Mobile communication base station site selection auxiliary method and device

Abstract

The invention discloses a mobile communication base station site selection auxiliary method and device, and the method comprises the steps: building a three-dimensional model of a target region based on a neural radiation field modeling mode, determining a plurality of base station candidate positions based on the three-dimensional model, and carrying out the location selection of a plurality of base stations. And then simulating the light projection condition of each candidate position point and the signal quality estimated according to the projection condition through a three-dimensional model based on a neural radiation field and a voxel rendering processing mode, and determining the target site selection based on the signal quality of each point, thereby achieving the purpose of optimizing the site selection task of the mobile communication base station.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a method and device for assisting in the location selection of mobile communication base stations. Background Art

[0002] With the increasing maturity and popularization of 5G technology, people's current lives are inseparable from mobile communication. However, the coverage area of 5G base stations is relatively small. For areas with a large population, a large number of base stations need to be built. The location selection of these newly built base stations, especially for urban areas with complex terrain, needs to consider the influence of various buildings, terrain and other factors. The traditional base station location selection method relies on 3D maps, and the acquisition of 3D maps mainly comes from data of the Surveying and Mapping Bureau. However, the data of the Surveying and Mapping Bureau is updated slowly, and more of it is mainly planar data, lacking real-time 3D data, especially the 3D data of various buildings. Even if there is a 3D map, it is only the simple appearance size, thus affecting the accuracy of wireless signal evaluation and resulting in the technical problem of unstable base station location selection effects obtained by this method. Summary of the Invention

[0003] This application provides a method and device for assisting in the location selection of mobile communication base stations, which are used to achieve the invention purpose of optimizing the mobile communication base station location selection task.

[0004] To achieve the above invention purpose, the first aspect of this application provides a method for assisting in the location selection of mobile communication base stations, including:

[0005] Obtain a geographical environment image of a target area, and based on the geographical environment image, construct a 3D model of the target area through the neural radiance field modeling method;

[0006] Based on the 3D model, determine a number of base station candidate locations in the 3D model;

[0007] Determine the wireless signal quality evaluation data emitted from the base station candidate locations through the voxel rendering processing method;

[0008] Determine the target location selection of the mobile communication base station according to the wireless signal quality evaluation data.

[0009] Preferably, the step of determining a number of base station candidate locations in the 3D model based on the 3D model specifically includes:

[0010] Based on the 3D model, randomly determine a number of base station candidate locations in the 3D model.

[0011] Preferably, the step of determining the wireless signal quality evaluation data emitted from the base station candidate locations through the voxel rendering processing method specifically includes:

[0012] Generate a number of rays with the candidate base station location as the origin according to the candidate base station location;

[0013] Divide the rays into a number of ray segments according to the voxel sampling method, and query each ray segment with the voxel grid to obtain the attenuation coefficient corresponding to the space of each ray segment;

[0014] Calculate the cumulative attenuation of the candidate base station location according to a preset cumulative attenuation calculation formula, and use the cumulative attenuation as the radio signal quality evaluation data sent by the candidate base station location.

[0015] Preferably, the cumulative attenuation calculation formula is specifically:

[0016]

[0017] In the formula, is the cumulative attenuation, is the set transmit power of the mobile communication base station, L is the ray length, is the attenuation coefficient corresponding to each position x on the ray path.

[0018] Preferably, determining the target location of the mobile communication base station according to the radio signal quality evaluation data specifically includes:

[0019] According to a preset neural network model, use the radio signal quality evaluation data of each candidate base station location as the model input, and use the target cost function in the neural network model to optimize the data, so as to determine the optimal target location of the mobile communication base station according to the result of the model optimization.

[0020] Meanwhile, a second aspect of the present application provides an auxiliary device for mobile communication base station location selection, including:

[0021] A three-dimensional model construction unit, configured to obtain a geographical environment image of a target area, and construct a three-dimensional model of the target area by means of neural radiance field modeling according to the geographical environment image;

[0022] A candidate location determination unit, configured to determine a number of candidate base station locations in the three-dimensional model based on the three-dimensional model;

[0023] A signal quality evaluation unit, configured to determine radio signal quality evaluation data sent from the candidate base station location by means of voxel rendering processing;

[0024] A target location determination unit, configured to determine the target location of the mobile communication base station according to the radio signal quality evaluation data.

[0025] Preferably, the candidate location determination unit is specifically configured to:

[0026] Based on the three-dimensional model, a number of base station candidate locations are randomly determined in the three-dimensional model.

[0027] Preferably, the signal quality evaluation unit is specifically configured to:

[0028] According to the base station candidate locations, a number of rays with the base station candidate locations as the sources are generated;

[0029] According to the voxel sampling method, the rays are divided into several ray segments, and each ray segment is queried with the voxel grid to obtain the attenuation coefficient corresponding to the space of each ray segment;

[0030] According to a preset cumulative attenuation calculation formula, the cumulative attenuation amount of the base station candidate location is calculated, and the cumulative attenuation amount is used as the radio signal quality evaluation data emitted by the base station candidate location.

[0031] Preferably, the specific form of the cumulative attenuation calculation formula is:

[0032]

[0033] In the formula, is the cumulative attenuation amount, is the set transmit power of the mobile communication base station, L is the ray length, is the attenuation coefficient corresponding to each position x on the ray path.

[0034] Preferably, the target site selection determination unit is specifically configured to:

[0035] According to a preset neural network model, the radio signal quality evaluation data of each base station candidate location is used as the model input, and the target cost function in the neural network model is used for data optimization, so as to determine the target site selection of the optimal mobile communication base station according to the result of model optimization.

[0036] From the above technical solutions, it can be seen that the embodiments of the present application have the following advantages:

[0037] The solution provided by the present application constructs a three-dimensional model of the target area based on the neural radiance field modeling method. Then, based on this three-dimensional model, a number of base station candidate locations are determined. Next, the light projection situation of each candidate location point is simulated through the three-dimensional model based on the neural radiance field and the voxel rendering processing method, as well as the signal quality estimated from the projection situation. And based on the signal quality of each point, the target site selection is determined, so as to achieve the invention purpose of optimizing the mobile communication base station site selection task. Description of the Drawings

[0038] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0039] Figure 1 It is a schematic flowchart of an embodiment of a method for assisting in the site selection of a mobile communication base station provided by the present application.

[0040] Figure 2 It is a detailed flowchart of step 103 in an embodiment of a method for assisting in the site selection of a mobile communication base station provided by the present application.

[0041] Figure 3 It is a schematic overall flowchart of an embodiment of a method for assisting in the site selection of a mobile communication base station provided by the present application.

[0042] Figure 4 It is a schematic structural diagram of an embodiment of a device for assisting in the site selection of a mobile communication base station provided by the present application. Specific embodiments

[0043] The embodiments of the present application provide a method and a device for assisting in the site selection of a mobile communication base station, which are used to achieve the invention purpose of optimizing the site selection task of a mobile communication base station.

[0044] In order to make the invention purpose, features, and advantages of the present application more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the embodiments described below are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0045] First, a detailed description of an embodiment of a method for assisting in the site selection of a mobile communication base station provided by the present application is as follows:

[0046] Please refer to Figures 1 to 3 , a method for assisting in the site selection of a mobile communication base station provided by an embodiment of the present application includes:

[0047] Step 101, obtain a geographical environment image of the target area, and construct a three-dimensional model of the target area by means of neural radiance field modeling according to the geographical environment image;

[0048] It should be noted that first, a target area for a new mobile communication base station is modeled. The implementation method of the modeling is to obtain a geographical environment image of the target area. The geographical environment image can specifically be obtained by using a drone to take videos of the area. Then, based on these geographical environment images, a three-dimensional model of the target area is constructed through the neural radiance field modeling method.

[0049] Step 102: Based on the three-dimensional model, determine several base station candidate positions in the three-dimensional model;

[0050] It should be noted that based on the three-dimensional model constructed in Step 101, several base station candidate positions are determined in the three-dimensional model.

[0051] Step 103: Determine the radio signal quality evaluation data emitted from the base station candidate positions through the voxel rendering processing method;

[0052] It should be noted that in the neural radiance field three-dimensional model, simulation sampling of each base station candidate position is performed. The implementation method is to perform voxel rendering, and based on the result of the voxel rendering, the arrival situation of the light emitted from the base station position is calculated, and its radio signal quality is estimated.

[0053] More specifically, as Figure 2 shown, Step 103 in this embodiment specifically includes the following steps:

[0054] Step 1031: Generate several rays with the base station candidate positions as the sources according to the base station candidate positions;

[0055] Step 1032: Divide the rays into several ray segments according to the voxel sampling method, and query each ray segment with the voxel grid to obtain the attenuation coefficient corresponding to the space of each ray segment;

[0056] Step 1033: Calculate the cumulative attenuation amount of the base station candidate position according to the preset cumulative attenuation calculation formula, and use the cumulative attenuation amount as the radio signal quality evaluation data emitted from the base station candidate position.

[0057] It should be noted that in the voxel rendering of the neural radiance field, the density and color are integrated along the light rays to obtain the pixel color. However, in the radio signal quality evaluation scenario, this embodiment pays more attention to the attenuation of "waves" (rather than visible light) in space due to occlusion, scattering, reflection, etc. The "density" in the neural radiance field can be extended to understand as the attenuation coefficient related to the attenuation of radio frequency signals, so as to simulate the propagation of waves during the ray tracing process. When evaluating the coverage of a certain base station position in the environment, the signal "emitted" from the base station can be regarded as beams of rays (similar to the light rays in the rendering). Sampling and tracing these rays in the three-dimensional scene, the key steps include:

[0058] 1. Determine the emission source: i.e., the candidate base station location (emission point);

[0059] 2. Define the ray direction: The space can be sampled uniformly, or rays of the arrival path can be defined for target locations of interest (such as user locations);

[0060] 3. Sample along the ray in a 3D scene: Similar to the voxel sampling of neural radiance fields, divide a ray into several segments, and query each segment with a neural network (or voxel grid) to obtain the density or attenuation coefficient corresponding to the space of that segment.

[0061] 4. Cumulative attenuation: Integrate or multiply the attenuation factors along the ray to calculate the cumulative attenuation of the signal on this ray. The total cumulative attenuation of this emission source point can be used as the wireless signal quality evaluation data for this point.

[0062] More specifically, the cumulative attenuation calculation formula is specifically as follows:

[0063]

[0064] In the formula, is the cumulative attenuation, is the set transmission power of the mobile communication base station, L is the ray length, is the attenuation coefficient corresponding to each position x on the ray path, which can be extended from the density σ in the neural radiance field.

[0065] Step 104: Determine the target location of the mobile communication base station according to the wireless signal quality evaluation data.

[0066] It should be noted that finally, according to the wireless signal quality of each point obtained through Step 103, the target location of the mobile communication base station is determined. Specifically, the signal quality evaluation data of all locations obtained from the above Step 103 can be used as input to create a multi-layer convolutional neural network, and the target cost function is set to the mean square error to ensure that the signal quality of each location is relatively average. The mathematical formula is as follows:

[0067]

[0068] In the formula, n is the total number of input samples, is the true value of the i-th input sample, is the predicted value of the i-th input sample. By observing the change trend of the MSE value, when it has not changed significantly for a long time, the most recent address can be selected as the final location of the base station to exit the processing flow; otherwise, use the method of stochastic gradient descent to modify the location of the current base station location and return to Step 103 for calculation.

[0069] Among them, the mathematical formula of its stochastic gradient descent is as follows:

[0070]

[0071] In the formula, is the model parameter vector, t is the current iteration period, is the learning rate, which is used to determine the step size of each update, is for the i-th sample ( ), is the gradient of the loss function J with respect to the parameter .

[0072] The above is a detailed description of an embodiment of a mobile communication base station site selection assistance method provided by this application. Next is a detailed description of an embodiment of a mobile communication base station site selection assistance device provided by this application.

[0073] Please refer to Figure 4 , a mobile communication base station site selection assistance device provided by an embodiment of this application includes:

[0074] A three-dimensional model construction unit 201, configured to obtain a geographical environment image of a target area, and construct a three-dimensional model of the target area through a neural radiance field modeling method according to the geographical environment image;

[0075] A candidate location determination unit 202, configured to determine a plurality of base station candidate locations in the three-dimensional model based on the three-dimensional model;

[0076] A signal quality evaluation unit 203, configured to determine wireless signal quality evaluation data emitted from the base station candidate locations through a voxel rendering processing method;

[0077] A target site selection determination unit 204, configured to determine the target site selection of the mobile communication base station according to the wireless signal quality evaluation data.

[0078] Further, the candidate location determination unit 202 is specifically configured to:

[0079] Randomly determine a plurality of base station candidate locations in the three-dimensional model based on the three-dimensional model.

[0080] Further, the signal quality evaluation unit 203 is specifically configured to:

[0081] According to each base station candidate location, combine preset ray generation configuration information to generate a plurality of rays with the base station candidate location as the source;

[0082] According to each ray, perform segmentation processing on the ray to determine the attenuation coefficient of each ray segment;

[0083] According to a preset cumulative attenuation calculation formula, calculate the cumulative attenuation of the candidate base station locations, and use the cumulative attenuation as the radio signal quality evaluation data sent by the candidate base station locations.

[0084] Further, the cumulative attenuation calculation formula is specifically:

[0085]

[0086] In the formula, is the cumulative attenuation, is the set transmission power of the mobile communication base station, L is the ray length, is the attenuation coefficient corresponding to each position x on the ray path.

[0087] Further, the target site selection determination unit 204 is specifically configured to:

[0088] According to a preset neural network model, use the radio signal quality evaluation data of each candidate base station location as the model input, and use the target cost function in the neural network model to optimize the data, so as to determine the target site selection of the optimal mobile communication base station according to the result of the model optimization.

[0089] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0090] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in an electrical, mechanical or other form.

[0091] In the description of the present application and the above-mentioned accompanying drawings, terms such as "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present application described herein, for example, can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0092] It should be understood that in the present application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0095] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0096] As described above, the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present application.

Claims

1. A method for assisting site selection of a mobile communication base station, characterized in that: include: Acquire a geographical environment image of a target area, and construct a three-dimensional model of the target area by neural radiation field modeling according to the geographical environment image; Based on the three-dimensional model, determining a plurality of candidate base station locations in the three-dimensional model; Determining wireless signal quality assessment data emitted from the candidate base station location by voxel rendering processing; The target site selection of the mobile communication base station is determined according to the wireless signal quality evaluation data.

2. A mobile communication base station site selection assistance method according to claim 1, characterized in that: The determining of a plurality of candidate base station positions in the three-dimensional model based on the three-dimensional model specifically includes: Based on the three-dimensional model, a number of base station candidate positions are randomly determined in the three-dimensional model.

3. A method for assisting site selection of a mobile communication base station according to claim 1, characterized in that: The step of determining the wireless signal quality assessment data emitted from the candidate base station position by voxel rendering processing specifically includes: According to the candidate base station position, generating a plurality of rays with the candidate base station position as a source; According to the voxel sampling method, the ray is divided into a number of ray segments, and each ray segment is queried with the voxel grid to obtain the attenuation coefficient corresponding to each ray segment space; The cumulative attenuation of the candidate base station position is calculated according to a preset cumulative attenuation calculation formula, and the cumulative attenuation is used as the quality evaluation data of the wireless signal sent by the candidate base station position.

4. A method for assisting site selection of a mobile communication base station according to claim 3, characterized in that: The cumulative attenuation calculation formula is specifically: In the formula, is the cumulative attenuation, is the set transmission power of the mobile communication base station, L is the ray length, is the attenuation coefficient corresponding to each position x on the ray path.

5. A mobile communication base station site selection assistance method according to claim 1, characterized in that: Determining the target site selection of the mobile communication base station according to the wireless signal quality evaluation data specifically includes: According to the preset neural network model, the wireless signal quality evaluation data of each base station candidate location is used as the model input, and the target cost function in the neural network model is used to perform data optimization to determine the optimal target location of the mobile communication base station based on the result of model optimization.

6. A mobile communication base station site selection auxiliary device, characterized in that: include: A three-dimensional model construction unit, used to obtain a geographical environment image of a target area, and construct a three-dimensional model of the target area according to the geographical environment image by a neural radiation field modeling method; a candidate position determination unit, configured to determine a plurality of base station candidate positions in the three-dimensional model based on the three-dimensional model; A signal quality evaluation unit, configured to determine wireless signal quality evaluation data emitted from the candidate base station position by voxel rendering processing; The target site determination unit is used to determine the target site of the mobile communication base station according to the wireless signal quality evaluation data.

7. A mobile communication base station site selection auxiliary device according to claim 6, characterized in that: The candidate position determination unit is specifically used for: Based on the three-dimensional model, a number of base station candidate positions are randomly determined in the three-dimensional model.

8. A mobile communication base station site selection auxiliary device according to claim 6, characterized in that: The signal quality evaluation unit is specifically used for: According to the candidate base station position, generating a plurality of rays with the candidate base station position as a source; According to the voxel sampling method, the ray is divided into a number of ray segments, and each ray segment is queried with the voxel grid to obtain the attenuation coefficient corresponding to each ray segment space; The cumulative attenuation of the candidate base station position is calculated according to a preset cumulative attenuation calculation formula, and the cumulative attenuation is used as the quality evaluation data of the wireless signal sent by the candidate base station position.

9. A mobile communication base station site selection auxiliary device according to claim 8, characterized in that: The cumulative attenuation calculation formula is specifically: In the formula, is the cumulative attenuation, is the set transmission power of the mobile communication base station, L is the ray length, is the attenuation coefficient corresponding to each position x on the ray path.

10. The mobile communication base station site selection auxiliary device according to claim 6, characterized in that: The target site determination unit is specifically used for: According to the preset neural network model, the wireless signal quality evaluation data of each base station candidate location is used as the model input, and the target cost function in the neural network model is used to perform data optimization to determine the optimal target location of the mobile communication base station based on the result of model optimization.

Images