Base station positioning method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a base station positioning method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring target fingerprint data collected by at least three terminals, wherein the target fingerprint data comprises cellular signals, terminal identifiers, terminal positions and distances from the terminals to a target area; processing the target fingerprint data through a pre-configured path processing model to obtain the distance from each terminal to the target base station; and processing based on the terminal position of each terminal, the distance from each terminal to the target base station and the distance from each terminal to the target area to obtain the spatial position of the target base station. Through adoption of the method, the real-time spatial position of the target base station is positioned through the fingerprint data acquired by the plurality of measurement terminals and the deep learning model, adaptive calibration of positioning is realized, and the positioning accuracy of the target base station is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wireless communication, and in particular to a base station positioning method and device, computer equipment, a computer readable storage medium and a computer program product. BACKGROUND

[0002] With the development of indoor and outdoor positioning technology, the operator's cellular base station is developing towards miniaturization and multifunctionalization, and the functions integrated in the indoor cellular small station are becoming more and more rich, such as the UTDOA positioning (Uplink Time Difference of Arrival) technology, the 5G core network element LMF (Location Management Function) support enables the base station to measure and report uplink fingerprint data, and promotes the development of the indoor positioning technology industry chain. In some supermarket or large factory scenarios, the operator deploys indoor base stations in the ceiling. In the daily maintenance and technical upgrading process of the cellular base station in the actual use scenario, the position of the base station can generally be determined only based on the manually entered position of the installation and maintenance personnel, and the manually entered position is relatively rough, resulting in poor accuracy of base station positioning. SUMMARY

[0003] Therefore, it is necessary to provide a base station positioning method, device, computer equipment, computer readable storage medium and computer program product capable of improving positioning accuracy in view of the above technical problems.

[0004] In a first aspect, the present application provides a base station positioning method, comprising:

[0005] obtaining target fingerprint data collected by at least three terminals, the target fingerprint data comprising a cellular signal, a terminal identifier, a terminal position and a distance from the terminal to a target area;

[0006] processing the target fingerprint data through a pre-configured path processing model to obtain a distance from each terminal to a target base station;

[0007] processing based on the terminal position of each terminal, the distance from each terminal to the target base station and the distance from the terminal to the target area to obtain a spatial position of the target base station.

[0008] In one of the embodiments, the obtaining of the target fingerprint data collected by at least three terminals comprises:

[0009] receiving initial fingerprint data reported by each terminal;

[0010] The initial fingerprint data is preprocessed to obtain target fingerprint data, and the preprocessing includes data formatting processing or normalization processing.

[0011] In one of the embodiments, the target area is a target plane, and each terminal is located on the target plane; the processing based on the terminal position of each terminal, the distance from each terminal to a target base station, and the distance from each terminal to a target area to obtain the spatial position of the target base station includes:

[0012] Based on the association model between distance and coordinate, the distance from each terminal to a target base station and the terminal position of each terminal are processed to obtain the projection position of the target base station on the target plane and the height of the target base station to the target plane.

[0013] Based on the height of the target plane, the projection position of the target base station on the target plane, and the height of the target base station to the target plane, the spatial position of the target base station is obtained.

[0014] In one of the embodiments, the processing based on the height of the target plane, the projection position of the target base station on the target plane, and the height of the target base station to the target plane to obtain the spatial position of the target base station includes:

[0015] The sum of the height of the target plane and the height of the target base station to the target plane is calculated, and the sum is determined as a height coordinate.

[0016] Based on the projection position of the target base station on the target plane and the height coordinate, the spatial position of the target base station is obtained.

[0017] In one of the embodiments, the path processing model includes a path signal attenuation model and a path selection model; the method further includes:

[0018] The sample fingerprint data reported by a terminal and the sample distance corresponding to the sample fingerprint data are processed by the path signal attenuation model and the path selection model to be trained to obtain a predicted distance.

[0019] Based on the predicted distance and the sample distance, the path signal attenuation model and the path selection model to be trained are trained to obtain a trained path processing model.

[0020] In one of the embodiments, the method further includes:

[0021] The spatial position of the target base station is returned to the terminal, so that the terminal displays the real-time position of the target base station in a preset map based on the spatial position of the target base station.

[0022] In a second aspect, the present application further provides a base station positioning device applied to a server, comprising:

[0023] The acquisition module is configured to acquire target fingerprint data collected by at least three terminals, wherein the target fingerprint data comprises cellular signals, terminal identifiers, terminal positions and distances from the terminals to a target area;

[0024] The first processing module is configured to process the target fingerprint data by using a preconfigured path processing model to obtain distances from the terminals to a target base station;

[0025] The second processing module is configured to process the terminal positions of the terminals, the distances from the terminals to the target base station and the distances from the terminals to the target area to obtain a spatial position of the target base station.

[0026] In one embodiment, the acquisition module is specifically configured to:

[0027] Receive initial fingerprint data reported by the terminals;

[0028] Preprocess the initial fingerprint data to obtain target fingerprint data, wherein the preprocessing comprises data formatting processing or normalization processing.

[0029] In one embodiment, the target area is a target plane, and the terminals are located on the target plane; the second processing module is specifically configured to:

[0030] Process the distances from the terminals to the target base station and the terminal positions of the terminals based on an association model between distances and coordinates to obtain a projection position of the target base station on the target plane and a height of the target base station to the target plane;

[0031] Obtain the spatial position of the target base station based on a height of the target plane, the projection position of the target base station on the target plane and the height of the target base station to the target plane.

[0032] In one embodiment, the second processing module is further specifically configured to:

[0033] Calculate a sum of the height of the target plane and the height of the target base station to the target plane, and determine the sum as a height coordinate;

[0034] obtaining a spatial position of the target base station based on the target base station's projected position on the target plane and the height coordinate.

[0035] In one of the embodiments, the path processing model comprises a path signal attenuation model and a path selection model; and the apparatus further comprises:

[0036] a third processing module configured to process the sample fingerprint data reported by the terminal and the sample distance corresponding to the sample fingerprint data by using the path signal attenuation model and the path selection model to be trained, to obtain a predicted distance;

[0037] a training module configured to train the path signal attenuation model and the path selection model to be trained based on the predicted distance and the sample distance, to obtain a trained path processing model.

[0038] In one of the embodiments, the apparatus further comprises:

[0039] a returning module configured to return the spatial position of the target base station to the terminal, so that the terminal renders a real-time position of the target base station in a preset map based on the spatial position of the target base station.

[0040] In a third aspect, the present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0041] obtaining target fingerprint data collected by at least three terminals, the target fingerprint data comprising a cellular signal, a terminal identifier, a terminal position, and a distance from the terminal to a target area;

[0042] processing the target fingerprint data by using a pre-configured path processing model, to obtain a distance from each terminal to a target base station;

[0043] obtaining a spatial position of the target base station based on the terminal position of each terminal, the distance from each terminal to the target base station, and the distance from the terminal to the target area.

[0044] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0045] obtaining target fingerprint data collected by at least three terminals, the target fingerprint data comprising a cellular signal, a terminal identifier, a terminal position, and a distance from the terminal to a target area;

[0046] processing the target fingerprint data through a pre-configured path processing model to obtain distances of the terminals to the target base station;

[0047] processing based on the terminal positions of the terminals, the distances of the terminals to the target base station, and the distances of the terminals to the target area to obtain the spatial position of the target base station.

[0048] In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the following steps:

[0049] obtaining target fingerprint data collected by at least three terminals, the target fingerprint data comprising a cellular signal, a terminal identifier, a terminal position, and a distance of the terminal to a target area;

[0050] processing the target fingerprint data through a pre-configured path processing model to obtain distances of the terminals to the target base station;

[0051] processing based on the terminal positions of the terminals, the distances of the terminals to the target base station, and the distances of the terminals to the target area to obtain the spatial position of the target base station.

[0052] The base station positioning method, device, computer device, computer readable storage medium, and computer program product, wherein the method comprises: obtaining target fingerprint data collected by at least three terminals, the target fingerprint data comprising a cellular signal, a terminal identifier, a terminal position, and a distance of the terminal to a target area; processing the target fingerprint data through a pre-configured path processing model to obtain distances of the terminals to the target base station; and processing based on the terminal positions of the terminals, the distances of the terminals to the target base station, and the distances of the terminals to the target area to obtain the spatial position of the target base station. By using the method, the real-time spatial position of the target base station is positioned through the fingerprint data collected by multiple measurement terminals and a deep learning model, adaptive calibration of positioning is achieved, the positioning accuracy of the target base station is improved, base station positioning is achieved through a cloud server, terminal energy consumption is further reduced, and collaborative deployment and efficient use of communication resources are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0054] Figure 1An application environment diagram of the base station positioning method in an embodiment;

[0055] Figure 2 A flowchart of the base station positioning method in an embodiment;

[0056] Figure 3 A schematic diagram of a communication system in an embodiment;

[0057] Figure 4 A flowchart of the model training step in the base station positioning method in an embodiment;

[0058] Figure 5 A structural block diagram of the base station positioning device in an embodiment;

[0059] Figure 6 An internal structure diagram of the computer device in an embodiment. DETAILED DESCRIPTION

[0060] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0061] It should be noted that the terms "first", "second" and the like used in the present application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "include" and "have" and any variations thereof used in the present application are intended to cover non-exclusive inclusion. The term "multiple" used in the present application refers to two and more than two. The term "and / or" used in the present application refers to one of the options or any combination of multiple options.

[0062] The base station positioning method provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the server 200 communicates with multiple terminals 100 through the network. Among them, each terminal 100 can be a communication device deployed on the same plane, and each terminal can collect fingerprint data and upload the collected fingerprint data to the server 200; in this way, the server 200 can process the fingerprint data reported by each terminal 100 based on the received fingerprint data to obtain the base station positioning result in the current application environment, that is, to determine the spatial position coordinates of the base station. Among them, the terminal 100 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, unmanned aerial vehicles, low-altitude aircraft, Internet of Things devices, and portable wearable devices. The Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 200 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0063] In one exemplary embodiment, as Figure 2 shown, a base station positioning method is provided, and the method is applied to Figure 1 the server 200 in the above application environment for illustration, including:

[0064] Step 202, obtaining target fingerprint data collected by at least three terminals.

[0065] Among them, the target fingerprint data includes cellular signals, terminal identification, terminal position, and terminal-to-target area distance. The server can be a cloud server; the way each terminal collects fingerprint data is consistent; this embodiment does not limit the way the terminal collects fingerprint data. For example, the terminal can be installed with an application program for collecting cellular fingerprint signals, and the terminal can collect the fingerprint data corresponding to the terminal by starting the application program. The cellular signal can include the reference channel received power, base station identification, signal angle, and time difference of arrival when the terminal communicates with the target base station; the terminal identification can be the name information, device identification, or IMEI of the terminal, etc.; the terminal position can be the spatial position coordinates of the terminal, for example, the terminal can be a terminal deployed on a target plane, and the terminal position of terminal 1 can be (x1, y1, h1); wherein h1 represents the height of the target plane; the target area can be a first plane in parallel relationship with the target plane. For example, in actual application scenarios, the target area can be a ceiling, and the target plane can be the ground, etc.

[0066] Exemplarily, the terminal can collect fingerprint data corresponding to the terminal, and report the fingerprint data to the server. After receiving the fingerprint data uploaded by at least three terminals, the server can obtain target fingerprint data based on the fingerprint data reported by the three terminals.

[0067] Optionally, the server can issue a base station positioning request to at least three terminals. After receiving the base station positioning request, the terminal can collect fingerprint data corresponding to the terminal. The at least three terminals are measurement terminals located on the same plane for collecting fingerprint data.

[0068] In step 204, the target fingerprint data is processed by a pre-configured path processing model to obtain the distance of each terminal to the target base station.

[0069] The pre-configured path processing model can be one or more of a pre-trained neural network model, a deep learning model, a CNN model, and a LEE model. The path processing model is used to determine the distance of the measurement terminal to the target base station. The measurement terminal is a terminal for collecting fingerprint data. The target base station is a base station to be positioned, i.e., a base station whose real-time position is to be determined.

[0070] Exemplarily, after obtaining the target fingerprint data corresponding to each terminal, the server can input the target fingerprint data into the pre-configured path processing model, and process the target fingerprint data of the terminal by the model to obtain the predicted distance of the measurement terminal predicted by the model. The predicted distance represents the distance of the measurement terminal to the target base station.

[0071] In step 206, the spatial position of the target base station is obtained based on the terminal position of each terminal, the distance of each terminal to the target base station, and the distance of the terminal to the target area.

[0072] The terminals are located on the same plane, and the distance of the terminal to the target area is also the same, i.e., the distance of the terminal to the target area can be the vertical distance of the terminal to the target area. In the case of a target area being a ceiling, the distance of the terminal to the target area can be the vertical distance of the terminal to the ceiling. The spatial position of the target base station can be the real-time spatial position of the base station to be positioned, i.e., the three-dimensional position coordinates in a three-dimensional space.

[0073] Exemplarily, the server can calculate the spatial position of the target base station in a three-dimensional space based on the terminal position corresponding to each of the at least three terminals, the distance of the terminal to the base station to be positioned, and the distance of each terminal to the target area.

[0074] In the base station positioning method, target fingerprint data collected by at least three terminals is obtained, and the target fingerprint data includes cellular signals, terminal identifiers, terminal positions, and distances from the terminals to a target area. The target fingerprint data is processed by a preconfigured path processing model to obtain distances from the terminals to a target base station. The terminal positions of the terminals, the distances from the terminals to the target base station, and the distances from the terminals to the target area are processed to obtain a spatial position of the target base station. By using the method, the real-time spatial position of the target base station is positioned by using fingerprint data collected by multiple measurement terminals and a deep learning model, adaptive calibration of positioning is achieved, the positioning accuracy of the target base station is improved, base station positioning is achieved through a cloud server, terminal energy consumption is further reduced, and collaborative deployment and efficient use of communication resources are achieved.

[0075] In one embodiment, the specific implementation process of the step of "obtaining target fingerprint data collected by at least three terminals" can include:

[0076] The initial fingerprint data reported by each terminal is received. The target fingerprint data is obtained by preprocessing each initial fingerprint data, and the preprocessing includes data formatting processing or normalization processing.

[0077] The initial fingerprint data is fingerprint data directly collected by the terminal.

[0078] For example, for each terminal, the terminal can upload the collected initial fingerprint data to the server. After receiving the initial fingerprint data reported by each terminal, the server can perform data formatting processing and normalization processing on each initial fingerprint data to obtain the target fingerprint data.

[0079] In this embodiment, preprocessing of the collected fingerprint data can improve the usability, integrity, and accuracy of the data, and provide a better data basis for subsequent base station positioning.

[0080] In one embodiment, each terminal is located on a target plane. The at least three terminals can be terminal devices located on the same plane, for example, each terminal can be deployed on the target plane. The target area can be a first plane, i.e., a plane in parallel position relationship with the target plane. Optionally, the target plane can be the ground, and the first plane can be a ceiling parallel to the ground.

[0081] The specific implementation process of the step of "processing the terminal positions of the terminals, the distances from the terminals to the target base station, and the distances from the terminals to the target area to obtain a spatial position of the target base station" can include:

[0082] Based on the association model between the distance and the coordinate, the distance from each terminal to the target base station and the terminal position of each terminal are processed to obtain the projection position of the target base station on the target plane and the height of the target base station to the target plane. Based on the height of the target plane, the projection position of the target base station on the target plane and the height of the target base station to the target plane, the spatial position of the target base station is obtained.

[0083] The association model between the distance and the coordinate can be an association relationship between the distance of the position point where the terminal is located, the position point where the base station is located and the projection position point of the base station on the target plane where the terminal is located.

[0084] Exemplarily, the distance from each terminal to the target base station and the terminal position corresponding to at least three terminals are jointly solved and processed based on the preset association model between the distance and the coordinate to obtain the projection position of the target base station on the target plane and the height of the target base station to the target plane. In this way, the server can calculate the height position coordinate of the target base station based on the height of the target plane and the height of the target base station to the target plane, and obtain the spatial position of the target base station, i.e. the three-dimensional position coordinate of the target base station, based on the height position coordinate of the target base station and the projection position of the target base station on the target plane.

[0085] In this embodiment, the distance and the position of at least three terminals are jointly processed based on the association model between the distance and the coordinate, which can improve the accuracy of the obtained spatial position of the base station, realize the positioning calibration of the cellular base station and further improve the application range of the base station positioning method.

[0086] In one embodiment, the specific implementation process of the step of "obtaining the spatial position of the target base station based on the height of the target plane, the projection position of the target base station on the target plane and the height of the target base station to the target plane" can include:

[0087] The sum of the height of the target plane and the height of the target base station to the target plane is calculated to determine the sum value as the height coordinate. Based on the projection position of the target base station on the target plane and the height coordinate, the spatial position of the target base station is obtained.

[0088] Exemplarily, the projection position of the target base station on the target plane can include coordinate data of a projection position point of the target base station on the target plane, i.e., include first coordinate axis data, second coordinate axis data, and height coordinate axis data; the height of the target base station to the target plane can be a vertical distance between the target base station and the target plane. The server can perform superposition processing on the height of the target base station to the target plane based on the height coordinate axis data of the projection position point of the target base station on the target plane, obtain a sum, and determine the sum as the coordinate value of the height coordinate axis of the target base station in space. In this way, the server can determine the first coordinate axis data and the second coordinate axis data in the projection position point as the first coordinate axis data and the second coordinate axis data of the target base station in space, and obtain the spatial position of the target base station based thereon.

[0089] In one embodiment, the path processing model includes a path signal attenuation model and a path selection model. The base station positioning method further includes:

[0090] The path processing path signal attenuation model and the path selection model to be trained are used to process the sample fingerprint data reported by the terminal and the sample distance corresponding to the sample fingerprint data, to obtain a predicted distance. The path processing path signal attenuation model and the path selection model to be trained are trained based on the predicted distance and the sample distance, to obtain a trained path processing model.

[0091] The sample distance represents the distance between the terminal collecting the sample fingerprint data and the base station; and the predicted distance represents the distance between the terminal collecting the sample fingerprint data and the base station predicted by the path processing model.

[0092] The server can input the sample fingerprint data reported by the terminal and the sample fingerprint data into the path processing path signal attenuation model and the path selection model to be trained, calculate the predicted distance corresponding to the sample fingerprint data, and calculate the loss value between the predicted distance and the sample distance through a loss function. If it is determined that the loss value does not satisfy a preset training completion condition, the parameters of the path processing model are updated to obtain an updated model. The step of model training is re-executed based on the updated model until the preset training completion condition is satisfied, to obtain a trained path processing model. That is, a preconfigured path processing model is obtained.

[0093] In one example, if the server determines that the current number of training iterations has satisfied a preset number of training iteration threshold, the server can determine that the preset training completion condition has been satisfied at present; in another example, if the server determines that the loss value corresponding to the loss function calculated at present has satisfied a preset convergence condition, the server can determine that the preset training completion condition has been satisfied at present. The preset convergence condition can be that the loss value corresponding to the loss function has not changed, or that the loss value has reached a minimum loss value threshold, etc.

[0094] In the embodiment, the efficiency of base station positioning can be improved by training the path processing model in advance, and the accuracy and practicability of base station positioning can be further improved by implementing base station positioning in combination with the trained deep learning model.

[0095] In one embodiment, the base station positioning method further comprises:

[0096] The spatial position of the target base station is returned to the terminal, so that the terminal renders and displays the real-time position of the target base station in a preset map based on the spatial position of the target base station.

[0097] Exemplarily, the cloud server returns the calculated position of the target base station to the client, and the client renders the position of the target base station on an indoor map or a CAD map, so that the maintenance personnel can view the real position of the target base station in real time.

[0098] In the embodiment, the spatial position of the base station is displayed in real time, which facilitates the maintenance of the base station and realizes the visualization of the position of the base station.

[0099] In one embodiment, as shown in Figure 3 may be a schematic diagram of a current communication system, which includes a target base station and three measurement terminals 1. The target base station can be a base station to be positioned, and the measurement terminals 1 are used to collect fingerprint data corresponding to the terminals. The terminal positions of the measurement terminals are (x1, y1, h1), (x2, y2, h1) and (x3, y3, h1) respectively. The terminal positions are known data. The spatial position coordinates of the target base station are (x, y, h1+h), the coordinates of the projection position point of the target base station on a target plane can be (x, y, h1), the distances of the target base station to the measurement terminals can be d1, d2 and d3 respectively, and the height of the target base station to the projection position point can be h. The x, y, h, d1, d2 and d3 are unknown data.

[0100] As shown in Figure 4 may be a specific execution process of the model training process in the base station positioning method in another embodiment:

[0101] 3 terminals start to collect the cellular fingerprint, i.e. initial fingerprint data; the terminal reports the fingerprint data, including terminal id, plane coordinates, height, fingerprint data, i.e. the terminal reports the initial fingerprint data to the server; the cloud server data processing (cleaning, normalization, etc.); the cloud server stores the fingerprint data; the cloud server calls the model to generate the path attenuation model and the path selection model at regular intervals; if the fitting effect of the model is good, the model is generated and stored, and the generated model is redeployed in the cloud; if the fitting effect is not good, the model is trained through the corresponding training mode of machine learning, the generated model is stored, and the generated model is redeployed in the cloud.

[0102] In the following, the specific implementation steps of the above base station positioning method are described in detail in combination with a specific embodiment:

[0103] With the development of indoor and outdoor positioning technology, the operator indoor cellular base station is developing towards miniaturization and multi-function. In terms of function, the small base station integrates more capabilities, such as UTDOA positioning technology. In terms of miniaturization, the base station manufacturing process is improved, and the size of the base station is similar to that of an ordinary router, and the installation and deployment conditions become simple, only occupying a small indoor area. In actual production, large supermarkets and factories want to be beautiful, so the construction party deploys indoor small base stations in a concealed manner, which does not occupy the surface position and is installed on the ceiling as a whole. But this brings some problems to daily installation and upgrading, and the installation and maintenance personnel cannot accurately locate the accurate position of the indoor cellular small base station. On the other hand, the manually entered cellular base station position by the installation and maintenance personnel is often biased, which brings problems to the later positioning business development.

[0104] In view of the above problems, the base station positioning method provided in the embodiment is a method for accurately calculating the real-time spatial position of the cellular base station by detecting the cellular base station signal strength value through the client, which can be used for base station positioning in the current area in combination with the map of the current area. The current area is deployed with a base station, and the map of the current area can be an indoor map or a CAD map of the construction party of the indoor environment. The method provided in the embodiment can accurately calculate the accurate position of the specified cellular small station. At least 3 measuring terminals (the positions of the terminals are known, and each terminal is in the same horizontal plane a) are used to collect the cellular base station signal strength, and the signal strength value is reported to the cloud server. The cloud server is deployed with a path detection algorithm and a path attenuation model, and the distance from the terminal phone to the cellular base station can be calculated, and the height h from the ceiling to the measuring terminal can be measured, so as to establish an equation group to calculate the projection position of the target base station on the horizontal plane a, and finally obtain the accurate position of the target base station, realizing the high-accuracy base station position detection and correction.

[0105] Specifically, three terminal measurement devices of the same model (position known, tool measurement) are selected, the same app for collecting cellular fingerprint signals is installed on the terminal, and the three terminals are on the same horizontal plane, referred to as plane a. The app on the terminal is started at the same time, and the collected cellular signals, the current terminal ID, the current terminal position coordinates, the terminal-to-ceiling distance h, and the like are reported to the cloud server. After receiving the data, the cloud server pre-processes the data using data formatting, normalization, and the like, and then stores the pre-processed data on the local disk. A set of path signal attenuation algorithm model and path selection model are trained using the LEE model, and the trained model is deployed on the cloud server. The fingerprint data reported by the client is input into the model as an input parameter to make a prediction, and the distance from the measurement terminal to the target base station is calculated. Combined with the real-time position coordinates of the three terminals, the terminal-to-ceiling distance h, and the distance from the terminal to the target base station, the projection coordinates (x, y) of the cellular base station on plane a are calculated using the Pythagorean theorem. The cloud server returns the calculated position of the target base station to the client, and the client renders the position of the target base station on the indoor map or CAD map, so that the installation and maintenance personnel can view the real position of the target base station in real time.

[0106] In one embodiment, "processing the distance from each terminal to the target base station and the terminal position of each terminal based on the association model between the distance and the coordinates to obtain the projection position of the target base station on the target plane and the height of the target base station to the target plane" can also be determined by the following steps:

[0107] The distances from the at least three terminals to the base station obtained by the server through the path processing model can be d1, d2, and d3. The terminal positions of each measurement terminal are (x1, y1, h1), (x2, y2, h1), and (x3, y3, h1), respectively; each terminal position is known data. The spatial position coordinates of the target base station are (x, y, h1+h), the projection position coordinates of the target base station on the target plane can be (x, y, h1), the distances from the target base station to each terminal can be d1, d2, and d3, respectively, and the height of the target base station to the projection position point can be denoted as h, wherein x, y, h, d1, d2, and d3 are unknown data.

[0108] Then, for each terminal, the server can obtain the distance of each terminal to the target base station through the path processing model, i.e., can determine d1, d2 and d3; then the server can determine the position point of the terminal, the position point of the target base station, the projection position point of the target base station on the target plane, and the correlation model between the distance and the coordinates can be a correlation relationship based on the Pythagorean theorem between the distance between the position point where the terminal is located, the position point where the base station is located, and the projection position point of the base station on the target plane where the terminal is located. Then the correlation relationship between the above three terminals can be represented by the following public expression:

[0109] ;

[0110] In this way, the server can jointly solve the above correlation relationship to obtain the projection coordinates (x, y) of the target base station on the target plane a, and calculate based on the height h1 of the target plane to obtain the coordinates (x, y, h) of the target base station.

[0111] The base station positioning method provided in the embodiment realizes the scheme of cloud service adaptive generation of path attenuation model and path selection model through deep learning, performs real-time inference through the pre-configured path processing model to obtain the distance of the terminal to the target base station; specifically, three same type measurement terminals can be introduced, and the cellular signal strength, coordinate position and horizontal height and other data of the measurement terminals are synchronously collected as training samples to obtain the trained path processing model. Advanced data processing technology is used for pre-processing and feature extraction. Through sufficient utilization and processing of data, the stability and adaptability of the model are improved. Deep learning and algorithm are integrated with the cellular base station path attenuation, path recognition and positioning system, and the system is optimized, deep learning and algorithm are applied to the cellular base station position calibration field, and the overall structure of the system is optimized to improve the practicality and scalability of the calibration method.

[0112] The base station positioning method provided in the embodiment also realizes cloud adaptive calibration; the generated model is stored and deployed on the cloud server. After the model deployment is completed, the terminal can collect and report the cellular fingerprint data to the cloud server, the cloud server sends the data into the deployed neural network model to calculate the distance of the measurement terminal to the target base station, and then establishes an equation set through the known conditions such as the distance to obtain the accurate position of the cellular base station.

[0113] The base station positioning method provided in the embodiment can be combined with indoor and outdoor cellular fingerprint technology, and can provide an operator installation and maintenance personnel with a method capable of accurately obtaining a base station position. The cloud cellular fingerprint signal path attenuation model and path selection model scheme provided in the base station positioning method can be popularized to other wireless positioning schemes. The path processing model in the base station positioning method is a deep learning model, which can continuously learn in practice and continuously optimize the parameters of the model to adapt to path recognition and distance algorithms of different base stations. The deep learning model generated by the base station positioning method is deployed and run on a cloud server, and does not need to be downloaded to a local terminal, thereby avoiding occupying local terminal memory and computing resources and improving user experience.

[0114] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0115] Based on the same inventive concept, the embodiment of the present application also provides a base station positioning device for implementing the above-mentioned base station positioning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, and therefore the specific limitations in one or more base station positioning device embodiments provided below can refer to the limitations of the base station positioning method described above, which will not be described here again.

[0116] In one exemplary embodiment, as shown in Figure 5 a base station positioning device 500 is provided, applied to a server, comprising:

[0117] The acquisition module 502 is configured to acquire target fingerprint data collected by at least three terminals, the target fingerprint data including cellular signals, terminal identifiers, terminal positions, and distances from the terminals to a target area;

[0118] The first processing module 504 is configured to process the target fingerprint data by using a preconfigured path processing model to obtain distances from the terminals to a target base station;

[0119] The second processing module 506 is configured to perform processing based on the terminal positions of the terminals, distances from the terminals to the target base station, and distances from the terminals to the target area, to obtain the spatial position of the target base station.

[0120] In one of the embodiments, the obtaining module is specifically configured to:

[0121] receive the initial fingerprint data reported by each terminal;

[0122] perform preprocessing on each initial fingerprint data to obtain target fingerprint data, wherein the preprocessing includes data formatting processing or normalization processing.

[0123] In one of the embodiments, the target area is a target plane, and each terminal is located on the target plane; the second processing module is specifically configured to:

[0124] perform processing on the distances from the terminals to the target base station and the terminal positions of the terminals based on an association model between distance and coordinate, to obtain a projection position of the target base station on the target plane and a height of the target base station to the target plane;

[0125] obtain the spatial position of the target base station based on a height at which the target plane is located, the projection position of the target base station on the target plane, and the height of the target base station to the target plane.

[0126] In one of the embodiments, the second processing module is further specifically configured to:

[0127] calculate a sum of the height at which the target plane is located and the height of the target base station to the target plane, and determine the sum as a height coordinate;

[0128] obtain the spatial position of the target base station based on the projection position of the target base station on the target plane and the height coordinate.

[0129] In one of the embodiments, the path processing model includes a path signal attenuation model and a path selection model; the device further includes:

[0130] The third processing module is configured to perform processing on sample fingerprint data reported by a terminal and a sample distance corresponding to the sample fingerprint data by using the path signal attenuation model and the path selection model to be trained, to obtain a predicted distance.

[0131] The training module is configured to perform training on the path signal attenuation model and the path selection model to be trained based on the predicted distance and the sample distance, to obtain a trained path processing model.

[0132] In one of the embodiments, the apparatus further comprises:

[0133] a returning module, configured to return the spatial position of the target base station to the terminal, so that the terminal renders the real-time position of the target base station in a preset map based on the spatial position of the target base station.

[0134] The modules in the base station positioning apparatus can be implemented by software, hardware or a combination thereof. The modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0135] In one example embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 6 The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store positioning data of base stations. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a base station positioning method.

[0136] Those skilled in the art can understand that Figure 6 the structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0137] In one example embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the following steps:

[0138] acquire target fingerprint data collected by at least three terminals, the target fingerprint data including cellular signals, terminal identifiers, terminal positions and distances from the terminals to a target area;

[0139] processing the target fingerprint data based on a pre-configured path processing model to obtain distances from the terminals to the target base station;

[0140] processing the terminal positions of the terminals, the distances from the terminals to the target base station and the distances from the terminals to the target area to obtain the spatial position of the target base station.

[0141] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0142] receiving initial fingerprint data reported by the terminals;

[0143] pre-processing the initial fingerprint data to obtain target fingerprint data, the pre-processing including data formatting processing or normalization processing.

[0144] In one embodiment, the target area is a target plane, and the terminals are located on the target plane; the processor, when executing the computer program, further implements the following steps:

[0145] processing the distances from the terminals to the target base station and the terminal positions of the terminals based on an association model between distance and coordinate to obtain a projection position of the target base station on the target plane and a height of the target base station to the target plane;

[0146] obtaining the spatial position of the target base station based on a height of the target plane, the projection position of the target base station on the target plane and the height of the target base station to the target plane.

[0147] In one embodiment, the processor, when executing the computer program, further implements the following steps:

[0148] calculating a sum of the height of the target plane and the height of the target base station to the target plane, and determining the sum as a height coordinate;

[0149] obtaining the spatial position of the target base station based on the projection position of the target base station on the target plane and the height coordinate.

[0150] In one embodiment, the path processing model includes a path signal attenuation model and a path selection model; the processor, when executing the computer program, further implements the following steps:

[0151] processing sample fingerprint data reported by a terminal and a sample distance corresponding to the sample fingerprint data based on a to-be-trained path processing path signal attenuation model and a path selection model to obtain a predicted distance;

[0152] Based on the predicted distance and the sample distance, a path signal attenuation model and a path selection model are trained based on the to-be-trained path to obtain a trained path processing model.

[0153] In one embodiment, the processor also implements the following steps when executing the computer program:

[0154] The spatial position of the target base station is returned to the terminal, so that the terminal renders and displays the real-time position of the target base station in a preset map based on the spatial position of the target base station.

[0155] In one embodiment, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0156] In one embodiment, a computer program product is provided, and the computer program product includes a computer program. The computer program is executed by a processor to implement the steps in the above method embodiments.

[0157] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with relevant regulations.

[0158] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0159] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0160] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A base station positioning method, characterized in that, Applied to a server, the method includes: Acquire target fingerprint data collected by at least three terminals, wherein the target fingerprint data includes cellular signal, terminal identifier, terminal location, and distance from the terminal to the target area; The target fingerprint data is processed using a pre-configured path processing model to obtain the distance from each terminal to the target base station. The spatial location of the target base station is obtained by processing the terminal location of each terminal, the distance from each terminal to the target base station, and the distance from each terminal to the target area.

2. The method according to claim 1, characterized in that, The acquisition of target fingerprint data collected by at least three terminals includes: Receive initial fingerprint data reported by each of the terminals; The initial fingerprint data is preprocessed to obtain the target fingerprint data. The preprocessing includes data formatting or normalization.

3. The method according to claim 1, characterized in that, Each of the terminals is located on the target plane; the spatial location of the target base station is obtained by processing the terminal location, the distance from each terminal to the target base station, and the distance from each terminal to the target area, including: Based on the correlation model between distance and coordinates, the distance from each terminal to the target base station and the terminal position of each terminal are processed to obtain the projection position of the target base station on the target plane and the height of the target base station from the target plane. The spatial location of the target base station is obtained based on the height of the target plane, the projection position of the target base station on the target plane, and the height of the target base station from the target plane.

4. The method according to claim 3, characterized in that, The step of obtaining the spatial location of the target base station based on the height of the target plane, the projection position of the target base station on the target plane, and the height of the target base station from the target plane includes: Calculate the sum of the height of the target plane and the height from the target base station to the target plane, and determine the sum as a height coordinate; The spatial location of the target base station is obtained based on the projection position of the target base station on the target plane and the height coordinates.

5. The method according to claim 1, characterized in that, The path processing model includes a path signal attenuation model and a path selection model; the method further includes: The path signal attenuation model and path selection model to be trained are used to process the sample fingerprint data reported by the terminal and the sample distance corresponding to the sample fingerprint data to obtain the predicted distance. Based on the predicted distance and the sample distance, the path processing signal attenuation model and the path selection model to be trained are trained to obtain the trained path processing model.

6. The method according to claim 1, characterized in that, The method further includes: The spatial location of the target base station is returned to the terminal, so that the terminal can render a preset map based on the spatial location of the target base station and display the real-time location of the target base station.

7. A base station positioning device, characterized in that, Applied to a server, the device includes: The acquisition module is used to acquire target fingerprint data collected by at least three terminals. The target fingerprint data includes cellular signals, terminal identifiers, terminal locations, and the distance from the terminal to the target area. The first processing module is used to process the target fingerprint data through a pre-configured path processing model to obtain the distance from each terminal to the target base station; The second processing module is used to process the terminal location of each terminal, the distance from each terminal to the target base station, and the distance from each terminal to the target area to obtain the spatial location of the target base station.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to 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, it implements the steps of the method according to any one of claims 1 to 6.

Images