Network service area determination method, electronic equipment and storage medium
By using methods such as generating concave hulls and Bayesian optimizers, combined with geographic normalization, the problem of inconsistency between management areas and network service boundaries was solved, achieving more accurate network service area division and resource allocation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-01
- Publication Date
- 2026-04-07
AI Technical Summary
In existing technologies, the boundary of the management area lacks correlation with the boundary of network services, resulting in reduced accuracy of network resource allocation and inaccurate risk assessment results.
By acquiring network service information for a specified area, including measurement report data and service type for each cell, a concave hull is generated to characterize the network service boundary of the service type. The network service area is determined based on the concave hull. The concaveness parameter is adjusted using a Bayesian optimizer to optimize the generation of the concave hull. Finally, geographic normalization is performed to ensure that the network service area is aligned with the management area.
This enables more accurate determination of network service areas, improves the precision of network resource allocation and the effectiveness of risk assessment, and ensures that network service areas are more closely aligned with real network boundaries.
Smart Images
Figure CN121815192A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of communication technology, and in particular to a method for determining a network service area, an electronic device, and a storage medium. Background Technology
[0002] In the planning, optimization, and emergency support system of communication networks, the refined and standardized division of geographical space into network service areas (or service-aware geographical units) is a fundamental technical support for achieving efficient resource allocation, accurate risk assessment, and automated operation and maintenance management.
[0003] As the complexity of network services continues to increase, higher demands are placed on the accuracy of network service area (BSA) delineation. However, current technologies often use a single administrative region as one or more BSAs, and then provide network services based on these BSAs. Because the boundaries of these administrative regions lack a clear correlation with network services, significant discrepancies can arise between the BSA boundaries and the BSA boundaries. This reduces the accuracy of subsequent network resource allocation and affects the effectiveness of risk assessment results.
[0004] Therefore, determining a suitable network service area is a technical problem that urgently needs to be solved. Summary of the Invention
[0005] This application provides a method, electronic device, and storage medium for determining a network service area, used to identify a suitable network service area.
[0006] In a first aspect, embodiments of this application provide a method for determining a network service area, including: Obtain network service information for a specified area, where the specified area corresponds to multiple cells, and the network service information includes measurement report (MR) data for each cell and the service type for each cell; Based on the MR data corresponding to each service type of cell, a concave pod is generated for that service type, and the concave pod is used to characterize the network service boundary of that service type. Based on the concave packet of each service type, different network service areas are determined in the specified region.
[0007] Obtain network service information for a specified area, where the specified area corresponds to multiple cells, and the network service information includes measurement report (MR) data for each cell and the service type for each cell; Based on the MR data corresponding to each service type of cell, a concave pod is generated for that service type, and the concave pod is used to characterize the network service boundary of that service type. Based on the concave packet of each service type, different network service areas are determined in the specified region.
[0008] Secondly, embodiments of this application provide a network service area determination apparatus, comprising: The acquisition module is used to acquire network service information for a specified area, where the specified area corresponds to multiple cells, and the network service information includes the measurement report (MR) data for each cell and the service type for each cell. The generation module is used to generate a concave pod for each service type based on the MR data corresponding to the cell for each service type. The concave pod is used to characterize the network service boundary of the service type. The determination module is used to determine different network service areas in the specified area based on the emboss of each service type.
[0009] Thirdly, embodiments of this application provide an electronic device, including: at least one processor, and a memory communicatively connected to the at least one processor, wherein: The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the method for determining any of the aforementioned network service areas.
[0010] Fourthly, embodiments of this application provide a storage medium in which, when a computer program in the storage medium is executed by a processor of an electronic device, the electronic device is able to execute any of the above-described methods for determining network service areas.
[0011] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method for determining any of the aforementioned network service areas.
[0012] In this embodiment, network service information for a specified area is obtained. This specified area corresponds to multiple cells, and the network service information includes MR data for each cell and the service type for each cell. Based on the MR data for each service type, a concave pod representing the network service boundary of that service type is generated. Then, based on the concave pods for each service type, different network service areas are determined within the specified area. Thus, by introducing MR data that can depict network coverage and user experience, and combining it with the MR data for each service type to generate concave pods that represent the network service boundary of that service type, network service areas that better match the actual network boundary can be determined. Furthermore, the concave pods can more accurately describe the network service boundary; therefore, the determined network service areas are more appropriate. Attached Figure Description
[0013] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating a method for determining a network service area provided in this application embodiment; Figure 2 A flowchart for generating a concave hull for a business type is provided in an embodiment of this application; Figure 3 A flowchart for determining different network service areas in a specified region is provided as an embodiment of this application; Figure 4 A schematic diagram illustrating the overall process of determining a network service area provided in this application embodiment; Figure 5 This application provides a schematic diagram of an adaptive optimal hull generation process. Figure 6 A schematic diagram of a geographic normalization process provided in an embodiment of this application; Figure 7 A schematic diagram of a network service area determination device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the hardware structure of an electronic device for implementing a method for determining a network service area, provided in an embodiment of this application. Detailed Implementation
[0014] To determine a suitable network service area, embodiments of this application provide a method for determining a network service area, an electronic device, and a storage medium.
[0015] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.
[0016] For ease of understanding, the technical terms used in this application are as follows: 1. Concave hull (or concave hull profile).
[0017] The concave hull is a concept in computational geometry and spatial data analysis. It is a generalization or supplement to the convex hull, used to more accurately describe the boundary shape of a set of points, such as an MR dataset, especially when the point set distribution is non-convex and has concave characteristics. In this case, the concave hull reflects the true contour of the point set better than the convex hull. For a set of points, different values of the concavity parameter will result in different concave hulls. When the value approaches infinity, the concave hull will degenerate into a convex hull. When the value approaches 0, the boundary of the concave hull will shrink drastically and may break. Therefore, only appropriate values can yield a compact and connected concave hull.
[0018] 2. Network service area (or service-aware geographic unit) refers to the basic geographic management unit that is generated based on massive amounts of real MR data and through a series of processes in this application, and that reflects real network coverage, business relevance and geographic regularity.
[0019] In the planning, optimization, and emergency support system of communication networks, the refined and standardized division of network service areas in geographic space is a fundamental technical support for achieving efficient resource allocation, accurate risk assessment, and automated operation and maintenance management.
[0020] As the complexity of network services continues to increase, higher demands are placed on the accuracy of network service area (BSA) delineation. However, current technologies often use a single administrative region as one or more BSAs, and then provide network services based on these BSAs. Because the boundaries of these administrative regions lack a clear correlation with network services, significant discrepancies can arise between the BSA boundaries and the BSA boundaries. This reduces the accuracy of subsequent network resource allocation and affects the effectiveness of risk assessment results.
[0021] Therefore, in this embodiment of the application, MR data that can depict network coverage and user experience is introduced. By combining the MR data corresponding to the cell for each service type, a concave hull that can characterize the network service boundary of this service type is generated. This can determine a network service area that matches the real network boundary more accurately. Furthermore, the concave hull can more accurately describe the network service boundary, thus the determined network service area is more appropriate.
[0022] See Figure 1 , Figure 1 A flowchart of a method for determining a network service area provided in an embodiment of this application includes the following steps.
[0023] In step 101, network service information for a specified area is obtained. The specified area corresponds to multiple cells, and the network service information includes the MR data for each cell and the service type for each cell.
[0024] The designated area, such as a province, a city, or a town, usually corresponds to multiple neighborhoods. Furthermore, the designated area can be gridded, and the grid size can be determined according to actual needs.
[0025] In practical applications, MR data reported by terminals in a specified area within a given time period can be collected. Based on the reporting location contained in each MR data, the corresponding grid of this MR data (i.e., which grid the MR data was reported from) can be determined, and the corresponding cell can be identified by which this MR was reported. Each cell contains multiple grids, and the MR data reported to this cell from these grids constitutes the MR data corresponding to that cell.
[0026] It should be noted that a grid usually corresponds to multiple MR data, but these multiple MR data may be reported to different cells. Therefore, different cells may correspond to MR data in the same grid, but one MR data corresponds to only one cell.
[0027] In this way, determining the MR data corresponding to each cell in each grid can depict the actual network coverage and user experience of the cell, which is beneficial for subsequently determining the appropriate network service area.
[0028] In practical applications, based on the service data of each cell in a specified area, the density-based unsupervised clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) can be used to cluster the cells by business, thereby determining the business type of each cell, such as office buildings, residential buildings, scenic spots, etc.
[0029] The service data for each cell can include static service data and dynamic service data. Static service data can include cell parameters such as location, whether it is indoors or outdoors, which are used to characterize the static service characteristics of the cell; dynamic service data can include performance data such as Radio Resource Control (RRC) and traffic, which are used to characterize the dynamic service characteristics of the cell.
[0030] In step 102, based on the MR data corresponding to each service type cell, a concave hull is generated for each service type. The concave hull is used to characterize the network service boundary of the service type.
[0031] See Figure 2 , Figure 2 A flowchart for generating a concave hull for a business type is provided for an embodiment of this application, including the following steps.
[0032] In step 1021, a candidate concave hull is generated based on the MR data and concavity parameter values corresponding to each service type of cell. The concavity parameter values are determined by the Bayesian optimizer using a probability model. Initially, the model parameters of the probability model are preset values.
[0033] Generally, the smaller the value of the concavity parameter, the greater and more rugged the concavity of the hull; conversely, the larger the value of the concavity parameter, the smaller and smoother the concavity of the hull, and the closer it is to a convex hull. The model parameters of a probabilistic model can characterize the probability of different values of the concavity parameter being selected. A higher probability of a concavity parameter value being selected indicates a greater likelihood of obtaining a good evaluation result, while a lower probability indicates a greater likelihood of obtaining a bad evaluation result.
[0034] In practical applications, a candidate concave hull can be generated using the Alpha Shape algorithm based on the MR data and concavity parameter values corresponding to each service type of cell. For example, Delaunay triangulation is performed on the MR data corresponding to each service type of cell to obtain multiple triangles (or edges). Then, the circumcircle radius R of each triangle (or edge) is calculated, and triangles (or edges) with R smaller than the concavity parameter are selected. The outermost edge is extracted from these triangles (or edges), and connecting these edges forms a candidate concave hull.
[0035] In step 1022, the evaluation result of the candidate concave hull is determined according to the preset evaluation rules.
[0036] In practice, the evaluation results of candidate concave hulls can be determined according to the following steps.
[0037] The first step is to determine the data coverage score of the candidate notch based on the number of MR data entries contained in the candidate notch and the number of MR data entries corresponding to the cell of the corresponding service type.
[0038] for example, ; in, The data coverage score is given by N1, where N1 is the number of MR data entries contained in the candidate concave cell, and N2 is the number of MR data entries corresponding to the cell of the corresponding service type. The value of the concavity parameter is... The candidate indentation hull generated at that time.
[0039] The second step is to determine the compactness score of the candidate concave hull based on its area and perimeter.
[0040] for example, ; in, The compactness score is assigned to the candidate concave hull. Let be the area of the candidate concave hull. Let be the perimeter of the candidate concave hull.
[0041] The third step is to determine the area penalty score of the candidate concave hull based on the area of the candidate concave hull and the preset area threshold.
[0042] for example, ; in, The area penalty score is used to determine the candidate concave hull. This is a preset threshold.
[0043] Step 4: Determine the evaluation result of the candidate concave hull based on its data coverage score, compactness score, and area penalty score.
[0044] for example, ; in, It is the evaluation result (or comprehensive score) of the candidate concave hull. , , These are pre-determined weighting coefficients that can be adjusted according to specific business needs.
[0045] It should be noted that there is no strict sequential order between the first, second, and third steps mentioned above.
[0046] In step 1023, it is determined whether the loop termination condition is met. If not, proceed to step 1024; if yes, proceed to step 1026.
[0047] Among them, loop termination conditions include reaching the maximum number of loops or the evaluation results of the candidate concave hull reaching the preset convergence conditions.
[0048] In step 1024, the evaluation results of the candidate concave hull are provided to the Bayesian optimizer, which is then triggered to adjust the model parameters of the probabilistic model based on the evaluation results.
[0049] In its initial state, the Bayesian optimizer has a prior value, which assumes that all values of the concavity parameter have similar evaluation effects. After the iteration begins, it can gradually adjust the model parameters of the probability model based on the observed evaluation results of different values, making its prediction of how to obtain a good evaluation result more accurate.
[0050] In step 1025, the values of the concavity parameters, which are redefined by the Bayesian optimizer using the probabilistic model, are obtained, and the process returns to step 1021.
[0051] In step 1026, the candidate concave with the best evaluation result is determined as the concave for this business type.
[0052] In step 103, different network service areas in the specified area are determined based on the emboss of each service type.
[0053] In some embodiments, the octave of each service type can be determined as a network service area in a specified region.
[0054] In some embodiments, the network service area may be further refined based on the regional overlap and / or cross-management area situation of the network service area, so as to align it with the management area and make it more complete in terms of geographical topology.
[0055] See Figure 3 , Figure 3 A flowchart for determining different network service areas in a specified region, provided in an embodiment of this application, includes the following steps.
[0056] In step 1031, each service type's embossed area is used as an initial network service area.
[0057] Each network service area corresponds to a type of service.
[0058] In step 1032, when there is regional overlap between different network service areas, the outlines of the different network service areas are adjusted.
[0059] For each grid where different network service areas overlap, the network service areas can be counted based on the service type corresponding to each MR data entry in the grid. For example, the count of the network service area corresponding to a given service type is incremented by 1. Initially, the counts of different network service areas can all be 0. Then, based on the counting results, the network service area corresponding to this grid can be determined. For instance, the network service area with the highest count value is identified as the network service area corresponding to this grid. Finally, the outlines of the different network service areas are adjusted according to the network service areas corresponding to each grid where they overlap. In this way, the different network service areas do not overlap geographically, which is beneficial for subsequent network service deployment.
[0060] It should be noted that after the outline of a network service area is adjusted, it may still be a network service area, or it may result in at least two sub-service areas. For example, if a network service area is cut off in the middle by other network service areas, it will result in two sub-service areas.
[0061] In step 1033, when a network service area covers at least two management areas, the outline of the network service area is adjusted according to the boundaries of the at least two management areas.
[0062] Generally, a network service area covers several management areas. By adjusting the outline of the network service area according to the boundaries of the management areas, several sub-service areas are obtained. This avoids the final network service area spanning multiple management areas, thereby reducing the difficulty of network deployment and operation.
[0063] In practical applications, steps 1032 and 1033 can be performed either once or both times. The specific method can be determined by the technical personnel based on actual needs, and will not be elaborated here.
[0064] In step 1034, if a network service area is adjusted to obtain at least two sub-service areas, then a network service area and at least one alternative service area are selected from these at least two sub-service areas.
[0065] For example, the largest of these at least two sub-service areas can be designated as the network service area, while the other sub-service areas can be designated as alternative service areas.
[0066] In step 1035, each candidate service area is merged with an adjacent network service area according to a preset service area merging rule to obtain different network service areas in the specified area.
[0067] Each candidate service area can be adjacent to a network service area that is geographically contiguous with it. Pre-defined service area merging rules include, for example, that the combined area of the candidate service area and the network service area does not exceed the maximum area limit, and that the candidate service area and the network service area belong to the same management region.
[0068] Generally, a candidate service area can only be merged into a network service area if it has only one adjacent network service area, provided that the above rules are met. However, if a candidate service area has at least two adjacent network service areas, the affinity of each network service area can be determined, provided that the above rules are met. Affinity is used to characterize the probability of merging the candidate service area into the network service area, and then the candidate service area is merged into the network service area with the highest affinity.
[0069] In practice, the affinity of a network service area can be determined based on the shared geometric boundary between the alternative service area and the network service area, the number of MR data entries in the network service area, and the number of MR data entries in the alternative service area.
[0070] Generally, the affinity of a network service area can be determined according to the following rules: the shared geometric boundary between the candidate service area and the network service area is positively correlated with the affinity of the network service area; and the absolute value of the difference between the number of MR data records in the network service area and the number of MR data records in the candidate service area is positively correlated with the affinity of the network service area.
[0071] For example, the affinity of a network service area = the shared geometric boundary between the candidate service area and the network service area + the number of MR data records in the network service area / the number of MR data records in the candidate service area.
[0072] This application provides a scheme for automatically generating network service areas (FSAs) within a specified region from MR data corresponding to each cell and the service types of each cell. See also... Figure 4 , Figure 4 The schematic diagram of the overall process for determining a network service area provided in this application embodiment includes the following stages.
[0073] Phase A: Generation of MR data spatial index.
[0074] This stage is the offline preprocessing stage, which aims to establish a gridded spatial index relationship between the cell and MR data.
[0075] Input: MR data.
[0076] The processing flow includes: Cleaning and preprocessing: such as checking the completeness of MR data and removing duplicates from MR data; Spatial index mapping: Based on the reported location in each MR data, map each MR data to a grid; Relationship modeling and aggregation: A grid corresponds to multiple MR data, and the grid belongs to the cell to which each MR data was reported.
[0077] It should be noted that due to overlapping cell coverage, a single grid may belong to multiple cells simultaneously.
[0078] Output: Cell-Spatial Index-MR Data.
[0079] In other words, it can ultimately be determined which grids correspond to a cell and which MR data from these grids are reported to this cell.
[0080] Phase B: Cluster generation.
[0081] This stage aims to generate initial clusters related to the business based on the business attributes of the community itself, with each cluster representing a business type.
[0082] Input: The operating parameters and performance data of the community.
[0083] The processing flow includes: based on the cell's operating parameters and performance data, using the DBSCAN algorithm to cluster the cells for services, identifying a class of cells with similar service users and similar user behavior patterns, with each class of cells corresponding to a service type identifier ID.
[0084] Output: Cell-Service Type ID.
[0085] That is, the business type ID of each community can be obtained in the end.
[0086] Phase C: Service-aware geographic unit generation.
[0087] Input: The output of stage A and the output of stage B.
[0088] The processing flow includes three modules: adaptive optimal hull generation, conflict voting resolution, and geographic normalization. These three modules will be described in detail below.
[0089] Adaptive Optimal Concave Generation: This module intelligently optimizes and generates the optimal (or most suitable) concave (or geographical boundary) for each service type based on the MR data corresponding to the cells included in each service type.
[0090] Input: Cell-Spatial Index-MR data, and Cell-Service Type ID.
[0091] See Figure 5 , Figure 5 This application provides a schematic diagram of an adaptive optimal hull generation process, which includes the following steps.
[0092] 1. Initialization: Define the search space for the values of the concavity parameter and construct the multi-objective comprehensive evaluation function F(α).
[0093] Generally, the search space for concavity parameters is used to set a reasonable and limited range of values for the concavity parameters so that the most suitable concavity parameters can be automatically selected later.
[0094] The comprehensive evaluation function F(α) for the objective is as follows: ; ; ; ; Where Sα is the candidate concave hull generated when the concavity parameter is α; , , These are the weighting coefficients for each item, which can be adjusted according to business needs; , , These represent the data coverage score, compactness score (or geometric health score), and area penalty score for Sα, respectively. N1 is the number of MR data entries contained in the candidate concave hull, and N2 is the number of MR data entries corresponding to the cell of the corresponding service type. Let be the area of the candidate concave hull. Let be the perimeter of the candidate concave hull. This is a preset threshold.
[0095] 2. Intelligent selection: The Bayesian optimizer uses its internal probability model to select the value of the concavity parameter α.
[0096] The probability model inside the Bayesian optimizer is used to predict the value of the concavity parameter that will achieve the highest overall score. That is, α is the value that the Bayesian optimizer believes is most likely to produce a high score.
[0097] 3. Execution and Evaluation: Based on the MR data of cells with the same α and service type ID, a candidate indentation Sα is generated using the Alpha Shape algorithm, and the comprehensive score F(α) of the candidate indentation Sα is calculated.
[0098] Taking a cell with 10 MR data points for a certain service type as an example, we can first perform Delaunay triangulation on these 10 MR data points to obtain multiple triangles (or edges). Then, we can calculate the circumcircle radius R of each triangle (or edge), select triangles (or edges) with R less than α, extract the outermost edges of these triangles (or edges), and connect these edges to obtain the candidate concavity hull Sα of these 10 MR data points when the concavity parameter is α.
[0099] Then, substitute the relevant information of the candidate concave hull Sα into... Then, the comprehensive score F(α) of the candidate concave hull Sα can be obtained.
[0100] 4. Loop decision: Determine whether the convergence condition or the maximum number of iterations has been met. If not, proceed to step 5; if yes, proceed to step 6.
[0101] Among them, the convergence condition is that the comprehensive score F(α) of the candidate concave hull Sα is greater than the set value, and the number of iterations is the number of loops.
[0102] 5. Feedback Update: Feed α and F(α) back to the Bayesian optimizer in the form of key-value pairs. The Bayesian optimizer updates its internal probability model. Then, return to step 2.
[0103] The update objective is to enable the updated probability model to more accurately predict the α that will achieve the highest overall score.
[0104] 6. Output: Contour information of the highest-scoring α and the corresponding candidate concave hull Sα.
[0105] Among them, the corresponding candidate concave hull Sα is the most suitable concave hull for the corresponding business type.
[0106] In this embodiment, the concave hull for each business type is the optimal solution found under a complex multi-objective function, and the scientific validity and rationality of the concave hull boundary are relatively high.
[0107] Conflict resolution by voting: This module is used to resolve geographical overlap issues between different concave areas.
[0108] Generally, each concave hull can be defined as a network service area.
[0109] In practical applications, designated areas are gridded, which may lead to different network service areas covering the same grid. To address this, for each MR data entry in each grid covered by different network service areas, a voting process can be conducted based on the cell corresponding to that MR data, determining the network service area corresponding to the service type of that cell. The network service area with the most votes is then identified as the network service area for that grid. Subsequently, the outlines of different network service areas can be adjusted based on the network service areas corresponding to each grid covered by different network service areas.
[0110] After the above processing, some network service areas will remain as one network service area after adjustment, while others will become at least two sub-service areas after adjustment.
[0111] Geographical normalization: This module performs fine-grained post-processing on network service areas (and possibly sub-service areas) after conflict resolution through voting, ensuring the usability of their final form.
[0112] Input: The network service area (and possibly sub-service areas) after conflict resolution by voting, and the boundary of the management area.
[0113] See Figure 6 , Figure 6 This application provides a schematic diagram of a geographic normalization process, which includes the following steps.
[0114] 1. Boundary alignment and segmentation: The network service area / sub-service area is segmented according to the boundary of the management area.
[0115] The purpose of this step is to align the network service area with the management boundary, facilitating subsequent deployment and application.
[0116] 2. Alternate service area identification: If a network service area is adjusted to obtain at least two sub-service areas, the one with the largest area among these two sub-service areas is taken as the network service area, and the others are taken as alternative service areas.
[0117] 3. Neighbor discovery for alternative service areas: Identify the network service areas adjacent to each alternative service area.
[0118] 4. Screening of Network Service Areas that Can Be Merged: From the network service areas adjacent to each candidate service area, select network service areas that belong to the same management area as the candidate service area and whose area after merging with the candidate service area does not exceed the area limit. These network service areas are selected as candidate service areas that can be merged.
[0119] 5. Calculate the affinity of mergeable network service areas for each candidate service area: For each mergeable network service area of each candidate service area, determine the affinity of mergeable network service areas based on the shared boundary length (geometric) of the two service areas and the MR number of both sides.
[0120] For example, the affinity score of a mergeable network service area = the length of the shared boundary between the candidate service area and the mergeable network service area + the number of MR records in the mergeable network service area / the number of MR records in the candidate service area.
[0121] 6. Merging Decision: Based on the affinity of each candidate service area to the mergeable network service area, merge the candidate service area into the mergeable network service area with the highest affinity.
[0122] 7. Loop judgment: Determine whether all candidate service areas have been merged. If not, return to step 3; if yes, proceed to step 8.
[0123] 8. Output: Multiple service-aware geographic units.
[0124] Thus, in the service-aware geographic unit (MAU) generation stage, two major modules are introduced: Bayesian optimization-based adaptive optimal hull generation and geographic normalization. This ensures that the final generated MAU achieves optimal boundaries, regularity in shape, and alignment for management, allowing for seamless integration into application systems. Furthermore, complex expert decision-making processes (such as selecting concavity parameters and boundary correction) are transformed into automatically executable algorithms, achieving end-to-end automation from raw MR data to high-quality MAUs.
[0125] Based on the same technical concept, this application also provides a network service area determination device. The principle of the network service area determination device in solving the problem is similar to the above-mentioned network service area determination method. Therefore, the implementation of the network service area determination device can refer to the implementation of the network service area determination method, and the repeated parts will not be described again.
[0126] Figure 7 A schematic diagram of a network service area determination device provided in this application embodiment includes: The acquisition module 701 is used to acquire network service information of a specified area, wherein the specified area corresponds to multiple cells, and the network service information includes the measurement report (MR) data corresponding to each cell and the service type of each cell. The generation module 702 is used to generate a concave pod for each service type based on the MR data corresponding to the cell for each service type. The concave pod is used to characterize the network service boundary of the service type. The determination module 703 is used to determine different network service areas in the specified area based on the emboss of each service type.
[0127] In some embodiments, the generation module 702 is specifically used for: Based on the MR data and concavity parameter values corresponding to each service type of cell, a candidate concavity is generated. The concavity parameter values are determined by the Bayesian optimizer using a probability model. Initially, the model parameters of the probability model are preset values. The evaluation result of the candidate concave hull is determined according to the preset evaluation rules; The evaluation results are provided to the Bayesian optimizer, which then adjusts the model parameters of the probability model based on the evaluation results. Obtain the value of the concavity parameter as determined by the Bayesian optimizer using the probability model; The process involves generating a candidate concave hull based on the MR data and concavity parameter values corresponding to each service type of cell. This process continues until the loop termination condition is met, at which point the candidate concave hull with the best evaluation result is determined as the concave hull for the service type.
[0128] In some embodiments, the generation module 702 is specifically used for: The data coverage score of the candidate notch is determined based on the number of MR data entries contained in the candidate notch and the number of MR data entries corresponding to the cell of the service type. The compactness score of the candidate concave hull is determined based on its area and perimeter. The area penalty score of the candidate indentation is determined based on the area of the candidate indentation and a preset area threshold. The evaluation result of the candidate concave hull is determined based on the data coverage score, the compactness score, and the area penalty score.
[0129] In some embodiments, the determining module 703 is specifically used for: Each service type's emboss is used as an initial network service area. When different network service areas overlap, the contours of the different network service areas are adjusted. If a network service area is adjusted to obtain at least two sub-service areas, then select one network service area and at least one alternative service area from the at least two sub-service areas. According to the preset service area merging rules, each candidate service area is merged with the adjacent network service areas to obtain different network service areas in the specified area.
[0130] In some embodiments, the designated area is divided into multiple grids, and the MR data corresponding to each cell includes the MR data of the cell in the corresponding grid. The determining module 703 is specifically used for: For each grid that overlaps with the different network service areas, the different network service areas are counted according to the service type corresponding to each MR data in the grid, and the network service area corresponding to the grid is determined based on the counting results; The outlines of the different network service areas are adjusted according to the network service areas corresponding to each grid that overlaps with the different network service areas.
[0131] In some embodiments, the determining module 703 is further configured to: When a network service area covers at least two management areas, the outline of the network service area is adjusted according to the boundaries of the at least two management areas.
[0132] In some embodiments, the service type of each cell is determined based on the service data of the cell, which includes static service data and dynamic service data.
[0133] The module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. Coupling between modules can be achieved through interfaces, typically electrical communication interfaces, but mechanical interfaces or other types of interfaces are also possible. Therefore, modules described as separate components may or may not be physically separate; they can be located in one place or distributed across different locations on the same or different devices. The integrated modules described above can be implemented in hardware or as software functional modules.
[0134] Having introduced the method and apparatus for determining network service areas according to exemplary embodiments of this application, we will now introduce an electronic device according to another exemplary embodiment of this application.
[0135] The following reference Figure 8 To describe an electronic device 130 implemented according to this embodiment of the present application. Figure 8 The electronic device 130 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0136] like Figure 8 As shown, the electronic device 130 is presented in the form of a general electronic device. The components of the electronic device 130 may include, but are not limited to: at least one processor 131, at least one memory 132, and a bus 133 connecting different system components (including memory 132 and processor 131).
[0137] Bus 133 represents one or more of several bus structures, including a memory bus or memory controller, peripheral bus, processor, or local bus using any of the various bus structures.
[0138] The memory 132 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 1321 and / or cache memory 1322, and may further include read-only memory (ROM) 1323.
[0139] The memory 132 may also include a program / utility 1325 having a set (at least one) of program modules 1324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.
[0140] Electronic device 130 can also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), and with one or more devices that enable a user to interact with electronic device 130, and / or with any device that enables electronic device 130 to communicate with one or more other electronic devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 135. Furthermore, electronic device 130 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 136. As shown, network adapter 136 communicates with other modules used in electronic device 130 via bus 133. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0141] In an exemplary embodiment, the electronic device of this application may include at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, it enables the at least one processor to perform the steps of the method for determining any network service area provided in the embodiments of this application.
[0142] In an exemplary embodiment, a storage medium is also provided, which, when executed by a processor of an electronic device, enables the electronic device to perform any of the aforementioned methods for determining network service areas. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.
[0143] In an exemplary embodiment, a computer program product is also provided, which, when executed by an electronic device, enables the electronic device to implement any of the exemplary methods provided in this application.
[0144] It should be noted that although several modules or sub-modules of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.
[0145] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.
[0146] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.
[0147] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, then this application also includes such modifications and variations.
Claims
1. A method for determining a network service area, characterized in that, include: Obtain network service information for a specified area, where the specified area corresponds to multiple cells, and the network service information includes the measurement report (MR) data for each cell and the service type for each cell; Based on the MR data corresponding to each service type of cell, a concave pod is generated for that service type, and the concave pod is used to characterize the network service boundary of that service type. Based on the concave packet of each service type, different network service areas are determined in the specified region.
2. The method as described in claim 1, characterized in that, Based on the MR data corresponding to each service type cell, generate the concave hull for that service type, including: Based on the MR data and concavity parameter values corresponding to each service type of cell, a candidate concavity is generated. The concavity parameter values are determined by the Bayesian optimizer using a probability model. Initially, the model parameters of the probability model are preset values. The evaluation result of the candidate concave hull is determined according to the preset evaluation rules; The evaluation results are provided to the Bayesian optimizer, which then adjusts the model parameters of the probability model based on the evaluation results. Obtain the value of the concavity parameter as determined by the Bayesian optimizer using the probability model; The process involves generating a candidate concave hull based on the MR data and concavity parameter values corresponding to each service type of cell. This process continues until the loop termination condition is met, at which point the candidate concave hull with the best evaluation result is determined as the concave hull for the service type.
3. The method as described in claim 2, characterized in that, The evaluation result of the candidate concave hull is determined according to the preset evaluation rules, including: The data coverage score of the candidate notch is determined based on the number of MR data entries contained in the candidate notch and the number of MR data entries corresponding to the cell of the service type. The compactness score of the candidate concave hull is determined based on its area and perimeter. The area penalty score of the candidate indentation is determined based on the area of the candidate indentation and a preset area threshold. The evaluation result of the candidate concave hull is determined based on the data coverage score, the compactness score, and the area penalty score.
4. The method according to any one of claims 1-3, characterized in that, Based on the concave packet of each service type, different network service areas are determined in the specified region, including: Each service type's emboss is used as an initial network service area. When different network service areas overlap, the contours of the different network service areas are adjusted. If a network service area is adjusted to obtain at least two sub-service areas, then select one network service area and at least one alternative service area from the at least two sub-service areas. According to the preset service area merging rules, each candidate service area is merged with the adjacent network service areas to obtain different network service areas in the specified area.
5. The method as described in claim 4, characterized in that, The designated area is divided into multiple grids, and the MR data corresponding to each cell includes the MR data of the cell in the corresponding grid. Contour adjustment is performed on the different network service areas, including: For each grid that overlaps with the different network service areas, the different network service areas are counted according to the service type corresponding to each MR data in the grid, and the network service area corresponding to the grid is determined based on the counting results; The outlines of the different network service areas are adjusted according to the network service areas corresponding to each grid that overlaps with the different network service areas.
6. The method as described in claim 4, characterized in that, Also includes: When a network service area covers at least two management areas, the outline of the network service area is adjusted according to the boundaries of the at least two management areas.
7. The method as described in claim 1, characterized in that, The service type of each community is determined based on the service data of that community, which includes static service data and dynamic service data.
8. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to said at least one processor, wherein: The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method as described in any one of claims 1-7.
9. A storage medium, characterized in that, When the computer program in the storage medium is executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-7.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-7.