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

Equipment state monitoring method and device based on massive logs and medium

A device status and log technology, applied in the field of log processing, can solve problems such as poor failure and low device efficiency, achieve data volume reduction, unified content, and improve the effect of log analysis Sudoku

Pending Publication Date: 2022-03-08
INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for the data center, there are a large number of devices, different types of devices, a large amount of logs generated by the devices, and different log formats generated by different machines or systems, which leads to limited log analysis resources. It is inefficient to conduct a comprehensive analysis of the log and use it to monitor the abnormality of the equipment in the data center, and the failure rate is still very poor.

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
  • Equipment state monitoring method and device based on massive logs and medium
  • Equipment state monitoring method and device based on massive logs and medium
  • Equipment state monitoring method and device based on massive logs and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] refer to figure 1 As shown, the embodiment of the present invention provides a device status monitoring method based on massive logs, including:

[0047] S100, collect logs from the device for classifying and analyzing logs; in the specific implementation process, construct a communication link with the device for classifying and analyzing logs, preset the cycle of collecting logs from the device for classifying and analyzing logs, and designate the target storage for obtaining logs Address, collect logs from the device to the target storage address by using the communication link built according to the set period.

[0048]S200, preprocessing the collected logs to obtain log records; during the specific implementation process, the serial number and time data contained in the logs are constantly changing, and will not participate in the formation of classification template pairs, which is invalid information for the classification template extraction process. Preprocess...

Embodiment 2

[0084] refer to Figure 4 As shown, the embodiment of the present invention provides a device log classification template extraction and classification analysis device, including: a collection module, the collection module is used to collect logs from devices to be classified and analyzed logs;

[0085] A log preprocessing module, the log preprocessing module is used to delete the number and time data in the collected log to obtain log records;

[0086] A feature statistics module, the feature statistics module is used to perform word segmentation feature statistics on the word segmentation in the log record, and further form a log record feature set;

[0087] A template extraction module, the template extraction module is used to compare grouped log record feature sets, and extract classification templates from the grouped log record feature sets;

[0088] A classification module, which classifies the logs according to the extracted classification template;

[0089] A stora...

Embodiment 3

[0093] An embodiment of the present invention provides a medium for implementing a device status monitoring method based on massive logs. The medium for implementing the device status monitoring method based on massive logs stores at least one instruction, and reads and executes the instruction to implement the massive log-based device status monitoring method. A device status monitoring method for logs.

[0094]The present invention uses the word segmentation weight, word segmentation index and word segmentation length as the word segmentation features of each word segmentation in the log record, and the present invention arranges the word segmentation features according to the word segmentation order to form a log record feature set. The Logging Characteristic Collection characterizes log records numerically based on the content of the log records. The log is classified by using the consistency of the elements in the digitally characterized log record feature set, and the pa...

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 relates to an equipment state monitoring method and device based on massive logs and a medium. The method comprises the following steps: collecting logs from equipment of to-be-classified and analyzed logs; preprocessing the collected logs to obtain log records; counting the word segmentation weight, the word segmentation index and the word segmentation length of each word segmentation in the log record as word segmentation features; arranging word segmentation features of all segmented words in the log record according to a word sequence of the segmented words to form a log record feature set; comparing the log record feature sets with the same element quantity, and dividing according to the word segmentation feature consistency quantity greater than or equal to half of the total element quantity of the log record feature sets; extracting parts with the same elements in the log record feature set as a classification template; the logs are classified and stored according to the extracted classification template, the stored classification logs are analyzed, and an equipment analysis report is generated. According to the method, the classification template can be automatically extracted, and the logs can be classified, stored and analyzed according to the classification template.

Description

technical field [0001] The present invention relates to the technical field of log processing, and in particular to a device status monitoring method, device and medium based on massive logs. Background technique [0002] There are a large number of physical equipment infrastructures in the data center, such as servers, switches, routers, firewalls, SDN, disk arrays, distributed storage, etc. During the operation of the equipment infrastructure in the data center, various factors such as temperature, abnormal power on and off, and abnormal collisions will cause state changes, which will affect the services running on the equipment. Due to the variety of equipment types and the large number of equipment, this brings great challenges to equipment status management. [0003] At present, the industry's management method for equipment status is to monitor equipment status based on sensors such as temperature, pressure, displacement, and speed, or various indicators such as hard ...

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): G06F11/34
CPCG06F11/3452G06F11/3476
Inventor 任广磊
Owner INSPUR SUZHOU INTELLIGENT TECH CO LTD