Base station site selection method and related equipment for co-building and sharing network

Abstract

The present disclosure provides a base station site selection method and related equipment for co-building and sharing networks. The method includes: respectively obtaining the first user behavior data of the contractor and the second user behavior data of the sharer; respectively inputting the first user behavior data and the second user behavior data into the first business model and the second business model to obtain the first business score and the second business score and their corresponding grid information; determining the business score of the target grid according to the first business score and the second business score and their corresponding grid information; respectively obtaining the first network data and the second network data of the contractor and the sharer in the target grid; inputting the business score, the first network data and the second network data of the target grid into the grid scoring model to obtain the site selection prediction score of the target grid. The method can obtain a more accurate site selection prediction score, thereby improving the accuracy of base station site selection and ensuring the security of user data and operator network data.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a base station site selection method, device, electronic device and storage medium for co-building and sharing a network. Background Art

[0002] With the rapid development of communication technology, the commercial use of 5G base stations has been put on the agenda, so the reasonable planning of site for the construction of 5G base stations has become an important issue. In related technologies, each operator uses its own data to plan the site selection of base stations. The data source is single and the accuracy of base station site selection is poor.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The purpose of the present disclosure is to provide a base station site selection method, device, electronic device and storage medium for jointly building and sharing a network. The method can obtain a more accurate site selection prediction score, thereby improving the accuracy of base station site selection and ensuring the security of user data and operator network data.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] The disclosed embodiment provides a base station site selection method for a co-built and shared network, wherein the co-built and shared network includes a builder and a sharer, and the method includes: respectively obtaining first user behavior data of the builder and second user behavior data of the sharer; respectively inputting the first user behavior data and the second user behavior data into a first business model and a second business model to obtain a first business score and a second business score and corresponding grid information; determining a business score of a target grid according to the first business score and the second business score and corresponding grid information; respectively obtaining first network data and second network data of the target grid of the builder and the sharer; and inputting the business score of the target grid, the first network data and the second network data into a grid scoring model to obtain a site selection prediction score of the target grid.

[0007] The embodiment of the present disclosure provides a base station site selection device for co-building and sharing a network, including: a user behavior data acquisition module, used to respectively acquire first user behavior data of the construction party and second user behavior data of the sharing party; a business score acquisition module, used to input the first user behavior data and the second user behavior data into a first business model and a second business model, respectively, to obtain a first business score and a second business score and their corresponding grid information; a business score determination module, used to determine the business score of a target grid according to the first business score and the second business score and their corresponding grid information; a network data acquisition module, used to respectively acquire first network data and second network data of the construction party and the sharing party at the target grid; and a site selection prediction score acquisition module, used to input the business score of the target grid, the first network data and the second network data into a grid scoring model, to obtain a site selection prediction score of the target grid.

[0008] An embodiment of the present disclosure provides an electronic device, including: at least one processor; a storage terminal device, used to store at least one program, when the at least one program is executed by the at least one processor, the at least one processor implements any of the above-mentioned base station site selection methods for jointly building a shared network.

[0009] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, any of the above-mentioned base station site selection methods for jointly building and sharing a network is implemented.

[0010] The base station site selection method for a co-built and shared network provided in the embodiments of the present disclosure can, on the one hand, obtain more accurate business scores by utilizing user behavior data of multiple operators (i.e., builders and sharers); and can obtain more accurate site selection prediction scores by utilizing the obtained business scores and network data of multiple operators, thereby improving the accuracy of base station site selection; and on the other hand, can ensure the security of user data by processing the user behavior data of builders and sharers through business models; and can ensure the security of operator network data by processing the network data of builders and sharers through grid scoring models.

[0011] 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

[0012] 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.

[0013] Figure 1 It is a flow chart showing a method for selecting a base station site for a co-built and shared network according to an exemplary embodiment.

[0014] Figure 2 It is a schematic diagram of a business model jointly constructed by multiple parties according to an example.

[0015] Figure 3 It is a schematic diagram of constructing a base station site selection model according to an example.

[0016] Figure 4 It is a block diagram of a base station site selection device for co-building and sharing a network according to an exemplary embodiment.

[0017] Figure 5 is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0018] 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 limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0019] 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 thus 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 terminal devices and / or microcontroller terminal devices.

[0020] Hereinafter, each step of the base station site selection method for co-building and sharing a network in an exemplary embodiment of the present disclosure will be described in more detail with reference to the accompanying drawings and embodiments.

[0021] Figure 1The present invention is a flowchart of a method for selecting a base station site for a co-built and shared network according to an exemplary embodiment. The co-built and shared network may include one or more contractors and one or more sharing parties. The method provided in the embodiment of the present disclosure may be executed by a server of a contractor, a sharing party, or a third party, and the present disclosure does not limit this.

[0022] like Figure 1 As shown, the base station site selection method for co-building and sharing a network provided by the embodiment of the present disclosure may include the following steps.

[0023] In step S102, the first user behavior data of the contractor and the second user behavior data of the sharing party are obtained respectively.

[0024] In the embodiments of the present disclosure, there may be one or more contractors and one or more sharing parties, and the following description is made by taking one contractor and one sharing party as an example, but the present disclosure is not limited thereto. Both the contractor and the sharing party may be operators.

[0025] In the disclosed embodiment, the builder and the sharer respectively prepare their own user behavior data, which may include but are not limited to: user basic data, Internet behavior data, traffic usage data, user location information data, user communication behavior data, user terminal data information, network holiday data and other attributes, as well as user 5G network access information.

[0026] In step S104, the first user behavior data and the second user behavior data are input into the first business model and the second business model respectively to obtain the first business score and the second business score and their corresponding grid information.

[0027] In the disclosed embodiment, the first user behavior data may be input into the first business model to obtain a first business score and its corresponding grid information, and the second user behavior data may be input into the second business model to obtain a second business score and its corresponding grid information.

[0028] Among them, the grid information can represent a region, and multiple partners (i.e. the above-mentioned contractors and sharing parties) use a unified grid division standard.

[0029] In the embodiment of the present disclosure, the first user behavior data and the second user behavior data are respectively input into the first business model and the second business model, so as to obtain the first business scores and the second business scores of different users in different time periods in different grids.

[0030] In an exemplary embodiment, the first business model includes at least one of a first user value model, a first network perception scoring model and a first 5G network access probability model, the second business model includes at least one of a second user value model, a second network perception scoring model and a second 5G network access probability model, the first business score includes at least one of a user value score, a network perception score and a 5G network access demand score, and the second business score includes at least one of a user value score, a network perception score and a 5G network access demand score.

[0031] For example, when the business model is a user value model, the user value score is output; when the business model is a network perception model, the network perception score is output; when the business model is a 5G network access probability model, the 5G network access demand score is output.

[0032] In the embodiment of the present disclosure, the first business model and the second business model can be trained by the following method.

[0033] In an exemplary embodiment, the first training user behavior data of the contractor and the second training user behavior data of the sharer are respectively obtained; the first training user behavior data and the second training user behavior data are respectively binned to obtain first binning results and second binning results; the first binning results and the second binning results are sent to a convergence center, so that the convergence center determines and returns splitting point data according to the first binning results and the second binning results; a first decision tree model is constructed according to the splitting point data and the first training user behavior data, and a second decision tree model is constructed according to the splitting point data and the second training user behavior data; the first decision tree model and the second decision tree model are trained to obtain a first business model and a second business model.

[0034] In the disclosed embodiment, the first training user behavior data of the contractor can be obtained, the first training user behavior data can be binned, a first binning result can be obtained, and the first binning result can be sent to the convergence center; the second training user behavior data of the sharer can be obtained, the second training user behavior data can be binned, a second binning result can be obtained, and the second binning result can be sent to the convergence center; the convergence center determines the binning boundaries according to the first binning result and the second binning result, and returns the binning boundaries to the contractor and the sharer, and the contractor and the sharer respectively re-bin according to the binning boundaries, calculate the gradient information of the training data according to the training labels, generate a histogram and send it to the convergence center; the convergence center converges the histograms of the contractor and the sharer, and then calculates the optimal splitting point, and returns the optimal splitting point to the contractor and the sharer; the contractor and the sharer respectively split according to the optimal splitting point to obtain a complete decision tree model; the contractor and the sharer respectively calculate the loss function according to the decision tree model, and complete the construction of the business model when the loss reaches the convergence condition.

[0035] The following takes the business model as a network perception scoring model as an example to illustrate how to perform joint calculation (i.e., the model training process). The joint calculation process of the user value model and the 5G network access probability model is similar to the network perception scoring model, and will not be repeated in this disclosure.

[0036] Each participating operator prepares its own training data according to the agreed data features, the main features of which include but are not limited to user basic data, Internet behavior data, traffic usage data, user location information data, user communication behavior data, user terminal data information, network measurement data and other attributes;

[0037] The model label is known user network perception information (such as known user network perception score), and the user's perception of the network is related to time and region.

[0038] The data format may be as shown in Table 1, for example.

[0039] Table 1

[0040] User ID Grid id Label Time Feature 1 …… Features A 3 60 8：00 …… …… …… A 2 70 12：00 …… …… …… B 2 80 14：00 …… …… …… B 5 90 20：00 …… …… …… …… …… …… …… …… …… ……

[0041] In this calculation mode, the data formats of various operators participating in the calculation are aligned, including unified encoding of some discrete features, unified preprocessing of numerical features, and each operator has its own data label.

[0042] The main steps for each operator (also referred to as each participant) to perform distributed security modeling and build a joint model may include:

[0043] i. Each participant negotiates and specifies a random number x, such that x1+x2+…+x n =0;

[0044] ii. Each participant performs statistical binning on its local feature data according to the modeling parameters to obtain binning results, adds a random number x to the binning results, and sends them to the aggregation center;

[0045] iii. The aggregation center adds up and averages the bin boundaries and returns it to each participant;

[0046] iv. Each participant re-bins according to the received bin boundaries, and then calculates the gradient and second-order gradient of its own data based on its own labels, aggregates them into a histogram, and then adds a random number x to the result and transmits it to the aggregation center;

[0047] v. The aggregation center aggregates the histograms of each participant and calculates the best split point, and returns the calculation result to each participant;

[0048] vi. Each participant splits according to the splitting point, repeating the above steps to continue splitting until a complete tree model is obtained;

[0049] vii. Each participant calculates the loss function based on the obtained tree model and determines whether the loss reaches the convergence condition; if the pre-set convergence condition is reached, proceed to the next step; if the pre-set convergence condition is not reached, repeat steps i-vi;

[0050] viii. The loss reaches the convergence condition and the network perception scoring model is built.

[0051] Each participant obtains a fusion model (i.e., a network perception scoring model). In actual applications, each participant inputs their own data for model prediction. The model output format can be shown in Table 2.

[0052] Table 2

[0053] User ID Grid ID Time Length of stay Duration ratio …… Network Awareness Score A 1 7-9 50 10％ …… 100 A 4 9-12 150 30％ …… 70 B 6 14-18 200 33％ …… 90 B 10 19-22 90 15％ …… 80 …… …… …… …… …… …… ……

[0054] Figure 2 It is a schematic diagram of a business model jointly constructed by multiple parties according to an example.

[0055] Take the 5G network access probability model as an example, refer to Figure 2 In the disclosed embodiment, multiple operators (i.e., the construction party and the sharing party) prepare their own data, mainly including the following data: user basic data, Internet behavior data, traffic usage data, user location information data, user communication behavior data, user terminal data information, network holiday data and other attributes and user 5G network access information; each party counts the histogram information of the attribute data, and encrypts the histogram information and sends it to the aggregation center; the aggregation center aggregates the histogram information of multiple operators, calculates the optimal segmentation of the model, and then sends the optimal segmentation to the operators participating in the joint modeling; each operator uses the information sent by the aggregation center to update the model; each operator calculates the loss function according to the updated model, and determines whether the loss reaches the convergence condition; if the pre-set convergence condition is not met, repeat the above steps; if the pre-set convergence condition is met, the 5G network access probability model is completed.

[0056] In step S106, the business score of the target grid is determined according to the first business score and the second business score and their corresponding grid information.

[0057] In the embodiment of the present disclosure, referring to Table 2, the first service score and the second service score may be service scores of different users in different grids at different time periods, which may be converted into service scores in grid dimensions.

[0058] Specifically, the business score data corresponding to the same grid may be counted to obtain the business score of each grid.

[0059] For example, taking the target grid whose grid ID is 1 as an example, the network perception score of the grid whose ID is 1 is counted, which is the business score of the target grid.

[0060] In the embodiment of the present disclosure, the number of users staying in the target grid corresponding to each time period is obtained; the business score of the target grid is determined according to the number of users staying in the target grid corresponding to each time period and the first business score and the second business score of the target grid corresponding to each time period.

[0061] Specifically, the network perception score data of the same user in the same grid in different time periods are merged, and the user's network perception score V1 in the target grid = ∑ (the total number of users staying in the target grid in the i-th time period * the user's network perception score V0 in the i-th time period) / ∑ The number of users staying in the target grid in n time periods; where n is an integer greater than or equal to 1, and i is an integer greater than or equal to 1 and less than or equal to n.

[0062] Specifically, for mobile users who may appear in multiple grids in one day, data with short stay time can be eliminated and only TOPN data can be retained.

[0063] Specifically, the network perception score V2 of the target grid = ∑(the user's network perception score V1 in the target grid*the user's user value weight), wherein the user value weight can be calculated based on statistical methods such as the entropy method to obtain the entropy value of each feature, and then the feature entropy value is used to calculate the user weight; it can also be set according to actual conditions.

[0064] In the disclosed embodiment, the final score of each participant on the target grid can be used as an input feature of the next model.

[0065] In step S108, the first network data and the second network data of the contractor and the sharing party in the target grid are respectively obtained.

[0066] In the disclosed embodiment, the first network data of the contractor in each grid and the second network data of the sharing party in each grid can be obtained, and the first network data and the second network data corresponding to the target grid can be obtained according to the grid identifier of the target grid.

[0067] In an exemplary embodiment, the first network data includes at least one of the number of 4G base stations of the contractor, the network coverage of the contractor, the network usage of the contractor, and the number of users of the contractor, and the second network data includes at least one of the number of 4G base stations of the sharer, the network coverage of the sharer, the network usage of the sharer, and the number of users of the sharer.

[0068] In step S110, the business score of the target grid, the first network data and the second network data are input into the grid scoring model to obtain the site selection prediction score of the target grid.

[0069] Among them, the site selection prediction score of the target grid can represent the network demand of the target grid (for example, 5G network demand).

[0070] In an exemplary embodiment, the above method may further include: determining whether to establish a base station at the target grid according to the site selection prediction score of the target grid.

[0071] In the disclosed embodiment, whether a 5G base station needs to be built in the geographical location corresponding to the target grid can be determined based on the site selection prediction score.

[0072] In the disclosed embodiment, the grid scoring model (also referred to as a base station site selection model) can be trained by the following method.

[0073] In an exemplary embodiment, first training sample data of a builder and second training sample data of a sharer are obtained respectively, the first training sample data including a grid identifier, training network data of the builder, a training business score and a model label; the second training sample data including a grid identifier, training network data of the sharer, and a training business score; an encryption algorithm is used to perform sample encryption collision on the first training network data and the second training sample data to obtain the common sample data of the builder and the sharer; a third decision tree model is constructed based on the common sample data and model labels of the builder and the sharer; and the third decision tree model is trained to obtain a grid scoring model.

[0074] Specifically, the base station site selection model can be constructed through the following steps.

[0075] a) The cooperating parties (i.e. the contractor and the sharing party) use the grid ID as the data ID, combine their respective roles, add the influencing characteristics of their respective base station site selection, and prepare modeling data. The main information is as follows:

[0076] The data of the contractor mainly includes grid ID (using the same grid encoding method as the sharing party), the number of 4G base stations of the contractor, the network coverage of the contractor, the network usage of the contractor, the number of users of the contractor, the business value of the users of the contractor (which can be output by the first business model), the network perception of the contractor (which can be output by the first business model), the traffic volume of the contractor, the network access demand of the users of the contractor (which can be output by the first business model), the regional construction cost and other characteristics, and the 5G construction status (model label); among which, the 5G construction status can be the user perception score of the constructed base station, or the user network demand of the grid corresponding to the constructed base station;

[0077] Sharing party data, mainly including grid ID, number of sharing party 4G base stations, sharing party network coverage, sharing party network usage, number of sharing party users, sharing party network perception (which can be output by the second business model), sharing party user business value (which can be output by the second business model), sharing party traffic volume, sharing party user network access requirements (which can be output by the second business model) and other characteristics

[0078] b) The sample IDs (grid IDs) of the cooperating parties are encrypted and collided using an encryption algorithm to find the common samples of all parties and prepare data: the common grids and their related features;

[0079] c) The contractor calculates the gradient information of each sample based on the model label (5G construction status) and encrypts it, and transmits it to the sharing party together with the grid ID;

[0080] d) The sharing party uses the encrypted information of the contractor to calculate the relevant features of its own attributes in the encrypted domain, and transmits the calculation results: {its own attribute ID, attribute segmentation threshold ID, left encrypted derivative sum} and other related information to the contractor;

[0081] e) The contractor decrypts the information sent by the sharing party, combines its own feature information and label information, and calculates the current optimal segmentation of the model (the optimal segmentation here is the same concept as the optimal segmentation in the business model, and different calculation methods can be used);

[0082] f) The contractor determines whether the optimal segmentation field is on its side; if not, it transmits the optimal segmentation attribute, attribute threshold ID and other information to the sharing party;

[0083] g) Each party retains its own segmentation attributes and information.

[0084] The above steps c)-g) are calculated repeatedly until the decision tree model converges, thus completing the construction of the base station site selection model.

[0085] Figure 3 It is a schematic diagram of constructing a base station site selection model according to an example.

[0086] refer to Figure 3, multiple operators (i.e., contractors and sharing parties) prepare data, and the main information is as follows: Sharing party data, mainly including grid ID, number of sharing party 4G base stations, sharing party network coverage, sharing party network usage, number of sharing party users, sharing party network perception, sharing party user business value, sharing party traffic volume, sharing party user network access needs and other characteristics; Contractor data, mainly including grid ID (using the same grid encoding method as the sharing party), number of contractor 4G base stations, contractor network coverage, contractor network usage, number of contractor users, contractor user business value, contractor network perception, contractor traffic volume, contractor user network access needs, regional construction costs and other characteristics, as well as 5G construction status (model label); Two The encryption algorithm is used to perform sample encryption collision on the sample ID of the party to obtain the shared samples of both parties: the shared grid and its related features; the contractor calculates the information of each sample according to the model label and encrypts it, and transmits the grid ID and the encrypted inverse to the sharing party; the sharing party uses the contractor's encrypted information to calculate the attribute-related features, and transmits its own attribute ID, attribute segmentation threshold ID, left encrypted derivative and other related information to the contractor; the contractor decrypts the information transmitted by the sharing party, and uses its own related information to calculate the optimal segmentation of the model; the contractor determines whether the optimal segmentation field is on its side; if not, the optimal segmentation attribute, attribute threshold ID and other information are transmitted to the sharing party; the two parties each save their own segmentation attributes and information; the above steps are repeated until the model converges.

[0087] The base station site selection method for a co-built and shared network provided in the embodiments of the present disclosure can, on the one hand, obtain more accurate business scores by utilizing user behavior data of multiple operators (i.e., builders and sharers); and can obtain more accurate site selection prediction scores by utilizing the obtained business scores and network data of multiple operators, thereby improving the accuracy of base station site selection; and on the other hand, can ensure the security of user data by processing the user behavior data of builders and sharers through business models; and can ensure the security of operator network data by processing the network data of builders and sharers through grid scoring models.

[0088] In addition, in some embodiments, the user behavior characteristics, network characteristics, regional characteristics and other multi-dimensional attributes of the existing networks of multiple operators are used to jointly construct a user value model, a network perception scoring model and a 5G network access probability model of the co-built network, and cross-operator calculations are performed under the condition of protecting user privacy to build a unified standard calculation model. At the same time, the increase in cross-operator data samples also greatly improves the accuracy of model calculations. The user network access probability, base station layout, network usage status of each operator are combined with multi-dimensional data inputs such as regional construction costs. The base station site selection model is constructed by sharing features, and the site selection prediction score of the regional grid is output. The influencing factors of base station site selection are analyzed from multiple angles of time, space, and users. At the same time, privacy-safe computing technology is used to calculate multi-party data features when necessary to achieve joint modeling and improve the accuracy of base station site selection under the conditions of network co-construction and sharing.

[0089] It should be understood that the above is only to help those skilled in the art better understand the embodiments of the present disclosure, and is not intended to limit the scope of the embodiments of the present disclosure. Based on the above examples given, those skilled in the art can obviously make various equivalent modifications or changes. For example, some steps in the above method may not be necessary, or some new steps may be added. Or a combination of any two or any multiple embodiments of the above. Such modifications, changes or combined solutions also fall within the scope of the embodiments of the present disclosure.

[0090] It should also be understood that the above description of the embodiments of the present disclosure focuses on emphasizing the differences between the various embodiments, and the same or similar points that are not mentioned can be referenced to each other. For the sake of brevity, they will not be repeated here.

[0091] It should also be understood that the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present disclosure.

[0092] It should also be understood that in the various embodiments of the present disclosure, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0093] The above text describes in detail an example of a base station site selection method for co-building and sharing a network provided by the present disclosure. It is understandable that, in order to implement the above functions, the computer device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0094] The following are embodiments of the device disclosed herein, which can be used to execute the method embodiments disclosed herein. For details not disclosed in the device embodiments disclosed herein, please refer to the method embodiments disclosed herein.

[0095] Figure 4 It is a block diagram of a base station site selection device for co-building and sharing a network according to an exemplary embodiment.

[0096] like Figure 4 As shown, the base station site selection device 400 for co-building and sharing a network may include: a user behavior data acquisition module 402, a service score acquisition module 404, a service score determination module 406, a network data acquisition module 408 and a site selection prediction score acquisition module 410.

[0097] Among them, the user behavior data acquisition module 402 is used to respectively acquire the first user behavior data of the contractor and the second user behavior data of the sharer; the business score acquisition module 404 is used to input the first user behavior data and the second user behavior data into the first business model and the second business model respectively, and obtain the first business score and the second business score and their corresponding grid information; the business score determination module 406 is used to determine the business score of the target grid according to the first business score and the second business score and their corresponding grid information; the network data acquisition module 408 is used to respectively acquire the first network data and the second network data of the contractor and the sharer in the target grid; the site selection prediction score acquisition module 410 is used to input the business score of the target grid, the first network data and the second network data into the grid scoring model, and obtain the site selection prediction score of the target grid.

[0098] In an exemplary embodiment, the above-mentioned device may also include: a business model training module, used to respectively obtain the first training user behavior data of the contractor and the second training user behavior data of the sharing party; respectively bin the first training user behavior data and the second training user behavior data to obtain the first binning result and the second binning result; send the first binning result and the second binning result to the convergence center, so that the convergence center determines and returns the splitting point data according to the first binning result and the second binning result; construct a first decision tree model according to the splitting point data and the first training user behavior data, and construct a second decision tree model according to the splitting point data and the second training user behavior data; train the first decision tree model and the second decision tree model to obtain the first business model and the second business model.

[0099] In an exemplary embodiment, the first business score includes a first business score of a target grid corresponding to multiple time periods, and the second business score includes a second business score of a target grid corresponding to multiple time periods; the business score determination module 406 is further used to obtain the number of users staying in the target grid corresponding to each time period; and determine the business score of the target grid according to the number of users staying in the target grid corresponding to each time period and the first business score and the second business score of the target grid corresponding to each time period.

[0100] In an exemplary embodiment, the above-mentioned device may also include: a grid scoring model training module, which is used to respectively obtain the first training sample data of the contractor and the second training sample data of the sharer, the first training sample data including the grid identifier, the training network data of the contractor, the training business score and the model label; the second training sample data including the grid identifier, the training network data of the sharer, and the training business score; using an encryption algorithm to perform sample encryption collision on the first training network data and the second training sample data to obtain the common sample data of the contractor and the sharer; constructing a third decision tree model based on the common sample data of the contractor and the sharer and the model label; training the third decision tree model to obtain the grid scoring model.

[0101] In an exemplary embodiment, the above-mentioned device may further include: a base station site selection module, configured to determine whether to establish a base station at the target grid according to the site selection prediction score of the target grid.

[0102] In an exemplary embodiment, the first business model includes at least one of a first user value model, a first network perception scoring model and a first 5G network access probability model, the second business model includes at least one of a second user value model, a second network perception scoring model and a second 5G network access probability model, the first business score includes at least one of a user value score, a network perception score and a 5G network access demand score, and the second business score includes at least one of a user value score, a network perception score and a 5G network access demand score.

[0103] In an exemplary embodiment, the first network data includes at least one of the number of 4G base stations of the contractor, the network coverage of the contractor, the network usage of the contractor, and the number of users of the contractor, and the second network data includes at least one of the number of 4G base stations of the sharer, the network coverage of the sharer, the network usage of the sharer, and the number of users of the sharer.

[0104] It should be noted that the block diagrams shown in the above figures are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor terminal devices and / or microcontroller terminal devices.

[0105] Figure 5 is a schematic diagram of a structure of an electronic device according to an exemplary embodiment. It should be noted that: Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0106] like Figure 5 As shown, the electronic device 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0107] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0108] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present disclosure are executed.

[0109] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, terminal device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, a terminal device or a device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, a terminal device or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0110] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor includes a sending unit, an acquisition unit, a determination unit, and a first processing unit. Among them, the names of these units do not constitute a limitation on the units themselves in certain cases, for example, the sending unit may also be described as "a unit that sends a picture acquisition request to the connected server."

[0112] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the following embodiments. For example, the electronic device may implement the following Figure 1 The steps shown.

[0113] According to one aspect of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in various optional implementations of the above-mentioned embodiments.

[0114] It should be understood that any number of elements in the drawings of the present disclosure is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.

[0115] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure 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 disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0116] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A base station site selection method for co-building and sharing a network, characterized in that: The co-construction and sharing network includes a construction party and a sharing party, and the method includes: Respectively obtaining the first user behavior data of the contractor and the second user behavior data of the sharing party; Inputting the first user behavior data and the second user behavior data into a first business model and a second business model respectively to obtain a first business score and a second business score and corresponding grid information thereof; Determine the business score of the target grid according to the first business score and the second business score and the corresponding grid information; Respectively obtain the first network data and the second network data of the contractor and the sharing party in the target grid; The business score of the target grid, the first network data and the second network data are input into a grid scoring model to obtain a site selection prediction score of the target grid.

2. The method according to claim 1, characterized in that Also includes: Respectively obtaining the first training user behavior data of the contractor and the second training user behavior data of the sharing party; Respectively binning the first training user behavior data and the second training user behavior data to obtain a first binning result and a second binning result; Sending the first binning result and the second binning result to a convergence center, so that the convergence center determines and returns split point data according to the first binning result and the second binning result; Building a first decision tree model according to the splitting point data and the first training user behavior data, and building a second decision tree model according to the splitting point data and the second training user behavior data; The first decision tree model and the second decision tree model are trained to obtain the first business model and the second business model.

3. The method according to claim 1, characterized in that: The first business score includes first business scores of target grids corresponding to multiple time periods, and the second business score includes second business scores of target grids corresponding to multiple time periods; Determining the business score of the target grid according to the first business score and the second business score and the corresponding grid information includes: Obtain the number of users staying in the target grid corresponding to each time period; The service score of the target grid is determined according to the number of users staying in the target grid corresponding to each time period and the first service score and the second service score of the target grid corresponding to each time period.

4. The method according to claim 1, characterized in that: Also includes: Respectively obtain the first training sample data of the contractor and the second training sample data of the sharer, wherein the first training sample data includes a grid identifier, the training network data of the contractor, a training business score and a model label; and the second training sample data includes a grid identifier, the training network data of the sharer, and a training business score; Using an encryption algorithm to perform sample encryption collision on the first training sample data and the second training sample data to obtain the shared sample data of the contractor and the sharing party; Constructing a third decision tree model according to the shared sample data of the contractor and the sharing party and the model label; The third decision tree model is trained to obtain the grid scoring model.

5. The method according to claim 1, characterized in that Also includes: Determine whether to establish a base station at the target grid according to the site selection prediction score of the target grid.

6. The method according to any one of claims 1 to 5, characterized in that: The first business model includes at least one of a first user value model, a first network perception scoring model and a first 5G network access probability model; the second business model includes at least one of a second user value model, a second network perception scoring model and a second 5G network access probability model; the first business score includes at least one of a user value score, a network perception score and a 5G network access demand score; the second business score includes at least one of a user value score, a network perception score and a 5G network access demand score.

7. The method according to any one of claims 1 to 5, characterized in that: The first network data includes at least one of the number of 4G base stations of the contractor, the network coverage of the contractor, the network usage of the contractor and the number of users of the contractor; the second network data includes at least one of the number of 4G base stations of the sharer, the network coverage of the sharer, the network usage of the sharer and the number of users of the sharer.

8. A base station site selection device for co-building and sharing a network, characterized in that: include: A user behavior data acquisition module, used to respectively acquire the first user behavior data of the contractor and the second user behavior data of the sharing party; A business score obtaining module, used to input the first user behavior data and the second user behavior data into a first business model and a second business model respectively, to obtain a first business score and a second business score and corresponding grid information thereof; A business score determination module, used to determine the business score of the target grid according to the first business score and the second business score and their corresponding grid information; A network data acquisition module, used to respectively acquire the first network data and the second network data of the contractor and the sharing party in the target grid; The site selection prediction score acquisition module is used to input the business score of the target grid, the first network data and the second network data into the grid scoring model to obtain the site selection prediction score of the target grid.

9. An electronic device, characterized in that: include: at least one processor; A storage device, used to store at least one program, when the at least one program is executed by the at least one processor, enables the at least one processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images