Shared parking service area division and capacity configuration method based on road network accessibility

Abstract

This invention discloses a method for the division and capacity allocation of shared parking service areas based on road network accessibility. The method involves acquiring and preprocessing a multi-source dataset of the target area; extracting the location information of all parking demand points within the target time period and performing cluster analysis to obtain an initial set of shared parking service areas for the target time period based on the clustering results; assigning each basic spatial analysis unit to the corresponding service area with the shortest travel time based on the shortest path algorithm; calculating supply and demand indicators for each service area; constructing a quantitative evaluation index for inter-regional supply and demand fairness based on the obtained supply and demand index values ​​for each service area; comparing the quantitative evaluation index with a fairness threshold to determine whether the current area division scheme meets fairness requirements; if not, iterative optimization and area adjustment are performed. This invention solves the problems of traditional division methods ignoring the differences between road network structure and actual travel time, and lacking a fairness adjustment mechanism, achieving dynamic, comprehensive, and fair division and capacity allocation of shared parking service areas based on the actual road network.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation and urban parking management technology, specifically to a method for dividing and configuring the capacity of shared parking service areas based on road network accessibility. Background Technology

[0002] With the accelerating pace of urbanization and the continuous increase in the number of motor vehicles, "parking difficulties" have become a common problem that restricts the efficient operation of urban traffic and affects residents' travel experience. Shared parking, as a novel solution, aims to effectively improve the overall utilization efficiency of existing parking facilities and alleviate the parking supply and demand imbalance in specific areas by revitalizing idle parking spaces in residential, commercial, and office areas and opening them to the public at different times.

[0003] A fundamental and crucial technical aspect of implementing shared parking services is the rational division of service areas. Scientific and precise area division is a prerequisite for orderly management, accurate matching of supply and demand, dynamic pricing, and the execution of cross-regional allocation strategies. Currently, the methods for dividing shared parking service areas in practice and research can be mainly summarized into the following categories: The first category is the division method based on fixed geographical boundaries. The most common approach is to directly use administrative boundaries, such as the boundaries of streets or communities, or to divide the city into regular geographical grids. The advantage of this method is its ease of management and clear boundaries. However, its fundamental flaw lies in the fact that the division process completely ignores the actual topology of the urban road network, traffic impedance, and traffic conditions changing over time. Two parking demand points that are close in a straight line may have vastly different actual travel times due to factors such as road grade, traffic flow, and one-way restrictions. Static division based on fixed boundaries cannot reflect the accessibility of users in the real traffic environment, easily leading to a serious disconnect between the defined "service area" and the "service range" actually perceived by users.

[0004] The second type is the "circle-drawing" method based on a fixed service radius. This method typically defines a circular service area around a parking lot or hub, with a fixed Euclidean distance (e.g., 500 meters) as the radius. While this method considers spatial proximity, it also has significant limitations. First, it assumes isotropic travel conditions and fails to account for the uneven accessibility in different directions caused by the road network structure. For example, two points with similar straight-line distances may have significantly longer actual travel times due to barriers such as rivers, railways, or highways. Second, the fixed radius cannot adapt to the impact of dynamic traffic flow; congestion during peak hours can significantly compress the actual service area. Third, this method is prone to coverage gaps or overlapping areas, making it difficult to form a seamless, comprehensive management unit system.

[0005] While the third type of method attempts to incorporate traffic factors, it is often relatively simple or static. For example, it uses road network distance instead of straight-line distance, or uses a single average vehicle speed for calculation. However, urban traffic is highly time-varying, with significant differences in travel time for the same road segment during morning rush hour, evening rush hour, and off-peak hours. Static, time-invariant road network models cannot capture this dynamism, causing the areas they divide into to become unreasonable at different times of the day.

[0006] A core challenge faced by all the existing classification methods mentioned above is the lack of a systematic and equitable adjustment mechanism. Because the supply (distribution of shared parking spaces) and demand (distribution of driver parking needs) of parking resources are inherently mismatched spatially, simple geographical or static traffic divisions inevitably lead to a severe imbalance in the supply-demand ratio (supply / demand) of parking resources within each service area. Some areas may have idle resources due to abundant supply, while others may experience severe shortages due to highly concentrated demand. This unfair allocation of resources between areas not only reduces the overall utilization efficiency and social benefits of the shared parking system but may also trigger user dissatisfaction and, in the long run, lead to unsustainable services in certain areas.

[0007] Therefore, the current shared parking management field urgently needs a method for area division and capacity allocation. This method must be able to: 1) reflect the actual accessibility of users based on the real road network and its dynamic travel time; 2) have dynamic division capabilities to adapt to the time-varying characteristics of demand and traffic conditions; 3) establish a clear fairness-oriented optimization mechanism to proactively adjust resource allocation between areas and achieve a global supply-demand balance; and 4) ensure full coverage and no overlap in the division results, forming stable and operable management zones. This invention is proposed precisely to address these long-standing technical bottlenecks. Summary of the Invention

[0008] This invention provides a method for dividing and configuring the capacity of shared parking service areas based on road network accessibility. This method addresses the technical problems of existing methods for dividing shared parking service areas, such as coarse division methods, neglect of differences in actual road network traffic, and lack of fairness adjustment mechanisms. This method uses the actual road network and its dynamic travel time as the core measurement benchmark. Through systematic data processing, model calculation, and iterative optimization, it achieves a scientific, dynamic, precise, and fair division of service areas and allocates parking capacity reasonably for each area. This provides core technical support for building an efficient, fair, and operable shared parking operation and management system.

[0009] According to the first aspect, one embodiment provides a method for dividing and configuring the capacity of a shared parking service area based on road network accessibility, the method comprising: Acquire multi-source datasets within the target area, including shared parking supply data, parking demand data, and urban road network traffic data, and perform preprocessing. Based on the obtained multi-source dataset, the location information of all parking demand points within the target time period is extracted and clustering analysis is performed using a clustering algorithm. The initial set of shared parking service areas for the target time period is obtained based on the clustering results. The target area is divided into multiple basic spatial analysis units, and based on the shortest path algorithm, each basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time. Based on the delineation results of all basic spatial analysis units, supply and demand indicators are calculated for each initial shared parking service area. The supply and demand indicators are calculated based on the total number of available parking spaces in all shared parking lots within the current service area during the target time period and the total number of parking demand points within the current area during the target time period. Based on the supply and demand index values ​​of each initial shared parking service area, a quantitative evaluation index for the fairness of supply and demand between areas is constructed. The quantitative evaluation index for fairness is compared with a preset fairness threshold to determine whether the current area division scheme meets the fairness requirements. If it does not meet the requirements, iterative optimization and area adjustment are carried out to obtain an optimized set of shared parking service areas. Based on the optimized set of shared parking service areas, the final result of the dynamic division and capacity configuration scheme for shared parking service areas is generated.

[0010] Furthermore, multi-source datasets, including shared parking supply data, parking demand data, and urban road network traffic data, are acquired within the target area and preprocessed, specifically including: The shared parking supply data includes the geographical location of each shared parking lot and the number of available parking spaces during different operating periods; the parking demand data includes parking demand point data in the spatiotemporal dimensions; the urban road network traffic data includes road network topology data and the historical average traffic speed of different road sections at different times.

[0011] Furthermore, multi-source datasets, including shared parking supply data, parking demand data, and urban road network traffic data, are acquired within the target area and preprocessed, specifically including: The collected data undergoes preprocessing, including coordinate system unification, timestamp alignment, and format standardization, to construct a unified spatiotemporal analysis dataset.

[0012] Furthermore, based on the obtained multi-source dataset, the location information of all parking demand points within the target time period is extracted and clustering analysis is performed using a clustering algorithm. Based on the clustering results, an initial set of shared parking service areas for the target time period is obtained, specifically including: The K-means clustering algorithm was used to perform cluster analysis on the location information of all parking demand points within the target time period, resulting in multiple clusters and their corresponding centroid coordinates; Each cluster represents a core demand area. The centroid of each cluster is used as the center of an initial shared parking service area, thus obtaining the initial set of shared parking service areas.

[0013] Furthermore, the target area is divided into multiple basic spatial analysis units, and based on the shortest path algorithm, each basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time, specifically including: By combining the historical average travel speed of each road segment during the target time period, the Dijkstra shortest path algorithm is used to calculate the shortest travel time from the geometric center point of each basic spatial analysis unit to the center of all initial shared parking service areas, and the corresponding basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time.

[0014] Furthermore, based on the delineation results of all basic spatial analysis units, supply and demand indicators are calculated for each initial shared parking service area. These indicators are calculated based on the total number of available parking spaces in all shared parking lots within the current service area during the target time period and the total number of parking demand points within the current area during the target time period. Specifically, these indicators include: Based on the delineation results of all basic spatial analysis units, a supply-demand ratio is calculated for each initial shared parking service area. This supply-demand ratio is the total number S of available parking spaces in all shared parking lots within the current service area during the target time period. k Q, the total number of parking demand points in the current area during the target time period k The ratio of .

[0015] Furthermore, based on the obtained supply and demand index values ​​for each initial shared parking service area, a quantitative evaluation index for the fairness of supply and demand between areas is constructed. This fairness evaluation index is compared with a preset fairness threshold to determine whether the current area division scheme meets fairness requirements. If not, iterative optimization and area adjustment are performed to obtain an optimized set of shared parking service areas, specifically including: Based on the obtained supply-demand ratio index value of each initial shared parking service area, calculate the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period, and determine whether the statistical variance exceeds a preset threshold. If it does, perform iterative optimization with the goal of minimizing the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period to obtain an optimized set of shared parking service areas.

[0016] Furthermore, iterative optimization is performed with the objective of minimizing the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period, resulting in an optimized set of shared parking service areas, specifically including: Optimization is achieved during the iteration process by adjusting the spatial structure of the service area, including: Identify the initial shared parking service area with the lowest current supply-demand ratio, and move its center point toward the center of the adjacent service area with a relatively high supply-demand ratio by a preset small step size; Analyze the basic spatial analysis units located within a preset range of adjacent service area boundaries, assess the impact of changing their service area affiliation on the optimization objective, and reassign them to service areas that are more conducive to reducing the overall statistical variance. The iteration stops when the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period does not exceed the preset threshold or when the preset maximum number of iterations is reached.

[0017] Furthermore, based on the optimized set of shared parking service areas, the final result of the dynamic division and capacity configuration scheme for shared parking service areas is generated, specifically including: The final result of the shared parking service area dynamic division and capacity configuration scheme includes: a unique identifier and geographical boundary description of each shared parking service area, a list of basic spatial analysis unit IDs contained in each shared parking service area, a list of all shared parking lots contained in each shared parking service area and their available capacity during the target time period, and the total effective shared parking capacity configured for each shared parking service area, which is the sum of the number of available parking spaces in all parking lots in each area.

[0018] According to a second aspect, one embodiment provides a shared parking service area dynamic partitioning and capacity configuration system based on road network accessibility, the system comprising: The data acquisition and processing module is used to acquire and preprocess multi-source datasets, including shared parking supply data, parking demand data, and urban road network traffic data, within the target area. The dynamic region division module is used to extract the location information of all parking demand points within the target time period based on the obtained multi-source dataset and perform cluster analysis using a clustering algorithm. Based on the clustering results, the initial set of shared parking service areas for the target time period is obtained. The unit attribution and division module is used to divide the target area into multiple basic spatial analysis units, and based on the shortest path algorithm, assign each basic spatial analysis unit to the service range of the corresponding initial shared parking service area with the shortest travel time. The supply and demand accounting module is used to calculate the supply and demand indicators for each initial shared parking service area based on the allocation results of all basic spatial analysis units. The supply and demand indicators are calculated based on the total number of available parking spaces in all shared parking lots in the current service area during the target time period and the total number of parking demand points in the current area during the target time period. The fairness quantitative assessment and iterative optimization module is used to construct a fairness quantitative assessment index between regions based on the supply and demand index values ​​of each initial shared parking service area. The fairness quantitative assessment index is compared with a preset fairness threshold to determine whether the current region division scheme meets the fairness requirements. If it does not meet the requirements, iterative optimization and region adjustment are performed to obtain an optimized set of shared parking service areas. The results output module is used to generate the final result of the dynamic division and capacity configuration scheme of shared parking service areas based on the optimized set of shared parking service areas.

[0019] This invention provides a method for the division and capacity allocation of shared parking service areas based on road network accessibility, which has the following beneficial effects: This invention deeply integrates real road network traffic data, demand-driven spatiotemporal clustering, and iterative optimization aimed at quantifying fairness. It changes the traditional coarse division model based on fixed radii or administrative boundaries, achieving a refined division of shared parking service areas that closely matches real traffic conditions, dynamically changes with demand, and proactively pursues fairness in resource allocation among areas. This method not only ensures the rationality and full coverage of the division in principle, but also effectively alleviates the serious imbalance between supply and demand among areas caused by resource spatial mismatch through a built-in fairness assessment and optimization mechanism. Therefore, it provides a reliable technical foundation for improving the operational efficiency, resource utilization fairness, and user satisfaction of the entire shared parking system. Attached Figure Description

[0020] Figure 1 A flowchart illustrating a method for dividing and configuring the capacity of a shared parking service area based on road network accessibility, as provided in one embodiment of the present invention; Figure 2 This is a flowchart illustrating a specific implementation of a shared parking service area division and capacity configuration method based on road network accessibility, as provided in one embodiment of the present invention. Detailed Implementation

[0021] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0022] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0023] The first embodiment of this invention provides a method for dividing and configuring the capacity of a shared parking service area based on road network accessibility. The following is a combination of... Figure 1 and Figure 2 Please provide a detailed explanation.

[0024] like Figure 1 As shown, in step S1, a multi-source dataset including shared parking supply data, parking demand data, and urban road network traffic data within the target area is obtained and preprocessed.

[0025] Specifically, this step, as the foundation of the methodology, is responsible for integrating and preprocessing three core input data sources: First, parking supply data, which clearly provides the precise geographical location of each shared parking lot and the available parking space capacity during different operating periods (e.g., by hour or peak / off-peak periods); second, parking demand data, which can be a discrete set of demand points with geographical locations and initiation timestamps, or gridded demand intensity data covering the study area with spatiotemporal dimensions; and third, basic data of the urban road network and its dynamic attribute data, which not only includes the topological connections of road segments, but more importantly, integrates the travel time or average vehicle speed of each road segment at different times of the day. By preprocessing the above data through coordinate system unification, timestamp alignment, and format standardization, a unified spatiotemporal analysis dataset is constructed.

[0026] In one specific embodiment, the data required for implementing this method is collected and prepared, including: S11: Parking supply data: Information on 200 shared parking lots cooperating with this invention is obtained from the city's smart parking platform, including their precise latitude and longitude coordinates, as well as the number of available shared parking spaces during the morning peak (7:00-9:00), evening peak (17:00-19:00), and off-peak (other times).

[0027] S12: Parking demand data: One week's worth of ride-hailing order drop-off point data in the city (after anonymization) is used as proxy data for parking demand. Each data point includes the latitude and longitude coordinates of the drop-off point and the drop-off timestamp, totaling approximately 1 million records.

[0028] S13: Road network data: Obtain urban road network vector data (including road segments, nodes and topological relationships) and historical average traffic speed attributes attached to road segments, divided by hour, from the city's traffic information center.

[0029] The three types of data mentioned above are uniformly converted to the WGS-84 coordinate system, and all time information is aligned to the 24-hour format to form a unified spatiotemporal dataset.

[0030] like Figure 1 As shown, in step S2, based on the obtained multi-source dataset, the location information of all parking demand points within the target time period is extracted and clustering analysis is performed using a clustering algorithm. Based on the clustering results, the initial set of shared parking service areas for the target time period is obtained.

[0031] Specifically, this step aims to dynamically determine the service center location for each time period based on the spatiotemporal distribution pattern of parking demand. First, the target analysis day is divided into several consecutive time periods. For each independent time period, the spatial location information of all parking demand points within that period is extracted. Then, a spatiotemporal clustering algorithm is used to analyze the demand point set, identifying demand hotspots that exhibit spatial clustering characteristics within that time period. The algorithm ultimately generates a preset number (K) of clusters, each representing a core demand area, and the centroid of each cluster is automatically selected as a candidate shared parking service area center for that time period. This data-driven center selection method ensures that the starting point of the area division is closely related to the actual distribution of demand.

[0032] In one specific embodiment, taking the morning rush hour (7:00-9:00) as an example, the selection of the regional center is as follows: S21: Extract all parking demand points (i.e. ride-hailing drop-off points) during the morning peak hours (7:00-9:00), resulting in approximately 150,000 demand points.

[0033] S22: Using the K-means clustering algorithm, with K=30, spatial clustering was performed on the latitude and longitude coordinates of the aforementioned 150,000 required points. The algorithm calculated 30 clusters and their corresponding centroid coordinates.

[0034] S23: Determine the centroid coordinates of these 30 clusters as the initial shared parking service area center during the morning peak period, denoted as set C = {C1, C2, ..., C30}.

[0035] like Figure 1 As shown, in step S3, the target area is divided into multiple basic spatial analysis units, and based on the shortest path algorithm, each basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time.

[0036] Specifically, this step is the core of achieving precise and reasonable regional division. Using the K dynamic regional centers obtained in the previous step as "anchor points," and traffic analysis zones or regular geographic grids as the basic spatial analysis units, road network data integrating dynamic traffic attributes is used. A graph-based shortest path algorithm (such as Dijkstra's algorithm) is employed to accurately calculate the shortest travel time from each spatial unit to these K center points. This calculation process fully incorporates the influence of actual road routes, traffic restrictions, and time-series congestion. Based on this, according to the "minimum travel time" principle, each spatial unit is assigned to the region center with the shortest travel time. Once all spatial units have been assigned, K service areas are naturally formed spatially. The boundaries of these areas are irregular closed figures formed by connecting isochronous circles where "travel times to different centers are equal," thus ensuring that the division results cover the entire region without overlap, and that the actual traffic impedance from any point within a region to its service center is relatively minimized.

[0037] In one specific embodiment, 1,500 Traffic Analysis Zones (TAZs) divided within the city are used as the basic spatial units, as detailed below: S31: Based on the road network traffic speed during the morning peak hours obtained in step S13, calculate the shortest travel time from the geometric center point of each traffic analysis cell to the 30 regional centers (C1-C30) determined in step S22. The calculation process uses Dijkstra's shortest path algorithm in graph theory.

[0038] S32: For each traffic analysis cell, compare its travel time to the 30 centers and find the minimum value.

[0039] S33: Assign the traffic analysis cell to the area represented by the area center with the shortest travel time. For example, if the travel time from TAZ#101 to center C5 is the shortest, then TAZ#101 is assigned to the service area centered on C5.

[0040] S34: After all 1,500 traffic analysis zones have been assigned to specific locations, 30 seamless, non-overlapping service areas covering the entire city have been formed in geographic space. The extent of each area is an irregular polygon formed by the natural connection of isochronous circles where "travel time to different centers is equal".

[0041] like Figure 1 As shown, in step S4, based on the delineation results of all basic spatial analysis units, supply and demand indicators are calculated for each initial shared parking service area. The supply and demand indicators are calculated based on the total number of available parking spaces in all shared parking lots within the current service area during the target time period and the total number of parking demand points within the current area during the target time period.

[0042] After the initial partitioning, this step involves conducting independent supply and demand statistics for each service area. On the supply side, the total number of available parking spaces in all shared parking lots within the area during the current time period is summarized and denoted as the total regional supply Sk. On the demand side, the total demand of all parking demand points within the area during the current time period is summarized (or spatial integration of the gridded demand data is performed) and denoted as the total regional demand Q. k Then, the key performance indicator for each region—the supply-demand ratio R—is calculated. k = S k / Q k .

[0043] In one specific embodiment, the above steps specifically include: S41: For each service area defined in step S3, perform supply and demand calculations: Supply accounting: Total regional supply Sk = the sum of all shared parking spaces available in the region during the morning peak hours.

[0044] Demand calculation: Total regional demand Qk = the sum of the number of all morning peak parking demand points in the region (from step S21).

[0045] S42: Calculate the supply-demand ratio for each region: Rk = Sk / Qk.

[0046] like Figure 1As shown, in step S5, based on the supply and demand index values ​​of each initial shared parking service area, a quantitative evaluation index for the fairness of supply and demand between areas is constructed. The quantitative evaluation index for fairness is compared with a preset fairness threshold to determine whether the current area division scheme meets the fairness requirements. If it does not meet the requirements, iterative optimization and area adjustment are performed to obtain an optimized set of shared parking service areas.

[0047] This step objectively assesses the balance of resource allocation at the system level. It is based on the supply-demand ratio R for each region calculated in step S4. k Calculate the supply-demand ratio R for all K regions. k The statistical variance is used as a core quantitative indicator of fairness. This variance value directly reflects the magnitude of the differences in resource sufficiency among different regions. By comparing this calculated variance with a fairness threshold pre-set according to management objectives, it is possible to scientifically determine whether the current regional division scheme has reached an acceptable level of fairness.

[0048] If the evaluation result of step S5 indicates that fairness does not meet the requirements (i.e., variance exceeds the threshold), the intelligent optimization step is initiated. This step constructs an optimization model with the explicit objective of "minimizing the variance of the supply-demand ratio across all regions." The optimization process is achieved by iteratively adjusting the spatial structure of the regions. The main strategies include: 1) Fine-tuning the regional center position: Identifying the region with the lowest current supply-demand ratio (most scarce), and moving its center point in small steps towards the center of the adjacent region with a higher supply-demand ratio (relatively abundant); 2) Optimized redistribution of boundary units: Analyzing spatial units located near the boundaries of adjacent regions, evaluating the impact of changing their affiliation on the overall fairness index, and redistributing them to regions that are more conducive to reducing the overall variance. After each adjustment, it is necessary to return to step S3, and re-divide the regions, calculate supply and demand, and evaluate fairness based on the new spatial structure, forming a closed-loop feedback optimization process of "divide-calculate-evaluate-adjust" until the fairness index meets the threshold requirement or reaches the preset maximum number of iterations.

[0049] In one specific embodiment, the above steps specifically include: S51: Calculate the variance of the supply-demand ratio Rk for all 30 regions. In this embodiment, a variance less than or equal to 0.05 is considered to meet the fairness requirement.

[0050] S52: The variance of the initial partition is calculated to be 0.12, which is greater than the threshold and is therefore deemed unfair. The process needs to be optimized.

[0051] S53: Since the fairness standard was not met in step S52, iterative optimization is initiated. This embodiment uses the region center migration method for optimization, with the goal of minimizing variance.

[0052] S54: Identify the optimization target: Find the region with the lowest supply-demand ratio Rk among the current 30 regions (assuming it is region A, R_A = 0.4), and use it as the region with the most insufficient supply; at the same time, find the region with the highest supply-demand ratio Rk (assuming it is region B, R_B = 2.1).

[0053] S55: Perform adjustment: Move the center point of region A by 200 meters (preset step size) in the direction from the center point of region B to obtain the new center point coordinates A'.

[0054] S56: Replace coordinate A in the central set C of the region with A' to form a new central set C'.

[0055] S57: Return to step S3, and based on the new central set C', re-execute the full coverage area division (S31-S34), and then re-execute the supply and demand accounting and fairness assessment.

[0056] S58: Check the variance obtained from the new round of evaluation. If the variance drops to 0.05 or below, stop optimization; if it is still greater than 0.05 but less than the previous variance, repeat steps S53 to S57 for the next iteration; if the preset maximum number of iterations (e.g., 50) is not reached, select the solution with the smallest variance during the iteration process as the final result. In this embodiment, after 15 iterations, the variance dropped to 0.048, meeting the requirements.

[0057] like Figure 1 As shown, in step S6, the final result of the dynamic division and capacity configuration scheme of shared parking service areas is generated based on the optimized set of shared parking service areas.

[0058] Specifically, once the optimization process converges, the final area division and capacity allocation scheme that meets fairness requirements for the current time period is obtained. This step is responsible for transforming this scheme into structured, actionable management information for output. The output includes: a unique identifier for each service area and its precise geographical boundary description; a detailed list of all shared parking lots within the area and their available capacity for the current time period; the total effective shared parking capacity allocated to the area; and the final supply-demand ratio R. k Defined real-time status labels for specific areas (e.g., "Sufficient supply," "Supply and demand in balance," "Tight supply"). This complete solution can directly support advanced management functions such as parking reservation matching, differentiated dynamic pricing, and cross-regional resource allocation.

[0059] In one specific embodiment, the above steps specifically include: S61: Region Boundary Description: Outputs a list of traffic analysis cell IDs for each of the 30 regions, clearly defining their precise geographical boundaries.

[0060] S62: Parking Lot List: Outputs the unique identifiers (IDs) of all shared parking lots within each area and their available capacity during the morning peak hours.

[0061] S63: Capacity Configuration Result: Outputs the total effective shared parking capacity configured for each area, which is the sum of available parking spaces in all parking lots within each area.

[0062] S64: Status Identification: Based on the final supply-demand ratio Rk, mark the status of each region. The rules in this embodiment are: Rk ≥ 1.2 is marked as "Sufficient Supply", 0.8 ≤ Rk<1.2 is marked as "Supply and Demand Balanced", and Rk<0.8 is marked as "Tight Supply".

[0063] For other time periods such as evening peak and off-peak, repeat steps S2 to S6 to obtain the dynamic division and configuration scheme for the corresponding time period. The schemes for all time periods can be integrated into the shared parking management platform to guide time-sharing reservations, dynamic pricing, and cross-regional dispatch.

[0064] Corresponding to the aforementioned method for dividing and configuring shared parking service areas based on road network accessibility, this invention also discloses a system for dynamically dividing and configuring shared parking service areas based on road network accessibility, which specifically includes: The data acquisition and processing module is used to acquire and preprocess multi-source datasets, including shared parking supply data, parking demand data, and urban road network traffic data, within the target area. The dynamic region division module is used to extract the location information of all parking demand points within the target time period based on the obtained multi-source dataset and perform cluster analysis using a clustering algorithm. Based on the clustering results, the initial set of shared parking service areas for the target time period is obtained. The unit attribution and division module is used to divide the target area into multiple basic spatial analysis units, and based on the shortest path algorithm, assign each basic spatial analysis unit to the service range of the corresponding initial shared parking service area with the shortest travel time. The supply and demand accounting module is used to calculate the supply and demand indicators for each initial shared parking service area based on the allocation results of all basic spatial analysis units. The supply and demand indicators are calculated based on the total number of available parking spaces in all shared parking lots in the current service area during the target time period and the total number of parking demand points in the current area during the target time period. The fairness quantitative assessment and iterative optimization module is used to construct a fairness quantitative assessment index between regions based on the supply and demand index values ​​of each initial shared parking service area. The fairness quantitative assessment index is compared with a preset fairness threshold to determine whether the current region division scheme meets the fairness requirements. If it does not meet the requirements, iterative optimization and region adjustment are performed to obtain an optimized set of shared parking service areas. The results output module is used to generate the final result of the dynamic division and capacity configuration scheme of shared parking service areas based on the optimized set of shared parking service areas.

[0065] It should be noted that for a detailed description of the shared parking service area dynamic division and capacity configuration system based on road network accessibility provided in the embodiments of the present invention, please refer to the relevant description of the shared parking service area division and capacity configuration method based on road network accessibility provided in the embodiments of the present invention, which will not be repeated here.

[0066] In addition, embodiments of the present invention also provide an electronic device, the device comprising: a processor and a memory; the memory being used to store one or more program instructions; the processor being used to execute one or more program instructions to perform the steps of a shared parking service area division and capacity configuration method based on road network accessibility as described in any of the preceding embodiments.

[0067] It should be noted that for a detailed description of an electronic device provided in the embodiments of the present invention, please refer to the relevant description of a method for dividing and configuring the shared parking service area based on road network accessibility provided in the embodiments of this application, which will not be repeated here.

[0068] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the shared parking service area division and capacity configuration method based on road network accessibility as described in any of the preceding claims.

[0069] It should be noted that for a detailed description of the computer-readable storage medium provided in the embodiments of the present invention, please refer to the relevant description of the method for dividing and configuring the shared parking service area based on road network accessibility provided in the embodiments of this application, which will not be repeated here.

[0070] The above examples illustrate the present invention only to aid in understanding it and are not intended to limit the scope of the invention. Those skilled in the art can make various simple deductions, modifications, or substitutions based on the principles of this invention.

Claims

1. A method for dividing and configuring the capacity of shared parking service areas based on road network accessibility, characterized in that, The method includes: Acquire multi-source datasets within the target area, including shared parking supply data, parking demand data, and urban road network traffic data, and perform preprocessing. Based on the obtained multi-source dataset, the location information of all parking demand points within the target time period is extracted and clustering analysis is performed using a clustering algorithm. The initial set of shared parking service areas for the target time period is obtained based on the clustering results. The target area is divided into multiple basic spatial analysis units, and based on the shortest path algorithm, each basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time. Based on the delineation results of all basic spatial analysis units, supply and demand indicators are calculated for each initial shared parking service area. The supply and demand indicators are calculated based on the total number of available parking spaces in all shared parking lots within the current service area during the target time period and the total number of parking demand points within the current area during the target time period. Based on the supply and demand index values ​​of each initial shared parking service area, a quantitative evaluation index for the fairness of supply and demand between areas is constructed. The quantitative evaluation index for fairness is compared with a preset fairness threshold to determine whether the current area division scheme meets the fairness requirements. If it does not meet the requirements, iterative optimization and area adjustment are carried out to obtain an optimized set of shared parking service areas. Based on the optimized set of shared parking service areas, the final result of the dynamic division and capacity configuration scheme for shared parking service areas is generated.

2. The method for dividing and configuring the capacity of shared parking service areas based on road network accessibility as described in claim 1, characterized in that, Acquire multi-source datasets within the target area, including shared parking supply data, parking demand data, and urban road network traffic data, and perform preprocessing, specifically including: The shared parking supply data includes the geographical location of each shared parking lot and the number of available parking spaces during different operating periods; the parking demand data includes parking demand point data in the spatiotemporal dimensions; the urban road network traffic data includes road network topology data and the travel time and historical average travel speed of different road sections at different times.

3. The method for dividing and configuring the capacity of shared parking service areas based on road network accessibility as described in claim 1, characterized in that, Acquire multi-source datasets within the target area, including shared parking supply data, parking demand data, and urban road network traffic data, and perform preprocessing, specifically including: The collected data undergoes preprocessing, including coordinate system unification, timestamp alignment, and format standardization, to construct a unified spatiotemporal analysis dataset.

4. The method for dividing and configuring the capacity of shared parking service areas based on road network accessibility as described in claim 1, characterized in that, Based on the obtained multi-source dataset, the location information of all parking demand points within the target time period is extracted and clustering analysis is performed using a clustering algorithm. Based on the clustering results, an initial set of shared parking service areas for the target time period is obtained, specifically including: The K-means clustering algorithm was used to perform cluster analysis on the location information of all parking demand points within the target time period, resulting in multiple clusters and their corresponding centroid coordinates; Each cluster represents a core demand area. The centroid of each cluster is used as the center of an initial shared parking service area, thus obtaining the initial set of shared parking service areas.

5. The method for dividing and configuring the capacity of shared parking service areas based on road network accessibility as described in claim 1, characterized in that, The target area is divided into multiple basic spatial analysis units. Based on the shortest path algorithm, each basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time. Specifically, this includes: By combining the historical average travel speed of each road segment during the target time period, the Dijkstra shortest path algorithm is used to calculate the shortest travel time from the geometric center point of each basic spatial analysis unit to the center of all initial shared parking service areas, and the corresponding basic spatial analysis unit is assigned to the service area of ​​the corresponding initial shared parking service area with the shortest travel time.

6. The method for dividing and configuring the capacity of shared parking service areas based on road network accessibility as described in claim 1, characterized in that, Based on the delineation results of all basic spatial analysis units, supply and demand indicators are calculated for each initial shared parking service area. These indicators are calculated based on the total number of available parking spaces in all shared parking lots within the current service area during the target time period and the total number of parking demand points within the current area during the target time period. Specifically, these indicators include: Based on the delineation results of all basic spatial analysis units, a supply-demand ratio is calculated for each initial shared parking service area. This supply-demand ratio is the total number S of available parking spaces in all shared parking lots within the current service area during the target time period. k Q, the total number of parking demand points in the current area during the target time period k The ratio of .

7. The method for dividing and configuring the capacity of a shared parking service area based on road network accessibility as described in claim 1, characterized in that, Based on the supply and demand index values ​​obtained for each initial shared parking service area, a quantitative evaluation index for the fairness of supply and demand between areas is constructed. This fairness evaluation index is compared with a preset fairness threshold to determine whether the current area division scheme meets fairness requirements. If not, iterative optimization and area adjustment are performed to obtain an optimized set of shared parking service areas, specifically including: Based on the obtained supply-demand ratio index value of each initial shared parking service area, calculate the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period, and determine whether the statistical variance exceeds a preset threshold. If it does, perform iterative optimization with the goal of minimizing the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period to obtain an optimized set of shared parking service areas.

8. The method for dividing and configuring the capacity of a shared parking service area based on road network accessibility as described in claim 7, characterized in that, The optimization is performed iteratively with the objective of minimizing the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period, resulting in an optimized set of shared parking service areas, specifically including: Optimization is achieved during the iteration process by adjusting the spatial structure of the service area, including: Identify the initial shared parking service area with the lowest current supply-demand ratio, and move its center point toward the center of the adjacent service area with a relatively high supply-demand ratio by a preset small step size; Analyze the basic spatial analysis units located within a preset range of adjacent service area boundaries, assess the impact of changing their service area affiliation on the optimization objective, and reassign them to service areas that are more conducive to reducing the overall statistical variance. The iteration stops when the statistical variance of the supply-demand ratio of all initial shared parking service areas within the target time period does not exceed the preset threshold or when the preset maximum number of iterations is reached.

9. The method for dividing and configuring the capacity of a shared parking service area based on road network accessibility as described in claim 1, characterized in that, Based on the optimized set of shared parking service areas, the final result of the dynamic division and capacity configuration scheme for shared parking service areas is generated, specifically including: The final result of the shared parking service area dynamic division and capacity configuration scheme includes: a unique identifier and geographical boundary description of each shared parking service area, a list of basic spatial analysis unit IDs contained in each shared parking service area, a list of all shared parking lots contained in each shared parking service area and their available capacity during the target time period, and the total effective shared parking capacity configured for each shared parking service area, which is the sum of the number of available parking spaces in all parking lots in each area.

10. A system for dynamic division and capacity configuration of shared parking service areas based on road network accessibility, characterized in that, The system includes: The data acquisition and processing module is used to acquire and preprocess multi-source datasets, including shared parking supply data, parking demand data, and urban road network traffic data, within the target area. The dynamic region division module is used to extract the location information of all parking demand points within the target time period based on the obtained multi-source dataset and perform cluster analysis using a clustering algorithm. Based on the clustering results, the initial set of shared parking service areas for the target time period is obtained. The unit attribution and division module is used to divide the target area into multiple basic spatial analysis units, and based on the shortest path algorithm, assign each basic spatial analysis unit to the service range of the corresponding initial shared parking service area with the shortest travel time. The supply and demand accounting module is used to calculate the supply and demand indicators for each initial shared parking service area based on the allocation results of all basic spatial analysis units. The supply and demand indicators are calculated based on the total number of available parking spaces in all shared parking lots in the current service area during the target time period and the total number of parking demand points in the current area during the target time period. The fairness quantitative assessment and iterative optimization module is used to construct a fairness quantitative assessment index between regions based on the supply and demand index values ​​of each initial shared parking service area. The fairness quantitative assessment index is compared with a preset fairness threshold to determine whether the current region division scheme meets the fairness requirements. If it does not meet the requirements, iterative optimization and region adjustment are performed to obtain an optimized set of shared parking service areas. The results output module is used to generate the final result of the dynamic division and capacity configuration scheme of shared parking service areas based on the optimized set of shared parking service areas.

Images