CN113934615A - Data monitoring method, device and equipment - Google Patents
Data monitoring method, device and equipment Download PDFInfo
- Publication number
- CN113934615A CN113934615A CN202111527303.5A CN202111527303A CN113934615A CN 113934615 A CN113934615 A CN 113934615A CN 202111527303 A CN202111527303 A CN 202111527303A CN 113934615 A CN113934615 A CN 113934615A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- historical data
- historical
- trend
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F11/327—Alarm or error message display
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a data monitoring method, a device and equipment; according to the scheme, firstly, historical data needs to be collected, the type of the historical data is determined, the historical data is input into a prediction model corresponding to the type, and trend analysis is carried out on the historical data through the prediction model to obtain prediction data; then, comparing the predicted data with the actual data, if the predicted data meet the prediction requirement, displaying a trend prediction curve according to the predicted data, and performing alarm detection; and if the prediction requirements are not met, performing trend analysis on the newly generated actual data again through the prediction model. Therefore, according to the scheme, the historical data is subjected to trend analysis through the prediction model, and the prediction data of index change can be obtained before problems occur, so that the monitoring system is assisted to perform early warning, trend prediction curve display and equipment capacity management, and the user experience is improved.
Description
Technical Field
The present invention relates to the field of data monitoring technologies, and in particular, to a data monitoring method, device and apparatus.
Background
The current machine room monitoring alarm logic detects a monitoring index, and triggers an alarm if the monitoring index is detected to exceed a preset alarm threshold. Namely: the monitoring alarm logic belongs to a post alarm mechanism, and only after a problem occurs and a corresponding monitoring index exceeds a set alarm threshold value, an alarm can be triggered, early warning cannot be performed before the problem occurs, and the user experience is poor.
Disclosure of Invention
The invention aims to provide a data monitoring method, a data monitoring device and data monitoring equipment, so that early warning can be timely carried out before problems occur, and user experience is improved.
In order to achieve the above object, the present invention provides a data monitoring method, including:
collecting historical data;
determining the type of the historical data;
inputting the historical data into a prediction model corresponding to the type, and performing trend analysis on the historical data through the prediction model to obtain prediction data;
comparing the predicted data with actual data, if the predicted data meets the prediction requirement, displaying a trend prediction curve according to the predicted data, and performing alarm detection; and if the prediction requirement is not met, performing trend analysis on the newly generated actual data again through the prediction model.
Before determining the type of the historical data, the method further includes:
judging whether the historical data is a pure random sequence;
if not, continuing to execute the step of determining the type of the historical data.
Wherein the determining the type of the historical data and inputting the historical data into a prediction model corresponding to the type comprises:
judging whether the historical data is a stable sequence;
if yes, inputting the historical data into an ARMA model; and if not, performing differential operation on the historical data, and inputting the historical data into an ARIMA model.
Wherein the displaying a trend prediction curve according to the prediction data comprises:
and generating and displaying a trend prediction curve according to the historical data before the current moment and the prediction data after the current moment.
Wherein the performing alarm detection comprises:
judging whether the prediction data at the current moment is larger than an early warning threshold value or not;
and if so, generating and displaying early warning information.
Wherein comparing the predicted data to actual data comprises:
calculating the deviation degree of the predicted data and the corresponding actual data;
and if the deviation degree is within a preset deviation interval, judging that the prediction model meets the prediction requirement, otherwise, judging that the prediction model does not meet the prediction requirement.
And re-performing trend analysis on the newly generated actual data through the prediction model, wherein the trend analysis comprises the following steps:
determining a corresponding deviation score by using the deviation degree;
determining a weight ratio coefficient of newly generated actual data and historical data according to the deviation score;
and carrying out trend analysis again through the prediction model, newly generated actual data, historical data and weight ratio coefficients.
To achieve the above object, the present invention further provides a data monitoring apparatus, comprising:
the acquisition module is used for acquiring historical data;
a determining module for determining the type of the historical data;
the data input module is used for inputting the historical data into a prediction model corresponding to the type;
the analysis module is used for carrying out trend analysis on the historical data through the prediction model to obtain prediction data;
the comparison module is used for comparing the predicted data with the actual data;
the data processing module is used for displaying a trend prediction curve according to the prediction data and carrying out alarm detection when the prediction requirement is met; and if the prediction requirement is not met, triggering the analysis module to perform trend analysis on newly generated actual data again through the prediction model.
Wherein, the data monitoring device further comprises:
the judging module is used for judging whether the historical data is a pure random sequence;
the determining module is specifically configured to determine the type of the historical data when the historical data is not a purely random sequence.
To achieve the above object, the present invention further provides an electronic device comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps of the data monitoring method when executing the computer program.
According to the scheme, the embodiment of the invention provides a data monitoring method, a device and equipment; according to the scheme, firstly, historical data needs to be collected, the type of the historical data is determined, the historical data is input into a prediction model corresponding to the type, and trend analysis is carried out on the historical data through the prediction model to obtain prediction data; then, comparing the predicted data with the actual data, if the predicted data meet the prediction requirement, displaying a trend prediction curve according to the predicted data, and performing alarm detection; and if the prediction requirements are not met, performing trend analysis on the newly generated actual data again through the prediction model. Therefore, according to the scheme, the historical data is subjected to trend analysis through the prediction model, and the prediction data of index change can be obtained before problems occur, so that the monitoring system is assisted to perform early warning, trend prediction curve display and equipment capacity management, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a data monitoring method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a trend analysis disclosed in an embodiment of the present invention;
FIG. 3 is a flow chart of the prediction data early warning and display disclosed in the embodiments of the present invention;
FIG. 4 is a schematic structural diagram of a data monitoring apparatus according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a data monitoring method, a data monitoring device and data monitoring equipment, which are used for early warning in time before problems occur and improving user experience.
Referring to fig. 1, a schematic flow chart of a data monitoring method provided in an embodiment of the present invention includes:
s101, collecting historical data;
it should be noted that, many algorithm models for time series prediction based on Python (computer programming language) can predict the variation trend of a time series with a given length, and on the basis that data has a certain variation trend, the accuracy of the predicted data will be gradually improved along with the increase of the amount of given historical data, and theoretically, the effect of infinite convergence with actual data will be achieved. Therefore, in the application, based on the principle, the trend prediction analysis is carried out on historical data which are counted by a time dimension and exist in the operation and maintenance monitoring system, the data with a certain change trend are fitted, the prediction result is combined with the alarm module and the historical data fold line display, and the purposes of giving out an early warning notice and carrying out the change trend prediction analysis by the prediction data are achieved.
In this embodiment, historical data may be collected from the operation and maintenance monitoring system, where the historical data is data having a change trend in a time series, and the historical data may specifically be data of each monitoring index, such as: historical data of any monitoring indexes such as disk capacity data, CPU (Central processing Unit) utilization rate data, cloud platform virtual machine memory utilization rate data and the like.
S102, determining the type of historical data;
in this embodiment, not all the historical data may be input into the prediction model for trend prediction, only data with a trend effect may be input into the prediction model, and if the historical data is a purely random sequence, the trend prediction cannot be performed because the historical data does not have the trend effect. Therefore, in this embodiment, before determining the type of the historical data, it is further required to determine whether the historical data is a purely random sequence; if not, continuing to execute the step of determining the type of the historical data, if so, indicating that the historical data is not suitable for inputting a prediction model for trend prediction, and ending the process. In this embodiment, in order to generate more accurate prediction data according to the historical data, after determining that the historical data is data with a trend effect, the present solution needs to perform smoothness analysis on the historical data, and determine whether the historical data is a smooth sequence, so as to determine the type of the historical data. The types of the historical data comprise a stationary sequence and a non-stationary sequence, and different types of data need to be input into different prediction models.
S103, inputting the historical data into a prediction model corresponding to the type, and performing trend analysis on the historical data through the prediction model to obtain prediction data;
in this embodiment, if the historical data is a stationary sequence, the historical data is input into an arma (autoregegressive moving average model); if the historical data is a non-stationary sequence, the historical data is input into an ARIMA (automatic Integrated Moving Average model) after differential operation. The ARMA model is an autoregressive moving average model, is an important method for researching a time sequence, and is formed by mixing an autoregressive model (AR model for short) and a moving average model (MA model for short) on the basis. It is commonly used in market research for long-term follow-up data, such as: the Panel research is used for the change research of consumption behavior patterns; in retail research, it is used for sales volume with seasonal variation characteristics, prediction of market size, and the like. The ARIMA model is a differential integrated moving average autoregressive model, also called an integrated moving average autoregressive model, and is one of the time series prediction analysis methods. In ARIMA (p, d, q), AR is "autoregressive" and p is the number of autoregressive terms; MA is "moving average", q is the number of terms of the moving average, and d is the number of differences (order) made to make it a stationary sequence.
Referring to fig. 2, a flow chart of trend analysis is provided for an embodiment of the present invention. As can be seen from fig. 2, in the present scheme, after the operation and maintenance monitoring system acquires the historical data, the historical data needs to be imported into an analysis method for processing, and first, it is determined whether the historical data is a pure random sequence, if so, the historical data is determined to be a white noise sequence, and the analysis is terminated, and if not, the stationarity analysis is performed. According to the scheme, when judging whether the historical data is the pure random sequence or not, the probability value that the historical data is the pure random sequence can be determined through an analysis algorithm, if the probability value is larger than a preset threshold value, the historical data is judged to be the pure random sequence, and if not, the historical data is judged to be data with a trend effect. Further, after the historical data has a trend effect, smoothness analysis needs to be performed on the historical data, if the historical data is a stably distributed sequence, trend analysis is performed by using an ARMA (autoregressive moving average) model, and if the historical data is a non-smooth sequence, analysis is performed by using an ARIMA model after differential operation. After the historical data are input into the prediction model, the change trend of the historical data can be subjected to fitting analysis through the prediction model, and the prediction data are obtained.
S104, comparing the predicted data with the actual data, if the predicted data meet the prediction requirement, displaying a trend prediction curve according to the predicted data, and performing alarm detection; and if the prediction requirements are not met, performing trend analysis on the newly generated actual data again through the prediction model.
In this embodiment, when the prediction data is generated by the prediction model and the historical data, the actual data is also generated, so in order to verify the prediction accuracy of the prediction model, the prediction data needs to be compared with the actual data, so as to determine whether the prediction model meets the prediction requirement. Specifically, when the prediction data is compared with the actual data, the deviation degree of the prediction data and the corresponding actual data can be calculated, if the deviation degree is within a preset deviation interval, the prediction model is judged to meet the prediction requirement, and otherwise, the prediction model is judged not to meet the prediction requirement. For example: the historical data is CPU utilization rate data, the deviation interval is 0% -5%, if the CPU utilization rate of the current time in the predicted data is 50%, and the CPU utilization rate of the actual data is 54%, the deviation degree of the predicted data is 4%, and the prediction model is judged to meet the prediction requirement in the deviation interval; if the CPU utilization rate in the actual data is 65%, the deviation degree of the prediction data is 15%, and the prediction model is not in the deviation interval, so that the prediction model is judged not to meet the prediction requirement.
It should be noted that, in the embodiment, when the prediction data is compared with the actual data to determine whether the model meets the prediction requirement, the determination may be made not only according to the deviation degree, but also according to the deviation degree, a deviation score may be determined, and whether the prediction requirement is met may be determined according to the deviation score. For example: setting a deviation score to be 0-10, wherein the higher the score is, the more accurate the prediction is, and the lower the score is, the larger the prediction deviation is; therefore, when setting the deviation score, the larger the deviation degree is, the smaller the deviation score is. After the deviation score is determined, whether the prediction requirement is met can be judged directly according to the deviation score, such as: and judging whether the deviation score is greater than a preset threshold value, if so, judging that the prediction model meets the prediction requirement, and otherwise, judging that the prediction model does not meet the prediction requirement. Further, if the prediction model meets the prediction requirement, a trend prediction curve is generated and displayed according to historical data before the current moment and prediction data after the current moment. When the alarm detection is carried out, whether the prediction data at the current moment is larger than the early warning threshold value or not can be judged; if yes, generating early warning information and displaying the early warning information; if not, continuing to perform alarm detection.
Referring to fig. 3, a flow chart of prediction data early warning and display provided in the embodiment of the present invention is shown; as can be seen from fig. 3, the process specifically includes the following steps: comparing and calculating the prediction data fitted by the ARMA/ARIMA model with the actual data to obtain deviation scores; judging whether the deviation score is larger than a preset threshold value or not; if the deviation score is larger than the preset threshold value, generating a trend prediction curve and displaying the trend prediction curve, meanwhile, judging whether the prediction data meets the early warning condition, and if so, generating early warning information of the index. If the deviation score is not greater than the predetermined threshold, the newly generated actual data is merged with the historical data for trend analysis.
It should be noted that, after determining the corresponding deviation score by using the deviation degree, if the deviation score is not greater than the predetermined threshold, merging the newly generated actual data into the historical data for trend analysis again, and in the process, specifically, determining a weight ratio coefficient of the newly generated actual data and the historical data according to the deviation score; and (4) carrying out trend analysis again through the prediction model, newly generated actual data, historical data and weight ratio coefficients. The weight ratio coefficient represents the ratio of the weight of the newly generated actual data to the weight of the historical data, and can also be understood as the ratio of the influence factors of the newly generated actual data to the historical data.
It can be understood that the present application may set the early warning threshold according to the warning threshold of the index, for example: for CPU utilization data, the warning threshold is 90%, and the warning threshold for CPU utilization may also be set to 90%. In addition, the generated early warning information at least includes early warning time, current time, early warning data, and the like, where the early warning time is time when the predicted CPU utilization exceeds an early warning threshold, and the current time predicts the current time, and for example, the generated early warning information may be: the prediction data of the CPU utilization rate of 10:00 (early warning time) is predicted to be 92% at 9:00 (current time) and is higher than the early warning threshold value. The early warning information and the trend prediction curve are displayed and can be referred by an administrator, so that preparation measures can be made in time before problems occur, and data support is provided for increasing and decreasing configuration of related resources.
It should be noted that, in this embodiment, when determining whether the prediction model meets the prediction requirement according to the deviation score, the deviation score of each prediction may be recorded, and the time for trend prediction curve display and alarm detection is set according to the deviation score, for example: the trend prediction curve display and the alarm detection can be carried out when the deviation score is set to be larger than the preset threshold value once, or the trend prediction curve display and the alarm detection can be carried out after the deviation score is set to be larger than the preset threshold value continuously for multiple times. Moreover, after the trend prediction curve display and the alarm detection are carried out, whether the periodic detection prediction model meets the prediction requirement can be set, for example: when the deviation score of the prediction model is continuously 10 times larger than the preset threshold value, performing trend prediction curve display and alarm detection, calculating the deviation score of the prediction model again after a preset time interval, and if the detection model is still judged to meet the prediction requirement through the deviation score, continuing to perform the trend prediction curve display and alarm detection; if the detection model is judged not to be in accordance with the prediction requirement through the deviation score, whether trend prediction curve display needs to be continued or not can be determined according to the preset condition, but prompt information that the prediction model does not meet the prediction requirement needs to be displayed, and the alarm detection can be stopped until the prediction model meets the prediction requirement and then the alarm detection is carried out so as to prevent a large amount of false alarms.
In conclusion, according to the scheme, the change trend of the index can be subjected to fitting analysis to generate the prediction data of the index according to the historical data and the prediction model of the time sequence numerical index, and according to the prediction data, the early warning information can be generated before the problem occurs, so that the aim of supplementing and perfecting the conventional warning mechanism from the source is fulfilled. In addition, a prediction curve of a key monitoring index can be provided according to a trend analysis result, so that data support is provided for a manager to increase and decrease configuration of related resources such as disk capacity, the memory size of a cloud platform virtual machine and the number of CPU cores.
In the following, the monitoring apparatus, the device, and the storage medium provided by the embodiments of the present invention are introduced, and the monitoring apparatus, the device, and the storage medium described below and the monitoring method described above may be referred to each other.
Referring to fig. 4, a schematic structural diagram of a data monitoring apparatus provided in an embodiment of the present invention includes:
the acquisition module 11 is used for acquiring historical data;
a determining module 12, configured to determine a type of the historical data;
a data input module 13, configured to input the historical data into a prediction model corresponding to the type;
the analysis module 14 is configured to perform trend analysis on the historical data through the prediction model to obtain predicted data;
a comparison module 15, configured to compare the predicted data with actual data;
the data processing module 16 is used for displaying a trend prediction curve according to the prediction data and performing alarm detection when the prediction requirement is met; and if the prediction requirement is not met, triggering the analysis module to perform trend analysis on newly generated actual data again through the prediction model.
Wherein, the data monitoring device further comprises:
the judging module is used for judging whether the historical data is a pure random sequence;
the determining module is specifically configured to determine the type of the historical data when the historical data is not a purely random sequence.
The determining module is specifically configured to determine whether the historical data is a stationary sequence;
the data input module is specifically used for inputting the historical data into an ARMA model when the historical data is a stable sequence; and when the historical data is a non-stationary sequence, performing differential operation on the historical data, and inputting the historical data into an ARIMA model.
Wherein the data processing module comprises:
and the first display unit is used for generating and displaying a trend prediction curve according to the historical data before the current moment and the prediction data after the current moment.
And the second display unit is used for judging whether the prediction data at the current moment is larger than the early warning threshold value or not, and if so, generating and displaying early warning information.
Wherein the comparison module comprises:
a calculation unit for calculating a degree of deviation of the predicted data from the corresponding actual data;
and the judging unit is used for judging that the prediction model meets the prediction requirement when the deviation degree is within a preset deviation interval, and otherwise, judging that the prediction model does not meet the prediction requirement.
Wherein the analysis module comprises:
a first determining unit for determining a corresponding deviation score using the deviation degree;
the second determining unit is used for determining a weight ratio coefficient of newly generated actual data and historical data according to the deviation score;
and the analysis unit performs trend analysis again through the prediction model, newly generated actual data, historical data and the weight ratio coefficient.
Referring to fig. 5, an electronic device according to an embodiment of the present invention includes:
a memory 21 for storing a computer program;
a processor 22, configured to implement the steps of the data monitoring method according to the above-mentioned method embodiment when executing the computer program.
In this embodiment, the device may be a PC (Personal Computer), or may be a terminal device such as a smart phone, a tablet Computer, a palmtop Computer, or a portable Computer.
The device may include a memory 21, a processor 22, and a bus 23.
The memory 21 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 21 may in some embodiments be an internal storage unit of the device, for example a hard disk of the device. The memory 21 may also be an external storage device of the device in other embodiments, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) Card, Flash memory Card (Flash Card), etc. provided on the device. Further, the memory 21 may also include both an internal storage unit of the device and an external storage device. The memory 21 may be used not only to store application software installed in the device and various types of data such as program codes for executing a data monitoring method, etc., but also to temporarily store data that has been output or is to be output.
The processor 22 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip in some embodiments, and is used for executing program codes stored in the memory 21 or Processing data, such as program codes for executing data monitoring methods.
The bus 23 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus.
Further, the device may further include a network interface 24, and the network interface 24 may optionally include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), which are generally used to establish a communication connection between the device and other electronic devices.
Optionally, the device may further comprise a user interface 25, the user interface 25 may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 25 may also comprise a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the device and for displaying a visualized user interface.
Fig. 5 shows only the device with the components 21-25, and it will be understood by those skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the device, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the data monitoring method in the above-mentioned method embodiment are implemented.
Wherein the storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In conclusion, according to the scheme, the index historical data is subjected to trend analysis, the data with the determined change trend is predicted, early warning information before problems occur can be generated according to the predicted data, meanwhile, a change prediction curve is drawn by combining the predicted information with the actual historical data, and through the mode, the monitoring system can be assisted in index early warning, index change trend display and equipment capacity management.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for monitoring data, comprising:
collecting historical data;
determining the type of the historical data;
inputting the historical data into a prediction model corresponding to the type, and performing trend analysis on the historical data through the prediction model to obtain prediction data;
comparing the predicted data with actual data, if the predicted data meets the prediction requirement, displaying a trend prediction curve according to the predicted data, and performing alarm detection; and if the prediction requirement is not met, performing trend analysis on the newly generated actual data again through the prediction model.
2. The data monitoring method of claim 1, wherein prior to determining the type of the historical data, further comprising:
judging whether the historical data is a pure random sequence;
if not, continuing to execute the step of determining the type of the historical data.
3. The data monitoring method of claim 1, wherein the determining a type of the historical data and the inputting the historical data into a predictive model corresponding to the type comprises:
judging whether the historical data is a stable sequence;
if yes, inputting the historical data into an ARMA model; and if not, performing differential operation on the historical data, and inputting the historical data into an ARIMA model.
4. The data monitoring method of claim 1, wherein said displaying a trend prediction curve based on said prediction data comprises:
and generating and displaying a trend prediction curve according to the historical data before the current moment and the prediction data after the current moment.
5. The data monitoring method of claim 4, wherein the performing alarm detection comprises:
judging whether the prediction data at the current moment is larger than an early warning threshold value or not;
and if so, generating and displaying early warning information.
6. The data monitoring method of any one of claims 1 to 5, wherein comparing the predicted data with actual data comprises:
calculating the deviation degree of the predicted data and the corresponding actual data;
and if the deviation degree is within a preset deviation interval, judging that the prediction model meets the prediction requirement, otherwise, judging that the prediction model does not meet the prediction requirement.
7. The data monitoring method of claim 6, wherein said re-trending newly generated actual data by said predictive model comprises:
determining a corresponding deviation score by using the deviation degree;
determining a weight ratio coefficient of newly generated actual data and historical data according to the deviation score;
and carrying out trend analysis again through the prediction model, newly generated actual data, historical data and weight ratio coefficients.
8. A data monitoring device, comprising:
the acquisition module is used for acquiring historical data;
a determining module for determining the type of the historical data;
the data input module is used for inputting the historical data into a prediction model corresponding to the type;
the analysis module is used for carrying out trend analysis on the historical data through the prediction model to obtain prediction data;
the comparison module is used for comparing the predicted data with the actual data;
the data processing module is used for displaying a trend prediction curve according to the prediction data and carrying out alarm detection when the prediction requirement is met; and if the prediction requirement is not met, triggering the analysis module to perform trend analysis on newly generated actual data again through the prediction model.
9. The data monitoring device of claim 8, further comprising:
the judging module is used for judging whether the historical data is a pure random sequence;
the determining module is specifically configured to determine the type of the historical data when the historical data is not a purely random sequence.
10. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the data monitoring method according to any one of claims 1 to 7 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527303.5A CN113934615A (en) | 2021-12-15 | 2021-12-15 | Data monitoring method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527303.5A CN113934615A (en) | 2021-12-15 | 2021-12-15 | Data monitoring method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113934615A true CN113934615A (en) | 2022-01-14 |
Family
ID=79288944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111527303.5A Pending CN113934615A (en) | 2021-12-15 | 2021-12-15 | Data monitoring method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113934615A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664063A (en) * | 2022-04-07 | 2022-06-24 | 安徽智寰科技有限公司 | Equipment grading alarm method based on general index trend analysis |
| CN114968744A (en) * | 2022-06-07 | 2022-08-30 | 北京同创永益科技发展有限公司 | Implementation method and system for capacity management prediction analysis AI algorithm based on financial industry |
| CN115639470A (en) * | 2022-09-23 | 2023-01-24 | 贵州北盘江电力股份有限公司光照分公司 | Generator monitoring method and system based on data trend analysis |
| CN116610681A (en) * | 2023-07-20 | 2023-08-18 | 深圳维格云科技有限公司 | Data processing method, device, equipment and computer program for multidimensional table |
| CN116823075A (en) * | 2023-08-29 | 2023-09-29 | 小象飞羊(北京)科技有限公司 | City data construction model, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617468A (en) * | 2013-12-13 | 2014-03-05 | 李敬泉 | Medium and long term predication method for necessities of life |
| CN105550772A (en) * | 2015-12-09 | 2016-05-04 | 中国电力科学研究院 | Online historical data tendency analysis method |
| CN107832204A (en) * | 2017-11-29 | 2018-03-23 | 郑州云海信息技术有限公司 | A kind of server CPU energy consumption Forecasting Methodologies based on MDC |
| CN111221706A (en) * | 2020-01-06 | 2020-06-02 | 北京思特奇信息技术股份有限公司 | CPU utilization rate prediction method, system, medium and equipment |
| CN111913803A (en) * | 2020-07-21 | 2020-11-10 | 哈尔滨工程大学 | Service load fine granularity prediction method based on AKX hybrid model |
| CN113065678A (en) * | 2019-12-13 | 2021-07-02 | 中兴通讯股份有限公司 | Performance index early warning method, device, equipment and storage medium |
-
2021
- 2021-12-15 CN CN202111527303.5A patent/CN113934615A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617468A (en) * | 2013-12-13 | 2014-03-05 | 李敬泉 | Medium and long term predication method for necessities of life |
| CN105550772A (en) * | 2015-12-09 | 2016-05-04 | 中国电力科学研究院 | Online historical data tendency analysis method |
| CN107832204A (en) * | 2017-11-29 | 2018-03-23 | 郑州云海信息技术有限公司 | A kind of server CPU energy consumption Forecasting Methodologies based on MDC |
| CN113065678A (en) * | 2019-12-13 | 2021-07-02 | 中兴通讯股份有限公司 | Performance index early warning method, device, equipment and storage medium |
| CN111221706A (en) * | 2020-01-06 | 2020-06-02 | 北京思特奇信息技术股份有限公司 | CPU utilization rate prediction method, system, medium and equipment |
| CN111913803A (en) * | 2020-07-21 | 2020-11-10 | 哈尔滨工程大学 | Service load fine granularity prediction method based on AKX hybrid model |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664063A (en) * | 2022-04-07 | 2022-06-24 | 安徽智寰科技有限公司 | Equipment grading alarm method based on general index trend analysis |
| CN114968744A (en) * | 2022-06-07 | 2022-08-30 | 北京同创永益科技发展有限公司 | Implementation method and system for capacity management prediction analysis AI algorithm based on financial industry |
| CN114968744B (en) * | 2022-06-07 | 2023-04-07 | 北京同创永益科技发展有限公司 | Implementation method and system based on financial industry capacity management prediction analysis AI algorithm |
| CN115639470A (en) * | 2022-09-23 | 2023-01-24 | 贵州北盘江电力股份有限公司光照分公司 | Generator monitoring method and system based on data trend analysis |
| CN115639470B (en) * | 2022-09-23 | 2024-01-30 | 贵州北盘江电力股份有限公司光照分公司 | Generator monitoring method and system based on data trend analysis |
| CN116610681A (en) * | 2023-07-20 | 2023-08-18 | 深圳维格云科技有限公司 | Data processing method, device, equipment and computer program for multidimensional table |
| CN116610681B (en) * | 2023-07-20 | 2023-12-12 | 深圳维格云科技有限公司 | Data processing method, device, equipment and computer program for multidimensional table |
| CN116823075A (en) * | 2023-08-29 | 2023-09-29 | 小象飞羊(北京)科技有限公司 | City data construction model, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113934615A (en) | Data monitoring method, device and equipment | |
| CN109697207B (en) | Method and system for monitoring abnormity of time sequence data | |
| CN111813624B (en) | Robot execution time length estimation method based on time length analysis and related equipment thereof | |
| WO2019056793A1 (en) | Device, method, and computer readable storage medium for identifying resume | |
| KR20150036684A (en) | Method and device for controlling terminal and terminal thereof | |
| CN112446209A (en) | Method, equipment and device for setting intention label and storage medium | |
| CN109559218A (en) | A kind of determination method, apparatus traded extremely and storage medium | |
| CN113590007B (en) | Method and device for generating progress bar, computer equipment and storage medium | |
| CN110618797B (en) | Method and device for generating character trotting horse lamp and terminal equipment | |
| CN116824455A (en) | Event detection method, device, equipment and storage medium | |
| CN116431731A (en) | Data asynchronous export method, device, equipment and storage medium thereof | |
| CN115774602A (en) | Container resource allocation method, device, equipment and storage medium | |
| CN113112311B (en) | Method for training causal inference model and information prompting method and device | |
| CN114357293A (en) | Object recommendation method and device, electronic equipment and computer-readable storage medium | |
| RU2724799C1 (en) | Information processing method for filling data model library and device for its implementation | |
| CN111782208A (en) | Index early warning method and device, computer equipment and storage medium | |
| CN113743721A (en) | Marketing strategy generation method and device, computer equipment and storage medium | |
| CN109740056A (en) | It is a kind of for provide a user customization financial information method and apparatus | |
| CN116738241B (en) | Threshold generation method, device, terminal and medium based on time granularity | |
| CN112685246B (en) | Time sequence data processing method and device | |
| CN111783447B (en) | Sensitive word detection method, device and equipment based on ngram distance and storage medium | |
| US20210044237A1 (en) | Method and apparatus for adaptive control of motor, and storage medium | |
| CN111723577A (en) | Method, device and equipment for interrogation based on preset interrogation mode | |
| CN117216803A (en) | Intelligent finance-oriented user information protection method and system | |
| CN118152678A (en) | Article display 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220114 |
|
| RJ01 | Rejection of invention patent application after publication |