Communication base station investigation system, method and equipment and storage medium

Abstract

The invention discloses a communication base station investigation system and method, a storage medium and electronic equipment. The system comprises a multi-source sensing unit which is used for acquiring basic data of each candidate address at different sampling moments; the data processing unit is used for taking the basic data of each candidate address at different moments as input and inputting the basic data into a pre-trained deep learning model to obtain an attribute tag and prediction basic data of each candidate address; transmitting the predicted basic data of the initial candidate address of which the attribute label is the first label to an intelligent decision-making module; and the intelligent decision-making unit is used for inputting the predicted basic data of the initial candidate addresses and the historical site selection data into a pre-trained site selection evaluation model so as to screen out the optimal site selection of the communication base station from the initial candidate addresses.

Description

Technical Field

[0001] This application relates to the 6G field, and more particularly to a communication base station survey system, method, device, and storage medium. Background Technology

[0002] Communication base station site survey is a crucial step before base station construction. It requires investigation and evaluation of various factors such as terrain, transportation conditions, power supply, and surrounding environment, directly impacting network layout optimization, signal quality improvement, and construction cost control. Current technologies for communication base station site survey mainly rely on on-site survey methods, geographic information system (GIS) technology, remote sensing technology, and UAV aerial photography. While related patents cover functions such as BeiDou data transmission, connection handover optimization, and interference monitoring, there are significant shortcomings in technology integration and base station site selection.

[0003] Existing technologies fail to effectively integrate 6G communication technology, the BeiDou Navigation Satellite System, and the Internet of Things (IoT), resulting in limited accuracy in base station surveying and positioning, limited data collection dimensions, high data processing latency, and a lack of intelligent decision-making capabilities for base station site selection. Consequently, they cannot meet the demands of high-quality communication network construction. Therefore, there is an urgent need for a communication base station surveying system with high-precision positioning, real-time data processing, and intelligent decision-making capabilities. Summary of the Invention

[0004] This application provides a communication base station survey system, method, device, and storage medium to overcome the problems of limited positioning accuracy, single data collection dimension, high data processing delay, and insufficient intelligent decision-making capability in base station survey and site selection in the prior art.

[0005] Firstly, a communication base station survey system is provided, comprising: A multi-source sensing unit is used to acquire basic data of each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data. The data processing unit is used to input the basic data of each candidate address at different times as input to a pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and to transmit the prediction basic data of the initial candidate address with the attribute label as the first label to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station. The intelligent decision-making unit is used to input the predicted basic data of the initial candidate address and the historical site selection data into a pre-trained site selection evaluation model, so as to select the optimal site of the communication base station from the initial candidate addresses.

[0006] Optionally, the deep learning model includes convolutional neural networks (CNNs) and recurrent neural networks (RNNs); The CNN includes three convolutional layers and a max pooling layer connected in sequence. The three convolutional layers are connected by a ReLU activation function, and the last convolutional layer is connected to the max pooling layer. The RNN includes a bidirectional long short-term memory (LSTM) layer, a softmax layer, and a fully connected layer. The bidirectional LSTM layer serves as the input layer of the RNN and is connected to the max pooling layer. The softmax layer and the fully connected layer serve as the output layers of the RNN and are both connected to the bidirectional LSTM layer. The softmax layer is used to output the attribute labels of each candidate address. The fully connected layer is used to output the prediction base data for each candidate address.

[0007] Optionally, the multi-source sensing unit includes a positioning module, a multimodal sensor module, and an interference monitoring module; the positioning module is used to collect positioning data of the corresponding candidate address; the multimodal sensor module is used to collect environmental parameter data of the corresponding candidate address; and the interference monitoring module is used to collect network quality data of the corresponding candidate address.

[0008] Optionally, the multimodal sensor module includes a temperature sensor, a humidity sensor, and a light sensor; the temperature sensor is used to collect temperature data from the environmental parameter data of the corresponding candidate address; the humidity sensor is used to collect humidity data from the environmental parameter data of the corresponding candidate address; and the light sensor is used to collect light data from the environmental parameter data of the corresponding candidate address.

[0009] Optionally, the intelligent decision-making unit includes a storage module and a decision-making module; the storage module is used to store the prediction base data of the initial candidate address and historical site selection data; wherein, the historical site selection data includes the address of at least one historical communication base station and the corresponding base data of the historical communication base station; the decision-making module is used to input the prediction base data of the initial candidate address and the historical site selection data as input to a pre-trained site selection evaluation model, so as to select the optimal site of the communication base station from the initial candidate addresses.

[0010] Optionally, the site selection evaluation model is constructed based on a fusion of genetic algorithm and particle swarm optimization algorithm.

[0011] Optionally, the data processing unit is specifically used to: perform standardization processing on the basic data of each candidate address at different times to obtain standardized basic data of each candidate address at different times; the standardization processing includes data cleaning processing and normalization processing; The standardized basic data of each candidate address at different times are used as input to the pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and the prediction basic data of the initial candidate address with the attribute label as the first label is transmitted to the intelligent decision module.

[0012] Secondly, a method for surveying communication base stations is provided, including: Acquire basic data for each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data. The basic data of each candidate address at different times are used as input to a pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and the prediction basic data of the initial candidate address with the attribute label as the first label is transmitted to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station. The predicted basic data of the initial candidate address and the historical site selection data are used as inputs to a pre-trained site selection evaluation model to select the optimal site of the communication base station from the initial candidate addresses.

[0013] Thirdly, a computer-readable storage medium is provided, comprising: a computer program or instructions stored on the computer-readable storage medium, which, when the computer program or instructions are run on a computer, causes the method provided in the second aspect to be executed.

[0014] Fourthly, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the method provided in the second aspect above.

[0015] The communication base station survey system, method, storage medium, and electronic device according to the present invention have at least the following beneficial effects: by integrating a positioning module, centimeter-level high-precision positioning is achieved, improving the accuracy of communication base station site selection; by using a multimodal sensor module and an interference detection module, real-time acquisition and analysis of environmental parameters are achieved, improving the accuracy and real-time performance of data; by using a data processing unit, efficient data storage and management are achieved; and by using big data analysis and machine learning technology, intelligent decision-making and optimization of base station site selection and construction are achieved, improving the efficiency and quality of base station construction. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of a base station survey system applicable to this application; Figure 2 This is a schematic diagram of a base station survey method applicable to this application; Figure 3 This is a schematic diagram of the structure of an electronic device applicable to this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The specific operating methods in the method embodiments can also be applied to the device embodiments or system embodiments. In the description of this application, unless otherwise stated, "multiple" means two or more.

[0018] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0019] It is understood that the various numerical designations used in this application are merely for descriptive convenience and are not intended to limit the scope of this application. The order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic.

[0020] The terms "first," "second," "third," "fourth," and other various terminology (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] To facilitate understanding of the embodiments of this application, the terminology involved in the embodiments of this application will be briefly explained below.

[0022] Multimodal sensors: Integrate multiple sensors (such as temperature, humidity, and light) to collect environmental parameters in real time, support multi-dimensional data fusion and analysis, and improve the comprehensiveness and reliability of environmental perception.

[0023] Based on this, this application provides a communication base station survey system to overcome the shortcomings of existing communication base station survey methods, which make it difficult to achieve high-precision positioning and real-time acquisition, processing, and intelligent decision-making of environmental parameters.

[0024] Figure 1 This is a schematic diagram of a base station survey system applicable to this application; one embodiment of this application includes a communication base station survey system. For example... Figure 1 As shown, the system includes: a multi-source sensing unit 101, a data processing unit 102, and an intelligent decision-making unit 103.

[0025] The multi-source sensing unit 101 is used to acquire basic data of each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data; the data processing unit 102 is used to take the basic data of each candidate address at different times as input, input it into a pre-trained deep learning model, obtain the attribute labels and prediction basic data of each candidate address; and transmit the prediction basic data of the initial candidate address with the attribute label as the first label to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station; the intelligent decision unit 103 is used to take the prediction basic data of the initial candidate address and historical site selection data as input, input it into a pre-trained site selection evaluation model, so as to select the optimal site of the communication base station from the initial candidate addresses.

[0026] In one embodiment, the deep learning model includes a convolutional neural network (CNN) and a recurrent neural network (RNN). The CNN includes three convolutional layers and a max-pooling layer connected sequentially. The three convolutional layers are connected by a ReLU activation function, and the last of the three convolutional layers is connected to the max-pooling layer. The RNN includes a bidirectional long short-term memory (LSTM) layer, a softmax layer, and a fully connected layer. The bidirectional LSTM layer serves as the input layer of the RNN and is connected to the max-pooling layer. The softmax layer and the fully connected layer serve as the output layers of the RNN and are both connected to the bidirectional LSTM layer. The softmax layer is used to output the attribute labels of each candidate address. The fully connected layer is used to output the prediction base data for each candidate address.

[0027] In one embodiment, the multi-source sensing unit 101 includes a positioning module 101a, a multimodal sensor module 101b, and an interference monitoring module 101c; The positioning module 101a is used to collect positioning data for the corresponding candidate address. The positioning module 101a integrates a high-precision BeiDou positioning chip, supports multi-frequency positioning, and can achieve centimeter-level positioning accuracy. The positioning algorithm adopts a multi-frequency joint positioning algorithm. The multimodal sensor module 101b is used to collect environmental parameter data for the corresponding candidate address; the interference monitoring module 101c is used to collect network quality data for the corresponding candidate address.

[0028] In one embodiment, the multimodal sensor module 101b includes a temperature sensor, a humidity sensor, and a light sensor; the temperature sensor is used to collect temperature data from the environmental parameter data of the corresponding candidate address; the humidity sensor is used to collect humidity data from the environmental parameter data of the corresponding candidate address; and the light sensor is used to collect light data from the environmental parameter data of the corresponding candidate address.

[0029] In one embodiment, the intelligent decision-making unit 103 includes a storage module 103a and a decision-making module 103b; the storage module 103a is used to store the prediction base data of the initial candidate address and historical site selection data; wherein, the historical site selection data includes the address of at least one historical communication base station and the corresponding basic data of the historical communication base station; the decision-making module 103b is used to input the prediction base data of the initial candidate address and the historical site selection data as input to a pre-trained site selection evaluation model, so as to select the optimal site of the communication base station from the initial candidate addresses.

[0030] In one implementation, the site selection evaluation model is constructed based on a fusion of genetic algorithm and particle swarm optimization algorithm.

[0031] In one embodiment, the data processing unit 102 is specifically configured to: standardize the basic data of each candidate address at different times to obtain standardized basic data of each candidate address at different times; the standardization process includes data cleaning and normalization; input the standardized basic data of each candidate address at different times as input to a pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and transmit the prediction basic data of the initial candidate address with the attribute label as the first label to the intelligent decision-making module.

[0032] In one embodiment, this application also provides a method for surveying communication base stations, such as... Figure 2 As shown, the method includes steps S201, S202, and S203.

[0033] Step S201: Obtain basic data for each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data. The positioning data includes precise geographic data such as latitude, longitude, and altitude of candidate locations collected via a BeiDou positioning module (centimeter-level accuracy, multi-frequency joint positioning), addressing the fundamental question of "location suitability." The environmental parameter data includes environmental data of the candidate area collected by multimodal sensors (temperature, humidity, illumination, terrain sensors, etc.), while also covering key survey data such as transportation conditions and power supply accessibility. The network quality data includes signal coverage potential and interference source distribution data of the candidate area collected via 6G communication technology.

[0034] Step S202: The basic data of each candidate address at different times is used as input to the pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and the prediction basic data of the initial candidate address with the attribute label as the first label is transmitted to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station. The basic data undergoes real-time preprocessing: outliers are removed using the 3σ criterion, missing data is filled using linear interpolation, and then normalized using (data - mean) / standard deviation. The deep learning model extracts features through a CNN convolutional neural network → models the time series using LSTM → outputs the results. Online gradient descent (OGD) is used to fine-tune parameters every 7 days with 100,000 new data points to ensure prediction error ≤ ±2%. This rapidly identifies environmental adaptability (e.g., whether the terrain is suitable for base station construction, whether the power supply is stable) and reduces invalid data transmission.

[0035] Step S203: The predicted basic data of the initial candidate address and the historical site selection data are used as inputs to the pre-trained site selection evaluation model in order to select the optimal site of the communication base station from the initial candidate addresses.

[0036] The site selection evaluation model is constructed based on a fusion of genetic algorithm and particle swarm optimization algorithm.

[0037] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0038] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0039] The electronic device provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. The description of the electronic device embodiments corresponds to the description of the method embodiments. Therefore, for content not described in detail, please refer to the method embodiments above. For the sake of brevity, some content will not be repeated.

[0040] Figure 3 This is a schematic diagram of the structure of an electronic device applicable to this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0041] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0042] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0043] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a communication detection device at the logical level. The processor executes the program stored in memory and specifically performs the following operations: Acquire basic data for each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data. The basic data of each candidate address at different times are used as input to a pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and the prediction basic data of the initial candidate address with the attribute label as the first label is transmitted to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station. The predicted basic data of the initial candidate address and the historical site selection data are used as inputs to a pre-trained site selection evaluation model to select the optimal site of the communication base station from the initial candidate addresses.

[0044] The above is as stated in this application. Figure 3The methods executed by the electronic devices disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0045] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

Claims

1. A communication base station survey system, characterized in that, include: A multi-source sensing unit is used to acquire basic data of each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data. The data processing unit is used to input the basic data of each candidate address at different times as input to a pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and to transmit the prediction basic data of the initial candidate address with the attribute label as the first label to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station. The intelligent decision-making unit is used to input the predicted basic data of the initial candidate address and the historical site selection data into a pre-trained site selection evaluation model, so as to select the optimal site of the communication base station from the initial candidate addresses.

2. The system according to claim 1, characterized in that, The deep learning model includes convolutional neural networks (CNN) and recurrent neural networks (RNN); The CNN includes three convolutional layers and a max pooling layer connected in sequence. The three convolutional layers are connected by a ReLU activation function, and the last convolutional layer is connected to the max pooling layer. The RNN includes a bidirectional long short-term memory (LSTM) layer, a softmax layer, and a fully connected layer. The bidirectional LSTM layer serves as the input layer of the RNN and is connected to the max pooling layer. The softmax layer and the fully connected layer serve as the output layers of the RNN and are both connected to the bidirectional LSTM layer. The softmax layer is used to output the attribute labels of each candidate address. The fully connected layer is used to output the prediction base data for each candidate address.

3. The system according to claim 1, characterized in that, The multi-source sensing unit includes a positioning module, a multimodal sensor module, and an interference monitoring module; The positioning module is used to collect positioning data of the corresponding candidate addresses; The multimodal sensor module is used to collect environmental parameter data for the corresponding candidate addresses; The interference monitoring module is used to collect network quality data for the corresponding candidate addresses.

4. The system according to claim 3, characterized in that, The multimodal sensor module includes a temperature sensor, a humidity sensor, and a light sensor; The temperature sensor is used to collect temperature data from the environmental parameter data of the corresponding candidate address. The humidity sensor is used to collect humidity data from the environmental parameter data of the corresponding candidate address. The light sensor is used to collect light data from the environmental parameter data of the corresponding candidate address.

5. The system according to any one of claims 1 to 4, characterized in that, The intelligent decision-making unit includes a storage module and a decision-making module; The storage module is used to store the prediction base data of the initial candidate address and the historical addressing data; wherein, the historical addressing data includes the address of at least one historical communication base station and the corresponding base data of the historical communication base station; The decision module is used to input the predicted basic data of the initial candidate address and the historical site selection data into a pre-trained site selection evaluation model, so as to select the optimal site of the communication base station from the initial candidate addresses.

6. The system according to claim 5, characterized in that, The site selection evaluation model is constructed based on a fusion of genetic algorithm and particle swarm optimization algorithm.

7. The system according to claim 1, characterized in that, The data processing unit is specifically used for: The basic data of each candidate address at different times are standardized to obtain the standardized basic data of each candidate address at different times; the standardization process includes data cleaning and normalization. The standardized basic data of each candidate address at different times are used as input to the pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and the prediction basic data of the initial candidate address with the attribute label as the first label is transmitted to the intelligent decision module.

8. A method for surveying communication base stations, characterized in that, include: Acquire basic data for each candidate address at different sampling times; the basic data includes at least location data, environmental parameter data, and network quality data. The basic data of each candidate address at different times are used as input to a pre-trained deep learning model to obtain the attribute labels and prediction basic data of each candidate address; and the prediction basic data of the initial candidate address with the attribute label as the first label is transmitted to the intelligent decision module; the attribute label includes a first label and a second label; the first label is used to indicate that the corresponding candidate address can be used as the initial candidate address of the communication base station, and the second label is used to indicate that the corresponding candidate address cannot be used as the initial candidate address of the communication base station. The predicted basic data of the initial candidate address and the historical site selection data are used as inputs to a pre-trained site selection evaluation model to select the optimal site of the communication base station from the initial candidate addresses.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed on a computer, cause the method of claim 8 to be performed.

10. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, causes the at least one processor to perform the method as described in claim 8.

Images