Take-out station site selection method and device based on multiple factors and medium

Abstract

The invention discloses a take-out station site selection method and device based on multiple factors and a medium, and relates to the technical field of station site selection. The method comprises the following steps: dividing a take-out target area through a space grid, and generating target grid units; obtaining multi-factor data and historical orders of the target grid unit, and extracting a thermodynamic distribution diagram and time dimension fluctuation characteristics from the historical orders; constructing a multi-dimensional evaluation matrix, and calculating the score of the target grid unit in each dimension; and determining a weight coefficient of each dimension based on an analytic hierarchy process, generating a weighted score, sorting the target grid units according to the weighted score, and selecting a target area with a preset rank as a courier site. According to the method, through gridding precise analysis, multi-dimensional scientific evaluation, dynamic demand capture and competition differentiation positioning, the precision of take-out courier station site selection is remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of post station site selection, and in particular to a method, device and medium for site selection of a takeaway post station based on multiple factors. Background Art

[0002] With the popularity of online catering services, the food delivery industry has developed rapidly. As a workplace for riders to rest, the rationality of the location of food delivery stations is directly related to the delivery efficiency and service quality. Generally speaking, riders will eat, charge, and take other rest activities at food delivery stations during non-peak ordering times. The choice of the station location must not only consider the comfort of the environment, but also the convenience of the location for riders to go to merchants or consumer groups at any time. However, in reality, since food delivery stations are mostly non-profit operations led by government agencies, they do not fully consider the actual needs of riders, lack systematic and data-driven planning methods, and are often far away from places where restaurants are gathered or where demand for food delivery is high, resulting in uneven resource allocation and low utilization rate of food delivery riders.

[0003] Through the above analysis, the problems and defects of the existing technology are as follows:

[0004] The site selection of food delivery stations in the existing technology does not fully consider the actual needs of riders, resulting in uneven resource allocation and low utilization rate of food delivery riders. Summary of the Invention

[0005] The embodiments of the present application provide a method, device and medium for site selection of a takeaway station based on multiple factors, which can solve the problem in the prior art that the site selection of a takeaway station does not fully consider the actual needs of riders, resulting in uneven resource allocation and low utilization rate of takeaway riders.

[0006] In the first aspect, an embodiment of the present application provides a method for site selection of a takeaway station based on multiple factors, the method comprising: dividing the takeaway target area through spatial grids to generate target grid units; obtaining multi-factor data and historical orders of the target grid units, the multi-factor data including residential community data, office building data and existing station data, and extracting heat distribution maps and time dimension fluctuation characteristics from the historical orders; constructing a multi-dimensional evaluation matrix to calculate the score of the target grid unit in each dimension, the multi-dimensionality including the road accessibility dimension and the market competition dimension, and the existing station distribution data is reverse normalized by the distance threshold method; determining the weight coefficient of each dimension based on the hierarchical analysis method, generating a weighted score, and sorting the target grid units according to the weighted score, and selecting the target area with a preset ranking as the station site selection.

[0007] In one implementation of the present application, multi-factor data and historical orders of the target grid unit are obtained, specifically including: collecting real-time traffic flow data within the target grid unit; collecting the opening hours information of the community and office building in the community data and office building data, and the opening hours information includes whether deliverymen are prohibited from entering and exiting; collecting the geographic coordinates and service coverage of existing delivery stations, and calculating the station density.

[0008] In one implementation of the present application, the method further includes: calculating a traffic congestion index based on traffic flow data; calculating the straight-line distance and actual distance of the delivery area based on opening time information, the actual distance including cycling distance and human distance; calculating the transportation cost per unit distance based on the road slope of the target grid unit and the type of delivery vehicle; and calculating the average delivery time based on real-time traffic flow data and historical data.

[0009] In one implementation of the present application, heat distribution maps and time dimension fluctuation characteristics are extracted from historical orders, specifically including: eliminating abnormal orders from historical orders, abnormal orders include delivery time exceeding a preset time period and delivery distance exceeding a preset distance; classifying the processed historical orders by working days and holidays to obtain classified and stored order data; establishing a time slicing mechanism for the classified and stored order data, and generating order density heat maps according to different time periods.

[0010] In one implementation of the present application, the weight coefficient of each dimension is determined based on the hierarchical analysis method, specifically including: constructing a hierarchical judgment matrix of sub-indicators for the road accessibility dimension and the market competition dimension, the sub-indicators include traffic congestion index, actual distance, transportation cost, average delivery time, and the market competition dimension is the post station density after reverse normalization; combining historical data to verify the hierarchical judgment matrix; performing spatiotemporal coupling weight calculation on the verified hierarchical judgment matrix to generate an adaptive weighted scoring model.

[0011] In one implementation of the present application, after selecting a preset ranked target area as the station site, the method also includes: defining the boundary range of the target grid unit through geo-fencing technology, and extracting the current land use data within the boundary; screening available plots based on the current land use data, and eliminating areas with planned land use; and conducting on-site road network connectivity verification on the remaining available plots to generate the final station site.

[0012] In one implementation of the present application, after selecting a preset ranked target area as the station site, the method also includes: conducting on-site verification of the preset ranked target area, deploying temporary signal acquisition equipment, and counting the actual frequency of intersections between pedestrians and vehicles to simulate the probability of path conflict; and feeding back the path conflict probability to the evaluation matrix.

[0013] In one implementation of the present application, the transportation cost per unit distance is calculated in combination with the road slope of the target grid unit and the type of delivery vehicle, specifically including: obtaining road lighting intensity data during different delivery periods and associating it with the additional energy consumption coefficient for nighttime delivery; counting sections of road with high traffic accident rates and superimposing a safety risk correction factor; and calculating the impact of charging intervals on continuous delivery capabilities in combination with electric vehicle battery life data.

[0014] In a second aspect, an embodiment of the present application also provides a multi-factor based takeaway station site selection device, the device including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable at least one processor to: divide the takeaway target area by spatial grids to generate target grid units; obtain multi-factor data and historical orders of the target grid units, the multi-factor data including residential community data, office building data and existing station data, and extract thermal distribution maps and time dimension fluctuation characteristics from the historical orders; construct a multi-dimensional evaluation matrix to calculate the score of the target grid unit in each dimension, the multi-dimensionality including road accessibility dimension and market competition dimension, and the existing station distribution data is reverse normalized by the distance threshold method; determine the weight coefficient of each dimension based on the hierarchical analysis method, generate a weighted score, and sort the target grid units according to the weighted score, and select the target area with a preset ranking as the station site selection.

[0015] On the third aspect, the embodiment of the present application also provides a non-volatile computer storage medium for takeout station site selection based on multiple factors, which stores computer executable instructions, and the computer executable instructions are set to: divide the takeout target area by spatial grid to generate target grid units; obtain multi-factor data and historical orders of the target grid units, the multi-factor data includes residential community data, office building data and existing station data, and extract thermal distribution maps and time dimension fluctuation characteristics from the historical orders; construct a multi-dimensional evaluation matrix, calculate the score of the target grid unit in each dimension, the multi-dimensionality includes road accessibility dimension and market competition dimension, and the existing station distribution data is reverse normalized by the distance threshold method; determine the weight coefficient of each dimension based on the hierarchical analysis method, generate a weighted score, and sort the target grid units according to the weighted score, and select the target area with a preset ranking as the station site selection.

[0016] The embodiment of the present application provides a method, equipment and medium for site selection of takeaway stations based on multiple factors. The method divides the takeaway demand area into small-scale grid units, which can accurately capture local demand differences; combines data such as residential areas, office buildings, and existing stations to cover core elements such as population distribution, commercial activities, and competitive situation; constructs a dimensional matrix of road accessibility, market competition, etc., and processes existing station data through reverse standardization to quantify the site selection advantages and disadvantages of each grid and reduce the influence of subjective judgment; determines the weight of each dimension based on the hierarchical analysis method, generates a weighted score, ensures that the site selection decision takes into account both global and local factors, and improves the scientific nature and stability of the site selection. It significantly improves the accuracy of the site selection of takeaway stations, helps reduce operational risks, and improves the comfort of riders. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A flowchart of a method for selecting a takeaway delivery station location based on multiple factors provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the internal structure of a takeaway station site selection device based on multiple factors provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] The embodiments of the present application provide a method, device and medium for site selection of a takeaway station based on multiple factors, which solves the problem in the prior art that the site selection of a takeaway station does not fully consider the actual needs of riders, resulting in uneven resource allocation and low utilization rate of takeaway riders.

[0022] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0023] Figure 1 This is a flow chart of a method for selecting a takeaway station location based on multiple factors provided in the embodiment of this application. Figure 1 As shown, the embodiment of the present application provides a method for selecting a takeaway station location based on multiple factors, which specifically includes the following steps:

[0024] Step 10: Divide the takeaway target area into spatial grids and generate target grid cells;

[0025] In this step, the target area is divided into regular or irregular grid cells based on the urban road network and geographic boundaries. The cell size is dynamically adjusted according to the data accuracy. For example, in the following order density heat map, the higher-density areas are divided into 50m×50m, and the lower-density areas are divided into 200m×200m. The grid boundaries are ensured to be aligned with natural or artificial barriers such as roads and rivers to avoid data fragmentation.

[0026] Step 20: Obtain multi-factor data and historical orders of the target grid cell. The multi-factor data includes residential area data, office building data, and existing post station data. Extract the heat distribution map and time dimension fluctuation characteristics from the historical orders.

[0027] As an optional embodiment, obtaining multi-factor data and historical orders of the target grid unit may specifically include: Step 201: collecting real-time traffic flow data within the target grid unit; Step 202: collecting the opening hours information of the community and office building in the community data and office building data, and the opening hours information includes whether deliverymen are prohibited from entering and exiting; Step 203: collecting the geographic coordinates and service coverage of existing food delivery stations, and calculating the station density.

[0028] In this step, the real-time traffic speed, density, and congestion status of the main roads within the target grid unit are obtained through traffic cameras, vehicle GPS, or third-party APIs. The opening hours of residential communities and office buildings, or whether there are designated places for takeout, are collected, prohibited periods are marked, and a time constraint map is generated. The geographic coordinates and service coverage of the takeout stations are extracted, and the delivery drivers can be asked about the acceptable rest distance and order coverage to calculate the station density.

[0029] As an optional embodiment, the method may further include: step 204: calculating a traffic congestion index based on traffic flow data; step 205: calculating a straight-line distance and an actual distance of a delivery area based on opening hour information, where the actual distance includes a cycling distance and a human distance; step 206: calculating the transportation cost per unit distance based on the road slope of the target grid unit and the type of delivery vehicle; step 207: calculating the average delivery time based on real-time traffic flow data and historical data.

[0030] In this step, the congestion index = (real-time average speed / free-flow speed) × 100%. For example, if the congestion index is less than 50%, it is marked as a high-congestion area, and the time cost weight is increased in subsequent evaluations. The Dijkstra path planning algorithm is used to calculate the artificial distance based on the road slope and traffic flow. Based on the opening hours information, a detour penalty coefficient is added to the areas where delivery drivers are prohibited from entering. In other words, whether the detour distance is increased:

[0031]

[0032] Among them, θ is the slope, C0 is the basic energy consumption rate, γ is the endurance penalty coefficient, and α is the traffic congestion correction coefficient.

[0033]

[0034] Among them, di is the actual distance of the i-th path; vi is the real-time vehicle speed (affected by the congestion index); t,i is the waiting time caused by the open time constraint.

[0035] As an optional embodiment, extracting heat distribution maps and time dimension fluctuation characteristics from historical orders can specifically include: Step 208: eliminating abnormal orders from historical orders, abnormal orders include delivery time exceeding a preset time period and delivery distance exceeding a preset distance; Step 209: classifying the processed historical orders by working days and holidays to obtain classified and stored order data; Step 210: establishing a time slicing mechanism for the classified and stored order data, and generating order density heat maps according to different time periods.

[0036] In this step, the classified order data is sliced ​​according to a preset time period, such as every 10 minutes. The number of orders in the target grid cell in each slice is counted, and the order quantity is mapped to the corresponding grid cell to generate an order density matrix. The order density of different time periods is superimposed to form a dynamic heat map sequence.

[0037] Step 30: Construct a multi-dimensional evaluation matrix and calculate the score of the target grid unit in each dimension. The multi-dimensional dimensions include road accessibility and market competition. The existing post station distribution data is reverse normalized using the distance threshold method.

[0038] In this step,

[0039] Among them, Dmax is the maximum impact distance, d is the actual distance, S 竞争 =1, that is, the target grid cell is located in the post station coverage blind area; S 竞争= 0, indicating that the target grid cell is directly adjacent to an existing post station, indicating the most intense competition. The order overlap ratio between the target grid cell and the existing post station's service area is calculated as a supplementary indicator of the competition dimension. The road accessibility index and market competition data calculated in steps 201-210 are then reverse normalized, scored, and matrix-integrated to obtain a comprehensive score for each target grid cell.

[0040] Step 40: Determine the weight coefficient of each dimension based on the hierarchical analysis method, generate a weighted score, and sort the target grid units according to the weighted score, and select the target area with a preset ranking as the station site.

[0041] As an optional embodiment, the weight coefficient of each dimension is determined based on the hierarchical analysis method, which may specifically include: Step 401: Constructing a hierarchical judgment matrix of sub-indicators for the road accessibility dimension and the market competition dimension, respectively. The sub-indicators include traffic congestion index, actual distance, transportation cost, and average delivery time. The market competition dimension is the station density after reverse normalization; Step 402: Verifying the hierarchical judgment matrix in combination with historical data; Step 403: Performing spatiotemporal coupling weight calculation on the verified hierarchical judgment matrix to generate an adaptive weighted scoring model.

[0042] In this step, the weights of each sub-indicator are dynamically adjusted based on historical order time fluctuations, such as weekday and weekend schedules and morning and evening peak hours. The "Traffic Congestion Index" is weighted higher during peak hours, while the "Average Delivery Time" is spatially weighted based on the grid cell's geographic location and the presence of office buildings during the lunch hour. This spatiotemporal coupling of weights enables the model to capture both temporal fluctuations and spatial variations in regional demand. For each dimension, a pairwise comparison matrix is ​​constructed between the sub-indicators to reflect their relative importance.

[0043] As an optional embodiment, after selecting a preset ranked target area as the station site, the method may also include: defining the boundary range of the target grid unit through geo-fencing technology, and extracting the current land use data within the boundary; screening available plots based on the current land use data, and eliminating areas with planned land use; and conducting on-site road network connectivity verification on the remaining available plots to generate the final station site.

[0044] In this step, the current land use map of the target area can be obtained through a third-party data service provider.

[0045] As an optional embodiment, after selecting a preset ranked target area as the station site, the method may further include: conducting on-site verification of the preset ranked target area, deploying temporary signal acquisition equipment, and counting the actual frequency of intersections between pedestrians and vehicles to simulate the probability of path conflict; and feeding back the path conflict probability to the evaluation matrix.

[0046] In this step, adding the "path conflict probability" indicator to the site selection evaluation matrix can quickly identify high-risk areas and optimize site selection to ensure the safety and efficiency of station operations.

[0047] Furthermore, the transportation cost per unit distance is calculated in combination with the road slope of the target grid unit and the type of delivery vehicle, which may specifically include: Step 2061: obtaining road illumination intensity data at different delivery time periods, and associating it with the additional energy consumption coefficient for nighttime delivery; Step 2062: counting sections of road with high traffic accident incidence, and superimposing a safety risk correction factor; Step 2063: combining electric vehicle battery life data, and calculating the impact of charging intervals on continuous delivery capabilities.

[0048] In this step, for example, if the daily demand exceeds the effective range of a single vehicle, it is necessary to add vehicles or adjust the delivery range to avoid frequent charging leading to increased costs. The transportation costs of different grid units can be quickly evaluated, providing an intuitive and operational decision-making basis for the site selection of the post station.

[0049] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, this application embodiment also provides a takeaway station location selection device based on multiple factors, the structure of which is as follows: Figure 2 shown.

[0050] Figure 2 This is a schematic diagram of the internal structure of a takeaway station location selection device based on multiple factors provided in an embodiment of the present application. Figure 2 As shown, the equipment includes:

[0051] at least one processor 201;

[0052] and, a memory 202 communicatively coupled to the at least one processor;

[0053] Among them, the memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to: divide the takeaway target area through spatial grids to generate target grid units; obtain multi-factor data and historical orders of the target grid units, the multi-factor data includes residential community data, office building data and existing station data, and extract thermal distribution maps and time dimension fluctuation characteristics in the historical orders; construct a multi-dimensional evaluation matrix to calculate the score of the target grid unit in each dimension, the multi-dimensionality includes road accessibility dimension and market competition dimension, and the existing station distribution data is reverse normalized by the distance threshold method; determine the weight coefficient of each dimension based on the hierarchical analysis method, generate a weighted score, and sort the target grid units according to the weighted score, and select the target area with a preset ranking as the station site.

[0054] Some embodiments of the present application provide corresponding Figure 1A non-volatile computer storage medium for takeout station site selection based on multiple factors stores computer executable instructions, wherein the computer executable instructions are configured to: divide a takeout target area by spatial grids to generate target grid cells; obtain multi-factor data and historical orders of the target grid cells, wherein the multi-factor data includes residential area data, office building data, and existing station data, and extract heat distribution maps and time dimension fluctuation characteristics from the historical orders; construct a multi-dimensional evaluation matrix to calculate the score of the target grid cells in each dimension, wherein the multi-dimensionality includes road accessibility dimension and market competition dimension, and the existing station distribution data is reversely normalized using a distance threshold method; determine the weight coefficient of each dimension based on the hierarchical analysis method to generate a weighted score, and rank the target grid cells according to the weighted score, and select the target area with a preset ranking as the station site selection.

[0055] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from the other embodiments. In particular, the IoT device and media embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0056] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0057] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0058] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0061] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0062] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0063] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0064] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0065] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for selecting a takeaway station location based on multiple factors, characterized in that: The method comprises: Divide the takeaway target area by spatial grid and generate target grid cells; Acquire multi-factor data and historical orders of the target grid unit, wherein the multi-factor data includes residential area data, office building data, and existing post station data, and extract heat distribution maps and time dimension fluctuation characteristics from the historical orders; Constructing a multi-dimensional evaluation matrix and calculating the score of the target grid unit in each dimension, wherein the multi-dimensionality includes the road accessibility dimension and the market competition dimension, and the existing post station distribution data is reverse normalized using the distance threshold method; Based on the hierarchical analysis method, the weight coefficient of each dimension is determined to generate a weighted score, and the target grid units are sorted according to the weighted score, and the target area with a preset ranking is selected as the station site.

2. A method for selecting a takeaway delivery station location based on multiple factors according to claim 1, characterized in that: Obtain multi-factor data and historical orders of the target grid unit, specifically including: Collecting real-time traffic flow data within the target grid unit; In the residential area data and office building data, the opening hours information of the residential area and office building is collected, and the opening hours information includes whether delivery drivers are prohibited from entering or leaving; Collect the geographic coordinates and service coverage of existing food delivery stations, and calculate the station density.

3. A method for selecting a takeaway delivery station location based on multiple factors according to claim 2, characterized in that: The method further comprises: Calculating a traffic congestion index based on the traffic flow data; Calculate the straight-line distance and actual distance of the delivery area according to the opening time information, wherein the actual distance includes the cycling distance and the manual distance; Calculate the transportation cost per unit distance based on the road slope of the target grid cell and the type of delivery vehicle; Calculate average delivery time based on real-time traffic flow data and historical data.

4. A method for selecting a takeaway delivery station location based on multiple factors according to claim 1, characterized in that: The heat distribution map and time dimension fluctuation characteristics are extracted from historical orders, including: Eliminate abnormal orders from the historical orders, such as orders with delivery time exceeding a preset time or delivery distance exceeding a preset distance; The processed historical orders are classified by working days and holidays to obtain classified and stored order data; A time slicing mechanism is established for the classified and stored order data, and an order density heat map is generated according to different time periods.

5. The method for selecting a takeaway delivery station location based on multiple factors according to claim 3, characterized in that: The weight coefficient of each dimension is determined based on the hierarchical analysis method, including: For the road accessibility dimension and the market competition dimension, a hierarchical judgment matrix of sub-indicators is constructed respectively. The sub-indicators include the traffic congestion index, actual distance, transportation cost, and average delivery time. The market competition dimension is the post station density after reverse normalization. Verifying the hierarchical judgment matrix in combination with the historical data; The spatiotemporal coupling weights of the verified hierarchical judgment matrix are calculated to generate an adaptive weighted scoring model.

6. A method for selecting a takeaway delivery station location based on multiple factors according to claim 1, characterized in that: After selecting the target area with a preset ranking as the post station location, the method further includes: Defining the boundary of the target grid cell by geo-fencing technology and extracting the land use status data within the boundary; Screen available plots based on the land use status data and exclude areas where land use has been planned; Conduct on-site road network connectivity verification on the remaining available plots to generate the final station location.

7. The method for selecting a takeaway delivery station location based on multiple factors according to claim 1, characterized in that: After selecting the target area with a preset ranking as the post station location, the method further includes: Conduct field verification in the target areas of the preset rankings, deploy temporary signal collection equipment, and count the actual frequency of pedestrian and vehicle intersections to simulate the probability of path conflicts; The path conflict probability is fed back to the evaluation matrix.

8. The method for selecting a takeaway delivery station location based on multiple factors according to claim 1, characterized in that: The transportation cost per unit distance is calculated based on the road slope of the target grid cell and the type of delivery vehicle, including: Obtain road light intensity data at different delivery times and correlate it with the additional energy consumption coefficient for nighttime delivery; Collect statistics on high-incidence sections of traffic accidents and add safety risk correction factors; Combined with electric vehicle battery life data, the impact of charging interval on continuous delivery capability is calculated.

9. A takeaway station location selection device based on multiple factors, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Divide the takeaway target area by spatial grid and generate target grid cells; Acquire multi-factor data and historical orders of the target grid unit, wherein the multi-factor data includes residential area data, office building data, and existing post station data, and extract heat distribution maps and time dimension fluctuation characteristics from the historical orders; Constructing a multi-dimensional evaluation matrix and calculating the score of the target grid unit in each dimension, wherein the multi-dimensionality includes the road accessibility dimension and the market competition dimension, and the existing post station distribution data is reverse normalized using the distance threshold method; Based on the hierarchical analysis method, the weight coefficient of each dimension is determined to generate a weighted score, and the target grid units are sorted according to the weighted score, and the target area with a preset ranking is selected as the station site.

10. A non-volatile computer storage medium for selecting a takeaway station location based on multiple factors, storing computer-executable instructions, characterized in that: The computer executable instructions are configured to: Divide the takeaway target area by spatial grid and generate target grid cells; Acquire multi-factor data and historical orders of the target grid unit, wherein the multi-factor data includes residential area data, office building data, and existing post station data, and extract heat distribution maps and time dimension fluctuation characteristics from the historical orders; Constructing a multi-dimensional evaluation matrix and calculating the score of the target grid unit in each dimension, wherein the multi-dimensionality includes the road accessibility dimension and the market competition dimension, and the existing post station distribution data is reverse normalized using the distance threshold method; Based on the hierarchical analysis method, the weight coefficient of each dimension is determined to generate a weighted score, and the target grid units are sorted according to the weighted score, and the target area with a preset ranking is selected as the station site.

Images