Modeling method and system for urban environment

Abstract

The invention discloses an urban area environment modeling method and system. The method comprises the following steps: acquiring a Fresnel area according to latitude and longitude coordinates of a preset area; extracting environmental parameters influencing radio wave propagation in the Fresnel area according to a radio wave propagation theory; obtaining potential variables in the Fresnel area according to a preset algorithm; inputting the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result; through the method, precise prediction of a point-to-point large-scale channel in a dense urban area environment is realized, and an output prediction result can be applied to urban network planning and optimization; the system also has the same beneficial effects.

Description

Technical Field

[0001] The present application relates to the technical field of wireless channel detection modeling, and in particular to a modeling method and system for an urban environment. Background Art

[0002] With the development of the fifth generation mobile network (5G), wireless communication systems are increasingly used in government affairs and public safety. Channel propagation models are indispensable for the intelligent planning and efficient management of any wireless communication system. Some traditional channel propagation models are based on parameter fitting based on a large amount of measured data to obtain empirical formulas suitable for specific scenarios; however, these models are simple in form, but in actual application, the calculated results are often quite different from the actual results. With the provision of more and more wireless services with high performance requirements, the demand for new propagation models has become more urgent.

[0003] In view of this, providing an accurate and efficient urban environment modeling method and system is a technical problem that needs to be solved urgently by technical personnel in this field. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a modeling method and system for urban environments, which can realize the accurate prediction of point-to-point large-scale channels in dense urban environments. The output prediction results can be applied to urban network planning and optimization.

[0005] The first object of the present invention is to provide a modeling method for an urban environment; The technical solution provided by the present invention is as follows: A modeling method for an urban environment comprises the following steps: Get the Fresnel zone area according to the latitude and longitude coordinates of the preset area; Extracting environmental parameters that affect radio wave propagation in the Fresnel zone according to radio wave propagation theory; Acquire potential variables within the Fresnel zone according to a preset algorithm; The environmental parameters and the potential variables are input into a preset prediction model to obtain a path loss prediction result.

[0006] Preferably, the acquiring of the Fresnel zone area according to the latitude and longitude coordinates of a preset area specifically includes: According to the latitude and longitude coordinates of the preset area, a Fresnel zone area with the position of the transmitting and receiving antenna as the focus and the straight line path as the axis is intercepted.

[0007] Preferably, extracting the environmental parameters affecting radio wave propagation in the Fresnel zone according to radio wave propagation theory specifically includes: The average building height, building density and vegetation density that affect radio wave propagation in the Fresnel zone are calculated based on radio wave propagation theory.

[0008] Preferably, the obtaining of potential variables in the Fresnel zone according to a preset algorithm specifically includes: The latent variables in the Fresnel zone are obtained according to the improved β-VAE algorithm.

[0009] Preferably, the step of inputting the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result specifically includes: The environmental parameters are fused with the potential variables and then input into a preset prediction model to obtain a path loss prediction result.

[0010] Preferably, the preset prediction model specifically includes: The preset prediction model is composed of SVR algorithm, AdaBoost iterative algorithm, classification regression algorithm and random forest regression algorithm.

[0011] A second object of the present invention is to provide a modeling system for an urban environment; The technical solution provided by the present invention is as follows: A modeling system for an urban environment, comprising: a first acquisition module, an extraction module, a second acquisition module and a third acquisition module; The first acquisition module is used to acquire the Fresnel zone area according to the latitude and longitude coordinates of a preset area; The extraction module is used to extract environmental parameters that affect radio wave propagation in the Fresnel zone according to radio wave propagation theory; The second acquisition module is used to acquire potential variables in the Fresnel zone according to a preset algorithm; The third acquisition module is used to input the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result.

[0012] The third object of the present invention is to provide an electronic device; The technical solution provided by the present invention is as follows: An electronic device, comprising: at least one processor; and A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor so that the at least one processor can perform any one of the method steps described in a method for modeling an urban environment.

[0013] A fourth object of the present invention is to provide a computer readable storage medium; The technical solution provided by the present invention is as follows: A computer-readable storage medium is used to store a computer program, wherein the computer program is used to enable a computer to execute any one of the method steps described in a method for modeling an urban environment.

[0014] The present invention provides a modeling method for an urban environment, comprising: obtaining a Fresnel zone area according to the latitude and longitude coordinates of a preset area; extracting environmental parameters that affect radio wave propagation in the Fresnel zone area according to radio wave propagation theory; obtaining potential variables in the Fresnel zone area according to a preset algorithm; inputting the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result; the method realizes accurate prediction of point-to-point large-scale channels in a dense urban environment, and the output prediction results can be applied to urban network planning and optimization.

[0015] The present invention also provides a modeling system for an urban environment. Since the system and the modeling method for an urban environment solve the same technical problems and belong to the same technical concept, they should have the same beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of a flow chart of a modeling method for an urban environment in an embodiment of the present invention; Figure 2 A schematic diagram of a Fresnel zone captured in an embodiment of the present invention; Figure 3 A schematic diagram showing a comparison of prediction performances of different machine learning models in an embodiment of the present invention; Figure 4 A schematic diagram showing a comparison of the prediction performance between the machine learning model and the traditional model in an embodiment of the present invention; Figure 5 It is a schematic diagram for comparing the true value and various prediction models for a region in an embodiment of the present invention; Figure 6 A schematic diagram of the structure of a modeling system for an urban environment in an embodiment of the present invention; Figure 7 A schematic structural diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] It should be noted that when an element is referred to as being "fixed on" or "set on" another element, it can be directly on the other element or indirectly set on the other element; when an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0020] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "multiple" and "several" mean two or more, unless otherwise clearly and specifically defined.

[0022] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which this application can be implemented. Therefore, they have no substantive technical significance. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in this application without affecting the effects and purposes that can be achieved by this application.

[0023] like Figure 1 As shown, an embodiment of the present invention provides a modeling method for an urban environment, comprising the following steps: S1. Obtain the Fresnel zone area according to the latitude and longitude coordinates of the preset area; S2. Extracting environmental parameters that affect wave propagation in the Fresnel zone according to the wave propagation theory; S3. Obtaining potential variables within the Fresnel zone according to a preset algorithm; S4. Inputting the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result.

[0024] In step S1 to step S2, the Fresnel zone is intercepted on the DEM according to the longitude and latitude coordinates of the two points, and then the environmental parameters affecting the propagation of radio waves are extracted according to the radio wave propagation theory, such as the building density, the average building height, the vegetation density, the propagation distance, the height of the transceiver and other parameters, and then the entire Fresnel zone area is used as the input parameter, and the preset algorithm is used to obtain the potential variables of the propagation environment; finally, the extracted environmental parameters and potential variables are input into the preset prediction model to obtain the path loss prediction result; compared with the existing SISO detection system that obtains channel data by clustering, this method realizes the accurate prediction of point-to-point large-scale channels in dense urban environments, and the prediction results can be applied to urban network planning and optimization.

[0025] Preferably, the acquiring of the Fresnel zone area according to the latitude and longitude coordinates of a preset area specifically includes: According to the latitude and longitude coordinates of the preset area, a Fresnel zone area with the position of the transmitting and receiving antenna as the focus and the straight line path as the axis is intercepted.

[0026] In actual application, Figure 2 As shown, the Fresnel zone is between the transmitting and receiving antennas, and the difference between the straight path and the broken path of the radio wave is The Fresnel zone is formed by the reflection point; the Fresnel zone is an ellipse with the position of the transmitting and receiving antennas as the focus and the straight path as the axis. Here n represents the nth Fresnel zone, where the area with n=1 is the area that makes the main contribution to the signal, called the first Fresnel zone, also known as the effective zone; the two foci of the ellipse are the transmitting end T and the receiving end R, the distance is d, and the wavelength is , Q is any point on the Fresnel zone; according to the definition of the Fresnel zone, we can get:

[0027] According to the knowledge of plane geometry, the calculation formula of the major axis 2a and the minor axis 2b of the ellipse can be deduced as follows:

[0028]

[0029] Preferably, extracting the environmental parameters affecting radio wave propagation in the Fresnel zone according to radio wave propagation theory specifically includes: The average building height, building density and vegetation density that affect radio wave propagation in the Fresnel zone are calculated based on radio wave propagation theory.

[0030] In actual application, the reflection and scattering from urban buildings have a significant impact on radio wave propagation, and may also produce a waveguide effect on the signal. Similarly, diffuse reflection from vegetation will also have a significant impact on microwave propagation. In order to quantitatively describe the impact of environmental characteristics on radio wave propagation, the average building height in the Fresnel zone is calculated. , building density , vegetation density The calculation formulas for these three physical quantities are as follows:

[0031]

[0032]

[0033]

[0034] in, Indicates the height of a building or vegetation; Indicates the projected area of ​​a building or vegetation; is the area of ​​the Fresnel zone.

[0035] Preferably, the obtaining of potential variables in the Fresnel zone according to a preset algorithm specifically includes: The latent variables in the Fresnel zone are obtained according to the improved β-VAE algorithm.

[0036] In actual application, the improved β-VAE algorithm is used to compress the height data of various buildings in the Fresnel zone into several most critical features for PL prediction. Unlike the autoencoder model, the improved β-VAE algorithm reduces the massive feature dimensions of building data to 16 features while retaining spatial features. β-VAE is a variant of VAE. Its core goal is to discover decoupled or decomposed potential factors. It introduces an adjustable hyperparameter in the loss function of the original VAE objective. :

[0037] in, It is the reconstruction loss, which aims to make the generated data as close to the original data as possible; is a regular term, representing the KL divergence between the true distribution and the prior distribution of the latent variable z. When , β-VAE is the same as VAE; when When , the β-VAE algorithm has stronger constraints on potential bottlenecks and can obtain more disentangled latent variables. . A higher β value can encourage more efficient latent coding and further promote decoupling, but at the same time, a higher β value may produce a trade-off between reconstruction quality and decoupling degree, so a β value of 5 is selected when training the model. Compared with the traditional β-VAE, the improved β-VAE adds additional fully connected layers to the encoder and decoder parts. This structure allows the model to perform more complex transformations on the latent variables, giving the model better feature abstraction capabilities.

[0038] Preferably, the step of inputting the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result specifically includes: The environmental parameters are fused with the potential variables and then input into a preset prediction model to obtain a path loss prediction result.

[0039] In the actual application process, based on the knowledge of radio wave propagation, five features that have an important impact on radio wave propagation in the urban environment are extracted, namely the height of the receiving antenna, the building density in the Fresnel zone of the transmitting and receiving ends, the average building height, the vegetation density and the propagation distance, which can be expressed as: ={Altitude of Rx, Building Density, Average Building Height,Vegetation Density, Distance} First, use the trained -The encoder part of the VAE model extracts the mean of the latent variable distribution in the DEM data and variance , and then use the reparameterization technique to generate latent variables , and fused with the features extracted from expert knowledge, as shown below:

[0040] The above formula can be used to predict the actual path loss well.

[0041] Preferably, the preset prediction model specifically includes: The preset prediction model is composed of SVR algorithm, AdaBoost iterative algorithm, classification regression algorithm and random forest regression algorithm.

[0042] In actual application, the SVR algorithm is based on the idea of ​​SVM and is specifically used to deal with regression problems. Similar to SVM, SVR introduces kernel functions to deal with nonlinear relationships. The goal of SVR is to find an optimal hyperplane so that the error between the predicted value and the true value on this hyperplane is as small as possible, while limiting the error to a user-defined tolerance. The problems it solves are as follows:

[0043]

[0044]

[0045] Among them, C is the penalty term; represents the distance between the nth sample and the decision boundary; b represents the bias term; Will Mapped to a high-dimensional space. The trained SVR model uses the radial basis function as the kernel function, and the penalty term C is 100. is 0.01.

[0046] The core idea of ​​the AdaBoost iterative algorithm is to train different classifiers (weak classifiers) for the same training set, and then combine these weak classifiers to form a stronger final classifier (strong classifier). The algorithm principle is to adjust the sample weight and the weak classifier weight, and select the weak classifier with the smallest weight coefficient from the trained weak classifiers to combine into a final strong classifier. The AdaBoost model decision tree depth trained in this embodiment is 8, using 200 base learners, and the contribution weight of each base learner is 0.5.

[0047] The K-Nearest Neighbor classification and regression algorithm is the simplest and most commonly used classification and regression algorithm. It calculates the average value of the K nearest neighbor target values ​​as the prediction result. In this embodiment, the K value of the trained model is equal to 50. The distance calculation between sample points selects the Euclidean distance. The formula is as follows:

[0048] in, and They are and In the Coordinates in dimensions, Represents the dimension of the space where the data resides.

[0049] The random forest regression algorithm is an ensemble of multiple decision regression trees, each of which partitions the original data into smaller subsets partitioned by a split node. It starts by partitioning the dataset into n tree bootstrap samples, which are randomly selected (with replacement), one for each regression tree. Starting from the root node within the regression tree, each split node performs a binary test, which is applied to each subset to send it to the left or right child node. The test randomly selects a subset of features and looks for the value with the lowest mean squared error (MSE) to group the training samples into clusters. Sample points in the regression tree arrive at a specific leaf node based on their feature values, so the predicted value of the random tree regressor depends on its feature values. The final predicted value of the random forest algorithm corresponds to the average of the M tree regressors, as shown below:

[0050] in, Indicates A decision tree for input samples The predicted value of Represents the random forest model for the input sample The final predicted value.

[0051] The random forest model trained in this embodiment includes 50 decision trees, the maximum depth of each decision tree is 30, and the minimum number of samples required to split the internal nodes is 10.

[0052] The model performance was evaluated through experimental verification based on training and testing on 16 sets of data. The main evaluation indicators are the mean and standard deviation of the 16 RMSEs of the model's predicted value and true value on the validation set. The prediction error of each ML model is presented in the form of a box plot, such as Figure 3 As shown; the bottom and top of the box represent the first quartile (Q1) and the third quartile (Q3), respectively, and the red line inside the box represents the median. The whiskers outside the box usually extend to 1.5 times the interquartile range, indicating the range of the data, and points outside the whisker range are represented by circles; from Figure 3 It can be seen that by introducing the improved β-VAE algorithm to compress the latent variables of the propagation area, and then fusing the latent variables with the feature vector extracted based on expert knowledge, the prediction performance of the trained model is further improved. The prediction error of each model is reduced by an average of 0.75dB and the standard deviation is reduced by an average of 0.23dB compared to the model using only expert features. Figure 4It can be seen that compared with the three standard models, the prediction accuracy and robustness of the model built using the machine learning method in this paper are greatly improved. Compared with the traditional model, the average RMSE is reduced by 14.38dB and the standard deviation is reduced by 2.69dB. Moreover, because each time the model uses a route that has not been seen by the model as the validation set, it shows that the trained model has good generalization ability. A set of measurement data on the validation set and the prediction results of various models are selected as follows Figure 5 As shown. Since the measurement route is a circular route and LOS and NLOS scenarios overlap, the measured path loss results do not change with the distance rule. The COST231 and 3GPP UMa models only model the path loss as a function of distance and cannot meet the prediction needs. Using the ML algorithm, it can be intuitively seen from the figure that the model proposed in the present invention that extracts the fusion features of the propagation area environment for training can well predict the actual path loss.

[0053] like Figure 6 As shown, an embodiment of the present invention provides a modeling system for an urban environment, including: a first acquisition module, an extraction module, a second acquisition module and a third acquisition module; The first acquisition module is used to acquire the Fresnel zone area according to the latitude and longitude coordinates of a preset area; The extraction module is used to extract environmental parameters that affect radio wave propagation in the Fresnel zone according to radio wave propagation theory; The second acquisition module is used to acquire potential variables in the Fresnel zone according to a preset algorithm; The third acquisition module is used to input the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result.

[0054] In the actual application process, a first acquisition module, an extraction module, a second acquisition module and a third acquisition module are set up, wherein the first acquisition module is connected to the extraction module and the second acquisition module respectively; the third acquisition module is connected to the extraction module and the second acquisition module respectively; the first acquisition module sends the Fresnel zone area obtained according to the latitude and longitude coordinates of the preset area to the extraction module and the second acquisition module; the extraction module extracts the environmental parameters affecting the radio wave propagation in the Fresnel zone according to the radio wave propagation theory, and sends the environmental parameters to the third acquisition module; the second acquisition module obtains the potential variables in the Fresnel zone according to the preset algorithm, and sends the potential variables to the third acquisition module; the third acquisition module inputs the environmental parameters and the potential variables into the preset prediction model to obtain the path loss prediction result; the system realizes the accurate prediction of point-to-point large-scale channels in dense urban environments through the cooperation of the first acquisition module, the extraction module, the second acquisition module and the third acquisition module, and the output prediction results can be applied to urban network planning and optimization.

[0055] Furthermore, the embodiment of the present application also discloses an electronic device, Figure 7 This is a structural diagram of an electronic device according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0056] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the modeling method of the urban environment disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0057] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a modeling channel for the urban environment between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0058] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0059] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20 to realize the operation and processing of the data 223 in the memory 22 by the processor 21, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the modeling method of the urban environment performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to including data transmitted from an external device received by the modeling device of the urban environment, the data 223 can also include data collected by its own input and output interface 25, etc.

[0060] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0061] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned disclosed urban environment modeling method. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0062] It should be understood that the use of "method", "device", "unit" and / or "module" in this application is only a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

[0063] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements. The elements defined by the sentence "includes a..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.

[0064] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0065] If a flow chart is used in the present application, the flow chart is used to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, each step can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or a certain step or several steps of operations can be removed from these processes.

[0066] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A modeling method for an urban environment, characterized in that: The steps include: Get the Fresnel zone area according to the latitude and longitude coordinates of the preset area; Extracting environmental parameters that affect radio wave propagation in the Fresnel zone according to radio wave propagation theory; Acquire potential variables within the Fresnel zone according to a preset algorithm; The environmental parameters and the potential variables are input into a preset prediction model to obtain a path loss prediction result.

2. The method for modeling an urban environment according to claim 1, characterized in that: The step of obtaining the Fresnel zone area according to the latitude and longitude coordinates of the preset area specifically includes: According to the latitude and longitude coordinates of the preset area, a Fresnel zone area with the position of the transmitting and receiving antenna as the focus and the straight line path as the axis is intercepted.

3. The method for modeling an urban environment according to claim 1, characterized in that: The extracting of environmental parameters affecting radio wave propagation in the Fresnel zone according to radio wave propagation theory specifically includes: The average building height, building density and vegetation density that affect radio wave propagation in the Fresnel zone are calculated based on radio wave propagation theory.

4. The method for modeling an urban environment according to claim 1, characterized in that: The step of obtaining the potential variables in the Fresnel zone according to a preset algorithm specifically includes: The latent variables in the Fresnel zone are obtained according to the improved β-VAE algorithm.

5. The method for modeling an urban environment according to claim 1, characterized in that: The step of inputting the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result specifically includes: The environmental parameters are fused with the potential variables and then input into a preset prediction model to obtain a path loss prediction result.

6. The method for modeling an urban environment according to claim 5, characterized in that: The preset prediction model specifically includes: The preset prediction model is composed of SVR algorithm, AdaBoost iterative algorithm, classification regression algorithm and random forest regression algorithm.

7. A modeling system for an urban environment, characterized in that: include: A first acquisition module, an extraction module, a second acquisition module and a third acquisition module; The first acquisition module is used to acquire the Fresnel zone area according to the latitude and longitude coordinates of a preset area; An extraction module, used for extracting environmental parameters affecting radio wave propagation in the Fresnel zone according to radio wave propagation theory; A second acquisition module, used for acquiring potential variables within the Fresnel zone according to a preset algorithm; The third acquisition module is used to input the environmental parameters and the potential variables into a preset prediction model to obtain a path loss prediction result.

8. An electronic device, characterized in that: include: at least one processor; as well as A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor so that the at least one processor can execute the method of any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium is used to store a computer program, and the computer program is used to enable a computer to execute the method according to any one of claims 1 to 6.

Images