Service data volume monitoring method, device, equipment, medium and program product

Abstract

The invention provides a service data volume monitoring method which can be applied to the technical field of artificial intelligence. The service data volume monitoring method comprises the steps that service data volumes in continuous first m identical set time periods of a current set time period are acquired and serve as m first service data volumes, and m is an integer larger than or equal to 2; according to the m first service data volumes, predicting the service data volume of the current set time period by using a prediction model, and taking the predicted service data volume as a second service data volume; service data volumes in n historical time periods are acquired as n historical service data volumes, and n is an integer greater than or equal to 2; determining a service data volume threshold interval according to the second service data volume and the n historical service data volumes; and comparing the obtained actual service data volume of the current set time period with the service data volume threshold interval to obtain a monitoring result. The invention further provides a service data volume monitoring device and equipment, a storage medium and a program product.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a business data volume monitoring method and device, equipment, medium and program product. BACKGROUND

[0002] Data, as a strategic resource and key production factor, has important value and role for the banking industry. Through further analysis and feature mining of data, it is helpful to understand the personalized needs of users, so as to facilitate the bank to provide personalized services for users, and also facilitate the bank to improve risk management and make decision mechanism. With the development of financial technology, more and more banks establish observable platforms for related business data in a visual way for real-time monitoring, such as remote bank agent call-in and call-out quantity, text agent user access quantity, etc., so that the bank can more intuitively observe and understand the data and find potential problems.

[0003] However, the visualization of most business data only stays at the level of displaying data, without analyzing and managing abnormal situations. Taking the remote bank agent call-in quantity as an example, if only focusing on real-time data changes cannot effectively observe abnormalities, and cannot prevent risks such as large-scale telephone fraud. Therefore, how to monitor the business data volume and obtain the monitoring result has become a technical problem that needs to be solved by the technical personnel in the field. SUMMARY

[0004] In view of the above problems, the present application provides a business data volume monitoring method, device, equipment, medium and program product which are intelligent and have high accuracy.

[0005] According to a first aspect of the present application, a business data volume monitoring method is provided, comprising: acquiring business data volumes in m consecutive same set time periods in a current set time period as m first business data volumes, wherein m is an integer greater than or equal to 2; predicting a business data volume in the current set time period as a second business data volume by using a prediction model according to the m first business data volumes; acquiring business data volumes in n historical time periods as n historical business data volumes, wherein n is an integer greater than or equal to 2; determining a business data volume threshold interval according to the second business data volume and the n historical business data volumes; comparing an actual business data volume in the current set time period with the business data volume threshold interval to obtain a monitoring result.

[0006] According to an embodiment of this application, the step of predicting the business data volume for a current set time period based on the m first business data volumes using a prediction model, and using it as the second business data volume, includes: the prediction model assigning a corresponding weight to each of the m first business data volumes; and multiplying each of the m first business data volumes by its corresponding weight and then summing the results to obtain the second business data volume.

[0007] According to an embodiment of this application, the step of determining a service data volume threshold range based on the second service data volume and the n historical service data volumes includes: calculating a standard error based on the n historical service data volumes; calculating an upper limit threshold and a lower limit threshold for the service data volume based on the second service data volume and the standard error; and determining a service data volume threshold range based on the upper limit threshold and the lower limit threshold.

[0008] According to an embodiment of this application, the step of calculating the standard error based on the n historical business data volumes includes: calculating the average value based on the n historical business data volumes; calculating the standard deviation based on the n historical business data volumes and the average value; and calculating the standard error based on the standard deviation.

[0009] According to an embodiment of this application, when the currently set time period is a weekday period, the first m set time periods are weekday periods; when the currently set time period is a non-weekday period, the first m set time periods are non-weekday periods.

[0010] According to an embodiment of this application, the step of comparing the actual business data volume of the current set time period with the business data volume threshold range to obtain a monitoring result includes: when the actual business data volume of the current set time period is within the business data volume threshold range, the obtained monitoring result is that the data volume is normal and no measures need to be taken; when the actual business data volume of the current set time period is not within the business data volume threshold range, the obtained monitoring result is that the data volume is abnormal and alarm measures are taken.

[0011] A second aspect of this application provides a business data volume monitoring device, comprising: a first acquisition module, configured to acquire business data volumes within the previous m consecutive identical set time periods of a current set time period, as m first business data volumes, where m is an integer greater than or equal to 2; a first determination module, configured to predict the business data volume of the current set time period based on the m first business data volumes using a prediction model, as a second business data volume; a second acquisition module, configured to acquire business data volumes within n historical time periods, as n historical business data volumes, where n is an integer greater than or equal to 2; a second determination module, configured to determine a business data volume threshold range based on the second business data volume and the n historical business data volumes; and a third determination module, configured to compare the acquired actual business data volume of the current set time period with the business data volume threshold range to obtain a monitoring result.

[0012] A third aspect of this application provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0013] A fourth aspect of this application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0014] The fifth aspect of this application also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0015] According to some embodiments of this application, the business data volume within the previous m consecutive identical set time periods of the current set time period is obtained as m first business data volumes, where m is an integer greater than or equal to 2; based on the m first business data volumes, a prediction model is used to predict the business data volume of the current set time period, which is then used as the second business data volume; the business data volume within n historical time periods is obtained as n historical business data volumes, where n is an integer greater than or equal to 2; a business data volume threshold range is determined based on the second business data volume and the n historical business data volumes; the actual business data volume of the current set time period is compared with the business data volume threshold range to obtain the monitoring result. The business data volume monitoring method of this application can intelligently analyze and manage abnormal business data volume situations, rather than merely remaining at the level of data display, thereby reducing the burden on relevant personnel and obtaining more accurate monitoring results. Attached Figure Description

[0016] The above-mentioned contents, other objects, features and advantages of this application will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0017] Figure 1 The illustration shows an application scenario diagram of the business data volume monitoring method, apparatus, device, medium, and program product according to embodiments of this application;

[0018] Figure 2 A flowchart illustrating a service data volume monitoring method according to an embodiment of this application is shown schematically.

[0019] Figure 3 This illustration schematically shows a flowchart of the steps for determining a service data volume threshold range based on a second service data volume and n historical service data volumes according to an embodiment of this application.

[0020] Figure 4 This schematic diagram illustrates the structural block diagram of a service data volume monitoring device according to an embodiment of this application;

[0021] Figure 5 A block diagram of an electronic device suitable for implementing a business data volume monitoring method according to an embodiment of this application is shown schematically. Detailed Implementation

[0022] The embodiments of this application will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of this application. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of this application for ease of explanation. However, it will be apparent that one or more embodiments may be implemented without these specific details. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0023] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0024] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0025] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0026] Data, as a strategic resource and key production factor, holds significant value and plays a crucial role in the banking industry. Further analysis and feature mining of data helps understand users' personalized needs, enabling banks to provide customized services and improve risk management and decision-making mechanisms in a timely manner. With the development of financial technology, more and more banks are establishing observable platforms for relevant business data in a visualized manner for real-time monitoring, such as the number of inbound and outbound calls to remote banking agents and the number of users accessing text messaging services. This allows banks to observe and understand the data more intuitively and identify potential problems.

[0027] However, most business data visualizations only focus on displaying the data, without analyzing and managing anomalies. For example, regarding the number of inbound calls to remote banking agents, focusing solely on real-time data changes fails to effectively monitor anomalies and prevent risks such as widespread telephone fraud. Therefore, how to monitor business data volume and obtain monitoring results has become a pressing technical problem that needs to be solved by those skilled in the art.

[0028] Embodiments of this application provide a business data volume monitoring method, apparatus, electronic device, computer-readable storage medium, and computer program product. The business data volume monitoring method includes: acquiring the business data volume within the previous m consecutive identical defined time periods of a current defined time period, as m first business data volumes, where m is an integer greater than or equal to 2; predicting the business data volume of the current defined time period using a prediction model based on the m first business data volumes, as second business data volumes; acquiring the business data volume within n historical time periods, as n historical business data volumes, where n is an integer greater than or equal to 2; determining a business data volume threshold range based on the second business data volume and the n historical business data volumes; and comparing the acquired actual business data volume of the current defined time period with the business data volume threshold range to obtain a monitoring result.

[0029] It should be noted that the business data volume monitoring method, device, electronic device, computer-readable storage medium and computer program product of this application can be used in the field of artificial intelligence technology, or in any field other than artificial intelligence technology, such as the financial field. The field of this application is not limited here.

[0030] Figure 1The illustration shows an application scenario diagram of the business data volume monitoring method, apparatus, device, medium, and program product according to embodiments of this application.

[0031] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0032] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0033] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0034] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0035] It should be noted that the business data volume monitoring method provided in this application embodiment can generally be executed by server 105. Correspondingly, the business data volume monitoring device provided in this application embodiment can generally be located in server 105. The business data volume monitoring method provided in this application embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the business data volume monitoring device provided in this application embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0036] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0037] The following will be based on Figure 1 The described scene, through Figures 2-3 The method for monitoring business data volume according to the embodiments of this application will be described in detail.

[0038] Figure 2 A flowchart illustrating a business data volume monitoring method according to an embodiment of this application is shown schematically.

[0039] like Figure 2 As shown, the business data volume monitoring method in this embodiment includes operations S210 to S260.

[0040] In operation S210, the amount of business data within the first m consecutive identical defined time periods of the currently defined time period is obtained, and these are taken as the m first business data amounts, where m is an integer greater than or equal to 2. It is understood that the currently defined time period can be any time period within the current 24 hours. For example, if the current time is 0:01, the current 24 hours would be from 0:01 of the previous day to 0:01 of the current time; if the current time is 9:00, the current 24 hours would be from 9:00 of the previous day to 9:00 of the current time; if the current time is 0:00, the current 24 hours would be from 0:00 of the previous day to 0:00 of the current time. The above assumptions are merely illustrative examples to facilitate understanding that the currently defined time period can be any time period within the current 24 hours and should not be construed as limiting this application.

[0041] In some examples, the current time is 0:01, the current time period is 0:01~0:01, and the previous m consecutive time periods are 0:01~0:01 from the previous day to the previous m days. This example is for illustration only and should not be construed as a limitation of this application.

[0042] In operation S220, based on m first business data volumes, a prediction model is used to predict the business data volume for the current set time period, which is then used as the second business data volume.

[0043] As one possible approach, the step of using a prediction model to predict the business data volume for the current set time period based on m first business data volumes, and using this as the second business data volume, includes the following operations.

[0044] The prediction model assigns a corresponding weight to each of the m first business data quantities.

[0045] Understandably, the prediction model is pre-trained using sample data, and it has the ability to determine the corresponding weight for each of the m first business data quantities.

[0046] In some examples, the weights corresponding to the m first business data quantities can be a1~a2. m For example, m can be 7. The weight a1 corresponding to the first business data volume in the previous identical time period of the current time period can be 7 / 28, the weight a2 corresponding to the first business data volume in the previous two identical time periods of the current time period can be 6 / 28, the weight a3 corresponding to the first business data volume in the previous three identical time periods of the current time period can be 5 / 28, the weight a4 corresponding to the first business data volume in the previous four identical time periods of the current time period can be 4 / 28, the weight a5 corresponding to the first business data volume in the previous five identical time periods of the current time period can be 3 / 28, the weight a6 corresponding to the first business data volume in the previous six identical time periods of the current time period can be 2 / 28, and the weight a7 corresponding to the first business data volume in the previous seven identical time periods of the current time period can be 1 / 28. The above are merely illustrative examples and should not be construed as limiting this application.

[0047] The first business data volume is obtained by multiplying each of the m data volumes by its corresponding weight and then summing the results.

[0048] Here, we can continue with the example above. The first business data volume within the previous identical time period of the current time period can be represented by X. T-1 This indicates that the volume of the first business data within the two identical time periods preceding the current time period can be represented by X. T-2 This indicates that the volume of the first business data within the three identical time periods preceding the current time period can be represented by X. T-3 This indicates that the volume of the first business data within the four identical time periods preceding the current time period can be represented by X. T-4 This indicates that the volume of the first business data within the five identical time periods preceding the current time period can be represented by X. T-5 This indicates that the volume of the first business data within the first 6 identical time periods of the current time period can be represented by X. T-6 This indicates that the volume of the first business data within the seven identical time periods preceding the current time period can be represented by X. T-7 This means that the second business data volume can be represented by X. T The second business data volume can be obtained using the following formula.

[0049]

[0050] Therefore, the above operations make it easy to predict the business data volume for the current set time period based on m first business data volumes using a prediction model, and use this prediction as the second business data volume.

[0051] In operation S230, the business data volume within n historical time periods is obtained as n historical business data volumes, where n is an integer greater than or equal to 2.

[0052] In operation S240, the threshold range of business data volume is determined based on the second business data volume and n historical business data volumes.

[0053] As some possible ways to achieve this, such as Figure 3 As shown, operation S240 is the step of determining the threshold range of business data volume based on the second business data volume and n historical business data volumes, including operations S241 to S243.

[0054] In operation S241, the standard error is calculated based on n historical business data volumes.

[0055] In some specific examples, the steps for calculating the standard error based on n historical business data volumes include the following steps.

[0056] Calculate the average value based on n historical business data volumes. Here, the n historical business data volumes can be represented by X1~X... n This means that the amount of historical business data for the i-th time can be represented by X. i Let i be an integer greater than or equal to 1 and less than or equal to n. The average can be expressed as... The average value can be obtained using the following formula.

[0057]

[0058] Calculate the standard deviation based on the n historical business data points and their average. Here, the standard deviation can be expressed as... The standard deviation can be calculated using the following formula.

[0059]

[0060] The standard error is calculated based on the standard deviation. Here, the standard error can be represented by s, and it can be obtained by the following formula.

[0061]

[0062] The above operations facilitate the calculation of standard error based on n historical business data sets.

[0063] In operation S242, based on the second business data volume and standard error, the upper and lower thresholds of the business data volume are calculated. Here, the upper threshold of the business data volume can be represented by C. max This indicates that the lower limit threshold for business data volume can be represented by C. min The upper and lower limits of business data volume can be obtained using the following formulas.

[0064]

[0065] in, This is a constant value that can be determined by looking up a table.

[0066] In operation S243, the business data volume threshold range is determined based on the upper and lower thresholds of the business data volume. It can be understood that the business data volume threshold range can be set to [C]. min C max ].

[0067] By operating S241 to S243, it is easy to implement the steps of determining the threshold range of business data volume based on the second business data volume and n historical business data volumes.

[0068] When operating S250, the actual business data volume of the current set time period is compared with the business data volume threshold range to obtain the monitoring results.

[0069] As one possible approach, the step of comparing the actual business data volume of the current set time period with the business data volume threshold range to obtain the monitoring results includes the following steps.

[0070] When the actual business data volume within the business data volume threshold range for the current set time period, the monitoring result is that the data volume is normal and no action needs to be taken.

[0071] If the actual business data volume for the current set time period is not within the business data volume threshold range, the monitoring result is an abnormal data volume, and alarm measures are taken.

[0072] By following the steps above, no action is needed when the data volume is normal, but when the data volume is abnormal, relevant personnel can be notified in a timely manner for handling.

[0073] According to the business data volume monitoring method of this application, the business data volume within the previous m consecutive identical set time periods of the current set time period is obtained as m first business data volumes, where m is an integer greater than or equal to 2; based on the m first business data volumes, a prediction model is used to predict the business data volume of the current set time period, which is obtained as the second business data volume; the business data volume within n historical time periods is obtained as n historical business data volumes, where n is an integer greater than or equal to 2; a business data volume threshold range is determined based on the second business data volume and the n historical business data volumes; the actual business data volume of the current set time period is obtained and compared with the business data volume threshold range to obtain the monitoring result. The business data volume monitoring method of this application can intelligently analyze and manage abnormal business data volume situations, rather than merely focusing on data display, thereby reducing the burden on relevant personnel and obtaining more accurate monitoring results.

[0074] According to some embodiments of this application, when the currently set time period is a weekday period, the first m set time periods are weekday periods; when the currently set time period is a non-weekday period, the first m set time periods are non-weekday periods. It is understood that for weekday data... , The value is the same as the value at the same time on the previous working day, and so on. When calculating the value at the same time for the previous seven working days (i.e., when extrapolating the timeframe), non-working day data is ignored. Similarly, for non-working day data... , This value represents the data at the same time on the previous non-working day. This application differentiates between working day and non-working day data, which can eliminate the weekend effect, reduce errors, and improve the accuracy of identifying non-outlier intervals.

[0075] Based on the above-mentioned business data volume monitoring method, this application also provides a business data volume monitoring device. The following will combine... Figure 4 The device is described in detail.

[0076] Figure 4 A schematic block diagram of a business data volume monitoring device according to an embodiment of this application is shown.

[0077] like Figure 4 As shown, the business data volume monitoring device 10 includes a first acquisition module 1, a first determination module 2, a second acquisition module 3, a second determination module 4, and a third determination module 5.

[0078] The first acquisition module 1 is used to acquire the amount of business data within the first m consecutive identical set time periods of the current set time period, as the m first business data amounts, where m is an integer greater than or equal to 2.

[0079] The first determining module 2 is used to perform the following: based on m first business data volumes, it uses a prediction model to predict the business data volume for the current set time period, which is then used as the second business data volume.

[0080] The second acquisition module 3 is used to acquire the amount of business data within n historical time periods, which are used as n historical business data, where n is an integer greater than or equal to 2.

[0081] The second determining module 4 is used to determine the threshold range of business data volume based on the second business data volume and n historical business data volumes.

[0082] The third determining module 5 is used to compare the actual business data volume of the current set time period with the business data volume threshold range to obtain the monitoring results.

[0083] According to the business data volume monitoring device 10 of this application embodiment, the business data volume within the previous m consecutive identical set time periods of the current set time period is obtained as m first business data volumes, where m is an integer greater than or equal to 2; based on the m first business data volumes, a prediction model is used to predict the business data volume of the current set time period, which is obtained as second business data volume; the business data volume within n historical time periods is obtained as n historical business data volumes, where n is an integer greater than or equal to 2; a business data volume threshold range is determined based on the second business data volume and the n historical business data volumes; the actual business data volume of the current set time period is obtained and compared with the business data volume threshold range to obtain the monitoring result. The business data volume monitoring method of this application can intelligently analyze and manage abnormal business data volume, rather than merely remaining at the level of data display, thereby reducing the burden on relevant personnel and obtaining more accurate monitoring results.

[0084] According to embodiments of this application, any plurality of modules among the first acquisition module 1, first determination module 2, second acquisition module 3, second determination module 4, and third determination module 5 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this application, at least one of the first acquisition module 1, first determination module 2, second acquisition module 3, second determination module 4, and third determination module 5 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in a suitable combination of any of these. Alternatively, at least one of the first acquisition module 1, the first determination module 2, the second acquisition module 3, the second determination module 4, and the third determination module 5 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0085] The following describes in detail a service data volume monitoring method according to embodiments of this application. It is worth understanding that the following description is merely illustrative and not intended to limit the scope of this application.

[0086] Currently, the visualization of most banking business data only reaches the level of data display, without effective automation or intelligent detection or prediction. Taking the number of inbound calls to remote banking agents as an example, focusing only on real-time data changes or simply comparing historical averages cannot effectively detect anomalies and prevent risks such as widespread telephone fraud and intrusion. Furthermore, the number of inbound calls to remote banking agents is a single-indicator data point, and the total number of calls per day generally shows an upward trend. How to effectively detect anomalies is a topic worthy of further research.

[0087] This application provides a method for monitoring business data volume. In the visualization and monitoring of bank-related business data, single-indicator business data usually only displays real-time data or makes simple comparisons with historical averages, making it difficult to effectively detect anomalies or predict future data, and difficult to discover potential business risks from data curves and respond in a timely manner.

[0088] The banking business data monitoring method proposed in this application has the following main features: First, to address the issue of missing data in real-time data collection, the data is preprocessed and supplemented through forward sampling. Second, based on the presence of cyclical characteristics in the business data, anomaly detection is performed on both weekday and non-weekday data. Finally, a moving average is applied to historical data to smooth the time series data. This smoothed value is used as a prediction reference to calculate the normal fluctuation range of the data, and whether the current actual value falls within this fluctuation range determines whether the data is abnormal.

[0089] Time series data exhibits varying correlations with current data over time. This application replaces the common mean-average calculation method with a moving average, emphasizing the importance of recent data and effectively eliminating irregular fluctuations and noise interference in time series data. This application differentiates between weekday and non-weekday data, eliminating the weekend effect. It calculates the fluctuation range based on the predicted value at each moment and uses adaptive dynamic thresholds for anomaly detection. This eliminates the need for developers or operations personnel to manually maintain static thresholds and is applicable to various business indicator detection, providing more accurate alerts.

[0090] The overall process of the business data volume monitoring method is as follows.

[0091] Obtain the banking business data to be tested.

[0092] The application retrieves the banking business data and historical data to be tested from the data backend. Seven historical data points are used to calculate the predicted value of the current business data; therefore, only one month's historical data is extracted. The table structure of the single-indicator business data is shown below.

[0093]

[0094] Where %Y-%m-%d %H:%M:%S is the formatted representation of the time field, and x is the business indicator data.

[0095] Analyze data characteristics and perform data resampling and completion processing.

[0096] Since the data is real-time, some data points may be missing. The time field is formatted to a standard time data format, and missing times are filled in through resampling. Depending on the actual granularity of the business data, the sampling frequency can be set to seconds or minutes. Typically, the business data value at the current time T is the cumulative business data volume for that day. The total business volume of the previous day is recorded at 00:00:00 every day. The data is cleared at 00:00:01 or 00:01:00. When the data is missing at time T, the data is filled in forward according to the following formula.

[0097]

[0098] Develop prediction calculation models for both weekday and non-weekday data.

[0099] Banking data exhibits different characteristics on weekdays and non-weekdays, and is calculated separately. The predicted value is calculated using the following formula.

[0100]

[0101] Historical forecasts are calculated using a moving average of 7 historical values. Historical values ​​closer to the current moment are assigned higher weights. For weekday data... , The value is the same as the value at the same time on the previous working day, and so on. When calculating the value at the same time for the previous seven working days (i.e., when extrapolating the timeframe), non-working day data is ignored. Similarly, for non-working day data... , This is the value at the same time on the previous non-working day.

[0102] Set dynamic thresholds for anomaly detection.

[0103] The average value of historical data is calculated using the following formula.

[0104]

[0105] Where n is the number of historical data points, here n=7. Calculate the standard deviation of the n historical data points using the following formula.

[0106]

[0107] The standard error is calculated using the following formula.

[0108]

[0109] The upper and lower limits of the fluctuation range are calculated based on the predicted values ​​according to the following formula. The historical business data of the bank is t-distributed, and the upper and lower limits of the thresholds are calculated according to the following formula.

[0110]

[0111] in, For two-sided confidence levels, it is usually set to 1. , For degrees of freedom, Let be the t-distribution value corresponding to this confidence level and degrees of freedom, and .

[0112] Determine if the business data is abnormal, and issue an alarm if abnormal.

[0113] The system determines whether the current business value X is abnormal based on upper and lower thresholds, and visualizes it for easy real-time observation. If X is within the fluctuation range, i.e. If the business data is normal, it is considered an anomaly. If it is an anomaly, the cause of the anomaly should be investigated in a timely manner and the risk eliminated.

[0114] This application proposes a business data volume monitoring method. The advantages of this method are as follows: It uses a moving average method instead of a mean-average algorithm to calculate historical predicted values, assigning higher weight to historical data from the current time, emphasizing the importance of recent data, and effectively eliminating irregular fluctuations and noise interference in time series. This application distinguishes between weekday and non-weekday data, eliminating the weekend effect. Due to the use of fewer historical samples, it employs a t-distribution probability and historical predicted values ​​to calculate the anomaly detection threshold, resulting in smaller errors and improving the accuracy of identifying non-anomaly intervals. Anomaly detection is achieved through adaptive dynamic thresholds, eliminating the need for developers or operations personnel to manually maintain static thresholds, and it is applicable to various indicator detection methods, providing more accurate alarms.

[0115] Figure 5 A block diagram of an electronic device suitable for implementing a business data volume monitoring method according to an embodiment of this application is shown schematically.

[0116] like Figure 5 As shown, an electronic device 900 according to an embodiment of this application includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage portion 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this application.

[0117] RAM 903 stores various programs and data required for the operation of electronic device 900. Processor 901, ROM 902, and RAM 903 are interconnected via bus 904. Processor 901 executes various operations of the method flow according to embodiments of this application by executing programs in ROM 902 and / or RAM 903. It should be noted that the programs may also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 may also execute various operations of the method flow according to embodiments of this application by executing programs stored in said one or more memories.

[0118] According to embodiments of this application, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to a bus 904. The electronic device 900 may also include one or more of the following components connected to the input / output (I / O) interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 910 as needed so that computer programs read from it can be installed into the storage section 908 as needed.

[0119] This application also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0120] According to embodiments of this application, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this application, the computer-readable storage medium may include ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903 described above.

[0121] Embodiments of this application also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of this application.

[0122] When the computer program is executed by the processor 901, it performs the functions defined in the system / apparatus of this application embodiment. According to the embodiments of this application, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0123] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 909, and / or installed from a removable medium 911. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0124] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, it performs the functions defined in the system of this application embodiment. According to the embodiments of this application, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0125] According to embodiments of this application, program code for executing the computer programs provided in the embodiments of this application can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0127] Those skilled in the art will understand that the features described in the various embodiments of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application.

Claims

1. A method for monitoring business data volume, characterized in that, include: Get the amount of business data within the first m consecutive identical time periods of the current set time period, and use them as the m first business data amounts, where m is an integer greater than or equal to 2; Based on the m first business data volumes, the business data volume for the current set time period is predicted using a prediction model and used as the second business data volume. Obtain the business data volume within n historical time periods, and use these as n historical business data volumes, where n is an integer greater than or equal to 2; Based on the second business data volume and the n historical business data volumes, determine the business data volume threshold range; The monitoring results are obtained by comparing the actual amount of business data acquired in the current set time period with the threshold range of the business data amount.

2. The business data volume monitoring method according to claim 1, characterized in that, The step of predicting the business data volume for the current set time period based on the m first business data volumes using a prediction model, and using this prediction as the second business data volume, includes: The prediction model assigns a corresponding weight to each of the m first business data quantities; The m first business data quantities are multiplied by their corresponding weights and then summed to obtain the second business data quantity.

3. The business data volume monitoring method according to claim 1, characterized in that, The step of determining the threshold range of business data volume based on the second business data volume and the n historical business data volumes includes: Calculate the standard error based on the n historical business data volumes; Based on the second business data volume and the standard error, calculate the upper limit threshold and the lower limit threshold of the business data volume; The threshold range for business data volume is determined based on the upper limit threshold and the lower limit threshold.

4. The business data volume monitoring method according to claim 3, characterized in that, The steps for calculating the standard error based on the n historical business data volumes include: Calculate the average value based on the n historical business data volumes; Calculate the standard deviation based on the n historical business data volumes and the average value; The standard error is calculated based on the standard deviation.

5. The business data volume monitoring method according to claim 1, characterized in that, When the currently set time period is a weekday period, the previous m set time periods are weekday time periods; When the currently set time period is a non-working day period, the first m set time periods are non-working day periods.

6. The business data volume monitoring method according to claim 1, characterized in that, The step of comparing the actual business data volume of the current set time period with the business data volume threshold range to obtain the monitoring result includes: When the actual business data volume within the specified time period is within the threshold range of the business data volume, the monitoring result is that the data volume is normal and no action is required. If the actual business data volume during the current set time period is not within the business data volume threshold range, the monitoring result is an abnormal data volume, and an alarm is triggered.

7. A business data volume monitoring device, characterized in that, include: The first acquisition module is used to acquire the amount of business data within the first m consecutive identical set time periods of the current set time period, as m first business data amounts, where m is an integer greater than or equal to 2; The first determining module is used to perform a prediction model to predict the business data volume for the current set time period based on the m first business data volumes, and use the prediction model as the second business data volume. The second acquisition module is used to acquire the amount of business data within n historical time periods, which are used as n historical business data, where n is an integer greater than or equal to 2; The second determining module is used to determine the threshold range of the business data volume based on the second business data volume and the n historical business data volumes. The third determining module is used to compare the actual business data volume of the current set time period with the business data volume threshold range to obtain the monitoring result.

8. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

Images