Model training method, flow prediction method, device, equipment, medium and product

Abstract

The invention relates to the technical field of computers, in particular to a model training method and device, a traffic prediction method and device, equipment, a medium and a product, and the method comprises the steps: training a model through employing a last update result of historical traffic data, and obtaining a prediction result of the model; under the condition that the prediction result is greater than a threshold value, determining a current updating result based on the last updating result and the influence factor; under the condition that a prediction result obtained based on the current updating result is greater than a threshold value, updating a last updating result as the current updating result until the prediction result is less than or equal to the threshold value and the model is converged; and performing traffic prediction based on the obtained final convergence model. According to the method, the historical traffic data is updated by using the influence factor, the final convergence model is obtained, and the influence of a real-time operator strategy in a network on traffic prediction is considered, so that the prediction result can better conform to the real situation of the network, and the prediction accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a model training method, a traffic prediction method, a device, a equipment, a medium and a product. Background Art

[0002] With the development of Internet technology, network traffic prediction technology is also constantly improving and evolving. The importance of network traffic prediction lies in that it can help network operators, enterprises or service providers better understand and predict user behavior, thereby optimizing resource allocation and improving service quality. Therefore, the focus of network traffic prediction lies in accuracy.

[0003] There are many algorithms for traffic prediction. In order to improve the accuracy of prediction, various algorithms also have many optimization methods for themselves, such as accelerating the model training process through data preprocessing, improving the stability and generalization ability of the model, or accelerating the convergence speed of the model by optimizing model parameters and enhancing the generalization ability of the network. However, these existing optimization methods do not take into account the impact of real-time updated traffic scheduling or management strategies on the prediction results in the real network environment, which may cause the prediction results to be inconsistent with the actual situation of the current network, so it is difficult to guarantee the accuracy of the prediction. Summary of the invention

[0004] The present application is proposed in view of the above-mentioned problems, and the present application provides a model training method, traffic prediction method, device, equipment, medium and product.

[0005] According to one aspect of the present application, a model training method for traffic prediction is provided, comprising:

[0006] The model is trained using the last update result of the historical traffic data to obtain a prediction result of the model; when the last update result is the first update result, the last update result is obtained based on the historical traffic data and the current influencing factor; the influencing factor is the operator policy that affects the traffic usage of the network; the prediction result is the traffic usage of the network at a future set time, and the future set time is later than the generation time of the historical traffic data;

[0007] When the prediction result is greater than a threshold, determining a current update result of the historical traffic data based on a last update result of the historical traffic data and the influencing factor;

[0008] When the prediction result of the model obtained based on the current update result is greater than the threshold, the last update result is updated to the current update result, and the step of training the model using the last update result of the historical traffic data to obtain the prediction result of the model is returned until the prediction result of the model is less than or equal to the threshold and the model converges to obtain a final converged model.

[0009] In addition, the model training method for traffic prediction according to one aspect of the present application also includes:

[0010] Before obtaining the model's prediction results based on the last update of historical traffic data, it also includes:

[0011] Get original historical traffic data;

[0012] The original historical traffic data are grouped according to preset data attributes to obtain multiple groups of the historical traffic data, wherein the data attributes are the geographical area to which the traffic data belongs, the length of the traffic data, or the resource type of the traffic data.

[0013] In addition, the model training method for traffic prediction according to one aspect of the present application also includes:

[0014] Get raw historical traffic data, including:

[0015] Based on the preset maximum future setting time, original historical traffic data of a historical time period is acquired, and the historical time period is the same in length as the maximum future setting time.

[0016] According to another aspect of the present application, a flow prediction method is provided, comprising:

[0017] Obtain the traffic data to be predicted in the historical time period;

[0018] The final convergence model obtained above is used to predict the traffic data to be predicted, and a prediction result of a future set time required for the traffic data to be predicted is obtained.

[0019] In addition, the flow prediction method according to another aspect of the present application further includes:

[0020] The final convergence model obtained above is used to predict the traffic data to be predicted, including:

[0021] According to preset data attributes, the traffic data to be predicted are grouped to obtain multiple data groups; and data attributes of the historical traffic data used to train the final convergence model are obtained;

[0022] A target data group that is consistent with the data attributes of the historical traffic data is selected from the multiple data groups, and traffic prediction is performed on the target data group using the final convergence model.

[0023] In addition, the flow prediction method according to another aspect of the present application further includes:

[0024] Using the final converged model, flow prediction is performed on the target data group, including:

[0025] When all the final convergence models are obtained, the last prediction result of each final convergence model in the training phase is obtained, and the future setting time corresponding to each final convergence model is different;

[0026] Selecting n target prediction results with the highest accuracy from the multiple last prediction results, and using the final convergence model corresponding to the target prediction results as the traffic prediction model;

[0027] When the future set time required by the target data group is consistent with the future set time corresponding to the traffic prediction model, the traffic prediction model is used to perform traffic prediction on the target data group.

[0028] According to another aspect of the present application, a flow prediction device is provided, comprising:

[0029] A training module, used to train the model using the last update result of the historical traffic data to obtain a prediction result of the model; when the last update result is the first update result, the last update result is obtained based on the historical traffic data and a current influencing factor; the influencing factor is an operator policy that affects the traffic usage of the network;

[0030] A data updating module, configured to determine a current update result of the historical traffic data based on a last update result of the historical traffic data and the influencing factor when the prediction result is greater than a threshold;

[0031] A training update module, used for updating the last update result to the current update result when the prediction result of the model obtained based on the current update result is greater than the threshold, and returning to execute the step of training the model using the last update result of the historical traffic data to obtain the prediction result of the model, until the prediction result of the model is less than or equal to the threshold and the model converges to obtain a final converged model;

[0032] An acquisition module is used to obtain traffic data to be predicted in a historical time period;

[0033] The prediction module is used to use the final convergence model obtained above to predict the traffic data to be predicted, and obtain the prediction result of the future set time required for the traffic data to be predicted.

[0034] According to another aspect of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method of the above-mentioned another aspect.

[0035] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of the above-mentioned another aspect is implemented.

[0036] According to another aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method of the above-mentioned another aspect is implemented.

[0037] As will be described in detail below, according to a traffic prediction method, apparatus, device, storage medium and program product of an embodiment of the present application, the comparison result between the prediction result and the threshold is used as a trigger condition for calling the influencing factor, the historical traffic data is updated using the influencing factor, and the model is trained with the updated result of the historical traffic data to obtain the final converged model. The impact of the real-time operator strategy in the network on the traffic prediction is taken into account. When the final converged model is used for traffic prediction, the traffic prediction result can be made more consistent with the actual situation of the network, which is conducive to improving the accuracy of traffic prediction.

[0038] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0040] Figure 1 is a flowchart illustrating the application of a model training method for traffic prediction according to an embodiment of the present application.

[0041] Figure 2 It is a flow chart illustrating the application of the traffic prediction method according to an embodiment of the present application.

[0042] Figure 3is another flow chart illustrating the application of the traffic prediction method according to an embodiment of the present application.

[0043] Figure 4 It is a module calling logic diagram illustrating the application of the traffic prediction method according to the embodiment of the present application.

[0044] Figure 5 It is a schematic diagram illustrating the structure of a traffic prediction device according to an embodiment of the present application.

[0045] Figure 6 It is a schematic diagram illustrating the structure of a computer device according to an embodiment of the present application.

[0046] Figure 7 is a schematic diagram illustrating a computer program product according to an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application more obvious, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0048] With the development of Internet technology, network traffic prediction technology is also constantly improving and evolving. The importance of network traffic prediction lies in that it can help network operators, enterprises or service providers better understand and predict user behavior, thereby optimizing resource allocation and improving service quality. Therefore, the focus of network traffic prediction lies in accuracy.

[0049] There are many algorithms for traffic prediction. In order to improve the accuracy of prediction, various algorithms also have many optimization methods for themselves, such as accelerating the model training process through data preprocessing, improving the stability and generalization ability of the model, or accelerating the convergence speed of the model by optimizing model parameters and enhancing the generalization ability of the network. However, these existing optimization methods do not take into account the impact of real-time updated traffic scheduling or management strategies on the prediction results in the real network environment, which may cause the prediction results to be inconsistent with the actual situation of the current network, so it is difficult to guarantee the accuracy of the prediction.

[0050] In the above, a model training method, traffic prediction method, apparatus, device, medium and product according to an embodiment of the present application are described with reference to the accompanying drawings. The comparison result between the prediction result and the threshold is used as a trigger condition for calling the influence factor, the historical traffic data is updated using the influence factor, and the model is trained with the updated result of the historical traffic data to obtain the final converged model. The impact of the real-time operator strategy in the network on the traffic prediction is taken into account. When the final converged model is used for traffic prediction, the traffic prediction result can be made more consistent with the actual situation of the network, which is conducive to improving the accuracy of traffic prediction.

[0051] To facilitate understanding of this embodiment, a model training method for traffic prediction disclosed in the embodiment of the present application is first introduced in detail. The execution subject of the model training method provided in the embodiment of the present application is generally a computer device with certain computing capabilities, and the computer device includes, for example: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (Personal DiTital Assistant, PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the model training method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0052] like Figure 1 As shown, it is a flowchart of a model training method for traffic prediction provided in an embodiment of the present application, and the method includes S101-S103:

[0053] S101: Use the last update result of the historical traffic data to train the model to obtain the prediction result of the model.

[0054] The historical traffic data refers to the traffic data collected in the historical time period, such as the traffic data in the past 12 months, which can be obtained from the base station, server or cloud platform; the model is used for traffic prediction, such as the SVR model. The prediction result is the traffic usage of the network at a set time in the future, and the set time in the future is later than the generation time of the historical traffic data, such as the next 1 month, the next 3 months, etc. The indicator represented by the prediction result is the same as the threshold. Assuming that the indicator represented by the threshold is the link bandwidth utilization, the prediction result also represents the link bandwidth utilization.

[0055] When the last update result is the first update result, the last update result is obtained based on historical traffic data and current influencing factors, where the influencing factors are operator policies that affect the network's traffic usage, such as traffic scheduling policies with real-time update features, data management policies, etc.

[0056] Preferably, this embodiment further includes the following steps before S101:

[0057] (1) Obtain original historical traffic data.

[0058] Specifically, based on the preset maximum future setting time, the original historical traffic data of the historical time period is obtained, wherein the historical time period is the same as the maximum future setting time. For example, the preset future setting time is the next 1 month, 2 months...12 months, and the maximum future setting time is the next 12 months, and the original historical traffic data of the past 12 months is obtained. In this embodiment, the original historical traffic data is preferably day-granular data, that is, the original historical traffic data of the past 12 months collected with "day" as the time unit.

[0059] (2) According to preset data attributes, the original historical traffic data is grouped to obtain multiple groups of historical traffic data.

[0060] In this embodiment, the data attributes are preferably as follows:

[0061] 1) The geographical area to which the traffic data belongs: for example, provinces, cities, or districts within a city.

[0062] 2) Resource type of traffic data: for example, traffic data of device ports, traffic data of links, etc.

[0063] 3) Length of traffic data: The traffic data of some resource indicators in the network may not be monitored all the time, or the traffic data of some resource indicators may only be monitored periodically due to other operator policies, so the monitoring time of traffic data (i.e., the length of traffic data) may be different. For example, the traffic data of port A has been monitored for 12 months in the past 12 months, and the traffic data of port B has been monitored for 6 months in the past 12 months.

[0064] The embodiment of the present application sets data attributes in combination with the characteristics of the network itself, classifies the original historical traffic data, provides more accurate sample data for model training, and is conducive to improving the accuracy of prediction. Specifically, according to the above three data attributes, the original historical traffic data is divided into three groups to obtain three groups of historical traffic data, and S101 uses each group of historical traffic data to train the model in turn.

[0065] S102: When the prediction result is greater than the threshold, the current update result of the historical traffic data is determined based on the last update result of the historical traffic data, the influencing factor and the threshold.

[0066] Among them, the indicator represented by the threshold is related to the influencing factor. Assuming that the indicator represented by the threshold is the link bandwidth utilization, the algorithm of the influencing factor can be combined with the historical traffic data related to the link bandwidth of the entire network for calculation to obtain a batch of new traffic data (i.e., the current update result). Under this batch of new traffic data, the link bandwidth utilization of the entire network can reach a balanced state and does not exceed the threshold.

[0067] S103: When the prediction result of the model obtained based on the current update result is greater than the threshold, the last update result is updated as the current update result, and the process returns to S101 until the prediction result of the model is less than or equal to the threshold and the model converges to obtain a final converged model.

[0068] Among them, assuming that the prediction result of the model is less than or equal to the threshold, but the model has not converged, the obtained prediction result will no longer be compared with the threshold in the subsequent training stage until the model converges and the final converged model is obtained. Or, assuming that the model has converged, but the prediction result of the model is still greater than the threshold, then continue to train the model until the prediction result is less than or equal to the threshold and the final converged model is obtained.

[0069] like Figure 2 As shown, it is a flow chart of a traffic prediction method provided in an embodiment of the present application, and the method includes S201-S202:

[0070] S201: Obtain traffic data to be predicted in a historical time period.

[0071] Among them, the traffic data to be predicted is the sample historical traffic data used when applying the final convergence model for traffic prediction, such as the historical traffic data of the past 12 months. In this embodiment, the traffic data to be predicted is preferably daily granularity data, that is, the historical traffic data of the past 12 months collected with "day" as the time unit.

[0072] S202: The final converged model obtained in the above embodiment is used to predict the traffic data to be predicted, and a prediction result of a future set time required for the traffic data to be predicted is obtained.

[0073] Specifically, the traffic data to be predicted is grouped according to preset data attributes to obtain multiple data groups; and the data attributes of the historical traffic data used to train the final convergence model are obtained.

[0074] A target data group that is consistent with the data attributes of historical traffic data is selected from multiple data groups, and the traffic flow is predicted for the target data group using the final converged model.

[0075] In combination with the three data attributes of the above embodiment, the traffic data to be predicted are grouped to obtain three data groups. Assuming that the data attribute of the historical traffic data used to train the traffic prediction model is the resource type, a target data group with the attribute of the resource type is selected from the three data groups. By selecting the final convergence model with the same data attribute for each data group, the accuracy of traffic prediction is improved.

[0076] Specifically, S202 includes steps 11-13:

[0077] Step 11: When all the final converged models are obtained, obtain the last prediction result of each final converged model in the training phase.

[0078] Among them, the future setting time corresponding to each final convergence model is different. According to the number of preset future setting times, the model is trained using historical traffic data to obtain the same number of final convergence models. Assuming that the preset future setting times are 1 month, 2 months, 3 months...12 months in the future, and the number is 12, then 12 final convergence models will be obtained. For example, the first final convergence model is used to predict the traffic data for the next month, and the third final convergence model is used to predict the traffic data for the next 3 months.

[0079] Step 12: Select n target prediction results with the highest accuracy from the multiple last prediction results, and use the final converged model corresponding to the target prediction results as the traffic prediction model.

[0080] Among them, the prediction results output by the model each time include accuracy, which is used to indicate the accuracy of the prediction results this time. The n models with the highest accuracy are selected from the 12 final convergence models as traffic prediction models. n is a positive integer, and the specific value can be selected according to actual needs. In this embodiment, it is assumed that n=2, and the two final convergence models with the highest accuracy are respectively predicted for the next 7 months and 12 months. Then there are two traffic prediction models. The first traffic prediction model is used to predict traffic data within the next 7 months, and the second traffic prediction model is used to predict traffic data within the next 12 months.

[0081] Step 13: When the future setting time required by the target data group is consistent with the future setting time corresponding to the flow prediction model, the flow prediction model is used to perform flow prediction on the target data group.

[0082] Specifically, assuming that the future setting time of the target data group demand is the next 7 months, then the first traffic prediction model can be selected, and assuming that the future setting time of the target data group demand is the next 12 months, then the second traffic prediction model can be selected. In the preferred embodiment of this invention, in actual application, the future setting time of the target data group demand is inconsistent with the future setting time corresponding to the traffic prediction model, then the corresponding final convergence model can be selected according to the future setting time of the target data group demand for traffic prediction. For example, if the future setting time of the target data group demand is the next 6 months, then the sixth final convergence model (for predicting traffic data for the next 6 months) can be selected.

[0083] like Figure 3 As shown, it is another flow chart of the traffic prediction method provided in the embodiment of the present application, and the method includes S301-S309:

[0084] S301: Obtain original historical traffic data.

[0085] Specifically, based on the preset maximum future setting time, the original historical traffic data of the historical time period is obtained, wherein the historical time period is the same length as the maximum future setting time. For example, the preset future setting times are the next 1 month, 2 months...12 months, and the maximum future setting time is the next 12 months. In this way, the original historical traffic data of the past 12 months is obtained, wherein the day granularity represents the original historical traffic data collected with "day" as the time unit.

[0086] S302: Data storage.

[0087] The collected original historical traffic data with daily granularity for 12 months is stored in the storage unit as sample data used in the model training phase.

[0088] S303: Data processing.

[0089] The original historical traffic data is cleaned and preprocessed to delete discontinuous, missing or abnormal values, and to complete the data with minor defects, or to change the time node and move the subsequent data forward as a whole to retain the original form of the data.

[0090] S304: Grouping the original historical traffic data according to preset data attributes to obtain multiple groups of historical traffic data.

[0091] In this embodiment, the data attributes are preferably as follows:

[0092] 1) The geographical area to which the traffic data belongs: for example, provinces, cities, or districts within a city.

[0093] 2) Resource type: for example, traffic data of device ports, traffic data of links, etc.

[0094] 3) Length of traffic data: The traffic data of some resource indicators in the network may not be monitored all the time, or the traffic data of some resource indicators may only be monitored periodically due to other operator policies, so the monitoring time of traffic data (i.e., the length of traffic data) may be different. For example, the traffic data of port A has been monitored for 12 months in the past 12 months, and the traffic data of port B has been monitored for 6 months in the past 12 months.

[0095] The data attributes were set according to the characteristics of the network, and the original historical traffic data was divided into three categories. Each category of historical traffic data was subjected to independent model training and model prediction.

[0096] S305: Use historical traffic data to train the model.

[0097] Specifically, S305 includes steps 31-33:

[0098] Step 31: Use the last updated result of the historical traffic data to train the model and obtain the prediction result of the model.

[0099] The historical traffic data is the traffic data collected in the past 12 months, and the data attribute is, for example, the resource type, which can be obtained from the base station, server, or cloud platform. The model can be a SVR model. The indicator represented by the prediction result is the same as the threshold. For example, the indicator represented by the threshold is the link bandwidth utilization, and the prediction result also represents the link bandwidth utilization.

[0100] In the case where the last update result is the first update result, the last update result is obtained based on historical traffic data and current impact factors, where the impact factors are operator policies that affect the network traffic usage, such as traffic scheduling policies with real-time update characteristics, data control policies, etc. Among them, the indicator represented by the threshold is related to the impact factor. Assuming that the indicator represented by the threshold is link bandwidth utilization, the algorithm of the impact factor can be combined with the historical traffic data related to the link bandwidth of the entire network for calculation, and a batch of new traffic data can be obtained. Under this batch of new traffic data, the link bandwidth utilization of the entire network can be balanced and does not exceed the threshold.

[0101] Step 32: When the prediction result is greater than the threshold, the current update result of the historical traffic data is determined based on the last update result of the historical traffic data, the influencing factor and the threshold.

[0102] Among them, the indicator represented by the threshold is related to the influencing factor. Assuming that the indicator represented by the threshold is the link bandwidth utilization, the algorithm of the influencing factor can be combined with the historical traffic data related to the link bandwidth of the entire network for calculation to obtain a batch of new traffic data (i.e., the current update result). Under this batch of new traffic data, the link bandwidth utilization of the entire network can reach a balanced state and does not exceed the threshold.

[0103] Step 33: When the prediction result of the model obtained based on the current update result is greater than the threshold, update the last update result to the current update result, and return to execute step 31 until the prediction result of the model is less than or equal to the threshold and the model converges to obtain the final converged model.

[0104] S306: Obtain the traffic data to be predicted in the historical time period.

[0105] Among them, the traffic data to be predicted is the sample historical traffic data used when applying the final convergence model for traffic prediction, such as the historical traffic data of the past 12 months. In this embodiment, the traffic data to be predicted is preferably daily granularity data, that is, the historical traffic data of the past 12 months collected with "day" as the time unit.

[0106] S307: using the final convergence model to predict the traffic data to be predicted, and obtaining a prediction result of the future set time required for the traffic data to be predicted.

[0107] Specifically, steps 34-38 are included:

[0108] Step 34: grouping the traffic data to be predicted according to preset data attributes to obtain multiple data groups; and obtaining data attributes of the historical traffic data used to train the final convergence model.

[0109] Step 35: Select a target data group from multiple data groups that has data attributes consistent with the historical traffic data.

[0110] Combined with the three data attributes of the above embodiment, the traffic data to be predicted is grouped to obtain three data groups. Assuming that the data attribute of the historical traffic data used to train the traffic prediction model is the resource type, then the target data group with the attribute of the resource type is selected from the three data groups.

[0111] Step 36: When all the final converged models are obtained, obtain the last prediction result of each final converged model in the training phase.

[0112] Among them, the future setting time corresponding to each final convergence model is different. According to the number of preset future setting times, the model is trained using historical traffic data to obtain the same number of final convergence models. Assuming that the preset future setting times are 1 month, 2 months, 3 months...12 months in the future, and the number is 12, then this set of historical traffic data with the attribute of resource type will obtain 12 final convergence models. For example, the first final convergence model is used to predict the traffic data of the next month, and the second final convergence model is used to predict the traffic data of the next 2 months.

[0113] Step 37: Select n target prediction results with the highest accuracy from the multiple last prediction results, and use the final converged model corresponding to the target prediction results as the traffic prediction model.

[0114] Among them, the prediction results output by the model each time include accuracy, which is used to indicate the accuracy of the prediction results this time. The n models with the highest accuracy are selected from the 12 final convergence models as traffic prediction models. n is a positive integer, and the specific value can be selected according to actual needs. In this embodiment, it is assumed that n=2, and the two final convergence models with the highest accuracy are respectively predicted for the next 8 months and 10 months. Then, there are two traffic prediction models corresponding to this set of historical traffic data with the attribute of resource type. The first traffic prediction model is used to predict the traffic data for the next 8 months, and the second traffic prediction model is used to predict the traffic data for the next 10 months.

[0115] Step 38: When the future setting time required by the target data group is consistent with the future setting time corresponding to the flow prediction model, the flow prediction model is used to perform flow prediction on the target data group.

[0116] Specifically, assuming that the future setting time of the target data group demand is the next 7 months, then the first traffic prediction model can be selected, and assuming that the future setting time of the target data group demand is the next 12 months, then the second traffic prediction model can be selected. In the preferred embodiment of this invention, in actual application, the future setting time of the target data group demand is inconsistent with the future setting time corresponding to the traffic prediction model, then the corresponding final convergence model can be selected according to the future setting time of the target data group demand for traffic prediction. For example, if the future setting time of the target data group demand is the next 8 months, then the 8th final convergence model (for predicting traffic data for the next 8 months) can be selected.

[0117] S308: Results display.

[0118] The traffic prediction results obtained for each data group are presented to the user in a visual manner. Various data indicators and analysis results of the traffic prediction results can be displayed in charts and other forms. Users can query, filter and sort the predicted traffic data through an interactive interface.

[0119] S309: Optimize traffic strategy.

[0120] Based on the traffic prediction results, a network traffic optimization strategy is generated, such as bandwidth adjustment, resource allocation, etc. Preferably, the present embodiment can also monitor and alarm the network performance, so as to respond to changes in network traffic in a timely manner.

[0121] like Figure 4 As shown, it is a module call logic diagram of the traffic prediction method provided in the embodiment of the present application. According to the background of digital twins, the embodiment of the present application deploys various unit modules related to the traffic prediction method in the digital twin layer and application interaction layer of the digital twin, specifically including:

[0122] Data collection unit: obtains raw historical traffic data with daily granularity for the past 12 months.

[0123] Data storage unit: The collected original historical traffic data with daily granularity for 12 months is stored in the storage unit as sample data used in the model training phase.

[0124] Data processing unit: Clean and pre-process the original historical traffic data to delete discontinuous, missing or abnormal values, and fill in the data with minor defects, or change the time node to move the subsequent data forward as a whole to retain the original form of the data.

[0125] Data classification unit: according to preset data attributes, the original historical traffic data is grouped to obtain x groups of historical traffic data.

[0126] In this embodiment, the data attributes are preferably as follows:

[0127] 1) The geographical area to which the traffic data belongs: for example, provinces, cities, or districts within a city.

[0128] 2) Resource type: for example, traffic data of device ports, traffic data of links, etc.

[0129] 3) Length of traffic data: The traffic data of some resource indicators in the network may not be monitored all the time, or the traffic data of some resource indicators may only be monitored periodically due to other operator policies, so the monitoring time of traffic data (i.e., the length of traffic data) may be different. For example, the traffic data of port A has been monitored for 12 months in the past 12 months, and the traffic data of port B has been monitored for 6 months in the past 12 months.

[0130] Model training unit: Based on the historical traffic data of each group, each group of historical traffic data is trained separately, and finally the traffic prediction model of each group of historical traffic data is obtained. Different traffic prediction models only predict data groups with the same data attributes. The training stage of the SVR model specifically includes steps 41-45:

[0131] Step 41: Use the last update result of the historical traffic data to train the model and obtain the prediction result of the model.

[0132] In this embodiment, preferably, the indicator represented by the threshold is link bandwidth utilization, and the prediction result also represents link bandwidth utilization.

[0133] In the case where the last update result is the first update result, the last update result is obtained based on historical traffic data and current impact factors, where the impact factors are operator policies that affect the network traffic usage, such as traffic scheduling policies with real-time update characteristics, data control policies, etc. Among them, the indicator represented by the threshold is related to the impact factor. Assuming that the indicator represented by the threshold is link bandwidth utilization, the algorithm of the impact factor can be combined with the historical traffic data related to the link bandwidth of the entire network for calculation, and a batch of new traffic data can be obtained. Under this batch of new traffic data, the link bandwidth utilization of the entire network can be balanced and does not exceed the threshold.

[0134] Step 42: When the prediction result is greater than the threshold, the last update result of the historical traffic data is calculated based on the impact factor to obtain updated traffic data;

[0135] Based on the indicators represented by thresholds, the indicator values ​​are calculated using updated traffic data;

[0136] When the indicator value is less than or equal to the threshold, the updated traffic data is used as the current update result of the historical traffic data.

[0137] Step 43: When the prediction result of the model obtained based on the current update result is greater than the threshold, update the last update result to the current update result, and return to execute step 21 until the prediction result of the model is less than or equal to the threshold and the model converges to obtain the final converged model.

[0138] Step 44: When all the final converged models are obtained, the last prediction result of each final converged model in the training phase is obtained.

[0139] Among them, the future setting time corresponding to each final convergence model is different. According to the number of preset future setting times, the model is trained using historical traffic data to obtain the same number of final convergence models. Assuming that the preset future setting times are 1 month, 2 months, 3 months...12 months in the future, and the number is 12, then this set of historical traffic data with the attribute of resource type will obtain 12 final convergence models. For example, the first final convergence model is used to predict the traffic data of the next month, and the second final convergence model is used to predict the traffic data of the next 2 months.

[0140] Step 45: Select n target prediction results with the highest accuracy from the multiple last prediction results, and use the final converged model corresponding to the target prediction results as the traffic prediction model.

[0141] Among them, the prediction results output by the model each time include accuracy, which is used to indicate the accuracy of the prediction results this time. The n models with the highest accuracy are selected from the 12 final convergence models as traffic prediction models. n is a positive integer, and the specific value can be selected according to actual needs. In this embodiment, it is assumed that n=2, and the two final convergence models with the highest accuracy are respectively predicted for the next 8 months and 10 months. Then, there are two traffic prediction models corresponding to this set of historical traffic data with the attribute of resource type. The first traffic prediction model is used to predict the traffic data for the next 8 months, and the second traffic prediction model is used to predict the traffic data for the next 10 months.

[0142] Data prediction unit: Use the obtained traffic prediction model to perform traffic prediction on the traffic data to be predicted, and obtain the prediction results of the future set time required for the traffic data to be predicted. Among them, the traffic data to be predicted is the daily granularity traffic data of the past 12 months up to the present. According to the above three data attributes, the traffic data to be predicted is grouped to obtain three data groups. Based on the number of traffic prediction models, each data group will obtain the same number of traffic prediction results. Combined with step 38, taking the data group with the attribute of resource type as an example, two groups of traffic prediction results will be predicted, which are the traffic prediction results for the next 8 months and the next 10 months.

[0143] Data display unit: The prediction results of each data group are presented to the user in a visual manner. Various data indicators and analysis results of the prediction results can be displayed in the form of charts, etc. Users can query, filter and sort the predicted traffic data through an interactive interface.

[0144] Decision response unit: based on the prediction results, generates network traffic optimization strategies, such as bandwidth adjustment, resource allocation, etc. Preferably, the present embodiment can also monitor and alarm the network performance, so as to respond to changes in network traffic in a timely manner.

[0145] According to another aspect of the embodiment of the present application, a flow prediction device is provided, such as Figure 5 As shown, the device comprises:

[0146] The training module 101 is used to train the model using the last update result of the historical traffic data to obtain the prediction result of the model; when the last update result is the first update result, the last update result is obtained based on the historical traffic data and the current influencing factor; the influencing factor is the operator policy that affects the network traffic usage, and the prediction result is the network traffic usage at a set time in the future, and the future set time is later than the generation time of the historical traffic data.

[0147] The data updating module 102 is used to determine the current update result of the historical traffic data based on the last update result of the historical traffic data and the influencing factor when the prediction result is greater than a threshold.

[0148] The training update module 103 is used to update the last update result to the current update result when the prediction result of the model obtained based on the current update result is greater than the threshold, and return to the step of training the model using the last update result of historical traffic data to obtain the prediction result of the model, until the prediction result of the model is less than or equal to the threshold and the model converges to obtain a final converged model.

[0149] Acquisition module 104, used to obtain the traffic data to be predicted in the historical time period

[0150] The prediction module 105 is used to predict the traffic data to be predicted by using the final convergence model obtained above, and obtain the prediction result of the future set time required for the traffic data to be predicted.

[0151] The flow prediction device is also used to: obtain original historical flow data before obtaining the prediction result of the model based on the last update result of the historical flow data;

[0152] The original historical traffic data are grouped according to preset data attributes to obtain multiple groups of the historical traffic data, wherein the data attributes are the geographical area to which the traffic data belongs, the length of the traffic data, or the resource type of the traffic data.

[0153] In one or more embodiments, obtaining original historical traffic data includes:

[0154] Based on the preset maximum future setting time, original historical traffic data of a historical time period is acquired, and the historical time period is the same in length as the maximum future setting time.

[0155] In one or more embodiments, the prediction module 105 is used to:

[0156] According to preset data attributes, the traffic data to be predicted are grouped to obtain multiple data groups; and data attributes of the historical traffic data used to train the final convergence model are obtained;

[0157] A target data group that is consistent with the data attributes of the historical traffic data is selected from the multiple data groups, and traffic prediction is performed on the target data group using the final convergence model.

[0158] In one or more embodiments, using the final converged model to perform flow prediction on the target data group includes:

[0159] When all the final convergence models are obtained, the last prediction result of each final convergence model in the training phase is obtained, and the future setting time corresponding to each final convergence model is different;

[0160] Selecting n target prediction results with the highest accuracy from the multiple last prediction results, and using the final convergence model corresponding to the target prediction results as the traffic prediction model;

[0161] When the future set time required by the target data group is consistent with the future set time corresponding to the traffic prediction model, the traffic prediction model is used to perform traffic prediction on the target data group.

[0162] The traffic prediction device provided in the embodiment of the present application and the traffic prediction method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0163] The present application also provides a computer device to execute the above-mentioned traffic prediction method. Figure 6 It shows a schematic diagram of a computer device provided by some embodiments of the present application. Figure 6 As shown, the computer device 8 includes: a processor 800, a memory 801, a bus 802 and a communication interface 803, and the processor 800, the communication interface 803 and the memory 801 are connected via the bus 802; the memory 801 stores a computer program that can be run on the processor 800, and when the processor 800 runs the computer program, it executes the traffic prediction method provided in any of the aforementioned embodiments of the present application.

[0164] The memory 801 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 803 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0165] The bus 802 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 801 is used to store programs, and the processor 800 executes the program after receiving an execution instruction. The traffic prediction method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 800, or implemented by the processor 800.

[0166] The processor 800 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 800. The above processor 800 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-made programmable gate array (FPTA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 801, and the processor 800 reads the information in the memory 801 and completes the steps of the above method in combination with its hardware.

[0167] The computer device provided in the embodiment of the present application and the traffic prediction method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0168] An embodiment of the present application also provides a computer-readable storage medium corresponding to the traffic prediction method provided in the aforementioned embodiment. The computer-readable storage medium is a CD on which a computer program (i.e., a computer program product) is stored. When the computer program is run by a processor, it will execute the traffic prediction method provided in any of the aforementioned embodiments.

[0169] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0170] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the traffic prediction method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0171] The present application also provides a computer program product. Figure 7 The computer program product 600 carries a program code, namely, a computer program 601. The instructions included in the computer program 601 can be used to execute the steps of the traffic prediction method described in the above method embodiment. For details, please refer to the above method embodiment, which will not be repeated here.

[0172] The computer program product may be implemented in hardware, software or a combination thereof. In one optional embodiment, the computer program product is implemented as a computer storage medium. In another optional embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0173] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0174] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0175] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0176] It should also be noted that in the system and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0177] Various changes, substitutions, and modifications of the techniques described herein may be made without departing from the techniques of the teachings defined by the appended claims. Furthermore, the scope of the claims of this application is not limited to the specific aspects of the processes, machines, manufactures, compositions, means, methods, and actions described above. Currently existing or later to be developed processes, machines, manufactures, compositions, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects described herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions, means, methods, or actions within their scope.

[0178] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0179] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A model training method for traffic prediction, characterized in that: include: The model is trained using the last update result of the historical traffic data to obtain the model's prediction results; In the case where the last update result is the first update result, the last update result is obtained based on the historical traffic data and the current influencing factor; the influencing factor is the operator policy that affects the traffic usage of the network, and the prediction result is the traffic usage of the network at a future set time, and the future set time is later than the generation time of the historical traffic data; When the prediction result is greater than a threshold, determining a current update result of the historical traffic data based on a last update result of the historical traffic data, the influencing factor and the threshold; When the prediction result of the model obtained based on the current update result is greater than the threshold, the last update result is updated to the current update result, and the step of training the model using the last update result of the historical traffic data to obtain the prediction result of the model is returned until the prediction result of the model is less than or equal to the threshold and the model converges to obtain a final converged model.

2. The model training method for traffic prediction according to claim 1, characterized in that: Before obtaining the model's prediction results based on the last update of historical traffic data, it also includes: Get original historical traffic data; The original historical traffic data are grouped according to preset data attributes to obtain multiple groups of the historical traffic data, wherein the data attributes are the geographical area to which the traffic data belongs, the length of the traffic data, or the resource type of the traffic data.

3. The model training method for traffic prediction according to claim 2, characterized in that: Get raw historical traffic data, including: Based on the preset maximum future setting time, original historical traffic data of a historical time period is acquired, and the historical time period is the same in length as the maximum future setting time.

4. A flow prediction method, characterized in that: include: Obtain the traffic data to be predicted in the historical time period; The final convergence model described in any one of claims 1 to 3 is used to predict the traffic data to be predicted, and a prediction result of a future set time of the demand for the traffic data to be predicted is obtained.

5. The flow prediction method according to claim 4, characterized in that: Using the final convergence model obtained in claims 1-3 to predict the traffic data to be predicted includes: According to preset data attributes, the traffic data to be predicted are grouped to obtain multiple data groups; and data attributes of the historical traffic data used to train the final convergence model are obtained; A target data group that is consistent with the data attributes of the historical traffic data is selected from the multiple data groups, and traffic prediction is performed on the target data group using the final convergence model.

6. The flow prediction method according to claim 5, characterized in that: Using the final converged model, flow prediction is performed on the target data group, including: When all the final convergence models are obtained, the last prediction result of each final convergence model in the training phase is obtained, and the future setting time corresponding to each final convergence model is different; Selecting n target prediction results with the highest accuracy from the multiple last prediction results, and using the final convergence model corresponding to the target prediction results as the traffic prediction model; When the future set time required by the target data group is consistent with the future set time corresponding to the traffic prediction model, the traffic prediction model is used to perform traffic prediction on the target data group.

7. A flow prediction device, characterized in that: include: The training module is used to train the model using the last update result of the historical traffic data to obtain the prediction result of the model; In the case where the last update result is the first update result, the last update result is obtained based on the historical traffic data and the current influencing factor; the influencing factor is the operator policy that affects the traffic usage of the network; the prediction result is the traffic usage of the network at a future set time, and the future set time is later than the generation time of the historical traffic data; A data updating module, configured to determine a current update result of the historical traffic data based on a last update result of the historical traffic data and the influencing factor when the prediction result is greater than a threshold; A training update module, used for updating the last update result to the current update result when the prediction result of the model obtained based on the current update result is greater than the threshold, and returning to execute the step of training the model using the last update result of the historical traffic data to obtain the prediction result of the model, until the prediction result of the model is less than or equal to the threshold and the model converges to obtain a final converged model; An acquisition module is used to obtain traffic data to be predicted in a historical time period; A prediction module is used to use the final convergence model described in any one of claims 1-3 to predict the traffic data to be predicted, and obtain a prediction result of a future set time for the demand of the traffic data to be predicted.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 4 to 6.

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 method according to any one of claims 4 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 4 to 6 is implemented.

Images