A base station survey method and system based on edge computing

Abstract

The present application provides a base station survey method and system based on edge computing. Among them, one or more target areas are selected from the base station network coverage area, and the target area includes at least one candidate base station location; at least one edge computing device is deployed in the target area to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to the cloud server; coordinate data sharing and collaboration between edge computing devices, and build an environmental parameter map of the target area in combination with the instant feedback information; based on the environmental parameter map, combined with historical base station data and user behavior patterns, generate a site selection recommendation report for the candidate base station location. The present application comprehensively determines the candidate base station location through environmental parameter maps, historical base station data, and user behavior pattern analysis, thereby improving the site selection quality and efficiency.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of base station survey, and in particular to a base station survey method and system based on edge computing. Background Art

[0002] With the rapid development of mobile communication technology, the requirements for network coverage and service quality are constantly increasing, and the reasonable layout of base stations has become one of the important issues facing operators. In order to ensure the efficient operation of the communication network and the continuous improvement of user experience, base station survey has become a key link in the construction of communication infrastructure.

[0003] Currently, the site selection of base stations mainly relies on manual on-site surveys and empirical judgment, supplemented by some automated tools. These tools usually require a large amount of on-site data to be uploaded to a central server for processing, and then analyzed and decided by a team of experts.

[0004] Since data needs to be uploaded from edge devices to the cloud for processing and then the results are returned to on-site staff, this process may cause long delays, affecting the timeliness of decision-making, resulting in poor site selection quality and low site selection efficiency. Summary of the invention

[0005] The embodiments of the present application provide a base station survey method and system based on edge computing to solve the problems of poor site selection quality and low site selection efficiency in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a base station survey method based on edge computing, which is applied to a cloud server, including:

[0007] Select one or more target areas from the base station network coverage area, wherein the target area includes at least one candidate base station location;

[0008] Deploy at least one edge computing device in the target area to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to the cloud server, wherein the instant feedback information includes signal coverage, potential interference source location, and dynamic changes of the surrounding environment;

[0009] Coordinate data sharing and collaboration between the edge computing devices, and construct an environmental parameter map of the target area in combination with the instant feedback information, wherein the environmental parameter map reflects the signal coverage and interference distribution of the entire target area;

[0010] Based on the environmental parameter map, combined with historical base station data and user behavior patterns, a site selection recommendation report for candidate base station locations is generated, and the site selection recommendation report includes an optimal installation location and optimization suggestions.

[0011] Further, the coordinating data sharing and collaboration between the edge computing devices includes:

[0012] Using a security protocol, encrypting the communication link between the edge computing devices to establish a secure communication link;

[0013] On the basis of establishing a secure communication link, according to the data update frequency of the edge computing device, the edge computing device is synchronized to realize real-time exchange and synchronization of environmental parameter data between the edge computing devices;

[0014] The method further comprises:

[0015] A conflict detection algorithm is used to process data conflicts that occur during data sharing among the edge computing devices to ensure data consistency among the edge computing devices.

[0016] Furthermore, the step of constructing an environmental parameter map of the target area in combination with the instant feedback information includes:

[0017] Using a data fusion algorithm, the instant feedback information is fused with the existing environmental parameter data to obtain an environmental parameter map;

[0018] According to the latest instant feedback information, the environmental parameter map is updated in real time to obtain a dynamically updated environmental parameter map.

[0019] Furthermore, the instant feedback information is fused with the existing environmental parameter data using a data fusion algorithm to obtain an environmental parameter map, including:

[0020] Generate a preliminary environmental parameter map based on the existing environmental parameter data;

[0021] On the preliminary environmental parameter map, according to the potential interference source data in the instant feedback information, perform interference source position marking and positioning processing;

[0022] According to the signal coverage in the instant feedback information, performing signal coverage mapping processing on the preliminary environmental parameter map to generate a signal coverage heat map;

[0023] Based on the dynamic change data of the surrounding environment in the instant feedback information, dynamically update the preliminary environmental parameter map;

[0024] Generates environmental parameter maps containing interference source location information, signal coverage heat maps, and dynamically updated data.

[0025] Furthermore, the generating of a site selection recommendation report for candidate base station locations based on the environmental parameter map in combination with historical base station data and user behavior patterns includes:

[0026] Retrieving historical base station data of existing base stations related to the target area from a cloud database, including signal strength, coverage, and user access volume;

[0027] Analyze user behavior patterns in the target area, including user activity time, activity location, and communication needs;

[0028] According to the environmental parameter map, the historical base station data and the user behavior pattern, evaluating the suitability score of the candidate base station location to obtain an evaluation result;

[0029] The evaluation results are sorted and a site selection recommendation report containing the best installation location and optimization suggestions is generated based on the sorting results.

[0030] Further, the suitability score of the candidate base station location is evaluated according to the environmental parameter map, the historical base station data and the user behavior pattern to obtain an evaluation result, including:

[0031] Based on the historical base station data, user behavior patterns, and environmental parameter maps, a comprehensive evaluation model for evaluating the suitability of base station installation locations is constructed;

[0032] The comprehensive evaluation model is trained using a machine learning algorithm so that the comprehensive evaluation model can accurately predict the signal coverage quality, user access efficiency, and overall network performance of the candidate base station location;

[0033] Applying the trained comprehensive evaluation model to each candidate base station location to calculate a suitability score for each candidate base station location, wherein the suitability score reflects the expected service quality when the base station is installed at the corresponding location;

[0034] The suitability score of each candidate base station location is calculated using the following formula:

[0035] ;

[0036] in, Indicates the location of the candidate base station The suitability score of Indicates the location of the candidate base station The exponential form of the environmental parameter spectrum score; Indicates the location of the candidate base station The exponential form of the historical base station data score; Indicates the location of the candidate base station The index form of user behavior pattern score; are exponential coefficients, which are used to adjust the influence of environmental parameter map scores, historical base station data scores, and user behavior pattern scores; are weight coefficients, representing the relative importance of the environmental parameter map score, historical base station data score, and user behavior pattern score in the final suitability score;

[0037] Find the optimal weights by using the least squares method : , is the candidate base station location, is the actual performance score of the candidate base station location;

[0038] Environmental parameter map score:

[0039] , is the candidate base station location The distance to the nearest source of interference; It's location The degree to which the surrounding environment is dynamically changing; is the candidate base station location Coverage ratio on the signal coverage heat map, value range is the attenuation coefficient;

[0040] Historical base station data scores:

[0041] , is the candidate base station location Average signal strength; is the strongest signal strength; is the candidate base station location coverage; is the maximum coverage; is the candidate base station location The number of users accessing is the maximum number of user accesses; is the coefficient of each score of historical base station data;

[0042] User behavior pattern score:

[0043] , is the candidate base station location The proportion of active time of users; is the total active time; is the candidate base station location Percentage of user activity locations; It is the general activity location; is the candidate base station location The proportion of communication needs; is the total communication demand; It is the coefficient of each score of the user behavior pattern.

[0044] Furthermore, the method further comprises:

[0045] Based on the site selection recommendation report and the corresponding instant feedback information, specific guidance information is provided to the on-site survey personnel, and the specific guidance information includes optimal path planning, on-site equipment deployment suggestions and interference source avoidance solutions to optimize the base station installation process.

[0046] In a second aspect, an embodiment of the present application provides a base station survey system based on edge computing, including:

[0047] A selection module, configured to select one or more target areas from the base station network coverage area, wherein the target area includes at least one candidate base station location;

[0048] A deployment module, configured to deploy at least one edge computing device in the target area, so as to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to a cloud service end, wherein the instant feedback information includes signal coverage, location of potential interference sources, and dynamic changes of the surrounding environment;

[0049] A construction module is used to coordinate data sharing and collaboration between the edge computing devices, and to construct an environmental parameter map of the target area in combination with the instant feedback information, wherein the environmental parameter map reflects the signal coverage and interference distribution of the entire target area;

[0050] A generation module is used to generate a site selection recommendation report for candidate base station locations based on the environmental parameter map, combined with historical base station data and user behavior patterns, wherein the site selection recommendation report includes an optimal installation location and optimization suggestions.

[0051] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a base station survey method based on edge computing as described in the first aspect above.

[0052] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a base station survey method based on edge computing as described in the first aspect.

[0053] In an embodiment of the present application, one or more target areas are selected from the base station network coverage area, and the target area includes at least one candidate base station location; at least one edge computing device is deployed in the target area to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to the cloud server; coordinate data sharing and collaboration between edge computing devices, and build an environmental parameter map of the target area in combination with the instant feedback information; based on the environmental parameter map, combined with historical base station data and user behavior patterns, generate a site selection recommendation report for the candidate base station location. The present application comprehensively determines the candidate base station location through environmental parameter maps, historical base station data, and user behavior pattern analysis, thereby improving the site selection quality and efficiency.

[0054] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 A flow chart of a base station survey method based on edge computing provided in an embodiment of the present application;

[0057] Figure 2 A schematic diagram of the structure of a base station survey system based on edge computing provided in an embodiment of the present application;

[0058] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0060] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0062] Figure 1 A flow chart of a base station survey method based on edge computing is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes:

[0063] 101. Select one or more target areas from a base station network coverage area, wherein the target area includes at least one candidate base station location;

[0064] In this step, the goal is to identify the network coverage areas that need to be optimized. These areas may be places with poor signal quality or high user density, and are selected by analyzing existing network performance indicators (such as signal strength, call drop rate, etc.).

[0065] In the embodiment of the present application, for example, a commercial block is selected as the target area in the city center because the area is densely populated and has high requirements for network quality. By analyzing the network performance report provided by the operator, it is found that there are many weak signal areas in the area, so it is decided to use it as the optimization object.

[0066] 102. Deploy at least one edge computing device in the target area to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to a cloud server, wherein the instant feedback information includes signal coverage, potential interference source locations, and dynamic changes of the surrounding environment;

[0067] In this step, edge computing devices will be installed in the selected target area. These devices are responsible for collecting surrounding environmental parameters (such as electromagnetic field strength, noise level, etc.) and performing preliminary processing on them in order to respond quickly and reduce data transmission delays.

[0068] In the embodiment of the present application, it is assumed that several small edge computing nodes are installed in the commercial block selected in the previous step, and each node is equipped with a sensor to monitor the electromagnetic environment. When a sudden drop in signal strength in a specific area is detected, the edge computing device can quickly identify the possible cause (such as a new interference source) and send this information to the cloud platform in real time.

[0069] 103. Coordinate data sharing and collaboration between the edge computing devices, and construct an environmental parameter map of the target area in combination with the instant feedback information, wherein the environmental parameter map reflects the signal coverage and interference distribution of the entire target area;

[0070] In this step, all edge computing devices share data and process it through algorithms to form a map that comprehensively reflects the signal coverage and interference conditions in the target area. This helps to more intuitively understand the communication environment of the entire area.

[0071] In the embodiment of the present application, using the data collected in the previous step, the development team can use GIS technology to create a detailed electronic map, which not only shows the signal strength of each location, but also marks the location of the main interference source and its impact range. In addition, the map can be dynamically updated to reflect the latest impact of environmental changes.

[0072] Optionally, the "coordinating data sharing and collaboration between the edge computing devices" in step 103 includes: using a security protocol to encrypt the communication link between the edge computing devices to establish a secure communication link; based on the establishment of the secure communication link, according to the data update frequency of the edge computing device, the edge computing device is synchronized to achieve real-time exchange and synchronization of environmental parameter data between the edge computing devices; the method also includes: using a conflict detection algorithm to handle data conflicts that occur during the data sharing process of the edge computing devices to ensure data consistency between the edge computing devices.

[0073] Security protocol: refers to a series of rules and technologies used to protect the security of data transmission, such as TLS / SSL, which can prevent data from being eavesdropped or tampered with during transmission.

[0074] Data update frequency: refers to the frequency at which edge computing devices send the latest data to other devices regularly or irregularly based on their own working status or changes in the external environment.

[0075] Data synchronization: refers to the process of keeping the same type of data on different devices consistent, ensuring that all relevant parties have the latest information.

[0076] Conflict detection algorithm: An algorithm used to identify and resolve problems that may arise when multiple users or systems attempt to modify the same resource at the same time.

[0077] First, the communication links between edge computing devices are encrypted using security protocols to ensure the security of data during transmission and avoid unauthorized access or data leakage. Secondly, based on the data update frequency of each edge computing device, the synchronization strategy is dynamically adjusted to ensure that data can be transmitted timely and accurately among all relevant devices. Finally, by deploying a conflict detection algorithm, conflicts caused by multiple devices updating the same data at the same time are automatically discovered and resolved to maintain data consistency.

[0078] In the embodiment of the present application, it is assumed that in a smart city project, multiple edge computing devices (such as smart cameras and environmental monitoring stations) are distributed in different locations in the city, responsible for collecting information such as traffic flow and air quality. In order to improve data processing efficiency and service quality, these devices need to frequently exchange and synchronize information.

[0079] All devices are configured with the TLS1.3 protocol, and authentication and encryption are performed before each data transmission to ensure that only legitimate recipients can decrypt and read the data. Secondly, considering the differences in data update requirements of different devices (for example, smart cameras generate new data every second, while environmental monitoring stations update once an hour), the system adopts an adaptive synchronization mechanism, which dynamically adjusts the synchronization cycle according to the actual update frequency of each device, which not only ensures the freshness of the data, but also reduces unnecessary network burden. Furthermore, in a routine operation, two adjacent environmental monitoring stations uploaded new measurements of PM2.5 concentrations at the same location almost at the same time. The system's built-in conflict detection algorithm quickly identified this situation and automatically selected the correct data version based on preset rules (such as data with newer timestamps takes precedence), avoiding analysis errors caused by inconsistent data.

[0080] By implementing the above solution, not only the data security between edge computing devices is strengthened and the efficiency and accuracy of data synchronization are improved, but also the data conflict problem is effectively solved, providing a solid foundation for building accurate environmental parameter maps, thereby improving the intelligence level and service quality of smart city management.

[0081] Optionally, the "combining the instant feedback information to construct an environmental parameter map of the target area" in step 103 includes: using a data fusion algorithm to fuse the instant feedback information with existing environmental parameter data to obtain an environmental parameter map; and updating the environmental parameter map in real time according to the latest instant feedback information to obtain a dynamically updated environmental parameter map.

[0082] Data fusion algorithm: A method of combining information from multiple sensors or data sources with the goal of producing results that are more accurate and reliable than any single source.

[0083] Instant feedback information: refers to the data obtained in real time from various sensors or devices, which reflects the latest status of the current environment.

[0084] Environmental parameter map: A visualization tool used to show the spatial distribution of various environmental parameters (such as signal strength, interference distribution, etc.) in a specific area.

[0085] First, the data fusion algorithm is used to fuse the instant feedback information with the existing environmental parameter data to generate the initial environmental parameter map. Secondly, the environmental parameter map is updated in real time based on the latest instant feedback information to ensure that the map always reflects the latest environmental status.

[0086] In the embodiment of the present application, it is assumed that in a smart city project, an environmental parameter map reflecting the signal coverage and interference distribution of the city needs to be constructed. Multiple edge computing devices are deployed in the project, including signal towers, environmental monitoring stations, and mobile devices (such as smartphones).

[0087] First, historical data obtained from signal towers and environmental monitoring stations, including signal strength, interference level, etc. Second, signal strength and interference data uploaded in real time from mobile devices (such as smartphones). The Kalman filter is then used to fuse the above two types of data. The Kalman filter is a recursive least squares estimation method that can effectively handle noise and uncertainty.

[0088] Assume that the existing data and immediate feedback information are expressed as and , then the fused data It can be expressed as:

[0089] ;

[0090] in, is the Kalman gain, which can be adjusted according to actual conditions.

[0091] Further, the mobile device uploads the signal strength and interference data every 5 minutes. Whenever new instant feedback information is received, the system will immediately update the environmental parameter map using the above data fusion algorithm.

[0092] Suppose at a certain moment, the system receives a new set of immediate feedback information , then the updated environmental parameter map It can be expressed as:

[0093] ;

[0094] By implementing the above solution, the accuracy and real-time performance of the environmental parameter map can be significantly improved. Specifically, through real-time update processing, the environmental parameter map can quickly reflect the latest environmental changes and provide timely support for decision-making. And the data fusion algorithm can effectively integrate information from multiple data sources, reduce noise and uncertainty, and improve the accuracy of the map. Secondly, the solution can flexibly respond to different application scenarios, whether it is fixed equipment or mobile equipment, and can effectively integrate the instant feedback information it provides.

[0095] 104. Based on the environmental parameter map, combined with historical base station data and user behavior patterns, generate a site selection recommendation report for candidate base station locations, wherein the site selection recommendation report includes an optimal installation location and optimization suggestions.

[0096] In this step, specific recommendations are made for adding or adjusting base station locations based on the information obtained in the first three steps, combined with historical data and expected user demand. These recommendations are intended to improve overall network efficiency and service quality.

[0097] In the embodiment of this application, based on the environmental parameter map constructed above, analysts found that there is an obvious signal blind spot in the northwest corner of the commercial district. Considering the population growth trend in the area in the next few years, it is recommended to add a small base station here. At the same time, for some existing base stations, power adjustment and antenna direction optimization are proposed to improve the user experience in their service area.

[0098] Optionally, in step 104, "generating a site selection recommendation report for candidate base station locations based on the environmental parameter map, combined with historical base station data and user behavior patterns" includes: retrieving historical base station data of existing base stations related to the target area from a cloud database, including signal strength, coverage, and user access volume; analyzing user behavior patterns in the target area, including user activity time, activity location, and communication needs; evaluating the suitability scores of candidate base station locations based on the environmental parameter map, the historical base station data, and the user behavior patterns to obtain evaluation results; sorting according to the evaluation results, and generating a site selection recommendation report containing the best installation location and optimization suggestions based on the sorting results.

[0099] Environmental parameter map: refers to a map of information such as topography, building density, and population distribution of the target area obtained through technical means such as geographic information system (GIS).

[0100] Historical base station data: including but not limited to indicators such as signal strength, coverage, and user access volume, reflecting the actual operating conditions of the base station.

[0101] User behavior patterns: Through data analysis of user usage habits, we can understand the user's activity time, activity location and communication needs.

[0102] Suitability score: A quantitative evaluation of candidate base station locations after taking into account factors such as environmental parameters, historical base station performance, and user needs.

[0103] First, collect relevant data of all active base stations in the target area from the cloud database, such as signal strength, coverage, user access volume, etc. Secondly, use big data analysis technology to explore the activity patterns of users in the target area, including peak hours, popular locations, etc. Then combine the environmental parameter map with historical base station data and user behavior patterns, and use a weighted scoring model to calculate the suitability score of each candidate location. Finally, sort all candidate locations according to the suitability score, select the highest-scoring locations as the best installation points, and make corresponding optimization suggestions.

[0104] In the embodiment of this application, it is assumed that a city plans to add 5G base stations to improve network coverage and service quality in the downtown area. The project team first collected data such as signal strength, coverage, and user access volume of all base stations in the area in the past year from the cloud database. Then, through data analysis, it was found that 5 pm to 9 pm every day is the peak period of user traffic, and most users are concentrated near the commercial street.

[0105] The project team used GIS technology to create an environmental parameter map of the area, combined with historical base station data and user behavior patterns, and used the following formula to calculate the suitability score of each candidate location:

[0106] Suitability score Environmental adaptability Signal coverage User demand satisfaction

[0107] in, and Represent the weight values ​​of environmental adaptability, signal coverage capability and user demand satisfaction, and adjust according to actual conditions. For example, assuming that the weights of environmental adaptability, signal coverage capability and user demand satisfaction are and 0.3, for a candidate location, its environmental adaptability score is 80, signal coverage score is 70, and user demand satisfaction score is 90, then the suitability score of the location is:

[0108] Suitability score ;

[0109] In this way, the project team can evaluate multiple candidate locations and ultimately select the highest-scoring locations as the best installation points for new base stations. In addition, the report will make specific optimization recommendations for each selected location, such as adjusting the antenna angle to expand coverage or adding frequency bands to increase data transmission rates.

[0110] Optionally, the data fusion algorithm is used to fuse the instant feedback information with existing environmental parameter data to obtain an environmental parameter map, including: generating a preliminary environmental parameter map based on the existing environmental parameter data; marking and locating the interference source on the preliminary environmental parameter map based on the potential interference source data in the instant feedback information; performing signal coverage range drawing on the preliminary environmental parameter map based on the signal coverage range in the instant feedback information to generate a signal coverage heat map; dynamically updating the preliminary environmental parameter map based on the surrounding environment dynamic change data in the instant feedback information; generating an environmental parameter map containing interference source location information, a signal coverage heat map and dynamically updated data.

[0111] Data fusion algorithm: A method of combining information from multiple sensors or data sources with the goal of producing results that are more accurate and reliable than any single source.

[0112] Instant feedback information: refers to the data obtained in real time from various sensors or devices, which reflects the latest status of the current environment.

[0113] Environmental parameter map: A visualization tool used to show the spatial distribution of various environmental parameters (such as signal strength, interference distribution, etc.) in a specific area.

[0114] Potential interference source data: refers to the location and strength information of sources that may cause interference to signal transmission.

[0115] Signal coverage heat map: A visualization tool that shows the distribution of signal coverage and strength in a specific area.

[0116] Dynamic changes in the surrounding environment: refers to factors in the environment that change over time, such as changes in the location of mobile devices, the addition or removal of buildings, etc.

[0117] First, based on the existing environmental parameter data, a preliminary environmental parameter map is generated. Secondly, on the preliminary environmental parameter map, the interference source position is marked and located according to the potential interference source data in the instant feedback information. Further, based on the signal coverage range in the instant feedback information, the signal coverage range is drawn on the preliminary environmental parameter map to generate a signal coverage heat map. Based on the dynamic change data of the surrounding environment in the instant feedback information, the preliminary environmental parameter map is dynamically updated. Finally, a final environmental parameter map containing interference source location information, signal coverage heat map and dynamically updated data is generated.

[0118] In the embodiment of the present application, it is assumed that in an urban area, an environmental parameter map reflecting signal coverage and interference distribution needs to be constructed. Multiple edge computing devices are deployed in the project, including signal towers, environmental monitoring stations, and mobile devices (such as smartphones).

[0119] First, historical data is obtained from signal towers and environmental monitoring stations, including signal strength, interference level, etc. These historical data are used to generate preliminary environmental parameter maps to show the basic situation of signal coverage and interference distribution. Secondly, potential interference source data uploaded in real time from mobile devices (such as smartphones), including the location and strength of the interference source. On the preliminary environmental parameter map, position marking and positioning processing are performed based on these interference source data. For example, a certain interference source is located at coordinates (100,200) and the interference strength is 80dBm. Further, signal coverage data uploaded in real time from mobile devices, including signal strength and coverage. On the preliminary environmental parameter map, drawing processing is performed based on these signal coverage data to generate a signal coverage heat map. For example, the signal strength at a certain location (150,250) is 75dBm and the coverage range is 300 meters. Secondly, the dynamic change data of the surrounding environment uploaded in real time from mobile devices, such as changes in the location of mobile devices, new buildings, etc. Based on these dynamic change data, the preliminary environmental parameter map is updated in real time. For example, a mobile device moves from position (100,100) to (200,200), and its signal coverage and interference information need to be updated. Finally, a final environmental parameter map containing interference source location information, signal coverage heat map, and dynamically updated data is generated.

[0120] By implementing the above solution, the accuracy and real-time performance of the environmental parameter map can be significantly improved. Through real-time update processing, the environmental parameter map can quickly reflect the latest environmental changes and provide timely support for decision-making. And by using data fusion algorithms, combining instant feedback information and existing environmental parameter data, the generated map is more accurate and reliable. In addition, the map not only shows the basic situation of signal coverage and interference distribution, but also includes interference source location information and dynamically updated data, providing more comprehensive information support. Finally, the solution can flexibly respond to different application scenarios, whether it is fixed equipment or mobile equipment, and can effectively integrate the instant feedback information it provides.

[0121] Optionally, the suitability scores of candidate base station locations are evaluated according to the environmental parameter map, the historical base station data and the user behavior patterns to obtain evaluation results, including: constructing a comprehensive evaluation model for evaluating the suitability of base station installation locations based on the historical base station data, user behavior patterns and environmental parameter maps; training the comprehensive evaluation model using a machine learning algorithm so that the comprehensive evaluation model can accurately predict the signal coverage quality, user access efficiency and overall network performance of the candidate base station locations; applying the trained comprehensive evaluation model to each candidate base station location to calculate the suitability score of each candidate base station location, wherein the suitability score reflects the expected service quality when the base station is installed at the corresponding location.

[0122] Comprehensive evaluation model: A mathematical model used to comprehensively evaluate the suitability of a base station installation location, taking into account multiple factors such as historical base station data, user behavior patterns, and environmental parameter maps.

[0123] Machine learning algorithm: An algorithm that learns patterns from a training data set and can be used to predict performance indicators on unknown data.

[0124] Signal coverage quality: refers to the signal coverage range and strength of the candidate base station location, reflecting the availability and stability of the signal.

[0125] User access efficiency: refers to the user access speed and success rate at the candidate base station location, reflecting the convenience of users using the network.

[0126] Overall network performance: This reflects the overall performance of the base station installation location by taking into account signal coverage quality, user access efficiency, and other relevant indicators.

[0127] First, a comprehensive evaluation model for evaluating the suitability of base station installation locations is constructed based on historical base station data, user behavior patterns, and environmental parameter maps. Secondly, a machine learning algorithm is used to train the comprehensive evaluation model so that it can accurately predict the signal coverage quality, user access efficiency, and overall network performance of candidate base station locations. Finally, the trained comprehensive evaluation model is applied to each candidate base station location to calculate the suitability score of each candidate base station location, which reflects the expected service quality when the base station is installed at the corresponding location.

[0128] In the embodiment of the present application, it is assumed that in a base station site selection project in a new urban area, the suitability of multiple candidate base station locations needs to be evaluated. The specific steps are as follows:

[0129] First, historical base station data (signal strength, coverage, user access volume), user behavior patterns (activity time, activity location, communication needs), and environmental parameter maps (signal coverage heat map, interference source location information). Signal coverage quality, user access efficiency, and overall network performance. Secondly, collect a large amount of historical base station data and user behavior pattern data from the cloud database, and combine them with the environmental parameter map to form a training data set. Select a suitable machine learning algorithm, such as Random Forest, Support Vector Machine (SVM), or Neural Network. Use the training data set to train the comprehensive evaluation model and optimize the model parameters so that it can accurately predict the various performance indicators of the candidate base station location. For example, assuming the random forest algorithm is used, the trained model can be expressed as:

[0130] ;

[0131] in, is the suitability score, Input features include signal strength, coverage, user access, activity time, activity location, and communication needs

[0132] Further select several candidate base station locations, such as locations A, B, and C. Extract the corresponding input features based on the environmental parameter map, historical base station data, and user behavior patterns of each candidate location. Use the trained comprehensive evaluation model to calculate the suitability score of each candidate location.

[0133] For example, suppose the input features at position A are:

[0134] Signal strength: 85dBm, coverage: 600 meters, user access volume: 600 users / hour, activity time: 9 am to 5 pm, activity location: commercial area, communication demand: high-speed Internet, these features are input into the trained model, and the suitability score of location A is calculated to be 8.5 (out of 10 points). Similarly, the suitability scores of locations B and C are calculated: location B: 8.0 points, location C: 7.5 points. Finally, the ranking is based on the scoring results: location A> location B> location C. Generate a site selection recommendation report, recommend location A as the best installation location, and provide detailed optimization suggestions, such as increasing the antenna height, optimizing the signal direction, etc.

[0135] By implementing the above solution, a comprehensive evaluation model can be constructed and trained using machine learning algorithms to provide a scientific basis for decision-making and improve the accuracy and reliability of the evaluation. It also comprehensively considers multiple factors such as historical base station data, user behavior patterns, and environmental parameter maps to ensure the comprehensiveness and systematicness of the evaluation. Secondly, it can accurately predict the signal coverage quality, user access efficiency, and overall network performance of the candidate base station location, providing strong support for decision-making. Finally, it not only recommends the best installation location, but also provides specific optimization suggestions, which helps to improve the performance of the base station and user experience.

[0136] This application takes into account that in the existing technology, the site selection evaluation of base stations mainly relies on the experience of engineers and limited historical data. The traditional evaluation method lacks systematic and quantitative evaluation indicators, and it is difficult to fully reflect the suitability of the candidate base station location. And relying only on historical base station data and simple user behavior pattern analysis, it fails to make full use of the rich information provided by the environmental parameter map. Traditional methods are difficult to accurately predict the signal coverage quality, user access efficiency and overall network performance of the candidate base station location, resulting in the decision-making of base station site selection being not scientific and reliable enough. In order to solve the above problems, an embodiment of the present invention proposes an optional solution, which constructs a comprehensive evaluation model and uses a machine learning algorithm for training to accurately predict the various performance indicators of the candidate base station location, thereby generating a scientific site selection recommendation report. In particular, the suitability score of each candidate base station location is calculated by a specific mathematical formula, which further improves the accuracy and reliability of the evaluation.

[0137] The options are as follows:

[0138] Optionally, applying the trained comprehensive evaluation model to each candidate base station location to calculate a suitability score for each candidate base station location includes:

[0139] The suitability score of each candidate base station location is calculated using the following formula:

[0140] ;

[0141] in, Indicates the location of the candidate base station The suitability score of Indicates the location of the candidate base station The exponential form of the environmental parameter spectrum score; Indicates the location of the candidate base station The exponential form of the historical base station data score; Indicates the location of the candidate base station The index form of user behavior pattern score; are exponential coefficients, which are used to adjust the influence of environmental parameter map scores, historical base station data scores, and user behavior pattern scores; are weight coefficients, representing the relative importance of the environmental parameter map score, historical base station data score, and user behavior pattern score in the final suitability score;

[0142] Find the optimal weights by using the least squares method : , is the candidate base station location, is the actual performance score of the candidate base station location;

[0143] Environmental parameter map score:

[0144] , is the candidate base station location The distance to the nearest source of interference; It's location The degree to which the surrounding environment is dynamically changing; is the candidate base station location Coverage ratio on the signal coverage heat map, value range is the attenuation coefficient;

[0145] Historical base station data scores:

[0146] , is the candidate base station location Average signal strength; is the strongest signal strength; is the candidate base station location coverage; is the maximum coverage; is the candidate base station location The number of users accessing is the maximum number of user accesses; is the coefficient of each score of historical base station data;

[0147] User behavior pattern score:

[0148] , is the candidate base station location The proportion of active time of users; is the total active time; is the candidate base station location Percentage of user activity locations; It is the general activity location; is the candidate base station location The proportion of communication needs; is the total communication demand; It is the coefficient of each score of the user behavior pattern.

[0149] Comprehensive evaluation model: A mathematical model used to comprehensively evaluate the suitability of a base station installation location, taking into account multiple factors such as historical base station data, user behavior patterns, and environmental parameter maps.

[0150] Machine learning algorithm: An algorithm that learns patterns from a training data set and can be used to predict performance indicators on unknown data.

[0151] Suitability score: A comprehensive score that reflects the expected quality of service when the base station is installed in the corresponding location.

[0152] Environmental parameter map score: reflects the score of the environmental parameters of the candidate base station location (such as signal coverage, interference distribution, etc.).

[0153] Historical base station data score: reflects the score of the historical base station data (such as signal strength, coverage, user access volume, etc.) of the candidate base station location.

[0154] User behavior pattern score: A score that reflects the user behavior pattern (such as activity time, activity location, communication needs, etc.) of the candidate base station location.

[0155] Least squares method: A commonly used optimization method used to find the best weight coefficient so that the sum of squared errors between the predicted value and the actual value is minimized.

[0156] First, based on historical base station data, user behavior patterns, and environmental parameter maps, a comprehensive evaluation model for evaluating the suitability of base station installation locations is constructed. Secondly, a machine learning algorithm is used to train the comprehensive evaluation model so that it can accurately predict the signal coverage quality, user access efficiency, and overall network performance of candidate base station locations.

[0157] In the embodiment of the present application, it is assumed that in a base station site selection project in a new urban area, the suitability of three candidate base station locations A, B and C needs to be evaluated. The specific steps are as follows:

[0158] First, input historical base station data (signal strength, coverage, user access volume), user behavior patterns (activity time, activity location, communication needs), and environmental parameter maps (signal coverage heat map, interference source location information). Signal coverage quality, user access efficiency, and overall network performance. Secondly, collect a large amount of historical base station data and user behavior pattern data from the cloud database, and combine them with the environmental parameter map to form a training data set. Select the random forest algorithm. Use the training data set to train the comprehensive evaluation model and optimize the model parameters so that it can accurately predict the various performance indicators of the candidate base station location. Further candidate locations, locations A, B, and C. According to the environmental parameter map, historical base station data, and user behavior patterns of each candidate location, extract the corresponding input features. For example, the input features of location A are: signal strength: 85dBm, coverage: 600 meters, user access volume: 600 users / hour, activity time: 9 am to 5 pm, activity location: commercial area, communication demand: high-speed Internet, distance to the nearest interference source: 100 meters, degree of dynamic change of the surrounding environment: 0.2, signal coverage ratio: 0.8, and the suitability score of location A is calculated using the above formula:

[0159] ;

[0160] Similarly, calculate the suitability scores for locations B and C: Location B: 2.75, Location C: 2.60

[0161] Sort by scoring results: Position A>Position B>Position C.

[0162] Generate a site selection recommendation report, recommend location A as the best installation location, and provide detailed optimization suggestions, such as increasing antenna height, optimizing signal direction, etc.

[0163] By implementing the above scheme, the scientificity and reliability of base station site selection can be significantly improved. By building a comprehensive evaluation model and using machine learning algorithms for training, a scientific decision-making basis is provided, which improves the accuracy and reliability of the evaluation. In addition, multiple factors such as historical base station data, user behavior patterns, and environmental parameter maps are comprehensively considered to ensure the comprehensiveness and systematicness of the evaluation. The ability to accurately predict the signal coverage quality, user access efficiency, and overall network performance of candidate base station locations provides strong support for decision-making. Finally, not only is the optimal installation location recommended, but specific optimization suggestions are also provided to help improve the performance of the base station and user experience.

[0164] Optionally, it also includes:

[0165] Based on the site selection recommendation report and the corresponding instant feedback information, specific guidance information is provided to the on-site survey personnel, and the specific guidance information includes optimal path planning, on-site equipment deployment suggestions and interference source avoidance solutions to optimize the base station installation process.

[0166] Site selection recommendation report: A professional recommendation document for base station site selection based on a comprehensive evaluation of GIS data, historical data, user needs and other information.

[0167] Instant feedback information: information about the actual situation on site uploaded in real time by on-site survey personnel via mobile devices, including but not limited to photos, videos, text descriptions, etc.

[0168] Optimal Path Planning: Based on site conditions and traffic rules, an algorithm is used to calculate the best route from the starting point to the target location, aiming to save time and cost.

[0169] Onsite equipment deployment recommendations: Recommendations on equipment type, quantity, layout, etc. for specific site conditions to ensure optimal performance.

[0170] Interference source avoidance plan: Identify and evaluate interference factors that may affect the normal operation of base stations, and propose corresponding countermeasures or measures to mitigate the impact of these interferences.

[0171] First, the project team will screen multiple candidate sites based on preset criteria and prepare a site selection recommendation report. Subsequently, field survey personnel will be dispatched to each candidate site to record and upload the specific site conditions through smart terminals. Secondly, combined with the site selection report and instant feedback, the path planning algorithm is used to determine the best route for the construction team to the selected site. Further based on the results of the field investigation, the engineers will give detailed suggestions on the number, model and installation location of the required equipment. Finally, effective prevention and mitigation measures will be formulated for potential interference factors on site.

[0172] In the embodiment of this application, it is assumed that a communications company plans to add a new 5G base station in City A. After preliminary analysis, three possible construction sites were identified. The company sent technicians to conduct detailed field surveys of the three sites and uploaded relevant data through a mobile phone APP. After receiving this information, the background system automatically analyzed the pros and cons of each site and formulated a specific construction plan for each site.

[0173] For example, at location B, the system found that there was a large hospital nearby, which might pose a risk of electromagnetic interference. Therefore, it not only planned a driving route for the technicians to avoid congested roads during peak hours, but also recommended the use of antennas with stronger anti-interference capabilities and the installation of shielding facilities around the base station. In addition, the system also provided a detailed equipment list and installation guide to ensure that all operations could proceed smoothly.

[0174] The implementation of this solution can significantly improve the efficiency and success rate of base station construction projects, reduce the additional costs caused by insufficient preliminary preparation, and ensure the quality of network services. Through accurate path planning and reasonable equipment configuration, various obstacles encountered during construction can be effectively avoided or reduced, accelerating the progress of the project. At the same time, taking preventive measures for possible interference problems will help maintain a good communication environment and meet users' growing data transmission needs.

[0175] Figure 2 A schematic diagram of the structure of a base station survey system based on edge computing is provided for an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0176] A selection module 21, configured to select one or more target areas from within the base station network coverage area, wherein the target area includes at least one candidate base station location;

[0177] A deployment module 22 is used to deploy at least one edge computing device in the target area to perform real-time analysis on the collected environmental parameter data through the edge computing device, generate instant feedback information, and upload the instant feedback information to a cloud server. The instant feedback information includes signal coverage, potential interference source locations, and dynamic changes in the surrounding environment;

[0178] A construction module 23 is used to coordinate data sharing and collaboration between the edge computing devices, and to construct an environmental parameter map of the target area in combination with the instant feedback information, wherein the environmental parameter map reflects the signal coverage and interference distribution of the entire target area;

[0179] The generating module 24 is used to generate a site selection recommendation report for candidate base station locations based on the environmental parameter map in combination with historical base station data and user behavior patterns, wherein the site selection recommendation report includes an optimal installation location and optimization suggestions.

[0180] Figure 2 The base station survey system based on edge computing can perform Figure 1 The implementation principle and technical effect of the base station survey method based on edge computing described in the illustrated embodiment will not be repeated. The specific manner in which each module and unit performs operations in the base station survey system based on edge computing in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0181] In one possible design, Figure 2 A base station survey system based on edge computing in the illustrated embodiment can be implemented as a computing device, such as Figure 3As shown, the computing device may include a storage component 31 and a processing component 32;

[0182] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0183] The processing component 32 is used to: select one or more target areas from the base station network coverage area, the target area includes at least one candidate base station location; deploy at least one edge computing device in the target area to perform real-time analysis on the collected environmental parameter data through the edge computing device, generate instant feedback information, and upload the instant feedback information to the cloud server; coordinate data sharing and collaboration between edge computing devices, and construct an environmental parameter map of the target area based on the instant feedback information; based on the environmental parameter map, combined with historical base station data and user behavior patterns, generate a site selection recommendation report for the candidate base station location.

[0184] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0185] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0186] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0187] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0188] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0189] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0190] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 A base station survey method based on edge computing in the illustrated embodiment.

[0191] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0192] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0193] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0194] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A base station survey method based on edge computing, characterized in that: Applied to cloud servers, including: Select one or more target areas from the base station network coverage area, wherein the target area includes at least one candidate base station location; Deploy at least one edge computing device in the target area to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to the cloud server, wherein the instant feedback information includes signal coverage, potential interference source location, and dynamic changes of the surrounding environment; Coordinate data sharing and collaboration between the edge computing devices, and construct an environmental parameter map of the target area in combination with the instant feedback information, wherein the environmental parameter map reflects the signal coverage and interference distribution of the entire target area; Based on the environmental parameter map, combined with historical base station data and user behavior patterns, a site selection recommendation report for candidate base station locations is generated, and the site selection recommendation report includes an optimal installation location and optimization suggestions.

2. The method according to claim 1, characterized in that The coordinating data sharing and collaboration between the edge computing devices includes: Using a security protocol, encrypting the communication link between the edge computing devices to establish a secure communication link; On the basis of establishing a secure communication link, according to the data update frequency of the edge computing device, the edge computing device is synchronized to realize real-time exchange and synchronization of environmental parameter data between the edge computing devices; The method further comprises: A conflict detection algorithm is used to process data conflicts that occur during data sharing among the edge computing devices to ensure data consistency among the edge computing devices.

3. The method according to claim 1, characterized in that The step of constructing an environmental parameter map of the target area in combination with the instant feedback information includes: Using a data fusion algorithm, the instant feedback information is fused with the existing environmental parameter data to obtain an environmental parameter map; According to the latest instant feedback information, the environmental parameter map is updated in real time to obtain a dynamically updated environmental parameter map.

4. The method according to claim 3, characterized in that The instant feedback information is fused with the existing environmental parameter data using a data fusion algorithm to obtain an environmental parameter map, including: Generate a preliminary environmental parameter map based on the existing environmental parameter data; On the preliminary environmental parameter map, according to the potential interference source data in the instant feedback information, perform interference source position marking and positioning processing; According to the signal coverage in the instant feedback information, performing signal coverage mapping processing on the preliminary environmental parameter map to generate a signal coverage heat map; Based on the dynamic change data of the surrounding environment in the instant feedback information, dynamically update the preliminary environmental parameter map; Generates environmental parameter maps containing interference source location information, signal coverage heat maps, and dynamically updated data.

5. The method according to claim 4, characterized in that The generating of a site selection recommendation report for a candidate base station location based on the environmental parameter map in combination with historical base station data and user behavior patterns includes: Retrieving historical base station data of existing base stations related to the target area from a cloud database, including signal strength, coverage, and user access volume; Analyze user behavior patterns in the target area, including user activity time, activity location, and communication needs; According to the environmental parameter map, the historical base station data and the user behavior pattern, evaluating the suitability score of the candidate base station location to obtain an evaluation result; The evaluation results are sorted and a site selection recommendation report containing the best installation location and optimization suggestions is generated based on the sorting results.

6. The method according to claim 5, characterized in that The step of evaluating the suitability score of the candidate base station location according to the environmental parameter map, the historical base station data, and the user behavior pattern to obtain an evaluation result includes: Based on the historical base station data, user behavior patterns, and environmental parameter maps, a comprehensive evaluation model for evaluating the suitability of base station installation locations is constructed; The comprehensive evaluation model is trained using a machine learning algorithm so that the comprehensive evaluation model can accurately predict the signal coverage quality, user access efficiency, and overall network performance of the candidate base station location; Applying the trained comprehensive evaluation model to each candidate base station location to calculate a suitability score for each candidate base station location, wherein the suitability score reflects the expected service quality when the base station is installed at the corresponding location; The suitability score of each candidate base station location is calculated using the following formula: ; in, Indicates the location of the candidate base station The suitability score of Indicates the location of the candidate base station The exponential form of the environmental parameter spectrum score; Indicates the location of the candidate base station The exponential form of the historical base station data score; Indicates the location of the candidate base station The index form of user behavior pattern score; are exponential coefficients, which are used to adjust the influence of environmental parameter map scores, historical base station data scores, and user behavior pattern scores; are weight coefficients, representing the relative importance of the environmental parameter map score, historical base station data score, and user behavior pattern score in the final suitability score; Find the optimal weights by using the least squares method : , is the candidate base station location, is the actual performance score of the candidate base station location; Environmental parameter map score: , is the candidate base station location The distance to the nearest source of interference; It's location The degree to which the surrounding environment is dynamically changing; is the candidate base station location Coverage ratio on the signal coverage heat map, value range is the attenuation coefficient; Historical base station data scores: , is the candidate base station location Average signal strength; is the strongest signal strength; is the candidate base station location coverage; is the maximum coverage; is the candidate base station location The number of users accessing is the maximum number of user accesses; is the coefficient of each score of historical base station data; User behavior pattern score: , is the candidate base station location The proportion of active time of users; is the total active time; is the candidate base station location Percentage of user activity locations; It is the general activity location; is the candidate base station location The proportion of communication needs; is the total communication demand; It is the coefficient of each score of the user behavior pattern.

7. The method according to claim 5, characterized in that The method further comprises: Based on the site selection recommendation report and the corresponding instant feedback information, specific guidance information is provided to the on-site survey personnel, and the specific guidance information includes optimal path planning, on-site equipment deployment suggestions and interference source avoidance solutions to optimize the base station installation process.

8. A base station survey system based on edge computing, characterized in that: include: A selection module, configured to select one or more target areas from the base station network coverage area, wherein the target area includes at least one candidate base station location; A deployment module, configured to deploy at least one edge computing device in the target area, so as to analyze the collected environmental parameter data in real time through the edge computing device, generate instant feedback information, and upload the instant feedback information to a cloud service end, wherein the instant feedback information includes signal coverage, location of potential interference sources, and dynamic changes of the surrounding environment; A construction module is used to coordinate data sharing and collaboration between the edge computing devices, and to construct an environmental parameter map of the target area in combination with the instant feedback information, wherein the environmental parameter map reflects the signal coverage and interference distribution of the entire target area; A generation module is used to generate a site selection recommendation report for candidate base station locations based on the environmental parameter map, combined with historical base station data and user behavior patterns, wherein the site selection recommendation report includes an optimal installation location and optimization suggestions.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a base station survey method based on edge computing as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a base station survey method based on edge computing as described in any one of claims 1 to 7 is implemented.

Images