Neighboring cell planning method, base station, medium and computer program product

Abstract

Provided in the present disclosure is a neighboring cell planning method. The method comprises: on the basis of engineering parameters of a first base station in a communication network, performing calculation to obtain first feature data, the first feature data being used for describing a spatial feature relationship between a first source cell of the first base station and a first target cell, and at least comprising an overlapping coverage area coefficient and the number of tiers between the first base station and a second base station in the communication network, the first target cell being a cell corresponding to the second base station, the second base station being within a first preset tier quantity range of the first base station, and the number of tiers representing a geographic position association relationship between the base stations; and, on the basis of the first feature data and a preset neighboring cell planning model, determining a neighboring cell planning result corresponding to the first base station. Also provided in the present disclosure are a base station, a computer-readable medium and a computer program product.

Description

Neighborhood planning methods, base stations, media and computer program products

[0001] Cross-reference to related applications

[0002] This patent application claims priority to Chinese Patent Application No. 202410502195.3, filed on April 24, 2024, with the State Intellectual Property Office of China, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to the field of communication technology, and in particular to a neighboring cell planning method, base station, medium, and computer program product. Background Technology

[0004] Communication networks are the core infrastructure for the development of the digital economy, and network planning is the first step in their construction. Neighbor cell planning for communication base stations is a crucial part of this overall network planning. Neighbor cell planning directly affects the handover between base stations for mobile devices, a vital technology in communication networks. When a mobile device moves from one cell to another, neighbor cell handover allows for seamless switching while maintaining communication connectivity, ensuring continuity of calls and data transmission, thus providing a smoother mobile experience and guaranteeing communication quality.

[0005] Therefore, there is an urgent need for a solution that can achieve accurate neighborhood planning. Summary of the Invention

[0006] This disclosure provides a neighbor cell planning method, a base station, media, and computer program products.

[0007] In a first aspect, embodiments of this disclosure provide a neighbor cell planning method, comprising: calculating first feature data based on engineering parameters of a first base station in a communication network, wherein the first feature data is used to describe the spatial feature relationship between a first source cell and a first target cell of the first base station, including at least an overlapping coverage area coefficient and the number of layers between the first base station and a second base station in the communication network, the first target cell being the cell corresponding to the second base station, the second base station being within a first preset number of layers of the first base station, the number of layers representing the geographical location association between the base stations; and determining the neighbor cell planning result corresponding to the first base station based on the first feature data and a preset neighbor cell planning model.

[0008] Secondly, embodiments of this disclosure provide a base station, which includes a memory and a processor, wherein the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements the neighbor cell planning method described in the first aspect.

[0009] Thirdly, embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the neighbor cell planning method of the first aspect.

[0010] Thirdly, embodiments of this disclosure provide a computer program product, which includes a computer program that, when executed by a processor, implements the neighbor cell planning method described in the first aspect. Attached Figure Description

[0011] In the accompanying drawings of the embodiments disclosed herein:

[0012] Figure 1 is a flowchart of a neighbor cell planning method provided in an embodiment of this disclosure;

[0013] Figure 2 is a schematic diagram of the relationship between the base station and the cell provided in the embodiments of this disclosure;

[0014] Figure 3 is a schematic diagram of the base station triangular network provided in an embodiment of this disclosure;

[0015] Figure 4 is a schematic diagram of the hierarchical distribution rendering effect of the first base station and other base stations provided in the embodiments of this disclosure;

[0016] Figure 5 is a schematic diagram of the included angle coefficient provided in the embodiments of this disclosure;

[0017] Figure 6 is a flowchart of a specific implementation method of step S1 in an embodiment of this disclosure;

[0018] Figure 7 is a schematic diagram of the structure of the overlapping coverage portion of the cell provided in an embodiment of this disclosure;

[0019] Figure 8 is a flowchart of a specific implementation method of step S11 in an embodiment of this disclosure;

[0020] Figure 9 is a simulation diagram of the cell coverage provided in the embodiments of this disclosure;

[0021] Figure 10 is a flowchart of a specific implementation method of step S2 in an embodiment of this disclosure;

[0022] Figure 11 is a flowchart of the method for determining the neighboring cell planning model provided in the embodiments of this disclosure;

[0023] Figure 12 is a flowchart of a specific implementation method of step S02 in an embodiment of this disclosure;

[0024] Figure 13 is a flowchart of a specific implementation method of step S021 in an embodiment of this disclosure;

[0025] Figure 14 is a schematic diagram of the structure of a base station provided in an embodiment of this disclosure;

[0026] Figure 15 is a schematic diagram of the structure of a computer-readable medium provided in an embodiment of this disclosure;

[0027] Figure 16 is a schematic diagram of the structure of an exemplary neighbor cell planning system provided in an embodiment of this disclosure;

[0028] Figure 17 is a flowchart of an exemplary feature calculation provided in an embodiment of this disclosure;

[0029] Figure 18 is a flowchart of an exemplary model training provided in an embodiment of this disclosure;

[0030] Figure 19 is a schematic diagram of training data for an exemplary model training provided in an embodiment of this disclosure;

[0031] Figure 20 is a flowchart of an exemplary neighbor cell planning method provided in an embodiment of this disclosure;

[0032] Figure 21 is a flowchart of yet another exemplary neighbor cell planning method provided in an embodiment of this disclosure;

[0033] Figure 22 is a flowchart of an exemplary model training provided in an embodiment of this disclosure. Detailed Implementation

[0034] To enable those skilled in the art to better understand the technical solutions of this disclosure, the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.

[0035] The present disclosure will be described more fully below with reference to the accompanying drawings; however, the embodiments shown may be embodied in different forms, and the present disclosure should not be construed as limited to the embodiments set forth below. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will enable those skilled in the art to fully understand the scope of the disclosure.

[0036] The accompanying drawings of the embodiments disclosed herein are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the detailed embodiments to explain this disclosure and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the description of the detailed embodiments with reference to the accompanying drawings.

[0037] This disclosure may be described with reference to plan and / or cross-sectional views using the ideal schematic diagrams of this disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances.

[0038] Where there is no conflict, the various embodiments of this disclosure and the features thereof in the embodiments may be combined with each other.

[0039] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the disclosure. The term "and / or" as used in this disclosure includes any and all combinations of one or more of the associated enumerated entries. The singular forms "a" and "the" as used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. The terms "comprising," "made of," etc., as used in this disclosure specify the presence of features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof.

[0040] Unless otherwise specified, all terms used in this disclosure (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined in this disclosure.

[0041] In some related technologies, in 2G (the 2nd generation mobile communication technology) and 3G networks, neighbor cell planning is typically achieved through tool-based planning or manual adjustment. Tool-based planning requires using the latitude, longitude, and azimuth information of the cell corresponding to the new base station. Based on the distance and angle between the new base station and existing base stations, multiple nearby cells in the forward coverage direction of the new base station's cell are added to the neighbor cell list. However, this neighbor cell planning method, which primarily relies on cell distance and angle, suffers from various problems such as missing neighbor cell allocations, low planning accuracy, and an excessive number of neighbor cells, making it difficult to guarantee the accuracy of neighbor cell planning.

[0042] In the 4G network era, while ANR (Automatic Neighbor Relations) technology was introduced to address the neighbor cell planning needs of communication networks, in addition to tool-based planning and manual adjustments, ANR technology is limited by the fact that newly added base stations need to operate on the network for a period of time before automatic neighbor cell planning and optimization are performed based on the signals reported by the mobile devices corresponding to the new base stations. In other words, ANR technology cannot obtain accurate planning results before the new base stations are connected to the network, resulting in poor timeliness in the neighbor cell planning process.

[0043] Therefore, there is an urgent need for a more refined, intelligent, and timely neighbor cell planning method to adapt to the increasingly complex communication network environment.

[0044] Figure 1 is a flowchart of a neighbor cell planning method provided by an embodiment of this disclosure. Referring to Figure 1, an embodiment of this disclosure provides a neighbor cell planning method, which includes steps S1 and S2.

[0045] In step S1, first feature data is calculated based on the engineering parameters of the first base station in the communication network. The first feature data is used to describe the spatial feature relationship between the first source cell and the first target cell of the first base station, including at least the overlapping coverage area coefficient and the number of layers between the first base station and the second base station in the communication network. The first target cell is the cell corresponding to the second base station, and the second base station is within the first preset number of layers of the first base station. The number of layers represents the geographical location association between the base stations.

[0046] In step S2, the neighbor cell planning result corresponding to the first base station is determined based on the first feature data and the preset neighbor cell planning model.

[0047] The engineering parameters of the first base station include at least one of the following: base station ID, base station name, base station longitude, base station latitude, cell ID, cell name, and cell azimuth. The first base station refers to a newly added base station in the communication network, and the second base station refers to a base station within a first preset layer range of the first base station. The first preset layer range is used to define base stations in the communication network that meet preset geographical location conditions with respect to the first base station. The first source cell is the serving cell of the first base station, and the first target cell is the serving cell of the second base station. This embodiment of the disclosure does not impose a special limitation on the number of serving cells for each base station.

[0048] Figure 2 is a schematic diagram of the relationship between a base station and a cell provided in an embodiment of this disclosure. As shown in Figure 2, in some embodiments, a base station A may include three serving cells (source cell 1, source cell 2, and source cell 3), which cover three different directions respectively.

[0049] The first feature data is used to describe the spatial feature relationship between the first source cell and the first target cell of the first base station. This spatial feature relationship includes at least the overlap coverage area coefficient and the number of layers between the first base station and the second base station. The overlap coverage area coefficient refers to the proportion of the overlapping coverage area between the first source cell and the first target cell within the first source cell. The number of layers refers to the geographical location association between the first base station corresponding to the first source cell and the second base station corresponding to the first target cell.

[0050] The first feature data in this embodiment describes the spatial feature relationship between the first source cell corresponding to the newly added first base station and the first target cell corresponding to the second base station. It introduces the overlapping coverage area coefficient and the number of layers between base stations to characterize the spatial feature relationship. Compared with some related technologies that mainly consider distance and angle in neighbor cell planning schemes, this embodiment solves the problems of missing neighbor cell configuration, low planning accuracy, and too many neighbor cells, and fully ensures the accuracy of neighbor cell planning.

[0051] The preset neighbor cell planning model is based on the neighbor cell planning experience of the communication network and is obtained by learning the neighbor cell planning rules of each base station in the communication network. In some embodiments, the preset neighbor cell planning model is trained based on the indicator data of the communication network and the engineering parameters and neighbor cell configuration data of the known base stations in the communication network.

[0052] This disclosure does not impose any special restrictions on the type of neighbor cell planning model. In some embodiments, the neighbor cell planning model learns from the neighbor cell planning results of base stations that have already undergone neighbor cell planning in the communication network using machine learning technology. The trained preset neighbor cell planning model can output the neighbor cell planning result corresponding to the base station based on the feature data of the input base station.

[0053] Compared to ANR technology, newly added base stations do not need to operate on the network for a period of time, nor do they need to perform automatic neighbor cell planning and optimization based on the signals reported by the mobile devices corresponding to the new base stations. Instead, accurate neighbor cell planning results can be obtained before the new base station is connected to the network (i.e., the new base station is connected to the communication network), which significantly improves the timeliness of neighbor cell planning for new base stations. Moreover, after being connected to the network, there is no need to optimize based on the signals reported by the mobile devices, which ensures the continuity of mobile devices in making calls and transmitting data in the new base stations, and can provide mobile device users with a smoother mobile experience and better communication quality.

[0054] The neighbor cell planning method provided in this disclosure further includes the step of: determining a first target cell.

[0055] In some embodiments, determining the first target cell may include: constructing a hierarchical relationship between the first base station and other base stations based on the engineering parameters of the first base station and the engineering parameters of other base stations in the communication network; determining the base stations in the other base stations whose hierarchical relationship satisfies a first preset number of layers as second base stations, and determining the cell corresponding to the second base station as the first target cell.

[0056] In some embodiments, constructing a hierarchical relationship between the first base station and other base stations based on the engineering parameters of the first base station and other base stations may include: constructing a base station triangulation network using the longitude and latitude values ​​of the first base station and other base stations as the vertices of triangles in the base station triangulation network, wherein the circumcircle of each triangle in the base station triangulation network includes only the three vertices of the triangle, and the incircle of the triangle does not include any base station vertices; determining the hierarchical relationship between the first base station and other base stations based on the base station triangulation network, wherein the hierarchical relationship is used to characterize that other base stations are at the nth level of the first base station, where n is a positive integer.

[0057] In some embodiments, the base station triangulation is a Delaunay triangulation.

[0058] In some embodiments, determining the hierarchical relationship between the first base station and other base stations based on the base station triangulation may include: if a vertex of one of the other base stations is connected to a vertex of the first base station by at least n triangle edges, then the other base station is determined to be the nth level of the first base station.

[0059] Figure 3 is a schematic diagram of the base station triangulation provided in this embodiment. As shown in Figure 3, the vertex positions can be determined based on the longitude and latitude values ​​of the first base station and other base stations. Using the first base station and other base stations as the vertices of the triangles in the base station triangulation, a De Lao inner triangulation is constructed. This De Lao inner triangulation is a triangulation constructed from the set of vertices of the first base station and other base stations, and does not contain any base station vertices within the inscribed circle of their triangles. Based on the constructed De Lao inner triangulation, base stations of the same or different levels around the first base station can be determined. Furthermore, a base station list can be constructed based on these base stations of different levels.

[0060] Figure 4 is a schematic diagram of the hierarchical distribution rendering effect of the first base station and other base stations provided in the embodiments of this disclosure. As shown in Figure 4, with the first base station as the center, and the first preset layer range set to 3 layers, the base station of layer 1, the base station of layer 2, and the base station of layer 3 can all be identified as the second base station. The hierarchy reflects the geographical relationship between other base stations and the first base station.

[0061] In some embodiments, after constructing the base station triangulation network, the neighbor cell planning method provided in this disclosure may further include the steps of: determining the base station in the first preset layer range among other base stations as the second base station, and constructing a first target cell pair list according to the first target cell corresponding to the second base station.

[0062] The information contained in the first target cell in the first target cell pair list includes at least one of the following: the base station ID of the first source cell, the base station name of the first source cell, the cell ID of the first source cell, the cell name of the first source cell, the latitude and longitude of the first source cell, the cell azimuth of the first source cell, the base station ID of the first target cell, the base station name of the first target cell, the cell ID of the first target cell, the cell name of the first target cell, the latitude and longitude of the first target cell, the cell azimuth of the first target cell, and the layer number of the first target cell in the first source cell.

[0063] In some embodiments, the first feature data further includes at least one of the following: a distance multiple between the first source cell and the first target cell, an angle coefficient between the first source cell and the first target cell, and an identifier indicating the correspondence between the first source cell and the first target cell.

[0064] The distance multiplier reflects the relationship between the first distance between the newly added first base station and the second base station, and the second distance between the first base station and all base stations within the third preset layer range. The cell spacing value between the first source cell and the first target cell is the site spacing between the first base station corresponding to the first source cell and the second base station corresponding to the first target cell. In some embodiments, this site spacing can be calculated based on the engineering parameters of the first base station and the engineering parameters of the second base station in the communication network.

[0065] In some embodiments, the distance multiple between the first source cell and the first target cell is calculated using the longitude and latitude values ​​of the first base station and the second base station.

[0066] In some embodiments, when the first feature data includes a distance multiple between the first source cell and the first target cell, step S1 includes: determining a second distance between the first base station and all intermediate base stations within its corresponding third preset layer range; dividing the first distance between the first base station and the second base station by the median value of the second distance to obtain the distance multiple.

[0067] In some embodiments, the intermediate base stations within the third preset layer range refer to base stations with a layer number of 1 surrounding the first base station. The distance multiple is then calculated using the formula:

[0068] It is worth noting that when there are multiple intermediate base stations within the third preset layer range, the present disclosure embodiment does not impose special restrictions on the statistical method of the second distance. It can be the median of the second distance (i.e., the median value among all second distances), or the average value, maximum value, minimum value, etc., which can be set according to actual needs.

[0069] The angle coefficient between the first source cell and the first target cell refers to the relationship between the line connecting the first source cell and the first target cell and the azimuth vector of either the first source cell or the first target cell. The angle coefficient is calculated based on the forward angle and / or the reverse angle. The forward angle is the angle between the line connecting the first source cell and the first target cell and the azimuth vector of the first source cell; that is: forward angle = angle between the line connecting the first source cell and the first target cell and the azimuth vector of the first source cell. The reverse angle is the angle between the line connecting the first source cell and the first target cell and the azimuth vector of the first target cell; that is: reverse angle = angle between the line connecting the first target cell and the first source cell and the azimuth vector of the first target cell.

[0070] In some embodiments, the included angle coefficient is calculated using the following formula:

[0071] Figure 5 is a schematic diagram of the included angle coefficient provided in an embodiment of this disclosure. As shown in Figure 5, base station B includes three serving cells (AL0001A, AL0001B, and AL0001C) covering three different directions, and base station C includes three serving cells (AL0002A, AL0002B, and AL0002C) covering three different directions. AL0001B is the source cell, and AL0002C is the target cell. The azimuth angle of AL0001B is 120°, and the azimuth angle of the line connecting AL0001B and AL0002C is 80°, so the forward included angle is 40°. Using the formula: included angle coefficient = included angle / 180°, the included angle coefficient corresponding to the forward included angle with AL0001B as the source cell and AL0002C as the target cell is calculated to be 40 / 180 = 0.222222.

[0072] The identifier is used to uniquely index the first source cell and the first target cell; that is, the identifier is a unique identifier for the first source cell and the first target cell. In some embodiments, the identifier is a combination of the base station ID of the first base station corresponding to the first source cell and the ID of the first target cell. This disclosure does not impose any special limitations on the representation of the identifier.

[0073] Figure 6 is a flowchart of a specific implementation method of step S1 in an embodiment of this disclosure. Referring to Figure 6, in some embodiments, step S1 includes steps S11 and S12.

[0074] In step S11, the coverage area of ​​the first source cell is calculated.

[0075] In step S12, the first feature data is calculated based on the coverage area of ​​the first source cell and the coverage area of ​​the first target cell.

[0076] The coverage area of ​​a cell refers to the signal coverage range of the corresponding base station, which is the geographical area within the mobile network that the cell can provide communication services. The overlap coverage area coefficient can be calculated based on the coverage areas of the first source cell and the first target cell. The overlap coverage area coefficient is the ratio between the area of ​​the overlap between the first source cell and the first target cell and the coverage area of ​​the first source cell, that is:

[0077] Figure 7 is a schematic diagram of the structure of the overlapping coverage area of ​​cells provided in an embodiment of this disclosure. As shown in Figure 7, in some embodiments, the serving cell corresponding to base station A is cell A, and the serving cell corresponding to base station B is cell B. The area of ​​the overlapping coverage areas of cell A and cell B is the area of ​​the overlapping portion between cell A and cell B. When calculating the overlapping coverage area coefficient of cell A relative to cell B, the area of ​​the overlapping portion is divided by the coverage area of ​​cell A; when calculating the overlapping coverage area coefficient of cell B relative to cell A, the area of ​​the overlapping portion is divided by the coverage area of ​​cell B.

[0078] Compared to neighbor cell planning schemes that focus on distance and angle, this disclosure first divides each base station into hierarchical levels based on the engineering parameters of each base station in the communication network and the engineering parameters of the newly added first base station, and then calculates the first feature data, which includes at least the overlapping coverage area coefficient. This introduces more considerations about the relationship between each base station, which can effectively solve problems such as missing neighbor cell allocation, low planning accuracy, and too many neighbor cells. Introducing more factors for neighbor cell division can effectively improve the accuracy of neighbor cell planning and better cope with different complex communication network environments.

[0079] Figure 8 is a flowchart of a specific implementation method of step S11 in an embodiment of this disclosure. Referring to Figure 8, in some embodiments, step S11 includes steps S111 to S113.

[0080] In step S111, the coverage radius of the first source cell is determined.

[0081] In step S112, multiple angles in the angle range of the first source cell and a first ratio corresponding to each angle are obtained, wherein the first ratio is the ratio of the coverage radius of the first source cell to the reference radius.

[0082] In step S113, the coverage area of ​​the first source cell is determined based on multiple angles in the angle range of the first source cell, the first ratio corresponding to each angle, and the coverage radius.

[0083] The coverage area of ​​the first source cell can be calculated based on its angle, the first ratio corresponding to each angle, and its coverage radius. The first ratio refers to the ratio of the coverage radius of the first source cell to its reference radius. The reference radius refers to the signal coverage radius of the cell under ideal conditions, that is, the furthest distance the base station's signal can cover without obstructions such as terrain or buildings.

[0084] Furthermore, this disclosure does not impose any special limitations on the coverage area of ​​the cell. It should be understood that in actual operation, the coverage area of ​​the cell corresponding to the base station is not necessarily a standard fan-shaped structure; the coverage pattern of the cell can be drawn using simulation and other technical means.

[0085] Figure 9 is a simulation diagram of the cell coverage area provided in this embodiment. As shown in Figure 9, the coverage area of ​​this cell is not a fan-shaped structure, but rather the coverage radius gradually decreases within the angle range of [+80°, -80°]. The specific relationship between the angle and the first ratio is as follows:

[0086] [(-80,0.25),(-70,0.4),(-60,0.5),(-50,0.75),(-40,1.1),(-32.5,1.25),(-25.5,1.3),(-17,1.4),(-10,1.42),(-5,1.43),(0,1.45),(5,1.43),(10,1.42),(17,1.4),(25.5,1.3),(32.5,1.25),(40,1.1),(50,0.75),(60,0.5),(70,0.4),(80,0.25)].

[0087] In (-80, 0.25), -80 represents an angle of -80°, and 0.25 represents the first ratio value corresponding to -80° as 0.25. Similarly, in (-70, 0.4), -70 represents an angle of -70°, and 0.4 represents the first ratio value corresponding to -70° as 0.4. The same logic applies to other values, and will not be repeated here to avoid redundancy. Therefore, it is evident that the coverage area of ​​a cell corresponding to a base station is not necessarily a standard fan-shaped pattern, and its coverage radius does not necessarily change linearly with the angle.

[0088] Once the first ratio (which relates to the coverage radius and the reference radius) corresponding to each angle of the coverage area is determined, and the coverage radius is also determined, the coverage area of ​​the cell can be calculated.

[0089] In some embodiments, step S111 includes: detecting a second base station within a preset angle range corresponding to the positive angle between the first source cell and each first target cell; and determining the coverage radius of the first source cell based on the number of detected second base stations.

[0090] Since the first base station corresponding to the first source cell is a new base station that needs to be added to the communication network, the base station TA (Tracking Area) index of the first base station has not yet been updated in the corresponding index data of the communication network before the first base station is added to the communication network. The base station TA index is used to describe the tracking area corresponding to the base station in the mobile network. The tracking area refers to an area in a communication network used to track the location of the mobile device corresponding to the base station. The base station TA index can be used to calculate the coverage radius of the base station. However, since the first base station has not yet been added to the communication network, the base station TA index cannot be obtained. Instead, the coverage radius is determined by detecting all second base stations within a preset angle range corresponding to the positive angle between the first source cell and each first target cell, and the number of detected second base stations is calculated.

[0091] In some embodiments, when the number of detected second base stations is zero, the coverage radius of the first source cell is determined to be a preset empirical radius value; when the number of detected second base stations is greater than zero, the coverage radius of the first source cell is determined to be the median of the distance values ​​between the detected second base stations and the first base station. This disclosure does not impose any special limitation on the preset empirical radius value; in some embodiments, the preset empirical radius value can be determined based on the base station site density of different communication networks.

[0092] In some embodiments, from the base stations in the three layers surrounding the first source cell of the newly built first base station, all second base stations located within a 60° range of the positive angle between the first source cell of the newly built first base station are detected, and the site spacing between the first base station and the detected second base stations is calculated to obtain a site spacing list.

[0093] If the number of second base stations detected in the site spacing list is zero (i.e., there are no base stations within a 60° range of the positive angle between the first source cell of the newly established first base station), the coverage radius is set to 4000m. If the number of second base stations in the site spacing list is greater than 3, the median of the second base station with the largest site spacing from the first base station in the site spacing list is used as the coverage radius. If the number of second base stations in the site spacing list is 1, the site spacing between the first base station and that second base station is used as the coverage radius. If the number of second base stations in the site spacing list is 2, the average of the site spacings between the first base station and these two second base stations is used as the coverage radius.

[0094] Figure 10 is a flowchart of a specific implementation method of step S2 in an embodiment of this disclosure. Referring to Figure 10, in some embodiments, step S2 includes S21 and S22.

[0095] In step S21, the overlapping coverage area coefficient and the number of layers between the first base station and the second base station are input into the preset neighbor cell planning model.

[0096] In step S22, a target neighbor cell is determined from the first target cell of the second base station using a preset neighbor cell planning model, so as to obtain the neighbor cell planning result corresponding to the first base station. The neighbor cell planning result includes the target neighbor cell.

[0097] A pre-defined neighbor cell planning model is used to select one or more cells from the second base stations as target neighbor cells of the first base station based on the overlapping coverage area coefficient of the newly added first base station and the layer relationship between the first base station and the second base station. In some embodiments, the neighbor cell planning model can construct a feature information column based on the overlapping coverage area coefficient, layer relationship, distance multiple, angle coefficient, and identifier indicating the correspondence between the first source cell and the first target cell in the first feature data to perform neighbor cell planning. It should be understood that the more factors included in the first feature data, the more accurate the neighbor cell planning result.

[0098] Before step S21, step S2 further includes at least one of the following steps: establishing a unique index between the first base station and the second base station (i.e., an identifier indicating the correspondence between the first source cell and the first target cell), which can be in various forms, such as "base station ID + cell ID"; deleting the newly added first feature data of the first base station and redundant data in the layer relationship between the first base station and the second base station, so as to eliminate the interference of redundant data on the neighbor cell planning of the model.

[0099] In some embodiments, after determining the target neighboring cells, the neighboring cell planning method provided in this disclosure further includes: generating a recommended score column for the first target cell corresponding to each second base station.

[0100] This recommended score column is used to prioritize the first target cell of the second base station as a target neighbor cell. This allows for the selection of the corresponding threshold score for the recommended score column based on the specific scenario of the communication network in practical applications, thereby more quickly filtering the list of target neighbor cells. This helps optimize neighbor cell planning and improves its flexibility, enabling it to adapt to different application scenarios and communication networks with varying application requirements.

[0101] In some embodiments, after S2, the neighbor cell planning method provided in this disclosure further includes: updating the neighbor cell configuration data corresponding to the neighbor cell planning result to the neighbor cell configuration data of known base stations in the communication network.

[0102] Neighbor cell configuration data is used to describe information related to the target neighboring cells of the first base station. Once the neighbor cell planning results for the newly added first base station are determined—that is, the target neighboring cells are planned for the first base station—neighbor cell configuration data corresponding to the neighbor cell planning results can be generated and updated to the neighbor cell configuration data of known base stations in the communication network. In some embodiments, the neighbor cell configuration data of known base stations in the communication network is a neighbor cell script, i.e., a configuration file or script used in the communication network to describe the relationships between neighboring cells.

[0103] Figure 11 is a flowchart of a method for determining a neighboring cell planning model provided in an embodiment of this disclosure. Referring to Figure 11, in some embodiments, the determination method further includes steps S01 to S03.

[0104] In step S01, the indicator data of the communication network and the engineering parameters and neighbor cell configuration data of the sample base station are obtained. The sample base station is a known base station in the communication network.

[0105] In step S02, the second feature data corresponding to the sample base station is calculated based on the index data and the engineering parameters of the sample base station. The second feature data is used to describe the spatial feature relationship between the second source cell and the second target cell of the first sample base station in the sample base station. It includes at least the overlapping coverage area coefficient and the number of layers between the first sample base station and the second sample base station in the communication network. The second target cell is the cell corresponding to the second sample base station. The second sample base station is within the second preset number of layers of the first sample base station. The number of layers represents the geographical location association between the base stations.

[0106] In step S03, the preset model is trained based on the second feature data and neighbor cell configuration data corresponding to the sample base station to obtain the neighbor cell planning model.

[0107] The sample base station is a base station selected from known base stations in the communication network. In some embodiments, the engineering parameters and neighbor cell configuration data of the sample base station are obtained by processing the engineering parameters and neighbor cell configuration data of the known base stations in the communication network. This disclosure does not impose special limitations on the type of data processing; it can include redundant data removal, data validity verification, base station latitude and longitude processing, etc. The first sample base station is the base station corresponding to the second source cell, and the second sample base station is the base station corresponding to the second target cell.

[0108] The metrics data of the communication network include at least one of the following: base station identifier ID, base station name, cell identifier ID, cell name, and base station TA metric.

[0109] The neighbor cell configuration data includes at least one of the following: base station ID, base station name, cell ID, cell name, base station ID of the neighbor cell, base station name of the neighbor cell, neighbor cell ID, and neighbor cell name.

[0110] The engineering parameters include at least one of the following: base station ID, base station name, base station longitude, base station latitude, cell ID, cell name, and cell azimuth.

[0111] It should be understood that the indicator data, neighbor cell configuration data, and engineering parameters of the communication network all include: base station identifier ID, base station name, cell identifier ID, and cell name. This data can be used to correlate the indicator data, neighbor cell configuration data, and engineering parameters of the communication network corresponding to the same base station.

[0112] This disclosure does not impose any special restrictions on the method of obtaining the communication network's indicator data, neighbor cell configuration data, and engineering parameters. In some embodiments, the communication network's indicator data, neighbor cell configuration data, and engineering parameters are obtained from the wireless communication access network using an application programming interface provided by the wireless communication access network.

[0113] The second feature data corresponding to the sample base station is calculated based on the indicator data in the communication network and the engineering parameters of the sample base station. The second feature data includes at least one of the following: an overlap coverage area coefficient and the number of layers between the first sample base station and the second sample base station. In some embodiments, the second feature data may further include at least one of the following: a distance multiple between the first sample base station and the second sample base station, an angle coefficient between the first sample base station and the second sample base station, and an identifier indicating the correspondence between the second source cell and the second target cell.

[0114] When the second feature data is a distance multiple, an angle coefficient, an identifier indicating the second source cell and the second target cell, and the number of layers between the first sample base station and the second sample base station, the calculation process of the second feature data is the same as or similar to the calculation process corresponding to step S1. To avoid repetition, it will not be described again here.

[0115] When the second feature data is the overlapping coverage area coefficient, since both the first and second sample base stations have known corresponding indicator data (including the base station TA indicator), and the base station TA indicator can be used to calculate the coverage radius of the base station, the overlapping coverage area coefficient can be calculated directly using the base station TA indicator in the indicator data, thus obtaining a more accurate overlapping coverage area coefficient. Therefore, the second feature data is used as the input value of the preset model, and the neighboring cells corresponding to the sample base stations are used as the target values ​​to train the preset model, resulting in a neighbor cell planning model.

[0116] In some embodiments, obtaining the engineering parameters and neighbor cell configuration data of a sample base station by processing the engineering parameters and neighbor cell configuration data of a known base station in a communication network may include at least one of the following steps: Redundant data removal: Based on the engineering parameters of the known base stations, determine the redundant base stations among the known base stations; remove the engineering parameters and neighbor cell configuration data of the redundant base stations from the engineering parameters and neighbor cell configuration data of the known base stations to obtain the engineering parameters and neighbor cell configuration data of the sample base station.

[0117] Redundant data removal from the engineering parameters and neighbor cell configuration data of known base stations can prevent the existence of problematic base stations (e.g., decommissioned base stations, faulty base stations, and base stations with long-term disconnections) in the communication network due to historical reasons. Problematic base stations may have missing engineering parameters, neighbor cell configuration data, and their corresponding indicator data in the communication network. If problematic base stations are not addressed, it may lead to reduced model accuracy and contamination of model training data. As one embodiment of this disclosure, redundant data removal includes identifying and removing problematic base stations with missing engineering parameters, missing indicators, or missing neighbor cell configuration data to prevent these problematic base stations from interfering with model analysis and processing.

[0118] Data validity verification: The engineering parameters of known base stations are validated for validity. Base stations that fail the validation are identified as invalid base stations. The engineering parameters and neighbor cell configuration data of invalid base stations are removed from the engineering parameters and neighbor cell configuration data of known base stations to obtain the engineering parameters and neighbor cell configuration data of sample base stations. In some embodiments, a base station that fails to meet the requirements refers to a base station whose relevant data contains data that is obviously illogical, such as a cell azimuth angle greater than 360° or a longitude value outside the range of [-180, 180], which effectively avoids interference with model training.

[0119] Base station latitude and longitude processing: The latitude and longitude in the engineering parameters of known base stations are counted and retained. Base stations with the same processing results are merged to obtain the engineering parameters and neighbor cell configuration data of sample base stations.

[0120] Processing the engineering parameters and neighbor cell configuration data of known base stations using base station latitude and longitude coordinates can prevent situations where some cells, although belonging to the same base station, have slightly different latitude and longitude values ​​due to historical reasons during base station triangulation construction. For example, serving cell A has latitude and longitude coordinates of (113.7400193, 1.79156), and serving cell B has latitude and longitude coordinates of (113.7400194, 1.79156). Both serving cells A and B belong to the known base station A, but due to the slight difference in their longitude values, they may be incorrectly identified as two serving cells of different base stations during the construction of the hierarchical base station triangulation. This situation increases the computational load of subsequent feature calculations and also affects the accuracy of neighbor cell planning in the model after training. Therefore, by performing counting and retention processing on latitude and longitude, for example, retaining six decimal places, we can meet the accuracy requirements of neighbor cell planning and ensure that when constructing the base station triangulation network, the base stations will not be mistakenly identified as different base stations due to slight differences in latitude and longitude values.

[0121] Figure 12 is a flowchart of a specific implementation method of step S02 in an embodiment of this disclosure. Referring to Figure 12, in some embodiments, step S02 includes steps S021 and S022.

[0122] In step S021, the coverage area of ​​the second source cell is calculated.

[0123] In step S022, the second feature data is calculated based on the coverage area of ​​the second source cell and the coverage area of ​​the second target cell.

[0124] The coverage area of ​​a cell refers to the signal coverage range of the corresponding base station, which is the geographical area within the mobile network that the cell can provide communication services. The overlap coverage area coefficient can be calculated based on the coverage areas of the second source cell and the second target cell. The overlap coverage area coefficient is the ratio between the area of ​​the overlap between the second source cell and the second target cell and the coverage area of ​​the second source cell, that is:

[0125] Compared to neighbor cell planning schemes that focus on distance and angle, this method first divides each base station into hierarchical levels based on the engineering parameters of the first and second sample base stations, and then calculates the second feature data, which includes at least the overlapping coverage area coefficient. This introduces more factors to consider regarding the relationship between each base station, so that the trained neighbor cell planning model can effectively solve problems such as missing neighbor cell allocation, low planning accuracy, and too many neighbor cells. Introducing more factors for neighbor cell division can effectively improve the accuracy of the model in neighbor cell planning, and also enable the model to better cope with different complex communication network environments.

[0126] Figure 13 is a flowchart of a specific implementation method of step S021 in an embodiment of this disclosure. Referring to Figure 13, in some embodiments, step S021 includes steps S0211 to S0213.

[0127] In step S0211, the coverage radius of the second source cell is determined based on the indicator data of the communication network.

[0128] In step S0212, multiple angles in the angle range of the second source cell and a second ratio corresponding to each angle are obtained, wherein the second ratio is the ratio of the coverage radius of the second source cell to the reference radius.

[0129] In step S0213, the coverage area of ​​the second source cell is determined based on multiple angles in the angle range of the second source cell, the second ratio corresponding to each angle, and the coverage radius.

[0130] The coverage area of ​​the second source cell can be calculated based on its angle, the corresponding second ratio for each angle, and its coverage radius. The second ratio refers to the ratio of the coverage radius of the second source cell to its reference radius. The reference radius refers to the signal coverage radius of the cell under ideal conditions, that is, the furthest distance the base station's signal can cover without obstructions such as terrain or buildings.

[0131] Furthermore, this disclosure does not impose any special limitations on the coverage area of ​​the cell. It should be understood that in actual operation, the coverage area of ​​the cell corresponding to the base station is not necessarily a standard fan-shaped structure; the coverage pattern of the cell can be drawn using simulation and other technical means.

[0132] Once the coverage range of the second source cell is determined at each angle, the second ratio (which relates to the coverage radius and the reference radius) and the coverage radius are known, the coverage area of ​​the second source cell can be calculated.

[0133] In some embodiments, step S0211 includes: determining the proportion of users corresponding to each base station tracking area (TA) index of the first sample base station; determining the base station TA index that meets the preset proportion threshold among the user proportions as the target base station TA index; and determining the coverage radius of the second source cell based on the target base station TA index.

[0134] The percentage of users corresponding to each base station TA indicator for the first sample base station can be obtained from the base station TA indicator in the corresponding indicator data of the communication network. The base station TA indicator is a statistical measure of the percentage of mobile devices operating within the area covered by that base station within a certain time range; that is, the user percentage. This user percentage reflects the proportion of mobile device users communicating or transmitting data through that base station within that area to the total number of users within the coverage area of ​​that base station. Therefore, by setting a preset percentage threshold for the user percentage, the areas where most mobile device users are located can be filtered out, that is, the target base station TA indicator can be selected. Based on the target base station TA indicator, the coverage radius of the second source cell can then be calculated.

[0135] In some embodiments, at least one base station TA index is selected from the coverage radius range corresponding to at least one base station TA index that is less than a preset percentage threshold, and the largest radius value is selected as the coverage radius of the second source cell.

[0136] As one embodiment of this disclosure, the base station TA index is shown in tabular form, as shown in Table 1:

[0137] Table 1

[0138] In the query granularity in Table 1, TA(0-78.12) represents the range of coverage radius from 0 to 78.12. The number of users of mobile devices corresponding to TA(0-78.12) accounts for 3.19%, and the cumulative percentage is 3.19%.

[0139] TA(78.12-234.36) represents the coverage radius from 78.12 to 234.36. The percentage of users with mobile devices corresponding to this TA(78.12-234.36) is 15.25%, and the cumulative percentage is 18.44%. The cumulative percentage is the sum of the percentage of users corresponding to TA(0-78.12) and the cumulative percentage corresponding to TA(78.12-234.36).

[0140] TA(234.36-390.6) represents the range from 234.36 to 390.6. The percentage of users with mobile devices corresponding to TA(234.36-390.6) is 21.44%, and the cumulative percentage is 39.88%. The cumulative percentage is the sum of the percentage of users with TA(234.36-390.6) and the cumulative percentage corresponding to TA(78.12-234.36). The percentage of users with TA and the cumulative percentage for other query granularities are similar, and will not be repeated here.

[0141] The preset percentage threshold is set to 98%. The largest radius value (6327.72) in the coverage radius range corresponding to the TA index of base stations with a cumulative percentage greater than 98% (i.e., TA (3906-6327.72) in Table 1) is taken as the coverage radius of the second source cell. In this way, the coverage radius of the first source cell corresponding to the first sample base station is closer to the actual coverage radius.

[0142] In some embodiments, step S03 includes: using the second feature data corresponding to the sample base station as the input value and the neighboring cells corresponding to the sample base station as the target value to train a preset model to obtain a neighboring cell planning model, wherein the neighboring cells corresponding to the sample base station are obtained from the neighboring cell configuration data of the sample base station.

[0143] After performing feature operations on the sample base stations, the second feature data corresponding to the sample base stations is obtained. There can be multiple sample base stations in the communication network. Therefore, a feature data pair list is generated based on the second feature data corresponding to multiple sample base stations. Each sample base station corresponds to one feature data in the feature data pair list. This feature data includes at least the overlapping coverage area coefficient and the number of layers between the sample base station and its base stations within a second preset layer range. It may also include at least one of the following: distance multiple, angle coefficient, and an identifier indicating the correspondence between the first source cell and the first target cell. The second feature data is used as the input value of a preset model, and the known neighboring cells of the sample base station are used as target values ​​for training.

[0144] In some embodiments, the training process may include at least one of data identification, feature column adjustment, training parameter adjustment, and accuracy adjustment.

[0145] Data identification involves comparing the neighboring cells corresponding to the sample base station with each cell in the communication network to determine whether the neighboring cell exists in the current communication network. If it exists, it means that the neighboring cells assigned by the sample base station are reasonable and can be marked as 1. If it does not exist, it means that the neighboring cells assigned by the sample base station are unreasonable and can be marked as 0.

[0146] Feature column adjustment: During model training, the order of the feature information columns used for training is adjusted to improve the accuracy of the neighbor cell planning results of the neighbor cell planning model. In some embodiments, the feature information that has a greater impact on the neighbor cell planning results is placed earlier in the feature information columns.

[0147] Training parameter adjustment: A preset model is used for training. The values ​​of training parameters such as the number of network layers, activation function, and Dropout rate in the preset model are adjusted after cross-validation to improve the accuracy of the trained neighbor cell planning model. This disclosure does not impose special restrictions on the type of preset model; it can be a neural network model or other models. This embodiment of the disclosure leverages the powerful learning capabilities of neural networks to effectively improve the accuracy of neighbor cell planning. Furthermore, it not only incorporates new second feature data but also allows for in-depth learning through neighbor cell planning experience in communication networks, making the model more flexible and better able to cope with the ever-evolving communication network environment.

[0148] By inputting the second feature data into a preset model for training, and adjusting the training parameters based on the accuracy of the trained neighbor planning model, the model can produce good prediction results on the data, achieve better neighbor planning results, and improve the adaptability of the neighbor planning model in different networks.

[0149] The first feature data in this embodiment describes the spatial feature relationship between the source cell corresponding to the newly added base station in the communication network and the first target cell corresponding to the base station within the first preset layer range. The first feature data includes at least the overlapping coverage area coefficient and the number of layers between the newly added base station and the base station within the first preset layer range, which fully ensures the accuracy of neighbor cell planning. At the same time, the neighbor cell planning model learns from the planning experience of each known base station in the communication network. By inputting the first feature data into the neighbor cell planning model, neighbor cell planning can be realized before the newly added base station enters the network based on the first feature data, which significantly improves the timeliness of neighbor cell planning for the newly added base station.

[0150] This disclosure provides a base station. Figure 14 is a schematic diagram of the structure of a base station provided in this disclosure. As shown in Figure 14, the base station includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements any of the neighbor cell planning methods of this disclosure.

[0151] This disclosure provides a computer-readable medium. Figure 15 is a schematic diagram of the structure of a computer-readable medium provided in this disclosure. As shown in Figure 15, the computer-readable medium stores a computer program, which, when executed by a processor, implements any of the neighbor cell planning methods of this disclosure.

[0152] This disclosure provides a computer program product, which includes a computer program that, when executed by a processor, implements any of the neighbor cell planning methods of this disclosure.

[0153] In some embodiments, the computer program product described above can be used to implement the various steps of the neighbor cell planning method described above.

[0154] To enable those skilled in the art to more clearly understand the technical solutions provided by the embodiments of this disclosure, the technical solutions provided by the embodiments of this disclosure will be described in detail below through specific embodiments.

[0155] Example 1

[0156] Figure 16 is a schematic diagram of the structure of an exemplary neighbor cell planning system provided in an embodiment of this disclosure. As shown in Figure 16, the neighbor cell planning system is used to plan the neighbor cells of newly added base stations in the wireless communication access network. The system includes a data extraction module, a data processing module, a feature calculation module, a model training module, a neighbor cell planning module, and a script creation module.

[0157] The data extraction module is used to obtain the indicator data of the communication network, as well as the engineering parameters and neighbor cell configuration data of the known base stations from the wireless communication access network.

[0158] The data processing module is used to clean the communication network indicator data obtained from the wireless communication access network, as well as the engineering parameters and neighbor cell configuration data of known base stations. The data cleaning process includes redundant data removal, data validity verification, and base station latitude and longitude processing. The filtered data is then organized and summarized according to the cell level.

[0159] The feature calculation module is used to calculate feature data consisting of at least the overlapping coverage area coefficient and the number of layers based on the indicator data of the communication network and the engineering parameters and neighbor cell configuration data of the known base station. The feature data is then normalized and includes 5 feature information columns.

[0160] Figure 17 is a flowchart of an exemplary feature calculation provided in an embodiment of this disclosure. As shown in Figure 17, the feature calculation process of the feature calculation module includes steps 1701 to 1704.

[0161] In step 1701, based on the latitude and longitude of each sample base station, a Delano base station triangulation network is established with each sample base station as a vertex.

[0162] In step 1702, each cell in the wireless communication access network is traversed. According to the De Lao inner triangulation, if the vertices corresponding to other base stations are connected to the vertices corresponding to the first base station through at least n triangle edges, it is determined that other base stations are the nth level of the first base station. The serving cells of other base stations with a layer number less than 3 or equal to 3 in the wireless communication access network are determined as the first target cells, and a three-layer neighbor cell pair list is generated based on the second target cells.

[0163] In step 1703, the coverage radius is determined based on the base station TA index data in the index data corresponding to the sample base station; the coverage area of ​​the sample base station and its second target cell is calculated based on the second ratio corresponding to the coverage radius and the coverage range angle; the overlapping coverage area coefficient is calculated based on the coverage area of ​​the sample base station and its second target cell; the site distance between the sample base station and each second target cell is calculated; and the forward angle and the reverse angle are calculated based on the line connecting the sample base station and each second target cell and the azimuth vector.

[0164] In step 1704, the overlapping coverage area coefficient, site spacing, forward angle, and backward angle are normalized to obtain the distance multiple, the layer number of the second target cell in the three-layer neighbor cell pair list, the overlapping coverage area coefficient, the forward angle coefficient, and the backward angle coefficient. These distance multiples, the layer number of the second target cell in the three-layer neighbor cell pair list, the overlapping coverage area coefficient, the forward angle coefficient, and the backward angle coefficient constitute the feature information column.

[0165] The model training module is used to adjust factors such as the order of feature information columns and the threshold of neural network parameters to debug the neighbor planning model so that the accuracy of the neighbor planning results is greater than the preset accuracy value.

[0166] Figure 18 is a flowchart of an exemplary model training process provided in an embodiment of this disclosure. As shown in Figure 18, the model training process of the model training module includes steps 1801 to 1805.

[0167] In step 1801, collect the indicator data of the wireless communication access network, as well as the engineering parameters and neighbor cell configuration data of the known base stations.

[0168] In step 1802, the collected data is processed by removing redundant data, verifying data validity, and processing the latitude and longitude of base stations to obtain the processed index data of the communication network, as well as the engineering parameters and neighbor cell configuration data of the sample base stations.

[0169] In step 1803, based on the indicator data of the communication network and the neighbor cell configuration data, the engineering parameters of the sample base station are processed to obtain the second feature data. The second feature data includes the distance multiple, the layer number of the second target cell in the three-layer neighbor cell pair list, the overlapping coverage area coefficient, the forward angle coefficient, and the backward angle coefficient.

[0170] In step 1804, the second feature data is used as the input value, and the neighboring cells corresponding to the sample base station are used as the target value to train the preset model, thereby obtaining the neighboring cell planning model. Training is complete when the accuracy of the trained neighboring cell planning model meets the expected value.

[0171] Figure 19 is a schematic diagram of training data for an exemplary model training provided in an embodiment of this disclosure. As shown in Figure 19, the accuracy of data training is measured by the loss value and the accuracy.

[0172] Referring back to Figure 18, in step 1805, the neighbor cell planning model can be used to plan neighbor cells for newly added base stations in the wireless communication access network.

[0173] The neighbor cell planning module is used to perform feature calculations on newly added base stations, and then use the trained neighbor cell planning model to perform neighbor cell planning on the newly added base stations to obtain the neighbor cell planning results.

[0174] Figure 20 is a flowchart of an exemplary neighbor cell planning method provided in an embodiment of this disclosure. As shown in Figure 20, the neighbor cell planning method includes steps 2001 to 2003.

[0175] In step 2001, the engineering parameters of the base station to be added to the communication network are obtained, including: base station ID, base station name, cell ID, cell name, latitude and longitude, cell azimuth, etc.

[0176] In step 2002, feature calculations are performed on the engineering parameters of the newly added base station to obtain the first feature data.

[0177] In step 2003, the first feature data is input into the trained neighbor planning model to obtain the neighbor planning result.

[0178] The script creation module is used to generate neighbor cell scripts that can be imported into the existing network based on the neighbor cell planning results, and to synchronize the neighbor cell scripts to the wireless communication access network.

[0179] Example 2

[0180] Figure 21 is a flowchart of another exemplary neighbor cell planning method provided in an embodiment of this disclosure. As shown in Figure 21, the neighbor cell planning method includes steps 2101 to 2106.

[0181] In step 2101, the indicator data of the wireless communication access network, as well as the engineering parameters and neighbor cell configuration data of the known base stations, are obtained.

[0182] In step 2102, the second feature data is calculated using the indicator data of the wireless communication access network and the engineering parameters and neighbor cell configuration data of the known base stations. This second feature data includes distance coefficient, relative angle (i.e., angle coefficient), overlapping coverage area coefficient, and number of layers. The second feature data reflects the spatial relationship and coverage between the newly added base station and base stations within a second preset layer range, providing a foundation for training the neighbor cell planning model.

[0183] In step 2103, a preset model based on a neural network machine learning method is used to train the second feature data to obtain an intelligent preset neighbor cell planning model. This model fully learns the known neighbor cell configuration experience of the existing network (i.e., the communication network) base stations, has strong adaptability, and can understand and utilize the complex relationship between the second feature data and the neighbor cell planning.

[0184] In step 2104, in the case of a new base station, the engineering parameters of the new base station are obtained.

[0185] Step 2105: Calculate the first feature data of the newly built base station based on the engineering parameters of the new base station, and input the first feature data into the trained neighbor cell planning model.

[0186] In step 2106, the neighbor cell planning results are obtained through the neighbor cell planning model to ensure that the neighbor cell configuration of the newly built base station meets the optimal requirements of the communication network.

[0187] Figure 22 is a flowchart of an exemplary model training process provided in an embodiment of this disclosure. As shown in Figure 22, the model training process in step 2103 includes steps 2201 to 2204.

[0188] In step 2201, the calculated second feature data is compared with the neighbor cell configuration data in the communication network to determine whether the neighbor cell planning in the known base stations is reasonable, thereby identifying the data. A unique index is established between the sample base station and its neighbor cells, and redundant data is deleted.

[0189] In step 2202, the feature columns are adjusted, placing the feature information columns that have a greater impact on the neighboring cell planning results earlier. Cross-validation and adjustments are performed on the values ​​of parameters such as the number of network layers, activation function, and Dropout rate in the preset model.

[0190] In step 2203, the model is trained.

[0191] In step 2204, the accuracy of the neighbor planning of the trained model is compared with the preset accuracy value. If the accuracy meets the standard, the training is completed. If the accuracy does not meet the standard, the parameters are adjusted and the model is retrained.

[0192] A processor is a device with data processing capabilities, including but not limited to a central processing unit (CPU); a memory is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); an I / O interface (read / write interface) connects the processor and the memory, enabling information exchange between the memory and the processor, including but not limited to a data bus (Bus).

[0193] Those skilled in the art will understand that all or some of the steps, systems, and devices disclosed above, as functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0194] In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be executed by several physical components working together.

[0195] Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit (CPU), digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technique for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH) or other disk storage; read-only optical disc (CD-ROM), digital versatile disc (DVD) or other optical disc storage; magnetic cartridges, magnetic tapes, disk storage or other magnetic storage; and any other media that can be used to store desired information and can be accessed by a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0196] This disclosure has disclosed exemplary embodiments, and although specific terminology has been used, it is for general illustrative purposes only and should not be construed as limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in connection with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in connection with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this disclosure as set forth by the appended claims.

Claims

1. A neighborhood planning method, comprising: First feature data is calculated based on the engineering parameters of a first base station in the communication network. This first feature data describes the spatial relationship between a first source cell and a first target cell of the first base station, and includes at least an overlap coverage area coefficient and the number of layers between the first base station and a second base station in the communication network. The first target cell is the cell corresponding to the second base station, and the second base station is located within a first preset number of layers of the first base station, where the number of layers represents the geographical location association between the base stations. Based on the first feature data and the preset neighbor cell planning model, the neighbor cell planning result corresponding to the first base station is determined.

2. The method according to claim 1, wherein, The first feature data, calculated based on the engineering parameters of the first base station, includes: Calculate the coverage area of ​​the first source cell; and The first feature data is calculated based on the coverage area of ​​the first source cell and the coverage area of ​​the first target cell.

3. The method according to claim 2, wherein, Calculating the coverage area of ​​the first source cell includes: Determine the coverage radius of the first source cell; Obtain multiple angles within the angle range of the first source cell and a first ratio corresponding to each of the multiple angles, wherein the first ratio is the ratio of the coverage radius of the first source cell to the reference radius; and The coverage area of ​​the first source cell is determined based on the angle of the first source cell, the first ratio corresponding to each of the plurality of angles, and the coverage radius.

4. The method according to claim 3, wherein, Determining the coverage radius of the first source cell includes: The second base station is detected within a preset angle range corresponding to the positive angle between each of the first source cell and the first target cell; and The coverage radius of the first source cell is determined based on the number of second base stations detected.

5. The method according to claim 1, wherein, Based on the first feature data and the preset neighbor cell planning model, the neighbor cell planning result corresponding to the first base station is determined, including: The overlapping coverage area coefficient and the number of layers between the first base station and the second base station are input into the preset neighbor cell planning model; and Using the preset neighbor cell planning model, target neighbor cells are determined from the first target cell of the second base station to obtain the neighbor cell planning result corresponding to the first base station. The neighbor cell planning result includes the target neighbor cells.

6. The method according to any one of claims 1 to 5, wherein, After determining the neighbor cell planning result corresponding to the first base station based on the first feature data and the preset neighbor cell planning model, the method further includes: The neighbor cell configuration data corresponding to the neighbor cell planning results is updated to the neighbor cell configuration data of the known base stations in the communication network.

7. The method according to any one of claims 1 to 5, wherein, The first feature data also includes at least one of the following: the distance multiple between the first source cell and the first target cell, the angle coefficient between the first source cell and the first target cell, and the identifier indicating the correspondence between the first source cell and the first target cell.

8. The method according to claim 1, further comprising: Acquire the indicator data of the communication network and the engineering parameters and neighbor cell configuration data of the sample base station, wherein the sample base station is a known base station in the communication network; The second feature data corresponding to the sample base station is calculated based on the indicator data and the engineering parameters of the sample base station. The second feature data is used to describe the spatial feature relationship between the second source cell and the second target cell of the first sample base station in the sample base station. It includes at least the overlapping coverage area coefficient and the number of layers between the first sample base station and the second sample base station in the communication network. The second target cell is the cell corresponding to the second sample base station. The second sample base station is within the second preset number of layers of the first sample base station. The number of layers represents the geographical location association between the base stations. Based on the second feature data corresponding to the sample base station and the neighbor cell configuration data, the preset model is trained to obtain the preset neighbor cell planning model.

9. The method according to claim 8, wherein, The second feature data corresponding to the sample base station is calculated based on the indicator data and the engineering parameters of the sample base station, including: Calculate the coverage area of ​​the second source cell; The second feature data is calculated based on the coverage area of ​​the second source cell and the coverage area of ​​the second target cell.

10. The method according to claim 9, wherein, Calculating the coverage area of ​​the second source cell includes: The coverage radius of the second source cell is determined based on the indicator data of the communication network. Obtain multiple angles within the angle range of the second source cell and a second ratio corresponding to each of the multiple angles, wherein the second ratio is the ratio of the coverage radius of the second source cell to the reference radius; The coverage area of ​​the second source cell is determined based on the angle of the second source cell, the second ratio corresponding to each of the plurality of angles, and the coverage radius.

11. The method according to claim 10, wherein, Based on the indicator data of the communication network, the coverage radius of the second source cell is determined, including: Determine the percentage of users corresponding to each base station tracking area indicator of the first sample base station; The base station tracking area indicators that meet the preset percentage threshold among the user number percentages are determined as the target base station tracking area indicators. The coverage radius of the second source cell is determined based on the target base station tracking area index.

12. The method according to claim 8, wherein, Based on the second feature data corresponding to the sample base station and the neighbor cell configuration data, the preset model is trained to obtain the preset neighbor cell planning model, including: The second feature data corresponding to the sample base station is used as the input value, and the neighboring cells corresponding to the sample base station are used as the target value to train the preset model to obtain the preset neighboring cell planning model, wherein the neighboring cells corresponding to the sample base station are obtained from the neighboring cell configuration data of the sample base station.

13. A base station, comprising a memory and a processor, wherein, The memory stores a computer program that can be executed by the processor, which, when executed by the processor, implements the neighbor cell planning method according to any one of claims 1 to 12.

14. A computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the neighbor cell planning method of any one of claims 1 to 12.

15. A computer program product comprising a computer program that, when executed by a processor, implements the neighbor cell planning method of any one of claims 1 to 12.

Images