Base station deployment information generation method and device, equipment, medium and program product

Abstract

The invention provides a base station deployment information generation method and device, equipment, a medium and a program product, and is applied to the technical field of data processing, and the method comprises the steps: obtaining historical logistics unmanned plane flight path data, historical logistics order density data and geographical environment data of a target region; predicting first logistics order density data based on the historical logistics order density data; based on the historical logistics unmanned aerial vehicle flight path data, the geographical environment data and the first logistics order density data, base station deployment information used for base station deployment of the target area is generated, and base stations comprise a fixed base station and a mobile base station. According to the method, the base station deployment information matched with the first logistics order density data can be generated, so that the situation that the number and the positions of fixed base stations cannot respond to logistics order changes in time is reduced, and the stability of a low-altitude logistics communication network is improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, device, medium, and program product for generating base station deployment information. Background Technology

[0002] In the field of wireless communication, base stations, as key infrastructure providing wireless coverage and communication services, are crucial for ensuring communication quality. Traditional base station deployment is mainly based on fixed geographical area divisions and population density statistics, determining the location and number of base stations through pre-planning and on-site surveys. In terrestrial communication networks, this deployment method, to a certain extent, meets the communication needs of most users.

[0003] In the field of low-altitude logistics communication, fixed base stations are used for communication coverage. These fixed base stations are typically deployed in a grid pattern within cities or specific areas to ensure communication services for logistics drones within a certain range. Once the deployment locations of fixed base stations are determined, they are difficult to change and cannot be adjusted according to the dynamic changes in the real-time flight paths of logistics drones and order density. For example, during certain periods, a significant increase in logistics orders in certain areas leads to a sharp rise in communication demand, but the number and location of fixed base stations cannot respond to this change in a timely manner, potentially resulting in communication congestion or even outages. Therefore, the stability of existing low-altitude logistics communication networks is relatively poor. Summary of the Invention

[0004] This application provides a method, apparatus, device, medium, and program product for generating base station deployment information, which can solve the problem of poor stability in low-altitude logistics communication networks.

[0005] In a first aspect, embodiments of this application provide a method for generating base station deployment information, the method comprising: Acquire historical flight trajectory data, historical logistics order density data, and geographic environment data of the target area; Based on the historical logistics order density data, a first logistics order density data is predicted. The first logistics order density data is the logistics order density data for a first time period, which is the period after the historical logistics order density data is obtained. Based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for deploying base stations in the target area is generated, wherein the base stations include fixed base stations and mobile base stations.

[0006] Optionally, the first logistics order density data predicted based on the historical logistics order density data includes: The historical logistics order density data is input into a pre-trained order prediction model for prediction, and the second logistics order density data output by the order prediction model is obtained. Obtain a first parameter, which includes at least one of the following: weather forecast data and holiday information, wherein the weather forecast data is used to indicate the weather information of the target area during the first time period, and the holiday information is used to indicate whether the target area is a holiday during the first time period; The second logistics order density data is updated based on the first parameter to obtain the first logistics order density data.

[0007] Optionally, based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for deploying base stations in the target area is generated, including: Based on the historical logistics drone flight trajectory data and the first logistics order density data, a set of deployment schemes is determined. The set of deployment schemes includes multiple deployment schemes. Each deployment scheme in the set of deployment schemes can meet the following conditions: each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station, and all logistics order locations indicated by the first logistics order density data are within the coverage area of ​​the base station. Based on the geographic environment data and the first logistics order density data, a target deployment scheme is determined from the deployment scheme set. The target deployment scheme is the deployment scheme with the smallest objective function value in the deployment scheme set. The objective function value corresponding to the deployment scheme is determined based on the geographic environment data and the first logistics order density data. Based on the target deployment plan, the base station deployment information is generated.

[0008] Optionally, determining the target deployment scheme from the deployment scheme set based on the geographic environment data and the first logistics order density data includes: Obtain the maximum coverage of each deployment scheme in the deployment scheme set, and obtain multiple maximum coverages that correspond one-to-one with the multiple deployment schemes; Based on the geographic environment data, the construction cost information of each deployment scheme in the deployment scheme set is determined, resulting in multiple construction cost information corresponding one-to-one with the multiple deployment schemes; Based on the first logistics order density data, the energy consumption information of each deployment scheme in the deployment scheme set is determined, and multiple energy consumption information corresponding one-to-one with the multiple deployment schemes is obtained; Based on the multiple maximum coverage areas, the multiple construction cost information, and the multiple energy consumption information, multiple objective function values ​​are determined that correspond one-to-one with the multiple deployment schemes. The objective function values ​​are inversely proportional to the maximum coverage area values, directly proportional to the construction cost information values, and directly proportional to the energy consumption information values. The deployment scheme corresponding to the smallest objective function value among the multiple objective function values ​​is determined as the target deployment scheme.

[0009] Optionally, after generating base station deployment information for deploying base stations in the target area, the method further includes: Obtain the base station load information of the first fixed base station in the target area, wherein the first fixed base station is any fixed base station in the target area; If the base station load information indicates that the load of the first fixed base station is greater than the first load threshold, the base station transmit power of the first fixed base station is increased. When the base station load information indicates that the load of the first fixed base station is less than a second preset load threshold, the base station transmit power of the first fixed base station is reduced, and the second preset load threshold is less than the first load threshold.

[0010] Optionally, after generating base station deployment information for deploying base stations in the target area, the method further includes: Obtain real-time traffic flow information and real-time logistics order density data for the target area; Based on the real-time traffic flow information and the real-time logistics order density data, mobile base station planning information is generated, wherein the mobile base station planning information indicates the movement route of mobile base stations in the target area.

[0011] Secondly, embodiments of this application also provide a base station deployment information generation apparatus, the apparatus comprising: The data acquisition module is used to acquire historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data for the target area; The prediction module is used to predict first logistics order density data based on the historical logistics order density data. The first logistics order density data is the logistics order density data for a first time period, which is the period after the historical logistics order density data is obtained. The base station control module is used to generate base station deployment information for deploying base stations in the target area based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data. The base stations include fixed base stations and mobile base stations.

[0012] Thirdly, embodiments of this application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for generating base station deployment information as described in the first aspect.

[0013] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for generating base station deployment information as described in the first aspect.

[0014] Fifthly, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the method for generating base station deployment information as described in the first aspect.

[0015] In this embodiment, historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data of the target area are acquired. Based on the historical logistics order density data, a first logistics order density data is predicted, where the first logistics order density data is the logistics order density data for a first time period, which is the period after the acquisition of the historical logistics order density data. Based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for base station deployment in the target area is generated, wherein the base stations include fixed base stations and mobile base stations. Specifically, after predicting the first logistics order density data using historical logistics order density data, the base station deployment information generated based on the first logistics order density data can match the logistics demand of the first logistics order density data. Compared with the prior art, in areas where the first order density data indicates a low order volume, the number of base stations is less, and in areas where the first order density data indicates a high order volume, the number of base stations is more. This reduces the situation where "high order volumes lead to a sharp increase in communication demand in the area, but the number and location of fixed base stations cannot respond to this change in time, potentially resulting in communication congestion or even interruption." Therefore, the base station deployment information generation method of this application can improve the stability of the low-altitude logistics communication network. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is one of the flowcharts for the method of generating base station deployment information provided in the embodiments of this application; Figure 2 This is the second flowchart of the method for generating base station deployment information provided in the embodiments of this application; Figure 3 This is the third flowchart of the method for generating base station deployment information provided in the embodiments of this application; Figure 4 This is a structural diagram of a base station deployment information generation apparatus provided in an embodiment of this application; Figure 5 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] This application provides a method for generating base station deployment information.

[0020] See Figure 1 , Figure 1 This is a flowchart of a method for generating base station deployment information provided in an embodiment of this application. The method includes the following steps: Step 101: Obtain historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data for the target area.

[0021] This step involves collecting historical logistics drone flight trajectory data, historical logistics order density data, and geographic environment data. Specifically, historical logistics drone flight trajectory data is collected in real-time using GPS positioning devices and communication modules installed on the drones, capturing information such as flight altitude, speed, path, and docking points. Historical logistics order density data is obtained from the logistics management system, including order generation time, destination, and quantity, and the order density of different sub-regions within the target area at different time periods is statistically analyzed. Geographic environment data is acquired using a Geographic Information System (GIS) to obtain information such as terrain, urban building density, etc., providing a reference for base station site selection. Additionally, real-time traffic flow information can be collected simultaneously: through data interfaces with traffic management departments or traffic monitoring equipment, real-time traffic flow and congestion information are obtained to consider the impact of traffic factors on drone flight when planning base station locations.

[0022] In an optional implementation, the acquired data can be processed. Since different data sources may have different formats, sampling frequencies, and spatiotemporal resolutions, the raw data first needs to be cleaned and standardized to unify the data format and remove noise and outliers. Then, the data from different sources are integrated and correlated, and key features are extracted for subsequent analysis and processing. Data processing methods can include: (1) Spatiotemporal correlation: ① Correlation between drone trajectory and order density: Based on timestamps and geographical locations, drone flight trajectories are correlated with order density data. For example, the number of high-order-density areas passed by a drone within a specific time period is counted. ② Correlation between geographical environment and drone trajectory: The impact of terrain (such as mountains and rivers) or buildings (such as densely populated high-rise areas) on drone flight paths is analyzed, and potential signal blockage risks are calculated. ③ Correlation between traffic flow and drone scheduling: Real-time traffic data is combined to optimize drone path planning, avoid congested sections, and improve delivery efficiency.

[0023] (2) Feature extraction and quantification: ① UAV behavior characteristics: average flight speed, maximum climb rate, hovering frequency (reflecting task complexity), path repetition rate (high-frequency round-trip areas may require enhanced coverage). ② Order density characteristics: including both time and spatial dimensions. The time dimension mainly refers to the order distribution patterns during morning, noon, and evening peak hours; the spatial dimension mainly refers to the order concentration in hotspot areas, such as commercial and residential areas. ③ Environmental constraint characteristics: terrain undulation (affecting base station site selection height), building obstruction coefficient (affecting wireless signal propagation). ④ Traffic dynamic characteristics: road congestion index (affecting vehicle-mounted base station mobile path planning), traffic flow prediction (adjusting base station resource allocation in advance).

[0024] (3) Data standardization and normalization: For numerical features, such as order density and flight speed, standardization (Z-score) or normalization (Min-Max Scaling) is performed to eliminate differences in units; for categorical features, such as region type, one-hot encoding or embedding is performed.

[0025] Afterwards, all processed data is integrated into a unified, structured data model for easy use by subsequent algorithms. The data storage architecture includes: (1) a time-series database (such as TimescaleDB) for storing time-series data such as drone trajectories and order density, supporting efficient time range queries. (2) a spatial database (such as PostGIS) for managing spatial data such as geographic environment and base station locations, supporting spatial queries and analysis. (3) a graph database (such as Neo4j) for modeling the dynamic relationships between drones, base stations, and orders (such as the connection relationship between drones and base stations).

[0026] Step 102: Based on the historical logistics order density data, predict the first logistics order density data. The first logistics order density data is the logistics order density data for a first time period, which is the period after the historical logistics order density data is obtained.

[0027] In this step, machine learning models can be used to predict logistics demand, such as LSTM (Long Short-Term Memory) time series models and XGBoost regression models. The specific model selection depends on the data scale, feature complexity, and prediction accuracy requirements. For example, traditional time series models such as ARIMA (Autoregressive Integral Moving Average) are suitable for linear time series prediction but have a weak ability to capture nonlinear patterns. SARIMA (Seasonal ARIMA) is suitable for logistics demand with obvious periodicity (such as a surge in orders on weekends). XGBoost or LightGBM are gradient-boosting decision tree models that are good at handling structured data and can automatically capture nonlinear relationships between features. LSTM (Long Short-Term Memory) is suitable for handling time series data with long-term dependencies and can capture long-term trends and short-term fluctuations.

[0028] By using historical logistics order density data, we can pre-determine logistics order density data for a certain period in the future (the first period) (first logistics order density data), which can guide the deployment of subsequent base stations.

[0029] The first time period can be a time period starting from the moment when "historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data of the target area" are collected, or it can be a time period starting from a certain point in time after the collection of "historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data of the target area".

[0030] Step 103: Based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, generate base station deployment information for deploying base stations in the target area, wherein the base stations include fixed base stations and mobile base stations.

[0031] By using historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, the deployment scheme of fixed base stations and mobile base stations can be determined. The base station deployment information determined in this way can meet the needs of the first order density data in the first time period. Compared with the prior art, in areas where the first order density data indicates a low order volume, there are fewer base stations, and in areas where the first order density data indicates a high order volume, there are more base stations. This can reduce the situation where "the communication demand in areas with high order volume rises sharply, but the number and location of fixed base stations cannot respond to this change in time, which may lead to communication congestion or even interruption." Therefore, the base station deployment information generation method of this application can improve the stability of the low-altitude logistics communication network.

[0032] The following explanation applies to fixed base stations and mobile base stations: Fixed base stations: Deployed in areas with long-term high demand (such as logistics hubs and commercial centers) to provide basic wide-area coverage. They employ low-power design and high-gain antennas to ensure signal stability.

[0033] Mobile base stations are dynamically dispatched to temporary hotspot areas (such as areas with sudden surges in orders or remote delivery points) and flexibly fill blind spots through vehicle-mounted or drone relays, forming a two-layer network architecture of "static anchor points + dynamic enhancement".

[0034] Fixed base stations and mobile base stations can form a dynamic coordination strategy: Coverage coordination: Fixed base stations are responsible for large-scale continuous coverage, while mobile base stations fill signal blind spots (such as areas obstructed by buildings or newly developed delivery routes) according to real-time needs. Resource allocation coordination: Dynamically allocate spectrum resources through a centralized control platform (such as edge computing nodes), prioritizing the allocation of high-bandwidth links to high-priority areas covered by mobile base stations; Load balancing coordination: When a fixed base station is overloaded, nearby mobile base stations are dispatched to divert communication traffic and avoid network congestion.

[0035] Optionally, the first logistics order density data predicted based on the historical logistics order density data includes: The historical logistics order density data is input into a pre-trained order prediction model for prediction, and the second logistics order density data output by the order prediction model is obtained. Obtain a first parameter, which includes at least one of the following: weather forecast data and holiday information, wherein the weather forecast data is used to indicate the weather information of the target area during the first time period, and the holiday information is used to indicate whether the target area is a holiday during the first time period; The second logistics order density data is updated based on the first parameter to obtain the first logistics order density data.

[0036] In this embodiment, the initial model of the pre-trained order prediction model can adopt the following approaches: Short-term prediction (less than 6 hours): using Temporal Fusion Transformer (TFT) to balance long-term trends and short-term fluctuations. Long-term prediction (more than 6 hours): combining Prophet (to handle holiday effects) and XGBoost (to capture feature interactions).

[0037] The training process for the order prediction model can be as follows: The initial model is input with historical order sequences (a 24-hour sliding window) (the historical logistics order density data includes the historical order sequences from the training process; understandably, the historical logistics order density data can be divided into multiple data sets according to time sequence, such as first data, second data, third data, and fourth data. First data is historical data relative to second data, and second data is future data relative to first data; first data and second data can form a training dataset and training labels; similarly, first data and second data can form a training dataset, and third data can be the label corresponding to "first data and second data"), weather codes (One-Hot codes) (historical weather data), and holiday markers (historical holiday information). During training, the loss function used is Pinball Loss (quantile regression, considering the prediction interval) to optimize predictions at different confidence levels; the hyperparameter tuning method is to use Optuna to automatically search for key hyperparameters such as the number of LSTM layers and the learning rate to improve model performance.

[0038] like Figure 2 As shown, after inputting the historical logistics order density data into the pre-trained order prediction model for prediction and obtaining the second logistics order density data output by the order prediction model, in order to ensure that the demand prediction model can adapt to real-time changing environmental factors (such as sudden weather, holiday promotions, traffic control, etc.) and thus improve the accuracy of prediction, the pre-trained order prediction model in this embodiment also includes a dynamic correction mechanism: Real-time feedback: Prediction error (MAPE) is calculated hourly; if it exceeds 15%, incremental model training is triggered. External factor fusion: The second logistics order density data is updated based on the first parameters to obtain the first logistics order density data (e.g., dynamically weighting the impact of weather and emergencies through an attention mechanism). For example: Scenario assumption: Initial prediction: Based on historical logistics order density data, the pre-trained order model predicts that the order density in Business District A will be 50 orders / hour from 10:00 AM to 12:00 PM today.

[0039] Unexpected situation: At 10:30, a sudden downpour caused the actual order volume to plummet to 20 orders per hour (only 40% of the predicted value).

[0040] - Dynamic correction process: ① Error Detection. The system monitors the actual order volume in real time, calculates the prediction error (such as MAPE, Mean Absolute Percentage Error), and sets a threshold (such as triggering correction when the error exceeds 15%). In this example, the error reaches 60%, far exceeding the threshold.

[0041] ② Model Adjustment. Short-term Correction: Immediately reduce the forecast value for region A and correlate with weather API data to confirm the scope and duration of the rainstorm's impact (e.g., continuing until 12:30). Parameter Update: Adjust the attention weight of the TFT model, increasing the weight of the "severe weather" feature. Lower the forecast value for the subsequent time window (11:00-12:00) to 25 orders / hour.

[0042] ③ Resource scheduling response. Based on the revised forecast values, the base station control system performs the following operations: Reduce the transmission power of fixed base stations in area A (to save energy). Dispatch the vehicle-mounted base station away from area A and relocate it to residential area B, which was not affected by the rainstorm (orders in area B have increased due to increased demand for staying at home).

[0043] ④ Long-term learning: Add the features of this rainstorm event (such as rainfall and duration) to the training dataset to improve the model's ability to predict similar events.

[0044] By employing the method described in this embodiment, the accuracy of the predicted first logistics order density data can be improved, thereby enhancing the resource utilization rate of base station deployment information in the subsequent actual logistics process. This reduces the situation where "base station resources may be idle in areas with low order volume, while resources may be insufficient in areas with high order volume, leading to a waste of overall network resources," and improves resource utilization.

[0045] Optionally, based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for deploying base stations in the target area is generated, including: Based on the historical logistics drone flight trajectory data and the first logistics order density data, a set of deployment schemes is determined. The set of deployment schemes includes multiple deployment schemes. Each deployment scheme in the set of deployment schemes can meet the following conditions: each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station, and all logistics order locations indicated by the first logistics order density data are within the coverage area of ​​the base station. Based on the geographic environment data and the first logistics order density data, a target deployment scheme is determined from the deployment scheme set. The target deployment scheme is the deployment scheme with the smallest objective function value in the deployment scheme set. The objective function value corresponding to the deployment scheme is determined based on the geographic environment data and the first logistics order density data. Based on the target deployment plan, the base station deployment information is generated.

[0046] In this embodiment, a deployment scheme set can be determined based on the historical logistics drone flight trajectory data and the first logistics order density data. The deployment scheme set is a collection of numerous deployment schemes generated by a computer under certain target conditions, which may include: Each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station, and all logistics order locations indicated by the first logistics order density data are within the coverage area of ​​the base stations. The statement that "each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station" can be expressed by the following formula: ,in, This refers to the base station indicated by the deployment plan. This indicates the first [item] in the historical logistics drone flight trajectory data. The set of all discrete trajectory points on the flight path of a drone. A specific trajectory point on the drone's flight path. This indicates the existence of a base station. Represents trajectory points With base station The distance between them For base stations The coverage radius. The formula for expressing "all logistics order locations indicated by the first logistics order density data are within the base station coverage area" is similar to the formula above. The target conditions may also include: Base station number constraint: Total number of base stations ≤ , This indicates the maximum allowed number of base stations, which limits the total number of base stations and prevents over-deployment. Mobile base station scheduling constraints: Mobile base stations must meet dynamic scheduling requirements, such as travel time and charging time, which can be expressed by the following formula: , Indicates the first Mobile base stations, This indicates the actual window for scheduling.

[0047] After obtaining the set of deployment schemes, the objective function value corresponding to each deployment scheme can be calculated based on the geographical environment data and the first logistics order density data. Based on the objective function value, the target deployment scheme can be determined, and base station deployment information for base station deployment can be generated.

[0048] In this embodiment, a set of candidate deployment schemes is automatically generated based on historical flight trajectories and processing environment data. The target deployment scheme is obtained by calculating the objective function value and then the base station deployment information is automatically generated. Compared with manual site selection and manual planning, this method can significantly improve deployment efficiency and reduce planning costs.

[0049] Optionally, determining the target deployment scheme from the deployment scheme set based on the geographic environment data and the first logistics order density data includes: Obtain the maximum coverage of each deployment scheme in the deployment scheme set, and obtain multiple maximum coverages that correspond one-to-one with the multiple deployment schemes; Based on the geographic environment data, the construction cost information of each deployment scheme in the deployment scheme set is determined, resulting in multiple construction cost information corresponding one-to-one with the multiple deployment schemes; Based on the first logistics order density data, the energy consumption information of each deployment scheme in the deployment scheme set is determined, and multiple energy consumption information corresponding one-to-one with the multiple deployment schemes is obtained; Based on the multiple maximum coverage areas, the multiple construction cost information, and the multiple energy consumption information, multiple objective function values ​​are determined that correspond one-to-one with the multiple deployment schemes. The objective function values ​​are inversely proportional to the maximum coverage area values, directly proportional to the construction cost information values, and directly proportional to the energy consumption information values. The deployment scheme corresponding to the smallest objective function value among the multiple objective function values ​​is determined as the target deployment scheme.

[0050] In this embodiment, the objective function construction needs to comprehensively consider three core objectives: coverage area, construction cost, and energy consumption, and balance them through weighting coefficients. The objective function can be: ； in This indicates the deployment plan of the base stations (including location, number, power, etc.). Indicates the maximum coverage area (0≤ ≤1 (a larger value indicates better coverage). This indicates the construction cost index (unit: 10,000 yuan or standardized value). Energy consumption index (unit: kW h or standardized value). Here are the weighting coefficients, where This is used to adjust the priority of various targets. Coverage range refers to the flight area of ​​the logistics drones that the base station can effectively cover. Construction cost includes the cost of equipment procurement, installation, commissioning, and maintenance of the base station. Energy consumption refers to the electricity consumed during the operation of the base station.

[0051] It should be noted that the weighting coefficients determine the priority of the optimization direction and need to be dynamically adjusted according to actual business needs. A higher level indicates priority for coverage (e.g., emergency logistics to remote areas), prioritizing ensuring full coverage; when A higher value indicates cost sensitivity, where cost is the most important factor and must be considered first (e.g., in commercial logistics where quick profitability is crucial); when... A higher value indicates a need to prioritize green energy conservation (e.g., policy requirements for low-carbon operation) and low power consumption. Simultaneously, the weighting can be automatically adjusted based on real-time data (e.g., peak order times, electricity price fluctuations). For example, during daytime peak hours, the weighting is increased. (Coverage coverage), reduce (High energy consumption is allowed); during off-peak hours at night, increase [energy consumption]. (Energy Saving Mode) Disable redundant base stations.

[0052] The objective function needs to satisfy: Coverage Maximize coverage feedback to ensure stable communication connectivity for logistics drones throughout the delivery area and reduce communication blind spots. This coverage range is determined by the coverage capability of each base station's equipment and the location of the base stations in the deployment plan. ; Where C represents the total coverage area, Indicates the first One base station, where D represents the drone flight trajectory data; Construction costs Minimize: Minimizing construction costs can reduce the costs of base station construction, maintenance, and energy consumption, including the costs of site selection, equipment procurement, and power consumption for fixed base stations.

[0053] , Where B represents the total construction cost, including base station equipment cost, installation fee, power consumption, etc. The difference in construction cost between different deployment schemes is mainly determined by the number of base stations and geographical environment data. The geographical environment will affect the installation difficulty of the base station, thus affecting the installation cost, etc. Minimize energy consumption (E): Optimize the power allocation and operation mode of base stations to reduce overall energy consumption and improve energy utilization efficiency; , Where E represents total energy consumption. Indicates base station The energy consumption of different deployment schemes is mainly affected by the first logistics order density data.

[0054] Based on the characteristics and constraints of the objective function described above, Mixed Integer Programming (MIP) or reinforcement learning algorithms (such as DQN) can be used to determine the optimal location of fixed base stations. Mixed Integer Programming (MIP): Applicable to fixed base station site selection (discrete variables), using Gurobi or CPLEX solvers. Variables include base station location (binary variable, whether the base station is deployed at candidate location i, 0 or 1) and power (continuous variable, the base station's transmit power), yielding a globally optimal solution that minimizes cost and maximizes coverage. Reinforcement learning algorithms (such as DQN-Deep Q-Network): Dynamically schedule mobile base stations, using state matrices such as order density distribution, current base station distribution, and traffic conditions to plan the adjustment of base station movement direction (e.g., East (+x), South (-y), West (-x), North (+y)) or power (±5dBm).

[0055] By using the Reward Function (the core mechanism of learning, defining the feedback from the environment to the agent's behavior, guiding the agent on how to take actions to maximize long-term gains. By trying different actions, observing the reward patterns, and gradually adjusting the strategy to obtain higher rewards), we can observe how to maximize coverage (C), minimize energy consumption (B), and minimize disturbances (E).

[0056] ; in, Coverage Reward covers user satisfaction (such as order completion rate, signal strength); :Battery / Power Cost, base station energy consumption (the higher the power, the greater the energy consumption); Interference / Energy Efficiency refers to interference or energy efficiency penalties (such as interference from adjacent base stations or overlapping coverage areas).

[0057] parameter: The weights need to be adjusted according to business needs; for example, if more emphasis is placed on coverage, the weights should be increased. If energy conservation is a priority, then it will increase. .

[0058] Optionally, the base station deployment scheme also has a dynamic adjustment mechanism to collect data feedback in real time: (1) drone trajectory update, drone flight data is updated every T minutes, and coverage is recalculated; (2) order density change capture, base station priority is adjusted according to real-time order data, such as increasing base station density in high-order areas; (3) according to traffic flow, the mobile base station path is dynamically adjusted to avoid congested sections. Secondly, adaptive optimization is carried out. As new data arrives, the model parameters are continuously optimized, and the weight coefficient is dynamically adjusted according to the actual business needs. Sudden high demand scenarios, such as: [Scenario] The order density in a certain area suddenly increases by 200%. [Dynamic adjustment response] The nearest vehicle-mounted base station is dispatched, and the power of the fixed base station is temporarily increased by 20%.

[0059] Optionally, after generating base station deployment information for deploying base stations in the target area, the method further includes: Obtain the base station load information of the first fixed base station in the target area, wherein the first fixed base station is any fixed base station in the target area; If the base station load information indicates that the load of the first fixed base station is greater than the first load threshold, the base station transmit power of the first fixed base station is increased. When the base station load information indicates that the load of the first fixed base station is less than a second preset load threshold, the base station transmit power of the first fixed base station is reduced, and the second preset load threshold is less than the first load threshold.

[0060] In this embodiment, a first load threshold and a second load threshold are set to control the base station transmission power of the first fixed base station, thereby improving resource utilization.

[0061] Optionally, after generating base station deployment information for deploying base stations in the target area, the method further includes: Obtain real-time traffic flow information and real-time logistics order density data for the target area; Based on the real-time traffic flow information and the real-time logistics order density data, mobile base station planning information is generated, wherein the mobile base station planning information indicates the movement route of mobile base stations in the target area.

[0062] In this embodiment, real-time traffic flow information and real-time logistics order density data can be input into a preset model to generate mobile base station planning information. This allows the mobile base station's movement route to meet the real-time logistics order density data while planning a more efficient route based on the real-time traffic flow information.

[0063] It should be noted that after deploying base stations according to the base station deployment information, resource scheduling can be carried out based on the actual situation. The goal of resource scheduling is to ensure that logistics drones maintain a stable communication connection throughout the entire delivery process by dynamically adjusting the allocation and deployment location of base station resources, while optimizing network resource utilization and reducing operating costs. The resource scheduling process mainly includes a collaborative control, real-time monitoring, and adjustment mechanism for fixed base stations and vehicle-mounted base stations. Resource scheduling can include the following aspects: Coordinated control of fixed and vehicle-mounted base stations. Mobile base stations are controlled to move between areas with high concentrations of logistics drones (such as warehouse clusters and delivery terminals), forming a coordinated coverage network of "fixed base stations + vehicle-mounted base stations." Connections are switched in real-time via communication protocols to ensure the stability of the drone communication link. A communication coordination mechanism is established between base stations to achieve data sharing and collaborative processing, improving overall network performance. Coordinated control of fixed and vehicle-mounted base stations includes: Deployment and Optimization of Fixed Base Stations. Fixed base stations are the foundation of logistics communication networks, and their deployment location needs to comprehensively consider coverage, order density, and energy consumption optimization. Coverage ensures communication continuity along drone flight paths and reduces blind spots; order density ensures more base stations are deployed in high-order-density areas to meet communication needs; energy consumption optimization reduces energy consumption through low-power design. The optimization of fixed base station deployment is mainly based on AI-driven demand forecasting. By using historical flight trajectories and order density data, future logistics demand hotspots are predicted to guide the site selection optimization of fixed base stations. Simultaneously, based on real-time changes in order density, the power and spectrum resource allocation of fixed base stations are dynamically adjusted. For example, during nighttime order low periods, 50% of the base station radio frequency modules are turned off, allowing some base stations to enter sleep mode. Dynamic scheduling of vehicle-mounted base stations. Vehicle-mounted base stations supplement fixed base stations and are suitable for temporary high-demand scenarios (such as sudden logistics peaks and delivery to remote areas). Their deployment and scheduling strategies need to consider: ① Real-time traffic conditions: avoiding congested road sections and improving mobility efficiency; ② Drone distribution: prioritizing coverage of areas with high drone density (such as warehouse clusters and delivery endpoints); ③ Battery life: rationally planning driving routes to ensure that the vehicle-mounted base station returns to the charging station before its battery is depleted. Specifically, reinforcement learning can be used to dynamically adjust the location and task allocation of the vehicle-mounted base station, and the connection object can be switched in real time through communication protocols to ensure the stability of the drone communication link. The path planning of the vehicle-mounted base station can combine Dijkstra's algorithm (shortest path) and real-time traffic data to avoid congestion. The charging strategy can be to navigate to the nearest charging station when the battery level is less than 30%, and have a backup base station take over. Resource scheduling can also include real-time monitoring and adjustment mechanisms. This involves real-time monitoring of network status, including base station signal strength, load conditions, and drone flight status, and dynamically adjusting base station resource allocation and deployment locations based on monitoring results to adapt to changes in logistics demands. The real-time monitoring and adjustment mechanism includes: Network Status Monitoring. To ensure the stability and reliability of the communication network, this proposal requires real-time monitoring of three key indicators: base station signal strength (checking for weak or dead zones), base station load (assessing CPU, memory, and bandwidth utilization to avoid overload), and drone flight status (monitoring drone position, speed, battery level, and other parameters to ensure stable communication links). This is achieved by deploying sensors on base stations and drones to collect data in real-time and upload it to the central control system. Simultaneously, lightweight AI models, such as TinyML (a micro-machine learning model), are deployed on base stations or drones to monitor drone connection status in real-time. A handover is triggered if the ping latency exceeds 100ms (Note: Ping latency refers to the time it takes for a data packet to travel from the sender to the receiver and back, usually measured in milliseconds; it measures network connection quality and speed, reflecting data transmission speed and network stability). Lightweight edge computing is used for local data processing and anomaly detection to achieve real-time network status monitoring. Dynamic adjustment strategy. Based on monitoring data, dynamically adjust base station resource allocation and deployment location to adapt to changes in logistics demand. ① Base station power adjustment: Increase base station transmission power to expand coverage in high-load areas; reduce base station power to reduce energy consumption in low-load areas. ② Spectrum resource allocation: Utilize cognitive radio technology to dynamically allocate spectrum resources, avoiding interference and improving spectrum utilization, allocating more bandwidth and low-latency resources to high-priority tasks (such as emergency supplies delivery). ③ Vehicle-mounted base station scheduling: Dynamically adjust the task allocation of vehicle-mounted base stations based on drone distribution and order density (e.g., prioritizing coverage of high-demand areas), and plan optimal driving routes based on real-time traffic data to improve mobility efficiency. ④ Rapid fault recovery: Deploy backup base stations in critical areas to ensure rapid switching in the event of a primary base station failure, and automatically detect and repair network faults using AI algorithms (e.g., switching to backup frequency bands or base stations).

[0064] like Figure 3As shown, in the base station deployment information generation method of this application, the deployment locations of ground fixed base stations and drone relay nodes are dynamically planned by combining the historical flight trajectory, order density, and real-time traffic data of logistics drones, and mobile base station technology (such as vehicle-mounted base stations) is introduced to further reduce network construction costs. This scheme achieves an optimal balance between coverage, resource utilization, and cost-effectiveness through the coordinated operation of fixed and mobile base stations, specifically including the following four steps: ① Data collection and analysis: Integrating multi-source data (flight trajectory, order density, geographical environment, traffic flow) to construct a dynamic demand model. ② Demand forecasting: Predicting future logistics demand hotspots and time distribution based on machine learning. ③ Site selection optimization: Determining the optimal deployment scheme for fixed and mobile base stations through a multi-objective optimization algorithm. ④ Resource scheduling: Dynamically adjusting base station resource allocation to ensure the stability and efficiency of the communication network.

[0065] Existing fixed base station deployment methods are ill-suited to the dynamically changing flight paths of logistics drones, easily leading to communication blind spots. This proposal employs an AI-driven dynamic base station deployment algorithm, which dynamically adjusts the deployment location and resource allocation of base stations based on the real-time flight path of the logistics drone and the dynamic changes in order density. This ensures that the logistics drone maintains a stable communication connection throughout the entire delivery process, improving coverage flexibility.

[0066] Existing fixed base station resource allocation technologies cannot adjust in real time according to changes in order density, resulting in low resource utilization. This proposal, through a multi-objective optimization site selection model and a real-time monitoring and adjustment mechanism, can adjust base station resource allocation in real time according to changes in order density, reducing resource investment in areas with low order volume and increasing resource supply in areas with high order volume, thereby improving resource utilization.

[0067] The construction of fixed base stations in existing technologies requires significant upfront investment, and the construction and maintenance costs are high in remote areas or temporary logistics delivery zones. This proposal introduces mobile base station technology, which dynamically schedules mobile base stations to move between areas with high concentrations of logistics drones, reducing the number of fixed base stations and their construction costs. Furthermore, based on demand forecasting and dynamic planning, unnecessary base station construction and resource waste are avoided, further reducing construction costs.

[0068] Existing fixed base stations are difficult to expand and adjust, making it difficult to quickly respond to changes in the scale of logistics operations and delivery areas. The system architecture proposed in this paper has good scalability. By adding mobile base stations or adjusting the deployment location and resource configuration of existing base stations, it can quickly adapt to the development and changes in logistics operations and meet the communication needs of different scenarios.

[0069] See Figure 4 , Figure 4This is a structural diagram of a base station deployment information generation apparatus provided in an embodiment of this application. Figure 4 As shown, the device 400 includes: Data acquisition module 401 is used to acquire historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data of the target area; Prediction module 402 is used to predict first logistics order density data based on the historical logistics order density data, wherein the first logistics order density data is the logistics order density data for a first time period, and the first time period is the period after the historical logistics order density data is obtained; The base station control module 403 is used to generate base station deployment information for deploying base stations in the target area based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, wherein the base stations include fixed base stations and mobile base stations.

[0070] Optionally, the prediction module 402 is also used for: The historical logistics order density data is input into a pre-trained order prediction model for prediction, and the second logistics order density data output by the order prediction model is obtained. Obtain a first parameter, which includes at least one of the following: weather forecast data and holiday information, wherein the weather forecast data is used to indicate the weather information of the target area during the first time period, and the holiday information is used to indicate whether the target area is a holiday during the first time period; The second logistics order density data is updated based on the first parameter to obtain the first logistics order density data.

[0071] Optionally, the base station control module 403 is also used for: Based on the historical logistics drone flight trajectory data and the first logistics order density data, a set of deployment schemes is determined. The set of deployment schemes includes multiple deployment schemes. Each deployment scheme in the set of deployment schemes can meet the following conditions: each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station, and all logistics order locations indicated by the first logistics order density data are within the coverage area of ​​the base station. Based on the geographic environment data and the first logistics order density data, a target deployment scheme is determined from the deployment scheme set. The target deployment scheme is the deployment scheme with the smallest objective function value in the deployment scheme set. The objective function value corresponding to the deployment scheme is determined based on the geographic environment data and the first logistics order density data. Based on the target deployment plan, the base station deployment information is generated.

[0072] Optionally, the base station control module 403 is also used for: Obtain the maximum coverage of each deployment scheme in the deployment scheme set, and obtain multiple maximum coverages that correspond one-to-one with the multiple deployment schemes; Based on the geographic environment data, the construction cost information of each deployment scheme in the deployment scheme set is determined, resulting in multiple construction cost information corresponding one-to-one with the multiple deployment schemes; Based on the first logistics order density data, the energy consumption information of each deployment scheme in the deployment scheme set is determined, and multiple energy consumption information corresponding one-to-one with the multiple deployment schemes is obtained; Based on the multiple maximum coverage areas, the multiple construction cost information, and the multiple energy consumption information, multiple objective function values ​​are determined that correspond one-to-one with the multiple deployment schemes. The objective function values ​​are inversely proportional to the maximum coverage area values, directly proportional to the construction cost information values, and directly proportional to the energy consumption information values. The deployment scheme corresponding to the smallest objective function value among the multiple objective function values ​​is determined as the target deployment scheme.

[0073] Optionally, the device 400 also includes an adjustment module for: Obtain the base station load information of the first fixed base station in the target area, wherein the first fixed base station is any fixed base station in the target area; If the base station load information indicates that the load of the first fixed base station is greater than the first load threshold, the base station transmit power of the first fixed base station is increased. When the base station load information indicates that the load of the first fixed base station is less than a second preset load threshold, the base station transmit power of the first fixed base station is reduced, and the second preset load threshold is less than the first load threshold.

[0074] Optionally, the device 400 also includes a route generation module for: Obtain real-time traffic flow information and real-time logistics order density data for the target area; Based on the real-time traffic flow information and the real-time logistics order density data, mobile base station planning information is generated, wherein the mobile base station planning information indicates the movement route of mobile base stations in the target area.

[0075] In this embodiment, the data acquisition module is responsible for collecting flight trajectory data, order density data, geographical environment data, and real-time traffic flow information of the logistics drones. It cleans, preprocesses, and integrates the collected data to provide high-quality data support for subsequent analysis and processing. The prediction module uses machine learning models to predict logistics demand and generates order density prediction results for different regions. Based on the prediction results and external factors, it dynamically adjusts the prediction model to improve prediction accuracy. The base station control module includes scheduling algorithms for fixed base stations and vehicle-mounted base stations. Based on site selection optimization results and resource scheduling strategies, it controls the deployment location and resource allocation of base stations. It monitors the network status in real time and dynamically adjusts the operating parameters of the base stations based on the monitoring results to ensure network stability and reliability.

[0076] The base station deployment information generation device 400 in this embodiment can perform... Figure 1 The complete steps of the method for generating base station deployment information shown are used to achieve the same beneficial effects, and will not be repeated here to avoid duplication.

[0077] This application also provides an electronic device. Since the principle by which the electronic device solves the problem is similar to the method for generating base station deployment information in this application, the implementation of this electronic device can refer to the implementation of the aforementioned method for generating base station deployment information; repeated details will not be elaborated further. Figure 5 As shown, the electronic device of this application embodiment includes: a processor 500, configured to read a program from a memory 520 and execute the following processes: Acquire historical flight trajectory data, historical logistics order density data, and geographic environment data of the target area; Based on the historical logistics order density data, a first logistics order density data is predicted. The first logistics order density data is the logistics order density data for a first time period, which is the period after the historical logistics order density data is obtained. Based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for deploying base stations in the target area is generated, wherein the base stations include fixed base stations and mobile base stations.

[0078] Among them, Figure 5In this context, the bus architecture can include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 500) and memory (memory 520). The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides the interface. Processor 500 is responsible for managing the bus architecture and general processing, and memory 520 can store data used by processor 500 during operation.

[0079] Optionally, the processor 500 is configured to read the program from the memory 520 and execute the following processes: The historical logistics order density data is input into a pre-trained order prediction model for prediction, and the second logistics order density data output by the order prediction model is obtained. Obtain a first parameter, which includes at least one of the following: weather forecast data and holiday information, wherein the weather forecast data is used to indicate the weather information of the target area during the first time period, and the holiday information is used to indicate whether the target area is a holiday during the first time period; The second logistics order density data is updated based on the first parameter to obtain the first logistics order density data.

[0080] Optionally, the processor 500 is configured to read the program from the memory 520 and execute the following processes: Based on the historical logistics drone flight trajectory data and the first logistics order density data, a set of deployment schemes is determined. The set of deployment schemes includes multiple deployment schemes. Each deployment scheme in the set of deployment schemes can meet the following conditions: each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station, and all logistics order locations indicated by the first logistics order density data are within the coverage area of ​​the base station. Based on the geographic environment data and the first logistics order density data, a target deployment scheme is determined from the deployment scheme set. The target deployment scheme is the deployment scheme with the smallest objective function value in the deployment scheme set. The objective function value corresponding to the deployment scheme is determined based on the geographic environment data and the first logistics order density data. Based on the target deployment plan, the base station deployment information is generated.

[0081] Optionally, the processor 500 is configured to read the program from the memory 520 and execute the following processes: Obtain the maximum coverage of each deployment scheme in the deployment scheme set, and obtain multiple maximum coverages that correspond one-to-one with the multiple deployment schemes; Based on the geographic environment data, the construction cost information of each deployment scheme in the deployment scheme set is determined, resulting in multiple construction cost information corresponding one-to-one with the multiple deployment schemes; Based on the first logistics order density data, the energy consumption information of each deployment scheme in the deployment scheme set is determined, and multiple energy consumption information corresponding one-to-one with the multiple deployment schemes is obtained; Based on the multiple maximum coverage areas, the multiple construction cost information, and the multiple energy consumption information, multiple objective function values ​​are determined that correspond one-to-one with the multiple deployment schemes. The objective function values ​​are inversely proportional to the maximum coverage area values, directly proportional to the construction cost information values, and directly proportional to the energy consumption information values. The deployment scheme corresponding to the smallest objective function value among the multiple objective function values ​​is determined as the target deployment scheme.

[0082] Optionally, the processor 500 is configured to read the program from the memory 520 and execute the following processes: Obtain the base station load information of the first fixed base station in the target area, wherein the first fixed base station is any fixed base station in the target area; If the base station load information indicates that the load of the first fixed base station is greater than the first load threshold, the base station transmit power of the first fixed base station is increased. When the base station load information indicates that the load of the first fixed base station is less than a second preset load threshold, the base station transmit power of the first fixed base station is reduced, and the second preset load threshold is less than the first load threshold.

[0083] Optionally, the processor 500 is configured to read the program from the memory 520 and execute the following processes: Obtain real-time traffic flow information and real-time logistics order density data for the target area; Based on the real-time traffic flow information and the real-time logistics order density data, mobile base station planning information is generated, wherein the mobile base station planning information indicates the movement route of mobile base stations in the target area.

[0084] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the various processes of the above-described method for generating base station deployment information, achieving the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0085] This application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above-described... Figure 1 The various processes of the method embodiment for generating base station deployment information shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0086] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0087] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0088] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for generating base station deployment information, characterized in that, The method includes: Acquire historical flight trajectory data, historical logistics order density data, and geographic environment data of the target area; Based on the historical logistics order density data, a first logistics order density data is predicted. The first logistics order density data is the logistics order density data for a first time period, which is the period after the historical logistics order density data is obtained. Based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for deploying base stations in the target area is generated, wherein the base stations include fixed base stations and mobile base stations.

2. The method according to claim 1, characterized in that, The first logistics order density data predicted based on the historical logistics order density data includes: The historical logistics order density data is input into a pre-trained order prediction model for prediction, and the second logistics order density data output by the order prediction model is obtained. Obtain a first parameter, which includes at least one of the following: weather forecast data and holiday information, wherein the weather forecast data is used to indicate the weather information of the target area during the first time period, and the holiday information is used to indicate whether the target area is a holiday during the first time period; The second logistics order density data is updated based on the first parameter to obtain the first logistics order density data.

3. The method according to claim 1, characterized in that, Based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data, base station deployment information for deploying base stations in the target area is generated, including: Based on the historical logistics drone flight trajectory data and the first logistics order density data, a set of deployment schemes is determined. The set of deployment schemes includes multiple deployment schemes. Each deployment scheme in the set of deployment schemes can meet the following conditions: each drone flight trajectory point indicated by the historical logistics drone flight trajectory data is covered by at least one base station, and all logistics order locations indicated by the first logistics order density data are within the coverage area of ​​the base station. Based on the geographic environment data and the first logistics order density data, a target deployment scheme is determined from the deployment scheme set. The target deployment scheme is the deployment scheme with the smallest objective function value in the deployment scheme set. The objective function value corresponding to the deployment scheme is determined based on the geographic environment data and the first logistics order density data. Based on the target deployment plan, the base station deployment information is generated.

4. The method according to claim 3, characterized in that, The step of determining the target deployment scheme from the deployment scheme set based on the geographic environment data and the first logistics order density data includes: Obtain the maximum coverage of each deployment scheme in the deployment scheme set, and obtain multiple maximum coverages that correspond one-to-one with the multiple deployment schemes; Based on the geographic environment data, the construction cost information of each deployment scheme in the deployment scheme set is determined, resulting in multiple construction cost information corresponding one-to-one with the multiple deployment schemes; Based on the first logistics order density data, the energy consumption information of each deployment scheme in the deployment scheme set is determined, and multiple energy consumption information corresponding one-to-one with the multiple deployment schemes is obtained; Based on the multiple maximum coverage areas, the multiple construction cost information, and the multiple energy consumption information, multiple objective function values ​​are determined that correspond one-to-one with the multiple deployment schemes. The objective function values ​​are inversely proportional to the maximum coverage area values, directly proportional to the construction cost information values, and directly proportional to the energy consumption information values. The deployment scheme corresponding to the smallest objective function value among the multiple objective function values ​​is determined as the target deployment scheme.

5. The method according to any one of claims 1 to 4, characterized in that, After generating base station deployment information for deploying base stations in the target area, the method further includes: Obtain the base station load information of the first fixed base station in the target area, wherein the first fixed base station is any fixed base station in the target area; If the base station load information indicates that the load of the first fixed base station is greater than the first load threshold, the base station transmit power of the first fixed base station is increased. When the base station load information indicates that the load of the first fixed base station is less than a second preset load threshold, the base station transmit power of the first fixed base station is reduced, and the second preset load threshold is less than the first load threshold.

6. The method according to any one of claims 1 to 4, characterized in that, After generating base station deployment information for deploying base stations in the target area, the method further includes: Obtain real-time traffic flow information and real-time logistics order density data for the target area; Based on the real-time traffic flow information and the real-time logistics order density data, mobile base station planning information is generated, wherein the mobile base station planning information indicates the movement route of mobile base stations in the target area.

7. A device for generating base station deployment information, characterized in that, The device includes: The data acquisition module is used to acquire historical logistics drone flight trajectory data, historical logistics order density data, and geographical environment data for the target area; The prediction module is used to predict first logistics order density data based on the historical logistics order density data. The first logistics order density data is the logistics order density data for a first time period, which is the period after the historical logistics order density data is obtained. The base station control module is used to generate base station deployment information for deploying base stations in the target area based on the historical logistics drone flight trajectory data, the geographical environment data, and the first logistics order density data. The base stations include fixed base stations and mobile base stations.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for generating base station deployment information as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for generating base station deployment information as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions, which, when executed by a processor, implement the steps of the method for generating base station deployment information as described in any one of claims 1 to 6.

Images