A data flow abnormal value monitoring method, system, device and storage medium

By performing normal distribution calculations and eliminating low-probability events from historical network communication data traffic data, and dynamically setting the early warning range, the problem of inaccurate early warning value settings in the communication equipment room operation and maintenance platform is solved, and efficient and accurate monitoring of abnormal data traffic values ​​is achieved.

CN115811486BActive Publication Date: 2024-11-15LIUZHOU DADI TELECOMM EQUIP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211573979.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-12-08
Publication Date
2024-11-15
Estimated Expiration
2042-12-08

AI Technical Summary

Technical Problem

The existing communication equipment room operation and maintenance platform cannot reasonably set the warning value of abnormal traffic based on the normal trend of network communication data traffic and business growth, resulting in inaccurate warning value settings.

Method used

By acquiring historical data of network communication data traffic, a first normal distribution calculation and low-probability event elimination are performed to determine a first range threshold. Then, a second normal distribution calculation is performed to determine a second range threshold. Finally, outlier monitoring of target data traffic is performed based on the second range threshold.

Benefits of technology

It enables adaptive setting of early warning range based on historical data, accurately monitors abnormal data traffic values, and improves the efficiency and accuracy of abnormal value monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115811486B_ABST
    Figure CN115811486B_ABST
Patent Text Reader

Abstract

The present invention discloses a data flow abnormal value monitoring method, system, device and storage medium, the method comprising: obtaining historical data of network communication data flow within a preset period as a first statistical data; performing a first normal distribution calculation on the first statistical data to determine a first range threshold; determining a second statistical data based on the first statistical data and the first range threshold; performing a second normal distribution calculation on the second statistical data to determine a second range threshold; and performing abnormal value monitoring of target data flow based on the second range threshold. The present invention performs an iterative calculation of the first normal distribution calculation and the second overall distribution calculation based on the historical data of network communication data flow to determine the second range threshold, which can realize accurate data flow abnormal value monitoring, and adaptively determines the early warning range based on historical data, which can efficiently perform data flow abnormal value monitoring, and can be widely used in the field of abnormal value monitoring technology.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of abnormal value monitoring technology, and in particular to a data flow abnormal value monitoring method, system, device and storage medium. Background Art

[0002] Network communication data flow monitoring is one of the main functions of the communication room operation and maintenance platform. The change of network communication data flow reflects the degree of change of network communication within a period of time, and can also characterize the abnormal flow changes caused by illegal intrusion. In addition to being able to count the real-time network communication data flow, the communication room operation and maintenance platform also needs to be able to automatically determine the flow abnormality and issue prompts or warnings. The size of the warning value is usually set to a fixed value. Although the operation is simple, it cannot be reasonably set according to the normal change trend of the flow and the increase in flow caused by the growth of business. Therefore, the setting range of the warning value must not only change according to the data flow change trend of the operation and maintenance platform, but also the size of the warning value is set by manual dynamic estimation, which cannot meet the actual needs. Therefore, how to reasonably set the warning value of abnormal flow is one of the problems that need to be solved in the operation and maintenance process of the communication room. Summary of the invention

[0003] In view of this, embodiments of the present invention provide a method, system, device and storage medium for monitoring data flow abnormal values, which can monitor data flow abnormal values ​​efficiently and accurately.

[0004] On the one hand, an embodiment of the present invention provides a method for monitoring abnormal values ​​of data traffic, comprising:

[0005] Acquire historical data of network communication data flow within a preset period as first statistical data;

[0006] Performing a first normal distribution calculation on the first statistical data to determine a first range threshold;

[0007] Determining second statistical data according to the first statistical data and based on the first range threshold;

[0008] Performing a second normal distribution calculation on the second statistical data to determine a second range threshold;

[0009] According to the second range threshold, abnormal value monitoring of target data traffic is performed.

[0010] Optionally, the obtaining of historical statistical data of network communication data flow within a preset period includes:

[0011] According to a preset statistical data cycle, historical data of network communication data flow per day in the statistical data cycle is obtained;

[0012] According to the historical data, the communication flow data of each day is taken as a statistical data value to obtain the first statistical data.

[0013] Optionally, it also includes:

[0014] Based on a preset period, historical data of network communication data traffic within a preset period is periodically obtained to update the first statistical data.

[0015] Optionally, performing a first normal distribution calculation on the first statistical data to determine a first range threshold includes:

[0016] Performing a first normal distribution calculation on the first statistical data to obtain a mean value and a standard deviation value of the first statistical data;

[0017] According to the mean and standard deviation of the first statistical data, [μ1-2σ1, μ1+2σ1] is determined as the first range threshold; wherein μ1 represents the mean of the first statistical data, and σ1 represents the standard deviation of the first statistical data.

[0018] Optionally, determining second statistical data according to the first statistical data and based on the first range threshold includes:

[0019] Based on the first range threshold, data of low-probability events are eliminated from the first statistical data to obtain second statistical data.

[0020] Optionally, performing a second normal distribution calculation on the second statistical data to determine a second range threshold includes:

[0021] Performing a second normal distribution calculation on the second statistical data to obtain a mean value and a standard deviation value of the second statistical data;

[0022] According to the mean and standard deviation of the second statistical data, [μ2-2σ2, μ2+2σ2] is determined as the second range threshold; wherein μ1 represents the mean of the second statistical data, and σ1 represents the standard deviation of the second statistical data.

[0023] Optionally, performing abnormal value monitoring of target data traffic according to the second range threshold includes:

[0024] Determine an upper limit and a lower limit of the data flow abnormal value according to the second range threshold;

[0025] Perform abnormal value monitoring of target data flow according to the upper limit and lower limit of the abnormal value of the data flow;

[0026] When the target data flow is greater than the upper limit or less than the lower limit, an abnormal value prompt is given.

[0027] On the other hand, an embodiment of the present invention provides a data flow abnormal value monitoring system, including:

[0028] The first module is used to obtain historical data of network communication data flow within a preset period as first statistical data;

[0029] A second module is used to perform a first normal distribution calculation on the first statistical data to determine a first range threshold;

[0030] A third module is used to determine second statistical data according to the first statistical data and based on the first range threshold;

[0031] A fourth module is used to perform a second normal distribution calculation on the second statistical data to determine a second range threshold;

[0032] The fifth module is used to monitor the abnormal value of the target data flow according to the second range threshold.

[0033] On the other hand, an embodiment of the present invention provides a data flow abnormal value monitoring device, including a processor and a memory;

[0034] The memory is used to store programs;

[0035] The processor executes the program to implement the method described above.

[0036] On the other hand, an embodiment of the present invention provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0037] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0038] The embodiment of the present invention first obtains historical data of network communication data traffic within a preset period as a first statistical data; performs a first normal distribution calculation on the first statistical data to determine a first range threshold; determines a second statistical data based on the first statistical data and the first range threshold; performs a second normal distribution calculation on the second statistical data to determine a second range threshold; and performs abnormal value monitoring of target data traffic based on the second range threshold. The present invention performs iterative calculations of the first normal distribution calculation and the second overall distribution calculation based on the historical data of network communication data traffic to determine the second range threshold, which can achieve accurate data traffic abnormal value monitoring, and adaptively determines the warning range based on historical data, which can efficiently monitor data traffic abnormal values. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flow chart of a method for monitoring abnormal values ​​of data flow provided by an embodiment of the present invention;

[0041] Figure 2 A principle block diagram of a method for monitoring abnormal values ​​of data flow provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of a data flow abnormal value monitoring system provided by an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of a data flow abnormal value monitoring device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0045] In order to make the content and technical solution of this application clearer, the relevant terms and their meanings are explained:

[0046] Normal distribution: It is an important concept in parameter estimation in probability theory, also known as Gaussian distribution. It means that the random variable X obeys a mathematical expectation of μ and a standard deviation of σ. 2 Gaussian distribution: X∈N(μ,σ 2). The data distribution characteristics of the normal distribution are that theoretically 99.73% of the X values ​​are between [μ-3σ, μ+3σ], 95.45% of the X values ​​are between [μ-2σ, μ+2σ], and 68.27% of the X values ​​are between [μ-σ, μ+σ]. This is called the "3σ" principle of the normal distribution.

[0047] Low-probability event: usually refers to an event with a probability of less than 5%, which is considered to be almost impossible to occur in a single experiment.

[0048] On the one hand, referring to Figure 1 , an embodiment of the present invention provides a data flow abnormal value monitoring method, comprising:

[0049] S100, obtaining historical data of network communication data flow within a preset period as first statistical data;

[0050] It should be noted that in some embodiments, according to a preset statistical data period, historical data of network communication data traffic for each day in the statistical data period is obtained; based on the historical data, the communication traffic data of each day is taken as a statistical data value to obtain the first statistical data.

[0051] In some embodiments, the method further includes: periodically obtaining historical data of network communication data flow within a preset period based on a preset cycle, and updating the first statistical data. In order to make the judgment result more accurate, the training data is continuously updated periodically to ensure the real-time nature of the reference data. In other embodiments, the historical data of network communication data flow within a preset period may be obtained irregularly to update the first statistical data.

[0052] Specifically, Figure 2 As shown, read a section of historical network communication traffic statistics: according to statistical experience, read a section of historical network communication traffic statistics (i.e., first statistical data) from the database, for example, each statistical data cycle is 30 days, each statistical data value is one day's traffic data, in MB;

[0053] S200, performing a first normal distribution calculation on the first statistical data to determine a first range threshold;

[0054] It should be noted that, in some embodiments, a first normal distribution calculation is performed on the first statistical data to obtain the mean and standard deviation value of the first statistical data; based on the mean and standard deviation value of the first statistical data, [μ1-2σ1, μ1+2σ1] is determined as the first range threshold; wherein μ1 represents the mean of the first statistical data, and σ1 represents the standard deviation value of the first statistical data.

[0055] Specifically, Figure 2As shown, the normal distribution is calculated once (i.e., the first normal distribution calculation): the mean and standard deviation of the read statistical data (i.e., the first statistical data) are calculated, both in MB, and the value range of [μ1-2σ1, μ1+2σ1] (i.e., the first range threshold) is determined. Wherein, μ1 represents the mean of the first statistical data, and σ1 represents the standard deviation of the first statistical data.

[0056] S300, determining second statistical data according to the first statistical data and based on a first range threshold;

[0057] It should be noted that, in some embodiments, based on the first range threshold, data of low-probability events are eliminated from the first statistical data to obtain the second statistical data.

[0058] Specifically, Figure 2 As shown, data of low-probability events are eliminated: the values ​​that are not in the range of [μ1-2σ1, μ1+2σ1] are removed from the statistical data (i.e., the first statistical data), and a set of statistical data of N in number (i.e., the second statistical data) is re-formed, where N≤30.

[0059] S400, performing a second normal distribution calculation on the second statistical data to determine a second range threshold;

[0060] It should be noted that, in some embodiments, a second normal distribution calculation is performed on the second statistical data to obtain the mean and standard deviation value of the second statistical data; based on the mean and standard deviation value of the second statistical data, [μ2-2σ2, μ2+2σ2] is determined as the second range threshold; wherein μ1 represents the mean of the second statistical data, and σ1 represents the standard deviation value of the second statistical data.

[0061] Specifically, Figure 2 As shown, the normal distribution is calculated twice (i.e., the second normal distribution calculation): based on a newly formed set of statistical data (i.e., the second statistical data), its data mean and standard deviation are calculated again to determine the value range of [μ2-2σ2, μ2+2σ2] (i.e., the second range threshold).

[0062] S500: Monitor the abnormal value of the target data flow according to the second range threshold.

[0063] It should be noted that, in some embodiments, the upper limit and lower limit of the data flow abnormal value are determined based on the second range threshold; based on the upper limit and lower limit of the data flow abnormal value, the abnormal value of the target data flow is monitored; when the target data flow is greater than the upper limit or less than the lower limit, an abnormal value prompt is given.

[0064] Specifically, Figure 2As shown, the threshold value of the network communication flow value of the day is judged: first, the upper limit value μ2+2σ2 and the lower limit value μ2-2σ2 of the warning value are determined according to [μ2-2σ2, μ2+2σ2]. The communication room operation and maintenance platform judges the threshold value of the network communication flow value of the day. When it is judged that the value is not within the value [μ2-2σ2, μ2+2σ2] of the secondary calculation result, a prompt is given according to the judgment rule determined by the implementation, and the gateway personnel are notified to observe the phenomenon and analyze the root cause.

[0065] The present invention will be further explained below in conjunction with specific embodiments, which should not be construed as limiting the present invention:

[0066] The first step is to read a historical network traffic statistics. The statistical room operation and maintenance platform reads a historical statistical data X from the database, recorded as X = {x1, x2, ..., x n}, where n = 30; x n Indicates the traffic statistics value of the nth day in the historical statistics;

[0067] Step 2: Calculate the normal distribution once. Calculate the average value of the statistical data for this segment Calculate the standard deviation of the statistical data for this segment Determine the [μ1-2σ1, μ1+2σ1] value of the calculation result, and determine the upper limit of the calculation warning value at the same time Calculate the lower limit of the warning value once

[0068] Step 3: Eliminate data of low-probability events. Judge each value in array X in turn and make range judgments. and less than The values ​​of are removed, and a new array X2 is formed in {x1, x2,…, x m}, where m≤30; where, when some data are removed, the values ​​represented by x1, x2, ... in X2 are not the same as or completely different from the values ​​represented by x1, x2, ... in X;

[0069] Step 4: Second calculation of normal distribution. In order to more accurately describe the normal range and warning value and reduce the impact of low-probability event data, the average value of array X2 is calculated. And the standard deviation of the data segment Re-determine the upper limit of the warning value for the secondary calculation Secondary calculation of the lower limit of the warning value

[0070] Step 5: Determine the threshold value of the network traffic value for the day. Assume that the traffic statistics value for the day is X today , using the upper limit of the warning value and the lower limit of the warning value With X today Compare the size, that is, judge X today Greater than or X today Less than If the value is too high, it is considered that the traffic of the day needs to be analyzed for the root cause, and the reason for the large or small traffic is analyzed. Then an early warning prompt is given, so that the gateway personnel can observe the phenomenon and analyze the root cause.

[0071] In summary, the present invention provides a data flow abnormal value monitoring method. Automatic calculation and monitoring of abnormal values ​​is realized, and an irregular iterative calculation method based on normal distribution is adopted, which includes a section of saved network communication flow data statistics. According to the section of network communication flow data statistics, a calculation of the mean and standard deviation is performed. In order to optimize the distribution of abnormal value range, based on the principle of small probability events, data in the range of [μ1-2σ1, μ1+2σ1] is retained, that is, values ​​greater than μ1+2σ1 and values ​​less than μ1-2σ1 are eliminated, and the mean and standard deviation values ​​of the historical data are calculated again, and finally the optimized abnormal threshold [μ2-2σ2, μ2+2σ2] is calculated, which is used as the basis for judging real-time traffic in the future. The present invention can realize accurate data flow abnormal value monitoring, and adaptively determine the warning range based on historical data, and can efficiently monitor data flow abnormal values.

[0072] On the other hand, referring to Figure 3 An embodiment of the present invention provides a data traffic anomaly monitoring system 600, including: a first module 610, used to obtain historical data of network communication data traffic within a preset period as a first statistical data; a second module 620, used to perform a first normal distribution calculation on the first statistical data to determine a first range threshold; a third module 630, used to determine a second statistical data based on the first statistical data and the first range threshold; a fourth module 640, used to perform a second normal distribution calculation on the second statistical data to determine a second range threshold; a fifth module 650, used to perform anomaly monitoring of target data traffic based on the second range threshold.

[0073] The contents of the method embodiments of the present invention are all applicable to the system embodiments. The functions specifically implemented by the system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method.

[0074] Reference Figure 4 , another aspect of the embodiment of the present invention further provides a data flow abnormal value monitoring device 700, including a processor 710 and a memory 720;

[0075] The memory is used to store programs;

[0076] The processor executes the program to implement the above method.

[0077] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0078] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0079] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0080] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0081] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0082] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0083] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0084] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution device, apparatus or device (such as a computer-based device, a device including a processor, or other device that can fetch instructions from an instruction execution device, apparatus or device and execute the instructions), or in conjunction with such instruction execution device, apparatus or device. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution device, apparatus or device, or in conjunction with such instruction execution device, apparatus or device.

[0085] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0086] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0087] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0088] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0089] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for monitoring abnormal values ​​of data flow, characterized in that: include: Acquire historical data of network communication data flow within a preset period as first statistical data; Performing a first normal distribution calculation on the first statistical data to determine a first range threshold; The performing a first normal distribution calculation on the first statistical data to determine a first range threshold includes: Performing a first normal distribution calculation on the first statistical data to obtain a mean value and a standard deviation value of the first statistical data; According to the mean and standard deviation of the first statistical data, [μ1-2σ1, μ1+2σ1] is determined as the first range threshold; wherein μ1 represents the mean of the first statistical data, and σ1 represents the standard deviation of the first statistical data; Determining second statistical data according to the first statistical data and based on the first range threshold; Performing a second normal distribution calculation on the second statistical data to determine a second range threshold; The performing a second normal distribution calculation on the second statistical data to determine a second range threshold includes: Performing a second normal distribution calculation on the second statistical data to obtain a mean value and a standard deviation value of the second statistical data; According to the mean and standard deviation of the second statistical data, [μ2-2σ2, μ2+2σ2] is determined as the second range threshold; wherein μ2 represents the mean of the second statistical data, and σ2 represents the standard deviation of the second statistical data; According to the second range threshold, abnormal value monitoring of target data traffic is performed.

2. A data flow abnormal value monitoring method according to claim 1, characterized in that: The obtaining of historical statistical data of network communication data flow within a preset period includes: According to a preset statistical data cycle, historical data of network communication data flow per day in the statistical data cycle is obtained; According to the historical data, the communication flow data of each day is taken as a statistical data value to obtain the first statistical data.

3. A data flow abnormal value monitoring method according to claim 1, characterized in that: Also includes: Based on a preset period, historical data of network communication data traffic within a preset period is periodically obtained to update the first statistical data.

4. A data flow abnormal value monitoring method according to claim 1, characterized in that: The determining, according to the first statistical data and based on the first range threshold, second statistical data includes: Based on the first range threshold, data of low-probability events are eliminated from the first statistical data to obtain second statistical data.

5. A data flow abnormal value monitoring method according to claim 1, characterized in that: The monitoring of abnormal values ​​of target data flow according to the second range threshold includes: Determine an upper limit and a lower limit of the data flow abnormal value according to the second range threshold; Perform abnormal value monitoring of target data flow according to the upper limit and lower limit of the abnormal value of the data flow; When the target data flow is greater than the upper limit or less than the lower limit, an abnormal value prompt is given.

6. A data flow abnormal value monitoring system, characterized in that: include: The first module is used to obtain historical data of network communication data flow within a preset period as first statistical data; The second module is configured to perform a first normal distribution calculation on the first statistical data to determine a first range threshold; wherein the performing a first normal distribution calculation on the first statistical data to determine the first range threshold includes: Performing a first normal distribution calculation on the first statistical data to obtain a mean value and a standard deviation value of the first statistical data; According to the mean and standard deviation of the first statistical data, [μ1-2σ1, μ1+2σ1] is determined as the first range threshold; wherein μ1 represents the mean of the first statistical data, and σ1 represents the standard deviation of the first statistical data; A third module is used to determine second statistical data according to the first statistical data and based on the first range threshold; The fourth module is used to perform a second normal distribution calculation on the second statistical data to determine a second range threshold; wherein the performing a second normal distribution calculation on the second statistical data to determine the second range threshold includes: Performing a second normal distribution calculation on the second statistical data to obtain a mean value and a standard deviation value of the second statistical data; According to the mean and standard deviation of the second statistical data, [μ2-2σ2, μ2+2σ2] is determined as the second range threshold; wherein μ2 represents the mean of the second statistical data, and σ2 represents the standard deviation of the second statistical data; The fifth module is used to monitor the abnormal value of the target data flow according to the second range threshold.

7. A data flow abnormal value monitoring device, comprising a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 5.