Service index monitoring method and device

What is AI technical title?
AI technical title is built by Patsnap AI team. It summarizes the technical point description of the patent document.
Through time series prediction analysis based on historical data, the predicted expectation value of business indicators is calculated and the upper and lower limit of dynamic expectation is determined, which solves the problem that business indicator abnormalities cannot be discovered in a timely manner in the prior art, and improves the accuracy of monitoring.

CN120216277APending Publication Date: 2025-06-27NETSUNION CLEARING CORP

View PDF 0 Cites 0 Cited by

Patent Information

Application Number: CN202311801405.0
Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner
Filing Date: 2023-12-26
Publication Date: 2025-06-27

AI Technical Summary

Technical Problem

In the monitoring of business indicators, the existing technology cannot promptly discover the situation where the actual value does not exceed the expected value but is lower than the conventional standards, resulting in the inability to promptly discover abnormal business indicators.

Method used

By performing time series prediction analysis based on historical data, the predicted expected value of business indicators is calculated, and the expected upper limit and lower limit are determined based on the expected value and preset value, so as to monitor it to avoid failure to detect abnormal situations in time.

Benefits of technology

It improves the accuracy of business indicator monitoring, can promptly detect abnormal situations in business indicators, and avoid potential losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN120216277A_ABST

Patent Text Reader

Abstract

The invention discloses a service index monitoring method and device, and the method comprises the steps: determining an expected value corresponding to a service index at a prediction moment from a mapping relation in response to a monitoring request; wherein the mapping relation comprises expected values corresponding to the current moment and moments after the current moment, and is obtained by calculation according to a time sequence prediction method based on historical business indexes; the prediction time is any one of the current time and the time after the current time. And determining an expected upper limit and an expected lower limit corresponding to the business index at the prediction moment according to the expected value corresponding to the business index at the prediction moment and a preset value. And finally, monitoring the business index at the prediction moment according to the expected upper limit and the expected lower limit corresponding to the business index at the prediction moment. The problem that if the actual value of the service index does not exceed the expected value, but the actual value is lower than the conventional standard, the abnormality of the service index cannot be found in time is avoided, and the accuracy of service index monitoring is improved.

Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular, to a method and device for monitoring service metrics. Background Art

[0002] Service metrics are metrics that reflect the service status or service level, such as the network card traffic at the entrance of a certain server, the memory capacity of a certain middleware, the access volume of a certain middleware service, etc. For service metrics, it is necessary to monitor them to give a reminder when an abnormal situation occurs.

[0003] When monitoring service metrics, an expected value will be defined, and the actual value of the service metric will be compared with the expected value. When the difference between the actual value and the expected value is greater than the threshold, it means that an abnormal situation occurs, triggering an alarm to notify relevant personnel to handle it. In the related art, when defining the expected value, the maximum and minimum values of the defined expected value are fixed, and when the actual value exceeds the maximum value or is lower than the minimum value, it indicates that an abnormal situation occurs. In some scenarios, although the actual value does not exceed the expected value, but the actual value is lower than the normal standard, the abnormality of the service metric cannot be detected in time.

[0004] Therefore, how to avoid the situation that the abnormality of the service metric cannot be detected in time when the actual value of the service metric does not exceed the expected value but is lower than the normal standard is an urgent problem to be solved at present. Summary of the Invention

[0005] Embodiments of the present invention provide a method and device for monitoring service metrics, which are used for time series prediction analysis based on historical data, avoiding the situation that the abnormality of the service metric cannot be detected in time when the actual value of the service metric does not exceed the expected value but is lower than the normal standard, and improving the accuracy of service metric monitoring.

[0006] In a first aspect, an embodiment of the present invention provides a method for monitoring service metrics, including:

[0007] In response to a monitoring request, determine the expected value corresponding to the service metric at the prediction moment from the mapping relationship; the mapping relationship includes the expected values corresponding to the current moment and the moments after the current moment; the prediction moment is any moment among the current moment and the moments after the current moment; the mapping relationship is obtained by calculating according to the time series prediction method based on historical service metrics;

[0008] Determine the upper expected limit and the lower expected limit corresponding to the service metric at the prediction moment according to the expected value corresponding to the service metric at the prediction moment and a preset value;

[0009] Monitor the service metric at the prediction moment according to the upper expected limit and the lower expected limit corresponding to the service metric at the prediction moment.

[0010] In the above technical solution, it is necessary to monitor the service. Therefore, in response to a monitoring request, the expected value corresponding to the prediction time is obtained from the mapping relationship. The prediction time can be the current time and any time after the current time, and any prediction time has a corresponding expected value. The mapping relationship is calculated based on historical service metrics according to the time series prediction method. After obtaining the expected value at the prediction time, the upper and lower limits of the expectation are determined according to a preset value, and then the corresponding service metrics are monitored according to the upper and lower limits of the expectation. It realizes time series prediction analysis based on historical service metric monitoring data, avoids the inability to detect service metric anomalies in a timely manner when the actual value of the service metric does not exceed the expected value but is lower than the normal standard, and improves the accuracy of service metric monitoring.

[0011] Optionally, the mapping relationship is calculated based on historical service metrics according to the time series prediction method, and includes:

[0012] Determine the historical period corresponding to the current time;

[0013] Predict the service metrics within the historical period according to the time series prediction method to obtain the mapping relationship.

[0014] In the above technical solution, the historical period corresponding to the current time is determined according to the current time, and the service metrics within the historical period are determined. The service metrics within the historical period are input into the time series prediction method to obtain a mapping relationship including each time and the expected value corresponding to each time. It realizes time series prediction analysis based on historical service metric monitoring data to obtain the expected value, and improves the accuracy of service metric monitoring.

[0015] Optionally, determining the upper and lower limits of the expectation corresponding to the service metric at the prediction time according to the expected value and the preset value corresponding to the service metric at the prediction time includes:

[0016] Calculate the sum of the expected value of the service metric at the prediction time and the preset value to obtain the upper limit of the expectation of the service metric at the prediction time;

[0017] Calculate the difference between the expected value of the service metric at the prediction time and the preset value to obtain the lower limit of the expectation of the service metric at the prediction time.

[0018] In the above technical solution, after obtaining the expected value of the service metric at the prediction time, the upper limit of the expectation is determined according to the sum of the expected value and the preset value; the lower limit of the expectation is determined according to the difference between the expected value and the preset value. Among them, the preset value can be a value preset according to experience. It realizes determining the upper and lower limits of the expectation based on the expected value, and improves the accuracy of service metric monitoring

[0019] Optionally, monitoring the service metric at the prediction moment according to the expected upper limit and the expected lower limit corresponding to the service metric at the prediction moment includes:

[0020] If it is determined that the service metric at the prediction moment is greater than the expected upper limit of the service metric at the prediction moment, or the service metric at the prediction moment is less than the expected lower limit of the service metric at the prediction moment, an alarm is triggered.

[0021] In the above technical solution, when the service metric is greater than the corresponding expected upper limit or less than the expected lower limit, an alarm is triggered, avoiding losses caused by the failure to detect abnormal situations in time.

[0022] In a second aspect, an embodiment of the present invention provides a monitoring device for service metrics, including:

[0023] An acquisition module, configured to determine, in response to a monitoring request, an expected value corresponding to the service metric at the prediction moment from a mapping relationship; the mapping relationship includes expected values corresponding to the current moment and moments after the current moment; the prediction moment is any moment among the current moment and moments after the current moment; the mapping relationship is obtained by calculation based on historical service metrics according to the time series prediction method;

[0024] A processing module, configured to determine an expected upper limit and an expected lower limit corresponding to the service metric at the prediction moment according to the expected value corresponding to the service metric at the prediction moment and a preset value;

[0025] Monitor the service metric at the prediction moment according to the expected upper limit and the expected lower limit corresponding to the service metric at the prediction moment.

[0026] Optionally, the processing module is specifically configured to:

[0027] Determine the historical period corresponding to the current moment;

[0028] Predict the service metrics within the historical period according to the time series prediction method to obtain the mapping relationship.

[0029] Optionally, the processing module is specifically configured to:

[0030] Calculate the sum of the expected value of the service metric at the prediction moment and the preset value to obtain the expected upper limit of the service metric at the prediction moment;

[0031] Calculate the difference between the expected value of the service metric at the prediction moment and the preset value to obtain the expected lower limit of the service metric at the prediction moment.

[0032] Optionally, the processing module is specifically configured to:

[0033] If it is determined that the service metric at the prediction moment is greater than the expected upper limit of the service metric at the prediction moment, or the service metric at the prediction moment is less than the expected lower limit of the service metric at the prediction moment, an alarm is triggered.

[0034] Thirdly, an embodiment of the present invention further provides a computer device, including:

[0035] A memory for storing program instructions;

[0036] A processor for calling the program instructions stored in the memory and executing the above-mentioned service metric monitoring method according to the obtained program.

[0037] Fourthly, an embodiment of the present invention further provides a computer-readable storage medium, and the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to make a computer execute the above-mentioned service metric monitoring method. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0039] Figure 1 A schematic diagram of service metric monitoring provided by an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of a system architecture provided by an embodiment of the present invention;

[0041] Figure 3 A flowchart of a service metric monitoring method provided by an embodiment of the present invention;

[0042] Figure 4 A schematic diagram of service metric monitoring provided by an embodiment of the present invention;

[0043] Figure 5 A flowchart of a service metric monitoring method provided by an embodiment of the present invention;

[0044] Figure 6 A schematic diagram of the structure of a service metric monitoring device provided by an embodiment of the present invention. Detailed Embodiments

[0045] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0046] Before introducing a method for monitoring a service metric provided by an embodiment of the present application, for the convenience of understanding, first, the terms and technical background related to the embodiments of the present application will be introduced below.

[0047] Time series: Data organized in chronological order.

[0048] Time series prediction: Based on known time series data, predicting the data value or value range corresponding to a future time.

[0049] Time series prediction method: A method for realizing time series prediction. Its basic principle is: on the one hand, it recognizes the continuity of the development of things, uses past time series data for statistical analysis, and infers the development trend of things; on the other hand, it fully considers the randomness caused by accidental factors. In order to eliminate the influence of random fluctuations, historical data is used for statistical analysis, and the data is appropriately processed for trend prediction.

[0050] Service: A service that can contribute value, including services directly serving end customers and also middleware services.

[0051] Service metric: An indicator reflecting the service state or service level, such as: the traffic of the network card at the entrance of a certain server, the memory capacity of a certain middleware, the access volume of a certain middleware service, etc. Usually, service metrics have an obvious time cycle attribute, showing obvious periodic characteristics on a daily or annual basis.

[0052] When monitoring service metrics, it is necessary to define an expected value. In the related art, when defining the expected value, the maximum and minimum values of the defined expected value are fixed. As Figure 1 shown Figure 1A schematic diagram of business metric monitoring provided by an embodiment of the present invention. In the figure, the x-axis represents time, the y-axis represents business metric values, the dashed lines respectively correspond to the maximum value of the expected value and the minimum value of the expected value, and the solid line is the business metric monitored within two time periods. Among the business metrics monitored in the second time period in the figure, the business metric value corresponding to t2 should be comparable to the business metric value corresponding to t1 in the first time period. However, in fact, the business metric value corresponding to t2 is much lower than the business metric value corresponding to t1, indicating that an abnormal situation has occurred. However, since the business metric value corresponding to t2 is not greater than the maximum value of the expected value or less than the minimum value of the expected value, this abnormal situation cannot be detected.

[0053] Therefore, the present invention proposes a method for monitoring business metrics. Based on historical business metrics, time series prediction analysis is performed. According to the expected value obtained from the time series prediction analysis and the preset reasonable floating range, the upper limit of the expectation and the lower limit of the expectation are obtained, and the business metrics are monitored accordingly. This solves the problem that when the maximum value and the minimum value of the fixed set expected value are set, if the actual value of the business metric does not exceed the expected value but the actual value is lower than the normal value, the abnormal situation of the business metric cannot be detected in time, and improves the accuracy of business metric monitoring.

[0054] Figure 2 An exemplary system architecture applicable to an embodiment of the present invention is shown. The system architecture includes a server 200, and the server 200 may include a processor 210, a communication interface 220, and a memory 230.

[0055] Among them, the communication interface 220 is used to send alarm information to the background.

[0056] The processor 210 is the control center of the server 200, connecting various parts of the entire server 200 through various interfaces and lines. By running or executing software programs / modules stored in the memory 230, and by calling data stored in the memory 230, various functions of the server 200 are executed and data is processed. Optionally, the processor 210 may include one or more processing units.

[0057] The memory 230 can be used to store software programs and modules. The processor 210 executes various functional applications and data processing by running the software programs and modules stored in the memory 230. The memory 230 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc.; the data storage area may store data created according to business processing, etc. In addition, the memory 230 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0058] It should be noted that the aboveFigure 2 The structure shown is only an example, and the embodiments of the present invention do not limit this.

[0059] Based on the above description, Figure 3 An exemplary flowchart of a method for monitoring a service metric provided by an embodiment of the present invention is shown. This process can be executed by a service metric monitoring device.

[0060] As Figure 3 shown, this process specifically includes:

[0061] Step 310, in response to a monitoring request, determine the expected value corresponding to the service metric at the prediction moment from the mapping relationship.

[0062] In the embodiments of the present invention, since it is necessary to monitor the service metric, a monitoring request for this service metric will be generated. In response to this monitoring request, the expected value corresponding to the service metric at the prediction moment is determined from the mapping relationship. Among them, the monitoring request can be generated periodically according to the monitoring requirements of the service metric, or manually triggered by the staff. Specifically, a monitoring request is generated every time period, or a monitoring request is generated every moment. The prediction moment is any moment among the current moment and the moments after the current moment. For example, if the current moment is 10:00 on November 15, 2023, the prediction moment is any moment after 10:00 on November 15, 2023, including 10:00 on November 15, 2023.

[0063] The mapping relationship is obtained by calculation according to the time series prediction method based on historical business indicators, including the expected values corresponding to the current moment and the moments after the current moment. Specifically, first determine the historical period corresponding to the current moment. For example, if the current moment is 10:00 on November 15, 2023, the corresponding historical period is from 00:00 to 10:00 before November 15, 2023. Among them, the number of days corresponding to the historical period is not limited. For example, it can be from 00:00 to 10:00 on January 1, 2022 to 00:00 to 10:00 on November 14, 2023, or from 00:00 to 10:00 on May 15, 2023 to 00:00 to 10:00 on November 14, 2023. Then, predict the business indicators within the historical period according to the time series prediction method to obtain the mapping relationship. Among them, the format of the business indicators within the historical period can be defined as the time series format, that is, (t1, v1), (t2, v2), (t3, v3)...(tn, vn). For example, if the business indicator is the access volume of a certain middleware service and the historical period is from 00:00 to 10:00 on May 15, 2023 to 00:00 to 10:00 on November 14, 2023, the business indicators within the historical period are (00:00 on May 15, 2023, 10), (0:01 on May 15, 2023, 15), (0:02 on May 15, 2023, 13)...(10:00 on November 14, 2023, 20). The format of the mapping relationship can also be defined as the time series format, that is, (tx1, vx1), (tx2, vx2), (tx3, vx3)...(txn, vxn). For example, (00:00 on November 15, 2023, 10), (0:01 on November 15, 2023, 15), (0:02 on November 15, 2023, 13)...(10:00 on November 15, 2023, 20).

[0064] Exemplarily, the time series prediction method can be divided into single-variable prediction, multi-variable prediction, hybrid model prediction, frequency domain method prediction, etc. Among them, single-variable time series prediction only depends on a single time series data source for prediction, mainly used for how to predict future data based on past data. Common single-variable prediction methods include autoregressive moving average model, exponential smoothing model, random forest, and deep learning model, etc. Multi-variable time series prediction uses two or more related time series for prediction, which can better utilize the mutual relationship between different variables. Common multi-variable prediction methods include vector autoregressive model, cointegration model, and multi-variable deep learning model, etc. In this application, there is only one time series data, so the single-variable time series prediction method is used. Different single-variable time series prediction methods can be selected according to different requirements, which are not specifically limited here.

[0065] In some embodiments, the business metrics in the historical period in the above time series format are input into the time series prediction method for analysis. It is known that the time period of the business metrics is one day. The expected value at the current moment is calculated based on the historical business metrics of each day. For example, if the current moment is 10:00 on November 15, 2023, the historical business metrics at 10:00 on November 14, 2023, the historical business metrics at 10:00 on November 13, 2023, and so on, until the historical business metrics at 10:00 on May 15, 2023 are summed up and the average value is calculated, which is the expected value at 10:00 on November 15, 2023, such as 18. In this embodiment, the mapping relationship is calculated in real time according to the current moment. That is, if the current moment is 10:00 on November 15, 2023, the corresponding historical period is from 00:00 to 10:00 before November 15, 2023. Based on the business metrics in this historical period, the mapping relationship at the current moment is predicted, and the expected value of the business metrics at the current moment is determined to be 10; if the current moment is 10:01 on November 15, 2023, the corresponding historical period is from 00:00 to 10:01 before November 15, 2023. Based on the business metrics in this historical period, the mapping relationship at the current moment is predicted, and the expected value of the business metrics at the current moment is determined to be 15.

[0066] In a possible embodiment, the mapping relationship of the current time period is determined once for each time period. The mapping relationship includes each moment in the current time period and the expected value corresponding to each moment. Exemplarily, the time period of the business metrics is one week, and the current time period is from November 13, 2023 to November 19, 2023. Based on the historical business metrics before the current time period, the mapping relationship of this time period is calculated according to the time series prediction method. If it is necessary to obtain the expected value at 11:00 on November 15, 2023, the above moment is input into the mapping relationship of this time period to obtain the expected value of this moment.

[0067] Step 320, determine the expected upper limit and the expected lower limit of the business metrics at the prediction moment according to the expected value and the preset value corresponding to the business metrics at the prediction moment.

[0068] In the embodiments of the present invention, the upper and lower limits of expectation corresponding to the service metric at the prediction time are determined based on the expected value and the preset value corresponding to the service metric at the prediction time. Among them, the preset value can be a value preset according to experience, representing the reasonable floating range of the service metric, and no specific limitation is made here. Specifically, the sum of the expected value and the preset value of the service metric at the prediction time is calculated to obtain the upper limit of expectation of the service metric at the prediction time. For example, if the current time is 10:00 on November 15, 2023, the expected value of the corresponding service metric is 10, and the preset value is 4, then the sum of the expected value 10 and the preset value 4 of the service metric at the current time is calculated to be 14, that is, the upper limit of expectation of the service metric at the current time is 14. The difference between the expected value and the preset value of the service metric at the prediction time is calculated to obtain the lower limit of expectation of the service metric at the prediction time. Based on the above example, the difference between the expected value 10 and the preset value 4 of the service metric at the current time is calculated to be 6, that is, the lower limit of expectation of the service metric at the current time is 6.

[0069] Step 330, monitor the service metric at the prediction time according to the upper and lower limits of expectation corresponding to the service metric at the prediction time.

[0070] In the embodiments of the present invention, the service metric at the prediction time is monitored according to the upper and lower limits of expectation corresponding to the service metric at the prediction time determined in the above steps. Specifically, if it is determined that the service metric at the prediction time is greater than the upper limit of expectation of the service metric at the prediction time, or the service metric at the prediction time is less than the lower limit of expectation of the service metric at the prediction time, an alarm is triggered. Exemplarily, the current time is 10:00 on November 15, 2023, the actual value of the service metric at the current time is 17, which is greater than the upper limit of expectation 14 at the current time; or the actual value of the service metric at the current time is 3, which is less than the lower limit of expectation 6 at the current time, and an alarm is triggered to prompt relevant personnel to handle it. If the actual value of the service metric at the current time is 10, which is not greater than the upper limit of expectation 14 at the current time and is not less than the lower limit of expectation 6 at the current time, the service metric at the next time of the current time is continuously monitored. For example Figure 4 , Figure 4 is a schematic diagram of service metric monitoring provided by the embodiments of the present invention. In the figure, the x-axis represents time, the y-axis represents the service metric value, the dotted lines respectively correspond to the upper and lower limits of expectation, and the solid line is the monitored service metric. It can be seen that the upper and lower limits of expectation in the figure are different from those in Figure 1 , Figure 4 The upper and lower limits of expectation in are broken lines that fit the service metric better. Therefore, Figure 1 Abnormal situations that cannot be found in can be found in Figure 4 and an alarm is triggered.

[0071] To better explain the above technical solution, Figure 5 An exemplary flowchart of a positioning method provided by an embodiment of the present invention is shown, as Figure 5 shown. The specific process includes:

[0072] Step 501: Determine the expected value corresponding to the business metric at the current moment from the mapping relationship.

[0073] Determine the historical period corresponding to the current moment (e.g., from 00:00 to 10:00 before November 15, 2023), input the historical business metrics in the historical period into the time series prediction method to obtain the mapping relationship (e.g., (00:00 on November 15, 2023, 10), (0:01 on November 15, 2023, 15), (0:02 on November 15, 2023, 13)... (10:00 on November 15, 2023, 10)). Determine the expected value corresponding to the current moment from the mapping relationship according to the current moment (e.g., the determined expected value is 10).

[0074] Step 502: Determine the upper and lower expected limits according to the expected value and the preset value of the business metric at the current moment.

[0075] The preset value is 4. Calculate the sum of the expected value 10 of the business metric at the current moment and the preset value 4, which is 14, that is, the upper expected limit of the business metric at the current moment is 14.

[0076] Calculate the difference between the expected value 10 of the business metric at the current moment and the preset value 4, which is 6, that is, the lower expected limit of the business metric at the current moment is 6.

[0077] Step 503: Compare the business metric at the current moment with the upper and lower expected limits at the current moment, and determine whether it is greater than the upper expected limit or less than the lower expected limit.

[0078] Step 504: If the business metric at the current moment is greater than the upper expected limit or less than the lower expected limit, trigger an alarm.

[0079] Step 505: If the business metric at the current moment is not greater than the upper expected limit or less than the lower expected limit, repeat the above steps to monitor the business metric at the next moment.

[0080] In the embodiments of the present invention, a mapping relationship is calculated based on historical business metrics and the time series prediction method, and then the expected value at each moment is determined. Further, based on the expected value and the preset value at each moment, the upper and lower limits of the expectation are determined, realizing the dynamic setting of the upper and lower limits of the monitoring expectation, solving the problem that when the maximum and minimum values of the fixed set expected values are set, if the actual value of the business metric does not exceed the expected value but is lower than the conventional standard, the abnormality of the business metric cannot be detected in time, and improving the accuracy of business metric monitoring.

[0081] Based on the same technical concept, Figure 6 An exemplary structural diagram of a monitoring device for business metrics provided by an embodiment of the present invention is shown. This device can execute the process of the monitoring method for business metrics.

[0082] As Figure 6 shown, the device specifically includes:

[0083] An acquisition module 610, configured to determine, in response to a monitoring request, the expected value corresponding to the business metric at the prediction moment from the mapping relationship; the mapping relationship includes the expected values corresponding to the current moment and the moments after the current moment; the prediction moment is any moment among the current moment and the moments after the current moment; the mapping relationship is obtained by calculation based on historical business metrics according to the time series prediction method;

[0084] A processing module 620, configured to determine the upper and lower limits of the expectation corresponding to the business metric at the prediction moment according to the expected value corresponding to the business metric at the prediction moment and the preset value;

[0085] Monitor the business metric at the prediction moment according to the upper and lower limits of the expectation corresponding to the business metric at the prediction moment.

[0086] Optionally, the processing module 620 is specifically configured to:

[0087] Determine the historical period corresponding to the current moment;

[0088] Predict the business metrics within the historical period according to the time series prediction method to obtain the mapping relationship.

[0089] Optionally, the processing module 620 is specifically configured to:

[0090] Calculate the summation result of the expected value of the business metric at the prediction moment and the preset value to obtain the upper limit of the expectation of the business metric at the prediction moment;

[0091] Calculate the difference between the expected value of the business metric at the prediction moment and the preset value to obtain the lower limit of the expectation of the business metric at the prediction moment.

[0092] Optionally, the processing module 620 is specifically configured to:

[0093] If it is determined that the service metric at the prediction moment is greater than the expected upper limit of the service metric at the prediction moment, or the service metric at the prediction moment is less than the expected lower limit of the service metric at the prediction moment, an alarm is triggered.

[0094] Based on the same technical concept, an embodiment of the present invention further provides a computer device, including:

[0095] A memory for storing program instructions;

[0096] A processor for calling the program instructions stored in the memory and executing the monitoring method of the above service metrics according to the obtained program.

[0097] Based on the same technical concept, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute the monitoring method of the above service metrics.

[0098] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0100] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device realizes the functions in Figure 1 one process or multiple processes and / or blocksFigure 1 The functions specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one or more processes and / or boxes Figure 1 One process or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes.

[0102] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, then this application is also intended to include these changes and modifications.

Claims

1. A method for monitoring service indicators, characterized in that, including: In response to a monitoring request, determining an expected value corresponding to a service metric at a prediction time from a mapping relationship; The mapping relationship includes expected values corresponding to the current time and times after the current time; the prediction time is any time among the current time and times after the current time; the mapping relationship is obtained by calculation based on historical service metrics according to a time series prediction method; Determining an upper expected limit and a lower expected limit corresponding to the service metric at the prediction time according to the expected value corresponding to the service metric at the prediction time and a preset value; Monitoring the service metric at the prediction time according to the upper expected limit and the lower expected limit corresponding to the service metric at the prediction time.

2. The method according to claim 1, characterized in that The mapping relationship is obtained by calculation based on historical service metrics according to a time series prediction method, and includes: Determining a historical period corresponding to the current time; Predicting the service metrics within the historical period according to the time series prediction method to obtain the mapping relationship.

3. The method according to claim 1, characterized in that, Determining an upper expected limit and a lower expected limit corresponding to the service metric at the prediction time according to the expected value corresponding to the service metric at the prediction time and a preset value, including: Calculating the sum result of the expected value of the service metric at the prediction time and the preset value to obtain the upper expected limit of the service metric at the prediction time; Calculating the difference between the expected value of the service metric at the prediction time and the preset value to obtain the lower expected limit of the service metric at the prediction time.

4. The method according to claim 1, wherein Monitoring the service metric at the prediction time according to the upper expected limit and the lower expected limit corresponding to the service metric at the prediction time, including: If it is determined that the service metric at the prediction time is greater than the upper expected limit of the service metric at the prediction time, or the service metric at the prediction time is less than the lower expected limit of the service metric at the prediction time, triggering an alarm.

5. A monitoring device for business metrics, characterized in that, including: An acquisition module, configured to, in response to a monitoring request, determine an expected value corresponding to a service metric at a prediction time from a mapping relationship; The mapping relationship includes expected values corresponding to the current time and times after the current time; the prediction time is any time among the current time and times after the current time; the mapping relationship is obtained by calculation based on historical service metrics according to a time series prediction method; A processing module, configured to determine an upper expected limit and a lower expected limit corresponding to the service metric at the prediction time according to the expected value corresponding to the service metric at the prediction time and a preset value; Monitoring the service metric at the prediction time according to the upper expected limit and the lower expected limit corresponding to the service metric at the prediction time.

6. The device according to claim 5, characterized in that, The processing module is specifically configured to: Determine a historical period corresponding to the current time; Predict the service metrics within the historical period according to the time series prediction method to obtain the mapping relationship.

7. The device according to claim 5, characterized in that The processing module is specifically configured to: Calculating the sum result of the expected value of the service metric at the prediction time and the preset value to obtain the upper expected limit of the service metric at the prediction time; Calculating the difference between the expected value of the service metric at the prediction time and the preset value to obtain the lower expected limit of the service metric at the prediction time.

8. The device according to claim 5, characterized in that The processing module is specifically configured to: If it is determined that the service metric at the prediction moment is greater than the expected upper limit of the service metric at the prediction moment, or the service metric at the prediction moment is less than the expected lower limit of the service metric at the prediction moment, an alarm is triggered.

9. A computer device, characterized in that, Including: A memory for storing program instructions; A processor for calling the program instructions stored in the memory and executing the method according to any one of claims 1 to 4 according to the obtained program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute the method according to any one of claims 1 to 4.