CN106656662A - Method and system for determining abnormal bandwidth, and electronic device - Google Patents

Abstract

The embodiment of the present invention discloses a method, system, and electronic device for determining abnormal bandwidth, wherein the method includes: obtaining historical bandwidth data used by users at different time points within a preset time; The bandwidth prediction model of the bandwidth range used at different time points; predict the bandwidth range used by the user at a certain time point according to the bandwidth prediction model; compare the actual bandwidth used by the user at a certain time point with the bandwidth range ; When the actual bandwidth exceeds the bandwidth range, it is determined that the actual bandwidth is an abnormal bandwidth. The embodiment of the present invention determines the bandwidth prediction model according to the historical bandwidth data, and uses the bandwidth prediction model to determine the bandwidth range used by the user at a certain point in time, and then compares the actual bandwidth used by the user at a certain point in time with the bandwidth range It is realized to determine whether the actual bandwidth used by the user at a certain point in time is abnormal bandwidth.

Description

Method, system and electronic device for determining abnormal bandwidth

technical field

The embodiments of the present invention relate to the technical field of the Internet, and in particular to a method, system and electronic equipment for determining abnormal bandwidth.

Background technique

Bandwidth is a very useful concept and plays an important role in network communication. The network bandwidth refers to the amount of data that can be transmitted within a unit of time (generally refers to 1 second). With the rapid development of the Internet, more and more CDN service providers provide users with bandwidth services. With the fierce competition, CDN service providers are more and more concerned about the service quality of the bandwidth service that users get, so as to better meet the needs of users.

However, the inventor found in the process of implementing the embodiment of the present invention that because the bandwidth services provided by CDN service providers for different services always have fluctuations, the service quality of users is sometimes good or bad. volatility. Therefore, how to timely determine the abnormal bandwidth point that causes the fluctuation of the bandwidth service for reference to eliminate the fluctuation has become an urgent technical problem to be solved.

Contents of the invention

Embodiments of the present invention provide a method, system and electronic device for determining abnormal bandwidth, which are used to solve the technical problem in the prior art that abnormal bandwidth points in bandwidth services cannot be determined.

In the first aspect, an embodiment of the present invention provides a method for determining abnormal bandwidth, including:

Obtain historical bandwidth data used by users at different points in time within a preset period;

determining a bandwidth prediction model for predicting bandwidth ranges used by the user at different time points according to the historical bandwidth data;

Predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model;

comparing the actual bandwidth used by the user at the certain time point with the bandwidth range;

When the actual bandwidth exceeds the bandwidth range, it is determined that the actual bandwidth is an abnormal bandwidth.

In the second aspect, the embodiment of the present invention also provides a system for determining abnormal bandwidth, including:

The historical data acquisition module is used to acquire historical bandwidth data used by users at different time points within a preset time;

A model determination module, configured to determine a bandwidth prediction model for predicting the range of bandwidth used by the user at different time points according to the historical bandwidth data;

A bandwidth range determination module, configured to predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model;

A comparison module, configured to compare the actual bandwidth used by the user at the certain time point with the bandwidth range;

An abnormality determination module, configured to determine that the actual bandwidth is an abnormal bandwidth when the actual bandwidth exceeds the bandwidth range.

In the third aspect, the embodiment of the present invention provides a non-volatile computer-readable storage medium, and one or more programs including execution instructions are stored in the storage medium, and the execution instructions can be executed by electronic devices (including but not limited to a computer, server, or network device, etc.) to read and execute, so as to implement any one of the methods for determining abnormal bandwidth described above in the embodiments of the present invention.

In a fourth aspect, an electronic device is provided, which includes: at least one processor, and a memory connected to the at least one processor in communication, wherein the memory stores instructions executable by the at least one processor, The instructions are executed by the at least one processor, so that the at least one processor can execute any one of the methods for determining abnormal bandwidth in the embodiments of the present invention.

In the fifth aspect, the embodiment of the present invention also provides a computer program product, the computer program product includes a computing program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program When the instructions are executed by a computer, the computer is made to execute any one of the methods for determining abnormal bandwidth described above.

The embodiment of the present invention determines a bandwidth prediction model for predicting the user's future bandwidth according to the user's historical bandwidth data, and uses the determined bandwidth prediction model to determine the bandwidth range used by the user at a certain point in time, and then compares the user's The manner of the actual bandwidth actually used at the certain time point and the determined bandwidth range realizes determining whether the actual bandwidth used by the user at the certain time point is an abnormal bandwidth.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

Fig. 1 is the flowchart of an embodiment of the abnormal bandwidth determination method of the present invention;

Fig. 2 is the flowchart of an embodiment of step S12 in Fig. 1;

FIG. 3 is a flow chart of another embodiment of the abnormal bandwidth determination method of the present invention;

FIG. 4 is a flowchart of another embodiment of the abnormal bandwidth determination method of the present invention;

Fig. 5 is the structural block diagram of an embodiment of the abnormal bandwidth determination system of the present invention;

Fig. 6 is the structural block diagram of an embodiment of the model determination module in the abnormal bandwidth determination system of the present invention;

FIG. 7 is a structural block diagram of another embodiment of the abnormal bandwidth determination system of the present invention;

Fig. 8 is a structural block diagram of another embodiment of the model determination module in the abnormal bandwidth determination system of the present invention;

FIG. 9 is a schematic structural diagram of an embodiment of the electronic device of the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the embodiments of the present invention.

It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

Embodiments of the invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Embodiments of the invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

In the embodiments of the present invention, "module", "device", "system" and the like refer to related entities applied to computers, such as hardware, a combination of hardware and software, software or software in execution, and the like. In particular, for example, an element may be, but is not limited to being, a process running on a processor, a processor, an object, an executable element, a thread of execution, a program and/or a computer. Also, an application program or a script program running on a server, and the server may both be components. One or more elements can be within a process and/or thread of execution and an element can be localized on one computer and/or distributed between two or more computers and executed by various computer-readable media . Components may also communicate via a signal having one or more packets of data, for example, from one interacting with a local system, another component in a distributed system, and/or interacting with other systems via a network over the Internet. local and/or remote procedures to communicate.

Finally, it should also be noted that in this text, relational terms such as first and second etc. are only used to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations, any such actual relationship or order exists. Moreover, the terms "comprising" and "comprising" not only include those elements, but also include other elements not explicitly listed, or also include elements inherent in such a process, method, article, or device. Without further limitations, an element defined by the statement "comprising..." does not exclude the presence of additional same elements in the process, method, article or device comprising said element.

As shown in Figure 1, the abnormal bandwidth determination method of an embodiment of the present invention includes:

S11. Obtain historical bandwidth data used by users at different time points within a preset time;

S12. Determine a bandwidth prediction model for predicting the range of bandwidth used by the user at different time points according to the historical bandwidth data;

S13. Predict the bandwidth range used by the user at a certain time point according to the bandwidth prediction model;

S14. Comparing the actual bandwidth used by the user at the certain time point with the bandwidth range;

S15. Determine that the actual bandwidth is an abnormal bandwidth when the actual bandwidth exceeds the bandwidth range.

The method for determining abnormal bandwidth in this embodiment determines a bandwidth prediction model for predicting the user's future bandwidth according to the user's historical bandwidth data, and uses the determined bandwidth prediction model to determine the bandwidth range used by the user at a certain point in time, Then, by comparing the actual bandwidth actually used by the user at the certain time point with the determined bandwidth range, it is realized whether the actual bandwidth used by the user at the certain time point is an abnormal bandwidth.

The historical bandwidth data in step S11 can be the bandwidth data used by users within a period of time before the current date, and the bandwidth data is a period of one day, and is a fixed time point in a day (dividing a day according to a predetermined time granularity For example, take 5 minutes as the collection granularity of bandwidth data, that is, get a bandwidth value every 5 minutes. Different time granularities can be selected according to different services, and the embodiment of the present invention does not limit the selection of time granularity). value. For example, bandwidth data and corresponding time points 60 days before the current date. The bandwidth data can be obtained through various bandwidth data detection devices distributed in the communication network or channels, or through other methods. The historical bandwidth data in this embodiment may include multiple data sample subsets, and the multiple data sample subsets may be divided according to users, that is, the bandwidth of each user at each time point may constitute a data sample subset, so that targeted Analyze and predict the user bandwidth usage that needs to be analyzed. In other embodiments, data sample subsets can also be drawn according to the user and time, that is, the bandwidth of a certain user within a preset time period can be used to form a data sample subset, and the preset time period can be based on a year The unit, such as a year, may also be a unit of a month, such as one month, or any other time interval, but in a preferred embodiment, it is generally not less than one month.

In some embodiments, the historical bandwidth data includes bandwidth A _ij acquired at each time point, where A _i,j represents the bandwidth when date is i and time is j. For example, A _20160101 , 1200 may indicate the amount of bandwidth of the user at 12 o'clock on January 1, 2016, and the data sample set in this embodiment includes a large number of data sets about A _ij .

As shown in FIG. 2, in some embodiments, step S12, determining a bandwidth prediction model for predicting the range of bandwidth used by the user at different time points according to the historical bandwidth data includes:

S21. Calculate the first-order difference between the bandwidth at the same time point every day and the bandwidth at a time point separated from the same time point by a first time within the preset time to form a first-order difference set, and obtain the first-order difference set. - the mode in the first-order difference set is the first mode;

S22. Calculate respectively the first-order difference between the bandwidth at the same time point every day and the bandwidth at a time point separated from the same time point by a second time within a preset time to form a second first-order difference set, and obtain the The mode in the second first-order difference set is the second mode;

S23. Determine the bandwidth prediction model according to the first mode and the second mode; the bandwidth prediction model is as follows:

F _i,j = a*(A _i,j-t1 +mean ₁ )+b*(A _i,j-t2 +mean ₂ );

Wherein, a represents the first weight, b represents the second weight, and a+b=1, mean ₁ represents the first mode, mean ₂ represents the second mode, F _i,j represents the prediction bandwidth when the time is j, A _i,j-t1 represents the bandwidth when time j is separated by the first time t1, and A _i,j-t2 represents the bandwidth when time j is separated by the second time t2.

In this embodiment, in order to calculate the bandwidth of each user at each time point every day, it is necessary to analyze and calculate the bandwidth value at the same time point every day, so as to predict the bandwidth at the time point of the next day.

In this embodiment, within the preset time (such as half a year), the first-order difference between the bandwidth at the same time point every day and the bandwidth separated by the first time can be randomly calculated to form the first first-order difference set, and at the same time point every day The first-order difference between the bandwidth of the bandwidth and the bandwidth separated by the second time constitutes a second first-order difference set; the first time and the second time can be any time interval, generally in minutes (generally less than 30 minutes), For example, the first time in this embodiment may be 5 minutes, and the second time may be 10 minutes.

That is to say, the first first-order difference set obtained in this embodiment can be expressed as Bn=A _i,j -A _i,j-nt1 , where Bn represents the first-order difference values at intervals of the first time, and t1 represents first timing.

The second first-order difference set obtained in this embodiment can be expressed as Cn=A _i,j -A _i,j-nt2 , where Cn represents the first-order difference values at intervals of the second time, and t2 represents the second time.

In this embodiment, after determining the first first-order difference set and the second first-order difference set, the histogram principle is used to determine the first mode corresponding to the first first-order difference set and the first mode corresponding to the second first-order difference set. Two modes. The "mode" refers to the data in the interval that appears intensively. In the embodiment of the present invention, the maximum value and the minimum value of the sequence in the first first-order difference set and the second first-order difference set are used as two endpoints of the entire interval, and the partition parameter n=3 is set. Count the number of sequences falling into the corresponding interval, select the data in the interval with the largest number, calculate its mean value and determine it as the mode.

For example, the expression of the first first-order difference set may be expressed as B _i,j-nt1 =A _i,j -A _i,j-nt1 , where n is an integer, and t1 represents the first time. E.g:

B _20160530 , 1155 = A _20160530 , 1200 -A _20160530 , 1155;

B _20160529 , 1155 = A _20160529 , 1200 -A _20160529 , 1155;

B _20160528 , 1155 = A _20160528 , 1200 -A _20160528 , 1155;  ….

Among them, B _20160530 , 115, B _20160529 , 1155, B _20160528 , 1155, etc. are the sequence values in the first first-order difference set.

For example, the expression of the second first-order difference set may be expressed as C _i,j-nt1 =A _i,j -A _i,j-nt1 , where n is an integer, and t2 represents the second time. E.g:

C _20160530 , 1155 = A _20160530 , 1200 -A _20160530 , 1155;

C _20160529 , 1155 = A _20160529 , 1200-A _20160529 , 1155;

C _20160528 , 1155 = A _20160528 , 1200 -A _20160528 , 1155;  ….

Among them, C _20160530 , 115, C _20160529 , 1155, C _20160528 , 1155, etc. are the sequence values in the second first-order difference set.

In this embodiment, the mode of mode is used to determine the first mode and the second mode for determining the bandwidth prediction model, and a more accurate bandwidth prediction model can be obtained. With the concept of "moderate number", determine the value that appears most in the sequence as the bandwidth prediction model, avoiding the occasional small probability sequence value from affecting the accuracy of the final bandwidth prediction model.

As shown in Figure 3, in some embodiments, the abnormal bandwidth determination method further includes:

S31. Calculate the first-order difference between the actual bandwidth and the predicted bandwidth at the same time point every day within the preset time respectively to form a third first-order difference set;

S32. Determine the upper boundary and the lower boundary of the bandwidth range; wherein

The expression of the upper boundary is:

L ₁ ＝a*(A _i,j-t1 +mean ₁ +3*σ ₁ )+b*(A _i,j-t2 +mean ₂ +3*σ ₂ )+3*σ ₃ ;

The expression of the lower bound is:

L ₂ ＝a*(A _i,j-t1 +mean ₁ -3*σ ₁ )+b*(A _i,j-t2 +mean ₂ -3*σ ₂ )-3*σ ₃ ;

Wherein, L ₁ represents the upper boundary of the bandwidth range, L ₂ represents the lower boundary of the bandwidth range, σ ₁ is the standard deviation of the first first-order difference set, and σ ₂ is the second first-order difference set The standard deviation of , σ ₃ is the standard deviation of the third first-order difference set.

The amount of white noise between the actual bandwidth value and the predicted bandwidth value is calculated in step S31 of this embodiment. White noise, defined as the deviation between the actual bandwidth value and the predicted bandwidth value, is one of the unavoidable variables. By considering the white noise caused by the deviation between the real value and the predicted value, the upper and lower boundaries of the bandwidth range determined in this embodiment are more in line with the actual situation, so that the abnormal bandwidth can be determined more accurately.

The expression of the third first-order difference set in this embodiment can be expressed as D _i,j =A _i,j -F _i,j , where A _i,j is the actual bandwidth value when the date is i and the time is j , F _i,j is the predicted bandwidth value when the date is i and the time is j. E.g:

D _20160530 , 1155 = A _20160530 , 1155-F _20160530 , 1155;

D _20160529 , 1155 = A _20160529 , 1155-F _20160529 , 1155;

D _20160528 , 1155 = A _20160528 , 1155 -F _20160528 , 1155;  ….

Among them, D _20160530 , 1155, D _20160529 , 1155, D _20160528 , 1155, etc. are the sequence values in the third first-order difference set.

In this embodiment, it is necessary to calculate the standard deviation σ 1 of the first first-order difference set, the standard deviation σ ₂ of the second first-order difference set, and the standard deviation σ ₃ of the _third first-order difference set, so as to determine the bandwidth range Upper and lower boundaries.

As shown in Figure 4, in some embodiments the first weight and the second weight are determined by the following steps:

S41. Calculate the square sum Q of the first-order difference values between the actual bandwidth and the predicted bandwidth in the third first-order difference set:

Among them, A' _i,j ＝A _i,j-t1 +mean ₁ ; A” _i,j ＝A _i,j-t2 +mean ₂ , the interval of date i is (i0, iend), and the interval of time j is (j0, jend);

S42. According to with The first weight a and the second weight b are obtained through calculation.

In this embodiment, the first weight a and the second weight b are determined by minimizing the square of the difference between the actual bandwidth and the predicted bandwidth as a constraint condition by using the least square method. Therefore, the first weight and the second weight determined in this embodiment are used as parameters of the bandwidth prediction model, which can minimize the difference between the predicted bandwidth value and the real bandwidth value, and improve the accuracy of the bandwidth prediction model.

The historical bandwidth data in the above embodiment is divided into two parts, the first part of data is used as benchmark data (1/3 of historical bandwidth data), and the second part of data is used as test data (2/3 of historical bandwidth data). Among them, the first part of data is used to determine the first mode and the second mode to determine the bandwidth prediction model in the above embodiment; the second part of data is used to bring into the bandwidth prediction model to obtain the predicted bandwidth value, and compare with the actual The third first-order difference set is determined after the bandwidth value is the worst. Then, the weight of the optimal bandwidth prediction model is determined based on the least squares method according to the third first-order difference set.

In addition, because there are abnormal points in the historical bandwidth data, in order to avoid the influence of the abnormal points on the accuracy of establishing the bandwidth prediction model, in the embodiment of the present invention, the differences in the third first-order difference set are sorted according to their size. Delete the previous larger value (eg 5% of the sequence) and the later smaller value (eg 5% of the sequence) in the sequence according to the percentage, and keep the remaining difference (90% of the sequence) for subsequent calculation.

In some embodiments, alarm information is generated after the actual bandwidth is determined to be abnormal bandwidth when the actual bandwidth exceeds the bandwidth range.

The method for determining the abnormal bandwidth in this embodiment can notify the staff to perform emergency treatment through the alarm information at the first time when the abnormal bandwidth is determined, so as to solve the problem that causes the abnormal bandwidth to occur.

Practice has found that multiple abnormal bandwidths may appear at the same time. However, due to the limited staff, it is only possible to analyze the multiple abnormal bandwidths one by one and solve the resulting abnormal bandwidth problems. However, multiple abnormal bandwidths may have different severities. It is obviously unreasonable for the staff to mechanically analyze and solve them one by one. Instead, the ones with higher severity should be analyzed and processed with high priority. Therefore, the alarm information generated in the embodiment of the present invention clearly performs hierarchical alarms according to the severity of the bandwidth anomaly.

In the embodiment of the present invention, a logic table structure is designed and named as alarm level rule table. Introduce two index parameters to divide the alarm level. The two index parameters are respectively: the relative bandwidth change rate d and the number m of abnormal users of the same service line. Among them, the bandwidth relative change rate d is defined as: the ratio of the difference between the bandwidth value at the current time point and the bandwidth value at the previous time point to the bandwidth value at the current time point, for example, the bandwidth value at the current 5-minute point minus the previous 5 The bandwidth value at the minute point is divided by the current bandwidth value at the 5-minute point.

The step of classifying and alerting the abnormal bandwidth includes:

Determine whether the relative change rate d of the bandwidth of the abnormal bandwidth point under the current service is greater than a preset value (for example, the preset value is 60%) relative to the bandwidth of the previous time point;

Generate four-level alarm information when it is determined that the relative change rate d of bandwidth under the current service is greater than or equal to the preset value and the number of applications is greater than or equal to 3;

When it is determined that the relative change rate d of the bandwidth under the current service is greater than or equal to the preset value and the usage number is greater than or equal to 2, a three-level alarm message is generated;

When it is determined that the relative rate of change of bandwidth d under the current service is greater than or equal to the number of users whose preset value is greater than or equal to 1, a secondary alarm message is generated;

When it is determined that the number of users whose bandwidth relative change rate d is less than the preset value under the current service is greater than or equal to 3, a three-level alarm message is generated;

When it is determined that the number of users whose bandwidth relative change rate d is less than the preset value under the current service is greater than or equal to 2, a secondary alarm message is generated;

When it is determined that the number of users whose bandwidth relative change rate d is less than the preset value under the current service is greater than or equal to 1, a first-level alarm message is generated. In this embodiment, the abnormal bandwidth conditions represented by the first-level alarm information to the fourth-level alarm information are serious step by step.

It should be noted that, for the sake of simple description, all the aforementioned method embodiments are described as a series of combined actions. However, those skilled in the art should know that the embodiments of the present invention are not limited by the sequence of actions described. Because according to the embodiment of the present invention, some steps may be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of the present invention.

In the foregoing embodiments, the descriptions of each embodiment have their own emphases, and for parts not described in detail in a certain embodiment, reference may be made to relevant descriptions of other embodiments.

As shown in Figure 5, an abnormal bandwidth determination system 500 provided by an embodiment of the present application includes:

A historical data acquisition module 510, configured to acquire historical bandwidth data used by users at different time points within a preset time;

A model determination module 520, configured to determine a bandwidth prediction model for predicting the range of bandwidth used by the user at different time points according to the historical bandwidth data;

A bandwidth range determination module 530, configured to predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model;

A comparison module 540, configured to compare the actual bandwidth used by the user at the certain time point with the bandwidth range;

An abnormality determination module 550, configured to determine that the actual bandwidth is an abnormal bandwidth when the actual bandwidth exceeds the bandwidth range.

As shown in FIG. 6, in some embodiments, the historical bandwidth data includes bandwidth A _i,j acquired at each time point, where A _i,j represents the bandwidth when the date is i and the time is j;

The model determination module 520 includes:

The first mode determination unit 521 is configured to respectively calculate the first-order difference between the bandwidth at the same time point every day and the bandwidth at a time point separated from the same time point by a first time within a preset time to form the first one An order difference set, obtaining the mode number in the first first order difference set as the first mode number;

The second mode determination unit 522 is configured to respectively calculate the first-order difference between the bandwidth at the same time point every day and the bandwidth at a time point separated from the same time point by a second time within the preset time to form the second mode. A first-order difference set, obtaining the mode in the second first-order difference set as the second mode;

A model determining unit 523, configured to determine the bandwidth prediction model according to the first mode and the second mode; wherein

The bandwidth prediction model is: F _i,j =a*(A _i,j-t1 +mean ₁ )+b*(A _i,j-t2 +mean ₂ );

Wherein, a represents the first weight, b represents the second weight, and a+b=1, mean ₁ represents the first mode, mean ₂ represents the second mode, F _i,j represents the prediction bandwidth when the time is j, A _i,j-t1 represents the bandwidth when time j is separated by the first time t1, and A _i,j-t2 represents the bandwidth when time j is separated by the second time t2.

As shown in FIG. 7, in some embodiments, the abnormal bandwidth determination system 500 further includes:

The difference calculation module 560 is used to calculate the first-order difference between the actual bandwidth and the predicted bandwidth at the same time point every day within the preset time to form a third first-order difference set;

The upper and lower boundary determination module 570 is used to determine the upper boundary and the lower boundary of the bandwidth range; wherein

The expression of the upper boundary is:

L ₁ ＝a*(A _i,j-t1 +mean ₁ +3*σ ₁ )+b*(A _i,j-t2 +mean ₂ +3*σ ₂ )+3*σ ₃ ;

The expression of the lower bound is:

L ₂ ＝a*(A _i,j-t1 +mean ₁ -3*σ ₁ )+b*(A _i,j-t2 +mean ₂ -3*σ ₂ )-3*σ ₃ ;

Wherein, L ₁ represents the upper boundary of the bandwidth range, L ₂ represents the lower boundary of the bandwidth range, σ ₁ is the standard deviation of the first first-order difference set, and σ ₂ is the second first-order difference set The standard deviation of , σ ₃ is the standard deviation of the third first-order difference set.

As shown in Figure 8, the model determination module 520 also includes a weight determination unit 521, and the weight determination unit 521 includes:

The square sum calculation element 5211 is used to calculate the square sum Q of the first-order difference values between the actual bandwidth and the predicted bandwidth in the third first-order difference set:

Among them, A' _i,j ＝A _i,j-t1 +mean ₁ ; A” _i,j ＝A _i,j-t2 +mean ₂ , the interval of date i is (i0, iend), and the interval of time j is (j0, jend);

Weight calculation element 5212, for according to with The first weight a and the second weight b are obtained through calculation.

In some embodiments, the abnormal bandwidth determination system 500 further includes an alarm information generating module, configured to generate alarm information after determining that the actual bandwidth is abnormal bandwidth when the actual bandwidth exceeds the bandwidth range.

The system for determining the abnormal bandwidth of the above-mentioned embodiment of the present invention can be used to execute the method for determining the abnormal bandwidth of the embodiment of the present invention, and correspondingly achieve the technical effect achieved by the method for determining the abnormal bandwidth of the embodiment of the present invention, which will not be repeated here.

In the embodiment of the present invention, a hardware processor (hardware processor) may be used to implement related functional modules.

On the other hand, an embodiment of the present invention provides a non-volatile computer-readable storage medium, where one or more programs including execution instructions are stored in the storage medium, and the execution instructions can be executed by an electronic device (including but not limited to computers, servers, or network devices, etc.) to read and execute, to perform the relevant steps in the above method embodiments, for example:

Obtain historical bandwidth data used by users at different points in time within a preset period;

determining a bandwidth prediction model for predicting bandwidth ranges used by the user at different time points according to the historical bandwidth data;

Predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model;

comparing the actual bandwidth used by the user at the certain time point with the bandwidth range;

When the actual bandwidth exceeds the bandwidth range, it is determined that the actual bandwidth is an abnormal bandwidth.

On the other hand, the embodiment of the present invention also discloses an electronic device, which includes:

At least one memory for storing computer operation instructions;

at least one processor configured to execute said memory stored computer operating instructions to perform:

Obtain historical bandwidth data used by users at different points in time within a preset period;

determining a bandwidth prediction model for predicting bandwidth ranges used by the user at different time points according to the historical bandwidth data;

Predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model;

comparing the actual bandwidth used by the user at the certain time point with the bandwidth range;

When the actual bandwidth exceeds the bandwidth range, it is determined that the actual bandwidth is an abnormal bandwidth.

Fig. 9 is a schematic diagram of the hardware structure of an electronic device for performing an abnormal bandwidth determination method provided by another embodiment of the present application. As shown in Fig. 9, the device includes:

One or more processors 910 and memory 920, one processor 910 is taken as an example in FIG. 9 .

The device for executing the method for determining the abnormal bandwidth may further include: an input device 930 and an output device 940 .

The processor 910, the memory 920, the input device 930, and the output device 940 may be connected through a bus or in other ways, and connection through a bus is taken as an example in FIG. 9 .

The memory 920, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the program corresponding to the abnormal bandwidth determination method in the embodiment of the present application directive/module. The processor 910 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 920, that is, implements the method for determining abnormal bandwidth in the above method embodiment.

The memory 920 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the usage of the abnormal bandwidth determination device, and the like. In addition, the memory 920 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 920 may optionally include a memory that is remotely located relative to the processor 910, and these remote memories may be connected to the abnormal bandwidth determining device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 930 can receive input number or character information, and generate key signal input related to user setting and function control of the abnormal bandwidth determination device. The output device 940 may include a display device such as a display screen.

The one or more modules are stored in the memory 920, and when executed by the one or more processors 910, execute the method for determining abnormal bandwidth in any of the above method embodiments.

The above-mentioned products can execute the method provided by the embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, refer to the method provided in the embodiment of this application.

The electronic equipment of the embodiment of the present application exists in various forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access. Such terminals include: PDA, MID and UMPC equipment, such as iPad.

(3) Portable entertainment equipment: This type of equipment can display and play multimedia content. Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

(4) Server: A device that provides computing services. The composition of a server includes a processor, hard disk, memory, system bus, etc. The server is similar to a general-purpose computer architecture, but due to the need to provide high-reliability services, it is important in terms of processing power and stability. , Reliability, security, scalability, manageability and other aspects have high requirements.

(5) Other electronic devices with data interaction function.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solutions or the part that contributes to related technologies can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, disk , CD, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims (11)

1. A method for determining abnormal bandwidth, comprising: Obtain historical bandwidth data used by users at different points in time within a preset period; determining a bandwidth prediction model for predicting bandwidth ranges used by the user at different time points according to the historical bandwidth data; Predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model; comparing the actual bandwidth used by the user at the certain time point with the bandwidth range; When the actual bandwidth exceeds the bandwidth range, it is determined that the actual bandwidth is an abnormal bandwidth. 2. The method according to claim 1, wherein the historical bandwidth data includes bandwidth A _i,j acquired at each point in time, wherein A _i,j represents the bandwidth when the date is i and the time is j; The determining the bandwidth prediction model for predicting the range of bandwidth used by the user at different time points according to the historical bandwidth data includes: Respectively calculate the first-order difference between the bandwidth at the same time point every day and the bandwidth at the time point at the first time apart from the same time point within the preset time to form a first-order difference set, and obtain the first-order difference set. The mode in the order difference set is the first mode; Respectively calculating the first-order difference between the bandwidth at the same time point every day and the bandwidth at a time point separated from the same time point by a second time within the preset time constitutes a second first-order difference set, and obtaining the second The mode in the first-order difference set is the second mode; According to the first mode and the second mode, the bandwidth prediction model is determined as follows: F _i,j = a*(A _i,j-t1 +mean ₁ )+b*(A _i,j-t2 +mean ₂ ); Wherein, a represents the first weight, b represents the second weight, and a+b=1, mean ₁ represents the first mode, mean ₂ represents the second mode, F _i,j represents the prediction bandwidth when the time is j, A _i,j-t1 represents the bandwidth when time j is separated by the first time t1, and A _i,j-t2 represents the bandwidth when time j is separated by the second time t2. 3. The method of claim 2, further comprising: Calculate the first-order difference between the actual bandwidth and the predicted bandwidth at the same time point every day within the preset time respectively to form a third first-order difference set; determining the upper and lower boundaries of the bandwidth range; wherein The expression of the upper boundary is: L ₁ ＝a*(A _i,j-t1 +mean ₁ +3*σ ₁ )+b*(A _i,j-t2 +mean ₂ +3*σ ₂ )+3*σ ₃ ; The expression of the lower bound is: L ₂ ＝a*(A _i,j-t1 +mean ₁ -3*σ ₁ )+b*(A _i,j-t2 +mean ₂ -3*σ ₂ )-3*σ ₃ ; Wherein, L ₁ represents the upper boundary of the bandwidth range, L ₂ represents the lower boundary of the bandwidth range, σ ₁ is the standard deviation of the first first-order difference set, and σ ₂ is the second first-order difference set The standard deviation of , σ ₃ is the standard deviation of the third first-order difference set. 4. The method of claim 3, wherein the first weight and the second weight are determined by: Calculate the sum of squares Q of the first-order difference values between the actual bandwidth and the predicted bandwidth in the third first-order difference set: $\mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}\mathrm{<span\; class="notranslate">\; 0</span>}}{\overset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; no</span>}\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; no</span>}\mathrm{<span\; class="notranslate">\; d</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; *</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}^{<span\; class="notranslate">\; ,</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; b</span>}<span\; class="notranslate">\; *</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}^{<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ,</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$ Among them, A' _i,j ＝A _i,j-t1 +mean ₁ ; A” _ij ＝A _i,j-t2 +mean ₂ , the interval of date i is (i0, iend), and the interval of time j is (j0 ,jend); according to with The first weight a and the second weight b are obtained through calculation. 5. The method according to claim 4, wherein the alarm information is generated after determining that the actual bandwidth is an abnormal bandwidth when the actual bandwidth exceeds the bandwidth range. 6. A system for determining abnormal bandwidth, comprising: The historical data acquisition module is used to acquire historical bandwidth data used by users at different time points within a preset time; A model determination module, configured to determine a bandwidth prediction model for predicting the range of bandwidth used by the user at different time points according to the historical bandwidth data; A bandwidth range determination module, configured to predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model; A comparison module, configured to compare the actual bandwidth used by the user at the certain time point with the bandwidth range; An abnormality determination module, configured to determine that the actual bandwidth is an abnormal bandwidth when the actual bandwidth exceeds the bandwidth range. 7. The system according to claim 6, wherein the historical bandwidth data includes bandwidth A _i,j acquired at each time point, wherein A _i,j represents the bandwidth when the date is i and the time is j; The model determination module includes: The first mode determination unit is used to respectively calculate the first-order difference between the bandwidth at the same time point every day and the bandwidth at the time point separated from the same time point by the first time within the preset time to form the first first-order difference set, obtaining the mode number in the first first-order difference set as the first mode number; The second mode determination unit is configured to calculate respectively the first-order difference between the bandwidth at the same time point every day and the bandwidth at a time point separated from the same time point by a second time within a preset time to form a second first-order difference An order difference set, obtaining the mode in the second first-order difference set as the second mode; A model determination unit, configured to determine the bandwidth prediction model according to the first mode and the second mode; wherein The bandwidth prediction model is: F _i,j =a*(A _i,j-t1 +mean ₁ )+b*(A _i,j-t2 +mean ₂ ); Wherein, a represents the first weight, b represents the second weight, and a+b=1, mean ₁ represents the first mode, mean ₂ represents the second mode, F _i,j represents the prediction bandwidth when the time is j, A _i,j-t1 represents the bandwidth when time j is separated by the first time t1, and A _i,j-t2 represents the bandwidth when time j is separated by the second time t2. 8. The system of claim 7, further comprising: The difference calculation module is used to calculate the first-order difference between the actual bandwidth and the predicted bandwidth at the same time point every day within a preset time to form a third first-order difference set; An upper and lower boundary determination module, configured to determine the upper and lower boundaries of the bandwidth range; wherein The expression of the upper boundary is: L ₁ ＝a*(A _i,j-t1 +mean ₁ +3*σ ₁ )+b*(A _i,j-t2 +mean ₂ +3*σ ₂ )+3*σ ₃ ; The expression of the lower bound is: L ₂ ＝a*(A _i,j-t1 +mean ₁ -3*σ ₁ )+b*(A _i,j-t2 +mean ₂ -3*σ ₂ )-3*σ ₃ ; Wherein, L ₁ represents the upper boundary of the bandwidth range, L ₂ represents the lower boundary of the bandwidth range, σ ₁ is the standard deviation of the first first-order difference set, and σ ₂ is the second first-order difference set The standard deviation of , σ ₃ is the standard deviation of the third first-order difference set. 9. The system according to claim 8, wherein the model determination module further comprises a weight determination unit, and the weight determination unit comprises: A sum of squares calculation element, used to calculate the sum of squares Q of the first-order difference values between the actual bandwidth and the predicted bandwidth in the third first-order difference set: $\mathrm{<span\; class="notranslate">\; Q</span>}<span\; class="notranslate">\; =</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; 0</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}\mathrm{<span\; class="notranslate">\; 0</span>}}{\overset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; no</span>}\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; j</span>}\mathrm{<span\; class="notranslate">\; e</span>}\mathrm{<span\; class="notranslate">\; no</span>}\mathrm{<span\; class="notranslate">\; d</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; *</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}^{<span\; class="notranslate">\; ,</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; b</span>}<span\; class="notranslate">\; *</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}^{<span\; class="notranslate">\; ,</span><span\; class="notranslate">\; ,</span>}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}$ Among them, A' _i,j ＝A _i,j-t1 +mean ₁ ; A” _i,j ＝A _i,j-t2 +mean ₂ , the interval of date i is (i0, iend), and the interval of time j is (j0,jend); weight calculation element for use according to with The first weight a and the second weight b are obtained through calculation. 10. The system according to claim 9, further comprising an alarm information generating module, configured to generate alarm information after determining that the actual bandwidth is abnormal bandwidth when the actual bandwidth exceeds the bandwidth range. 11. An electronic device comprising: at least one processor, and A memory connected in communication with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processing The device can perform: Obtain historical bandwidth data used by users at different points in time within a preset period; determining a bandwidth prediction model for predicting bandwidth ranges used by the user at different time points according to the historical bandwidth data; Predict the bandwidth range used by the user at a certain point in time according to the bandwidth prediction model; comparing the actual bandwidth used by the user at the certain time point with the bandwidth range; When the actual bandwidth exceeds the bandwidth range, it is determined that the actual bandwidth is an abnormal bandwidth.