occur in a certain period of time in the future

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Information system log-based fault time space prediction method and system
  • Information system log-based fault time space prediction method and system
  • Information system log-based fault time space prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solutions of the present invention will be further described below in combination with specific embodiments and accompanying drawings.

[0042] The present invention provides a fault time and space prediction method based on information system logs, including:

[0043] Obtain time series log data x within n time periods (t-n*Δt, t) before the current time t of the information system 1 , for preprocessing. The preprocessing process includes data cleaning, dictionary construction, and sample extraction. Data cleaning is used to delete some useless numbers and symbols in the log text. The dictionary construction is used to digitally encode the feature fields in the log. Based on the encoding Extract the feature fields in the feature vectors from the final log data, and form a training set in the corresponding format based on the needs of network model training;

[0044] Based on the time series log data, it is judged whether the information system will fail ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an information system log-based fault time space prediction method and system. The method comprises the steps of obtaining time sequence log data x1 in n time periods before acurrent moment t of an information system; judging whether a fault is generated in the future or not based on the time sequence log data; if the fault is not generated, not further processing; otherwise, further judging the specific time point and the spatial position of the fault; a multi-task learning model is adopted for judging the specific time point and the spatial position of the fault; joint training is carried out on two tasks of specific fault occurrence time and position; returning to the specific time point and the spatial position of the fault at the same time; according to the method, the fault occurrence time and the fault generation space position can be predicted at the same time on the basis of predicting whether the fault exists or not in the past, the two tasks are jointly trained, only one process is needed to realize the correlation between the fault information, two models do not need to be set for respective operation, and the efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a fault time and space prediction method and system based on information system logs. Background technique [0002] A log is an information source that reflects the running track of an information system, and is an essential part of every information system. Log data has the characteristics of full business scope, full time type, and full time dimension, and contains key information about the operation of the information system. In the actual production work, it plays a vital role in guiding the operation and maintenance personnel to carry out activities such as system maintenance and equipment status monitoring. Using log data can extract more useful fault information. [0003] In the prior art, fault prediction based on log data can only predict the presence or absence of faults, that is, whether faults will occur within a certain period of time in the future. Althoug...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/18G06F16/2458G06N3/04
CPCG06F16/1815G06F16/2474G06N3/045Y04S10/50
Inventor 吴树霖朱京赵子岩李宏发张江龙高扬李金凤吴小华张天奇赵云龙胡心颖郭庆杨彬彬李小威
Owner STATE GRID FUJIAN ELECTRIC POWER CO LTD