Network bandwidth prediction method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a network bandwidth prediction method and device, computer equipment, a readable storage medium and a program product. The method comprises the steps that multiple pieces of historical data of a target network are acquired, the multiple pieces of historical data are related data corresponding to different sampling time points of the target network in a preset period, and each piece of historical data comprises total bandwidth information, bandwidth information corresponding to different application programs and bandwidth information corresponding to different users; performing data processing on the plurality of historical data to obtain feature data; and inputting the feature data into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model. By adopting the method, the network bandwidth prediction accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of network security technology, and in particular to a network bandwidth prediction method, device, computer equipment, readable storage medium and program product. Background Art

[0002] With the rapid development of the Internet and communication technology, the growth of broadband users and applications has led to a rapid increase in bandwidth demand. Users' demand for the network is increasing day by day, and making full use of existing network resources to ensure high-quality Internet experience for most broadband users has become the focus of broadband operators.

[0003] Bandwidth planning during bandwidth operation is basically a fixed available bandwidth determined after manual evaluation. Most of the time, bandwidth demand is ensured at the cost of a higher amount of redundant bandwidth. When bandwidth demand suddenly increases and available bandwidth is exhausted in special circumstances, network congestion will cause poor user experience. If the bandwidth value and usage details at future times can be predicted in advance, the available bandwidth can be flexibly configured according to specific needs to avoid high redundancy, and the predicted value can also be used to adjust specific management strategies to significantly improve the quality of user experience.

[0004] In traditional technology, bandwidth prediction mainly relies on the historical overall network bandwidth to predict a specific bandwidth in the future. However, various applications in the network are complex and changeable, and the bandwidth changes over time. Therefore, the bandwidth obtained by only predicting the historical overall network bandwidth is less accurate. Summary of the invention

[0005] Based on this, it is necessary to provide a network bandwidth prediction method, device, computer equipment, readable storage medium and program product that can improve the accuracy of network bandwidth prediction in response to the above technical problems.

[0006] In a first aspect, the present application provides a network bandwidth prediction method, the method comprising: obtaining multiple historical data of a target network, the multiple historical data being relevant data corresponding to different sampling time points of the target network within a preset period, each historical data comprising total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users; performing data processing on the multiple historical data to obtain feature data; inputting the feature data into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

[0007] In one of the embodiments, the historical data also includes at least one of the total number of terminals of different types, the total number of concurrent users, the total number of concurrent connections, the number of connections corresponding to different applications, the number of terminals of different types used by different users, and status data corresponding to a sampling time point.

[0008] In one of the embodiments, multiple historical data are processed to obtain feature data, including: processing each type of data in the multiple historical data using a corresponding type of data processing method to obtain first feature data; the data processing method includes taking logarithm, linear normalization, standard deviation normalization and one-hot encoding; and obtaining feature data based on the first feature data.

[0009] In one embodiment, obtaining characteristic data according to first characteristic data includes: filling the first characteristic data with a default value to obtain second characteristic data; and using the second characteristic data as the characteristic data.

[0010] In one of the embodiments, first characteristic data are filled with default values ​​to obtain second characteristic data, including: filling each type of data in the first characteristic data with a corresponding type of default value filling method to obtain the second characteristic data; wherein the default value filling method is determined according to the data processing method corresponding to each type of data; the default value filling method includes observation value filling method, mean filling method, median filling method and mode filling method.

[0011] In one of the embodiments, the method also includes: obtaining multiple sample historical data of the target network; each sample historical data includes sample total bandwidth information, sample bandwidth information corresponding to different applications, and sample bandwidth information corresponding to different users; performing data processing on the multiple sample historical data to obtain sample feature data; training the to-be-trained model according to the sample feature data, and obtaining a bandwidth prediction model after the training is completed.

[0012] In the second aspect, the present application also provides a network bandwidth prediction device, which includes: an acquisition module, used to acquire multiple historical data of the target network, the multiple historical data are relevant data corresponding to different sampling time points of the target network within a preset period, and each historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users; a first determination module, used to process the multiple historical data to obtain feature data; and a second determination module, used to input the feature data into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

[0013] In one of the embodiments, the historical data also includes at least one of the total number of terminals of different types, the total number of concurrent users, the total number of concurrent connections, the number of connections corresponding to different applications, the number of terminals of different types used by different users, and status data corresponding to a sampling time point.

[0014] In one of the embodiments, the first determination module is specifically used to process each type of data in multiple historical data using a corresponding type of data processing method to obtain first feature data; the data processing method includes taking logarithm, linear normalization, standard deviation normalization and one-hot encoding; based on the first feature data, feature data is obtained.

[0015] In one of the embodiments, the first determination module is specifically configured to fill the first characteristic data with a default value to obtain the second characteristic data; and use the second characteristic data as the characteristic data.

[0016] In one of the embodiments, the first determination module is specifically used to fill each type of data in the first characteristic data with a corresponding type of default value filling method to obtain the second characteristic data; wherein the default value filling method is determined according to the data processing method corresponding to each type of data; the default value filling method includes the observation value filling method, the mean filling method, the median filling method and the mode filling method.

[0017] In one of the embodiments, the device also includes a training module for obtaining multiple sample historical data of the target network; each sample historical data includes sample total bandwidth information, sample bandwidth information corresponding to different applications, and sample bandwidth information corresponding to different users; data processing is performed on the multiple sample historical data to obtain sample feature data; the training model is trained according to the sample feature data, and a bandwidth prediction model is obtained after the training is completed.

[0018] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0020] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.

[0021] The above-mentioned network bandwidth prediction method, device, computer equipment, readable storage medium and program product obtain multiple historical data of the target network, which are relevant data corresponding to different sampling time points of the target network within a preset period, and each historical data includes total bandwidth information, bandwidth information corresponding to different applications and bandwidth information corresponding to different users. Then, the multiple historical data are processed to obtain feature data, and the feature data is input into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model. Since in addition to total bandwidth information, bandwidth information corresponding to different applications and bandwidth information corresponding to different users are also considered when predicting network bandwidth, it can more comprehensively, multi-dimensionally and finely display the bandwidth usage in the target network, thereby improving the accuracy of network bandwidth prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A diagram showing an application environment of a network bandwidth prediction method in an embodiment;

[0024] Figure 2 A schematic diagram of a flow chart of a network bandwidth prediction method in one embodiment;

[0025] Figure 3 A schematic diagram of a flow chart of a network bandwidth prediction method in another embodiment;

[0026] Figure 4 A schematic diagram of a flow chart of a network bandwidth prediction method in another embodiment;

[0027] Figure 5 is a structural block diagram of a network bandwidth prediction device in one embodiment;

[0028] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application 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 application and are not used to limit the present application.

[0030] With the rapid development of the Internet and communication technology, the growth of broadband users and applications has led to a rapid increase in bandwidth demand. Users' demand for the network is increasing day by day, and making full use of existing network resources to ensure high-quality Internet experience for most broadband users has become the focus of broadband operators.

[0031] Bandwidth planning during bandwidth operation is basically a fixed available bandwidth determined after manual evaluation. Most of the time, bandwidth demand is ensured at the cost of a higher amount of redundant bandwidth. When bandwidth demand suddenly increases and available bandwidth is exhausted in special circumstances, network congestion will cause poor user experience. If the bandwidth value and usage details at future times can be predicted in advance, the available bandwidth can be flexibly configured according to specific needs to avoid high redundancy, and the predicted value can also be used to adjust specific management strategies to significantly improve the quality of user experience.

[0032] In traditional technology, bandwidth prediction mainly relies on the historical overall network bandwidth to predict a specific bandwidth in the future. However, various applications in the network are complex and changeable, and bandwidth changes over time. Therefore, the bandwidth predicted based only on the historical overall network bandwidth is difficult to reflect the specific bandwidth change trend, and the accuracy of the predicted specific bandwidth is also low.

[0033] The network bandwidth prediction method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains multiple historical data of the target network, and the multiple historical data are related data corresponding to different sampling time points of the target network within a preset period. Each historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users; the multiple historical data are processed to obtain feature data; the feature data is input into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

[0034] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0035] The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0036] In an exemplary embodiment, Figure 2 As shown, a network bandwidth prediction method is provided, and the method is applied to Figure 1 The server in is taken as an example to illustrate, including the following steps 201 to 203.

[0037] in:

[0038] Step 201, obtain multiple historical data of the target network. The multiple historical data are relevant data corresponding to different sampling time points of the target network within a preset period, and each historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users.

[0039] The target network may refer to a network within a cell area or a network within a company area. The historical data of the target network may be obtained through an application identification function deployed in the target network, such as by using at least one of DPI (Deep Packet Inspection), DFI (Deep Flow Inspection) and intelligent identification technology to identify the category of traffic in the target network in real time, that is, the application category that generates the traffic can be identified, and the application category includes at least one of video conferencing, video calls, voice calls, videos, live broadcasts, games, downloads and e-commerce shopping.

[0040] The preset period may be one week or one month, etc., and adjacent sampling time points are separated by a preset time period, which may be one day or 12 hours, etc.

[0041] The bandwidth information corresponding to an application refers to the bandwidth consumed by the application when different users in the target network use the application; the bandwidth information corresponding to a user includes the bandwidth consumed when the user uses each application, and the sum of the bandwidth consumed when the user uses all applications; the total bandwidth information refers to the total bandwidth of the target network, which is the sum of the bandwidths in the bandwidth information corresponding to each application, or the sum of the bandwidths in the bandwidth information corresponding to each user.

[0042] Bandwidth can be divided into uplink bandwidth and downlink bandwidth. Therefore, the total bandwidth information includes the total uplink bandwidth and the total downlink bandwidth; the bandwidth information corresponding to the application includes the uplink bandwidth corresponding to the application and the downlink bandwidth corresponding to the application; the bandwidth information corresponding to the user includes the uplink bandwidth and the downlink bandwidth corresponding to the user. The total uplink bandwidth in the total bandwidth information can be the sum of the uplink bandwidth corresponding to each application or the sum of the uplink bandwidth corresponding to each user; the total downlink bandwidth in the total bandwidth information can be the sum of the downlink bandwidth corresponding to each application or the sum of the downlink bandwidth corresponding to each user.

[0043] Optionally, multiple initial historical data of the target network within a preset period (ie, real-time historical data in the target network) are obtained, and the multiple initial historical data are recorded and sorted according to a preset time interval as a sampling time point to obtain multiple historical data.

[0044] Step 202: Process multiple historical data to obtain feature data.

[0045] Optionally, the plurality of historical data are processed using at least one of normalization, logarithm processing, one-hot encoding, and default value filling to obtain feature data.

[0046] Step 203: input the characteristic data into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

[0047] The bandwidth prediction model is pre-trained based on a large amount of sample historical data in the target network. The bandwidth prediction model can be a time series prediction model, which can be specifically an ARIMA (Auto-Regressive Moving Average) model, a CNN (Convolutional Neural Networks), a GRU (Gate Recurrent Unit), a VAR (Value at Risk) model, a LSTM (Long Short-Term Memory), a Prophet model, a random forest, a multivariate deep learning, a Transformer, and an MTS-Mixers (Multi-Time-Series Mixers), etc., or a hybrid model obtained by combining multiple combinations.

[0048] The bandwidth prediction result may include at least one of the total uplink bandwidth in the target network corresponding to different time points in the future, the total downlink bandwidth in the target network, the uplink bandwidth corresponding to different applications, the downlink bandwidth corresponding to different applications, the total uplink bandwidth corresponding to different users, the uplink bandwidth corresponding to different applications used by different users, and the downlink bandwidth corresponding to different applications used by different users. In other words, the bandwidth prediction result includes different types of bandwidth sequences predicted.

[0049] In one possible implementation, the bandwidth prediction model includes multiple input ports and output ports corresponding to the multiple input ports, each input port is used to input feature data of a corresponding type, and each output port is used to output a bandwidth prediction result of a corresponding type. In other words, the bandwidth prediction model includes multiple trained sub-models, and each trained sub-model is used to make predictions based on feature data of a corresponding type. For example, the bandwidth consumed by user A using video calls within a preset period is input to input port A, and output port A outputs the predicted bandwidth that the user will consume using video calls within a period of time in the future; the bandwidth consumed by video conferencing within a preset period is input to input port B, and output port B outputs the predicted bandwidth that the video conferencing will consume within a period of time in the future.

[0050] In another possible implementation, the bandwidth prediction model includes an input port and an output port. In other words, the bandwidth prediction model includes a whole trained model, which can directly predict various types of feature data.

[0051] The above-mentioned bandwidth prediction method obtains multiple historical data of the target network. The multiple historical data are relevant data corresponding to different sampling time points of the target network within a preset period. Each historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users. Then, the multiple historical data are processed to obtain feature data, and the feature data is input into a pre-trained bandwidth prediction model to obtain the bandwidth prediction result output by the bandwidth prediction model. Since the bandwidth prediction model considers not only the total bandwidth information but also the bandwidth information corresponding to different applications and the bandwidth information corresponding to different users, it can more comprehensively, multi-dimensionally, and finely display the bandwidth usage in the target network, thereby improving the accuracy of network bandwidth prediction. In addition, the bandwidth prediction model is a time series prediction model, and the bandwidth prediction result includes different types of predicted bandwidth sequences, which can reflect different types of bandwidth change trends.

[0052] In one of the embodiments, the historical data also includes at least one of the total number of terminals of different types, the total number of concurrent users, the total number of concurrent connections, the number of connections corresponding to different applications, the number of terminals of different types used by different users, and status data corresponding to a sampling time point.

[0053] The total number of terminals of different types is the sum of the number of terminals of different types used by all users in the target network. For example, the total number of terminals corresponding to laptops is the sum of the number of laptops used by all users in the target network.

[0054] The total number of concurrent users is the total number of people who generate network traffic at the same time in the target network. The total number of concurrent connections is the sum of the number of connections established simultaneously by the applications used in the target network. The number of connections refers to the number of connections established by the application with other devices or software for transmitting data.

[0055] The application identification function can not only identify the category of network traffic, but also the type of terminal that generates network traffic, such as PC (desktop computer), laptop, tablet, smart phone and smart appliance, etc. Therefore, the type of terminal used by the user can also be obtained through the application identification function, so as to obtain the number of terminals of different types used by the user.

[0056] The status data corresponding to the sampling time point includes at least one of the status data of whether it is a working day, the status data of whether it is a holiday, and the status data of whether it is a special date. Among them, the status data of whether it is a working day can also include at least one of the status data of whether it is working time and the status data of whether it is rest time; special dates are such as sports events and other stages. The status data can be either yes or no.

[0057] Therefore, based on the statistics of multiple initial historical data, multiple historical data can be obtained according to the following Tables 1, 2, 3 and 4. Among them, Table 1 is a statistical analysis from the overall level of the target network; Table 2 is a statistical analysis from the application perspective of the target network; Table 3 is a statistical analysis from the user perspective of the target network; Table 4 is a statistical analysis from the sampling time point level.

[0058] Table 1

[0059]

[0060] Table 2

[0061]

[0062]

[0063] Table 3

[0064]

[0065]

[0066] Table 4

[0067]

[0068] In this embodiment, the network bandwidth prediction further considers the total number of terminals of different types, the total number of concurrent users, the total number of concurrent connections, the number of connections corresponding to different applications, the number of terminals of different types used by different users, and the state data corresponding to the sampling time point, that is, considering the application group characteristics, user behavior characteristics, terminal characteristics, and sampling time point characteristics, so that the predicted bandwidth prediction result is more accurate and more diverse bandwidth prediction is achieved. Among them, considering the state data corresponding to the sampling time point, that is, considering the different network usage (that is, bandwidth consumption) of users on weekdays, holidays, and special dates, can greatly improve the accuracy of bandwidth prediction.

[0069] In one embodiment, if Figure 3 As shown, another network bandwidth prediction method is provided. Multiple historical data are processed to obtain characteristic data, including:

[0070] Step 301, performing a corresponding type of data processing method on each type of data in a plurality of historical data to obtain first feature data; the data processing method includes taking logarithm, linear normalization, standard deviation normalization and one-hot encoding.

[0071] Among them, each type of data refers to bandwidth type data, connection number type data, terminal number type data, user number type data and status data type data. Bandwidth type data includes the total uplink bandwidth and total downlink bandwidth in the above-mentioned total bandwidth information, the uplink bandwidth and downlink bandwidth in the bandwidth information corresponding to each application, and the uplink bandwidth and downlink bandwidth in the bandwidth information corresponding to each user. Connection number type data includes the above-mentioned total concurrent connections and the number of connections corresponding to each application. Terminal number type data includes the total number of terminals of each type and the number of terminals of each type used by each user. User number type data includes the above-mentioned total concurrent users. Status data type includes the above-mentioned status data of whether it is a weekday, whether it is a holiday, whether it is a special date, whether it is working hours and whether it is rest time.

[0072] For bandwidth type data, since the values ​​of peaks and troughs may be extremely different, the logarithmic data processing method can be used to process it.

[0073] For data of the type of connection number, data of the type of terminal number, and data of the type of user number, the data processing method can be determined according to the scale of the target network. In one example, if the number of users in the target network is less than a preset number (e.g., 1000), the data of the type of connection number, the type of terminal number, and the type of user number may have a large difference in peak and trough values. At this time, a data processing method of taking logarithms can be used to process the data of the type of connection number, the type of terminal number, and the type of user number respectively; if the number of users in the target network is less than a preset number, at this time, a data processing method of linear normalization or standard deviation normalization can be used to process the data of the type of connection number, the type of terminal number, and the type of user number respectively.

[0074] The formula for linear normalization is as follows:

[0075]

[0076] Among them, x in is the original data value; x out is the normalized data value; x0 is the maximum value supported by the dimension.

[0077] The formula for standard deviation normalization is as follows:

[0078]

[0079] Among them, x in is the original data value; x out is the normalized data value; x mean is the mean of data of the same dimension; x std is the standard deviation of data of the same dimension.

[0080] For data of the status data type, there are only two cases: yes and no, so unique hot encoding (also called one-hot encoding) can be used to process it.

[0081] Step 302, obtaining characteristic data according to the first characteristic data.

[0082] In a possible implementation manner, the first characteristic data is directly used as the characteristic data.

[0083] In another possible implementation, the first characteristic data is filled with a default value to obtain the second characteristic data, and the second characteristic data is used as the characteristic data. The first characteristic data is filled with a default value, which can be filled randomly or in a corresponding default value filling manner according to the type of data.

[0084] In this embodiment, by processing each type of data in the plurality of historical data using a corresponding type of data processing method, characteristic data is obtained, which can reduce the processing time of the bandwidth prediction model for the characteristic data, thereby improving the bandwidth prediction efficiency.

[0085] In one embodiment, if Figure 4 As shown, another bandwidth prediction method is provided. The first characteristic data is filled with a default value to obtain the second characteristic data; the second characteristic data is used as the characteristic data, including:

[0086] Step 401, fill each type of data in the first characteristic data with a default value filling method of the corresponding type to obtain the second characteristic data; wherein the default value filling method is determined according to the data processing method corresponding to each type of data; the default value filling method includes the observation value filling method, the mean filling method, the median filling method and the mode filling method.

[0087] Step 402: Use the second characteristic data as characteristic data.

[0088] Among them, the observation value filling method refers to filling according to the mean of the data at the time points before and after the default time point.

[0089] Optionally, each type of data in the first characteristic data is filled with a default value filling method of a corresponding type. Specifically, for each type of data, the default value filling method corresponding to the type of data is determined according to the data processing method of the type of data. For example, for data processed by a data processing method of taking logarithms or linear normalization, the observation value filling method can be selected for filling; for data processed by a data processing method of standard deviation normalization, any one of the mean filling method, median filling method and mode filling method can be selected for filling. Preferably, for data processed by a data processing method of standard deviation normalization, the mean filling method is selected for filling.

[0090] In this embodiment, each type of data in the first characteristic data is filled with a default value of the corresponding type, so that the obtained characteristic data is more in line with the actual situation, and thus the bandwidth prediction result obtained by the bandwidth prediction model based on the characteristic data is more accurate.

[0091] In one embodiment, the method further comprises:

[0092] Step 501, obtaining multiple sample historical data of the target network; each sample historical data includes sample total bandwidth information, sample bandwidth information corresponding to different applications, and sample bandwidth information corresponding to different users.

[0093] Optionally, the sample history data may also include at least one of the total number of sample terminals of different types of terminals, the total number of sample concurrent users, the total number of sample concurrent connections, the number of sample connections corresponding to different applications, the number of sample terminals of different users using different types of terminals, and the sample status data corresponding to the sampling time point.

[0094] Among them, the sample historical data can be large sample data, such as obtaining the initial historical data of the target network for several months, a year or many years, and then recording and collating these initial historical data according to a preset time interval as a sampling time point to obtain multiple sample historical data. The specific recording and collating method can refer to the above Tables 1 to 4.

[0095] Step 502: Process multiple sample historical data to obtain sample characteristic data.

[0096] The data processing process for multiple sample historical data can refer to the above-mentioned data processing process for multiple historical data, which will not be repeated here.

[0097] Step 503: Train the model to be trained according to the sample feature data, and obtain a bandwidth prediction model after the training is completed.

[0098] The model to be trained may be a time series prediction model, specifically one of ARIMA model, CNN, GRU, VAR model, LSTM, Prophet model, random forest, multivariate deep learning, Transformer and MTS-Mixers, etc., or a hybrid model obtained by combining multiple models.

[0099] In a possible embodiment, the model to be trained includes multiple sub-models to be trained, and each sub-model to be trained is trained with sample feature data of a corresponding type. For example, sub-model A to be trained is trained according to the bandwidth consumed by user A using video calls at different time points; sub-model B to be trained is trained according to the bandwidth consumed by video conferences at different time points.

[0100] In another possible embodiment, the model to be trained is a complete model, which can be directly trained using sample feature data. During the training process, the results of the model output can be cross-validated to obtain an optimal bandwidth prediction model.

[0101] In addition, during the training process, the sample feature data can be divided into training data and test data. The training data is used to train the training model, and the test data is used to test the trained bandwidth prediction model. When the bandwidth prediction model passes the test, it can be deployed in the target network to realize the network bandwidth prediction function of the target network.

[0102] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0103] Based on the same inventive concept, the embodiment of the present application also provides a network bandwidth prediction device for implementing the network bandwidth prediction method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more network bandwidth prediction device embodiments provided below can refer to the limitations of the network bandwidth prediction method above, and will not be repeated here.

[0104] In an exemplary embodiment, Figure 5 As shown, a network bandwidth prediction device is provided, and the network bandwidth prediction device 500 includes: an acquisition module 501, a first determination module 502, and a second determination module 503, wherein:

[0105] The acquisition module 501 is used to acquire multiple historical data of the target network. The multiple historical data are related data corresponding to different sampling time points of the target network within a preset period. Each historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users.

[0106] The first determination module 502 is used to process a plurality of historical data to obtain characteristic data.

[0107] The second determination module 503 is used to input the characteristic data into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

[0108] In one of the embodiments, the historical data also includes at least one of the total number of terminals of different types, the total number of concurrent users, the total number of concurrent connections, the number of connections corresponding to different applications, the number of terminals of different types used by different users, and status data corresponding to a sampling time point.

[0109] In one embodiment, the first determination module 502 is specifically used to process each type of data in multiple historical data using a corresponding type of data processing method to obtain first feature data; the data processing method includes taking logarithm, linear normalization, standard deviation normalization and one-hot encoding; based on the first feature data, feature data is obtained.

[0110] In one embodiment, the first determining module 502 is specifically configured to fill the first characteristic data with a default value to obtain the second characteristic data; and use the second characteristic data as the characteristic data.

[0111] In one embodiment, the first determination module 502 is specifically used to fill each type of data in the first characteristic data with a corresponding type of default value filling method to obtain the second characteristic data; wherein the default value filling method is determined according to the data processing method corresponding to each type of data; the default value filling method includes the observation value filling method, the mean filling method, the median filling method and the mode filling method.

[0112] In one of the embodiments, the device also includes a training module for obtaining multiple sample historical data of the target network; each sample historical data includes sample total bandwidth information, sample bandwidth information corresponding to different applications, and sample bandwidth information corresponding to different users; data processing is performed on the multiple sample historical data to obtain sample feature data; the training model is trained according to the sample feature data, and a bandwidth prediction model is obtained after the training is completed.

[0113] Each module in the above network bandwidth prediction device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0114] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical data, feature data, etc. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a network bandwidth prediction method is implemented.

[0115] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0116] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any method in the above method embodiments are implemented.

[0117] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps described in any one of the above method embodiments are implemented.

[0118] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of any one of the methods in the above method embodiments when executed by a processor.

[0119] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0120] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0121] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0122] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A network bandwidth prediction method, characterized in that: The method comprises: Acquire multiple historical data of the target network, wherein the multiple historical data are relevant data corresponding to different sampling time points of the target network within a preset period, and each of the historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users; Processing the plurality of historical data to obtain characteristic data; The characteristic data is input into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

2. The method according to claim 1, characterized in that The historical data also includes at least one of the total number of terminals of different types, the total number of concurrent users, the total number of concurrent connections, the number of connections corresponding to different applications, the number of terminals of different types used by different users, and status data corresponding to a sampling time point.

3. The method according to claim 1 or 2, characterized in that: The processing of the plurality of historical data to obtain characteristic data includes: Processing each type of data in the plurality of historical data using a corresponding type of data processing method to obtain first feature data; the data processing method includes taking logarithms, linear normalization, standard deviation normalization, and one-hot encoding; The characteristic data is obtained according to the first characteristic data.

4. The method according to claim 3, characterized in that The obtaining the characteristic data according to the first characteristic data includes: Filling the first characteristic data with a default value to obtain second characteristic data; The second feature data is used as the feature data.

5. The method according to claim 4, characterized in that The step of filling the first characteristic data with a default value to obtain the second characteristic data includes: Each type of data in the first characteristic data is filled with a corresponding type of default value filling method to obtain the second characteristic data; wherein the default value filling method is determined according to the data processing method corresponding to each type of data; the default value filling method includes observation value filling method, mean filling method, median filling method and mode filling method.

6. The method according to claim 1, characterized in that The method further comprises: Acquire multiple sample historical data of the target network; each of the sample historical data includes sample total bandwidth information, sample bandwidth information corresponding to different applications, and sample bandwidth information corresponding to different users; Processing the plurality of sample historical data to obtain sample characteristic data; The model to be trained is trained according to the sample feature data, and the bandwidth prediction model is obtained after the training is completed.

7. A network bandwidth prediction device, characterized in that: The device comprises: An acquisition module, used to acquire multiple historical data of a target network, wherein the multiple historical data are relevant data corresponding to different sampling time points of the target network within a preset period, and each of the historical data includes total bandwidth information, bandwidth information corresponding to different applications, and bandwidth information corresponding to different users; A first determination module is used to process the plurality of historical data to obtain characteristic data; The second determination module is used to input the characteristic data into a pre-trained bandwidth prediction model to obtain a bandwidth prediction result output by the bandwidth prediction model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

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

Images