CN116185783B - Monitoring method and device of electronic equipment, electronic equipment and storage medium - Google Patents

Monitoring method and device of electronic equipment, electronic equipment and storage medium Download PDF

Info

Publication number
CN116185783B
CN116185783B CN202310443570.7A CN202310443570A CN116185783B CN 116185783 B CN116185783 B CN 116185783B CN 202310443570 A CN202310443570 A CN 202310443570A CN 116185783 B CN116185783 B CN 116185783B
Authority
CN
China
Prior art keywords
value
target class
target
time
sampling data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310443570.7A
Other languages
Chinese (zh)
Other versions
CN116185783A (en
Inventor
王绍密
冯斌
靳海燕
李增贺
李明辉
杨少飞
和希文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Guokun Power Group Co ltd
Original Assignee
Shandong Traceability Safety Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Traceability Safety Technology Co ltd filed Critical Shandong Traceability Safety Technology Co ltd
Priority to CN202310443570.7A priority Critical patent/CN116185783B/en
Publication of CN116185783A publication Critical patent/CN116185783A/en
Application granted granted Critical
Publication of CN116185783B publication Critical patent/CN116185783B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
    • G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
    • G06F11/3075—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting the data filtering being achieved in order to maintain consistency among the monitored data, e.g. ensuring that the monitored data belong to the same timeframe, to the same system or component
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
    • G06F11/324—Display of status information
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
    • G06F11/324—Display of status information
    • G06F11/325—Display of status information by lamps or LED's
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Debugging And Monitoring (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

The invention provides a monitoring method and device of electronic equipment, the electronic equipment and a storage medium, belonging to the field of data processing, wherein the method comprises the following steps: acquiring a historical sampling data set A of a target monitoring index; based on A, acquiring a mean list set D; acquiring a fluctuation value list set S based on the D; clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes; for any initial class, acquiring the average value of the average value list corresponding to each fluctuation value, and clustering the fluctuation values according to the average value of the average value list corresponding to each fluctuation value, so as to obtain a plurality of target classes; determining a monitoring threshold value corresponding to each target class; and fusing any target class time window to obtain at least one fused time period, and setting a corresponding monitoring threshold value for each corresponding fused time period based on the monitoring threshold value corresponding to the target class. The invention can enable the monitoring threshold value to be more accurate.

Description

Monitoring method and device of electronic equipment, electronic equipment and storage medium
Technical Field
The present invention relates to the field of data processing, and in particular, to a method and apparatus for monitoring an electronic device, and a storage medium.
Background
With the widespread use of network technology, almost all data transmissions currently rely on computer servers for processing. In the operation and maintenance of the computer server, it is necessary to monitor the operation indexes of each server system in real time, and these operation indexes may include, for example, the CPU utilization rate, the memory utilization rate, the hard disk utilization rate, the system load rate, the network bandwidth utilization amount, and so on of the computer. These indicators reflect the health of the computer, and when the indicators are not in a normal range, the computer system may not work properly.
One solution to the current monitoring of these metrics is to employ fixed threshold monitoring. This monitoring approach has the following problems: (1) For the threshold value of each type of index, the operation and maintenance expert needs to configure the threshold value which is considered reasonable according to the corresponding service condition. There is a difference in thresholds configured by different operation and maintenance personnel. (2) With the continuous change of the service, the pre-configured threshold value may not meet the current condition of the index, and the pre-configured threshold value needs to be checked every day to determine whether the configured threshold value is reasonable. If the threshold value is not adjusted, various problems such as inaccurate warning and insufficient warning are caused. (3) For index thresholds which pay attention to up-down change, a plurality of thresholds are required to be set to ensure the accuracy of alarming, so that the maintenance cost is high.
Another solution is to use dynamic threshold monitoring, such as a method and a system device for monitoring and alarming operation indexes of a host disclosed in patent document CN108509314 a. The patent discloses a scheme of dividing a day into a plurality of minute-sized time periods of equal length, and setting a monitoring threshold value for the time period based on a maximum value or a maximum value and a minimum value of historical monitoring data of an index in a corresponding time period. Compared with a fixed-threshold monitoring scheme, the scheme can realize finer and more sensitive index monitoring, however, because the threshold directly adopts the maximum value and the minimum value in a time period of a certain minute level, the problem of inaccurate setting of the threshold exists. In addition, monitoring at a fixed length of the order of minutes causes a problem in that monitoring is too frequent to make maintenance cost too high.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme:
the embodiment of the invention provides a monitoring method of electronic equipment, which comprises the following steps:
s100, acquiring a historical sampling data set A= { A of a target monitoring index 1 ，A 2 ，……，A i ，……，A m }，A i For the sample data set corresponding to the i-th historical period,A i ={a i1 ，a i2 ，……，a ij ，……，a in }，a ij a is the sample data set in the j-th time window of the i-th historical time period ij ={a 1 ij ，a 2 ij ，……，a k ij ，……，a h ij }， a k ij The method comprises the steps of taking the kth sampling data in the jth time window of an ith historical time period as the sampling data, wherein the value of i is 1 to m, m is the number of the historical time periods, the value of j is 1 to n, n is the number of the time windows in each historical time period, n=L/[ delta ] t, L is the duration corresponding to one historical time period, deltat is the duration corresponding to each time window, the value of k is 1 to h, h is the number of the sampling data in one time window, and h= [ delta ] t/f, f are sampling intervals;
s110, based on A, obtaining a mean list set D= { D 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m；
S120, based on D, acquiring a fluctuation value list set S= { S 1 ，S 2 ，……，S j ，……，S n }，S j For D j Corresponding fluctuation value S j =[(∑ k=1 h （D jk -AVG（D j ）） 2 ）/h] 1/2 ；
S130, clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes, wherein the difference value between any two fluctuation values in each initial class is smaller than a corresponding first set value;
s140, for any initial class, acquiring the average value of the average value list corresponding to each fluctuation value, and clustering the fluctuation values according to the average value of the average value list corresponding to each fluctuation value, so as to obtain G target classes; the difference value between the average values corresponding to any two fluctuation values in each target class is smaller than a corresponding second set value;
s150, for any target class p, generating a corresponding distribution diagram based on all sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets normal distribution conditions, determining a monitoring threshold corresponding to the target class based on a maximum fluctuation value corresponding to the target class and the corresponding normal distribution diagram; p has a value of 1 to G;
s160, sequencing time windows corresponding to any target class p according to time sequence, fusing the time windows with continuity in time to obtain at least one fused time period, and setting a corresponding monitoring threshold for each corresponding fused time period based on the monitoring threshold corresponding to the target class;
s170, acquiring current sampling data of a target monitoring index and corresponding sampling time;
s180, comparing the acquired current sampling data with a monitoring threshold corresponding to a fusion time period corresponding to the corresponding sampling time, executing S170 if the current sampling data is located in the corresponding monitoring threshold, otherwise, outputting early warning information. Another embodiment of the present invention provides a monitoring apparatus for an electronic device, including:
the data acquisition module is used for acquiring a historical sampling data set A= { A of the target monitoring index 1 ，A 2 ，……，A i ，……，A m }，A i For the sampling data set corresponding to the ith historical period, A i ={a i1 ，a i2 ，……，a ij ，……，a in }，a ij A is the sample data set in the j-th time window of the i-th historical time period ij ={ a 1 ij ，a 2 ij ，……，a k ij ，……，a h ij }，a k ij The sampling data is the kth sampling data in the jth time window of the ith historical time period, wherein the value of i is 1 to m, m is the number of the historical time periods, and the value of j is 1N, n is the number of time windows in each history time period, n=l/Δt, L is the duration corresponding to one history time period, Δt is the duration corresponding to each time window, k has a value of 1 to h, h is the number of sampling data in one time window, h= Δt/f, f is the sampling interval;
the data processing module is used for executing the following operations:
based on A, a mean list set D= { D is obtained 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m；
Based on D, a fluctuation value list set s= { S is acquired 1 ，S 2 ，……，S j ，……，S n }，S j For D j Corresponding fluctuation value S j =[(∑ k=1 h （D jk -AVG（D j ）） 2 ）/h] 1/2 ；
Clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes, wherein the difference value between any two fluctuation values in each initial class is smaller than a corresponding first set value;
for any initial class, acquiring the average value of the average value list corresponding to each fluctuation value, and clustering the fluctuation values according to the average value of the average value list corresponding to each fluctuation value, so as to obtain a plurality of target classes; the difference value between the average values corresponding to any two fluctuation values in each target class is smaller than a corresponding second set value;
for any target class, generating a corresponding distribution diagram based on all sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets normal distribution conditions, determining a monitoring threshold corresponding to the target class based on a maximum fluctuation value corresponding to the target class and the corresponding normal distribution diagram;
sequencing the time windows corresponding to any target class according to the time sequence, fusing the time windows with continuity in time to obtain at least one fused time period, and setting a corresponding monitoring threshold value for each corresponding fused time period based on the monitoring threshold value corresponding to the target class;
the monitoring module is used for executing the following operations:
operation 1, obtaining current sampling data and corresponding sampling time of a target monitoring index;
and 2, comparing the acquired current sampling data with a monitoring threshold corresponding to a fusion time period corresponding to the corresponding sampling time, executing the operation 1 if the current sampling data is positioned in the corresponding monitoring threshold, and otherwise, outputting early warning information.
Another embodiment of the present invention also provides a non-transitory computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement a method as described above.
Another embodiment of the present invention also provides an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
The invention has at least the following beneficial effects:
according to the monitoring method for the electronic equipment, provided by the embodiment of the invention, the time windows which have continuity in time and have similar fluctuation values in the sampled data and have the same average value are fused into a time period, and the corresponding monitoring threshold is set, so that the monitoring threshold can be switched without using fixed time, and the monitoring operation can be reduced. In addition, the monitoring threshold value of each time period is positively correlated with the corresponding fluctuation value, that is, the larger the fluctuation value is, the larger the monitoring threshold value is relatively, so that the number of false alarms can be reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a monitoring method of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
Embodiment one:
s100, acquiring a historical sampling data set A= { A of a target monitoring index 1 ，A 2 ，……，A i ，……，A m }，A i For the sampling data set corresponding to the ith historical period, A i ={a i1 ，a i2 ，……，a ij ，……，a in }，a ij A is the sample data set in the j-th time window of the i-th historical time period ij ={ a 1 ij ，a 2 ij ，……，a k ij ，……，a h ij }，a k ij The method comprises the steps of taking the kth sampling data in the jth time window of the ith historical time period as the sampling data, wherein the value of i is 1 to m, m is the number of the historical time periods, the value of j is 1 to n, n is the number of the time windows in each historical time period, n=L/[ delta ] t, L is the duration corresponding to one historical time period, deltat is the duration corresponding to each time window, the value of k is 1 to h, h is the number of the sampling data in one time window, and h= [ delta ] t/f, f are sampling intervals.
In embodiments of the present invention, the units of the historical time period may be hours, days or weeks, preferably days. The specific value of m may be set based on actual needs, for example, 30 days before the current time. Each time window may be in seconds or minutes, preferably, may be minutes, for example 5 minutes. In the case where the unit of the history period is day and the unit of the time window is 5 minutes, n=24·60 minutes/5 minutes=288. The sampling interval may be determined based on the performance of the sampling device and may be in seconds.
In the embodiment of the present invention, the target monitoring index may be an index required by the operation and maintenance of a computer server corresponding to the target electronic device to be monitored, for example, may be a broadband utilization rate or a CPU utilization rate, and the present invention is not particularly limited. In the embodiment of the invention, the broadband usage rate or the CPU usage rate can be obtained based on the existing mode, for example, the broadband usage rate or the CPU usage rate is obtained by sampling the broadband usage rate or the CPU usage rate through a sampler of a computer server corresponding to the electronic device. S110, based on A, obtaining a mean list set D= { D 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m。
S120, based on D, acquiring a fluctuation value list set S= { S 1 ，S 2 ，……，S j ，……，S n }，S j For D j Corresponding fluctuation value for representing D j Data fluctuation conditions of S j =[(∑ k=1 h （D jk -AVG（D j ）） 2 ）/h] 1/2 。
S130, clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes. Wherein the difference between any two fluctuation values in each initial class is smaller than the corresponding first set value. The first set point may be a custom value.
In the embodiment of the invention, the set clustering method can be an existing clustering method, such as a k-means clustering method, a neighbor propagation clustering method and the like.
S140, for any initial class, obtaining the average value of the average value list corresponding to each fluctuation value, e.g. D j Is (D) j1 +D j2 +……+D jk +……+D jh ) And (h) clustering the fluctuation values according to the average value of the average value list corresponding to each obtained fluctuation value to obtain G target classes. The difference between the average values corresponding to any two fluctuation values in each target class is smaller than a corresponding second set value, and the second set value can be a custom value.
S150, for any target class p, generating a corresponding distribution diagram based on all sampling data corresponding to the target class, and if the generated distribution diagram indicates that the corresponding sampling data meets the normal distribution condition, determining a monitoring threshold value corresponding to the target class based on a maximum fluctuation value corresponding to the target class and the corresponding normal distribution diagram, wherein the monitoring threshold value comprises an upper limit value and a lower limit value. p has a value of 1 to G.
In the embodiment of the invention, whether the distribution diagram generated by the sampling data is a normal distribution diagram is judged, and the distribution diagram can be determined based on the prior art. For example, the accuracy of the obtained result can be improved to a certain extent by performing a non-parametric test on the obtained data sample, judging whether the obtained data sample is subject to normal distribution according to the test result of the non-parametric test, and judging whether the obtained data sample is subject to normal distribution according to the non-parametric test result. Alternatively, when judging whether the acquired data sample is subject to normal distribution or not by performing non-parametric test on the acquired data sample according to the test result of the non-parametric test, the non-parametric test used may be a K-S test.
Further, in S150, the monitoring threshold corresponding to any target class p is obtained based on the following steps:
s151, obtaining a maximum fluctuation value PBp corresponding to any target class p and a maximum fluctuation value ZB in S. S152, based on PBp and ZB, obtains a target duty ratio MFp = PBp/zb·b corresponding to the target class p, where b is a preset duty ratio, and may be a custom value, for example, 95%. S153, acquiring a corresponding section with an area ratio equal to MFp from the normal distribution map based on MFp, and acquiring corresponding sample data from all sample data corresponding to the target class p based on the acquired corresponding section, as a target data set Dp of the target class p.
Those skilled in the art will recognize that any method for obtaining the corresponding interval with the area ratio equal to MFp from the normal distribution map based on MFp and obtaining the corresponding sample data from all the sample data corresponding to the target class p based on the obtained corresponding interval falls within the scope of the present invention.
S154, obtaining min (Dp) as a lower limit value of a monitoring threshold corresponding to the target class p and obtaining max (Dp) as an upper limit value of the monitoring threshold corresponding to the target class p, namely respectively taking the minimum value and the maximum value in Dp as a lower limit value and an upper limit value of the monitoring threshold corresponding to the target class p.
In the embodiment of the invention, the monitoring threshold value of each target class is positively correlated with the ratio of the corresponding maximum fluctuation value to the corresponding maximum fluctuation value of all the target classes, so that the larger the fluctuation value is, the closer the endowed monitoring threshold value is to the preset area occupation ratio is, and the false alarm times can be reduced.
Further, S150 further includes: if the generated distribution diagram indicates that the corresponding sampling data does not meet the normal distribution condition, the monitoring threshold TVp =f (W) of the time window corresponding to any target class p, W is all the sampling data corresponding to the target class, and f () is a set function expression.
In an embodiment of the present invention, f () may be an existing expression, for example, in one exemplary embodiment, f () may be a quarter-bit distance calculation method.
In one exemplary embodiment, TVp may be determined based on the average AVG (W) of W, specifically TVp may be (AVG (W) - [ delta ] d, AVG (W) + [ delta ] d), Δd being a preset value, which may be an empirical value.
In another exemplary embodiment, TVp can be based on a weighted average AVGW of W (W) =a·w. Specifically, TVp may be (AVGW (W) - [ delta ] d, AVGW (W) + [ delta ] d). A is a weight set corresponding to n time windows, the weights of sampling data in the same time window are the same, different time windows can be given different weights, and specific assignment can be an empirical value.
In another exemplary embodiment, TVp can be (min (W), max (W)), min (W) being the minimum of W, max (W) being the maximum of W.
S160, sequencing the time windows corresponding to any target class p according to time sequence, fusing the time windows with continuity in time to obtain at least one time period, and setting a corresponding monitoring threshold for each corresponding time period based on the monitoring threshold corresponding to the target class.
Further, S160 may specifically include:
s161, setting an initial time period list set TP p ={TP p1 ，TP p2 ，……，TP pd First initial period list TP p1 The initial value of (C) is (T) s p1 ，T e p1 ），T s p1 For the start time T of the first time window corresponding to the target class p s p1 ，T e p1 For the end time T of the first time window corresponding to the target class p e p1 ，TP p2 ，……，TP pd The initial value is empty set, d is TP p The number of initial time period lists in (a); q=2 is set. TP (Transmission protocol) p Stored is ordered data, initialized to a list containing header elements, the length of the list can be extended.
S162, if the start time T of the qth time window in the target class p s pq =T e p（q-1） Will (T) s pq ，T e pq ) And adding the time window to the initial time period list corresponding to the q-1 time window, executing S164, otherwise executing S163.
S163, will (T) s pq ，T e pq ) And adding the time window to a next initial time period list corresponding to the q-1 th time window, and executing S164.
S164, setting q=q+1, if q is less than or equal to h (p), executing S162, otherwise, executing S165; h (p) is the number of time windows corresponding to the target class p.
S165, based on the current TP p Obtaining a target time period list corresponding to the target class p, obtaining fusion time periods corresponding to each target time period list, and setting a corresponding monitoring threshold value for each fusion time period.
Those skilled in the art know that current TP p The number of the time period lists in (a) may not be equal to d which is initially set, may be smaller than d or larger than d, and the final target time period list is a time period list which does not contain an empty set.
Further, in the embodiment of the present invention, the monitoring threshold corresponding to each fusion time period is the same as the monitoring threshold corresponding to the corresponding target class.
Further, in another embodiment of the present invention, the monitoring threshold mpt=sp/sm·mt corresponding to any fusion period, SP is a maximum fluctuation value corresponding to the fusion period, SM is a maximum fluctuation value corresponding to the target class corresponding to the fusion period, and MT is a monitoring threshold corresponding to the target class corresponding to the fusion period.
In this embodiment, the monitoring threshold value of each time period is positively correlated with the corresponding maximum fluctuation value and the corresponding maximum fluctuation value of the target class, so that the determination of the monitoring threshold value is more accurate, and the false alarm times are further reduced.
S170, acquiring current sampling data of the target monitoring index and corresponding sampling time.
In the embodiment of the invention, the data of the target monitoring index can be sampled at each sampling time.
S180, comparing the obtained current sampling data with a monitoring threshold corresponding to a time period corresponding to the corresponding sampling time, if the current sampling data is located in the corresponding monitoring threshold, namely, is larger than the lower limit value of the monitoring threshold and smaller than the upper limit value of the monitoring threshold, the current sampling data is indicated to be normal, the next judgment is waited, namely, S170 is executed, otherwise, the current sampling data is indicated to be abnormal, and early warning information is output.
In the embodiment of the invention, the early warning information can be output in one or more modes of text, sound and lamplight flickering.
The embodiment of the invention also provides a monitoring device of the electronic equipment, which comprises:
the data acquisition module is used for acquiring a historical sampling data set A= { A of the target monitoring index 1 ，A 2 ，……，A i ，……，A m }，A i For the sampling data set corresponding to the ith historical period, A i ={a i1 ，a i2 ，……，a ij ，……，a in }，a ij A is the sample data set in the j-th time window of the i-th historical time period ij ={ a 1 ij ，a 2 ij ，……，a k ij ，……，a h ij }，a k ij The method comprises the steps of taking the kth sampling data in the jth time window of an ith historical time period as the sampling data, wherein the value of i is 1 to m, m is the number of the historical time periods, the value of j is 1 to n, n is the number of the time windows in each historical time period, n=L/[ delta ] t, L is the duration corresponding to one historical time period, deltat is the duration corresponding to each time window, the value of k is 1 to h, h is the number of the sampling data in one time window, and h= [ delta ] t/f, f are sampling intervals;
the data processing module is used for executing the following operations:
based on A, a mean list set D= { D is obtained 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m；
Based on D, a fluctuation value list set s= { S is acquired 1 ，S 2 ，……，S j ，……，S n }，S j For D j Corresponding fluctuation value S j =[(∑ k=1 h （D jk -AVG（D j ）） 2 ）/h] 1/2 ；
Clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes, wherein the difference value between any two fluctuation values in each initial class is smaller than a corresponding first set value;
for any initial class, acquiring the average value of the average value list corresponding to each fluctuation value, and clustering the fluctuation values according to the average value of the average value list corresponding to each fluctuation value, so as to obtain a plurality of target classes; the difference value between the average values corresponding to any two fluctuation values in each target class is smaller than a corresponding second set value;
for any target class, generating a corresponding distribution diagram based on all sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets normal distribution conditions, determining a monitoring threshold corresponding to the target class based on a maximum fluctuation value corresponding to the target class and the corresponding normal distribution diagram;
sequencing the time windows corresponding to any target class according to the time sequence, fusing the time windows with continuity in time to obtain at least one fused time period, and setting a corresponding monitoring threshold value for each corresponding fused time period based on the monitoring threshold value corresponding to the target class.
The monitoring module is used for executing the following operations:
and 1, acquiring current sampling data of a target monitoring index and corresponding sampling time.
And 2, comparing the acquired current sampling data with a monitoring threshold corresponding to a time period corresponding to the corresponding sampling time, if the current sampling data is positioned in the corresponding monitoring threshold, namely is larger than the lower limit value of the monitoring threshold and smaller than the upper limit value of the monitoring threshold, indicating that the current sampling data is normal, waiting for the next judgment, namely executing the operation 1, otherwise, indicating that the current sampling data is abnormal, and outputting early warning information.
Embodiment two:
the present embodiment provides a method for monitoring an electronic device, which is substantially the same as the method provided in the foregoing embodiment, and is different in that S120 to S150 are replaced with S220 to S250, specifically, S200 to S250 are:
s220, obtaining a relation graph between the sampling time in the characterization D and the average value of the sampling data set, and obtaining a curve in a historical time period, for example, 1 day. The horizontal axis of the graph may be the sampling time and the vertical axis may be the sampling data.
S230, cutting the curves in the graph according to n time windows to obtain n sub-curves. The specific cutting mode can be adopted by the prior art.
S240, clustering the n sub-curves based on a plurality of preset reference curves to obtain G target classes.
In the embodiment of the invention, the number and the specific shape of the preset reference curves can be determined based on actual conditions, for example, the number and the specific shape of the preset reference curves can be determined based on the fluctuation degree of data, and the preset reference curves can comprise curves capable of representing high-medium-low fluctuation conditions and the like. The preset reference curve may be determined based on a typical graph obtained from historical sampling data of a monitoring index corresponding to the target service, for example, a curve capable of representing a high fluctuation condition, a curve representing a medium fluctuation condition, a curve representing a low fluctuation condition, or the like is selected from the obtained curves as the reference curve. Different preset reference curves correspond to different preset duty ratios, and the larger the fluctuation degree of the reference curve is, the larger the corresponding preset duty ratio is. The preset duty cycle corresponding to each reference curve may be a custom value. In the embodiment of the invention, each preset reference curve corresponds to one target class. S240 may specifically include:
s241, for any sub-curve j, respectively obtaining the similarity between the sub-curves and a plurality of preset reference curves to obtain a similarity set CS about the sub-curve j j ={CS j1 ，CS j2 ，……,CS jv ，……，CS ju }；CS jv For the similarity between the sub-curve j and the v-th preset reference curve, the value of v is 1 to u, and u is the number of the preset reference curves.
Those skilled in the art will appreciate that the similarity between each sub-curve and the corresponding pre-set reference curve can be based on existing curve similarity methods.
S242, classifying the sub-curve j into max { CS j And the corresponding target class of the preset reference curve. max { CS j CS (x) } is j1 ，CS j2 ，……,CS jv ，……，CS ju Is the maximum value of (a).
Through S241 and S242, u target classes corresponding to u preset reference curves can be obtained.
S250, for any target class p, generating a corresponding distribution diagram based on sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets normal distribution conditions, determining a monitoring threshold value corresponding to the target class based on the maximum similarity corresponding to the target class and the corresponding normal distribution diagram, wherein the monitoring threshold value comprises an upper limit value and a lower limit value; the maximum similarity corresponding to each target class is the maximum value of the similarity between the sub-curves contained in the target class and the corresponding preset reference curve. p has a value of 1 to G.
Those skilled in the art will appreciate that the similarity between each sub-curve and the corresponding pre-set reference curve can be based on existing curve similarity methods.
In the embodiment of the invention, whether the distribution diagram generated by the sampling data is a normal distribution diagram is judged, and the distribution diagram can be determined based on the prior art. For example, the accuracy of the obtained result can be improved to a certain extent by performing a non-parametric test on the obtained data sample, judging whether the obtained data sample is subject to normal distribution according to the test result of the non-parametric test, and judging whether the obtained data sample is subject to normal distribution according to the non-parametric test result. Alternatively, when judging whether the acquired data sample is subject to normal distribution or not by performing non-parametric test on the acquired data sample according to the test result of the non-parametric test, the non-parametric test used may be a K-S test.
Further, in S250, the monitoring threshold corresponding to the target class p is obtained based on the following steps:
s251, obtaining the maximum similarity corresponding to the target class pDegree MS p Maximum similarity MSA corresponding to all target classes p =max（MS 1 ，MS 2 ，……，MS p ，……，MS Z ). The maximum similarity corresponding to the target class p is the maximum value in the similarity between the sub-curve contained in the target class p and the corresponding preset reference curve.
S252, based on MS p And MSA p Acquiring target duty ratio MFp =ms corresponding to target class p p /MSA p ·c p ，c p And the preset duty ratio corresponding to the reference curve corresponding to the target class p.
S253, acquiring a corresponding section with an area ratio equal to MFp from the normal distribution map based on MFp, and acquiring corresponding sample data from all sample data corresponding to the target class p based on the acquired corresponding section, as a target data set Dp of the target class p.
Those skilled in the art will recognize that any method for obtaining the corresponding interval with the area ratio equal to MFp from the normal distribution map based on MFp and obtaining the corresponding sampled data from all the sampled data corresponding to the target class p based on the obtained corresponding interval falls within the scope of the present invention.
S254, obtaining min (Dp) as a lower limit value of the monitoring threshold corresponding to the target class p and obtaining max (Dp) as an upper limit value of the monitoring threshold corresponding to the target class p, namely respectively taking the minimum value and the maximum value in Dp as a lower limit value and an upper limit value of the monitoring threshold corresponding to the target class p.
In the embodiment of the invention, the monitoring threshold value of each target class is positively correlated with the ratio of the corresponding maximum similarity to the maximum similarity corresponding to all the target classes, so that the larger the target class with larger similarity is, the larger the given monitoring threshold value is, the closer the preset area ratio of the corresponding reference curve is, and the false alarm times can be reduced.
Further, S250 further includes: if the generated distribution diagram indicates that the corresponding sampling data does not meet the normal distribution condition, the monitoring threshold TVp =f (W) of the time window corresponding to any target class p, W is all the sampling data corresponding to the target class, and f () is a set function expression.
In an embodiment of the present invention, f () may be an existing expression, for example, in one exemplary embodiment, f () may be a quarter-bit distance calculation method.
In one exemplary embodiment, TVp may be determined based on the average AVG (W) of W, specifically TVp may be (AVG (W) - [ delta ] d, AVG (W) + [ delta ] d), Δd being a preset value, which may be an empirical value.
In another exemplary embodiment, TVp can be based on a weighted average AVGW of W (W) =a·w. Specifically, TVp may be (AVGW (W) - [ delta ] d, AVGW (W) + [ delta ] d). A is a weight set corresponding to n time windows, the weights of sampling data in the same time window are the same, different time windows can be given different weights, and specific assignment can be an empirical value.
In another exemplary embodiment, TVp can be (min (W), max (W)), min (W) being the minimum of W, max (W) being the maximum of W.
The embodiment of the invention also provides a monitoring device for electronic equipment, and the device provided by the embodiment has basically the same structure as the device provided by the previous embodiment, except that the data processing module of the device is used for executing the following operations:
based on A, a mean list set D= { D is obtained 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m；
Acquiring a relation graph between the sampling time in the characterization D and the mean value of the sampling data set;
cutting the curves in the graph according to n time windows to obtain n sub-curves;
clustering the n sub-curves based on a plurality of preset reference curves to obtain a plurality of target classes;
for any target class, generating a corresponding distribution diagram based on sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets a normal distribution condition, determining a monitoring threshold value corresponding to the target class based on the maximum similarity corresponding to the target class and the corresponding normal distribution diagram, wherein the monitoring threshold value comprises an upper limit value and a lower limit value; the maximum similarity corresponding to each target class is the maximum value in the similarity between the sub-curve contained in the target class and the corresponding preset reference curve;
sequencing the time windows corresponding to any target class according to the time sequence, fusing the time windows with continuity in time to obtain at least one fused time period, and setting a corresponding monitoring threshold value for each corresponding fused time period based on the monitoring threshold value corresponding to the target class.
Embodiments of the present invention also provide a non-transitory computer readable storage medium that may be disposed in an electronic device to store at least one instruction or at least one program for implementing one of the methods embodiments, the at least one instruction or the at least one program being loaded and executed by the processor to implement the methods provided by the embodiments described above.
Embodiments of the present invention also provide an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium.
Embodiments of the present invention also provide a computer program product comprising program code for causing an electronic device to carry out the steps of the method according to the various exemplary embodiments of the invention as described in the specification, when said program product is run on the electronic device.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the present disclosure is defined by the appended claims.

Claims (9)

1. A method for monitoring an electronic device, the method comprising the steps of:
s100, acquiring a historical sampling data set A= { A of a target monitoring index 1 ，A 2 ，……，A i ，……，A m }，A i For the sampling data set corresponding to the ith historical period, A i ={a i1 ，a i2 ，……，a ij ，……，a in }，a ij A is the sample data set in the j-th time window of the i-th historical time period ij ={a 1 ij ，a 2 ij ，……，a k ij ，……，a h ij }， a k ij The method comprises the steps of taking the kth sampling data in the jth time window of an ith historical time period as the sampling data, wherein the value of i is 1 to m, m is the number of the historical time periods, the value of j is 1 to n, n is the number of the time windows in each historical time period, n=L/[ delta ] t, L is the duration corresponding to one historical time period, deltat is the duration corresponding to each time window, the value of k is 1 to h, h is the number of the sampling data in one time window, and h= [ delta ] t/f, f are sampling intervals;
s110, based on A, obtaining a mean list set D= { D 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m；
S120, based on D, acquiring a fluctuation value list set S= { S 1 ，S 2 ，……，S j ，……，S n }，S j For D j Corresponding fluctuation value S j =[(∑ k=1 h （D jk -AVG（D j ）） 2 ）/h] 1/2 ；
S130, clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes, wherein the difference value between any two fluctuation values in each initial class is smaller than a corresponding first set value;
s140, for any initial class, acquiring the average value of each average value element in the average value list corresponding to each fluctuation value, and clustering the fluctuation values according to the average value of each average value element in the average value list corresponding to each fluctuation value, so as to obtain G target classes; the difference value between the average values corresponding to any two fluctuation values in each target class is smaller than a corresponding second set value;
s150, for any target class p, generating a corresponding distribution diagram based on all sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets normal distribution conditions, determining a monitoring threshold corresponding to the target class based on a maximum fluctuation value corresponding to the target class and the corresponding normal distribution diagram; p has a value of 1 to G;
s160, sequencing time windows corresponding to any target class p according to time sequence, fusing the time windows with continuity in time to obtain at least one fused time period, and setting a corresponding monitoring threshold for each corresponding fused time period based on the monitoring threshold corresponding to the target class;
s170, acquiring current sampling data of a target monitoring index and corresponding sampling time;
s180, comparing the acquired current sampling data with a monitoring threshold corresponding to a fusion time period corresponding to the corresponding sampling time, executing S170 if the current sampling data is located in the corresponding monitoring threshold, otherwise, outputting early warning information;
in S150, the monitoring threshold corresponding to the target class p is obtained based on the following steps:
s151, obtaining a maximum fluctuation value PBp corresponding to the target class p and a maximum fluctuation value ZB in S;
s152, acquiring a target duty ratio MFp = PBp/zb·b corresponding to the target class p based on PBp and ZB, where b is a preset duty ratio;
s153, acquiring a corresponding section with the area ratio equal to MFp from the normal distribution diagram based on MFp, and acquiring corresponding sampling data from all sampling data corresponding to the target class p based on the acquired corresponding section, wherein the corresponding sampling data is used as a target data set Dp of the target class p;
s154, obtaining min (Dp) as the lower limit value of the monitoring threshold corresponding to the target class p, and obtaining max (Dp) as the upper limit value of the monitoring threshold corresponding to the target class p.
2. The method of claim 1, wherein S150 further comprises: if the generated distribution diagram indicates that the corresponding sampling data does not meet the normal distribution condition, the monitoring threshold value TVp =f (W) of the time window corresponding to any target class, W is all the sampling data corresponding to the target class, and f () is a set function expression.
3. The method according to claim 1, wherein S160 specifically comprises:
s161, setting an initial time period list set TP p ={TP p1 ，TP p2 ，……，TP pd First initial period list TP p1 The initial value of (C) is (T) s p1 ，T e p1 ），T s p1 For the start time T of the first time window corresponding to the target class p s p1 ，T e p1 For the end time T of the first time window corresponding to the target class p e p1 ，TP p2 ，……，TP pd The initial value is empty set, d is TP p The number of initial time period lists in (a);
s162, q=2; if the start time T of the qth time window in the target class p s pq =T e p（q-1） Will (T) s pq ，T e pq ) Adding the time window to the initial time period list corresponding to the q-1 time window, executing S164, otherwise, executing S163; s163, will (T) s pq ，T e pq ) Added to the initial time corresponding to the q-1 time windowIn the next initial time period list corresponding to the segment list, S164 is performed;
s164, setting q=q+1, if q is less than or equal to h (p), executing S162, otherwise, executing S165; h (p) is the number of time windows corresponding to the target class p;
s165, based on the current TP p And obtaining a target time period list corresponding to the target class p, and obtaining a fusion time period corresponding to each target time period list and a monitoring threshold corresponding to each fusion time period.
4. A method according to claim 3, wherein the monitoring threshold value corresponding to each fusion period is the same as the monitoring threshold value corresponding to the corresponding target class.
5. A method according to claim 3, wherein the monitor threshold mpt=sp/sm·mt corresponding to any fusion period, SP is a maximum fluctuation value corresponding to the fusion period, SM is a maximum fluctuation value corresponding to a target class corresponding to the fusion period, and MT is a monitor threshold corresponding to a target class corresponding to the fusion period.
6. The method of claim 1, wherein the target monitoring indicator is broadband usage or CPU usage.
7. A monitoring device for an electronic apparatus, the device comprising:
the data acquisition module is used for acquiring a historical sampling data set A= { A of the target monitoring index 1 ，A 2 ，……，A i ，……，A m }，A i For the sampling data set corresponding to the ith historical period, A i ={a i1 ，a i2 ，……，a ij ，……，a in }，a ij A is the sample data set in the j-th time window of the i-th historical time period ij ={ a 1 ij ，a 2 ij ，……，a k ij ，……，a h ij }，a k ij The method comprises the steps of taking the kth sampling data in the jth time window of an ith historical time period as the sampling data, wherein the value of i is 1 to m, m is the number of the historical time periods, the value of j is 1 to n, n is the number of the time windows in each historical time period, n=L/[ delta ] t, L is the duration corresponding to one historical time period, deltat is the duration corresponding to each time window, the value of k is 1 to h, h is the number of the sampling data in one time window, and h= [ delta ] t/f, f are sampling intervals;
the data processing module is used for executing the following operations:
based on A, a mean list set D= { D is obtained 1 ，D 2 ，……，D j ，……，D n J-th mean list D in D j ={D j1 ，D j2 ，……，D jk ，……，D jh }，D jk For the mean value of the kth sample dataset in the jth time window of each historical time period, D jk =（∑ i=1 m a k ij ）/m；
Based on D, a fluctuation value list set s= { S is acquired 1 ，S 2 ，……，S j ，……，S n }，S j For D j Corresponding fluctuation value S j =[(∑ k=1 h （D jk -AVG（D j ）） 2 ）/h] 1/2 ；
Clustering each fluctuation value in the S based on a set clustering method to obtain a plurality of initial classes, wherein the difference value between any two fluctuation values in each initial class is smaller than a corresponding first set value;
for any initial class, acquiring the average value of each average value element in the average value list corresponding to each fluctuation value, and clustering the fluctuation values according to the average value of each average value element in the average value list corresponding to each fluctuation value, so as to obtain G target classes; the difference value between the average values corresponding to any two fluctuation values in each target class is smaller than a corresponding second set value;
for any target class p, generating a corresponding distribution diagram based on all sampling data corresponding to the target class, and if the generated distribution diagram represents that the corresponding sampling data meets normal distribution conditions, determining a monitoring threshold corresponding to the target class based on a maximum fluctuation value corresponding to the target class and the corresponding normal distribution diagram; p has a value of 1 to G;
sequencing the time windows corresponding to any target class according to the time sequence, fusing the time windows with continuity in time to obtain at least one fused time period, and setting a corresponding monitoring threshold value for each corresponding fused time period based on the monitoring threshold value corresponding to the target class;
the monitoring module is used for executing the following operations:
operation 1, obtaining current sampling data and corresponding sampling time of a target monitoring index;
2, comparing the acquired current sampling data with a monitoring threshold corresponding to a fusion time period corresponding to the corresponding sampling time, executing an operation 1 if the current sampling data is positioned in the corresponding monitoring threshold, and otherwise, outputting early warning information;
the monitoring threshold value corresponding to the target class p is obtained based on the following steps:
obtaining a maximum fluctuation value PBp corresponding to the target class p and a maximum fluctuation value ZB in S;
acquiring a target duty ratio MFp = PBp/ZB.b corresponding to the target class p based on PBp and ZB, wherein b is a preset duty ratio;
acquiring a corresponding interval with the area ratio equal to MFp from the normal distribution diagram based on MFp, and acquiring corresponding sampling data from all sampling data corresponding to the target class p based on the acquired corresponding interval, wherein the corresponding sampling data is used as a target data set Dp of the target class p;
obtaining min (Dp) as a lower limit value of a monitoring threshold value corresponding to the target class p, and obtaining max (Dp) as an upper limit value of the monitoring threshold value corresponding to the target class p.
8. A non-transitory computer readable storage medium having stored therein at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the method of any one of claims 1-6.
9. An electronic device comprising a processor and the non-transitory computer readable storage medium of claim 8.
CN202310443570.7A 2023-04-24 2023-04-24 Monitoring method and device of electronic equipment, electronic equipment and storage medium Active CN116185783B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310443570.7A CN116185783B (en) 2023-04-24 2023-04-24 Monitoring method and device of electronic equipment, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310443570.7A CN116185783B (en) 2023-04-24 2023-04-24 Monitoring method and device of electronic equipment, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116185783A CN116185783A (en) 2023-05-30
CN116185783B true CN116185783B (en) 2023-07-14

Family

ID=86452451

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310443570.7A Active CN116185783B (en) 2023-04-24 2023-04-24 Monitoring method and device of electronic equipment, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116185783B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116361668B (en) * 2023-06-02 2023-08-11 北京安天网络安全技术有限公司 Monitoring method, device, equipment and medium for multiple SDR equipment
CN116595529B (en) * 2023-07-18 2023-09-19 山东溯源安全科技有限公司 Information security detection method, electronic equipment and storage medium
CN116866047A (en) * 2023-07-18 2023-10-10 山东溯源安全科技有限公司 Method, medium and device for determining malicious equipment in industrial equipment network
CN116599778B (en) * 2023-07-18 2023-09-26 山东溯源安全科技有限公司 Data processing method for determining malicious device
CN117148798A (en) * 2023-09-01 2023-12-01 山东溯源安全科技有限公司 Equipment monitoring method and device, storage medium and electronic equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111371490A (en) * 2020-04-26 2020-07-03 深圳市特发信息股份有限公司 Optical cable safety early warning monitoring equipment with real-time supervision
CN115563180A (en) * 2022-09-19 2023-01-03 烽台科技（北京）有限公司 Dynamic threshold generation method, device, equipment and storage medium

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2002329611A1 (en) * 2001-07-20 2003-03-03 Altaworks Corporation System and method for adaptive threshold determination for performance metrics
CN104572391B (en) * 2013-10-16 2019-03-15 深圳市腾讯计算机系统有限公司 Monitoring alarm tactics configuring method and device, monitoring alarm method and device
CN107871190B (en) * 2016-09-23 2021-12-14 阿里巴巴集团控股有限公司 Method and device for monitoring business indicators
CN112882889A (en) * 2021-01-22 2021-06-01 北京奇艺世纪科技有限公司 Abnormality monitoring method, abnormality monitoring system, electronic device, and storage medium
CN114446033B (en) * 2022-01-21 2023-06-20 四川省地质工程勘察院集团有限公司 A Dynamic Alarm Threshold Determination Method
CN114138617B (en) * 2022-02-07 2022-05-24 杭州朗澈科技有限公司 Self-learning frequency conversion monitoring method and system, electronic equipment and storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111371490A (en) * 2020-04-26 2020-07-03 深圳市特发信息股份有限公司 Optical cable safety early warning monitoring equipment with real-time supervision
CN115563180A (en) * 2022-09-19 2023-01-03 烽台科技（北京）有限公司 Dynamic threshold generation method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN116185783A (en) 2023-05-30

Similar Documents

Publication Publication Date Title
CN116185783B (en) Monitoring method and device of electronic equipment, electronic equipment and storage medium
WO2020215721A1 (en) Method for predicting service life of laser radar
US9396432B2 (en) Agreement breach prediction system, agreement breach prediction method and agreement breach prediction program
CN111222710B (en) Data abnormality warning method, device, equipment and storage medium
CN115480997A (en) An alarm method, device, electronic equipment and storage medium for abnormal index
CN117198032B (en) Tunnel ponding early warning method and system based on radar sensor
CN114595948B (en) Multi-risk parameter enterprise risk assessment method and system based on artificial intelligence
CN113342588A (en) Method and device for carrying out pressure test on server based on dynamic adjustment load
CN116909851A (en) Monitoring method, monitoring device, electronic equipment and storage medium
CN117436712A (en) A real-time monitoring method and system for construction hanging basket operation risks
CN118101426A (en) Monitoring and operation system based on IoT devices
CN114814419A (en) Electric power cabinet heat dissipation performance detection method based on big data
CN114005256A (en) Alarm delay device design method and system based on alarm duration probability function
US20100094590A1 (en) Automated information technology management
KR101738745B1 (en) A Method for a Crime Prediction by Estimating a Cell Value and A System for the Same
WO2015199584A1 (en) Prioritizing data traffic from and/or to devices in a wireless network
CN120234324B (en) A laboratory data collection management method, system, equipment and medium
CN109186044A (en) A kind of human perception method, apparatus and air conditioner
CN119045939A (en) Visual platform system for financial data scheduling
CN111817923B (en) Early warning analysis method and device for sudden change of flow of switch port
JP7675537B2 (en) BATTERY DIAGNOSIS METHOD, BATTERY DIAGNOSIS DEVICE, BATTERY DIAGNOSIS SYSTEM, BATTERY-EQUIPPED DEVICE, AND BATTERY DIAGNOSIS PROGRAM
CN116991102A (en) A laboratory intelligent control method, system and storage medium
CN115792632A (en) Battery life prediction method and system applied to fire-fighting product
CN118747340B (en) Network data analysis system based on deep learning
CN118378164B (en) Vehicle fault prediction method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240926

Address after: 250000 Room 310, Research and Production Building, No. 2766 Yingxiu Road, Shunhua Road Street, Jinan Area, China (Shandong) Pilot Free Trade Zone, Jinan City, Shandong Province

Patentee after: Shandong Guokun Power Group Co.,Ltd.

Country or region after: China

Address before: Room 1905, Dingfeng Center, No. 6 Jiefang Road, Lixia District, Jinan City, Shandong Province, 250014

Patentee before: Shandong Traceability Safety Technology Co.,Ltd.

Country or region before: China