Method and device for correcting 5g to b network cell service estimation

Abstract

The application provides a 5G ToB network cell service estimation quantity correction method and device, and relates to the technical field of 5G ToB network communication. The method comprises the following steps: obtaining a cell service estimation quantity in a preset period based on a service quantity estimation model; when the cell service estimation quantity in the preset period exceeds a threshold value, adjusting 5G ToB network settings; obtaining an estimation error value of the service quantity estimation model based on an error estimation model; obtaining a real cell service quantity in the preset period according to the cell service estimation quantity in the preset period, the adjusted cell service quantity after the adjustment of the 5G ToB network settings, and the estimation error value of the service quantity estimation model; and correcting the cell service estimation quantity in the preset period according to the real cell service quantity in the preset period. The 5G ToB network cell service estimation quantity correction method provided by the application is beneficial to avoiding high service quantity recurrence.

Description

Technical Field

[0001] This application relates to the field of 5G ToB network communication technology, specifically to a method, apparatus, electronic device, readable storage medium, and computer program product for correcting 5G ToB network cell service forecasts. Background Technology

[0002] Current technologies for traffic prediction and optimization primarily involve forecasting and assessing traffic volume on the existing network, and then dynamically optimizing the network based on the forecast results. More specifically, existing technologies mainly use models to estimate cell traffic volume based on past cell traffic patterns, and then optimize the network for cells during peak hours. However, once the network is optimized, the cell's traffic volume will decrease. If the model continues to assess future cell traffic volume based on the optimized cell's traffic volume, it creates the illusion that the cell's traffic volume remains stable and that there will be no high traffic volume in the future. In reality, the model should continue to assess future cell traffic volume based on the actual traffic volume before network optimization; otherwise, it may lead to the recurrence of high traffic volume issues. Summary of the Invention

[0003] This application provides a method for correcting the estimated service volume of a 5G ToB network cell, in order to solve the technical problem of high service volume recurrence.

[0004] In a first aspect, embodiments of this application provide a method for correcting the estimated service volume of a 5G ToB network cell, including:

[0005] Based on the traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained;

[0006] When the estimated volume of cell services within the preset time period exceeds the threshold, adjust the 5G ToB network settings.

[0007] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained;

[0008] The actual cell service volume within the preset time period is obtained based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model.

[0009] Based on the actual volume of cell services within the preset time period, the estimated volume of cell services within the preset time period is adjusted.

[0010] In one embodiment, obtaining the prediction error value of the traffic volume prediction model based on the error prediction model specifically involves:

[0011] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained according to the multiple linear regression expression.

[0012] The expression for the multiple linear regression is as follows:

[0013] e = w1x1 + w2x2 + ... + w k x k +b,

[0014] Where e represents the prediction error value of the traffic volume prediction model, and x k w represents the features used to train the traffic volume prediction model. k represents the parameter to be estimated, and b represents a constant.

[0015] In one embodiment, obtaining the actual cell service volume within the preset time period based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model specifically involves:

[0016] Based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, the actual cell service volume within the preset time period is obtained through the expression for the actual cell service volume.

[0017] The expression for the actual value of the cell service is:

[0018] y_true=(y_pred)–e–(y_adj),

[0019] Where y_true represents the actual volume of cell services within the preset time period, y_pred represents the estimated volume of cell services within the preset time period, e represents the prediction error value of the service volume prediction model, and y_adj represents the adjusted cell service volume after adjusting the 5G ToB network settings.

[0020] In one embodiment, correcting the estimated cell traffic volume within the preset time period based on the actual cell traffic volume within the preset time period includes:

[0021] The corrected cell service volume is obtained based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings.

[0022] Based on the cell service correction amount, adjust the estimated cell service volume within the preset time period.

[0023] In one embodiment, obtaining the cell service correction amount based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings specifically involves:

[0024] Based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings, the cell service correction amount is obtained through the cell service correction amount expression.

[0025] The expression for the cell service correction amount is:

[0026] y_gap = (y_true) – (y_adj),

[0027] Where y_gap represents the corrected amount of cell services, y_true represents the actual amount of cell services within the preset time period, and y_adj represents the adjusted amount of cell services after adjusting the 5G ToB network settings.

[0028] In one embodiment, obtaining the estimated cell traffic volume within a preset time period based on the traffic volume prediction model specifically involves:

[0029] Based on the aforementioned traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained according to historical cell traffic volume data and historical scenario data.

[0030] In one embodiment, the historical scene data includes any one of the following: urban scene data, suburban scene data, vehicle scene data, building scene data, and highway scene data.

[0031] Secondly, embodiments of this application provide a correction device for 5G ToB network cell service estimation, comprising:

[0032] The community traffic volume estimation module is used to: obtain the estimated community traffic volume within a preset time period based on the traffic volume estimation model;

[0033] The 5G ToB network setting adjustment module is used to adjust the 5G ToB network settings when the estimated volume of cell services within the preset time period exceeds a threshold value.

[0034] The module for obtaining the estimated error value is used to: obtain the estimated error value of the business volume estimated model based on the error estimated model;

[0035] The module for obtaining the actual volume of cell services is used to: obtain the actual volume of cell services within the preset time period based on the estimated volume of cell services within the preset time period, the adjusted cell service volume after adjusting the 5GToB network settings, and the prediction error value of the service volume prediction model.

[0036] The cell service volume estimation correction module is used to: correct the cell service volume estimation within the preset time period based on the actual cell service volume within the preset time period.

[0037] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing a computer program, wherein the processor executes the program to implement the steps of the 5G ToB network cell service estimation correction method described in the first aspect.

[0038] Fourthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the 5G ToB network cell service estimation correction method described in the first aspect.

[0039] The 5G ToB network cell service estimation correction method and apparatus provided in this application embodiment obtains the actual cell service volume that should exist within the preset time period based on the cell service volume estimation within a preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the estimation error value of the service volume estimation model. Then, the cell service volume estimation within the preset time period is corrected based on the actual cell service volume, effectively preventing the recurrence of high service volumes. Furthermore, the service volume estimation model can be used to estimate the cell service volume within another preset time period based on the corrected cell service volume estimation, which helps the service volume estimation model to more accurately assess the cell service volume and make timely and appropriate service and network adjustments to the cell, thereby reducing cell network capacity and improving the quality of the 5G ToB network. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart illustrating the method for correcting the estimated service volume of a 5G ToB network cell provided in an embodiment of this application.

[0042] Figure 2 This is a schematic diagram of the structure of the 5G ToB network cell service estimation correction device provided in the embodiments of this application;

[0043] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0045] Figure 1 This application provides a flowchart illustrating a method for correcting the estimated service volume of a 5G ToB network cell.

[0046] Reference Figure 1 This application provides a method for correcting the estimated service volume of a 5G ToB network cell, which may include:

[0047] S110. Based on the traffic volume prediction model, obtain the estimated traffic volume of the cell within the preset time period;

[0048] S120. When the estimated volume of cell services within the preset time period exceeds the threshold, adjust the 5G ToB network settings.

[0049] S130. Based on the error prediction model, obtain the prediction error value of the business volume prediction model;

[0050] S140. Based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, the actual cell service volume within the preset time period is obtained.

[0051] S150. Based on the actual volume of cell services within the preset time period, adjust the estimated volume of cell services within the preset time period.

[0052] It should be noted that the execution subject of the 5G ToB network cell service estimation correction method provided in this application embodiment can be a network-side device, such as a data processor.

[0053] It should be noted that the traffic volume prediction model can be pre-trained based on historical cell traffic volume data samples and historical scenario data samples to achieve the function of predicting cell traffic volume.

[0054] In step S110, the network-side device will obtain the estimated volume of cell services within a preset time period based on the service volume prediction model.

[0055] For example, network-side equipment can use a traffic prediction model to predict the estimated cell traffic volume at time T based on historical cell traffic volume data samples and historical scenario data samples from the time period (Tn) to (T-1) (n > 1). If the estimated cell traffic volume at time T is subsequently revised, the revised estimated cell traffic volume at time T can be used to predict the estimated cell traffic volume at time (T+1) and thereafter, thus resulting in a more accurate estimated cell traffic volume.

[0056] In step S120, the network-side device will adjust the 5G ToB network settings when the estimated cell service volume during the preset time period exceeds a threshold value.

[0057] It should be noted that the threshold value can be preset by the network-side equipment or set by the supervisor based on the actual situation.

[0058] When the estimated volume of cell services within a preset time period exceeds the threshold, it indicates that the volume of cell services within the preset time period may be excessive and the network capacity may be insufficient to support it. In this case, it is necessary to remind regulators to adjust the 5G ToB network settings, such as adjusting the rate at which the 5G ToB network processes services, or increasing the number of threads for processing services on the 5G ToB network, in order to achieve service offloading, etc.

[0059] In step S130, the network-side device obtains the predicted error value of the traffic volume prediction model based on the error prediction model.

[0060] It should be noted that the business volume forecasting model itself is not a perfect model, and it will inevitably have forecasting errors. Therefore, there will be corresponding forecasting error values. These values ​​can be evaluated by the forecasting performance of the business volume forecasting model. The forecasting error values ​​obtained can help adjust the business volume forecasting model itself and improve the forecasting quality.

[0061] It should be noted that the error prediction model can be pre-trained. The prediction error value can be evaluated by the prediction performance of the traffic volume prediction model.

[0062] For example, the error prediction model can be a multiple linear regression model, which can evaluate the prediction error of the business volume prediction model based on the features used to train the business volume prediction model, the parameters to be estimated, and constants.

[0063] In step S140, the network-side device will obtain the actual cell service volume within the preset time period based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5GToB network settings, and the prediction error value of the service volume prediction model.

[0064] The estimated cell traffic volume within a preset time period is the result of the traffic volume prediction model. The adjusted cell traffic volume after adjusting the 5G ToB network settings is the cell traffic volume after adjusting the 5G ToB network settings when the estimated cell traffic volume within the preset time period exceeds a threshold. The actual cell traffic volume within the preset time period can be calculated by combining the estimated cell traffic volume within the preset time period, the adjusted cell traffic volume after adjusting the 5G ToB network settings, and the prediction error value of the traffic volume prediction model. The actual cell traffic volume within the preset time period represents the actual cell traffic volume that should have existed within the preset time period before the adjustment of the 5G ToB network settings. The actual cell traffic volume within the preset time period can be used to correct the estimated cell traffic volume within the preset time period, so that the subsequent traffic volume prediction model can use the corrected cell traffic volume data to predict the cell traffic volume for subsequent time periods.

[0065] In step S150, the network-side device will adjust the estimated cell service volume within the preset time period based on the actual cell service volume within the preset time period.

[0066] Correcting the estimated volume of community services based on the actual volume of community services obtained above can ensure the accuracy and authenticity of the corrected volume. However, if the estimated volume of community services is corrected manually or through other means unrelated to the volume estimation itself, it is difficult to guarantee the quality of the correction.

[0067] The 5G ToB network cell service volume correction method provided in this application embodiment obtains the actual cell service volume that should exist within the preset time period based on the cell service volume prediction within a preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model. Then, the cell service volume prediction within the preset time period is corrected based on the actual cell service volume, which can effectively avoid the recurrence of high service volumes. Furthermore, the service volume prediction model can be used to predict the cell service volume within another preset time period based on the corrected cell service volume prediction. This helps the service volume prediction model to more accurately assess the cell service volume, enabling timely and appropriate service and network adjustments to the cell, thereby reducing cell network capacity and improving the quality of the 5G ToB network.

[0068] In one embodiment, obtaining the prediction error value of the traffic volume prediction model based on the error prediction model specifically involves:

[0069] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained according to the multiple linear regression expression.

[0070] The expression for the multiple linear regression is as follows:

[0071] e = w1x1 + w2x2 + ... + w k x k +b,

[0072] Where e represents the prediction error value of the traffic volume prediction model, and x k w represents the features used to train the traffic volume prediction model. k represents the parameter to be estimated, and b represents a constant.

[0073] It should be noted that the parameter to be estimated (w) k Parameters can be estimated using gradient descent.

[0074] By using the error prediction model based on the multiple linear regression expression, a more accurate prediction error value for the traffic volume prediction model can be obtained, providing good data for subsequent correction of the estimated traffic volume of the cell within the preset time period.

[0075] In one embodiment, obtaining the actual cell service volume within the preset time period based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model specifically involves:

[0076] Based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, the actual cell service volume within the preset time period is obtained through the expression for the actual cell service volume.

[0077] The expression for the actual value of the cell service is:

[0078] y_true=(y_pred)–e–(y_adj),

[0079] Where y_true represents the actual volume of cell services within the preset time period, y_pred represents the estimated volume of cell services within the preset time period, e represents the prediction error value of the service volume prediction model, and y_adj represents the adjusted cell service volume after adjusting the 5G ToB network settings.

[0080] Based on the estimated cell service volume within a preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, the network-side equipment can obtain a more realistic and accurate actual cell service volume within a preset time period, effectively ensuring the efficiency and quality of subsequent corrections to the estimated cell service volume within the preset time period.

[0081] In one embodiment, correcting the estimated cell traffic volume within the preset time period based on the actual cell traffic volume within the preset time period includes:

[0082] The corrected cell service volume is obtained based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings.

[0083] Based on the cell service correction amount, adjust the estimated cell service volume within the preset time period.

[0084] The actual cell traffic volume within the preset time period represents the cell traffic volume without adjusting the 5G ToB network settings. The network-side equipment can obtain the cell traffic correction volume based on the difference between the actual cell traffic volume within the preset time period and the adjusted cell traffic volume after adjusting the 5G ToB network settings. Then, based on the cell traffic correction volume, the estimated cell traffic volume within the preset time period is effectively corrected.

[0085] In one embodiment, obtaining the cell service correction amount based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings specifically involves:

[0086] Based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings, the cell service correction amount is obtained through the cell service correction amount expression.

[0087] The expression for the cell service correction amount is:

[0088] y_gap = (y_true) – (y_adj),

[0089] Where y_gap represents the corrected amount of cell services, y_true represents the actual amount of cell services within the preset time period, and y_adj represents the adjusted amount of cell services after adjusting the 5G ToB network settings.

[0090] By using the cell service correction expression, a more accurate cell service correction can be obtained based on the difference between the actual cell service volume within a preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings, thereby improving the quality and efficiency of correcting the estimated cell service volume within the preset time period.

[0091] In one embodiment, obtaining the estimated cell traffic volume within a preset time period based on the traffic volume prediction model specifically involves:

[0092] Based on the aforementioned traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained according to historical cell traffic volume data and historical scenario data.

[0093] It should be noted that the traffic volume prediction model can be pre-trained based on historical cell traffic volume data samples and historical scenario data samples to achieve the function of predicting cell traffic volume. Once the traffic volume prediction model is trained, it can predict the cell traffic volume at time T based on historical cell traffic volume data and historical scenario data, such as historical cell traffic volume data and historical scenario data at time (T-1).

[0094] Specifically, the community's business volume data can include past business volume data and / or business congestion data, while historical scenario data can include urban scenario data, suburban scenario data (such as leisure and entertainment area scenario data), transportation scenario data (such as high-speed rail scenario data), building scenario data (such as office building scenario data), highway scenario data, etc., which helps the business volume prediction model to more comprehensively predict the community's business volume within the preset time period.

[0095] The following describes the 5G ToB network cell service estimation correction device provided in the embodiments of this application. The 5G ToB network cell service estimation correction device described below and the 5G ToB network cell service estimation correction method described above can be referred to in correspondence with each other.

[0096] Figure 2 This application provides a schematic diagram of the structure of a 5G ToB network cell service estimation correction device.

[0097] Reference Figure 2 This application provides a device for correcting the estimated service volume of a 5G ToB network cell, which may include:

[0098] The community traffic volume estimation module 210 is used to: obtain the estimated community traffic volume within a preset time period based on the traffic volume estimation model;

[0099] 5G ToB network setting adjustment module 220 is used to: adjust the 5G ToB network settings when the estimated volume of cell services within the preset time period exceeds a threshold value;

[0100] The prediction error value acquisition module 230 is used to: obtain the prediction error value of the business volume prediction model based on the error prediction model;

[0101] The cell service actual volume acquisition module 240 is used to: obtain the cell service actual volume within the preset time period based on the cell service estimated volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model.

[0102] The cell service volume estimation correction module 250 is used to: correct the cell service volume estimation within the preset time period based on the actual cell service volume within the preset time period.

[0103] In one embodiment, the module 230 for obtaining the estimated error value is specifically used for:

[0104] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained according to the multiple linear regression expression.

[0105] The expression for the multiple linear regression is as follows:

[0106] e = w1x1 + w2x2 + ... + w k x k +b,

[0107] Where e represents the prediction error value of the traffic volume prediction model, and x k w represents the features used to train the traffic volume prediction model. k represents the parameter to be estimated, and b represents a constant.

[0108] In one embodiment, the cell service volume acquisition module 240 is specifically used for:

[0109] Based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, the actual cell service volume within the preset time period is obtained through the expression for the actual cell service volume.

[0110] The expression for the actual value of the cell service is:

[0111] y_true=(y_pred)–e–(y_adj),

[0112] Where y_true represents the actual volume of cell services within the preset time period, y_pred represents the estimated volume of cell services within the preset time period, e represents the prediction error value of the service volume prediction model, and y_adj represents the adjusted cell service volume after adjusting the 5G ToB network settings.

[0113] In one embodiment, the cell service forecast correction module 250 includes:

[0114] The cell service correction quantity acquisition submodule is used to: obtain the cell service correction quantity based on the actual cell service quantity within the preset time period and the adjusted cell service quantity after adjusting the 5G ToB network settings;

[0115] The cell service forecast correction submodule is used to: correct the cell service forecast within the preset time period based on the cell service correction amount.

[0116] In one embodiment, the cell service correction quantity obtaining submodule is specifically used for:

[0117] Based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings, the cell service correction amount is obtained through the cell service correction amount expression.

[0118] The expression for the cell service correction amount is:

[0119] y_gap = (y_true) – (y_adj),

[0120] Where y_gap represents the corrected amount of cell services, y_true represents the actual amount of cell services within the preset time period, and y_adj represents the adjusted amount of cell services after adjusting the 5G ToB network settings.

[0121] In one embodiment, the cell traffic estimation module 210 is specifically used for:

[0122] Based on the aforementioned traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained according to historical cell traffic volume data and historical scenario data.

[0123] In one embodiment, the historical scene data includes any one of the following: urban scene data, suburban scene data, transportation scene data, and building scene data.

[0124] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call a computer program in the memory 830 to execute steps of a method for correcting the 5GToB network cell service forecast, such as including:

[0125] Based on the traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained;

[0126] When the estimated volume of cell services within the preset time period exceeds the threshold, adjust the 5GToB network settings.

[0127] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained;

[0128] The actual cell service volume within the preset time period is obtained based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model.

[0129] Based on the actual volume of cell services within the preset time period, the estimated volume of cell services within the preset time period is adjusted.

[0130] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the 5G ToB network cell service estimation correction method provided in the above embodiments, such as including:

[0132] Based on the traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained;

[0133] When the estimated volume of cell services within the preset time period exceeds the threshold, adjust the 5GToB network settings.

[0134] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained;

[0135] The actual cell service volume within the preset time period is obtained based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model.

[0136] Based on the actual volume of cell services within the preset time period, the estimated volume of cell services within the preset time period is adjusted.

[0137] On the other hand, embodiments of this application also provide a processor-readable storage medium storing a computer program for causing a processor to perform the steps of the methods provided in the above embodiments, such as including:

[0138] Based on the traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained;

[0139] When the estimated volume of cell services within the preset time period exceeds the threshold, adjust the 5GToB network settings.

[0140] Based on the error prediction model, the prediction error value of the business volume prediction model is obtained;

[0141] The actual cell service volume within the preset time period is obtained based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model.

[0142] Based on the actual volume of cell services within the preset time period, the estimated volume of cell services within the preset time period is adjusted.

[0143] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0144] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0145] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for correcting the estimated service volume of a 5G ToB network cell, characterized in that, include: Based on the traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained; When the estimated volume of cell services within the preset time period exceeds the threshold, adjust the 5GToB network settings. Based on the error prediction model, the prediction error value of the business volume prediction model is obtained; The actual cell service volume within the preset time period is obtained based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model. Based on the actual volume of cell services within the preset time period, adjust the estimated volume of cell services within the preset time period; The traffic volume prediction model predicts the estimated traffic volume of a cell within a preset time period based on historical cell traffic volume data samples and historical scenario data samples; the error prediction model evaluates the prediction error value of the traffic volume prediction model based on the features used to train the traffic volume prediction model, the parameters to be estimated, and constants.

2. The method for correcting the estimated service volume of a 5G ToB network cell according to claim 1, characterized in that, The method for obtaining the prediction error value of the business volume prediction model based on the error prediction model is as follows: Based on the error prediction model, the prediction error value of the business volume prediction model is obtained according to the multiple linear regression expression. The expression for the multiple linear regression is as follows: e=w1x1+w2x2+…+w k x k +b, Where e represents the prediction error value of the traffic volume prediction model, and x k w represents the features used to train the traffic volume prediction model. k represents the parameter to be estimated, and b represents a constant.

3. The method for correcting the estimated service volume of a 5G ToB network cell according to claim 1, characterized in that, The process of obtaining the actual cell service volume within the preset time period based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, specifically involves: Based on the estimated cell service volume within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model, the actual cell service volume within the preset time period is obtained through the expression for the actual cell service volume. The expression for the actual value of the cell service is: y_true=(y_pred)–e–(y_adj), Where y_true represents the actual volume of cell services within the preset time period, y_pred represents the estimated volume of cell services within the preset time period, e represents the prediction error value of the service volume prediction model, and y_adj represents the adjusted cell service volume after adjusting the 5G ToB network settings.

4. The method for correcting the estimated service volume of a 5G ToB network cell according to any one of claims 1-3, characterized in that, The step of correcting the estimated cell traffic volume within the preset time period based on the actual cell traffic volume within the preset time period includes: The corrected cell service volume is obtained based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings. Based on the cell service correction amount, adjust the estimated cell service volume within the preset time period.

5. The method for correcting the estimated service volume of a 5G ToB network cell according to claim 4, characterized in that, The process of obtaining the cell service correction amount based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings is as follows: Based on the actual cell service volume within the preset time period and the adjusted cell service volume after adjusting the 5G ToB network settings, the cell service correction amount is obtained through the cell service correction amount expression. The expression for the cell service correction amount is: y_gap = (y_true) – (y_adj), Where y_gap represents the corrected amount of cell services, y_true represents the actual amount of cell services within the preset time period, and y_adj represents the adjusted amount of cell services after adjusting the 5G ToB network settings.

6. The method for correcting the estimated service volume of a 5G ToB network cell according to any one of claims 1-3, characterized in that, The estimated service volume of the cell within a preset time period is obtained based on the service volume prediction model, specifically as follows: Based on the aforementioned traffic volume prediction model, the estimated traffic volume of the cell within the preset time period is obtained according to historical cell traffic volume data and historical scenario data.

7. The method for correcting the estimated service volume of a 5G ToB network cell according to claim 6, characterized in that, The historical scene data includes any one of the following: urban scene data, suburban scene data, transportation scene data, building scene data, and highway scene data.

8. A correction device for 5G ToB network cell service forecasting, characterized in that, include: The community traffic volume estimation module is used to: obtain the estimated community traffic volume within a preset time period based on the traffic volume estimation model; The 5G ToB network setting adjustment module is used to adjust the 5G ToB network settings when the estimated volume of cell services within the preset time period exceeds a threshold value. The module for obtaining the estimated error value is used to: obtain the estimated error value of the business volume estimated model based on the error estimated model; The module for obtaining the actual volume of cell services is used to: obtain the actual volume of cell services within the preset time period based on the estimated volume of cell services within the preset time period, the adjusted cell service volume after adjusting the 5G ToB network settings, and the prediction error value of the service volume prediction model. The cell service volume estimation correction module is used to: correct the cell service volume estimation within the preset time period based on the actual cell service volume within the preset time period; The traffic volume prediction model predicts the estimated traffic volume of a cell within a preset time period based on historical cell traffic volume data samples and historical scenario data samples; the error prediction model evaluates the prediction error value of the traffic volume prediction model based on the features used to train the traffic volume prediction model, the parameters to be estimated, and constants.

9. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for correcting the 5G ToB network cell service estimation as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for correcting the 5GToB network cell service estimation as described in any one of claims 1 to 7.

Images