WO2021115116A1

WO2021115116A1 - Early-warning method and apparatus for performance indicator, and device and storage medium

Info

Publication number: WO2021115116A1
Application number: PCT/CN2020/131179
Authority: WO
Inventors: 戴新宇
Original assignee: 中兴通讯股份有限公司
Priority date: 2019-12-13
Filing date: 2020-11-24
Publication date: 2021-06-17
Also published as: CN113065678A

Abstract

An early-warning method and apparatus for a performance indicator, and a device and a storage medium. The early-warning method for a performance indicator comprises: according to the historical data of a performance indicator, determining the predicted data of the performance indicator within a set time period (S110); determining the change trend curve of a difference according to the difference between the predicted data and the actual data of the performance indicator in the set time period (S120); and if the time period during which the difference value reaches a corresponding difference value threshold in the change trend curve is less than a set time period, determining that the performance indicator is degraded (S130).

Description

Early warning method, device, equipment and storage medium of performance index

Cross-references to related applications

This application is filed based on the Chinese patent application with the application number 201911283180.8 and the filing date on December 13, 2019, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated into this application by reference.

Technical field

The embodiments of the present application relate to the field of communication technology, and in particular, to an early warning method, device, equipment, and storage medium for performance indicators.

Background technique

In the daily operation and maintenance of the communication system, some key performance indicators (KPI) are usually used to measure the operating status of the communication system. For example, the communication system can be measured according to KPI indicators such as traffic, connection rate, or dropped call rate. The running state is good or bad. The deterioration of KPI indicators usually has two forms: one is a rapid decline, that is, the KPI indicators have a large change in a short period of time; the other is a slow decline, that is, the KPI indicators have a large difference in a longer period of time. In view of the slow decline, the traditional way is to measure the operating status of the communication system by manually observing the changes of KPI indicators on a regular basis, which not only increases the manpower, but also fails to understand the operating status of the communication system in time.

Summary of the invention

The embodiments of the present application provide an early warning method, device, equipment, and storage medium for performance indicators, so as to solve the problem of not being able to understand the operating status of the communication system in time to at least a certain extent.

In the first aspect, an embodiment of the present application provides an early warning method for a performance indicator, which includes: determining predicted data of the performance indicator within a set time period based on historical data of the performance indicator; and based on the predicted data and the performance The difference between the actual data of the indicator in the set time period is determined, and the change trend curve of the difference is determined; if the difference reaches the corresponding difference threshold in the change trend curve and the duration is less than the set duration, then it is determined The performance index is degraded.

In a second aspect, an embodiment of the present application also provides an early warning device for a performance indicator, including: a prediction data determining module, configured to determine the predicted data of the performance indicator in a set time period according to the historical data of the performance indicator; and a curve; The determining module is used to determine the change trend curve of the difference according to the difference between the predicted data and the actual data of the performance index in a set time period; the performance index deterioration determining module is used to determine if the difference is When the time period when the value reaches the corresponding difference threshold in the change trend curve is less than the set time period, it is determined that the performance index is degraded.

In a third aspect, an embodiment of the present application also provides a device, including: one or more processors; a memory, used to store one or more programs; when the one or more programs are used by the one or more When the processor is executed, the one or more processors implement the early warning method of the performance index as described in the first aspect.

In a fourth aspect, an embodiment of the present application also provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the early warning method of the performance index as described in the first aspect is realized.

Description of the drawings

FIG. 1 is a flowchart of an early warning method for performance indicators provided by an embodiment of the application;

2 is a flowchart of another early warning method for performance indicators provided by an embodiment of the application;

FIG. 3 is a schematic diagram of a variation trend curve of a difference provided by an embodiment of the application;

FIG. 4 is an implementation flowchart of an early warning method for performance indicators provided by an embodiment of the application;

FIG. 5 is a structural diagram of a performance indicator early warning device provided by an embodiment of the application;

Fig. 6 is a structural diagram of a device provided by an embodiment of the application.

Detailed ways

The application will be further described in detail below with reference to the drawings and embodiments. It is understandable that the specific embodiments described here are only used to explain the application, but not to limit the application. In addition, it should be noted that, for ease of description, the drawings only show a part of the structure related to the present application instead of all of the structure. In addition, if there is no conflict, the embodiments in the application and the features in the embodiments can be combined with each other.

Figure 1 is a flow chart of an early warning method for performance indicators provided by an embodiment of the application. This embodiment is suitable for intelligent monitoring of changes in performance indicators, especially for monitoring changes in performance indicators in unattended communication systems. In order to understand the operating status of the communication system in advance based on changes in performance indicators. The method can be implemented by an early warning device of performance indicators, which can be implemented in software and/or hardware and integrated in a computer and other equipment. With reference to Figure 1, the method includes the following steps:

S110: According to the historical data of the performance indicator, determine the predicted data of the performance indicator within a set time period.

In this embodiment, the performance index is called KPI index. The KPI index can be determined according to the measured content. For example, when measuring the operating status of the communication system, the traffic, the connection rate, the traffic volume, or the dropped call rate can be used as the KPI index. . The historical data of the KPI indicator is the data of the KPI indicator in the historical time period. Among them, the size of the historical time period affects the accuracy of the predicted data. For example, if the historical time period is too small, it is easy to cause insufficient information, which makes the predicted data and the actual value If the historical time period is too large, it will not only increase the processing complexity and processing time, but also increase the risk of over-fitting, which will also cause a large deviation between the predicted data and the actual value. The historical time period in this embodiment takes 7 days as an example, that is, the historical data is the data of the KPI indicator within 7 days before the current time.

The predicted data is the data corresponding to the KPI indicator in the set time period after the current time. Considering that the KPI indicator in the communication system has periodic characteristics, that is, it changes regularly within 24 hours. In some embodiments, the set time period is 24 hours. , That is, according to historical data, determine the data of KPI indicators within 24 hours after the current time as forecast data. The size of the set time period can be used to determine the amount of forecast data on the one hand, and can be used to determine the time point of the next cycle on the other hand.

In some embodiments, the triple exponential smoothing algorithm, Holt-Winters algorithm for short, can be used to predict the data of the KPI indicator in the next 24 hours in combination with historical data. The Holt-Winters algorithm can predict time series that contain both trend and seasonality, and meets the trend and seasonality characteristics of KPI indicators such as traffic and traffic in the communication system. Specifically, the historical data of KPI indicators can be substituted into the Holt-Winters algorithm, the parameters included in the Holt-Winters algorithm can be obtained by fitting, and the KPI indicators in the next 24 hours can be predicted according to the fitted parameter values to obtain the prediction data.

S120: Determine a change trend curve of the difference according to the difference between the predicted data and the actual data of the performance indicator in a set time period.

The actual data of the KPI indicator is the actual data of the KPI indicator in the set time period. According to the forecast data and actual data, the difference between the KPI indicators in the set time period can be determined. In order to understand the change of KPI indicators in advance, the operation and maintenance personnel are notified in time before the risk of the communication system occurs. The embodiment predicts the change trend of the difference according to the difference between the predicted data of the KPI indicator and the actual data, and obtains the change trend of the difference. curve.

In some embodiments, the curve fitting method may be combined with the difference value within a set time period to obtain the change trend curve of the difference value, wherein the curve fitting method may be the least square method. The least square method, also known as the least square method, is a commonly used curve fitting method. The embodiment does not limit the specific fitting process. In this embodiment, the difference is predicted on the basis of the difference, and the change trend curve of the difference is obtained. According to the change trend curve, the change of the KPI index can be predicted in advance, so that when the deterioration of the KPI index is predicted, the operator is notified in advance. Maintenance personnel deal with it, reducing the risk.

S130: If the time period during which the difference value reaches the corresponding difference value threshold in the change trend curve is less than a set time period, determine that the performance index is degraded.

The change trend curve reflects the change of the difference over time, and each difference corresponds to a time point. The difference threshold is a point in the change trend curve. When determining whether the KPI indicator is degraded, it can be determined according to the time period when the difference between the predicted data and the actual data reaches the difference threshold. For example, when the difference between the predicted data and the actual data reaches the difference threshold, the time period is less than the set time. The KPI indicator is degraded, otherwise, it is determined that the KPI indicator is normal, where the size of the set duration can be set according to the actual situation, for example, it can be set to 1 hour. Considering that there are multiple predicted data and actual data in the set time period, that is, there are multiple differences, the multiple differences are arranged in chronological order, and the difference at the last time point is used as the basis for whether the KPI indicator has deteriorated. That is, if the time period during which the difference value corresponding to the last time point in the set time period reaches the difference value threshold is less than the set time period, it is determined that the KPI indicator is degraded.

In some embodiments, after determining the deterioration of the KPI indicator, the alarm information of the deterioration of the KPI indicator may be sent to the terminal corresponding to the operation and maintenance personnel in a short message or email, so that the operation and maintenance personnel can take measures in advance to eliminate alarms and potential safety hazards.

The embodiment of the present application provides an early warning method for performance indicators. According to historical data of the performance indicators, the predicted data of the performance indicators within a set time period is determined, and the predicted data of the performance indicators are within the set time period based on the predicted data and the performance indicators. Determine the change trend curve of the difference value by the difference value of the actual data, if the difference value reaches the corresponding difference value threshold in the change trend curve for a duration less than the set duration, then determine that the performance index is degraded. The embodiment of the application does not need to manually check regularly, which saves manpower, and can predict the change trend of the difference based on the historical data and actual data of the performance indicator, predict the change of the performance indicator in advance, and timely understand the operating status of the communication system corresponding to the performance indicator .

On the basis of the foregoing embodiments, in some embodiments, the prediction data of the KPI indicator within a set time period can be determined in the following manner:

Acquiring historical data of the performance indicator in a historical time period;

Determine the parameter information of the prediction algorithm according to the prediction algorithm and the historical data;

According to the parameter information, the predicted data of the performance index in a set time period is determined.

The prediction algorithm of this embodiment takes the Holt-Winters algorithm as an example. The Holt-Winters algorithm contains three parameters to be fitted, namely α, β, and γ. α, β, and γ are between 0-1. According to history The data can be fitted to the specific values of α, β and γ. When α, β, and γ are determined, substitute the Holt-Winters algorithm to predict the data of the KPI indicator in the future set time period. The embodiment does not limit the fitting process of α, β, and γ.

Fig. 2 is a flowchart of another early warning method for performance indicators provided by an embodiment of the application.

This embodiment is optimized on the basis of the above embodiment. Referring to FIG. 2, the method includes the following steps:

S210: According to the historical data of the performance indicator, determine the predicted data of the performance indicator within a set time period.

S220: Acquire actual data of the performance index at every set time interval within the set time period.

Considering the continuous characteristics of time, there are many forecast data and actual data. In the embodiment, the actual data of the KPI indicator is acquired at a set time interval as the actual data of the KPI indicator. In some embodiments, it can be obtained every 15 minutes, so that multiple actual data within a set time period can be obtained.

S230: Determine respectively the difference between the actual data and the predicted data at the time points corresponding to the actual data.

Every time a piece of actual data is obtained, the difference between the predicted data and the actual data at that point in time is calculated to obtain multiple differences. The embodiment records each actual data as a point.

S240: Determine a fitting curve of the difference according to each of the difference and the curve fitting algorithm, as a change trend curve of the difference.

When determining the change trend curve of the difference, it can be determined according to the obtained differences, or a part of the difference can be selected from it. The embodiment takes the partial difference as an example. When selecting partial differences, the number of differences needs to take into account both accuracy and timeliness of early warning. In this embodiment, the differences can be arranged in the order of time points, and the differences corresponding to the last three time points are selected as the change. The basis for determining the trend curve. Among them, the curve fitting algorithm takes the least square method as an example. Correspondingly, S240 includes:

Determine the parameter information of the curve fitting algorithm according to each of the differences and the curve fitting algorithm;

According to the parameter information of the curve fitting algorithm, a polynomial fitting curve is determined as the fitting curve of the difference.

The polynomial parameters of the least squares method can be determined according to the size of the selected three differences, combined with the least square method, and the polynomial parameters are substituted into the equation corresponding to the least square method to obtain the corresponding polynomial fitting equation, and draw the polynomial Fit the curve corresponding to the equation to obtain a polynomial fitting curve. The least square method can be used to fit the trend of the difference value, thereby predicting the time limit for exceeding the limit, and assisting the operation and maintenance personnel in decision-making, which not only reduces labor intensity, but also improves work efficiency.

FIG. 3 is a schematic diagram of a variation trend curve of a difference provided by an embodiment of the application.

The curve in Figure 3 is the difference change trend curve obtained by fitting the least square method and difference A, difference B and difference C. The time points corresponding to difference A, difference B and difference C are respectively t1 , T2 and t3, the time point corresponding to the difference threshold M is t0.

S250. Determine, according to the time point corresponding to the difference threshold value in the change trend curve and the time point of the difference value closest to the time point in the difference value, that the difference value closest to the time point reaches the difference value The duration of the threshold.

Referring to FIG. 3, the embodiment uses the time length of the time point t3 corresponding to the difference value C and the time point t0 corresponding to the difference value threshold M as the basis to determine whether the KPI indicator has deteriorated. Specifically, if the time period from t3 to t0 is less than the set time period, the KPI indicator is considered to be degraded, otherwise, the KPI indicator is considered to be normal.

S260. Whether the duration is less than the set duration, if yes, execute S270; otherwise, execute S290.

S270. Determine that the performance index has deteriorated.

S280. Display the early warning information of the deterioration of the performance index.

In some embodiments, after determining the deterioration of the KPI indicator, the early warning information of the deterioration of the KPI indicator is automatically pushed to the operation and maintenance personnel to notify the operation and maintenance personnel to deal with it in time and reduce the risk.

S290. Determine that the performance index is normal.

The early warning method for performance indicators provided in the embodiments of this application is based on the above embodiments, according to the difference between the predicted data and the actual data in a set time period, combined with the curve fitting algorithm to obtain the change trend curve of the difference, which realizes The prediction of the difference can predict in advance whether the KPI indicator will deteriorate, which not only reduces labor intensity and improves work efficiency, but also informs the operation and maintenance personnel to deal with it in time before the KPI indicator deteriorates, reducing the risk.

Fig. 4 is an implementation flowchart of a performance indicator warning method provided by an embodiment of the application.

Figure 4 takes the prediction algorithm as the Holt-Winters algorithm, and the curve fitting algorithm takes the least square method as an example. Specifically, according to the Holt-Winters algorithm, the acquired historical data of the KPI indicator is predicted to obtain the predicted data of the KPI indicator in a set time period, and the difference between the predicted data and the actual data of the KPI indicator in the set time period is made , Get a finite number of differences, and then predict the change trend of the difference according to the difference of the last three times and the least square method, and get the change trend curve. According to the difference threshold and the time point corresponding to the last difference, get the latest The time when the difference reaches the difference threshold. If the time is less than the set time, the KPI indicator is determined to be degraded, and the early warning information of the KPI indicator degradation is displayed to notify the operation and maintenance personnel to deal with it in time.

Fig. 5 is a structural diagram of an early warning device with performance indicators provided by an embodiment of the application. The device can execute the early warning method of performance indicators described in the foregoing embodiment. Referring to FIG. 5, the device includes:

The forecast data determining module 510 is configured to determine the forecast data of the performance index in a set time period according to the historical data of the performance index;

The curve determination module 520 is configured to determine the change trend curve of the difference according to the difference between the predicted data and the actual data of the performance index in a set time period;

The performance index deterioration determining module 530 is configured to determine that the performance index is deteriorated if the time period during which the difference value reaches the corresponding difference value threshold in the change trend curve is less than a set time period.

The embodiment of the present application provides an early warning device for a performance indicator, which determines the predicted data of the performance indicator in a set time period according to historical data of the performance indicator, and determines the predicted data of the performance indicator in a set time period according to the predicted data and the performance indicator. Determine the change trend curve of the difference value by the difference value of the actual data, if the difference value reaches the corresponding difference value threshold in the change trend curve for a duration less than the set duration, then determine that the performance index is degraded. The embodiment of the application does not need to manually check regularly, which saves manpower, and can predict the change trend of the difference based on the historical data and actual data of the performance indicator, predict the change of the performance indicator in advance, and timely understand the operating status of the communication system corresponding to the performance indicator .

On the basis of the foregoing embodiment, the prediction data determining module 510 is specifically configured to:

On the basis of the foregoing embodiment, the curve determination module 520 includes:

The actual data acquisition unit is configured to acquire the actual data of the performance index at every set time interval within the set time period;

The difference determining unit is used to determine the difference between each of the actual data and the predicted data at the time point corresponding to the actual data;

The curve determination unit is configured to determine the fitting curve of the difference according to each of the difference and the curve fitting algorithm, as the change trend curve of the difference.

On the basis of the foregoing embodiment, the curve determination unit is specifically used for:

On the basis of the foregoing embodiment, the performance index deterioration determining module 530 is specifically configured to:

According to the time point corresponding to the difference threshold value in the change trend curve and the time point of the difference value closest to the time point in the difference value, it is determined that the difference value closest to the time point reaches the difference value threshold value. duration;

If the duration is less than the set duration, it is determined that the performance index is degraded.

On the basis of the foregoing embodiment, the device further includes:

The information display module is configured to display the early warning information of the performance index deterioration after the performance index deterioration is determined.

The early-warning device for performance indicators provided in the embodiments of the present application can execute the early-warning method for performance indicators provided in the above-mentioned embodiments of the present application, and has the corresponding functional modules and beneficial effects of the execution method.

Referring to FIG. 6, the device includes a processor 610, a memory 620, an input device 630, and an output device 640. The number of processors 610 in the device may be one or more. In FIG. 6, one processor 610 is taken as an example. The processor 610, the memory 620, the input device 630, and the output device 640 may be connected by a bus or other methods. In FIG. 6, the connection by a bus is taken as an example.

As a computer-readable storage medium, the memory 620 can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the early warning method of performance indicators in the embodiments of the present application. The processor 610 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 620, that is, realizes the early warning method of the performance indicators of the foregoing embodiments.

The memory 620 mainly includes a program storage area and a data storage area. The program storage area can store an operating system and an application program required by at least one function; the data storage area can store data created according to the use of the terminal, and the like. In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some examples, the memory 620 may further include a memory remotely provided with respect to the processor 610, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 630 may be used to receive inputted numeric or character information, and generate key signal input related to user settings and function control of the device. The output device 640 may include a display device such as a display screen, a speaker, and an audio device such as a buzzer.

The equipment provided in this embodiment of the application and the performance indicator warning method provided in the above embodiment belong to the same concept. For technical details not described in this embodiment in detail, please refer to the above embodiment, and this embodiment has an early warning method for executing performance indicators. The same beneficial effect.

An embodiment of the present application further provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the method for early warning of performance indicators as described in the foregoing embodiment of the present application is implemented.

Of course, a storage medium containing computer-executable instructions provided by the embodiments of the present application is not limited to the operations in the early warning method for performance indicators as described above, and can also execute the operations provided in any of the embodiments of the present application. The related operations in the early warning method of the performance indicators of the system, and have corresponding functions and beneficial effects.

The embodiment of the application provides an early warning method, device, equipment, and storage medium of a performance indicator. According to historical data of the performance indicator, the predicted data of the performance indicator in a set time period is determined, and the predicted data of the performance indicator is determined according to the predicted data and the performance. The difference between the actual data of the indicator in the set time period is determined, and the change trend curve of the difference is determined. If the difference reaches the corresponding difference threshold in the change trend curve and the duration is less than the set duration, then it is determined The performance index is degraded. The embodiment of the application does not require manual periodic checking, which saves manpower, and can predict the change trend of the difference based on the historical data and actual data of the performance indicator, predict the change of the performance indicator in advance, and timely understand the operating status of the communication system corresponding to the performance indicator .

Through the above description of the implementation manners, those skilled in the art can clearly understand that this application can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation. . Based on this understanding, the technical solution of this application essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk. , Read-Only Memory (ROM), Random Access Memory (RAM), Flash memory (FLASH), hard disk or optical disk, etc., including several instructions to make a computer device (which can be a robot, A personal computer, a server, or a network device, etc.) execute the early warning method of performance indicators described in the above-mentioned embodiments of this application.

Note that the above are only the preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions can be made to those skilled in the art without departing from the protection scope of the present application. Therefore, although the application has been described in more detail through the above embodiments, the application is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the application. The scope of is determined by the scope of the appended claims.

Claims

An early warning method for performance indicators, including:

According to the historical data of the performance index, determine the predicted data of the performance index within a set time period;

Determine the change trend curve of the difference according to the difference between the predicted data and the actual data of the performance indicator in a set time period;

If the time period during which the difference value reaches the corresponding difference value threshold in the change trend curve is less than the set time period, it is determined that the performance index is degraded.
The method according to claim 1, wherein the determining the predicted data of the performance indicator in a set time period according to the historical data of the performance indicator comprises:

Acquiring historical data of the performance indicator in a historical time period;

Determine the parameter information of the prediction algorithm according to the prediction algorithm and the historical data;

According to the parameter information, the predicted data of the performance index in a set time period is determined.
The method according to claim 1, wherein the determining the change trend curve of the difference according to the difference between the predicted data and the actual data of the performance indicator in a set time period comprises:

Acquiring actual data of the performance index at every set time interval within the set time period;

Respectively determine the difference between the actual data and the predicted data at the time points corresponding to the actual data;

According to each of the difference and the curve fitting algorithm, a fitting curve of the difference is determined as a change trend curve of the difference.
The method according to claim 3, wherein said determining the fitting curve of the difference according to each of the difference and a curve fitting algorithm comprises:

Determining the parameter information of the curve fitting algorithm according to each of the differences and the curve fitting algorithm;

According to the parameter information of the curve fitting algorithm, a polynomial fitting curve is determined as the fitting curve of the difference.
3. The method according to claim 3, wherein the determining that the performance index is degraded if the time period during which the difference value reaches the corresponding difference value threshold in the change trend curve is less than a set time period comprises:

According to the time point corresponding to the difference threshold value in the change trend curve and the time point of the difference value closest to the time point in the difference value, it is determined that the difference value closest to the time point reaches the difference value threshold value. duration;

If the duration is less than the set duration, it is determined that the performance index is degraded.
The method according to any one of claims 1 to 5, wherein after determining that the performance index has deteriorated, the method further comprises:

Display the early warning information of the deterioration of the performance index.
An early warning device for performance indicators, including:

A predictive data determining module, which is used to determine the predictive data of the performance index in a set time period according to the historical data of the performance index;

A curve determination module, configured to determine the change trend curve of the difference according to the difference between the predicted data and the actual data of the performance index in a set time period;

The performance index degradation determining module is configured to determine that the performance index is degraded if the time period during which the difference reaches the corresponding difference threshold in the change trend curve is less than a set time period.
The device according to claim 7, wherein the predictive data determining module is configured to:

Acquiring historical data of the performance indicator in a historical time period;

Determine the parameter information of the prediction algorithm according to the prediction algorithm and the historical data;

According to the parameter information, the predicted data of the performance index in a set time period is determined.
A device that includes:

One or more processors;

Memory, used to store one or more programs;

When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the early warning method for performance indicators according to any one of claims 1-6.
A storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the early warning method of the performance index according to any one of claims 1 to 6 is realized.