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

Abstract

The invention provides a neighbor cell planning method. The method comprises the following steps: calculating first feature data according to engineering parameters of a first base station; wherein the first feature data is 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 comprises an overlapping coverage area coefficient and the number of layers between the first base station and the second base station; the first target cell is a cell corresponding to a second base station except the first base station in the communication network, the second base station is in a first preset layer number range of the first base station, and the layer number represents an association relationship of geographic positions between the base stations; and determining a neighbor cell planning result corresponding to the first base station according to the first feature data and a preset neighbor cell planning model. The disclosure also provides a base station, a computer readable medium, and a computer program product.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of communication technology, and in particular, to a method for neighbor cell planning, a base station, a medium and a computer program product. BACKGROUND

[0002] A communication network is the core infrastructure for the development of digital economy, and network planning of the communication network is the first construction step, and the neighbor cell planning of the communication base station is a crucial part of the entire network planning. The neighbor cell planning directly affects the neighbor cell switching between base stations for mobile terminal devices, and such switching is a crucial technology in the communication network. When a mobile device moves from one cell to another, the neighbor cell switching allows the mobile device to realize seamless switching while maintaining a communication connection, to ensure the continuity of calls and data transmission, thereby providing a smoother mobile experience and ensuring communication quality.

[0003] Therefore, there is an urgent need for a scheme capable of realizing accurate neighbor cell planning. SUMMARY

[0004] The present disclosure provides a method for neighbor cell planning, a base station, a medium and a computer program product.

[0005] In a first aspect, the present disclosure provides a method for neighbor cell planning, comprising:

[0006] calculating first feature data according to engineering parameters of a first base station; wherein the first feature data is used to describe a spatial feature relationship between a first source cell and a first target cell of the first base station, and at least includes an overlapping coverage area coefficient and a number of layers between the first base station and a second base station; the first target cell is a cell corresponding to the second base station in the communication network except the first base station, and the second base station is within a first preset number of layers of the first base station, and the number of layers represents a geographical location correlation relationship between base stations;

[0007] determining a neighbor cell planning result corresponding to the first base station according to the first feature data and a preset neighbor cell planning model.

[0008] In a second aspect, the present disclosure provides a base station, comprising a memory and a processor; the memory stores a computer program executable by the processor, and the computer program is executed by the processor to realize the method for neighbor cell planning in the first aspect.

[0009] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, and the computer program is executed by a processor to realize the method for neighbor cell planning in the first aspect.

[0010] In a third aspect, the embodiments of the present disclosure provide a computer program product, comprising a computer program, which, when executed by a processor, implements the neighbor planning method of the first aspect.

[0011] The first feature data in the embodiments of the present disclosure is used to describe the spatial feature relationship between the source cell corresponding to the newly added base station and the first target cell corresponding to the base station within the first preset layer number range of the newly added base station in the communication network, and the first feature data at least includes an overlapping coverage area coefficient and a layer number between the newly added base station and the base station within the first preset layer number range, which sufficiently guarantees the accuracy of the neighbor planning; meanwhile, the neighbor planning model learns the planning experience of each known base station in the communication network, and the first feature data is input into the neighbor planning model, so that the neighbor planning before the newly added base station is connected to the network can be realized based on the first feature data, and the timeliness of the neighbor planning of the newly added base station is significantly improved. BRIEF DESCRIPTION OF DRAWINGS

[0012] In the drawings of the embodiments of the present disclosure:

[0013] Figure 1 A flowchart of a neighbor planning method provided by the embodiments of the present disclosure;

[0014] Figure 2 A schematic diagram of the relationship between a base station and a cell provided by the embodiments of the present disclosure;

[0015] Figure 3 A structural schematic diagram of a base station triangular network provided by the embodiments of the present disclosure;

[0016] Figure 4 A hierarchical distribution rendering effect schematic diagram of a first base station and other base stations except the first base station provided by the embodiments of the present disclosure;

[0017] Figure 5 A schematic diagram of an included angle coefficient provided by the embodiments of the present disclosure;

[0018] Figure 6 A flowchart of a specific implementation method of step S1 in the embodiments of the present disclosure;

[0019] Figure 7 A structural schematic diagram of a cell overlapping coverage part provided by the embodiments of the present disclosure;

[0020] Figure 8 A flowchart of a specific implementation method of step S11 in the embodiments of the present disclosure;

[0021] Figure 9 A simulation schematic diagram of a cell coverage range provided by the embodiments of the present disclosure;

[0022] Figure 10 A flowchart of a specific implementation method of step S2 in the embodiments of the present disclosure;

[0023] Figure 11 A specific implementation method flow chart for determining a neighboring cell planning model in an embodiment of the present disclosure;

[0024] Figure 12 A specific implementation method flow chart for step S02 in an embodiment of the present disclosure;

[0025] Figure 13 A specific implementation method flow chart for step S021 in an embodiment of the present disclosure;

[0026] Figure 14 A structural schematic diagram of a base station provided in an embodiment of the present disclosure;

[0027] Figure 15 A structural schematic diagram of a computer readable medium provided in an embodiment of the present disclosure;

[0028] Figure 16 A structural schematic diagram of an exemplary neighboring cell planning system provided in an embodiment of the present disclosure;

[0029] Figure 17 A flow chart of exemplary feature calculation provided in an embodiment of the present disclosure;

[0030] Figure 18 A flow chart of exemplary model training provided in an embodiment of the present disclosure;

[0031] Figure 19 A training data schematic diagram of exemplary model training provided in an embodiment of the present disclosure;

[0032] Figure 20 A flow chart of an exemplary neighboring cell planning method provided in an embodiment of the present disclosure;

[0033] Figure 21 A flow chart of another exemplary neighboring cell planning method provided in an embodiment of the present disclosure;

[0034] Figure 22 A flow chart of exemplary model training provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0036] The present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the present disclosure are shown. The present disclosure may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0037] The accompanying drawings are included to provide a further understanding of embodiments of the present disclosure and are incorporated in and constitute a part of the specification. The drawings illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. The above and other features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, including the description of the detailed embodiments.

[0038] The present disclosure can be described with reference to plan views and / or cross-sectional views by virtue of the present disclosure idealized schematic. Consequently, the example illustrations can be modified according to manufacturing techniques and / or tolerances.

[0039] The embodiments of the present disclosure and the features in the embodiments can be combined with each other if there is no conflict.

[0040] The terms used in the present disclosure are merely used to describe particular embodiments, and are not intended to limit the present disclosure. As used in the present disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items. As used in the present disclosure, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. As used in the present disclosure, the terms "comprises," "comprising," "includes," "including," "has," "having," and the like are intended to be open-ended terms that specifically permit the presence of one or more other features, integers, steps, operations, elements, and / or groups thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or groups thereof.

[0041] Unless otherwise defined, all terms used in the present disclosure, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0042] The present disclosure is not limited to the embodiments shown in the drawings, but includes modifications of configurations formed based on manufacturing processes. Therefore, the regions exemplified in the drawings have a schematic property, and the shape of the regions shown in the drawings exemplifies a specific shape of a region of an element, but is not intended to be restrictive.

[0043] In some related technologies, in 2G (the 2th generation mobile communication technology) networks and 3G networks, the neighbor cell planning in the communication network is usually realized by means of tool planning or manual adjustment; the tool planning needs to add the multiple close-range cells in the forward coverage direction of the cell corresponding to the newly added base station to the neighbor cell list according to the distance and the included angle between the newly added base station and each base station in the existing network and the longitude and latitude and azimuth information of the cell corresponding to the newly added base station. However, this neighbor cell planning method mainly based on the distance and the included angle of the cells has various problems such as neighbor cell missing, low neighbor cell planning accuracy, and too many neighbor cells, which makes it difficult to guarantee the accuracy of the neighbor cell planning.

[0044] In the 4G network stage, although the ANR (Automatic Neighbor Relations) technology is introduced to solve the neighbor cell planning demand of the communication network on the basis of the tool planning and manual adjustment. However, the ANR technology is limited to the newly added base station needing to run in the network for a period of time, and then the neighbor cell is automatically planned and optimized according to the signals reported by the mobile device corresponding to the newly added base station, in other words, the ANR technology cannot obtain accurate planning results before the newly added base station is put into the network, which leads to the defect that the neighbor cell planning process has poor timeliness.

[0045] Therefore, there is an urgent need for a more fine, intelligent and more timely neighbor cell planning method to adapt to the increasingly complex communication network environment.

[0046] Figure 1 A flowchart of a neighbor cell planning method provided by the embodiments of the present disclosure is provided. Referring to Figure 1 , in a first aspect, the embodiments of the present disclosure provide a neighbor cell planning method, which comprises:

[0047] S1, calculating first feature data according to the engineering parameters of a first base station; wherein the first feature data is used to describe the spatial feature relationship between the first source cell of the first base station and the first target cell, and at least includes an overlapping coverage area coefficient and the number of layers between the first base station and a second base station; the first target cell is a cell corresponding to the second base station in the communication network except the first base station, and the second base station is within a first preset number of layers of the first base station, and the number of layers represents the association relationship of the geographical positions between the base stations;

[0048] S2, determining the neighbor cell planning result corresponding to the first base station according to the first feature data and a preset neighbor cell planning model.

[0049] Among them, the engineering parameters of the first base station include at least one of the base station identification 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 the first preset number of floors of the first base station. The first preset number of floors is used to define base stations in the communication network that meet the preset geographical location conditions with the first base station. The source cell is the service cell of the first base station, and the first target cell is the service cell of the second base station. The embodiment of the present disclosure does not impose any special restrictions on the number of service cells of each base station. For example Figure 2 As shown, in some embodiments, a base station may include three service cells (source cell 1, source cell 2, and source cell 3), and these three service cells cover three different directions respectively. The first characteristic data is used to describe the spatial characteristic relationship between the first source cell of the first base station and the first target cell, wherein the spatial characteristic relationship includes at least the overlapping coverage area coefficient and the number of layers between the base stations. The overlapping coverage area coefficient refers to the proportion of the overlapping coverage area between the first source cell and the first target cell in the first source cell. The number of layers refers to the association relationship between the geographical locations of the first base station corresponding to the first source cell and the second base station corresponding to the first target cell.

[0050] The first characteristic data in the embodiment of the present disclosure describes the spatial characteristic 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 in the communication network, and introduces the overlapping coverage area coefficient and the number of layers between base stations to characterize the spatial characteristic relationship. Compared with some related technologies that mainly consider the neighboring area planning scheme of distance and angle, the embodiment of the present disclosure solves the problems of missing neighboring areas, low planning accuracy, too many neighboring areas, etc., and fully guarantees the accuracy of neighboring area planning.

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

[0052] The disclosed embodiments do not impose any particular restrictions on the model type of the neighborhood planning model. In some embodiments, the neighborhood planning model uses machine learning techniques to learn the neighborhood planning results of base stations that have already undergone neighborhood planning in the communication network. The trained preset neighborhood planning model can output the neighborhood planning results corresponding to the base station based on the input base station feature data.

[0053] Compared with the ANR technology, the newly added base station does not need to run in the network for a period of time, and does not need to further optimize the neighbor cell planning according to the signals reported by the mobile device corresponding to the newly added base station, but can obtain an accurate neighbor cell planning result before the newly added base station is connected to the communication network (that is, the newly added base station is connected to the communication network), thereby significantly improving the timeliness of the neighbor cell planning of the newly added base station, and ensuring the continuity of the mobile device in the newly added base station when the mobile device is in a call or data transmission, thereby providing a more smooth mobile experience and better communication quality for the mobile device user.

[0054] The determination process of the number of layers between the first base station and the second base station is described below.

[0055] According to the engineering parameters of the first base station and the engineering parameters of the other base stations in the communication network except the first base station, a hierarchical relationship between the first base station and the other base stations is constructed.

[0056] The other base station satisfying the hierarchical relationship with the first base station in the first preset number of layer range is determined as the second base station, and the cell corresponding to the second base station is determined as the first target cell.

[0057] According to the engineering parameters of the first base station and the engineering parameters of the second base station, a hierarchical relationship between the first base station and the other base stations in the communication network except the first base station is constructed, including:

[0058] According to the longitude value and the latitude value of the first base station and the other base stations, the first base station and the other base stations are taken as the vertices of a triangle in a base station triangulation network, and the base station triangulation network is constructed; wherein, the circumscribed circle corresponding to each triangle only includes the vertices of the triangle, and the incircle of the triangle does not include any base station vertex; in some embodiments, the base station triangulation network is a De l aunay triangulation network.

[0059] According to the base station triangulation network, a hierarchical relationship between the first base station and the other base stations is determined; wherein, the hierarchical relationship is used to represent that the other base station is the n-level of the first base station, and n is a positive integer.

[0060] In some embodiments, according to the base station triangulation network, the hierarchical relationship between the first base station and the other base stations is determined, including: in the case that the vertex corresponding to the other base station and the vertex corresponding to the first base station are connected through at least n edges of the triangle, it is determined that the other base station is the n-level of the first base station.

[0061] As one of the modes of the embodiments of the present disclosure, as Figure 3As shown, the vertex positions are determined according to the longitude and latitude values of the first base station and other base stations except the first base station, a Delaunay triangulation is constructed with the first base station and other base stations as the vertices of the triangles in the triangulation, and the Delaunay triangulation is a triangulation constructed by the vertex set of the first base station and other base stations and not containing any base station vertex in the incircle of the triangle of which the base station vertex is a vertex. According to the constructed Delaunay triangulation, the base stations of the same or different levels around the first base station can be determined, and further, a base station list can be constructed according to the base stations of the levels.

[0062] Figure 4 The first base station and the level distribution rendering effect of other base stations except the first base station are provided for the embodiments of the present disclosure. As shown in Figure 4 The first base station is taken as the center, the first preset number of layers is set to 3 layers, and then the base stations of level 1, level 2 and level 3 can all be determined as the second base station, and the level reflects the association relationship between the geographical positions of the other base stations and the first base station.

[0063] In some embodiments, after the base station triangulation is constructed, the method can further include:

[0064] The base stations of the first preset number of layers in the other base stations are determined as the second base station, and a first target cell pair list is constructed according to the second base station corresponding to the first target cell.

[0065] The information contained in each 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 longitude and latitude of the first source cell, the cell azimuth angle 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 longitude and latitude of the first target cell, the cell azimuth angle of the first target cell, and the number of layers in which the cell of the first target cell is located in the first source cell.

[0066] In some embodiments, the first feature data further includes at least one of the following:

[0067] The distance multiple;

[0068] The included angle coefficient;

[0069] The identifier corresponding to the first source cell and the first target cell.

[0070] The distance multiple reflects a relationship between a first distance between the newly added first base station and the second base station and a second distance between the first base station and all base stations in the third preset number range of layers. The inter-cell distance value between the first source cell and the first target cell is the inter-site distance 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, the inter-site distance can be calculated according to the engineering parameters of the first base station and the engineering parameters of the second base station in the communication network. As one way of the embodiments of the present disclosure, the distance multiple between the first source cell and the first target cell is calculated by the longitude value and the latitude value of the first base station and the longitude value and the latitude value of the second base station.

[0071] In some embodiments, when the first feature data is the distance multiple, step S1 includes:

[0072] determining a second distance between the first base station and all intermediate base stations in the third preset number range of layers corresponding to the first base station;

[0073] 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.

[0074] As one way of the embodiments of the present disclosure, the intermediate base stations in the third preset number range of layers refer to the base stations with a layer number of 1 around the first base station, and the distance multiple is calculated by the formula:

[0075]

[0076] It should be noted that when the number of all intermediate base stations in the third preset number range of layers is multiple, the statistical method of the second distance in the embodiments of the present disclosure is not specially limited, which can be the median, the average, the maximum, the minimum, etc. of the second distance, and can be set according to actual requirements.

[0077] The angle coefficient refers to a relationship between a line connecting the first source cell and the first target cell and a cell azimuth angle vector of the first source cell or the first target cell. The angle coefficient is calculated according to a forward angle and / or a backward angle. The forward angle is an angle between the line connecting the first source cell and the first target cell and the cell azimuth angle vector of the first source cell, that is, the forward angle = the angle between the line connecting the first source cell and the first target cell and the cell azimuth angle vector of the first source cell. The backward angle is an angle between the line connecting the first source cell and the first target cell and the cell azimuth angle vector of the first target cell, that is, the backward angle = the angle between the line connecting the first target cell and the first source cell and the cell azimuth angle vector of the first target cell.

[0078] In some embodiments, the angle coefficient is calculated by the formula:

[0079]

[0080] As an embodiment of the present disclosure, as shown in Figure 5 , the base station B includes three serving cells covering three different directions (i.e. AL0001A, AL0001B, AL0001C), and the base station C includes three serving cells covering three different directions (i.e. AL0002A, AL0002B, AL0002C). Among them, AL0001B is the source cell, AL0002C is the target cell, the cell azimuth angle of AL0001B is 120°, and the line connecting AL0001B and AL0002C is 80°, so the forward included angle is 40°. Through the formula: included angle coefficient = included angle / 180°, the included angle coefficient corresponding to the forward included angle of AL0001B as the source cell and AL0002C as the target cell is calculated as 40 / 180 = 0.222222.

[0081] The identifier is used to uniquely index the first source cell and the first target cell, that is, the identifier is the unique identifier of 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 first target cell ID. The present disclosure does not make special restrictions on the form of the identifier.

[0082] Figure 6 is a specific implementation method flowchart of step S1 in the present disclosure. Referring to Figure 6 , in some embodiments, S1 includes:

[0083] S11, calculating the coverage area of the first source cell;

[0084] S12, calculating the first feature data according to the coverage area of the first source cell and the coverage area of the first target cell.

[0085] The coverage area of a cell refers to the signal coverage range of the corresponding base station, that is, the geographical area range that the cell can provide communication services in the mobile network. The overlapping coverage area coefficient can be calculated according to the coverage area of the first source cell and the coverage area of the first target cell. The overlapping coverage area coefficient refers to the ratio between the overlapping area between the first source cell and the first target cell and the coverage area of the first source cell, that is:

[0086]

[0087] As Figure 7As shown, in some embodiments, the service cell corresponding to base station A is cell A, the service cell corresponding to base station B is cell B, and the area of the overlapping coverage of cell A and cell B is the area of the overlapping part 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 part 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 part is divided by the coverage area of cell B.

[0088] Compared with the neighboring cell planning scheme focusing on distance and included angle, the first feature data including the overlapping coverage area coefficient is calculated after the hierarchical division of the base stations in the communication network according to the engineering parameters of the base stations and the engineering parameters of the first base station, which introduces more factors related to the relationship between the base stations and effectively solves the problems of neighboring cell missing, low planning accuracy, and excessive neighboring cells. In addition, introducing more factors for neighboring cell division can effectively improve the accuracy of neighboring cell planning and better cope with different complex communication network environments.

[0089] Figure 8 A specific implementation method flowchart for step S11 in the embodiments of the present disclosure is shown in FIG. 1. Referring to FIG. 1, Figure 8 In some embodiments, S11 includes:

[0090] S111, determining the coverage radius of the first source cell;

[0091] S112, obtaining the angles of the first source cell and the first ratio corresponding to each of the angles; wherein the first ratio is the ratio of the coverage radius of the first source cell to the reference radius;

[0092] S113, determining the coverage area of the first source cell according to the angles of the first source cell, the first ratio corresponding to each of the angles, and the coverage radius.

[0093] The coverage area of the first source cell can be calculated according to the angles of the first source cell, the first ratio corresponding to each of the angles, and the coverage radius, wherein the first ratio refers to the ratio of the coverage radius of the first source cell to the reference radius. The reference radius refers to the signal coverage range radius of the cell in an ideal state, that is, the range covered by the farthest distance that the signal of the base station can reach without being hindered by terrain, buildings, etc.

[0094] In addition, the coverage range of the cell is not specially limited in the embodiments of the present disclosure. It should be understood that in actual operation, the coverage range of the cell corresponding to the base station is not necessarily a standard fan-shaped structure range, and the coverage graph of the cell can be drawn through simulation and other technical means.

[0095] As a way of the embodiments of the present disclosure, as Figure 9As shown, the coverage range of the cell is not a sector structure, but within the angle range of [+80°, -80°], the coverage radius gradually decreases, and the specific angle and the corresponding relationship of the first ratio are as follows:

[0096] [(-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)].

[0097] Wherein -80 in (-80, 0.25) represents an angle of -80°, and 0.25 represents a first ratio of 0.25; -70 in (-70, 0.4) represents an angle of -70°, and 0.4 represents a first ratio of 0.4; and the others are the same. To avoid repetition, the explanation is not repeated here. As can be seen, the coverage range of the cell corresponding to the base station is not necessarily a standard sector graph, and the coverage radius is not necessarily linearly changed with the angle.

[0098] After determining the first ratio (the ratio is related to the relationship between the coverage radius and the reference radius) and the coverage radius corresponding to each angle of the coverage range, the coverage area of the cell can be calculated.

[0099] In some embodiments, S111 includes:

[0100] Detecting a second base station in a preset angle range corresponding to a forward included angle between the first source cell and each of the first target cells;

[0101] According to the number of detected second base stations, determining the coverage radius of the first source cell.

[0102] In the first base station corresponding to the first source cell is a base station that needs to be added in the communication network. In the case that the first base station has not been added to the communication network, the base station TA (Tracking Area) index of the first base station has not been updated in the index data corresponding to the communication network, and the base station TA index is used to describe the situation of the tracking area corresponding to the base station in the mobile network. The tracking area refers to an area in a communication network, which is 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 been added to the communication network, the base station TA index cannot be obtained, and the coverage radius is calculated by detecting all second base stations within the preset angle range corresponding to the forward included angle between the first source cell and each first target cell.

[0103] In some embodiments, in the case that the number of detected second base stations is zero, the coverage radius of the first source cell is determined as a preset empirical radius value; in the case that the number of detected second base stations is greater than zero, the coverage radius of the first source cell is determined as the median of the distance values between the detected second base stations and the first base station. Wherein, the preset empirical radius value is not specially limited in the present disclosure, and in some embodiments, the preset empirical radius value can be determined according to the base station site density of different communication networks.

[0104] As one way of the embodiments of the present disclosure, from the three layers of base stations around the first source cell of the newly built first base station, all second base stations located within the 60° range of the forward included angle of the first source cell of the newly built first base station are detected, and the inter-site distance between the first base station and the detected second base stations is calculated to obtain a site distance list.

[0105] In the case that the number of second base stations detected in the site distance list is zero, that is, there is no base station that meets the condition of being located within the 60° range of the forward included angle of the first source cell of the newly built first base station, the coverage radius is set to 4000m. In the case that the number of second base stations detected in the site distance list is greater than 3, the median of the three detected second base stations with the largest inter-site distance with the first base station in the site distance list is taken as the coverage radius. In the case that the number of second base stations detected in the site distance list is 1 or 2, the average of the inter-site distance is taken as the coverage radius.

[0106] Figure 10 A specific implementation method flow chart for step S2 in the embodiments of the present disclosure. Referring to Figure 10 In some embodiments, S2 includes:

[0107] S21, input the overlap coverage area coefficient and the number of layers between the first base station and the second base station into the preset neighbor planning model;

[0108] S22, determining a target neighbor cell from the first target cell of the second base station by using the preset neighbor planning model, to obtain a neighbor planning result corresponding to the first base station.

[0109] The preset neighbor planning model is used to select one or more cells from the second base station as the target neighbor cell of the first base station according to the inputted overlapping coverage area coefficient of the newly added first base station and the layer number relationship between the first base station and the second base station. In some embodiments, the neighbor planning model can construct a feature information column according to the overlapping coverage area coefficient, the layer number relationship, the distance multiple, the angle coefficient and the identifier corresponding to the first source cell and the first target cell in the first feature data of the first base station and each second base station, and then perform neighbor planning. It should be understood that the more factors included in the first feature data, the more accurate the neighbor planning result.

[0110] Before step S21, at least one of the following steps is further included:

[0111] Establishing a unique index between the first base station and the second base station (i.e. the identifier corresponding to the first source cell and the first target cell), which can be in various forms, such as the form of "base station ID + cell ID";

[0112] Deleting redundant process data in the first feature data of the newly added first base station and the layer number relationship between the first base station and the second base station, so as to exclude the interference of redundant data on the neighbor planning of the model.

[0113] In some embodiments, after determining the target neighbor cell, the method further includes:

[0114] Generating a recommended score column of the first target cell corresponding to each second base station.

[0115] The recommended score column is used to sort the priority of the first target cell corresponding to the second base station as the target neighbor cell of the source cell corresponding to the first base station. In actual application, a threshold score corresponding to the recommended score column can be selected according to the specific scene of the communication network, so as to quickly filter out the list of target neighbor cells, which helps to optimize the neighbor planning and improve the flexibility of the neighbor planning, so as to adapt to different application scenes and different application requirements of the communication network.

[0116] In some embodiments, after S2, the method further includes:

[0117] Updating the neighbor configuration data corresponding to the neighbor planning result to the neighbor configuration data of the known base station in the communication network.

[0118] The neighbor area configuration data is used to describe the neighbor cell related information of the base station. After determining the neighbor area planning result of the newly added first base station, that is, planning the target neighbor cell for the first base station, the neighbor area configuration data corresponding to the neighbor area planning result can be generated and updated to the neighbor area configuration data of the known base station in the communication network. In some embodiments, the neighbor area configuration data of the known base station in the communication network is a neighbor area script, that is, a configuration file or script used to describe the adjacent cell relationship in the communication network.

[0119] Figure 11 A specific implementation method flowchart for determining the neighbor area planning model in the embodiments of the present disclosure is shown in FIG. 1. Referring to FIG. 1, Figure 11 In some embodiments, the method further comprises:

[0120] S01, obtaining index data of the communication network and engineering parameters and neighbor area configuration data of sample base stations; the sample base stations are known base stations in the communication network;

[0121] S02, calculating second feature data corresponding to each sample base station according to the index data and the engineering parameters of each sample base station; wherein the second feature data is used to describe the spatial feature relationship between a second source cell and a second target cell of a first sample base station in the sample base stations, and at least includes an overlapping coverage area coefficient and a layer number between the first sample base station and a second sample base station; the second target cell is a cell corresponding to the second sample base station in the communication network except the first sample base station, and the second sample base station is within a second preset layer number range of the first sample base station, and the layer number represents the association relationship of the geographical positions between the base stations;

[0122] S03, training a preset model according to the second feature data and the neighbor area configuration data corresponding to the sample base stations to obtain a neighbor area planning model.

[0123] The sample base stations are selected from the known base stations in the communication network. In some embodiments, the engineering parameters and the neighbor area configuration data of the sample base stations are obtained by data processing on the engineering parameters and the neighbor area configuration data of the known base stations in the communication network. The processing type of the data processing is not specially limited in the embodiments of the present disclosure, and can be redundant data removal, data validity verification, base station latitude and longitude processing, etc. The first sample base station is a base station corresponding to the second source cell, and the second sample base station is a base station corresponding to the second target cell.

[0124] The index data of the communication network includes at least one of a base station identifier ID, a base station name, a cell identifier ID, a cell name, and a base station TA index.

[0125] The neighboring cell configuration data includes at least one of a base station ID, a base station name, a cell ID, a cell name, a base station ID to which a neighboring cell belongs, a base station name to which the neighboring cell belongs, a neighboring cell ID, and a neighboring cell name.

[0126] The engineering parameters include at least one of a base station ID, a base station name, a base station longitude, a base station latitude, a cell ID, a cell name, and a cell azimuth angle.

[0127] It should be understood that the index data of the communication network, the neighboring cell configuration data, and the engineering parameters each include a base station ID, a base station name, a cell ID, and a cell name. These data can associate the index data of the communication network, the neighboring cell configuration data, and the engineering parameters corresponding to the same base station.

[0128] The present disclosure does not make special restrictions on the manner of obtaining the index data of the communication network, the neighboring cell configuration data, and the engineering parameters. In some embodiments, the index data of the communication network, the neighboring cell configuration data, and the engineering parameters are obtained by pulling from a wireless communication access network using an application programming interface provided by the wireless communication access network.

[0129] The second feature data corresponding to each sample base station is calculated according to the index data in the communication network and the engineering parameters of each sample base station, wherein the second feature data at least includes an overlapping coverage area coefficient and a number of layers between the first sample base station and the second sample base station. In some embodiments, the second feature data can further include at least one of a distance multiple, an angle coefficient, and an identifier corresponding to the second source cell and the second target cell. In the case where the second feature data is the distance multiple, the angle coefficient, the identifier corresponding to 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, which will not be described here to avoid repetition. In the case where the second feature data is the overlapping coverage area coefficient, since both the first sample base station and the second sample base station are known to have corresponding index data (the index data includes a base station TA index), the base station TA index can be used to calculate the coverage radius of the base station, so the base station TA index in the index data can be used to calculate the overlapping coverage area coefficient, thereby obtaining a more accurate overlapping coverage area coefficient. Thus, the second feature data is taken as an input value of the preset model, and the neighboring cells corresponding to each sample base station are taken as target values, and the preset model is trained to obtain a neighboring cell planning model.

[0130] In some embodiments, the engineering parameters and the neighboring cell configuration data of the sample base station are obtained by performing data processing on the engineering parameters and the neighboring cell configuration data of the known base stations in the communication network, which can include at least one of the following steps:

[0131] Redundant data removal: according to the engineering parameters of the known base station, determine the redundant base station in the known base station; remove the engineering parameters and the neighboring area configuration data of the redundant base station from the engineering parameters and the neighboring area configuration data of the known base station, to obtain the engineering parameters and the neighboring area configuration data of the sample base station.

[0132] The redundant data removal on the engineering parameters and the neighboring area configuration data of the known base station can avoid the existence of some problem base stations (such as the retired base station, the fault base station, and the long-time disconnected base station, etc.) in the known base station due to historical reasons. The problem base station may exist in the case of missing engineering parameters, neighboring area configuration data, and corresponding index data in the communication network. If the problem base station is not processed, it may cause the reduction of the accuracy of the model, the pollution of the model training data, and other problems. As a way of the embodiments of the present disclosure, the redundant data removal includes identifying and removing the problem base station with missing engineering parameters, missing indicators, or missing neighboring area configurations to prevent the problem base station from interfering with the analysis and processing of the model.

[0133] Data validity verification: validity verification is performed on the engineering parameters of the known base station, and the base station with a verification result that does not meet the standard is determined as an invalid base station; remove the engineering parameters and the neighboring area configuration data of the invalid base station from the engineering parameters and the neighboring area configuration data of the known base station, to obtain the engineering parameters and the neighboring area configuration data of the sample base station. In some embodiments, the base station that does not meet the standard refers to the existence of obvious data that does not conform to the common sense of the relevant data of the base station, for example, the cell azimuth angle of the known base station is greater than 360°, or the longitude value of the known base station is outside the range of [-180, 180], etc., effectively avoiding the interference on the model training.

[0134] Base station latitude and longitude processing: count and retain the latitude and longitude in the engineering parameters of the known base station, merge the base stations with the same processing results in the known base station, to obtain the engineering parameters and the neighboring area configuration data of the sample base station.

[0135] Processing the engineering parameters and neighboring cell configuration data of known base stations with base station longitude and latitude can avoid the situation where some cells belong to the same base station but have slightly different longitude and latitude values ​​due to historical reasons when constructing the base station triangulation network. For example, the longitude and latitude of service cell A are (113.7400193, 1.79156), and the longitude and latitude of service cell B are (113.7400194, 1.79156). Service cells A and B both belong to known base station A, but due to the slight difference in their longitude values, they may be mistakenly considered to be two service cells of different base stations during the hierarchical base station triangulation network construction process. This situation not only increases the computational complexity of subsequent feature calculations, but also affects the accuracy of the neighboring cell planning of the model after model training. Therefore, the longitude and latitude can be counted and retained, for example, retaining six decimal places. This can not only meet the accuracy requirements of neighboring area planning, but also ensure that when constructing the base station triangulation network, they will not be mistaken for different base stations due to slight differences in longitude and latitude values.

[0136] Figure 12 This is a flow chart of a specific implementation method of step S02 in the embodiment of the present disclosure. Figure 12 In some embodiments, S02 includes:

[0137] S021. Calculate the coverage area of ​​the second source cell;

[0138] S022. Calculate the second characteristic data according to the coverage area of ​​the second source cell and the coverage area of ​​the second target cell.

[0139] The coverage area of ​​a cell refers to the signal coverage range of the corresponding base station, that is, the geographical area in which the cell can provide communication services in the mobile network. The overlapping coverage area coefficient can be calculated based on the coverage area of ​​the second source cell and the coverage area of ​​the second target cell. The overlapping coverage area coefficient refers to the ratio between the area of ​​the overlapping portion between the second source cell and the second target cell and the coverage area of ​​the second source cell, that is:

[0140]

[0141] Compared with the cell planning scheme focusing on distance and included angle, the first sample base station and the second sample base station are divided into levels according to the engineering parameters of the base stations, and then the second feature data including at least the overlapping coverage area coefficient is calculated, more factors about the relationship between the base stations are introduced, so that the trained cell planning model can effectively solve the problems of cell missing, low planning accuracy and excessive cells, and the introduction of more factors for cell division can effectively improve the accuracy of the model in cell planning, and the model can better cope with different complex communication network environments.

[0142] Figure 13 A specific implementation method flowchart for step S021 in the embodiments of the present disclosure is shown in FIG. 2. Figure 13 In some embodiments, S021 includes:

[0143] S0211, determining a coverage radius of a second source cell according to index data of the communication network;

[0144] S0212, obtaining an angle of the second source cell and a second ratio corresponding to each of the angles; wherein the second ratio is a ratio of the coverage radius of the second source cell to a reference radius;

[0145] S0213, determining a coverage area of the second source cell according to the angle of the second source cell, the second ratio corresponding to each of the angles, and the coverage radius.

[0146] The coverage area of the second source cell can be calculated according to the angle of the second source cell, the second ratio corresponding to each of the angles, and the coverage radius, wherein 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 range radius of the cell in the ideal state, that is, the farthest distance covered by the signal of the base station without obstacles such as terrain and buildings.

[0147] In addition, the coverage range of the cell is not specially limited in the embodiments of the present disclosure. It should be understood that in actual operation, the coverage range of the cell corresponding to the base station is not necessarily a standard fan-shaped structure range, and the coverage graph of the cell can be drawn through simulation and other technical means.

[0148] After the coverage range of the second source cell is determined, the second ratio corresponding to each angle (the ratio is related to the coverage radius and the reference radius) and the coverage radius, the coverage area of the second source cell can be calculated.

[0149] In some embodiments, S0211 includes:

[0150] determining a proportion of the number of users corresponding to each base station tracking area (TA) index of the first sample base station;

[0151] Filtering the base station TA indicator that meets a preset percentage threshold from the user number percentage and determining it as the target base station TA indicator;

[0152] The coverage radius of the second source cell is determined according to the TA indicator of the target base station.

[0153] Among them, the proportion of the number of users corresponding to the TA indicators of each base station in the first sample base station can be obtained through the base station TA indicator in the indicator data corresponding to the communication network. The base station TA indicator counts the proportion of mobile devices of the base station operating in the area within a certain time range, that is, the proportion of the number of users. The proportion of the number of users can reflect the proportion of the number of users of mobile devices that communicate or transmit data through the base station in the area to the total number of users within the coverage area of ​​the base station. Therefore, setting a preset proportion threshold for the proportion of the number of users can filter out the area where most mobile device users are located, that is, filter out the target base station TA indicator, and thus calculate the coverage radius of the second source cell based on the target base station TA indicator.

[0154] In some embodiments, at least one base station TA indicator that is less than a preset proportion threshold is selected, and the largest radius value is selected from the coverage radius range corresponding to the at least one base station TA indicator as the coverage radius of the second source cell.

[0155] As one embodiment of the present disclosure, the base station TA indicator is shown in a table, as shown in Table 1:

[0156] Table 1

[0157] Start Day 2023 / 12 / 1 / End Day 2023 / 12 / 2 / Query Granularity 1 Day(s) Cumulative Percent TA (0-78.12) 3.19％ 3.19％ TA (78.12-234.36) 15.25％ 18.44％ TA (234.36-390.6) 21.44％ 39.88％ TA (390.6-546.84) 16.24％ 56.12％ TA (546.84-703.08) 10.47％ 66.59％ TA (703.08-859.32) 6.85％ 73.44％ TA (859.32-1015.56) 4.67％ 78.11％ TA (1015.56-1562.4) 9.07％ 87.18％ TA (1562.4-2109.24) 4.23％ 91.41％ TA (2109.24-2656.08) 2.27％ 93.68％ TA (2656.08-3124.8) 1.33％ 95.01％ TA (3124.8-3906) 1.35％ 96.36％ TA (3906-6327.72) 1.85％ 98.21％ TA (6327.72-10077.48) 1.02％ 99.23％ TA (10077.48-13983.48) 0.51％ 99.74％ TA (13983.48-19998.72) 0.26％ 100.00％ TA (19998.72-29998.08) 0.00％ 100.00％ TA (29998.08-39997.44) 0.00％ 100.00％ TA (39997.44-49996.8) 0.00％ 100.00％ TA (49996.8-60074.28) 0.00％ 100.00％ TA (60074.28-70073.64) 0.00％ 100.00％ TA (70073.64-80073) 0.00％ 100.00％ TA (80073-90072.36) 0.00％ 100.00％ TA (90072.36-100149.84) 0.00％ 100.00％

[0158] In the query granularity in Table 1, TA (0-78.12) indicates that the coverage radius is from 0 to 78.12. The number of mobile device users corresponding to TA (0-78.12) accounts for 3.19%, and the cumulative percentage is 3.19%;

[0159] TA(78.12-234.36) indicates that within the coverage radius from 78.12 to 234.36, the number of mobile device users corresponding to TA(78.12-234.36) accounts for 15.25%, and the cumulative percentage is 18.44%. The cumulative percentage is the sum of the number of users corresponding to TA(0-78.12) and the cumulative percentage corresponding to TA(78.12-234.36);

[0160] TA(234.36-390.6) indicates that within the coverage radius of 234.36 to 390.6, the user share of mobile devices corresponding to TA(234.36-390.6) accounts for 21.44%, and the cumulative percentage is 39.88%. The cumulative percentage is the sum of the user share corresponding to TA(234.36-390.6) and the cumulative percentage corresponding to TA(78.12-234.36). The user share and cumulative percentage of TAs corresponding to other query granularities are similar and are not repeated here.

[0161] Among them, the preset proportion threshold is set to 98%, and the maximum radius value (6327.72) in the coverage radius range corresponding to the base station TA indicator with a cumulative percentage greater than 98% (i.e., TA (3906-6327.72) in Table 1) is used as the coverage radius of the second source cell. The coverage radius of the first source cell corresponding to the first sample base station determined in this way is closer to the actual coverage radius.

[0162] In some embodiments, S03 includes:

[0163] The second characteristic data corresponding to each of the sample base stations is used as an input value, and the neighboring cells corresponding to each of the sample base stations is used as a target value, and the preset model is trained to obtain a neighboring cell planning model; wherein, the neighboring cells corresponding to the sample base stations are obtained from the neighboring cell configuration data of the sample base stations.

[0164] Among them, after performing feature operations on each sample base station, the second feature data corresponding to the sample base station is obtained. The number of sample base stations in the communication network can be multiple, so a feature data pair list is generated based on the second feature data corresponding to the multiple sample base stations, wherein each sample base station corresponds to a feature data in the feature data pair list, and the feature data at least includes the overlapping coverage area coefficient and the number of layers between the sample base station and the base stations within the second preset layer number range, and may also include: at least one of the distance multiple, the angle coefficient, and the identifier corresponding to the first source cell and the first target cell. The second feature data is used as the input value of the preset model, and the known neighboring cells of the sample base station are used as the target value for training.

[0165] In some embodiments, the training process may include at least one of data identification, feature column adjustment, training parameter adjustment, and accuracy adjustment.

[0166] The data identifier is obtained by comparing the adjacent cell corresponding to the sample base station with each cell in the communication network, judging whether the adjacent cell exists in the current communication network, if it exists, indicating that the adjacent cell divided by the sample base station is reasonable, and marking it as 1, if it does not exist, indicating that the adjacent cell divided by the sample base station is unreasonable, and marking it as 0. The unique identifier of the second source cell and the second target cell is generated; the redundant data is deleted, and the redundant data includes the base station ID, the base station name, the cell ID, the cell name, the latitude and longitude, the cell azimuth angle of the second source cell, and the related information of the target cell. The feature information column (i.e. input value) for training including the overlap coverage area coefficient, the distance multiple, the angle coefficient, the identifier corresponding to the first source cell and the first target cell, and the layer number is obtained.

[0167] Feature column adjustment: in the model training process, the order of the feature information column for training is adjusted to make the accuracy of the adjacent area planning result of the adjacent area planning model higher. In some embodiments, the order of the feature information in the feature information column that has a greater impact on the adjacent area planning result is earlier.

[0168] Training parameter adjustment: the preset model is trained, and the values of the training parameters such as the number of network layers, the activation function, and the Dropout rate in the preset model are adjusted after cross-validation to make the accuracy of the trained adjacent area planning model higher. The type of the preset model is not specially limited in the present disclosure, which can be a neural network model or other models. The embodiments of the present disclosure effectively improve the accuracy of adjacent area planning by means of the powerful learning ability of the neural network. At the same time, not only the new second feature data is entered, but also the adjacent area planning experience of the communication network can be learned in depth, so that the model is more flexible and can better cope with the evolving communication network environment.

[0169] By inputting the second feature data into the preset model for training, the training parameters are adjusted according to the accuracy of the trained adjacent area planning model, so that the model can produce good prediction effect on the data, and better adjacent area planning effect is obtained, and at the same time, the adaptation ability of the adjacent area planning model in different networks can be improved.

[0170] The first feature data in the embodiments of the present disclosure is used to describe 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 number range, and the first feature data at least includes the overlap coverage area coefficient and the layer number between the newly added base station and the base station within the first preset layer number range, which fully guarantees the accuracy of the adjacent area planning; at the same time, the adjacent area planning model learns the planning experience of each known base station in the communication network, and the first feature data is input into the adjacent area planning model, so that the adjacent area planning before the newly added base station is connected to the network can be realized based on the first feature data, and the timeliness of the adjacent area planning of the newly added base station is significantly improved.

[0171] In a second aspect, referring to Figure 14 The embodiment of the present disclosure provides a base station, comprising a memory and a processor; the memory stores a computer program which can be executed by the processor, and the computer program is executed by the processor to implement any one of the neighbor cell planning methods of the embodiment of the present disclosure.

[0172] In a third aspect, referring to Figure 15 The embodiment of the present disclosure provides a computer readable medium, which stores a computer program, and the computer program is executed by a processor to implement any one of the neighbor cell planning methods of the embodiment of the present disclosure.

[0173] In a fourth aspect, the embodiment of the present disclosure provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement any one of the neighbor cell planning methods of the embodiment of the present disclosure.

[0174] In one specific embodiment, the computer program product described above can be used to implement each step of the neighbor cell planning method described in the first aspect.

[0175] In order for those skilled in the art to more clearly understand the technical solutions provided by the embodiments of the present disclosure, the technical solutions provided by the embodiments of the present disclosure are described in detail below with specific embodiments:

[0176] Example 1:

[0177] For example, as a specific form of the embodiment of the present disclosure, referring to Figure 16 The neighbor cell planning system is used for neighbor cell planning of the newly added base station of the wireless communication access network, wherein the system comprises a data extraction module, a data processing module, a feature calculation module, a model training module, a neighbor cell planning module and a script making module.

[0178] The data extraction module is used for obtaining the index data of the communication network and the engineering parameters and the neighbor cell configuration data of the known base station from the wireless communication access network.

[0179] The data processing module is used for data cleaning of the index data of the communication network and the engineering parameters and the neighbor cell configuration data of the known base station obtained from the wireless communication access network, and the data cleaning process comprises redundant data removal, data validity verification, base station latitude and longitude processing. For the screened data, the data is sorted and summarized according to the cell level.

[0180] The feature calculation module is used for calculating feature data comprising at least an overlapping coverage area coefficient and a number of layers according to the index data of the communication network and the engineering parameters and the neighbor cell configuration data of the known base station, and performing normalization processing on the feature data, and the feature data comprises five feature information columns.

[0181] Reference Figure 17 The feature calculation process of the feature calculation module includes:

[0182] Step 1701, according to the latitude and longitude of each sample base station, a Delaunay base station triangulation network is established with each sample base station as a vertex.

[0183] Step 1702, traverse each cell in the wireless communication access network, and determine that the other base stations are the nth level of the first base station under the condition that the vertices corresponding to the other base stations and the vertex corresponding to the first base station are connected through at least n edges of a triangle. The service cells of the other base stations in the wireless communication access network with a layer number less than 3 or equal to 3 are determined as the first target cell, and a three-layer neighbor list is generated according to the second target cell.

[0184] Step 1703, according to the base station TA index data in the index data corresponding to the sample base station, the coverage radius is determined; according to the second ratio corresponding to the coverage radius and the coverage range angle, the coverage area of the sample base station and the second target cell is calculated. According to the coverage area of the sample base station and the second target cell, the overlapping coverage area coefficient is calculated.

[0185] The site distance between the sample base station and each second target cell is calculated.

[0186] According to the connecting line between the sample base station and each second target cell and the azimuth angle vector, the forward included angle and the backward included angle are calculated.

[0187] Step 1704, the overlapping coverage area coefficient, the site distance, the forward included angle and the backward included angle are subjected to data normalization processing to obtain the distance multiple, the layer number of the second target cell in the three-layer neighbor list, the overlapping coverage area coefficient, the forward included angle coefficient and the backward included angle coefficient. The distance multiple, the layer number of the second target cell in the three-layer neighbor list, the overlapping coverage area coefficient, the forward included angle coefficient and the backward included angle coefficient are the feature information column.

[0188] The model training module is used to adjust the position and sequence of the feature information column, the neural network parameter threshold and other factors, and debug the accuracy rate of the neighbor planning result of the neighbor planning model to be greater than the preset accuracy rate value.

[0189] Reference Figure 18 The model training process of the model training module includes:

[0190] Step 1801, collect the index data of the wireless communication access network and the engineering parameters and neighbor configuration data of the known base station.

[0191] Step 1802, the collected data is processed to obtain the processed communication network index data and the sample base station engineering parameters and the neighbor cell configuration data.

[0192] Step 1803, according to the communication network index data and the neighbor cell configuration data, the engineering parameters of the sample base station are processed to obtain second feature data, and the second feature data includes distance multiple, the layer number of the second target cell in the three-layer neighbor cell pair list, overlap coverage area coefficient, forward angle coefficient and backward angle coefficient.

[0193] Step 1804, the second feature data is taken as an input value, and the neighbor cell corresponding to the sample base station is taken as a target value to train the preset model to obtain a neighbor cell planning model. When the model accuracy of the trained neighbor cell planning model meets the expected value, the training is completed. Referring to Figure 19 , the accuracy of data training is measured by loss and accuracy.

[0194] Step 1805, the neighbor cell planning model can be used for neighbor cell planning of the newly added base station in the wireless communication access network.

[0195] The neighbor cell planning module is used for neighbor cell planning of the newly added base station after feature calculation, and the trained neighbor cell planning model is used for neighbor cell planning of the newly added base station to obtain a neighbor cell planning result.

[0196] Referring to Figure 20 , the neighbor cell planning method includes:

[0197] 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 angle, etc.

[0198] Step 2002, the engineering parameters of the newly added base station are processed to obtain first feature data.

[0199] Step 2003, the first feature data is input into the trained neighbor cell planning model to obtain a neighbor cell planning result.

[0200] The script making module is used for generating a neighbor cell script that can be imported into the existing network according to the neighbor cell planning result, and synchronizing the neighbor cell script to the wireless communication access network.

[0201] Example 2:

[0202] For example, as a specific form of an embodiment of the present disclosure, referring to Figure 21 , the neighbor cell planning method includes:

[0203] Step 2121: Obtain indicator data of the wireless communication access network and engineering parameters and neighboring cell configuration data of known base stations.

[0204] Step 2122 uses the wireless communication access network's indicator data, known base station engineering parameters, and neighboring cell configuration data to calculate second characteristic data. This second characteristic data includes a distance coefficient, a relative angle (i.e., an angle coefficient), an overlapping coverage area coefficient, and a number of layers. This second characteristic data reflects the spatial relationship and coverage between the newly added base station and base stations within the second preset number of layers, providing a basis for training the neighboring cell planning model.

[0205] In step 2123, a preset model of a machine learning method based on a neural network is used to train the second feature data to obtain an intelligent preset neighborhood planning model. The model fully learns the neighboring cell configuration experience of known base stations in the existing network (i.e., the communication network), has strong adaptability, and can understand and utilize the complex relationship between the second feature data and neighborhood planning.

[0206] Step 2124: When a new base station is added, obtain the engineering parameters of the new base station.

[0207] Step 2125: Calculate first feature data of the newly added base station based on engineering parameters of the newly added base station, and input the first feature data into the trained neighborhood planning model.

[0208] Step 2126: Obtain the neighboring cell planning results through the neighboring cell planning model to ensure that the neighboring cell configuration of the newly built base station meets the optimal requirements of the communication network.

[0209] Among them, reference Figure 22 , the model training process in step 2123 is:

[0210] Step 2201 compares the calculated second feature data with the neighboring cell configuration data in the communication network to determine whether the neighboring cell planning of the known base station is reasonable, thereby identifying the data. A unique index is established between the sample base station and its neighboring cell, and redundant data is deleted.

[0211] Step 2202: Adjust the feature columns to place the feature information columns that have a greater impact on the neighborhood planning results at the top. Cross-validate and adjust the values ​​of parameters such as the number of network layers, activation function, and dropout rate in the preset model.

[0212] Step 2203: train the model.

[0213] Step 2204, compare the accuracy of the adjacent area planning of the trained model with the preset accuracy value, in the case of accuracy, the training is completed, in the case of accuracy, adjust the parameters and retrain the model.

[0214] The processor is a device with data processing capability, including but not limited to a central processing unit (CPU) and the like; the memory is a device with data storage capability, including but not limited to a random access memory (RAM, more specifically SDRAM, DDR, etc.), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory (FLASH); the I / O interface (read-write interface) is connected between the processor and the memory, and can realize information interaction between the memory and the processor, including but not limited to a data bus (Bus) and the like.

[0215] Those skilled in the art can understand that all or some of the functional modules / units in the above disclosed steps, systems and devices can be implemented as software, firmware, hardware and appropriate combinations thereof.

[0216] In the hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be executed by several physical components in cooperation.

[0217] Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit (CPU), a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As is well 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 technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is 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 magnetic disk storage; compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disk storage; magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage; any other medium that can be used to store desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media generally includes computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0218] The present disclosure has disclosed example embodiments, and while specific terminology has been employed, such should not be taken in a limiting sense, but rather should be understood to be in a generic sense, unless otherwise indicated. In some instances, it will be apparent to those skilled in the art that features, characteristics or / and elements described in connection with a particular embodiment can be used in conjunction with other embodiments unless otherwise explicitly stated. As such, those skilled in the art will appreciate that various changes can be made in form and detail without departing from the scope of the disclosure as set forth in the appended claims.

Claims

1. A neighborhood planning method, comprising: First characteristic data is calculated based on engineering parameters of the first base station; wherein the first characteristic data is used to describe a spatial characteristic relationship between a first source cell of the first base station and a first target cell, including at least an overlapping coverage area coefficient and a number of floors between the first base station and a second base station; the first target cell is a cell corresponding to the second base station other than the first base station in the communication network, and the second base station is within a first preset number of floors of the first base station, where the number of floors represents an association relationship between geographical locations of the base stations; Determine a neighboring cell planning result corresponding to the first base station based on the first feature data and a preset neighboring cell planning model.

2. The method of claim 1, wherein, The calculating and obtaining the first characteristic data according to the engineering parameters of the first base station includes: calculating the coverage area of ​​the first source cell; The first characteristic 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 of claim 2, wherein, The calculating the coverage area of ​​the first source cell includes: determining a coverage radius of the first source cell; Obtaining an angle of the first source cell and a first ratio corresponding to each of the angles; wherein the first ratio is a ratio of a coverage radius of the first source cell to a reference radius; The coverage area of ​​the first source cell is determined according to the angle of the first source cell, the first ratio corresponding to each of the angles, and the coverage radius.

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

5. The method of claim 1, wherein, The determining, based on the first feature data and a preset neighboring cell planning model, a neighboring cell planning result corresponding to the first base station includes: Inputting the overlapping coverage area coefficient and the number of layers between the first base station and the second base station into the preset neighborhood planning model; The preset neighboring cell planning model is used to determine a target neighboring cell from the first target cell of the second base station to obtain a neighboring cell planning result corresponding to the first base station.

6. The method according to any one of claims 1 to 5, wherein, After determining the neighboring cell planning result corresponding to the first base station based on the first feature data and a preset neighboring cell planning model, the method further includes: The neighboring cell configuration data corresponding to the neighboring cell planning result is updated to the neighboring 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 characteristic data further includes at least one of the following: Distance multiples; Angle coefficient; The identifiers corresponding to the first source cell and the first target cell.

8. The method of claim 1, wherein, The method further comprises: Obtaining indicator data of the communication network and engineering parameters and neighboring cell configuration data of a sample base station; the sample base station is a known base station in the communication network; Second feature data corresponding to each of the sample base stations is calculated according to the index data and engineering parameters of each of the sample base stations; wherein the second feature data is used to describe a spatial feature relationship between a second source cell of a first sample base station and a second target cell, and at least includes an overlapping coverage area coefficient and a layer number between the first sample base station and a second sample base station; the second target cell is a cell corresponding to the second sample base station in the communication network except for the first sample base station, and the second sample base station is within a second preset layer number range of the first sample base station, and the layer number represents a geographical position correlation relationship between base stations; A preset model is trained according to the second feature data corresponding to the sample base station and the adjacent cell configuration data, to obtain an adjacent cell planning model.

9. The method of claim 8, wherein, The second feature data corresponding to each of the sample base stations is calculated according to the index data and engineering parameters of each of the sample base stations, and includes: A coverage area of the second source cell is calculated; The second feature data is calculated according to the coverage area of the second source cell and a coverage area of the second target cell.

10. The method of claim 9, wherein, The coverage area of the second source cell is calculated, and includes: A coverage radius of the second source cell is determined according to index data of the communication network; An angle of the second source cell and a second ratio corresponding to each of the angles are obtained; wherein the second ratio is a ratio of the coverage radius of the second source cell to a reference radius; A coverage area of the second source cell is determined according to the angle of the second source cell, the second ratio corresponding to each of the angles and the coverage radius.

11. The method of claim 10, wherein, The coverage radius of the second source cell is determined according to the index data of the communication network, and includes: A user number proportion of the first sample base station corresponding to each base station tracking area (TA) index is determined; A base station TA index meeting a preset proportion threshold is filtered from the user number proportion, and is determined as a target base station TA index; The coverage radius of the second source cell is determined according to the target base station TA index.

12. The method of claim 8, wherein, The preset model is trained according to the second feature data corresponding to the sample base station and the adjacent cell configuration data, to obtain the adjacent cell planning model, and includes: The second feature data corresponding to each of the sample base stations is taken as an input value, and adjacent cells corresponding to each of the sample base stations are taken as target values, to train the preset model, to obtain the adjacent cell planning model; wherein the adjacent cells corresponding to the sample base stations are obtained from adjacent cell configuration data of the sample base stations.

13. A base station, comprising a memory and a processor; the memory stores a computer program capable of being executed by the processor, and the computer program is executed by the processor to implement the adjacent cell planning method in any one of claims 1 to 12.

14. A computer readable medium, which stores a computer program and the computer program is executed by a processor to implement the adjacent cell planning method in any one of claims 1 to 12.

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

Images