Antenna feeder shielding judgment method and device based on user distribution, equipment and product

Abstract

The invention provides an antenna feeder shielding judgment method and device based on user distribution, equipment and a product. The method comprises the following steps: acquiring user distribution data of a target cell; acquiring collection work parameter data and theoretical work parameter data of the target cell; inputting the first input data into a trained first prediction model, inputting the second input data into a trained second prediction model, and obtaining first antenna azimuth angle correction data output by the first prediction model and second antenna azimuth angle correction data output by the second prediction model, the first input data comprises user distribution data and theoretical work parameter data, and the second input data comprises user distribution data and collection work parameter data; and determining whether shielding exists between a base station antenna feeder corresponding to the target cell and the target cell based on the difference between the first antenna azimuth angle correction data and the second antenna azimuth angle correction data. According to the invention, the accuracy of antenna feeder shielding identification results can be improved.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an antenna feed shielding judgment method, device, equipment and product based on user distribution. Background Art

[0002] Identification of antenna feed obstruction problems (e.g., there are tall buildings between the base station antenna feed and the community, billboards blocking the antenna signal, etc.) plays a big role in network planning and optimization. In the prior art, the identification of antenna feed obstruction problems is often based on building and base station engineering parameter information. Through simple spatial trigonometric functions, it is determined whether the antenna feed is blocked based on the station height, orientation, and GIS information of the building. However, this method requires accurate base station engineering parameter information and building information. However, the urban development process is relatively fast, and the map of building information is not updated in time. The crawler does not obtain comprehensive data. In addition, there are many on-site antenna optimization actions, and the engineering parameter information of the existing base station is not updated in time. These factors will affect the recognition results, resulting in low accuracy of the existing antenna feed obstruction recognition results. Summary of the invention

[0003] The present invention provides an antenna feed blockage judgment method, device, equipment and product based on user distribution, so as to solve the defect of low accuracy of antenna feed blockage recognition result in the prior art and improve the accuracy of antenna feed blockage recognition result.

[0004] The present invention provides an antenna feed shielding judgment method based on user distribution, comprising: Acquire user distribution data of the target cell, where the user distribution data reflects the geographical location distribution of users of the target cell when accessing a base station corresponding to the target cell; Acquire collected engineering parameter data and theoretical engineering parameter data of the target cell, wherein the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; Inputting first input data into a trained first prediction model, and inputting second input data into a trained second prediction model, obtaining first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model, wherein the first input data includes the user distribution data and the theoretical engineering parameter data, and the second input data includes the user distribution data and the collected engineering parameter data; Determine whether there is any obstruction between the base station antenna feed corresponding to the target cell and the target cell based on a difference between the first antenna azimuth correction data and the second antenna azimuth correction data; The first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data respectively, the first training data includes sample first input data and first antenna azimuth angle labels, and the second training data includes sample second input data and second antenna azimuth angle labels.

[0005] According to the antenna feed shielding judgment method based on user distribution provided by the present invention, the step of obtaining user distribution data of the target cell includes: Obtain the latitude and longitude information of each sampled user; The user distribution data is obtained based on the latitude and longitude information of each of the sampled users.

[0006] According to the antenna feed shielding judgment method based on user distribution provided by the present invention, the user distribution data is obtained based on the latitude and longitude information of each of the sampled users, including: Initialize the mean and covariance matrix of each Gaussian distribution; Determine the probability that the sampled user belongs to each Gaussian distribution based on the latitude and longitude information of the sampled user; Updating the mean and covariance matrix of each Gaussian distribution based on the probability that the sampled user belongs to each Gaussian distribution; Repeat the step of determining the probability that the sampled user belongs to each Gaussian distribution based on the latitude and longitude information of the sampled user until the mean and covariance matrix of each Gaussian distribution converge or the number of updates of the mean and covariance matrix of each Gaussian distribution reaches a preset number; The mean of each Gaussian distribution is obtained as the center point of the user distribution, and the user distribution data is determined based on the center point.

[0007] According to the antenna feed shielding judgment method based on user distribution provided by the present invention, the step of obtaining the longitude and latitude information of each sampled user includes: Data matching is performed based on the 4G MR data and 5G MRO data of the target cell to obtain the latitude and longitude information of the sampled user.

[0008] According to the antenna feed shielding judgment method based on user distribution provided by the present invention, the first input data is input into a trained first prediction model, the second input data is input into a trained second prediction model, and the first antenna azimuth correction data output by the first prediction model and the second antenna azimuth correction data output by the second prediction model are obtained, including: Inputting the input data into a plurality of the first prediction models respectively, obtaining the first antenna azimuth correction data respectively output by the first prediction models, each of the first prediction models corresponding to an antenna downtilt angle; The input data is respectively input into a plurality of the second prediction models, and the second antenna azimuth correction data respectively output by the second prediction models is obtained, wherein each second prediction model corresponds to an antenna downtilt angle.

[0009] According to the antenna feed shielding judgment method based on user distribution provided by the present invention, the determining whether there is shielding between the base station antenna feed corresponding to the target cell and the target cell based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data includes: Acquire a mean square error between a first data group and a second data group, wherein the first data group includes each first antenna azimuth correction data, and the second data group includes each second antenna azimuth correction data; It is determined whether there is shielding between the base station antenna feeder corresponding to the target cell and the target cell based on the mean square error.

[0010] The present invention also provides an antenna feed shielding judgment device based on user distribution, comprising: A distribution data acquisition module, used to acquire user distribution data of a target cell, wherein the user distribution data reflects the geographical location distribution of users of the target cell when accessing a base station corresponding to the target cell; An engineering parameter data acquisition module, used to acquire collected engineering parameter data and theoretical engineering parameter data of the target cell, wherein the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; an azimuth correction module, used for inputting first input data into a trained first prediction model, and inputting second input data into a trained second prediction model, and obtaining first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model, wherein the first input data includes the user distribution data and the theoretical engineering parameter data, and the second input data includes the user distribution data and the collected engineering parameter data; A judgment module, configured to determine whether there is an obstruction between the base station antenna feed corresponding to the target cell and the target cell based on a difference between the first antenna azimuth correction data and the second antenna azimuth correction data; The first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data respectively, the first training data includes sample first input data and first antenna azimuth angle labels, and the second training data includes sample second input data and second antenna azimuth angle labels.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the antenna feed shielding judgment method based on user distribution as described in any one of the above is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the antenna feed shielding judgment method based on user distribution as described in any one of the above is implemented.

[0013] The present invention also provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned antenna feed shielding judgment methods based on user distribution.

[0014] The antenna feeder obstruction judgment method, device, equipment and product based on user distribution provided by the present invention obtain user distribution data of the target cell, use the trained first prediction model and the second prediction model, and calibrate the theoretical engineering parameter data reflecting the base station antenna feeder design parameters corresponding to the target cell and the antenna azimuth data in the base station antenna feeder design parameters calculated based on the MR data of the target cell based on the user distribution data. In this way, the first antenna azimuth correction data corresponding to the user distribution data of the target cell in an ideal state without obstruction and the second antenna azimuth correction data corresponding to the user distribution data of the target cell in an actual state can be obtained respectively. The difference between the second antenna azimuth correction data and the first antenna azimuth correction data is used to judge whether there is obstruction between the antenna feed and the target cell. In this process, the user distribution data is used to calibrate the antenna azimuth data of the antenna feed, and then the antenna feeder obstruction is identified, which can improve the accuracy of the antenna feeder obstruction identification result. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 The present invention is a flowchart of a method for determining antenna feed shielding based on user distribution.

[0017] Figure 2 This is a schematic diagram of identifying antenna feed obstruction based on building information.

[0018] Figure 3 It is a schematic diagram of the principle of an antenna feed shielding judgment method based on user distribution provided by the present invention.

[0019] Figure 4 It is a schematic diagram of a process for acquiring user longitude and latitude information in an antenna feed occlusion judgment method based on user distribution provided by the present invention.

[0020] Figure 5 It is a spatial distribution diagram of sampled users in an antenna feed occlusion judgment method based on user distribution provided by the present invention.

[0021] Figure 6 It is a structural schematic diagram of a prediction model in an antenna feed shading judgment method based on user distribution provided by the present invention.

[0022] Figure 7 It is a schematic diagram of the process of outputting antenna correction results in an antenna shielding judgment method based on user distribution provided by the present invention.

[0023] Figure 8 It is a schematic diagram of the effect of an antenna feed shielding judgment method based on user distribution provided by the present invention.

[0024] Fig. 9 It is a structural schematic diagram of an antenna feed shielding judgment device based on user distribution provided by the present invention.

[0025] Fig.10 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In the prior art, based on the engineering parameter information of buildings and base stations, simple spatial trigonometric functions are used to determine whether the antenna feed is blocked according to the station height, orientation, GIS information of buildings, etc. Figure 2As shown in the figure, if the angle between the two rays of Building A is within the horizontal lobe of the antenna (about 60 degrees for 5G and about 40 degrees for 4G), and the distance does not exceed the set value (300 meters for 2.6G, 800 meters for 700M, and 400 meters for 4G), the antenna is considered to cover Building A. If the angle between the rays of other buildings between the antenna and Building A overlaps with the angle of Building C by more than 80%, it is considered that there is an obstruction in the horizontal defense line of the middle building C. However, this method requires accurate base station engineering parameter information and building information, and the urban development process is relatively fast. The map of building information is not updated in time, and the crawler obtains incomplete data. In addition, there are many on-site antenna optimization actions, and the engineering parameter information of the existing base station is not updated in time. These factors will affect the recognition results, resulting in low accuracy of the existing antenna occlusion recognition results.

[0028] In order to solve the defect of low accuracy of antenna feed blockage identification results in the prior art, the present invention provides an antenna feed blockage judgment method, device, equipment and product based on user distribution, so as to improve the accuracy of antenna feed blockage identification results.

[0029] Combine the following Figure 1 The antenna feed shielding judgment method based on user distribution provided by the present invention is described as follows: Figure 1 As shown, the present invention provides an antenna feed shielding judgment method based on user distribution, comprising the steps of: S110, obtaining user distribution data of a target cell, where the user distribution data reflects the geographical location distribution of users of the target cell when they access a base station corresponding to the target cell; S120, acquiring collected engineering parameter data and theoretical engineering parameter data of the target cell, wherein the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; S130, inputting first input data into a trained first prediction model, and inputting second input data into a trained second prediction model, obtaining first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model, wherein the first input data includes user distribution data and theoretical engineering parameter data, and the second input data includes user distribution data and collected engineering parameter data; S140: Determine whether there is any shielding between the base station antenna feed corresponding to the target cell and the target cell based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data.

[0030] The method provided by the present invention obtains user distribution data of a target cell, utilizes a trained first prediction model and a second prediction model, and calibrates theoretical engineering parameter data reflecting base station antenna feed design parameters corresponding to the target cell and antenna azimuth data in the base station antenna feed design parameters inferred based on MR data of the target cell based on the user distribution data, respectively. In this way, first antenna azimuth correction data corresponding to the user distribution data of the target cell in an ideal state without obstruction and second antenna azimuth correction data corresponding to the user distribution data of the target cell in an actual state can be obtained respectively. The difference between the second antenna azimuth correction data and the first antenna azimuth correction data is used to determine whether there is obstruction between the antenna feed and the target cell. In this process, the user distribution data is utilized to calibrate the antenna azimuth data of the antenna feed, and then the antenna feed obstruction is identified, thereby improving the accuracy of the antenna feed obstruction identification result.

[0031] The user distribution data of the target cell reflects the geographical location distribution of the users of the target cell when they access the base station antenna feed corresponding to the target cell, and can be obtained through the geographical location of the communication terminal of the user of the target cell when it accesses the base station corresponding to the target cell. Since there are many users in the target cell, in a possible implementation of the present invention, instead of obtaining the geographical location of all users in the target cell, the users are sampled, and the user distribution data reflecting the user distribution of the target cell is obtained based on the geographical location of each sampled user, that is, obtaining the user distribution data of the target cell includes: Obtain the latitude and longitude information of each sampled user; The user distribution data is obtained based on the latitude and longitude information of each sampled user.

[0032] Specifically, the longitude and latitude information of each sampled user is obtained, including: Data matching is performed based on the 4G MR data and 5G MRO data of the target cell to obtain the latitude and longitude information of the sampled user.

[0033] like Figure 4 As shown, the longitude and latitude information of each sampled user can be obtained based on the 4G MR (Measurement Report) fingerprint library information table and the 5G heterogeneous system measurement data table. Specifically, through the neighboring area information of 4G carried by 5G, the 4G MR fingerprint library information table is queried in association to obtain the 4G longitude and latitude information, and the 4G longitude and latitude information is backfilled into the 5G MRO (MR Original, measurement report sample data file) sampling data with neighboring area relationship, and the 5G MRO rasterization processing is implemented to obtain the longitude and latitude information of the 5G user sampling point, such as Figure 5 shown.

[0034] In a possible implementation, the longitude and latitude information of each sampled user can be directly used as user distribution data, but this will generate a large amount of data processing and cannot directly reflect the distribution of users. In order to further extract user distribution data that can directly reflect the distribution of users and has a small amount of data, the user distribution data is obtained based on the longitude and latitude information of each sampled user, including: Initialize the mean and covariance matrix of each Gaussian distribution; Determine the probability that the sampled user belongs to each Gaussian distribution based on the latitude and longitude information of the sampled user; Update the mean and covariance matrix of each Gaussian distribution based on the probability that the sampled user belongs to each Gaussian distribution; Repeat the step of determining the probability that the sampled user belongs to each Gaussian distribution based on the latitude and longitude information of the sampled user until the mean and covariance matrix of each Gaussian distribution converge or the number of updates of the mean and covariance matrix of each Gaussian distribution reaches a preset number; The mean of each Gaussian distribution is obtained as the center point of the user distribution, and the user distribution data is determined based on the center point.

[0035] In one implementation of the method provided by the present invention, the latitude and longitude information group of the sampled users is regarded as a mixture composed of multiple Gaussian distributions, each Gaussian distribution represents a cluster, and the data is fitted by maximizing the likelihood function to find the best cluster center point, thereby obtaining user distribution data that can reflect the specific user distribution. Specifically, the latitude and longitude information corresponding to each sampled user is used as a data point to construct a data set, and the mean (representing the center point of the cluster) and covariance matrix of each Gaussian distribution are randomly initialized, and the probability (posterior probability) that each data point belongs to each Gaussian distribution is calculated: in, Represents data points The probability of belonging to the kth Gaussian distribution, is the weight of the kth Gaussian distribution, is the density function of the multivariate Gaussian distribution. Then, according to the probability that each data point belongs to the Gaussian distribution, the mean and covariance matrix are updated. The specific formula is as follows: ; ; .

[0036] Repeat the steps of calculating the probability that each data point belongs to each Gaussian distribution and updating the mean and covariance matrix until convergence (the mean and covariance matrix no longer change) or the preset number of iterations is reached. The final mean of each Gaussian distribution is used as the center point of the user cluster, and the user distribution data is determined based on the center point. Specifically, the position of the center point relative to the base station of the target cell can be used as the user distribution data. In one possible implementation, the center point can be connected to the base station vertex of the target cell to obtain a connecting line, and the angle and the starting and ending positions of the connecting line are used as the user distribution data.

[0037] The structure of the antenna feed will affect the distribution of users, because users tend to communicate in locations with better signals. Theoretically, the signal in the direction pointed by the antenna azimuth angle (also known as the direction of the normal line of the engineering parameter) will be better, and users will be concentrated on both sides of the direction pointed by the antenna azimuth angle. As the distance from the direction pointed by the antenna azimuth angle increases, the user sampling points should decrease. However, if there is an obstruction, the direction in which users are concentrated will deviate from the direction pointed by the antenna azimuth angle.

[0038] The method provided by the present invention utilizes this principle and, based on user distribution data, respectively utilizes the collected engineering parameter data and the theoretical engineering parameter data to infer the antenna azimuth in an unobstructed state, such as Figure 3 As shown, the antenna azimuth angle inferred based on theoretical engineering parameter data and user distribution data corresponds to the normal direction of the normal engineering parameter, and the antenna azimuth angle inferred based on the collected engineering parameter data and user distribution data corresponds to the fuzzy engineering parameter normal direction. Based on the difference between the two, it can be identified whether there is any obstruction between the target cell and the antenna feed.

[0039] The engineering parameter data includes the parameters of the base station antenna feed, and the theoretical engineering parameter data reflects the design parameters of the base station antenna feed corresponding to the target cell. The theoretical engineering parameter data can be obtained based on the design file of the antenna feed, such as the initial design file of the antenna feed, or the design file after on-site RF optimization. The theoretical engineering parameter data is the theoretical parameters of the base station antenna feed corresponding to the current target cell. However, since the base station may be RF optimized during operation, or affected by the environment during operation, the antenna azimuth angle recorded in the theoretical engineering parameter data in the design file may not be accurate data. The method provided by the present invention is based on user distribution data and theoretical engineering parameter data, and corrects the antenna azimuth angle in the theoretical engineering parameter data under the assumption of no obstruction. Specifically, the first input data including theoretical working parameter data and user distribution data is input into the first prediction model. The first prediction model is trained based on multiple groups of first training data. Each group of first training data includes sample first input data and a first antenna azimuth label. The first training data is obtained based on unobstructed cell data. That is to say, the first prediction model can output antenna azimuth correction data based on the input theoretical working parameter data and user distribution data, which can make the actual user distribution consistent with the user distribution data under unobstructed conditions.

[0040] The collected engineering parameter data is the base station antenna feed parameters calculated based on the MR data of the target cell. The MR data of the target cell is the data collected by the target terminal, that is, the MR data of the target cell reflects the actual user situation of the target cell. The base station antenna feed parameters can be inferred based on the MR data of the target cell. The collected engineering parameter data can also be called fuzzy engineering parameter data. The method provided by the present invention corrects the antenna azimuth in the collected engineering parameter data based on user distribution data and collected engineering parameter data. Specifically, the second input data including the collected engineering parameter data and the user distribution data is input into the second prediction model. The second prediction model is obtained by training based on multiple groups of second training data. Each group of second training data includes sample second input data and second antenna azimuth labels. The second training data can be obtained based on cells with or without obstructions. It can be seen that the collected engineering parameter data has reflected the base station antenna feed parameters corresponding to the actual user situation, and the user distribution data also reflects the base station antenna feed parameters corresponding to the actual user situation. Through the second prediction model, the corresponding antenna azimuth correction data under the actual state of the cell can be obtained.

[0041] From the foregoing description, it can be seen that the first prediction model corrects the theoretical antenna azimuth based on the user distribution data under the theoretical state without obstruction, and the output first antenna azimuth correction data is the antenna azimuth that produces the corresponding user distribution data under the theoretical state without obstruction. The second prediction model corrects the antenna azimuth inferred from the actual MR data based on the user distribution data, and the output is the antenna azimuth that produces the corresponding user distribution data under the actual state. Therefore, the closer the second antenna azimuth correction data output by the second prediction model is to the first antenna azimuth correction data output by the first prediction model, the lower the probability of occlusion.

[0042] like Figure 6 As shown, in a possible implementation, both the first prediction model and the second prediction model can adopt the Conv-LSTM model structure. During training, the sample data is divided into a standard set and a test set, where the standard set is divided into a ratio of K and the test level is (1-K). The data set is divided into a standard set train_set and a problem set test_set, that is, the standard set train_set = data set * K, and the test_set = data set * (1-K).

[0043] The main data processing contents in the Conv-LSTM model are: Input Gate: ; Forget Gate: ; Update Gate: ; Memory Cell Update: ; Output Gate: ; Hidden State Update: ; in, , , , Represent the outputs of the input gate, forget gate, update gate, and output gate respectively. Represents the memory cell at the current moment, Indicates the hidden state at the current moment, Represents the input at the current moment, W, U, b represent the weight matrix, recursive weight matrix and bias term respectively, σ represents the Sigmoid function, ⊙ represents element-by-element multiplication, and tanh represents the hyperbolic tangent function.

[0044] The antenna downtilt angle also has a certain influence on the user distribution. In a possible implementation, in order to improve the accuracy of the recognition result of the antenna feed shielding, the method provided by the present invention sets corresponding first prediction models and second prediction models for multiple antenna downtilt angles, that is, inputs the first input data into the trained first prediction model, inputs the second input data into the trained second prediction model, obtains the first antenna azimuth correction data output by the first prediction model and the second antenna azimuth correction data output by the second prediction model, including: Inputting the input data into a plurality of first prediction models respectively, obtaining first antenna azimuth correction data respectively output by each first prediction model, each first prediction model corresponding to an antenna downtilt angle; Input data are respectively input into a plurality of second prediction models to obtain second antenna azimuth correction data respectively output by each second prediction model, wherein each second prediction model corresponds to an antenna downtilt angle.

[0045] By training the prediction models under different downtilt angle scenarios, the corresponding antenna azimuth correction data can be output under different antenna downtilt angle scenarios, providing more data information and improving the accuracy of the results of judging whether the antenna feed is blocked.

[0046] Determining whether the antenna feed system to be determined is blocked based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data includes: Acquire a mean square error between a first data group and a second data group, wherein the first data group includes each first antenna azimuth correction data, and the second data group includes each second antenna azimuth correction data; It is determined whether the antenna feed system to be determined is blocked based on the mean square error.

[0047] The antenna azimuth under the assumption of no obstruction is corrected in different downtilt angle scenarios to obtain a set of first antenna azimuth correction data, and the antenna azimuth in the actual state is corrected in different downtilt angle scenarios to obtain a set of second antenna azimuth correction data, and the mean square error of the two sets of data is obtained. When the mean square error is within a preset range, it is determined that there is no obstruction. In a possible implementation, when the mean square error is below 3dB, it is determined that there is no obstruction, otherwise there is obstruction.

[0048] Furthermore, based on the second antenna azimuth correction data, antenna feed tuning suggestions can also be output, specifically, Figure 7As shown, the engineering parameter azimuth angle (collecting engineering parameter data) obtained based on the existing network MR data of each cell is corrected to obtain the calibrated normal angle (i.e., the second antenna azimuth correction data), and the deviation between the second antenna azimuth correction data corresponding to each cell and the standard engineering parameter normal angle (actual antenna azimuth angle) is calculated to output the antenna feed correction result. The antenna feed correction result is a tuning suggestion for the antenna feed, which may include adjusting the azimuth angle, adjusting the base station address position, etc.

[0049] After obtaining the judgment result of whether there is occlusion, the judgment result, the community location grid data, the building layer information, the GIS-based surrounding occluding building information and the optimization suggestions can be output together.

[0050] Taking a certain actual community as an example, the method provided by the present invention was experimentally verified. The result showed that the mean square error was 4.3 dB. It was judged that there was occlusion, and combined with the weak coverage grid data, the building where the weak coverage grid was located was locked. Figure 8 As shown, there is a weak coverage grid within the angle range of the first antenna azimuth correction data and the second antenna azimuth correction data. Combined with the on-site situation, it is found that there is indeed serious obstruction.

[0051] The following is a description of the antenna feed blocking judgment device based on user distribution provided by the present invention. The antenna feed blocking judgment device based on user distribution described below and the antenna feed blocking judgment method based on user distribution described above can be referred to each other. Fig. 9 As shown, the antenna feed shielding judgment device based on user distribution provided by the present invention includes: A distribution data acquisition module 910 is used to acquire user distribution data of a target cell, where the user distribution data reflects the geographical location distribution of users of the target cell when they access a base station corresponding to the target cell; The engineering parameter data acquisition module 920 is used to acquire the collected engineering parameter data and theoretical engineering parameter data of the target cell, wherein the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; Azimuth correction module 930, used to input first input data into a trained first prediction model, input second input data into a trained second prediction model, obtain first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model, the first input data includes user distribution data and theoretical engineering parameter data, and the second input data includes user distribution data and collected engineering parameter data; A judgment module 940 is used to determine whether there is an obstruction between the base station antenna feed corresponding to the target cell and the target cell based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data; The first prediction model and the second prediction model are trained based on multiple sets of first training data and multiple sets of second training data respectively, the first training data includes sample first input data and first antenna azimuth angle labels, and the second training data includes sample second input data and second antenna azimuth angle labels.

[0052] Fig.10 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.10 As shown, the electronic device may include: a processor 1010, a communication interface 1020, a memory 1030 and a communication bus 1040, wherein the processor 1010, the communication interface 1020 and the memory 1030 communicate with each other through the communication bus 1040. The processor 1010 may call the logic instructions in the memory 1030 to execute the antenna feed shielding judgment method based on user distribution, and the antenna feed shielding judgment method based on user distribution includes: obtaining user distribution data of the target cell, the user distribution data reflects the geographical location distribution of the users of the target cell when accessing the base station corresponding to the target cell; obtaining the collected engineering parameter data and theoretical engineering parameter data of the target cell, the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; inputting the first input data into the trained first prediction model, inputting the second input data into the trained second prediction model, and obtaining The first prediction model outputs the first antenna azimuth correction data and the second prediction model outputs the second antenna azimuth correction data, the first input data includes user distribution data and theoretical engineering parameter data, and the second input data includes user distribution data and collected engineering parameter data; based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data, determine whether there is an obstruction between the base station antenna feed corresponding to the target cell and the target cell; wherein the first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data, respectively, the first training data includes sample first input data and a first antenna azimuth label, and the second training data includes sample second input data and a second antenna azimuth label.

[0053] In addition, the logic instructions in the above-mentioned memory 1030 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0054] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the above-mentioned antenna feed obstruction judgment method based on user distribution. The antenna feed obstruction judgment method based on user distribution includes: obtaining user distribution data of the target cell, the user distribution data reflects the geographical location distribution of users of the target cell when accessing the base station corresponding to the target cell; obtaining collected engineering parameter data and theoretical engineering parameter data of the target cell, the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; inputting the first input data into the trained second A prediction model is provided, wherein the second input data is input into the trained second prediction model, and the first antenna azimuth correction data output by the first prediction model and the second antenna azimuth correction data output by the second prediction model are obtained, wherein the first input data includes user distribution data and theoretical engineering parameter data, and the second input data includes user distribution data and collected engineering parameter data; based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data, it is determined whether there is an obstruction between the base station antenna feed corresponding to the target cell and the target cell; wherein the first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data, respectively, the first training data includes sample first input data and a first antenna azimuth label, and the second training data includes sample second input data and a second antenna azimuth label.

[0055] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the above-mentioned antenna feed obstruction judgment method based on user distribution, and the antenna feed obstruction judgment method based on user distribution includes: obtaining user distribution data of a target cell, the user distribution data reflecting the geographical location distribution of users of the target cell when accessing a base station corresponding to the target cell; obtaining collected engineering parameter data and theoretical engineering parameter data of the target cell, the collected engineering parameter data reflecting the antenna feed parameters of the base station corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflecting the antenna feed design parameters of the base station corresponding to the target cell; inputting the first input data into a trained first prediction model, and inputting the second input data into a trained first prediction model. The first prediction model is input into the trained second prediction model to obtain the first antenna azimuth correction data output by the first prediction model and the second antenna azimuth correction data output by the second prediction model, wherein the first input data includes user distribution data and theoretical engineering parameter data, and the second input data includes user distribution data and collected engineering parameter data; based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data, it is determined whether there is an obstruction between the base station antenna feed corresponding to the target cell and the target cell; wherein the first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data, respectively, the first training data includes sample first input data and a first antenna azimuth label, and the second training data includes sample second input data and a second antenna azimuth label.

[0056] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0057] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining antenna feed shielding based on user distribution, characterized in that: include: Acquire user distribution data of the target cell, where the user distribution data reflects the geographical location distribution of users of the target cell when accessing a base station corresponding to the target cell; Acquire collected engineering parameter data and theoretical engineering parameter data of the target cell, wherein the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; Inputting first input data into a trained first prediction model, and inputting second input data into a trained second prediction model, obtaining first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model, wherein the first input data includes the user distribution data and the theoretical engineering parameter data, and the second input data includes the user distribution data and the collected engineering parameter data; Determine whether there is any obstruction between the base station antenna feed corresponding to the target cell and the target cell based on a difference between the first antenna azimuth correction data and the second antenna azimuth correction data; The first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data respectively, the first training data includes sample first input data and first antenna azimuth angle labels, and the second training data includes sample second input data and second antenna azimuth angle labels.

2. The antenna feed shielding judgment method based on user distribution according to claim 1, characterized in that: The obtaining of user distribution data of the target cell includes: Obtain the latitude and longitude information of each sampled user; The user distribution data is obtained based on the latitude and longitude information of each of the sampled users.

3. The antenna feed shielding judgment method based on user distribution according to claim 2, characterized in that: The acquiring the user distribution data based on the latitude and longitude information of each of the sampled users includes: Initialize the mean and covariance matrix of each Gaussian distribution; Determine the probability that the sampled user belongs to each Gaussian distribution based on the latitude and longitude information of the sampled user; Based on the probability that the sampled user belongs to each Gaussian distribution, the mean and covariance matrix of each Gaussian distribution are updated; Repeat the step of determining the probability that the sampled user belongs to each Gaussian distribution based on the latitude and longitude information of the sampled user until the mean and covariance matrix of each Gaussian distribution converge or the number of updates of the mean and covariance matrix of each Gaussian distribution reaches a preset number; The mean of each Gaussian distribution is obtained as the center point of the user distribution, and the user distribution data is determined based on the center point.

4. The antenna feed shielding judgment method based on user distribution according to claim 3, characterized in that: The obtaining of the latitude and longitude information of each sampled user includes: Data matching is performed based on the 4G MR data and 5G MRO data of the target cell to obtain the latitude and longitude information of the sampled user.

5. The antenna feed shielding judgment method based on user distribution according to claim 1, characterized in that: The step of inputting the first input data into a trained first prediction model, inputting the second input data into a trained second prediction model, and obtaining first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model includes: Inputting the input data into a plurality of the first prediction models respectively, obtaining the first antenna azimuth correction data respectively output by the first prediction models, each of the first prediction models corresponding to an antenna downtilt angle; The input data is respectively input into a plurality of the second prediction models, and the second antenna azimuth correction data respectively output by the second prediction models is obtained, wherein each second prediction model corresponds to an antenna downtilt angle.

6. The antenna feed shielding judgment method based on user distribution according to claim 5, characterized in that: The determining whether there is shielding between the base station antenna feed corresponding to the target cell and the target cell based on the difference between the first antenna azimuth correction data and the second antenna azimuth correction data includes: Acquire a mean square error between a first data group and a second data group, wherein the first data group includes each first antenna azimuth correction data, and the second data group includes each second antenna azimuth correction data; It is determined whether there is shielding between the base station antenna feeder corresponding to the target cell and the target cell based on the mean square error.

7. An antenna feed shielding judgment device based on user distribution, characterized in that: include: A distribution data acquisition module, used to acquire user distribution data of a target cell, wherein the user distribution data reflects the geographical location distribution of users of the target cell when accessing a base station corresponding to the target cell; An engineering parameter data acquisition module, used to acquire collected engineering parameter data and theoretical engineering parameter data of the target cell, wherein the collected engineering parameter data reflects the base station antenna feed parameters corresponding to the target cell obtained based on the MR data of the target cell, and the theoretical engineering parameter data reflects the base station antenna feed design parameters corresponding to the target cell; an azimuth correction module, used for inputting first input data into a trained first prediction model, and inputting second input data into a trained second prediction model, and obtaining first antenna azimuth correction data output by the first prediction model and second antenna azimuth correction data output by the second prediction model, wherein the first input data includes the user distribution data and the theoretical engineering parameter data, and the second input data includes the user distribution data and the collected engineering parameter data; A judgment module, configured to determine whether there is an obstruction between the base station antenna feed corresponding to the target cell and the target cell based on a difference between the first antenna azimuth correction data and the second antenna azimuth correction data; The first prediction model and the second prediction model are trained based on multiple groups of first training data and multiple groups of second training data respectively, the first training data includes sample first input data and first antenna azimuth angle labels, and the second training data includes sample second input data and second antenna azimuth angle labels.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the antenna feed shielding judgment method based on user distribution is implemented as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the antenna feed shielding judgment method based on user distribution is implemented as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the antenna feed shielding judgment method based on user distribution is implemented as described in any one of claims 1 to 6.

Images