Cell capacity expansion decision-making method and device and medium

Abstract

The invention provides a cell capacity expansion decision method and device and a medium, and relates to the technical field of communication, in order to solve the problem of how to optimize capacity expansion decision, the method comprises the following steps: obtaining a dynamic traffic value index DFVI of a cell according to historical service data and historical user information of the cell, the DFVI comprehensively represents the service quality, the user demand and the economic benefit of the cell; according to the service quality after the dilatation resource is obtained by the cell, obtaining the estimated increased traffic NUP of the cell; according to the DFVI and the NUP, obtaining an estimated increased flow value V after the district obtains the capacity expansion resource; and performing cell capacity expansion decision according to the V. According to the method and the device, the dynamic traffic value index DFVI comprehensively representing the service quality, the user demand and the economic benefit of the cell is acquired, the estimated increased traffic value V of the cell capacity expansion is acquired according to the DFVI of the cell and the estimated increased traffic NUP, the cell capacity expansion decision is made according to the V, the capacity expansion decision of an operator is optimized, and thus the capacity expansion value is improved.

Description

Technical Field

[0001] The present disclosure at least relates to the field of communication technology, and in particular to a cell expansion decision method, a cell expansion decision device, and a computer-readable storage medium. Background Art

[0002] With the popularization of the Internet and the rapid development of mobile devices, the number of mobile Internet users has increased dramatically, resulting in explosive growth in data traffic. In order to ensure that users have stable high-speed Internet access services, communication operators will take a series of measures, such as increasing the number of cells, bandwidth, and adding base stations, to expand the data traffic processing capacity within the cell to meet the needs of more people online at the same time, thereby improving the overall network experience. This is called cell expansion.

[0003] The core meaning of cell expansion is to increase the capacity of mobile networks to meet the growing user demand. Currently, the allocation of expansion resources is mainly determined based on the load level of the cells. Cells with higher loads are given priority in obtaining expansion resources. This method is too simplistic. Summary of the invention

[0004] The technical problem to be solved by the present disclosure is to provide a cell expansion decision method, a cell expansion decision device and a computer-readable storage medium in view of the above-mentioned shortcomings, so as to solve the problem of how to optimize the expansion decision.

[0005] In a first aspect, the present disclosure provides a cell expansion decision method, the method comprising:

[0006] According to the historical service data and historical user information of the cell, the dynamic traffic value index DFVI of the cell is obtained. DFVI comprehensively represents the service quality, user demand and economic benefits of the cell.

[0007] Obtain the estimated increased traffic NUP of the cell based on the service quality of the cell after it obtains the expansion resources;

[0008] According to DFVI and NUP, obtain the estimated increased traffic value V after the cell obtains the expansion resources;

[0009] Make cell expansion decisions based on V.

[0010] Furthermore, according to the historical service data and historical user information of the cell, the dynamic traffic value index DFVI of the cell is obtained, which specifically includes:

[0011] Get the total number of cells to be expanded I;

[0012] Get the historical service data of each cell to be expanded i∈I, the historical service data includes the total traffic K generated by the cell to be expanded i in the historical time period i, Number of access users D i , the first delay rate L i , the first packet loss rate P i , first user feedback score S i , operating costs C i ;

[0013] Obtain the historical user information of each cell to be expanded i∈I, where the historical user information includes the traffic K generated by each user n∈N connecting to the cell to be expanded i among the N users accessed by the cell to be expanded i within the historical time period n 、Consumption n ;

[0014] Get the first service quality score of the cell i to be expanded: Q i =w L *(1-L i )+w P *(1-P i )+w S *S i , where w L 、w P and w S is the weight of the first delay rate, the first packet loss rate and the first user feedback score, the sum of which is 1;

[0015] Get the user demand intensity of the cell i to be expanded: U i =D i / D sum , D i is the number of users accessing the cell i to be expanded during the historical period, D sum is the total number of access users in all cells to be expanded during the historical period;

[0016] Get the total traffic revenue of the cell i to be expanded: Get the unit traffic operation cost of the cell i to be expanded: W i =C i / K i ;

[0017] Get the dynamic traffic value index of the cell i to be expanded: DFVI i =(R i / K i ×U i ×Q i )×(1-W i / W sum ), where W sum Represents the total unit traffic operation cost of all cells to be expanded.

[0018] Further, wherein:

[0019] First user feedback rating S i Obtained through user satisfaction surveys, with values ​​between 0 and 1;

[0020] The first delay rate L i The number of connections for which the delay of the cell i to be expanded exceeds the preset time / the total number of connections;

[0021] Operating costs i Including: equipment cost, maintenance cost, personnel cost, and energy cost.

[0022] Furthermore, according to the service quality of the cell after the cell obtains the expansion resources, the estimated increase traffic NUP of the cell is obtained, which specifically includes:

[0023] Allocate expansion resources for all cells to be expanded i=[1,I];

[0024] According to the service quality after allocating expansion resources to each cell i to be expanded, predict the user growth rate Gmarket of the cell i to be expanded i ;

[0025] Get the estimated growth traffic after allocating expansion resources to each cell i to be expanded: NUP i =U current,i *(1+Gmarket i )*ARPU i , where U current,i is the current number of users in the cell i to be expanded; ARPU i It is the predicted usage traffic per user in the cell i to be expanded obtained based on the historical average usage traffic of each user.

[0026] Furthermore, according to the service quality of each cell i to be expanded after allocating expansion resources, the user growth rate Gmarket of the cell i to be expanded is predicted. i , specifically including:

[0027] Obtain the historical user growth data of the cell, as well as the corresponding historical service quality data, historical user behavior data, and historical regional competition data to form model training data;

[0028] Train the community user growth prediction model based on the model training data;

[0029] Obtaining expected service quality data, current user behavior data, and current regional competition data of each to-be-expanded cell i after allocating expansion resources to form prediction input data;

[0030] Input the predicted input data into the trained cell user growth prediction model to obtain the user growth rate Gmarket of each cell i to be expanded. i .

[0031] Further, wherein:

[0032] The historical user growth data includes the historical user number sequence U obtained at equal time intervals. t-m ,U t-m+1 ,…,U t , and / or, obtain the historical user growth rate sequence G according to the historical user number sequence t-m ,G t-m+1 ,…,G t , where G t =(U t -U t-1 ) / U t-1 ×100%, t is the current time point, t-1 is the previous time point;

[0033] Historical service quality data SQ t Including historical average delay rate, historical average packet loss rate, historical average user feedback score obtained at equal time intervals, and / or historical average service quality score obtained based on the historical average delay rate, historical average packet loss rate, and historical average user feedback score;

[0034] Historical user behavior data UB t Including historical user average usage traffic, historical user average connection time, historical number of active users, historical regional competition data CE obtained at equal time intervals t Including the number of historical competitors’ users, historical competitors’ service quality scores, and historical competitors’ prices obtained at equal time intervals;

[0035] The cell user growth prediction model specifically adopts a linear regression model: G t =β0+β1*SQ t +β2*UB t +β3*CE t +ε, where β0, β1, β2, β3 are model parameters and ε is the error term.

[0036] Furthermore, according to DFVI and NUP, the estimated increased traffic value V of the cell after obtaining the expansion resources is obtained, including:

[0037] The estimated growth traffic value of each cell i to be expanded after obtaining the expansion resources is obtained according to the following formula: V i =DFVI i* NUP i .

[0038] Furthermore, a cell expansion decision is made based on V, specifically including:

[0039] Select V based on the preset quantity threshold or the preset estimated growth traffic value threshold. i The capacity of several cells with high capacity to be expanded is expanded.

[0040] In a second aspect, the present disclosure provides a cell expansion decision device, the device comprising:

[0041] The index module is used to obtain the dynamic traffic value index DFVI of the cell based on the historical service data and historical user information of the cell. DFVI comprehensively represents the service quality, user demand and economic benefits of the cell;

[0042] The traffic estimation module is used to obtain the estimated increased traffic NUP of the cell according to the service quality of the cell after the cell obtains the expansion resources;

[0043] The value estimation module is connected with the index module and the traffic estimation module, and is used to obtain the estimated increased traffic value V after the cell obtains the expansion resources according to DFVI and NUP;

[0044] The decision module is connected to the value estimation module and is used to make a cell expansion decision based on V.

[0045] In a third aspect, the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the cell expansion decision method as described above is implemented.

[0046] The present invention provides a method, device and medium for making a decision on cell expansion. By obtaining a dynamic traffic value index DFVI that comprehensively represents the service quality, user demand and economic benefits of the cell, an estimated growth traffic value V of the cell expansion is obtained according to the DFVI and the estimated growth traffic NUP of the cell, and a cell expansion decision is made according to V, so as to optimize the operator's expansion decision and thus improve the expansion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a cell expansion decision method according to an embodiment of the present disclosure;

[0048] Figure 2 is a flow chart of another method for making decisions on cell expansion according to an embodiment of the present disclosure;

[0049] Figure 3 It is a structural diagram of a cell expansion decision device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0051] It should be understood that the specific embodiments and drawings described herein are only used to explain the present disclosure rather than to limit the present disclosure.

[0052] It can be understood that, in the absence of conflict, the various embodiments of the present disclosure and the various features in the embodiments can be combined with each other.

[0053] It can be understood that, for the convenience of description, the drawings of the present disclosure only show parts related to the present disclosure, while parts irrelevant to the present disclosure are not shown in the drawings.

[0054] It can be understood that each module or unit involved in the embodiments of the present disclosure may correspond to only one entity structure, or may be composed of multiple entity structures, or multiple modules or units may be integrated into one entity structure.

[0055] It will be understood that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present disclosure may occur in an order different from that marked in the drawings.

[0056] It is understood that the flowcharts and block diagrams of the present disclosure illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present disclosure. Each box in the flowchart or block diagram may represent a module, unit, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based device that implements the specified functions, or may be implemented by a combination of hardware and computer instructions.

[0057] It can be understood that the modules and units involved in the embodiments of the present disclosure can be implemented by software or hardware, for example, the modules and units can be located in a processor.

[0058] Embodiment 1:

[0059] like Figure 1 As shown, the present disclosure provides a cell expansion decision method, the method comprising:

[0060] S1. Obtain the dynamic traffic value index DFVI of the cell based on the cell's historical service data and historical user information. DFVI comprehensively represents the cell's service quality, user demand, and economic benefits.

[0061] S2. Obtain the estimated increase in traffic NUP of the cell based on the service quality of the cell after it obtains the expansion resources;

[0062] S3. According to DFVI and NUP, obtain the estimated increased traffic value V after the cell obtains the expansion resources;

[0063] S4. Make cell expansion decisions based on V.

[0064] In this embodiment, a method for making a decision on cell expansion is provided, which obtains a dynamic traffic value index DFVI that comprehensively represents the cell service quality, user demand and economic benefits, obtains the estimated growth traffic value V of the cell expansion according to the cell's DFVI and the estimated growth traffic NUP, makes a cell expansion decision based on V, optimizes the operator's expansion decision, and thus improves the expansion value.

[0065] DFVI is obtained based on the historical business data and historical user information of the cell. It can be that at least one parameter representing the service quality, user demand and economic benefit of the cell is obtained based on the historical business data and historical user information of the cell, and then the three parameters are combined to obtain DFVI. Those skilled in the art know that the historical business data and historical user information contain information representing the service quality, user demand and economic benefit of the cell, and the calculation method of the specific parameters can be designed as needed. NUP is obtained based on the service quality of the cell after the cell obtains the expansion resources, and can also be obtained in combination with the current load of the cell.

[0066] Specifically, with the development of mobile communication technology, the number of operators' users has grown rapidly, and users' demand for the network has shifted from simple voice communication to high-traffic, high-speed applications such as video streaming, online games, and virtual reality. This has caused a sharp increase in the traffic carried by the network, and the load pressure on the communication cells has continued to increase. At the same time, users' expectations for Internet access speeds are getting higher and higher, and long-term network delays and freezes are no longer acceptable. Operators increase the capacity of mobile networks by expanding cell capacity to meet the growing user needs.

[0067] However, the existing cell expansion method is only to alleviate the load of the cell to be expanded and improve the user experience. If multiple cells need to be expanded and the expansion resources are limited, priority is only allocated based on the load size. The larger the load, the priority expansion resources are obtained. This method is too single-dimensional.

[0068] In response to this defect, this embodiment provides a cell expansion decision method, which can also be called a cell expansion resource allocation method. The main technical concepts include: obtaining historical service data of all cells to be expanded in a certain period of time, including the total traffic generated in a certain period of time for each cell to be expanded, the number of access users, delay rate, packet loss rate, user feedback score (between 0 and 1), and operating cost. The feedback score is obtained through a user satisfaction survey. According to the access user information of the cell to be expanded, the traffic and call charges generated by the users who access the cell to be expanded in the corresponding time period are obtained; the dynamic traffic value index of the cell to be expanded is determined, and the traffic that can be expected to increase after all cells to be expanded obtain expansion resources is estimated, and the traffic value that will increase after the cells to be expanded are estimated, and high-value cells are selected for expansion resource allocation. This embodiment can establish a more accurate expansion value judgment model based on information such as historical access data of the cell to be expanded, and prioritize the cells to be expanded, thereby improving the expansion value.

[0069] In one implementation, S1 obtains the dynamic traffic value index DFVI of the cell according to the historical service data and historical user information of the cell, specifically including:

[0070] Get the total number of cells to be expanded I;

[0071] Get the historical service data of each cell to be expanded i∈I, the historical service data includes the total traffic K generated by the cell to be expanded i in the historical time period i , Number of access users D i , the first delay rate L i , the first packet loss rate P i , first user feedback score S i , operating costs C i ;

[0072] Obtain the historical user information of each cell to be expanded i∈I, where the historical user information includes the traffic K generated by each user n∈N connecting to the cell to be expanded i among the N users accessed by the cell to be expanded i within the historical time period n 、Consumption n ;

[0073] Get the first service quality score of the cell i to be expanded: Q i =w L *(1-L i )+w P *(1-P i )+w S *S i , where w L 、w P and w Sis the weight of the first delay rate, the first packet loss rate and the first user feedback score, the sum of which is 1;

[0074] Get the user demand intensity of the cell i to be expanded: U i =D i / D sum , D i is the number of users accessing the cell i to be expanded during the historical period, D sum is the total number of access users in all cells to be expanded during the historical period;

[0075] Get the total traffic revenue of the cell i to be expanded: Get the unit traffic operation cost of the cell i to be expanded: W i =C i / K i ;

[0076] Get the dynamic traffic value index of the cell i to be expanded: DFVI i =(R i / K i ×U i ×Q i )×(1-W i / W sum ), where W sum Represents the total unit traffic operation cost of all cells to be expanded.

[0077] In one embodiment, wherein:

[0078] First user feedback rating S i Obtained through user satisfaction surveys, with values ​​between 0 and 1;

[0079] The first delay rate L i The number of connections for which the delay of the cell i to be expanded exceeds the preset time / the total number of connections;

[0080] Operating costs i Including: equipment cost, maintenance cost, personnel cost, and energy cost.

[0081] In this embodiment, the method can also be as follows Figure 2 As shown, a method for allocating expansion resources is provided, which can be applied in the field of communication technology and includes steps S101-S106.

[0082] Corresponding to step S1, steps S101-S103 are included, specifically:

[0083] S101, obtaining historical service data of the cell to be expanded

[0084] The historical service data of the cell to be expanded in a certain period of time is obtained. The historical service data of the cell to be expanded includes the total traffic K generated by each cell to be expanded i in a certain period of time i , Number of access users D i , delay rate L i , Packet loss rate P i , User feedback score S i (between 0 and 1), operating cost C i The feedback score is obtained through user satisfaction survey. According to the data related to the cell to be expanded, the service quality score Q of the cell to be expanded is determined. i 、User demand intensity U i .

[0085] Service quality score of the cell i to be expanded: Q i =w L *(1-L i )+w P *(1-P i )+w S *S i , where w L 、w P and w S is the weight of delay, packet loss rate and user feedback, ensuring that the sum of the three is 1. This formula reflects the service quality of the cell to be expanded by comprehensively evaluating delay, packet loss and user feedback. i is defined as the number of connections in which the delay of the cell i to be expanded exceeds a certain time (for example, 300 milliseconds) / the total number of connections.

[0086] User demand intensity of cell i to be expanded: U i =D i / D sum , where D i : The number of users accessing the cell i to be expanded in a certain period of time, D sum : The total number of access users in all cells to be expanded in a certain period of time.

[0087] S102, obtaining access user information of the cell i to be expanded

[0088] According to the access user information of the cell to be expanded, obtain the traffic K generated by user n connecting to the cell to be expanded i among the N users accessing the cell to be expanded i in the corresponding time period n (GB), user n's phone bill consumption P n Total traffic revenue of the cell i to be expanded (yuan):

[0089] S103, determine the dynamic flow value index (DFVI) of the cell i to be expanded i )

[0090] The Dynamic Traffic Value Index (DFVI) is an important indicator used to evaluate the contribution of traffic generated by the cell to be expanded to the overall value of the operator. DFVI takes into account economic benefits (such as revenue and cost), user experience (such as user demand intensity U i ) and network performance (such as service quality score Q i ) and other aspects to help operators make efficient capacity expansion decisions under limited resources.

[0091] DFVI i =(R i / K i ×U i ×Q i )×(1-W i / W sum ), where: W i represents the unit traffic operation cost of the cell i to be expanded, W i =C i / K i ; W sum Represents the sum of the unit traffic operation costs of all cells to be expanded. The total operation cost C of cell i to be expanded i Including: equipment cost, maintenance cost, personnel cost (technical support and management), energy cost (power consumption), etc.

[0092] When allocating expansion resources, if resources are limited, the cells with higher service quality scores are considered for expansion first. These cells often carry large user traffic demands during peak hours and help improve overall user satisfaction. Although the service quality score is an important factor, in actual operations, expansion decisions should also be combined with other indicators, such as economic value (value per GB of traffic), user demand intensity, etc. Comprehensive consideration of multiple factors can more effectively optimize resource allocation.

[0093] In one implementation, S2, according to the service quality of the cell after the cell obtains the expansion resources, obtain the estimated increased traffic NUP of the cell, specifically including:

[0094] Allocate expansion resources for all cells to be expanded i=[1,I];

[0095] According to the service quality after allocating expansion resources to each cell i to be expanded, predict the user growth rate Gmarket of the cell i to be expanded i ;

[0096] Get the estimated growth traffic after allocating expansion resources to each cell i to be expanded: NUP i =U current,i *(1+Gmarket i )*ARPUi , where U current,i is the current number of users in the cell i to be expanded; ARPU i It is the predicted usage traffic per user in the cell i to be expanded obtained based on the historical average usage traffic of each user.

[0097] In this embodiment, if Figure 2 As shown, the method corresponds to step S2 and further includes step S104, specifically:

[0098] S104: estimate the traffic NUP that can be increased after all cells to be expanded obtain expansion resources i

[0099] NUP i =U current,i *(1+Gmarket i )*ARPU i , parameter explanation: U current,i

[0100] is the current number of users in the cell i to be expanded; Gmarket i is the user growth rate of cell i, usually expressed as a decimal (e.g. 0.15 represents a 15% growth); ARPU i : The average traffic usage per user (GB), which can be calculated using historical user traffic data.

[0101] By the current number of users U current,i As a basis, it reflects the impact of existing users on future growth, combined with the cell user growth rate G market , estimate the number of users that can be attracted after the expansion. Combined with ARPU, the expected increase in traffic after the expansion of all cells to be expanded can be calculated.

[0102] In one embodiment, based on the service quality of each cell i to be expanded after allocating expansion resources, the user growth rate Gmarket of the cell i to be expanded is predicted. i , specifically including:

[0103] Obtain the historical user growth data of the cell, as well as the corresponding historical service quality data, historical user behavior data, and historical regional competition data to form model training data;

[0104] Train the community user growth prediction model based on the model training data;

[0105] Obtaining expected service quality data, current user behavior data, and current regional competition data of each to-be-expanded cell i after allocating expansion resources to form prediction input data;

[0106] Input the predicted input data into the trained cell user growth prediction model to obtain the user growth rate Gmarket of each cell i to be expanded. i .

[0107] In this embodiment, in order to estimate the user growth rate Gmarket of a specific cell i , a prediction model can be established by combining historical user data, service quality, network usage behavior, and competitive environment.

[0108] In one embodiment, wherein:

[0109] The historical user growth data includes the historical user number sequence U obtained at equal time intervals t-m ,U t-m+1 ,…,U t , and / or, obtain the historical user growth rate sequence G according to the historical user number sequence t-m ,G t-m+1 ,…,G t , where G t =(U t -U t-1 ) / U t-1 ×100%, t is the current time point, t-1 is the previous time point;

[0110] Historical service quality data SQ t Including historical average delay rate, historical average packet loss rate, historical average user feedback score obtained at equal time intervals, and / or historical average service quality score obtained based on the historical average delay rate, historical average packet loss rate, and historical average user feedback score;

[0111] Historical user behavior data UB t Including historical user average usage traffic, historical user average connection time, historical number of active users, historical regional competition data CE obtained at equal time intervals t Including the number of historical competitors’ users, historical competitors’ service quality scores, and historical competitors’ prices obtained at equal time intervals;

[0112] The cell user growth prediction model specifically adopts a linear regression model: G t =β0+β1*SQ t +β2*UB t +β3*CE t +ε, where β0, β1, β2, β3 are model parameters and ε is the error term.

[0113] In this embodiment, a prediction model is established to estimate the user growth rate Gmarket of a specific cell by combining historical user data, service quality, network usage behavior, and competitive environment.i , the following are the implementation steps and a complete example of model building and prediction:

[0114] Step 1: Collect historical data. First, you need to collect and analyze the following historical data:

[0115] Historical data on the number of users: User growth in the past few months or years (distributed by month or quarter), t-n ,U t-n+1 ,…,U t : the number of users from tn to t; service quality data: including delay, packet loss rate, bandwidth utilization, etc.; user behavior data: including users' average traffic usage, number of active users, average connection time, etc.; competition data: the situation of other competing operators in the area, including their user growth and service quality.

[0116] Step 2: Calculate the historical user growth rate. Based on the historical user data, calculate the past user growth rate.

[0117] The formula for calculating the user growth rate is: G t =(U t -U t-1 ) / U t-1 ×100%,U t : the number of users at the current time t; U t-1 : The number of users at the previous time point t-1. Through the growth rates of multiple time points, we get a growth rate sequence: G t-n ,G t-n+1 ,…,G t .

[0118] Step 3: Analyze influencing factors, collect and analyze data on key factors affecting user growth:

[0119] Service quality: Collect relevant data, such as average latency (ms), packet loss rate (%), and user satisfaction score (between 0 and 1) per month. The higher the service quality, the faster the user growth.

[0120] User behavior: Collect user activity data, such as average traffic usage (GB), average connection time (minutes), and number of active users. If these indicators are high, it usually indicates that the number of users may increase; Competitive environment:

[0121] Collect competitor data, such as the number of competitors' users, service quality scores, price changes, etc. If the service quality of other competitors declines, users may transfer from the competitor to that cell.

[0122] Step 4: Build a forecasting model. Based on historical growth rates and analysis of influencing factors, a growth forecasting model can be built in the following ways:

[0123] Linear regression model: Use user growth rate as the dependent variable, service quality, user behavior, and competitive environment as independent variables to build a multivariate linear regression model to predict future user growth rate:

[0124] G t =β0+β1·SQ t +β2·UB t +β3·CE t +∈

[0125] Among them: SQ t : Quality of service; UB t :User behavior; CE t : competitive environment; β0,β1,β2,β3: model parameters; ∈: error term.

[0126] Training model: Divide the data set into a training set and a test set (such as 70% training and 30% test), train the regression model on the training set, and obtain the model parameters.

[0127] Evaluate the model: Make predictions on the test set and calculate the model's evaluation indicators, such as R2 value, root mean square error (RMSE), etc., to determine the degree of fit of the model. Visualize the comparison between the predicted results and the actual results to verify the accuracy of the model.

[0128] Step 5: Predict user growth rate. Assuming that we have collected the following data, we input the data of future service quality, user behavior and competitive environment into the model and predict the future user growth rate as shown in Table 1:

[0129] Table 1 Example of user growth rate forecast

[0130]

[0131] Here is an example of how to do this in Python:

[0132]

[0133] printf("Expected user growth rate for *year*month:

[0134] {predicted_growth_rate:.2f}%")

[0135] After running the above code, we get the predicted user growth rate G^ of the cell. t+1 =Model output.

[0136] Step 6: Apply the user growth rate, based on the predicted user growth rate G^ t+1 , we can estimate the number of users in the cell in the next time period: U^t+1 =U t ×(1+G^ t+1 / 100).

[0137] Implementation example:

[0138] Assume that the number of users and historical growth rate of a certain cell A in the past 6 months are shown in Table 2 below:

[0139] Table 2 Example of user growth rate prediction

[0140]

[0141] From the data in Table 2, we can see that the user growth rate of cell A has been gradually decreasing in the last three months, which were 4.55%, 4.35%, and 3.33% respectively. The user growth rate for next month is predicted. Assuming the predicted growth rate is 4.08%, the current number of users is 620. Based on the predicted growth rate, the estimated number of users for next month = 620 × (1 + 4.08 / 100) ≈ 645.

[0142] In one implementation, S3, according to DFVI and NUP, obtaining the estimated increased traffic value V after the cell obtains the expansion resources, specifically includes:

[0143] The estimated growth traffic value of each cell i to be expanded after obtaining the expansion resources is obtained according to the following formula: V i =DFVI i* NUP i .

[0144] In this embodiment, step S3 corresponds to Figure 2 Step S105 shown in the figure is to estimate the traffic value V of the cell to be expanded after the expansion. i =DFVI i* NUP i .

[0145] In one implementation, S4, making a cell expansion decision according to V, specifically includes:

[0146] Select V based on the preset quantity threshold or the preset estimated growth traffic value threshold. i The capacity of several cells with high capacity to be expanded is expanded.

[0147] In this embodiment, step S4 corresponds to Figure 2 Step S106 shown in FIG. 106, select V i The cells with the highest capacity to be expanded are expanded. Assuming that only 5 cells can be expanded, select V i The top five communities to be expanded will be expanded.

[0148] The following is an example to describe the present embodiment:

[0149] Assuming that there are three cells A, B and C to be expanded, the above values ​​corresponding to the three cells are shown in Table 3. Some data need to be calculated. For convenience, they have been calculated and filled in the table below. However, the current expansion resources are limited, so only two cells are selected for expansion.

[0150] Table 3 Example of parameters of cells to be expanded

[0151] parameter Cell A to be expanded Cell B to be expanded Cell C to be expanded <![CDATA[R i ]]> 20000 30000 25000 <![CDATA[K i ]]> 150GB 200GB 300GB <![CDATA[Q i ]]> 0.3 0.2 0.2 <![CDATA[U i ]]> 0.3 0.4 0.2 <![CDATA[C i ]]> 3000 2000 2500 Wi 20 10 8.33 <![CDATA[W sum ]]> 38.33 38.33 38.33 <![CDATA[U current,i ]]> 120 130 100 <![CDATA[Gmarket i ]]> 0.2 0.1 0.3 <![CDATA[ARPU i ]]> 50 40 30 <![CDATA[DFVI i ]]> 5.739130435 8.869565217 2.608695652 <![CDATA[NUP i ]]> 7200 5720 3900 <![CDATA[V i ]]> 41321.74 50733.91 10173.91

[0152] Through the above calculation, it can be seen that the capacity expansion value of base station cell A is 41,321.74 yuan, the capacity expansion value of base station cell B is 50,733.91 yuan, and the capacity expansion value of base station cell C is 10,173.91 yuan. The capacity expansion value of base station cells A and B is greater, so they are given priority for expansion.

[0153] This embodiment proposes an innovative method based on the combination of service quality score, user demand intensity, total traffic revenue, and dynamic traffic value index (DFVI) to optimize the operator's process in capacity expansion decision-making and resource allocation. The main innovations include:

[0154] 1) Multi-dimensional comprehensive scoring system: By comprehensively considering the service quality, user needs and economic benefits of the cell, DFVI, as a dynamic adjustment indicator, can help operators more accurately evaluate the priority of the cell in capacity expansion. This method is not only based on historical data, but also takes into account real-time changes in user needs and fluctuations in service quality, ensuring that capacity expansion resource allocation is more intelligent and reasonable.

[0155] 2) Weight-based service quality scoring model: By dynamically adjusting the weights of each indicator (such as w L 、w P and w S ), the model can be personalized according to different application scenarios, network types, user needs, etc. Different from the traditional single service quality evaluation method, this model is more flexible and adaptable, and can be adjusted at any time to ensure the effectiveness of expansion decisions.

[0156] 3) Innovative evaluation method combining user demand intensity and service quality: By combining user demand intensity with service quality scores, this evaluation method can effectively predict users' real demand for network resources and ensure that the needs of key user groups can be met first during peak hours.

[0157] 4) Economic benefit orientation based on total traffic revenue: The user composition, package type and business scenarios of different cells will lead to significant differences in the economic benefits of traffic. The innovation lies in dynamically optimizing the allocation of expansion resources through traffic revenue indicators, ensuring that cells with the highest resource input-output ratio are given priority to expansion resources, thereby improving the overall benefits of operators.

[0158] 5) Innovative application of Dynamic Traffic Value Index (DFVI): DFVI not only integrates multi-dimensional factors, but also makes expansion decisions forward-looking and adaptive through dynamic adjustment. It can adjust the priority ranking according to real-time data changes, ensuring that the allocation of expansion resources does not only rely on historical data, but also follows the rapid changes in the market and user behavior.

[0159] The method provided in this embodiment estimates the growth of traffic after expansion and the corresponding value through information such as user consumption and traffic of the cell to be expanded. It can be combined with the intelligent diagnosis software of the expansion strategy to manage and optimize the mobile communication network more scientifically and efficiently, effectively cope with various network challenges, and quickly respond to user complaints to reduce the complaint rate, thereby improving the overall operational efficiency and service quality.

[0160] Embodiment 2:

[0161] like Figure 3 As shown, the present disclosure provides a cell expansion decision device, the device comprising:

[0162] Index module 1 is used to obtain the dynamic traffic value index DFVI of the cell based on the historical service data and historical user information of the cell. DFVI comprehensively represents the service quality, user demand and economic benefits of the cell;

[0163] Traffic estimation module 2, used to obtain the estimated increased traffic NUP of the cell according to the service quality of the cell after the cell obtains the expansion resources;

[0164] The value estimation module 3 is connected to the index module 1 and the traffic estimation module 2, and is used to obtain the estimated increased traffic value V after the cell obtains the expansion resources according to the DFVI and NUP;

[0165] The decision module 4 is connected to the value estimation module 3 and is used to make a cell expansion decision based on V.

[0166] In one embodiment, the index module 1 specifically includes:

[0167] The expansion cell unit is used to obtain the total number of cells to be expanded I;

[0168] The service data unit is connected to the expansion cell unit and is used to obtain the historical service data of each cell to be expanded i∈I. The historical service data includes the total traffic K generated by the cell to be expanded i in the historical time period i , Number of access users D i , the first delay rate L i , the first packet loss rate P i , first user feedback score S i , operating costs C i ;

[0169] The user information unit is connected to the expansion cell unit and is used to obtain the historical user information of each cell to be expanded i∈I, where the historical user information includes the traffic K generated by each user n∈N connecting to the cell to be expanded i among the N users accessed by the cell to be expanded i within the historical time period. n 、Consumption n ;

[0170] The service quality unit is connected to the service data unit and is used to obtain the first service quality score of the cell i to be expanded: Q i =w L *(1-L i )+w P *(1-P i )+w S *S i , where w L 、w P and w S is the weight of the first delay rate, the first packet loss rate and the first user feedback score, the sum of which is 1;

[0171] The user demand unit is connected to the service data unit and is used to obtain the user demand intensity of the cell i to be expanded: U i =D i / D sum , D i is the number of users accessing the cell i to be expanded during the historical period, D sum is the total number of access users in all cells to be expanded during the historical period;

[0172] The economic benefit unit is connected with the user information unit and the service data unit to obtain the total traffic revenue of the cell i to be expanded: Get the unit traffic operation cost of the cell i to be expanded: W i =C i / K i ;

[0173] The value index unit is connected with the service quality unit, user demand unit and economic benefit unit to obtain the dynamic traffic value index of the cell i to be expanded: DFVIi =(R i / K i ×U i ×Q i )×(1-W i / W sum ), where W sum Represents the total unit traffic operation cost of all cells to be expanded.

[0174] In one embodiment, wherein:

[0175] First user feedback rating S i Obtained through user satisfaction surveys, with values ​​between 0 and 1;

[0176] The first delay rate L i The number of connections for which the delay of the cell i to be expanded exceeds the preset time / the total number of connections;

[0177] Operating costs i Including: equipment cost, maintenance cost, personnel cost, and energy cost.

[0178] In one implementation, the traffic estimation module 2 specifically includes:

[0179] A capacity expansion allocation unit, used to allocate capacity expansion resources to all cells to be expanded i=[1,I];

[0180] The growth prediction unit is connected to the expansion allocation unit and is used to predict the user growth rate Gmarket of the cell i to be expanded according to the service quality after the expansion resources are allocated to each cell i to be expanded. i ;

[0181] The traffic estimation calculation unit is connected to the growth prediction unit to obtain the estimated growth traffic after each cell i to be expanded is allocated with expansion resources: NUP i =U current,i *(1+Gmarket i )*ARPU i , where U current,i is the current number of users in the cell i to be expanded; ARPU i It is the predicted usage traffic per user in the cell i to be expanded obtained based on the historical average usage traffic of each user.

[0182] In one implementation, the growth prediction unit specifically includes:

[0183] A training data unit is used to obtain the historical user growth data of the cell, as well as the corresponding historical service quality data, historical user behavior data and historical regional competition data to form model training data;

[0184] A model training unit, connected to the training data unit, for training a cell user growth prediction model according to the model training data;

[0185] A prediction data unit, used to obtain expected service quality data, current user behavior data and current regional competition data of each to-be-expanded cell i after allocating expansion resources, so as to form prediction input data;

[0186] The growth prediction calculation unit is connected to the model training unit and the prediction data unit, and is used to input the prediction input data into the trained cell user growth prediction model to obtain the user growth rate Gmarket of each cell i to be expanded. i .

[0187] In one embodiment, wherein:

[0188] The historical user growth data includes the historical user number sequence U obtained at equal time intervals t-m ,U t-m+1 ,…,U t , and / or, obtain the historical user growth rate sequence G according to the historical user number sequence t-m ,G t-m+1 ,…,G t , where G t =(U t -U t-1 ) / U t-1 ×100%, t is the current time point, t-1 is the previous time point;

[0189] Historical service quality data SQ t Including historical average delay rate, historical average packet loss rate, historical average user feedback score obtained at equal time intervals, and / or historical average service quality score obtained based on the historical average delay rate, historical average packet loss rate, and historical average user feedback score;

[0190] Historical user behavior data UB t Including historical user average usage traffic, historical user average connection time, historical number of active users, historical regional competition data CE obtained at equal time intervals t Including the number of historical competitors’ users, historical competitors’ service quality scores, and historical competitors’ prices obtained at equal time intervals;

[0191] The cell user growth prediction model specifically adopts a linear regression model: G t =β0+β1*SQ t +β2*UB t +β3*CE t +ε, where β0, β1, β2, β3 are model parameters and ε is the error term.

[0192] In one embodiment, the value estimation module 3 is specifically used for:

[0193] The estimated growth traffic value of each cell i to be expanded after obtaining the expansion resources is obtained according to the following formula: V i =DFVI i* NUP i .

[0194] In one embodiment, the decision module 4 is specifically configured to:

[0195] Select V based on the preset quantity threshold or the preset estimated growth traffic value threshold. i The capacity of several cells with high capacity to be expanded is expanded.

[0196] Embodiment 3:

[0197] Embodiment 3 of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the cell expansion decision method described in Embodiment 1 or the cell expansion decision device described in Embodiment 2 is implemented.

[0198] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program elements or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0199] In addition, the present disclosure may also provide a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor runs the computer program stored in the memory, the processor executes the cell expansion decision method as described in Example 1. The computer device may be the cell expansion decision device as described in Example 2.

[0200] The memory is connected to the processor, the memory may be a flash memory or a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.

[0201] Embodiments 1-3 of the present disclosure provide a cell expansion decision method, a cell expansion decision device and a computer-readable storage medium, which obtain a dynamic traffic value index DFVI that comprehensively represents the service quality, user needs and economic benefits of the cell, obtain the estimated growth traffic value V of the cell expansion according to the DFVI and the estimated growth traffic NUP of the cell, make cell expansion decisions according to V, optimize the operator's expansion decisions, and thus improve the expansion value.

[0202] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A cell expansion decision method, characterized in that: The method comprises: According to the historical service data and historical user information of the cell, the dynamic traffic value index DFVI of the cell is obtained. DFVI comprehensively represents the service quality, user demand and economic benefits of the cell. Obtain the estimated increased traffic NUP of the cell based on the service quality of the cell after it obtains the expansion resources; According to DFVI and NUP, obtain the estimated increased traffic value V after the cell obtains the expansion resources; Make cell expansion decisions based on V.

2. The method according to claim 1, characterized in that According to the historical service data and historical user information of the cell, the dynamic traffic value index DFVI of the cell is obtained, including: Get the total number of cells to be expanded I; Get the historical service data of each cell to be expanded i∈I, the historical service data includes the total traffic K generated by the cell to be expanded i in the historical time period i , Number of access users D i , the first delay rate L i , the first packet loss rate P i , first user feedback score S i , operating costs C i ; Obtain the historical user information of each cell to be expanded i∈I, where the historical user information includes the traffic K generated by each user n∈N connecting to the cell to be expanded i among the N users accessed by the cell to be expanded i within the historical time period n 、Consumption n ; Get the first service quality score of the cell i to be expanded: Q i =w L *(1-L i )+w P *(1-P i )+w S *S i , where w L 、w P and w S is the weight of the first delay rate, the first packet loss rate and the first user feedback score, the sum of which is 1; Get the user demand intensity of the cell i to be expanded: U i =D i / D sum , D i is the number of users accessing the cell i to be expanded during the historical period, D sum is the total number of access users in all cells to be expanded during the historical period; Get the total traffic revenue of the cell i to be expanded: Get the unit traffic operation cost of the cell i to be expanded: W i =C i / K i ; Get the dynamic traffic value index of the cell i to be expanded: DFVI i =(R i / K i ×U i ×Q i )×(1-W i / W sum ), where W sum Represents the total unit traffic operation cost of all cells to be expanded.

3. The method according to claim 2, characterized in that in: First user feedback rating S i Obtained through user satisfaction surveys, with values ​​between 0 and 1; The first delay rate L i The number of connections for which the delay of the cell i to be expanded exceeds the preset time / the total number of connections; Operating costs i Including: equipment cost, maintenance cost, personnel cost, and energy cost.

4. The method according to claim 1, characterized in that: According to the service quality of the cell after it obtains the expansion resources, the estimated increase in traffic NUP of the cell is obtained, including: Allocate expansion resources for all cells to be expanded i=[1,I]; According to the service quality after allocating expansion resources to each cell i to be expanded, predict the user growth rate Gmarket of the cell i to be expanded i ; Get the estimated growth traffic after allocating expansion resources to each cell i to be expanded: NUP i =U current,i *(1+Gmarket i )*ARPU i , where U current,i is the current number of users in the cell i to be expanded; ARPU i It is the predicted usage traffic per user in the cell i to be expanded obtained based on the historical average usage traffic of each user.

5. The method according to claim 4, characterized in that According to the service quality after allocating expansion resources to each cell i to be expanded, predict the user growth rate Gmarket of the cell i to be expanded i , specifically including: Obtain the historical user growth data of the cell, as well as the corresponding historical service quality data, historical user behavior data, and historical regional competition data to form model training data; Train the community user growth prediction model based on the model training data; Obtaining expected service quality data, current user behavior data, and current regional competition data of each to-be-expanded cell i after allocating expansion resources to form prediction input data; Input the predicted input data into the trained cell user growth prediction model to obtain the user growth rate Gmarket of each cell i to be expanded. i .

6. The method according to claim 5, characterized in that in: The historical user growth data includes the historical user number sequence U obtained at equal time intervals. t-m ,U t-m+1 ,…,U t , and / or, obtain the historical user growth rate sequence G according to the historical user number sequence t-m ,G t-m+1 ,…,G t , where G t =(U t -U t-1 ) / U t-1 ×100%, t is the current time point, t-1 is the previous time point; Historical service quality data SQ t Including historical average delay rate, historical average packet loss rate, historical average user feedback score obtained at equal time intervals, and / or historical average service quality score obtained based on the historical average delay rate, historical average packet loss rate, and historical average user feedback score; Historical user behavior data UB t Including historical user average usage traffic, historical user average connection time, historical number of active users, historical regional competition data CE obtained at equal time intervals t Including the number of historical competitors’ users, historical competitors’ service quality scores, and historical competitors’ prices obtained at equal time intervals; The cell user growth prediction model specifically adopts a linear regression model: G t =β0+β1*SQ t +β2*UB t +β3*CE t +ε, where β0, β1, β2, β3 are model parameters and ε is the error term.

7. The method according to any one of claims 2 to 6, characterized in that: According to DFVI and NUP, the estimated increase in traffic value V after the cell obtains expansion resources is obtained, including: The estimated growth traffic value of each cell i to be expanded after obtaining the expansion resources is obtained according to the following formula: V i =DFVI i* NUP i .

8. The method according to claim 7, characterized in that The cell expansion decision is made based on V, including: Select V based on the preset quantity threshold or the preset estimated growth traffic value threshold. i The capacity of several cells with high capacity to be expanded is expanded.

9. A cell expansion decision device, characterized in that: The device comprises: The index module is used to obtain the dynamic traffic value index DFVI of the cell based on the historical service data and historical user information of the cell. DFVI comprehensively represents the service quality, user demand and economic benefits of the cell; The traffic estimation module is used to obtain the estimated increased traffic NUP of the cell according to the service quality of the cell after the cell obtains the expansion resources; The value estimation module is connected with the index module and the traffic estimation module, and is used to obtain the estimated increased traffic value V after the cell obtains the expansion resources according to DFVI and NUP; The decision module is connected to the value estimation module and is used to make a cell expansion decision based on V.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the cell expansion decision method according to any one of claims 1 to 8 is implemented.

Images