Operation and maintenance cost configuration method and device of wireless network, medium and electronic equipment

Abstract

The embodiment of the invention relates to an operation and maintenance cost configuration method and device of a wireless network, a computer readable storage medium and electronic equipment, and relates to the technical field of networks, and the operation and maintenance cost configuration method of the wireless network comprises the following steps: obtaining historical data of a cost benefit evaluation index of the wireless network, training and generating a prediction model based on a machine learning algorithm; obtaining a current-year cost-benefit evaluation index of the wireless network, and inputting the current-year cost-benefit evaluation index into the prediction model to obtain a predicted cost growth rate of the wireless network; and based on the predicted cost growth rate, in combination with a regulatory factor, obtaining the maintenance cost which needs to be configured by the wireless network in the next year. According to the invention, the accuracy and high efficiency of prediction of the maintenance cost of the wireless network can be realized.

Description

Background Art

[0002] With the iterative upgrade of network technology, the continuous expansion of network scale, and the increasing requirements of customers for network quality and service responsiveness, the maintenance cost demand of communication networks continues to increase. In particular, major operators have built 5G networks on a large scale. Considering that 5G base stations have more types and provide services that need to meet the information service needs of more diversified scenarios, the maintenance cost configuration of 5G wireless networks has become more complicated.

[0003] In the related technologies, the maintenance cost configuration of operators' 5G wireless networks is generally determined manually through historical data analysis, and the cost configuration is greatly influenced by subjectivity. In addition, the related technologies use fixed asset indicators as judgment factors, lack comprehensive analysis, have certain limitations, and have poor accuracy, which affects the refined management of maintenance costs. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method for configuring operation and maintenance costs of a wireless network, an operation and maintenance cost configuration device of a wireless network, an electronic device and a computer-readable storage medium, thereby at least to a certain extent overcoming the problems of inaccurate operation and maintenance cost configuration and lack of comprehensive analysis of the wireless network caused by the limitations and defects of the relevant technology.

[0005] According to a first aspect of the present disclosure, a method for configuring operation and maintenance costs of a wireless network is provided, comprising: obtaining historical data of cost-effectiveness evaluation indicators of the wireless network, and generating a prediction model based on machine learning algorithm training; obtaining the cost-effectiveness evaluation indicators of the current year of the wireless network, and inputting the cost-effectiveness evaluation indicators of the current year into the prediction model to obtain a predicted cost growth rate of the wireless network; based on the predicted cost growth rate, combined with an adjustment factor, obtaining the maintenance cost that needs to be configured for the wireless network in the next year.

[0006] In an exemplary embodiment of the present disclosure, the cost-effectiveness evaluation index value includes single base station cost, single user cost and unit fixed asset cost.

[0007] In an exemplary embodiment of the present disclosure, inputting the current year cost-benefit evaluation index into the prediction model to obtain a predicted cost growth rate of the wireless network includes:

[0008] Based on the prediction model, the cost-benefit evaluation index for the current year is fitted to determine the predicted cost growth rate of the wireless network.

[0009] In an exemplary embodiment of the present disclosure, the step of acquiring historical data of cost-effectiveness evaluation indicators of wireless networks and generating a prediction model based on machine learning algorithm training includes:

[0010] According to the historical cost-benefit evaluation index and the actual value of the historical cost growth rate, the model parameters are adjusted to perform model training to obtain the prediction model.

[0011] In an exemplary embodiment of the present disclosure, the maintenance cost that needs to be configured for the wireless network in the next year is obtained based on the predicted cost growth rate and in combination with the adjustment factor, including:

[0012] The predicted cost growth rate, the adjustment factor and the current year maintenance cost of the wireless network are logically processed to determine the maintenance cost that needs to be configured for the wireless network in the next year.

[0013] In an exemplary embodiment of the present disclosure, the single base station cost is determined based on the maintenance cost and the number of equivalent base stations, the single user cost is determined based on the maintenance cost and the number of mobile users in the network, and the unit fixed asset cost is determined based on the maintenance cost and the original value of the fixed assets.

[0014] In an exemplary embodiment of the present disclosure, the adjustment factor includes one or more of a labor cost adjustment factor, a topography correction factor, and a fixed asset renewal rate correction factor.

[0015] According to a second aspect of the present disclosure, there is provided an operation and maintenance cost configuration device for a wireless network, comprising: a model training module, used to obtain historical data of cost-effectiveness evaluation indicators of the wireless network, and generate a prediction model based on machine learning algorithm training; a growth rate prediction module, used to obtain the cost-effectiveness evaluation indicators of the wireless network for the current year, and input the cost-effectiveness evaluation indicators of the current year into the prediction model to obtain a predicted cost growth rate of the wireless network; a maintenance cost determination module, used to obtain the maintenance cost that needs to be configured for the wireless network in the next year based on the predicted cost growth rate in combination with an adjustment factor.

[0016] According to a third aspect of the present disclosure, 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 for configuring operation and maintenance costs of a wireless network described in any one of the above is implemented.

[0017] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned methods for configuring operation and maintenance costs of a wireless network by executing the executable instructions.

[0018] In the technical solution provided in the embodiment of the present disclosure, on the one hand, the cost-effectiveness evaluation index of the wireless network in the current year can be processed by the prediction model to obtain the predicted cost growth rate of the wireless network, and further the maintenance cost that needs to be configured for the wireless network in the next year can be obtained by combining the predicted cost growth rate with the adjustment factor. Since the cost-effectiveness evaluation index can include evaluation indicators of multiple dimensions, the problem that the cost configuration is mainly affected by subjective factors in the process of manual decision-making based on historical data is avoided, and a comprehensive analysis can be provided from multiple dimensions, thereby realizing the refined management of maintenance costs. On the other hand, determining the predicted cost growth rate of the wireless network from multiple dimensions provides a comprehensive decision-making basis for the prediction of operation and maintenance costs, can improve the accuracy of the predicted cost growth rate, further improve the accuracy of the determined maintenance costs, and can improve the efficiency of determining the maintenance costs, and can realize the prediction of the operation and maintenance costs of the entire network, increasing the scope of application and availability.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0021] Figure 1 A flowchart of a method for configuring operation and maintenance costs of a wireless network in an embodiment of the present disclosure is schematically shown.

[0022] Figure 2 A schematic diagram of a wireless network operation and maintenance cost model in an embodiment of the present disclosure is schematically shown.

[0023] Figure 3 The flowchart of the model training in the embodiment of the present disclosure is schematically shown.

[0024] Figure 4 A specific flow chart of determining the output of the prediction model is schematically shown in FIG.

[0025] Figure 5 A schematic diagram for determining maintenance cost is shown schematically in FIG.

[0026] Figure 6 A block diagram schematically illustrates an apparatus for configuring operation and maintenance costs of a wireless network in an embodiment of the present disclosure.

[0027] Figure 7The block diagram of the electronic device according to the embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0029] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0030] In some embodiments, the current maintenance cost configuration of 5G wireless networks of operators is mainly determined by experts through historical data analysis. The cost configuration is subject to a large degree of subjective influence, and fixed asset indicators are mainly used as judgment factors in the past, lacking comprehensive analysis, thus affecting the refined management of maintenance costs. In order to solve the technical problems existing in the above embodiments, a method for configuring the operation and maintenance cost of a wireless network is provided in the embodiments of the present disclosure, which can predict the operation and maintenance cost of the entire network.

[0031] Next, refer to Figure 1 The steps of the method for configuring the operation and maintenance cost of a wireless network in an embodiment of the present disclosure are specifically described in detail.

[0032] In step S110, historical data of cost-effectiveness evaluation indicators of the wireless network is obtained, and a prediction model is generated based on machine learning algorithm training.

[0033] In the disclosed embodiment, the wireless network may be any type of wireless network, for example, a 4G wireless network, a 5G wireless network, a 6G wireless network, etc., and a 5G wireless network is used as an example for explanation herein. The wireless network may also be a wireless network in any area. The cost-benefit evaluation index may be used to represent the maintenance information of the wireless network. The cost-benefit evaluation index may include various types of maintenance indicators, for example, various types of maintenance indicators such as base station maintenance, user maintenance, and asset maintenance. In the disclosed embodiment, the maintenance cost of the wireless network may be involved in the calculation process of the cost-benefit evaluation index, thereby obtaining the cost-benefit evaluation index of the wireless network. That is, the cost-benefit evaluation index of the wireless network may be determined based on the maintenance cost of the wireless network.

[0034] According to the definition of 3GPP, the 5G system consists of the 5G core network (5GC) and the 5G access network (RAN). The 5G wireless network refers to 5G-RAN, which is mainly composed of CU (Centralized Unit), DU (Distribute Unit), AAU (Active Antenna Unit) and other equipment. Based on the above system architecture, the maintenance cost of the 5G wireless network refers to the cost incurred for the daily maintenance of equipment such as centralized units, distributed units, and active antenna units, which may include at least one type of maintenance cost among on-site inspections, hardware repairs, wireless network optimization, and maintenance. Among them, the costs related to on-site inspections and hardware repairs are related to the scale of the corresponding base stations; the costs related to wireless network optimization are related to the scale of the corresponding users; and the maintenance costs are related to the original value of fixed assets.

[0035] In some embodiments, in order to obtain cost-effectiveness evaluation indicators of wireless networks, cost data of wireless network operation and maintenance can be collected from various related systems, and the cost data can be preprocessed to obtain preprocessed cost data. The preprocessing here can include data de-redundancy and data standardization.

[0036] Next, the pre-processed cost data can be calculated to obtain one or more cost-effectiveness evaluation indicators of wireless networks, and a data set can be formed based on the cost-effectiveness evaluation indicators of wireless networks. The cost-effectiveness evaluation indicators of wireless networks can be determined based on the actual production experience of operators, and may include but are not limited to the cost of a single base station C BS , Single user cost C U , Unit fixed asset cost C A .

[0037] In some embodiments, the cost of a single base station refers to the maintenance cost of each base station, and the cost of a single base station can be determined based on the maintenance cost and the number of equivalent base stations. Specifically, the cost of a single base station can be calculated according to formula (1):

[0038]

[0039] Among them, C represents the total maintenance cost (i.e. maintenance cost), which is the total cost of various 5G wireless network operating cost investment scenarios.

[0040] N BS is the number of equivalent base stations. According to the 3GPP TS38.104 standard, 5G base stations can be divided into four types: BS type 1-C, BS type 1-H, BS type 1-O, and BS type 2-O (hereinafter referred to as 1-C, 1-H, 1-O, and 2-0). Assume that the number of 1-C and 1-H equivalent base stations is N BS1 , the number of equivalent base stations of 1-0 and 2-0 is N BS2 Where N BS1 It is the sum of the number of 1-C and 1-H type base stations, that is, each 1-C or 1-H type base station corresponds to one equivalent base station; N BS2 is the total number of 1-0 and 2-0 type base stations in that year, N BS2 It can be determined by formula (2):

[0041]

[0042] Among them, C l2 is the sum of the maintenance costs of 1-0 and 2-0 type base stations in the previous year, N l2 is the total number of maintenance of 1-0 and 2-0 type base stations in the previous year, C l1 is the sum of the maintenance costs of 1-0 and 1-H type base stations in the previous year, N l1 It is the sum of the number of 1-0 and 1-H type base stations maintained in the previous year. Furthermore, it can be determined based on the sum of the number of 1-C and 1-H type base stations and the sum of the number of 1-0 and 2-0 type base stations in the current year, as shown in formula (3):

[0043] N BS =N BS1 +N BS2 Formula (3)

[0044] The single user cost can be used to represent the maintenance cost required for each user. The single user cost is determined based on the maintenance cost and the number of mobile users in the network. Specifically, it can be determined according to formula (4):

[0045] C U =CN UFormula (4)

[0046] Among them, C U is the cost per user, N U It is the number of mobile users online in that year.

[0047] The unit fixed asset cost can be determined based on the maintenance cost and the original value of the fixed assets. Specifically, it can be calculated according to formula (5):

[0048] C A =CN A Formula (5)

[0049] Among them, C A represents the unit fixed asset cost, N A It is the original value of fixed assets corresponding to the mobile network in that year.

[0050] In some embodiments, the maintenance cost of the wireless network is affected by other factors in addition to the network scale. To ensure the accuracy of the model, an adjustment factor can be introduced to balance the difference. The adjustment factor can include one or more of a labor cost adjustment factor, a terrain correction factor, and a fixed asset renewal rate correction factor.

[0051] Among them, the labor cost adjustment factor can be reasonably set according to the growth trend of the social wage level and the difference in social wage levels in the administrative regions where different local networks are located. As for the topography correction factor, the difficulty of equipment maintenance varies under different topography, so the topography correction factor can be corrected according to the differences in topography in various regions. In addition, since the construction level and construction cycle of different operators or different local networks of the same operator are not necessarily completely consistent, the service life of the equipment is inconsistent. The service life of the equipment is positively correlated with the failure rate, which will affect the investment in maintenance costs. The newness rate of fixed assets reflects the newness of fixed assets, and certain corrections should be made according to the newness rate level.

[0052] In the disclosed embodiment, after determining the type of cost-effectiveness evaluation index of the wireless network, the historical data of the cost-effectiveness evaluation index of the wireless network can be obtained. The historical data here can be the historical cost-effectiveness evaluation index of the wireless network in the previous year or any historical period, which can be determined according to actual needs. It should be noted that while obtaining the historical data of the cost-effectiveness evaluation index of the wireless network, the actual value of the historical cost growth rate of the wireless network can also be obtained, that is, the actual value of the historical cost growth rate of the wireless network in the previous year or any historical period. The actual value of the historical cost growth rate can be determined based on the difference between the historical costs of each year. In addition, the historical data can correspond to the historical cost growth rate.

[0053] After obtaining the historical data of the cost-benefit evaluation index of the wireless network, a prediction model can be generated based on the training of the machine learning algorithm. Exemplarily, the historical data of the cost-benefit evaluation index of the wireless network can be used as an input factor, and the model parameters can be adjusted based on the machine learning algorithm until the end condition is met, so as to realize the model training process and obtain the prediction model. During the training process, the historical cost-benefit evaluation index of the wireless network can be input into the model, and the model can be trained in combination with the actual value of the historical cost growth rate corresponding to the historical cost-benefit evaluation index of the wireless network to obtain the prediction model. The prediction model can be a wireless network operation and maintenance cost model. Based on the wireless network operation and maintenance cost model represented by the prediction model, the data sets of cost-benefit evaluation indexes and total maintenance costs of multiple different local networks in different years collected can be analyzed, and the relationship between the cost-benefit evaluation index and the cost growth rate can be analyzed, so as to determine the cost growth rate of the wireless network.

[0054] The wireless network operation and maintenance cost model represented by the prediction model can be constructed by using a BP neural network. The BP neural network algorithm is a multi-layer feedforward network trained by an error back propagation algorithm. Figure 2 A schematic diagram of a wireless network operation and maintenance cost model is shown schematically in Figure 2 As shown in , the wireless network operation and maintenance cost model may include an input layer, a hidden layer, and an output layer. The input of the input layer of the wireless network operation and maintenance cost model can be expressed as (x1, x2, x3), and the output of its output layer can be y. Therefore, the wireless network operation and maintenance cost model can process the input (x1, x2, x3) to obtain the output y. Among them, the input (x1, x2, x3) is used to represent multiple cost-effectiveness evaluation indicators, and the output y is used to represent the predicted cost growth rate.

[0055] After building the wireless network operation and maintenance cost model, in order to improve the accuracy of the model prediction results, the machine learning model can be trained based on the historical cost-benefit evaluation index of the wireless network to obtain a prediction model. The wireless network can be a wireless network to be analyzed, which can be any type of wireless network deployed in any region. The historical cost-benefit evaluation index can be the historical cost-benefit evaluation index value of the wireless network in each year.

[0056] The historical cost-benefit evaluation index of the wireless network in a certain year can be used as the input of the model, and the corresponding model output value can be determined according to the wireless network operation and maintenance cost model; the model training is further carried out according to the gap between the model output value and the target output value until the end condition is met to complete the model training process. The end condition here can be reaching the maximum number of iterations, or the minimum gap, etc.

[0057] Figure 3The flowchart of model training is shown schematically in Figure 3 As shown in , it mainly includes the following steps:

[0058] In step S310, an input vector and a target output value are given.

[0059] Specifically, since the wireless network operation and maintenance cost model may include an input layer, a hidden layer, and an output layer, the input vector, that is, the three values ​​that need to be input in the input layer are: (x1, x2, x3) = (C BS ,C U ,C A ); The target output value can be expressed as: y=g.

[0060] After determining the input and output, the data set generated based on the historical data of the cost-effectiveness evaluation index of the wireless network obtained in the index calculation can be used as a training sample. Based on this, the target output values ​​of the input and output of the kth sample can be expressed as formula (6):

[0061]

[0062] In step S320, the model is initialized. Specifically, the weights and biases in the wireless network operation and maintenance cost model may be initialized, the maximum number of iterations N may be set, and the learning rate may be set to 1.

[0063] In step S330, the input value and output value of the hidden layer are calculated.

[0064] Exemplarily, the hidden layer may include multiple nodes, and the input value h of each node j The weighted summation result obtained by weighted summation of the input of the input layer and the weight from the input layer to the hidden layer, and the bias of the hidden layer can be added together. Specifically, it can be calculated according to formula (7):

[0065] h j =∑w ij x i +θ j Formula (7)

[0066] Among them, h j represents the input of each node in the hidden layer, w ij represents the weight from the input layer to the hidden layer, x i represents the variable of the input layer, θ j represents the bias of the hidden layer.

[0067] The activation function of the hidden layer can be a sigmoid function, which can be specifically expressed as formula (8):

[0068]

[0069] Based on this, the input value can be processed based on the activation function to obtain the output value of each node in the hidden layer: f(h j ). It can be obtained that the output of the wireless network operation and maintenance cost model can be determined according to the weighted sum of the weights from the hidden layer to the output layer and the output value and the addition result of the bias of the output layer, which can be specifically expressed as:

[0070] y=∑v j f(h j )+θ k Formula (9)

[0071] Among them, v j represents the weight from the hidden layer to the output layer, θ k Represents the bias of the output layer.

[0072] In step S340 , the error between the target output value and the actual output value of the model is calculated.

[0073] For example, the actual output value of the model refers to the output value obtained by inputting the historical cost-benefit evaluation index into the model, and the target output value refers to the target output set in advance, which can be used to represent the historical cost growth rate corresponding to the historical data. The error here refers to the global error. The global error between the two can be determined according to formula (10):

[0074]

[0075] Where y is the actual output value of the cost growth rate of the wireless network obtained according to the wireless network operation and maintenance cost model, y e is the target output value of the cost growth rate of the wireless network.

[0076] In step S350, the reverse error is calculated.

[0077] Exemplarily, the reverse error refers to the error of the hidden layer and the input layer obtained by reverse calculation. The error of the hidden layer and the error of the input layer can be reversely calculated based on the global error. Specifically, the error of the hidden layer can be calculated by formula (11):

[0078]

[0079] The error of the input layer is shown according to formula (12):

[0080]

[0081] In step S360, the weights are updated.

[0082] Exemplarily, each weight may be updated according to the error gradient until the number of updates reaches the maximum number of iterations N set in advance, so as to obtain the updated weights from the input layer to the hidden layer, and the updated weights from the hidden layer to the output layer. Specifically, the input layer error and the error gradient corresponding to the input layer may be obtained, and the error gradient corresponding to the input layer may be added to the weight from the input layer to the hidden layer to obtain the updated weights from the input layer to the hidden layer. The updated weights from the input layer to the hidden layer may be calculated with reference to formula (13):

[0083]

[0084] Similarly, the error of the hidden layer can be obtained, and the error gradient corresponding to the hidden layer can be obtained. The error gradient corresponding to the hidden layer is added to the weight from the hidden layer to the output layer to obtain the updated weight from the hidden layer to the output layer. The updated weight from the hidden layer to the output layer can be determined by referring to formula (14):

[0085]

[0086] In step S370, it is determined whether the learning is finished. If so, it is finished; if not, it goes to step S330 to recalculate the input value and output value of the hidden layer, and determine the error between the target output value and the actual output value and the reverse error based on the recalculated input value and output value of the hidden layer, and continue to update the weights until the number of updates reaches the preset maximum number of iterations, thereby obtaining the updated weights from the input layer to the hidden layer, and the updated weights from the hidden layer to the output layer.

[0087] After obtaining the updated weights from the input layer to the hidden layer and the updated weights from the hidden layer to the output layer, a trained wireless network operation and maintenance cost model can be obtained based on the updated weights from the input layer to the hidden layer and the updated weights from the hidden layer to the output layer, and the trained wireless network operation and maintenance cost model can be used as a prediction model.

[0088] In some embodiments, the C of different local networks in each year can be BS , C U , C A The indicator value is used as the input of the model, and the corresponding g indicator value (cost growth rate) is used as the output. The model is trained based on the above training set, and finally the 5G wireless network maintenance cost growth rate model, that is, the prediction model, is obtained:

[0089] g = costgrowth (C BS ,C U ,C A ) Formula (15)

[0090] In the disclosed embodiment, the wireless network operation and maintenance cost model is trained from multiple dimensions through the historical data of the cost-effectiveness evaluation indicators of the wireless network to obtain a prediction model. The model can be trained from multiple dimensions, avoiding the influence of subjective factors when determining the maintenance cost in the related technology, increasing the comprehensiveness, and being able to improve the accuracy of the trained model and improve the reliability of the model.

[0091] Next, continue to refer to Figure 1 As shown in , in step S120, the cost-benefit evaluation index of the wireless network for the current year is obtained, and the cost-benefit evaluation index of the current year is input into the prediction model to obtain the predicted cost growth rate of the wireless network.

[0092] In the embodiment of the present disclosure, after obtaining the prediction model, the maintenance cost growth rate of the wireless network can be predicted based on the prediction model. For example, the cost-effectiveness evaluation index of the wireless network for the current year can be input into the prediction model, and the predicted cost growth rate of the wireless network for the next year can be obtained based on the prediction model.

[0093] In some embodiments, since the prediction model may include an input layer, a hidden layer, and an output layer. Based on the structure of the above prediction model, the multiple cost-effectiveness evaluation indicators of the wireless network in the current year can be input into the prediction model, and the input cost-effectiveness evaluation indicators of the current year are fitted through the hidden layer of the prediction model to obtain the output value of each node of the hidden layer; the output value of each node of the hidden layer is further fitted to obtain the output of the prediction model, that is, the predicted cost growth rate of the wireless network in the next year. In the above process, the input value of each node of the hidden layer can be first determined according to the cost-effectiveness evaluation indicator of the current year and the weight from the input layer to the hidden layer and the bias of the hidden layer. Then, the output value of each node of the hidden layer is determined according to the input value of each node of the hidden layer and the excitation function of the hidden layer. Further, the predicted cost growth rate of the wireless network in the next year is obtained according to the output value of each node of the hidden layer.

[0094] Figure 4 The specific process diagram for determining the output of the prediction model is schematically shown in Figure 4 As shown in , based on the model structure of the prediction model, the following steps are mainly included:

[0095] In step S410, the input value of each node of the hidden layer is determined according to the weight from the input layer to the hidden layer and the cost-effectiveness evaluation index of the current year;

[0096] In step S420, the input value of each node of the hidden layer is mapped to obtain the output value of each node of the hidden layer;

[0097] In step S430, the output value of each node of the hidden layer is combined with the weight from the hidden layer to the output layer to obtain the output value of the prediction model.

[0098] In the disclosed embodiment, first, the weights from the input layer to the hidden layer and the cost-effectiveness evaluation index of the current year can be weighted and summed, and the weighted summation result can be added to the bias of the hidden layer to obtain the input value of each node in the hidden layer. Then, the activation function of the hidden layer can be used to map the input value of each node in the hidden layer to obtain the output value of each node in the hidden layer. Further, the output value of each node in the hidden layer and the weights from the hidden layer to the output layer are weighted and summed, and the weighted summation result and the bias of the output layer are summed to obtain the output value of the prediction model, that is, the predicted cost growth rate of the wireless network in the next year. Among them, the activation function of the hidden layer can be a sigmoid function or other types of activation functions, which are not specifically limited here.

[0099] Continue to refer Figure 1 As shown in , in step S130, based on the predicted cost growth rate and in combination with the adjustment factor, the maintenance cost that needs to be configured for the wireless network in the next year is obtained.

[0100] In the embodiment of the present disclosure, the predicted cost growth rate of the wireless network can be used to represent the predicted cost growth rate for the next year. Based on the predicted cost growth rate, the maintenance cost for the next year can be determined. Figure 5 As shown in , the maintenance cost that needs to be configured for the wireless network in the next year can be jointly determined based on the predicted cost growth rate of the wireless network, the maintenance cost of the current year, and the adjustment factor. Exemplarily, the predicted cost growth rate of the next year, the maintenance cost of the current year, and the adjustment factor can be logically processed to obtain the maintenance cost that needs to be configured for the wireless network in the next year. Specifically, the predicted cost growth rate of the wireless network can be added to the preset parameters to obtain the addition result, and the addition result can be multiplied by the adjustment factor and the maintenance cost of the wireless network in the current year to obtain the maintenance cost that needs to be configured for the wireless network in the next year. For details, refer to formula (16) for calculation:

[0101] C i+1 =C i ×(1+g)×ρ Formula (16)

[0102] Among them, C i represents the maintenance cost of the 5G wireless network in the current year, C i+1 is the network maintenance cost required for 5G wireless in the next year, ρ is the relevant adjustment factor, and the preset parameter can be 1.

[0103] In the above formula, the adjustment factor may include various types of adjustment factors, for example, it may include one or more of a labor cost adjustment factor, a topography adjustment factor, and a fixed asset renewal rate correction factor.

[0104] After obtaining the maintenance cost that needs to be configured for the wireless network in the next year, the operator can output the next year's 5G wireless network operating cost budget configuration based on the maintenance cost that needs to be configured, thereby achieving reasonable and accurate maintenance cost configuration for the entire wireless network. Maintenance cost can be used to represent the operating cost of the wireless network.

[0105] The technical solution in the disclosed embodiment, the entire 5G wireless network operation cost configuration method may include the following steps: first, establish a machine learning algorithm (model) based on three-dimensional cost evaluation indicators, and analyze the mapping relationship between multiple cost evaluation indicators and maintenance costs through the machine learning algorithm; second, establish a cost evaluation indicator measurement system, and give the definition of each indicator and indicator algorithm. Using the BP neural network method, cost prediction is performed based on historical maintenance cost data and network operation related data such as the original value of fixed assets, equivalent base station number, equivalent number of users, etc., to provide operators or other companies involved in 5G wireless network operation and maintenance with a decision-making basis for wireless network cost configuration, and improve the level of refined management of maintenance costs.

[0106] According to the three types of 5G wireless network maintenance costs, cost evaluation indicators corresponding to base station scale, user scale, and original value of fixed assets can be formulated. Through the 5G wireless network operation and maintenance cost model, the corresponding predicted cost growth rate of 5G wireless network operation and maintenance costs is obtained when the 5G wireless network is in different network periods, that is, when the base station, user, and asset scale are constantly changing, and then the maintenance cost that needs to be configured for the wireless network in the next year is determined.

[0107] The technical solution provided in the embodiments of the present disclosure avoids the problem that the maintenance cost configuration of the operator's wireless network is mainly determined by experts through historical data analysis, lacking the ability of automated analysis, and also avoids the limitation of the related technology that the whole life cycle operation and maintenance cost prediction is mainly carried out for a single network device, and can realize automated maintenance cost configuration and improve the accuracy of maintenance cost configuration. In addition, the operation and maintenance cost of the entire wireless network can be predicted and configured, which increases the comprehensiveness and application scope.

[0108] The present disclosure also provides a device for configuring operation and maintenance costs of a wireless network. Figure 7 As shown, the wireless network operation and maintenance cost configuration device 700 mainly includes the following modules:

[0109] A model training module 701 is used to obtain historical data of cost-effectiveness evaluation indicators of wireless networks and generate a prediction model based on machine learning algorithm training;

[0110] A predicted value determination module 702 is used to obtain a cost-benefit evaluation index of the wireless network in the current year, and input the cost-benefit evaluation index of the current year into the prediction model to obtain a predicted cost growth rate of the wireless network;

[0111] The maintenance cost determination module 703 is used to obtain the maintenance cost that needs to be configured for the wireless network in the next year based on the predicted cost growth rate and the adjustment factor.

[0112] In an exemplary embodiment of the present disclosure, the cost-effectiveness evaluation index includes single base station cost, single user cost and unit fixed asset cost.

[0113] In an exemplary embodiment of the present disclosure, the step of inputting the cost-benefit evaluation index value of the current year into the prediction model to obtain the predicted cost growth rate of the wireless network includes:

[0114] Based on the prediction model, the cost-benefit evaluation index for the current year is fitted to determine the predicted cost growth rate of the wireless network.

[0115] In an exemplary embodiment of the present disclosure, the step of acquiring historical data of cost-effectiveness evaluation indicators of wireless networks and generating a prediction model based on machine learning algorithm training includes:

[0116] According to the historical cost-benefit evaluation index and the actual value of the historical cost growth rate, the model parameters are adjusted to perform model training to obtain the prediction model.

[0117] In an exemplary embodiment of the present disclosure, the maintenance cost that needs to be configured for the wireless network in the next year is obtained based on the predicted cost growth rate and in combination with the adjustment factor, including:

[0118] The predicted cost growth rate, the adjustment factor and the current year maintenance cost of the wireless network are logically processed to determine the maintenance cost that needs to be configured for the wireless network in the next year.

[0119] In an exemplary embodiment of the present disclosure, the single base station cost is determined based on the maintenance cost and the number of equivalent base stations, the single user cost is determined based on the maintenance cost and the number of mobile users in the network, and the unit fixed asset cost is determined based on the maintenance cost and the original value of the fixed assets.

[0120] In an exemplary embodiment of the present disclosure, the adjustment factor includes one or more of a labor cost adjustment factor, a topography correction factor, and a fixed asset renewal rate correction factor.

[0121] It should be noted that the specific details of each module in the above-mentioned wireless network operation and maintenance cost configuration device have been described in detail in the corresponding wireless network operation and maintenance cost configuration method, so they will not be repeated here.

[0122] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0123] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0124] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0125] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0126] Refer to the following Figure 7 An electronic device 700 according to this embodiment of the present disclosure is described. Figure 7 The electronic device 700 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0127] like Figure 7 As shown, the electronic device 700 is in the form of a general computing device. The components of the electronic device 700 may include, but are not limited to: the at least one processing unit 710, the at least one storage unit 720, a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710), and a display unit 740.

[0128] The storage unit stores program codes, which can be executed by the processing unit 710, so that the processing unit 710 performs the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 710 can perform the following steps: Figure 1 Follow the steps shown in .

[0129] The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 7201 and / or a cache storage unit 7202 , and may further include a read-only storage unit (ROM) 7203 .

[0130] The storage unit 720 may also include a program / utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0131] Bus 730 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0132] The electronic device 700 may also communicate with one or more external devices 800 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 700, and / or communicate with any device that enables the electronic device 700 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 750. Furthermore, the electronic device 700 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 760. As shown, the network adapter 760 communicates with other modules of the electronic device 700 via a bus 730. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0133] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or an electronic device, etc.) to execute the method according to the implementation of the present disclosure.

[0134] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above "Exemplary Method" section of the present specification.

[0135] According to the program product for implementing the above method in the embodiment of the present disclosure, it can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0136] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0137] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0138] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0139] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0140] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0141] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the inventions invented herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not invented by the present disclosure. The specification and examples are to be considered merely exemplary, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for configuring operation and maintenance costs of a wireless network, characterized in that: include: Obtain historical data on cost-effectiveness evaluation indicators of wireless networks and generate prediction models based on machine learning algorithm training; Obtaining a cost-benefit evaluation index of the wireless network for the current year, and inputting the cost-benefit evaluation index of the current year into the prediction model to obtain a predicted cost growth rate of the wireless network; Based on the predicted cost growth rate and in combination with the adjustment factor, the maintenance cost that needs to be configured for the wireless network in the next year is obtained.

2. The method for configuring operation and maintenance costs of a wireless network according to claim 1, characterized in that: The cost-effectiveness evaluation indicators include single base station cost, single user cost and unit fixed asset cost.

3. The method for configuring operation and maintenance costs of a wireless network according to claim 1, characterized in that: The step of inputting the current year cost-benefit evaluation index into the prediction model to obtain a predicted cost growth rate of the wireless network includes: Based on the prediction model, the cost-benefit evaluation index for the current year is fitted to determine the predicted cost growth rate of the wireless network.

4. The method for configuring operation and maintenance costs of a wireless network according to claim 1, characterized in that: The step of acquiring historical data of cost-effectiveness evaluation indicators of wireless networks and generating a prediction model based on machine learning algorithm training includes: According to the historical cost-benefit evaluation index and the actual value of the historical cost growth rate, the model parameters are adjusted to perform model training to obtain the prediction model.

5. The method for configuring operation and maintenance costs of a wireless network according to claim 1, characterized in that: The maintenance cost of the wireless network required to be configured in the next year is obtained based on the predicted cost growth rate and combined with the adjustment factor, including: The predicted cost growth rate, the adjustment factor and the current year maintenance cost of the wireless network are logically processed to determine the maintenance cost that needs to be configured for the wireless network in the next year.

6. The method for configuring operation and maintenance costs of a wireless network according to claim 2, characterized in that: The single base station cost is determined based on the maintenance cost and the number of equivalent base stations, the single user cost is determined based on the maintenance cost and the number of mobile users on the network, and the unit fixed asset cost is determined based on the maintenance cost and the original value of the fixed assets.

7. The method for configuring operation and maintenance costs of a wireless network according to claim 1, characterized in that: The adjustment factors include one or more of a labor cost adjustment factor, a topography correction factor, and a fixed asset renewal rate correction factor.

8. A device for configuring operation and maintenance costs of a wireless network, characterized in that: include: A model training module is used to obtain historical data of cost-effectiveness evaluation indicators of wireless networks and generate a prediction model based on machine learning algorithm training; A growth rate prediction module, used to obtain a cost-benefit evaluation index of the wireless network in the current year, and input the cost-benefit evaluation index of the current year into the prediction model to obtain a predicted cost growth rate of the wireless network; The maintenance cost determination module is used to obtain the maintenance cost that needs to be configured for the wireless network in the next year based on the predicted cost growth rate combined with the adjustment factor.

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 for configuring operation and maintenance costs of a wireless network as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the operation and maintenance cost configuration method of a wireless network as described in any one of claims 1 to 7 by executing the executable instructions.

Images