A multi-source spatial data fusion site selection method, system, terminal and storage medium for urban unmanned aerial vehicle instant delivery take-off and landing sites

Abstract

This invention relates to the field of data fusion technology and discloses a multi-source spatial data fusion site selection method, system, terminal, and storage medium for urban drone instant delivery take-off and landing sites. The method includes: based on the operational needs and spatial landing conditions of urban drone instant delivery, constructing a take-off and landing site site selection rule system around demand orientation, operational safety, NIMBY (Not In My Backyard) coordination, and feasibility; and transforming this rule system into a system including site selection area screening, facility scale prediction, suitability evaluation, candidate space extraction and controllable verification, and site selection scheme determination. This invention enables synergistic linkage between demand judgment, facility scale prediction, spatial suitability evaluation, candidate space extraction, and construction scheme determination, helping to improve the scientificity, safety, and feasibility of drone instant delivery take-off and landing site site selection, and enhancing the adaptability of take-off and landing site layout to urban spatial structure, instant delivery needs, operational safety requirements, and specific construction conditions.

Description

Technical Field

[0001] This invention relates to the field of data fusion technology, and in particular to a multi-source spatial data fusion site selection method, system, terminal, and computer-readable storage medium for urban drone instant delivery take-off and landing sites. Background Technology

[0002] With the development of the low-altitude economy, urban instant delivery, and smart logistics, drones are increasingly being used in urban instant delivery scenarios such as food delivery, fresh food delivery, emergency supplies transportation, and short-distance delivery to campuses and commercial areas. Compared with traditional ground delivery, drone instant delivery has advantages such as three-dimensional routes, high transportation efficiency, and less impact from ground traffic congestion, which can improve the efficiency of instant delivery in urban built-up areas.

[0003] However, the large-scale operation of drone-based instant delivery relies not only on aircraft performance, route organization, and operational management capabilities, but also heavily on the spatial supply of low-altitude logistics infrastructure such as take-off and landing sites, landing points, and airdrop lockers within cities. Among these, the location of take-off and landing sites, as crucial nodes for drone parking, take-off, landing, loading and unloading, charging, maintenance, and scheduling, directly impacts the service efficiency, operational safety, urban spatial coordination, and feasibility of facility implementation of the drone delivery system.

[0004] In urban built environments, take-off and landing sites face multiple constraints: on the one hand, facilities should be located near densely populated areas with active consumption and high delivery demand; on the other hand, facilities need to avoid specific areas, restricted flight zones, key control areas, high-risk sensitive facilities, noise-sensitive spaces, and privacy-sensitive spaces. Simultaneously, take-off and landing sites also need to meet certain spatial carrying capacity requirements, such as roof or platform area, airspace clearance, building structural load-bearing capacity, vertical transportation accessibility, power supply conditions, communication conditions, and management and maintenance conditions. Therefore, the site selection for urban drone on-demand delivery take-off and landing sites is not simply a logistics node layout issue, but a comprehensive spatial decision-making problem involving urban spatial structure, functional facility distribution, operational safety, NIMBY (Not In My Backyard) coordination, and feasibility.

[0005] Based on existing methods for drone logistics delivery, low-altitude infrastructure site selection, and urban spatial analysis, the technologies related to this invention can be mainly divided into three aspects: logistics network and operation optimization, low-altitude operation safety and facility standardization, and urban spatial data and site selection evaluation.

[0006] At the logistics network and operation optimization level, existing technologies typically treat drone take-off and landing sites, landing points, charging stations, or logistics nodes as service nodes in the delivery network, focusing on optimization of objectives such as demand coverage, delivery distance, response time, operating costs, energy consumption, facility quantity, and task scheduling. For example, some methods use location allocation models, path planning models, mixed integer programming models, location-path joint models, heuristic algorithms, or genetic algorithms to determine the node locations and delivery routes in the drone delivery network. These methods can improve delivery efficiency and facility coverage from a network operation perspective, but their main goal still leans towards logistics system optimization, with insufficient consideration for the relationship between take-off and landing sites and urban spatial structure, building space carriers, functional facility distribution, sensitive interfaces, and actual landing conditions. Especially in urban instant delivery scenarios, take-off and landing sites often need to be embedded in complex built environments such as business districts, office areas, residential areas, and public open spaces. Relying solely on delivery distance, service radius, or cost functions makes it difficult to determine whether a specific space truly has the conditions for construction and operation.

[0007] At the level of low-altitude operational safety and facility standards, existing technologies primarily focus on aspects such as route delineation, take-off and landing point setup, flight conflict avoidance, obstacle avoidance, airspace clearance conditions, airspace restrictions, and operational safety during drone operations. For example, take-off and landing points are defined as designated areas for unmanned aerial vehicles (UAVs) to take off, land, taxi, park, and engage in other activities. Urban UAV logistics routes are specified to include air routes, arrival and departure routes, take-off and landing points, and alternate landing points. While these technologies provide a foundation for safe UAV operation and route organization, most still focus on flight process, route network, or take-off and landing point operational safety, with less emphasis on addressing urban planning and architectural space considerations to determine which spaces within a city can serve as immediate delivery take-off and landing sites.

[0008] In urban spatial data and site selection evaluation, existing technologies typically employ methods such as GIS (Geographic Information System) spatial analysis, multi-criteria decision analysis, AHP (Analytic Hierarchy Process) weighting, buffer analysis, network analysis, kernel density analysis, and spatial overlay evaluation to assess the spatial suitability of public service facilities, logistics facilities, transportation facilities, and airports. While these methods can identify potentially suitable areas for facility layout to some extent, most remain at the level of two-dimensional spatial evaluation or network optimization, failing to adequately consider three-dimensional spatial implementation factors.

[0009] In summary, although existing technologies have laid a certain foundation in areas such as drone logistics network optimization, low-altitude operation safety control, and GIS spatial suitability evaluation, they still have the following shortcomings when selecting sites for urban drone instant delivery take-off and landing sites.

[0010] First, existing technologies lack a dedicated site selection rule system and process-oriented application methods for urban drone instant delivery take-off and landing sites. Logistics optimization methods focus more on delivery efficiency and network coverage, operational safety methods focus more on flight routes and conditions, and GIS evaluation methods focus more on spatial suitability zoning. There is a lack of continuous technical logic among these three, making it difficult to effectively connect demand, operational safety, NIMBY coordination, implementation conditions, and facility scale.

[0011] Secondly, existing technologies are insufficient for recognizing three-dimensional spatial carriers within the urban built environment. Urban drone delivery take-off and landing sites differ from general logistics nodes; they often rely on commercial building rooftops, podium platforms, connecting corridor platforms, multi-level surface spaces, or open ground spaces. Existing methods, if using only two-dimensional grids, road networks, plot units, or demand points as evaluation objects, struggle to determine actual implementation conditions such as building height, roof area, platform clearance, obstacle distribution, vertical transportation, power and communication access, structural load-bearing capacity, and management ownership. This can easily lead to a disconnect between model results and actual implementation conditions.

[0012] Furthermore, existing technologies lack a tiered processing mechanism for control constraints and evaluative indicators. The site selection for drone-based instant delivery takeoff and landing sites involves both rigid constraints that must be met, such as specific areas, restricted flight zones, airport airspace, flight path conflicts, safety distances, avoidance of sensitive facilities, site area, and airspace conditions; and evaluative factors for ranking and comparison, such as population demand, commercial activity, road accessibility, distribution of functional facilities, service coverage, and construction priority. Existing technologies often directly incorporate factors of different natures into the comprehensive score, which can easily lead to spaces with high demand but also security risks, NIMBY conflicts, or implementation obstacles being misjudged as suitable locations.

[0013] Finally, existing technologies are not sufficiently tailored to urban on-demand delivery scenarios. Compared to general express delivery, feeder logistics, emergency drones, or manned urban air transportation, urban drone on-demand delivery is characterized by high frequency, small batches, strong timeliness, dense last-mile demand, complex service scenarios, and facilities located close to everyday living spaces. Therefore, the selection of take-off and landing sites not only needs to meet flight safety and delivery efficiency requirements, but also needs to comprehensively consider factors such as residential life, office and commercial activities, public open spaces, noise impact, privacy sensitivity, public acceptance, and the feasibility of facility implementation.

[0014] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0015] The main objective of this invention is to provide a multi-source spatial data fusion site selection method, system, terminal, and computer-readable storage medium for urban drone instant delivery take-off and landing sites. This invention aims to solve the problems existing in the site selection of urban drone instant delivery take-off and landing sites, such as the disconnect between demand forecasting and spatial location, insufficient two-dimensional spatial evaluation and three-dimensional building carrier identification, mixed processing of control constraints and evaluation indicators, and the difficulty in directly converting site selection results into feasible implementation schemes.

[0016] To achieve the above objectives, the present invention provides a multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites, the method comprising the following steps: Based on the demand base and supply organization conditions of the target urban area, it is determined whether the target urban area has the basic conditions for selecting a site for drone instant delivery take-off and landing, and a site selection area screening result is formed. If the target urban area meets the basic site selection conditions based on the site selection area screening results, the required number of drones and the scale of take-off and landing facilities are predicted by combining the instant delivery demand level, drone instant delivery penetration rate, drone operation efficiency and average construction scale of take-off and landing sites in the target year, and the facility scale prediction results are obtained. Based on the geographic information dataset, spatial evaluation units of the target urban area are constructed. Combining population heat map, building characteristics, road network conditions and functional facility distribution, standardization, reclassification and weighted overlay methods are used to comprehensively evaluate the suitability of take-off and landing site selection of different spatial evaluation units in the target urban area and identify highly suitable areas. For the highly suitable area, candidate sites with actual spatial carrying capacity are extracted based on three-dimensional modeling and spatial identification methods. The candidate sites are then subject to control review from the perspectives of operational safety, NIMBY coordination and feasibility. Potential sites that do not meet the control requirements are eliminated to obtain a set of candidate sites. The candidate site set is compared with the facility size prediction results. If the number of candidate sites meets the prediction requirements, a final site selection plan is formed, and the output content should be expanded according to the hierarchy.

[0017] Optionally, the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites, wherein the step of judging whether the target urban area has the basic conditions for carrying out drone instant delivery take-off and landing site selection based on the demand basis and supply organization conditions of the target urban area, and forming a site selection area screening result, specifically includes: Obtain the demand base and supply organization conditions of the target urban area; Based on the aforementioned demand basis, it is determined whether the target urban area has the basic order scale to support the normalized operation of drone instant delivery. Whether the target urban area belongs to a high-intensity built-up area is used as the demand basis discrimination condition. When the plot ratio of the target urban area is not lower than a preset threshold, or belongs to a high-density area determined in the urban planning, it is determined that the target urban area has the demand basis for instant delivery. Based on the supply organization conditions, determine whether the target urban area has the supply organization foundation to support the operation of drone instant delivery, and determine whether there is a regional business district, large shopping center, commercial complex or multiple commercial facilities cluster area in the target urban area or within a certain service range of the target urban area. If so, determine that the target urban area has the supply organization foundation for instant delivery operation. The site selection results are obtained based on the judgment of demand and the judgment of supply organization conditions.

[0018] Optionally, the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites includes the facility scale prediction results including the peak daily demand for instant delivery, the number of instant delivery drones, and the scale of instant delivery take-off and landing sites. The method combines the target year's on-demand delivery demand level, drone on-demand delivery penetration rate, drone operational efficiency, and average construction scale of take-off and landing sites to predict the required number of drones and the scale of take-off and landing site facilities, resulting in a facility scale prediction result, specifically including: Predicting peak daily demand for instant delivery: Forecast the average daily demand for instant delivery in the study area for the target year, and predict future... The average daily demand for instant delivery per year is expressed as follows: ; in, express The average daily demand for on-demand delivery in the research area in 2018 express Annual study area service population, Indicates the penetration rate of on-demand delivery users. This indicates the average daily order volume per person. Calculate peak demand: ; in, express Annual research on peak demand for on-demand delivery in the region Indicates the peak value; After obtaining the peak-hour instant delivery demand, calculate the peak-hour order volume handled by drones: ; in, express Annual peak drone order volume in the research area This indicates the penetration rate of drone-based instant delivery; Predicted number of on-demand delivery drones: After obtaining the peak order volume for drones, and combining this with the entire lifecycle of a single drone, calculate the carrying capacity per unit time during the peak period: ; in, This indicates the carrying capacity of a single drone per unit time during peak hours. This indicates the entire lifecycle of a single drone; Calculate the number of drones required under peak operating conditions in the study area: ; in, express Number of drones required during peak periods in the annual research area Indicates the available coefficients of the system. Indicates rounding up; Predicted size of on-demand delivery takeoff and landing sites: After obtaining the number of drones, calculate the total area of ​​take-off and landing fields required for the study area in the target year based on the take-off and landing field area coefficient corresponding to the configuration of each drone: ; in, express Total area of ​​takeoff and landing field required for the annual study area This indicates the takeoff and landing area coefficient corresponding to a unit of UAV configuration; Based on the average buildable area of ​​a single takeoff and landing field, calculate the number of takeoff and landing fields required for the study area: ; in, express Number of take-off and landing fields required in the annual study area This indicates the average buildable area of ​​a single take-off and landing field.

[0019] Optionally, the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites, wherein the spatial evaluation units of the target urban area are constructed based on geographic information datasets, and combined with population heat maps, building characteristics, road network conditions, and functional facility distribution, a standardization, reclassification, and weighted overlay method is used to comprehensively evaluate the suitability of take-off and landing site selection for different spatial evaluation units within the target urban area, identifying highly suitable areas, specifically including: Construct a geographic information dataset for the selection of take-off and landing sites for drone instant delivery, the geographic information dataset including urban spatial structure data and urban functional distribution data; After establishing the geographic information dataset, the study area is divided into regular grids to form several spatial evaluation units; Based on the geographic information dataset and the spatial evaluation unit, the evaluation indicators are quantitatively calculated. The evaluation indicators include population heat map, building characteristics, road network conditions and functional distribution. After calculating all evaluation indicators, the indicator layers are standardized and reclassified to eliminate dimensional differences between different indicators and to unify the evaluation benchmark. After reclassification, the evaluation indicators are weighted and superimposed according to preset weights to calculate the comprehensive suitability score for each spatial evaluation unit. ; in, Indicates the first The overall suitability score of each spatial evaluation unit, Indicates the first The weight of each evaluation indicator, Indicates the first The spatial evaluation unit in the first Standardized scores on each evaluation indicator Indicates the total number of evaluation indicators; Based on the comprehensive suitability score, the areas are classified into four levels: most suitable, relatively suitable, generally suitable, relatively unsuitable, and unsuitable. The areas where the most suitable and relatively suitable site selection units are concentrated are identified as high suitability areas.

[0020] Optionally, the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites includes urban spatial structure data such as building-related data, population thermal data, and road network data. The building-related data is used to calculate the average building height and building coverage, the population thermal data is used to calculate the average and peak population thermal values, and the road network data is used to calculate the road network density. The urban functional distribution data includes POI data, which includes demand scenarios, noise-sensitive facilities, and privacy-sensitive facilities.

[0021] Optionally, the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites includes, for the highly suitable area, extracting candidate sites with actual spatial carrying capacity based on 3D modeling and spatial recognition methods, and performing a control review of the candidate sites from the perspectives of operational safety, NIMBY coordination, and feasibility, eliminating potential sites that do not meet the control requirements, to obtain a candidate site set, specifically including: For the highly suitable areas identified by the suitability assessment, digital modeling and spatial identification are carried out based on the three-dimensional modeling method to extract usable sites with actual carrying capacity and form an initial candidate site set; The initial candidate site set is screened out according to the airspace conditions, and the airspace conditions of the initial candidate site set are reviewed. Candidate spaces that do not meet the hard airspace constraints are eliminated to obtain the first candidate site set. Based on the requirements related to noise impact and privacy impact, it is determined whether the candidate spaces in the first candidate site set are located within sensitive spaces. Candidate spaces located within the scope of sensitive facilities are eliminated to obtain the second candidate site set. The feasibility and controllability of the candidate spaces in the second candidate site set are reviewed. The feasibility and controllability review includes land ownership review, carrier condition review and access condition review. Potential sites that do not meet the control requirements are eliminated to obtain the candidate site set.

[0022] Optionally, in the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites, the comparison of the candidate site set with the facility scale prediction results, and the formation of a final site selection scheme if the number of candidate sites meets the prediction requirements, and the output content should be expanded hierarchically, specifically including: The candidate site set, which has undergone feasibility control review, will be compared with the facility size prediction results. If the number of candidate sites that pass the feasibility control review meets the predicted number of takeoff and landing sites, then the final site selection plan is formed. If the number of candidate sites that pass the control review is insufficient, continue to carry out candidate space extraction and control review in areas classified as generally suitable until the number of candidate sites meets the facility scale requirements. The output should be presented in a hierarchical manner from macro to micro. At the macro level, it should clarify whether the target urban area has the basic conditions and required facility scale for the layout of drone instant delivery take-off and landing sites. At the meso level, it should output the suitability level of different spatial evaluation units in the study area and the distribution of highly suitable areas. At the micro level, it should identify specific candidate sites that have passed the control review of operational safety, NIMBY coordination and feasibility, and form a recommended construction plan that matches the predicted facility scale.

[0023] Furthermore, to achieve the above objectives, the present invention also provides a multi-source spatial data fusion site selection system for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites, wherein the multi-source spatial data fusion site selection system for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites includes: The site selection area screening module is used to determine whether the target urban area has the basic conditions for selecting a drone instant delivery take-off and landing site based on the demand base and supply organization conditions of the target urban area, and to form a site selection area screening result. The facility scale prediction module is used to predict the required number of drones and the scale of take-off and landing facilities if the target urban area meets the basic site selection conditions based on the site selection area screening results, and in combination with the instant delivery demand level, drone instant delivery penetration rate, drone operation efficiency and average construction scale of take-off and landing sites in the target year, so as to obtain the facility scale prediction results. The suitability evaluation module is used to construct spatial evaluation units of the target urban area based on the geographic information dataset, and combine population heat map, building characteristics, road network conditions and functional facility distribution. It adopts standardization, reclassification and weighted overlay methods to comprehensively evaluate the suitability of take-off and landing site selection of different spatial evaluation units in the target urban area and identify highly suitable areas. The candidate space extraction and controllability verification module is used to extract candidate sites with actual spatial carrying capacity based on three-dimensional modeling and spatial recognition methods for the high suitability area, and to perform controllability verification on the candidate sites from the aspects of operational safety, NIMBY coordination and feasibility, eliminating potential sites that do not meet the control requirements, and obtaining a candidate site set; The site selection scheme determination module is used to compare the candidate site set with the facility scale prediction results. If the number of candidate sites meets the prediction requirements, a final site selection scheme is formed, and the output content should be expanded according to the hierarchy.

[0024] In addition, to achieve the above objectives, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a multi-source spatial data fusion location program for urban UAV instant delivery take-off and landing sites stored in the memory and executable on the processor. When the multi-source spatial data fusion location program for urban UAV instant delivery take-off and landing sites is executed by the processor, it implements the steps of the multi-source spatial data fusion location method for urban UAV instant delivery take-off and landing sites as described above.

[0025] Furthermore, to achieve the above objectives, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a multi-source spatial data fusion location program for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites, and when the multi-source spatial data fusion location program for urban UAV instant delivery take-off and landing sites is executed by a processor, it implements the steps of the multi-source spatial data fusion location method for urban UAV instant delivery take-off and landing sites as described above.

[0026] In this invention, based on the demand and supply organization conditions of the target urban area, it is determined whether the target urban area possesses the basic conditions for selecting a site for drone instant delivery take-off and landing, thus forming a site selection area screening result. If the target urban area is determined to meet the basic site selection conditions based on the site selection area screening result, the required number of drones and the scale of take-off and landing facilities are predicted by combining the instant delivery demand level, drone instant delivery penetration rate, drone operating efficiency, and average construction scale of take-off and landing sites in the target year, thus obtaining a facility scale prediction result. A spatial evaluation unit of the target urban area is constructed based on a geographic information dataset, and population heat map, building characteristics, road network conditions, and functions are considered. The facility distribution employs standardization, reclassification, and weighted overlay methods to comprehensively evaluate the suitability of take-off and landing site selection for different spatial evaluation units within the target urban area, identifying highly suitable areas. For these highly suitable areas, candidate sites with practical spatial carrying capacity are extracted based on 3D modeling and spatial identification methods. These candidate sites undergo a controlled review based on operational safety, NIMBY (Not In My Backyard) coordination, and feasibility, eliminating potential sites that do not meet the control requirements, resulting in a candidate site set. This candidate site set is compared with the facility scale prediction results. If the number of candidate sites meets the prediction requirements, a final site selection plan is formed, and the output should be expanded hierarchically. This invention enables synergistic linkage between demand assessment, facility scale prediction, spatial suitability evaluation, candidate space extraction, and construction plan determination, helping to improve the scientific rigor, safety, and feasibility of urban drone instant delivery take-off and landing site selection, and enhancing the adaptability of take-off and landing site layout to urban spatial structure, instant delivery needs, operational safety requirements, and specific construction conditions. Attached Figure Description

[0027] Figure 1 This is a flowchart of a preferred embodiment of the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites of the present invention; Figure 2 This is a flowchart illustrating the entire implementation process of a preferred embodiment of the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites of the present invention. Figure 3 This is a structural diagram of a preferred embodiment of the multi-source spatial data fusion site selection system for urban drone instant delivery take-off and landing sites of the present invention; Figure 4 This is a structural diagram of a preferred embodiment of the terminal of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0029] To address the problems in existing urban drone instant delivery take-off and landing site selection, such as the disconnect between demand forecasting and spatial location, insufficient two-dimensional spatial evaluation and three-dimensional building carrier identification, mixed processing of control constraints and evaluation indicators, and the difficulty in directly converting site selection results into feasible solutions, this invention proposes a multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites.

[0030] The basic idea of ​​this invention is to construct a take-off and landing site selection rule system based on the operational needs and spatial landing conditions of urban drone instant delivery, focusing on demand orientation, operational safety, NIMBY (Not In My Backyard) coordination, and feasibility. This rule system is then transformed into a site selection process comprising five stages: site selection area screening, facility scale prediction, suitability evaluation, candidate space extraction and controllable verification, and site selection scheme determination. In this process, multi-source data such as population distribution, instant delivery needs, building form, road traffic, functional facilities, sensitive facilities, airspace restrictions, and candidate space carriers are uniformly incorporated into the take-off and landing site selection process to support the continuous derivation from macro-regional judgment to meso-level suitability identification and then to micro-level site verification.

[0031] Through the above-described scheme, this invention transforms the selection of urban drone instant delivery take-off and landing sites from traditional experience-based judgment or single suitability evaluation into a comprehensive site selection process supported by multi-source data, with clear process hierarchies, combining evaluation and verification, and results geared towards implementation. Compared with existing technologies, this invention enables synergistic linkage between demand assessment, facility scale prediction, spatial suitability evaluation, candidate space extraction, and construction scheme determination. This helps improve the scientific rigor, safety, and feasibility of urban drone instant delivery take-off and landing site selection, and enhances the adaptability of take-off and landing site layout to urban spatial structure, instant delivery needs, operational safety requirements, and specific construction conditions.

[0032] The preferred embodiment of the present invention describes a multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites, such as... Figure 1 and Figure 2 As shown, the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites includes the following steps: Step S10: Based on the demand base and supply organization conditions of the target urban area, determine whether the target urban area has the basic conditions for selecting a site for drone instant delivery take-off and landing, and form a site selection area screening result.

[0033] Specifically, site selection involves determining whether the target urban area possesses the basic conditions for establishing drone-based instant delivery take-off and landing sites. The construction and operation of drone-based instant delivery take-off and landing sites rely on a stable demand base and necessary supply organization capabilities. If the target urban area lacks sufficient order volume or supply support capacity, the construction of take-off and landing sites may encounter problems such as underutilization of facilities, low operational efficiency, and imbalanced resource allocation. The site selection method of this invention includes two aspects: demand base assessment and supply condition assessment.

[0034] (1) Demand basis judgment: The process involves obtaining the demand base of the target urban area and determining whether it has the basic order volume to support the routine operation of drone-based instant delivery. In practice, whether the target urban area is a high-intensity developed area is used as a condition for determining the demand base. If the plot ratio of the target urban area is not lower than a preset threshold, or if it belongs to a high-density area as defined in urban planning, it can be determined that the target urban area has the basic demand base for instant delivery. Conversely, areas with low development intensity, insufficient population activity density, or weak functional integration can be excluded from the subsequent site selection analysis.

[0035] (2) Judgment of supply conditions: The supply organization conditions of the target urban area are obtained, and based on these conditions, it is determined whether the target urban area possesses the supply organization foundation to support drone instant delivery operations. In specific implementation, it can be determined whether there are regional-level business districts, large shopping malls, commercial complexes, or areas with multiple commercial facilities clustered within the target urban area or a certain service range of the target urban area. If so, the target urban area is determined to have the supply organization foundation for instant delivery operations; if the target urban area lacks a core business district or the concentration of supply entities is insufficient, its supply organization conditions can be determined to be weak, and it will not proceed to the subsequent take-off and landing site selection process.

[0036] The site selection results are obtained based on the judgment of demand and the judgment of supply organization conditions.

[0037] Step S20: If the target urban area meets the basic site selection conditions based on the site selection area screening results, the required number of drones and the scale of take-off and landing facilities are predicted by combining the instant delivery demand level, drone instant delivery penetration rate, drone operation efficiency and average construction scale of take-off and landing sites in the target year, and the facility scale prediction results are obtained.

[0038] Specifically, the facility scale forecasting phase mainly estimates the required number of drones and the basic size of the take-off and landing sites based on the future on-demand delivery demand level of the target urban area. The facility scale forecasting results include the peak daily demand for on-demand delivery, the number of on-demand delivery drones, and the size of the on-demand delivery take-off and landing sites.

[0039] (1) Predicting peak daily demand for instant delivery: First, forecast the average daily demand for instant delivery in the study area for the target year, and then... The average daily demand for instant delivery per year is expressed as follows: ; in, express The average daily demand for on-demand delivery in the research area in 2018 express Annual study area service population, Indicates the penetration rate of on-demand delivery users. This indicates the average daily order volume per person.

[0040] Since on-demand delivery primarily handles time-sensitive orders such as food and retail, its order volume exhibits a clear peak characteristic within a day. Therefore, further calculations are needed to determine the demand during peak periods: ; in, express Annual research on peak demand for on-demand delivery in the region This represents the peak value coefficient.

[0041] After obtaining the peak-hour instant delivery demand, the peak-hour order volume handled by drones is further calculated: ; in, express Annual peak drone order volume in the research area This indicates the penetration rate of drone-based instant delivery.

[0042] (2) Predict the number of on-demand delivery drones: After obtaining the peak order volume for drones, and combining this with the entire lifecycle of a single drone (i.e., the complete operation time required for a single drone to complete one on-demand delivery task, typically including drone takeoff, flight, landing, cargo loading or transfer, pickup and delivery, return, charging or battery swapping, inspection and maintenance, and preparation time before entering the next round of delivery tasks), calculate the carrying capacity per unit time of a single drone during peak hours: ; in, This indicates the carrying capacity of a single drone per unit time during peak hours. This indicates the entire lifecycle of a single drone.

[0043] Further calculations were made regarding the number of drones required under peak operating conditions in the study area: ; in, express Number of drones required during peak periods in the annual research area Indicates the available coefficients of the system. This indicates rounding up to the nearest integer.

[0044] (3) Predict the size of the instant delivery take-off and landing site: After obtaining the number of drones, calculate the total area of ​​take-off and landing fields required for the study area in the target year based on the take-off and landing field area coefficient corresponding to the configuration of each drone: ; in, express Total area of ​​takeoff and landing field required for the annual study area This indicates the takeoff and landing area coefficient corresponding to the configuration of a unit UAV.

[0045] Furthermore, by combining the average buildable area of ​​a single takeoff and landing field, the required number of takeoff and landing fields for the study area is calculated: ; in, express Number of take-off and landing fields required in the annual study area This indicates the average buildable area of ​​a single take-off and landing field.

[0046] Through the three prediction steps described above, this invention can transform the service population, on-demand delivery usage level, peak demand characteristics, and drone delivery penetration rate of a target urban area into drone delivery demand during peak hours. Furthermore, by combining the entire lifecycle of a single drone and the system availability coefficient, it calculates the number of drones required to meet peak operational demands. Finally, based on the unit drone configuration area coefficient and the average buildable area of ​​a single take-off and landing site, it estimates the total area of ​​the take-off and landing sites and the number of facilities. Its technical advantage lies in transforming take-off and landing site size prediction from empirical judgment to quantitative derivation based on peak demand and drone operating efficiency. This provides a basis for controlling the number of facilities and spatial layout in subsequent site selection schemes, avoiding resource waste due to excessive facility configuration or insufficient service capacity during peak hours due to insufficient configuration.

[0047] Step S30: Construct spatial evaluation units for the target urban area based on the geographic information dataset, and combine population heat map, building characteristics, road network conditions and functional facility distribution, using standardization, reclassification and weighted overlay methods to comprehensively evaluate the suitability of take-off and landing site selection for different spatial evaluation units in the target urban area, and identify highly suitable areas.

[0048] Specifically, the suitability assessment stage mainly involves comprehensively judging the suitability of unmanned aerial vehicle (UAV) instant delivery take-off and landing sites in different spatial assessment units within the study area, and identifying highly suitable areas.

[0049] (1) Construction of geographic information dataset: First, a geographic information dataset for selecting take-off and landing sites for drone instant delivery is constructed. This dataset includes urban spatial structure data and urban functional distribution data. The urban spatial structure data includes building-related data, population heat map data, and road network data. The building-related data is primarily used to calculate average building height and building coverage; the population heat map data is primarily used to calculate average and peak population heat map values; and the road network data is primarily used to calculate road network density. The urban functional distribution data includes POI (Point of Interest) data, categorized according to the needs of drone instant delivery take-off and landing site selection: demand scenarios, noise-sensitive facilities, and privacy-sensitive facilities. Demand scenarios may include public open spaces and business office spaces; noise-sensitive facilities may include medical and elderly care facilities and campus facilities; and privacy-sensitive facilities may include residential facilities and specific facilities.

[0050] (2) Unified rasterization: After establishing the geographic information dataset, the study area is divided into regular grids to form several spatial evaluation units. A 100m×100m regular grid can be used as a spatial evaluation unit, and the evaluation results of various influencing factors are assigned to the corresponding grids to carry out spatial overlay and comprehensive evaluation.

[0051] (3) Calculation of evaluation indicators: Based on the geographic information dataset and the spatial evaluation unit, evaluation indicators are quantitatively calculated. These indicators include population heatmap, building characteristics, road network conditions, and functional distribution. Population heatmap indicators include mean and peak population heatmaps. Population heatmap data can be extracted during the main operating periods of drone delivery, and the mean and peak population heatmaps for each grid are calculated using weighted kernel density analysis and zonal statistical methods. Building characteristic indicators include building coverage and average building height. Building outline data can be spatially overlaid with the evaluation grid to calculate the building footprint area and building height within each grid, and then calculate the building coverage and average building height. Road network condition indicators include road network density. Road centerline data can be intersected with the evaluation grid to calculate the total road length within each grid, and the road network density is calculated as the ratio of total road length to grid area. Functional distribution indicators include the spatial clustering of demand scenarios, noise-sensitive facilities, and privacy-sensitive facilities. Kernel density analysis can be performed on relevant POI categories, and the mean kernel density can be extracted using the evaluation grid as a unit to form corresponding functional distribution indicators.

[0052] (4) Data reclassification and weighted overlay: After calculating all evaluation indicators, the indicator layer is standardized and reclassified to eliminate dimensional differences between different indicators and unify the evaluation benchmark. Preferably, a 5-point scale can be used to assign values ​​to each spatial evaluation unit, with higher scores indicating greater suitability for the layout of drone instant delivery take-off and landing sites. Indicators with different directions should be processed as positive or negative. Among them, population activity intensity and demand scenario agglomeration can be used as positive indicators; peak population activity, distribution of noise-sensitive facilities, distribution of privacy-sensitive facilities, building coverage, and building height can be used as negative indicators. For negative indicators, reverse assignment is performed during the reclassification process to ensure that all indicators have a consistent direction when weighted and superimposed.

[0053] After reclassification, the evaluation indicators are weighted and summed according to preset weights to calculate the comprehensive suitability score for each spatial evaluation unit: ; in, Indicates the first The overall suitability score of each spatial evaluation unit, Indicates the first The weight of each evaluation indicator, Indicates the first The spatial evaluation unit in the first Standardized scores on each evaluation indicator This indicates the total number of evaluation indicators.

[0054] Finally, based on the comprehensive suitability score, the areas are classified into four levels: most suitable, relatively suitable, generally suitable, relatively unsuitable, and unsuitable. The areas where the most suitable and relatively suitable site selection units are concentrated are identified as high suitability areas.

[0055] Through the above steps, this invention can uniformly convert data from different sources, formats, and scales, such as building morphology, population activity, road organization, and distribution of functional facilities, into calculable indicators on spatial evaluation units. Furthermore, through standardization, positive and negative reclassification, and weighted superposition, it generates a comprehensive suitability score and grade classification for each spatial evaluation unit within the study area. Its technical effect lies in transforming the demand orientation, spatial environment, traffic conditions, and impact of sensitive facilities involved in the site selection of urban drone instant delivery take-off and landing sites into quantifiable and comparable spatial evaluation results. This allows for the identification of blocks or areas with high layout potential, providing a clear scope for subsequent candidate space extraction and controllable review.

[0056] Step S40: For the highly suitable area, candidate sites with actual spatial carrying capacity are extracted based on three-dimensional modeling and spatial identification methods. The candidate sites are then subject to control review based on operational safety, NIMBY coordination and feasibility. Potential sites that do not meet the control requirements are eliminated to obtain a set of candidate sites.

[0057] Specifically, after obtaining the comprehensive suitability assessment results, it is necessary to further combine spatial physical conditions to extract candidate spaces and conduct controllable verification of potential sites within the high suitability area. This step is used to address the connection between the suitability assessment results and the actual implementation space.

[0058] (1) Candidate space extraction: For the highly suitable areas identified in the suitability assessment, digital modeling and spatial identification are carried out based on 3D modeling methods to extract usable sites with practical carrying capacity, forming an initial candidate site set. Candidate spaces that can be included in the initial candidate site set include rooftop platforms, podium platforms, ground open spaces, or other spaces that can be used for the deployment of drone instant delivery take-off and landing sites, which meet the basic spatial carrying capacity conditions. The extraction of candidate spaces focuses on whether they have effective usable area, basic spatial integrity, and the possibility of subsequent facility deployment.

[0059] (2) Operational safety control review: The candidate sites undergo operational safety control verification. First, the initial candidate site set is screened based on airspace conditions. Candidate sites located in specific areas, danger zones, airspace above 120m, controlled airspace, or their buffer zones are excluded from subsequent site selection. Based on this, the initial candidate site set undergoes a clearance condition verification to determine whether it meets the requirements for unobstructed space, approach / takeoff surfaces, transition surfaces, and route protection zones. Candidate sites that do not meet the hard clearance constraints are eliminated, resulting in the first candidate site set.

[0060] (3) Review of NIMBY coordination and control: The candidate sites are subject to NIMBY (Not In My Backyard) coordination and control review. Based on the requirements related to noise impact and privacy impact, it is determined whether the candidate sites in the first candidate site set are located within sensitive spaces such as educational facilities, medical and elderly care facilities, residential facilities, and specific facilities. Candidate sites located within the scope of sensitive facilities are eliminated to obtain the second candidate site set.

[0061] (4) Feasibility control review: A feasibility control review is conducted on the candidate spaces. This review covers the candidate spaces within the second candidate site set, including land ownership verification, infrastructure condition verification, and access condition verification. Regarding land ownership, the review verifies whether the ownership of the land or infrastructure where the candidate space is located is clear, whether it has a single or clearly defined management entity, and assesses the suitability of its land use nature in conjunction with relevant planning land classifications. Regarding infrastructure conditions, the review examines the effective usable area and structural bearing capacity of the candidate space. Preferably, it determines whether the effective area of ​​the candidate space meets the average area requirement of the take-off and landing field, and whether its structural bearing capacity meets the requirements for facility layout and operational loads. Regarding access conditions, the review verifies whether the candidate space has stable power access, reliable communication access, and convenient ground transportation connections. If the candidate space is located on a non-ground level, vertical transportation conditions such as elevators, stairs, and connecting corridors also need to be verified. Furthermore, it should be determined whether it has closed or semi-closed management conditions to support subsequent operation management and safety isolation. Candidate sites that do not meet the control requirements in any aspect are eliminated (i.e., potential sites that do not meet the control requirements are eliminated); after control review, the set of candidate sites that meet the actual implementation conditions is retained.

[0062] Through the above steps, this invention can further refine highly suitable areas at the mesoscale into specific, identifiable, and verifiable candidate sites, and conduct controlled screening of candidate spaces from three aspects: operational safety, NIMBY (Not In My Backyard) coordination, and feasibility. Its technical advantage lies in enabling takeoff and landing site selection to move beyond spatial suitability evaluation to a concrete spatial framework. This avoids determining locations solely based on comprehensive scores while neglecting practical implementation conditions such as airspace restrictions, clearance conditions, avoidance of sensitive facilities, ownership relationships, structural load-bearing capacity, power and communication access, and vertical transportation. This improves the operational safety, urban coordination, and feasibility of candidate sites.

[0063] Step S50: Compare the candidate site set with the facility scale prediction results. If the number of candidate sites meets the prediction requirements, a final site selection scheme is formed, and the output content is expanded according to the hierarchy.

[0064] Specifically, the site selection plan is used to integrate the results of the aforementioned site selection area screening, facility scale prediction, suitability evaluation, candidate space extraction, and control review to form the final recommended construction plan.

[0065] First, determine whether the target urban area meets the basic conditions for setting up take-off and landing sites for drone instant delivery. Second, predict the demand and facility scale of the target urban area. Third, identify highly suitable blocks or areas based on the suitability assessment results. Subsequently, extract usable candidate spaces from the highly suitable areas and conduct operational safety, NIMBY (Not In My Backyard) coordination, and feasibility control checks on the candidate spaces. Finally, compare the set of candidate sites that have passed the feasibility control check with the facility scale prediction results. If the number of candidate sites that have passed the feasibility control check meets the predicted number of take-off and landing sites, the final site selection plan is formed. If the number of candidate sites that have passed the control check is insufficient, continue to extract candidate spaces and conduct control checks in the next most suitable areas (i.e., areas with a general suitability level) until the number of candidate sites meets the facility scale requirements.

[0066] The final output should be structured from macro to micro levels. At the macro level, it should clarify whether the target urban area has the basic conditions and required facility scale for the layout of drone instant delivery take-off and landing sites. At the meso level, it should output the suitability level of different spatial evaluation units within the study area and the distribution of highly suitable areas. At the micro level, it should identify specific candidate sites that have passed the operational safety, NIMBY coordination, and feasibility control review, and formulate a recommended construction plan that matches the predicted facility scale.

[0067] Through the above steps, the present invention can integrate the suitability evaluation results, the control review results, and the facility scale requirements, so that the final plan is not only spatially suitable, but also meets the predicted facility quantity requirements and actual construction conditions.

[0068] like Figure 2 As shown, this invention proposes a multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites. Its overall technical route is as follows: site selection area screening → facility scale prediction → suitability evaluation → candidate space extraction and control verification → site selection scheme determination.

[0069] First, based on the demand base and supply organization conditions of the target urban area, an assessment is made as to whether it meets the basic conditions for selecting take-off and landing sites for drone instant delivery, resulting in a site selection area screening result. This step is used to avoid ineffective site selection in areas with weak demand base or insufficient supply organization capacity. Second, assuming the target urban area meets the basic site selection conditions, the required number of drones and the scale of take-off and landing facilities are predicted by combining the instant delivery demand level, drone instant delivery penetration rate, drone operating efficiency, and average construction scale of take-off and landing sites in the target year. This prediction of facility scale provides a basis for subsequent site quantity control. Third, spatial evaluation units of the target urban area are constructed based on geographic information datasets. Combining indicators such as population heat maps, building characteristics, road network conditions, and functional facility distribution, a comprehensive evaluation of the suitability of take-off and landing site selection in different spatial evaluation units within the target urban area is conducted using standardization, reclassification, and weighted overlay methods to identify highly suitable areas. Subsequently, for the highly suitable areas identified in the suitability assessment, candidate sites with practical spatial carrying capacity are extracted using 3D modeling and spatial identification methods. These candidate sites undergo a control review from three aspects: operational safety, NIMBY (Not In My Backyard) coordination, and feasibility, eliminating potential sites that do not meet the control requirements. Finally, the set of candidate sites that have passed the control review is compared with the facility size prediction results. If the number of candidate sites meets the prediction requirements, a final site selection plan is formed; if the number is insufficient, candidate spatial extraction and control review continue in the next most suitable areas until the facility size requirements are met.

[0070] Through the above technical approach, this invention forms a progressive site selection method consisting of macro-regional screening, meso-level suitability evaluation, and micro-level spatial verification. This method can transform the site selection of UAV instant delivery take-off and landing sites from a single experience-based judgment into a comprehensive site selection process that combines demand identification, scale prediction, spatial evaluation, and control verification.

[0071] Furthermore, possible design changes or modifications to the present invention include: (1) The site selection rule system can be adjusted according to different cities and application scenarios. In addition to demand orientation, operational safety, NIMBY coordination and feasibility, rules such as meteorological conditions, electromagnetic environment, operating costs and public acceptance can also be added.

[0072] (2) Different alternative indicators can be used for site selection criteria. The demand base can be characterized by development intensity, population density, instant delivery order volume or commercial activity; the supply conditions can be characterized by regional business districts, catering and retail POI agglomeration, delivery station density or platform order data.

[0073] (3) The parameters for predicting facility scale can be adjusted according to the drone model and operation mode. Drone operating efficiency, delivery penetration rate, peak coefficient, unit drone area coefficient and average area of ​​a single take-off and landing site can all be replaced based on different enterprise operating data or planning scenarios.

[0074] (4) Suitability evaluation units and evaluation tools can take different forms. Spatial evaluation units can be regular grids, blocks, plots or individual buildings; evaluation tools can be implemented using ArcGIS, QGIS, Python, Rhino, CIM platform or other spatial analysis platforms.

[0075] (5) The candidate space types can be expanded according to the urban built environment. In addition to rooftop platforms, podium platforms and ground open spaces, they can also include transportation hub platforms, parking garage roofs, commercial complex roofs, public building roofs or industrial park platforms, etc.

[0076] (6) This invention can be used for site selection of take-off and landing sites for urban drone instant delivery, and can also be extended to site selection of low-altitude logistics terminal take-off and landing facilities such as express delivery, fresh food delivery, campus delivery, scenic area delivery, medical supplies delivery and emergency supplies delivery. As long as the same or equivalent "site selection rule system + five-step progressive process" is adopted, it should be considered an extension of this invention.

[0077] The focus of this invention is not on protecting the weighted overlay, weighting, conventional demand forecasting formulas, or 3D modeling tools themselves, but rather on protecting the combined application of these mature technologies within the urban drone instant delivery take-off and landing site selection rule system. Its core lies in transforming demand-oriented, operational safety, NIMBY (Not In My Backyard) coordination, and feasibility-based site selection rules into a phased site selection method consisting of macro-level regional screening, meso-level suitability evaluation, and micro-level site verification.

[0078] The evaluation index system in this invention is open and scalable. Currently, the indicators used are selected primarily based on methodological maturity, data availability, and quantifiability to ensure the site selection process is operable and verifiable under existing data conditions. As low-altitude logistics operation data, urban sensing data, meteorological data, electromagnetic environment data, noise monitoring data, public feedback data, and platform order data are further improved, relevant influencing factors can be incorporated into the site selection rule system and transformed into calculable evaluation indicators or control conditions. This expansion of indicators does not change the basic technical approach of this invention—"site selection rule system + phased site selection process"—but rather enhances the refinement, dynamic adaptability, and reliability of the site selection evaluation results.

[0079] The parameters in this invention should not be interpreted as fixed values. For example, the plot ratio threshold, service area of ​​the business district, peak coefficient, drone delivery penetration rate, full life cycle of a single drone, unit drone configuration area coefficient, average buildable area of ​​a single take-off and landing site, evaluation grid scale, suitability grading method, etc., can all be adjusted according to different cities, different operating companies, different drone models, and different planning years. Changes in the above parameters do not affect the site selection rule system and process organization method proposed in this invention.

[0080] The site selection results generated by this invention should be understood as a planning recommendation, rather than a fixed final construction plan. Since urban drone delivery is still in its developmental stage, low-altitude airspace management requirements, drone performance, noise control technology, delivery organization models, public acceptance, and corporate operational strategies may all change. Therefore, this invention is suitable as a dynamically updated site selection method, which can be periodically revised in subsequent applications based on the latest regulations, operational data, and site conditions.

[0081] Furthermore, such as Figure 3 As shown, based on the above-mentioned multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites, the present invention also provides a multi-source spatial data fusion site selection system for urban drone instant delivery take-off and landing sites, wherein the multi-source spatial data fusion site selection system for urban drone instant delivery take-off and landing sites includes: The site selection area screening module 51 is used to determine whether the target urban area has the basic conditions for carrying out drone instant delivery take-off and landing site selection based on the demand basis and supply organization conditions of the target urban area, and form the site selection area screening result. The facility scale prediction module 52 is used to predict the required number of drones and the scale of take-off and landing facilities if the target urban area meets the basic site selection conditions based on the site selection area screening results, and in combination with the instant delivery demand level, drone instant delivery penetration rate, drone operation efficiency and average construction scale of take-off and landing sites in the target year, so as to obtain the facility scale prediction results. The suitability evaluation module 53 is used to construct spatial evaluation units of the target urban area based on the geographic information dataset, and combine population heat map, building characteristics, road network conditions and functional facility distribution, and adopt standardization, reclassification and weighted overlay methods to comprehensively evaluate the suitability of take-off and landing site selection of different spatial evaluation units in the target urban area, and identify highly suitable areas. The candidate space extraction and controllability verification module 54 is used to extract candidate sites with actual spatial carrying capacity based on three-dimensional modeling and spatial identification methods for the high suitability area, and to perform controllability verification on the candidate sites from the aspects of operational safety, NIMBY coordination and feasibility, eliminating potential sites that do not meet the control requirements, and obtaining a candidate site set. The site selection scheme determination module 55 is used to compare the candidate site set with the facility scale prediction results. If the number of candidate sites meets the prediction requirements, a final site selection scheme is formed, and the output content should be expanded according to the hierarchy.

[0082] Furthermore, such as Figure 4 As shown, based on the above-mentioned multi-source spatial data fusion site selection method and system for urban drone instant delivery take-off and landing sites, the present invention also provides a terminal, which includes a processor 10, a memory 20 and a display 30. Figure 4 Only some of the terminal components are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0083] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory. In other embodiments, the memory 20 may be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal. Further, the memory 20 may include both internal and external storage devices. The memory 20 is used to store application software and various types of data installed on the terminal, such as program code installed on the terminal. The memory 20 can also be used to temporarily store data that has been output or will be output. In one embodiment, the memory 20 stores a multi-source spatial data fusion addressing program 40 for urban UAV instant delivery take-off and landing sites. This multi-source spatial data fusion addressing program 40 can be executed by the processor 10, thereby implementing the multi-source spatial data fusion addressing method for urban UAV instant delivery take-off and landing sites in this application.

[0084] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in the memory 20 or process data, such as executing the multi-source spatial data fusion site selection method for urban drone instant delivery take-off and landing sites.

[0085] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display 30 is used to display information on the terminal and to display a visual user interface. The terminal's processor 10, memory 20, and display 30 communicate with each other via a system bus.

[0086] In one embodiment, when the processor 10 executes the multi-source spatial data fusion location program 40 for urban UAV instant delivery take-off and landing sites stored in the memory 20, it implements the steps of the multi-source spatial data fusion location method for urban UAV instant delivery take-off and landing sites as described above.

[0087] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a multi-source spatial data fusion location program for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites, and the multi-source spatial data fusion location program for urban UAV instant delivery take-off and landing sites, when executed by a processor, implements the steps of the multi-source spatial data fusion location method for urban UAV instant delivery take-off and landing sites as described above.

[0088] In summary, this invention provides a multi-source spatial data fusion site selection method, system, terminal, and computer-readable storage medium for urban drone instant delivery take-off and landing sites. The method includes: determining whether the target urban area possesses the basic conditions for selecting a drone instant delivery take-off and landing site based on the demand and supply organization conditions of the target urban area, thus forming a site selection area screening result; if the target urban area meets the basic site selection conditions based on the site selection area screening result, predicting the required number of drones and the scale of take-off and landing site facilities by combining the instant delivery demand level, drone instant delivery penetration rate, drone operating efficiency, and average construction scale of the take-off and landing site in the target year, thus obtaining a facility scale prediction result; and constructing the target urban area based on a geographic information dataset. The invention uses spatial evaluation units within a district, combined with population heat maps, building characteristics, road network conditions, and functional facility distribution, employing standardization, reclassification, and weighted overlay methods to comprehensively evaluate the suitability of take-off and landing site selection in different spatial evaluation units within the target urban area, identifying highly suitable areas. For these highly suitable areas, candidate sites with practical spatial carrying capacity are extracted based on 3D modeling and spatial recognition methods. These candidate sites undergo a controlled review from the perspectives of operational safety, NIMBY (Not In My Backyard) coordination, and feasibility, eliminating potential sites that do not meet the control requirements, resulting in a candidate site set. This candidate site set is compared with the facility scale prediction results. If the number of candidate sites meets the prediction requirements, a final site selection scheme is formed, and the output content should be expanded hierarchically. This invention enables synergistic linkage between demand assessment, facility scale prediction, spatial suitability evaluation, candidate space extraction, and construction scheme determination, helping to improve the scientific rigor, safety, and feasibility of urban drone instant delivery take-off and landing site selection, and enhancing the adaptability of take-off and landing site layout to urban spatial structure, instant delivery needs, operational safety requirements, and specific construction conditions.

[0089] 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 terminal 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 terminal. 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 terminal that includes that element.

[0090] Of course, those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.). The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The computer-readable storage medium can be a memory, magnetic disk, optical disk, etc.

[0091] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A multi-source spatial data fusion site selection method for urban UAV instant delivery landing sites, characterized in that, The multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites includes: Based on the demand base and supply organization conditions of the target urban area, it is determined whether the target urban area has the basic conditions for selecting a site for drone instant delivery take-off and landing, and a site selection area screening result is formed. If the target urban area meets the basic site selection conditions based on the site selection area screening results, the required number of drones and the scale of take-off and landing facilities are predicted by combining the instant delivery demand level, drone instant delivery penetration rate, drone operation efficiency and average construction scale of take-off and landing sites in the target year, and the facility scale prediction results are obtained. Based on the geographic information dataset, spatial evaluation units of the target urban area are constructed. Combining population heat map, building characteristics, road network conditions and functional facility distribution, standardization, reclassification and weighted overlay methods are used to comprehensively evaluate the suitability of take-off and landing site selection of different spatial evaluation units in the target urban area and identify highly suitable areas. For the highly suitable area, candidate sites with actual spatial carrying capacity are extracted based on three-dimensional modeling and spatial identification methods. The candidate sites are then subject to control review from the perspectives of operational safety, NIMBY coordination and feasibility. Potential sites that do not meet the control requirements are eliminated to obtain a set of candidate sites. The candidate site set is compared with the facility size prediction results. If the number of candidate sites meets the prediction requirements, a final site selection plan is formed, and the output content should be expanded according to the hierarchy.

2. The multi-source spatial data fusion site selection method for urban drone instant delivery landing sites according to claim 1, characterized in that, Based on the demand and supply organization conditions of the target urban area, the method of determining whether the target urban area possesses the basic conditions for selecting a site for drone instant delivery take-off and landing is used to form a site selection area screening result, specifically including: Obtain the demand base and supply organization conditions of the target urban area; Based on the aforementioned demand basis, it is determined whether the target urban area has the basic order scale to support the normalized operation of drone instant delivery. Whether the target urban area belongs to a high-intensity built-up area is used as the demand basis discrimination condition. When the plot ratio of the target urban area is not lower than a preset threshold, or belongs to a high-density area determined in the urban planning, it is determined that the target urban area has the demand basis for instant delivery. Based on the supply organization conditions, determine whether the target urban area has the supply organization foundation to support the operation of drone instant delivery, and determine whether there is a regional business district, large shopping center, commercial complex or multiple commercial facilities cluster area in the target urban area or within a certain service range of the target urban area. If so, determine that the target urban area has the supply organization foundation for instant delivery operation. The site selection results are obtained based on the judgment of demand and the judgment of supply organization conditions.

3. The multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites according to claim 1, characterized in that, The facility size forecast results include peak daily demand for on-demand delivery, the number of on-demand delivery drones, and the size of on-demand delivery take-off and landing sites; The method combines the target year's on-demand delivery demand level, drone on-demand delivery penetration rate, drone operational efficiency, and average construction scale of take-off and landing sites to predict the required number of drones and the scale of take-off and landing site facilities, resulting in a facility scale prediction result, specifically including: Predicting peak daily demand for instant delivery: Forecast the average daily demand for instant delivery in the study area for the target year, and predict future... The average daily demand for instant delivery per year is expressed as follows: ； in, express The average daily demand for on-demand delivery in the research area in 2018 express Annual study area service population, Indicates the penetration rate of on-demand delivery users. This indicates the average daily order volume per person. Calculate peak demand: ； in, express Annual research on peak demand for on-demand delivery in the region Indicates the peak value; After obtaining the peak-hour instant delivery demand, calculate the peak-hour order volume handled by drones: ； in, express Annual peak drone order volume in the research area This indicates the penetration rate of drone-based instant delivery; Predicted number of on-demand delivery drones: After obtaining the peak order volume for drones, and combining this with the entire lifecycle of a single drone, calculate the carrying capacity per unit time during the peak period: ； in, This indicates the carrying capacity of a single drone per unit time during peak hours. This indicates the entire lifecycle of a single drone; Calculate the number of drones required under peak operating conditions in the study area: ； in, express Number of drones required during peak periods in the annual research area Indicates the available coefficients of the system. Indicates rounding up; Predicted size of on-demand delivery takeoff and landing sites: After obtaining the number of drones, calculate the total area of ​​take-off and landing fields required for the study area in the target year based on the take-off and landing field area coefficient corresponding to the configuration of each drone: ； in, express Total area of ​​takeoff and landing field required for the annual study area This indicates the takeoff and landing area coefficient corresponding to a unit of UAV configuration; Based on the average buildable area of ​​a single takeoff and landing field, calculate the number of takeoff and landing fields required for the study area: ； in, express Number of take-off and landing fields required in the annual study area This indicates the average buildable area of ​​a single take-off and landing field.

4. The multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites according to claim 1, characterized in that, The spatial evaluation units of the target urban area are constructed based on geographic information datasets. Combining population heat maps, building characteristics, road network conditions, and functional facility distribution, and employing standardization, reclassification, and weighted overlay methods, the suitability of takeoff and landing site selection for different spatial evaluation units within the target urban area is comprehensively evaluated to identify highly suitable areas. Specifically, this includes: Construct a geographic information dataset for the selection of take-off and landing sites for drone instant delivery, the geographic information dataset including urban spatial structure data and urban functional distribution data; After establishing the geographic information dataset, the study area is divided into regular grids to form several spatial evaluation units; Based on the geographic information dataset and the spatial evaluation unit, the evaluation indicators are quantitatively calculated. The evaluation indicators include population heat map, building characteristics, road network conditions and functional distribution. After calculating all evaluation indicators, the indicator layers are standardized and reclassified to eliminate dimensional differences between different indicators and to unify the evaluation benchmark. After reclassification, the evaluation indicators are weighted and superimposed according to preset weights to calculate the comprehensive suitability score for each spatial evaluation unit. ； in, Indicates the first The overall suitability score of each spatial evaluation unit, Indicates the first The weight of each evaluation indicator, Indicates the first The spatial evaluation unit in the first Standardized scores on each evaluation indicator Indicates the total number of evaluation indicators; Based on the comprehensive suitability score, the areas are classified into four levels: most suitable, relatively suitable, generally suitable, relatively unsuitable, and unsuitable. The areas where the most suitable and relatively suitable site selection units are concentrated are identified as high suitability areas.

5. The multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites according to claim 4, characterized in that, The urban spatial structure data includes building-related data, population thermal data, and road network-related data; the building-related data is used to calculate the average building height and building coverage, the population thermal data is used to calculate the average and peak population thermal values, and the road network-related data is used to calculate the road network density. The urban functional distribution data includes POI data, which includes demand scenarios, noise-sensitive facilities, and privacy-sensitive facilities.

6. The multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites according to claim 4, characterized in that, For the highly suitable areas, candidate sites with practical spatial carrying capacity are extracted based on 3D modeling and spatial identification methods. These candidate sites are then subject to a control review based on operational safety, NIMBY (Not In My Backyard) compliance, and feasibility. Potential sites that do not meet the control requirements are eliminated, resulting in a candidate site set, specifically including: For the highly suitable areas identified by the suitability assessment, digital modeling and spatial identification are carried out based on the three-dimensional modeling method to extract usable sites with actual carrying capacity and form an initial candidate site set; The initial candidate site set is screened out according to the airspace conditions, and the airspace conditions of the initial candidate site set are reviewed. Candidate spaces that do not meet the hard airspace constraints are eliminated to obtain the first candidate site set. Based on the requirements related to noise impact and privacy impact, it is determined whether the candidate spaces in the first candidate site set are located within sensitive spaces. Candidate spaces located within the scope of sensitive facilities are eliminated to obtain the second candidate site set. The feasibility and controllability of the candidate spaces in the second candidate site set are reviewed. The feasibility and controllability review includes land ownership review, carrier condition review and access condition review. Potential sites that do not meet the control requirements are eliminated to obtain the candidate site set.

7. The multi-source spatial data fusion site selection method for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites according to claim 6, characterized in that, The process involves comparing the candidate site set with the facility size prediction results. If the number of candidate sites meets the prediction requirements, a final site selection plan is formed, and the output should be expanded hierarchically, specifically including: The candidate site set, which has undergone feasibility control review, will be compared with the facility size prediction results. If the number of candidate sites that pass the feasibility control review meets the predicted number of takeoff and landing sites, then the final site selection plan is formed. If the number of candidate sites that pass the control review is insufficient, continue to carry out candidate space extraction and control review in areas classified as generally suitable until the number of candidate sites meets the facility scale requirements. The output should be presented in a hierarchical manner from macro to micro. At the macro level, it should clarify whether the target urban area has the basic conditions and required facility scale for the layout of drone instant delivery take-off and landing sites. At the meso level, it should output the suitability level of different spatial evaluation units in the study area and the distribution of highly suitable areas. At the micro level, it should identify specific candidate sites that have passed the control review of operational safety, NIMBY coordination and feasibility, and form a recommended construction plan that matches the predicted facility scale.

8. A multi-source spatial data fusion site selection system for urban unmanned aerial vehicle (UAV) instant delivery take-off and landing sites, characterized in that, The multi-source spatial data fusion site selection system for urban drone instant delivery take-off and landing sites includes: The site selection area screening module is used to determine whether the target urban area has the basic conditions for selecting a drone instant delivery take-off and landing site based on the demand base and supply organization conditions of the target urban area, and to form a site selection area screening result. The facility scale prediction module is used to predict the required number of drones and the scale of take-off and landing facilities if the target urban area meets the basic site selection conditions based on the site selection area screening results, and in combination with the instant delivery demand level, drone instant delivery penetration rate, drone operation efficiency and average construction scale of take-off and landing sites in the target year, so as to obtain the facility scale prediction results. The suitability evaluation module is used to construct spatial evaluation units of the target urban area based on the geographic information dataset, and combine population heat map, building characteristics, road network conditions and functional facility distribution. It adopts standardization, reclassification and weighted overlay methods to comprehensively evaluate the suitability of take-off and landing site selection of different spatial evaluation units in the target urban area and identify highly suitable areas. The candidate space extraction and controllability verification module is used to extract candidate sites with actual spatial carrying capacity based on three-dimensional modeling and spatial recognition methods for the high suitability area, and to perform controllability verification on the candidate sites from the aspects of operational safety, NIMBY coordination and feasibility, eliminating potential sites that do not meet the control requirements, and obtaining a candidate site set; The site selection scheme determination module is used to compare the candidate site set with the facility scale prediction results. If the number of candidate sites meets the prediction requirements, a final site selection scheme is formed, and the output content should be expanded according to the hierarchy.

9. A terminal, characterized in that, The terminal includes: a memory, a processor, and a multi-source spatial data fusion location program for urban drone instant delivery take-off and landing sites stored in the memory and executable on the processor. When the processor executes the multi-source spatial data fusion location program for urban drone instant delivery take-off and landing sites, it implements the steps of the multi-source spatial data fusion location method for urban drone instant delivery take-off and landing sites as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a multi-source spatial data fusion location program for urban drone instant delivery take-off and landing sites. When the multi-source spatial data fusion location program for urban drone instant delivery take-off and landing sites is executed by a processor, it implements the steps of the multi-source spatial data fusion location method for urban drone instant delivery take-off and landing sites as described in any one of claims 1-7.

Images