A method for evaluating traffic network carrying capacity of land space multi-element fusion

Abstract

The application discloses a kind of fusion land space multi-element traffic network carrying efficiency evaluation method, it is related to land space planning and traffic engineering technical field, including integration multi-source land space element data and standardization, through multi-element correlation analysis model is carried out layer interaction influence analysis and dynamic weight iteration calculation, to accurately identify traffic carrying bottleneck area.For each bottleneck area, parallelly executed multi-scenario carrying simulation to generate multiple spatial intervention plan, and utilize historical efficiency comparison library to verify and stability mark.Based on the verification result, construct intervention scheme decision matrix to screen and optimize, determine recommended scheme and convert into specific adjustment parameter, finally coupled traffic network data output carrying efficiency evaluation atlas.The method is through dynamic iteration weight quantification complex correlation between elements, and with the aid of parallel simulation realizes multiple plan fast generation and comparison, improves the accuracy of bottleneck identification and the efficiency of scheme evaluation.

Description

Technical Field

[0001] This invention belongs to the field of land spatial planning and transportation engineering technology, specifically a method for evaluating the carrying capacity of transportation networks that integrates multiple elements of land space. Background Technology

[0002] Current assessments of transportation network carrying capacity primarily rely on the overlay analysis of static transportation infrastructure data and limited land spatial elements. Existing methods typically assign fixed weights to factors such as land use, population distribution, and ecological protection, and then perform linear combinations to estimate their comprehensive impact on the transportation system. This approach simplifies the complex spatially coupled system into a static, independent set of parameters.

[0003] Existing technologies have shortcomings. Fixed-weight linear models cannot characterize the dynamic and nonlinear interaction mechanisms among multiple elements of national land space. The synergistic and restrictive relationships between elements are ignored in the assessment process, leading to biases in the identification of key constraints on traffic carrying capacity. Furthermore, when faced with identified bottleneck areas, existing simulation technologies often employ a sequential calculation mode, testing different spatial intervention strategies one by one. This method is computationally inefficient and time-consuming, failing to fully verify and rapidly compare the long-term effectiveness and stability of multiple planning schemes within the decision-making cycle.

[0004] An assessment method is needed that can quantify the dynamic interaction effects of multiple factors and efficiently simulate multiple intervention scenarios in parallel to overcome the above-mentioned shortcomings. Summary of the Invention

[0005] This invention aims to solve at least one of the technical problems existing in the prior art;

[0006] Therefore, this invention proposes a method for evaluating the carrying capacity of transportation networks that integrates multiple elements of national land space, including:

[0007] It receives and integrates various element data from the national land and space basic information platform, performs spatial gridding and attribute layering processing on it, and generates standardized element layers;

[0008] All the standardized feature layers are input into a multi-feature association analysis model to perform interaction influence analysis and weight iteration calculation between layers;

[0009] Based on the output of the multi-factor correlation analysis model, a set of bottleneck areas that pose a key constraint on the carrying capacity of the transportation network is identified.

[0010] For each region in the bottleneck region set, a parallel multi-scenario carrying capacity simulation process is initiated to generate multiple potential spatial intervention schemes;

[0011] The simulation results and stability annotations for each potential spatial intervention scheme were performed using a historical performance comparison database.

[0012] By integrating the simulation results verification and stability annotation results, an intervention scheme decision matrix is ​​constructed, and multi-level screening and optimization are performed within the intervention scheme decision matrix;

[0013] Based on the screening and optimization results, a recommended spatial intervention scheme is determined and transformed into a specific set of adjustment parameters for national land space elements;

[0014] The set of adjusted parameters for land and space elements is coupled with basic data of the transportation network to output the final transportation network carrying capacity assessment map.

[0015] Furthermore, the process of receiving and integrating various element data from the national land spatial information platform, performing spatial gridding and attribute layering processing on them, and generating standardized element layers includes:

[0016] Receive and integrate various element data from the national land and space basic information platform to construct an initial fused data set;

[0017] Based on the preset land spatial planning classification system, the initial fused data set is spatially gridded and attribute-layered to form multiple interrelated element data layers;

[0018] Spatial registration and data standardization are performed on each of the aforementioned feature data layers to generate standardized feature layers with unified coordinate references and dimensions;

[0019] The initial fused data set is spatially gridded and attribute-layered according to a preset land spatial planning classification system, forming multiple interrelated element data layers, including:

[0020] Spatial control zoning rules, land use classification rules, and ecological protection red line rules are extracted from the preset national spatial planning classification system.

[0021] The initial fused data set is divided into administrative and functional partitions using the aforementioned spatial control partitioning rules to generate a spatial control partitioning layer;

[0022] The land use classification rules are used to strip the land use properties from the initial fused dataset to generate a current land use layer.

[0023] The ecological protection red line rules are used to identify ecologically sensitive areas in the initial fused dataset, generating an ecological constraint layer.

[0024] Establish spatial associations and attribute indexes between the spatial control zoning layer, the land use status layer, and the ecological constraint layer in the spatial database to ensure that attribute changes of any geospatial unit can be synchronously updated in all relevant feature data layers;

[0025] The multiple interconnected element data layers include the spatial control zoning layer, the land use status layer, and the ecological constraint layer.

[0026] Further, the step of performing spatial registration and data standardization processing on each of the feature data layers to generate a standardized feature layer with a unified coordinate reference and unit includes:

[0027] Each feature data layer is configured with an independent spatial coordinate transformation engine to uniformly transform all vector and raster data within the feature data layer to a preset national geodetic coordinate system;

[0028] In each feature data layer, all spatial patches and attribute fields contained therein are traversed to extract the original spatial geometric information and attribute values;

[0029] The preset attribute normalization processor is invoked to perform dimensionless processing and statistical distribution adjustment on the extracted attribute values;

[0030] The normalized attribute values ​​are re-associated with the corresponding spatial geometric information, and basic constraints from the national land spatial planning standards are injected to perform data integrity checks and logical consistency corrections.

[0031] The output spatial data, which has undergone spatial registration and data standardization, and has unified spatial reference and standardized attribute values, serves as the standardized feature layer.

[0032] Furthermore, the step of inputting all the standardized feature layers into a multi-factor association analysis model for interaction influence analysis and weight iteration calculation between layers includes:

[0033] Initialize the multi-factor correlation analysis model, which includes a public weight pool for storing intermediate analysis results and multiple private feature analyzers that correspond one-to-one with the standardized feature layers;

[0034] Each of the private feature analyzers reads the corresponding standardized feature layer and preliminarily calculates the influence intensity value of the feature based on the attributes of the standardized feature layer itself;

[0035] All the private feature analyzers write their respective influence intensity values ​​into the public weight pool, and trigger a round of feature interaction intensity calculation based on spatial overlay analysis within the public weight pool;

[0036] Based on the results of the element interaction strength calculation, promotion and inhibition signals between elements are generated, and the promotion and inhibition signals between elements are fed back to each of the private element analyzers.

[0037] Each of the private element analyzers dynamically corrects and recalculates the influence intensity value it has calculated based on the received promoting and inhibiting signals;

[0038] The process of writing influence intensity values, calculating interaction intensity, signal feedback, and numerical correction is repeated until the rate of change of influence intensity values ​​of each element in the public weight pool is lower than a preset threshold. Finally, a set of stable element comprehensive weights that reflect interaction relationships is output.

[0039] Furthermore, based on the output of the multi-factor correlation analysis model, a set of bottleneck areas that pose a key constraint on the carrying capacity of the transportation network is identified, including:

[0040] Based on the comprehensive weights of the elements output by the multi-element correlation analysis model, the entire assessment area covered by the transportation network is spatially rasterized, and a comprehensive constraint intensity index is calculated for each raster unit.

[0041] The comprehensive constraint intensity index is spatially superimposed with the basic traffic flow data of the traffic network to simulate the theoretical traffic flow capacity under different constraint conditions.

[0042] All grid cells whose theoretical capacity is lower than the preset carrying capacity threshold during the simulation are identified and marked as preliminary bottleneck cells.

[0043] Spatial clustering analysis is performed on the initial bottleneck units to merge spatially continuous initial bottleneck units with similar constraints, forming several bottleneck regions with clear spatial boundaries.

[0044] The set of bottleneck regions is determined by analyzing the dominant constraint types and their spatial distribution patterns within each bottleneck region.

[0045] Furthermore, for each region in the bottleneck region set, a parallel multi-scenario carrying capacity simulation process is initiated to generate multiple potential spatial intervention schemes, including:

[0046] Create an independent scenario simulation sandbox for each region in the bottleneck region set, and load the complete standardized feature layer data and traffic network data of the region into each scenario simulation sandbox.

[0047] In each of the scenario simulation sandboxes, one or more adjustment strategies for the dominant constraints of the region are selected from a predefined library of land space element adjustment strategies.

[0048] The selected adjustment strategies are combined with different implementation intensities and implementation sequences to construct multiple specific scenario parameter combinations;

[0049] In the scenario simulation sandbox, the corresponding standardized element layer data is dynamically modified according to each scenario parameter combination, and a traffic flow allocation model is driven to simulate the carrying capacity of the traffic network under new spatial element conditions.

[0050] Record key indicators such as changes in the traffic capacity and flow distribution of the regional traffic network at the end of each scenario simulation, and encapsulate the scenario parameters and simulation results to form a potential spatial intervention scheme.

[0051] Furthermore, the step of using a historical performance comparison library to verify the simulation results and label the stability of each potential spatial intervention scheme includes:

[0052] Extract the core feature parameters of each potential spatial intervention scheme, including the type of element to be adjusted, the spatial range, the adjustment magnitude, and the simulated changes in traffic capacity;

[0053] The core feature parameters are structured and encoded, and a similar case retrieval is performed in the historical performance comparison database to find historical records of cases that have taken similar intervention measures in similar spatial locations.

[0054] For each of the aforementioned case records retrieved, extract its long-term monitoring effectiveness data after actual implementation and the uncertainties that arose during the implementation process;

[0055] By comparing the simulated traffic capacity changes of the potential spatial intervention schemes with the long-term monitoring effectiveness data recorded in the case studies, the confidence level of the expected effectiveness of the potential spatial intervention schemes is calculated.

[0056] By analyzing the uncertainties in the case records, the volatility risk level faced by the potential spatial intervention schemes during implementation is assessed.

[0057] The expected performance confidence level and the volatility risk level are used as labels to assign corresponding potential spatial intervention schemes, thereby completing the simulation result verification and stability labeling.

[0058] Furthermore, by fusing the simulation results verification and stability annotation results, an intervention scheme decision matrix is ​​constructed, and multi-level screening and optimization are performed within the intervention scheme decision matrix, including:

[0059] Using each potential spatial intervention scheme as a candidate point, its expected effectiveness realization confidence level as the effectiveness dimension, and its volatility risk level as the robustness dimension, a two-dimensional decision matrix for the intervention scheme is constructed.

[0060] In the intervention scheme decision matrix, the priority-oriented weight of the current territorial spatial planning is introduced to weight the effectiveness and robustness dimensions, and the comprehensive priority score of each candidate point is calculated.

[0061] Based on the comprehensive priority score, sequential elimination and optimization iteration are performed: in each round, some candidate points with the lowest comprehensive priority score are eliminated, and the strategy parameters of the remaining candidate points are fine-tuned and cross-combined to generate new candidate points to be added to the intervention scheme decision matrix.

[0062] Repeat the elimination and iterative generation process until the average comprehensive priority score of the candidate points in the intervention scheme decision matrix no longer significantly improves;

[0063] From the final set of retained candidate points, the solution corresponding to the candidate point with the highest comprehensive priority score is selected as the final output of screening and optimization.

[0064] Furthermore, based on the results of screening and optimization, a recommended spatial intervention scheme is determined and transformed into a specific set of land space element adjustment parameters, including:

[0065] Analyze, filter, and optimize the recommended spatial intervention schemes in the final output to obtain their complete combination of scenario parameters;

[0066] The scenario parameter combination is broken down into operational instructions for specific land space elements, including land use change instructions, development intensity adjustment instructions, or ecological space restoration instructions.

[0067] For each of the aforementioned operation instructions, match the geospatial unit to which it applies, and specify the element attribute values, spatial boundaries, and implementation timing requirements before and after the operation.

[0068] All the operation instructions with spatiotemporal constraints are formatted and encoded according to the national land spatial planning data standard to form structured parameter data blocks;

[0069] All parameter data blocks undergo logical consistency review and spatial conflict detection to ensure that there are no contradictions between parameters, and are finally integrated into the set of adjustment parameters for land and space elements.

[0070] Furthermore, the coupling of the set of adjusted parameters for land and space elements with basic transportation network data to output the final transportation network carrying capacity assessment map includes:

[0071] The parameter data blocks in the set of adjustment parameters for the land and space elements are applied one by one to the standardized element layer corresponding to the assessment area to generate a set of predictive element layers that reflect the state after intervention.

[0072] The predicted feature layer is spatially overlaid with the existing traffic network basic data and input into the calibrated macro traffic model to simulate the overall road network carrying capacity.

[0073] Obtain the predicted traffic flow, road segment saturation, and node service level data for each traffic analysis unit within the evaluation area from the simulation results;

[0074] The predicted traffic flow, road segment saturation, and node service level data are combined with their spatial location information and rendered onto a geographic base map to generate a thematic map containing multi-layer carrying capacity information.

[0075] The thematic maps are symbolized and labeled with legends to form a transportation network carrying capacity assessment map that intuitively displays the changes in carrying capacity and spatial distribution of the transportation network after adjustments to land space elements.

[0076] Compared with the prior art, the beneficial effects of the present invention are:

[0077] A dynamic weight iteration mechanism based on machine learning algorithms is employed to automatically perform multiple rounds of calculations and parameter optimization within the multi-factor correlation analysis model. This method can autonomously learn from historical and real-time data and quantify the complex relationships and influence intensity among multiple elements in land space. The generated weights are dynamically adapted to specific spatial contexts, rather than being preset constants. This enables the multi-factor correlation analysis model to more realistically reflect the comprehensive and nonlinear impact of multiple factors such as land use change, population flow, and environmental constraints on transportation carrying capacity, improving the scientific rigor and accuracy of bottleneck area identification and overcoming the insufficient explanatory power of conventional linear superposition models.

[0078] A multi-scenario carrying capacity simulation process based on a distributed parallel computing framework is implemented, simultaneously launching multiple independent, parameterized, high-fidelity simulation instances for the same bottleneck area. This method enables the simultaneous simulation and deduction of various differentiated spatial intervention strategies in isolated environments, reducing the time cost required for traditional serial simulations. It achieves rapid generation and horizontal comparison of the carrying capacity effects of multiple planning schemes, allowing decision-makers to obtain a fully validated set of schemes and their stability characteristics in a short time, enhancing the responsiveness to complex spatial decision-making problems and the depth of scheme comparison. Attached Figure Description

[0079] Figure 1This is a flowchart illustrating the method for evaluating the carrying capacity of a transportation network that integrates multiple elements of national land space, as shown in this invention.

[0080] Figure 2 A flowchart for spatial registration and data standardization processing;

[0081] Figure 3 A heat map showing the evolution of traffic carrying capacity efficiency in the spatiotemporal dimensions;

[0082] Figure 4 Scatter plot of the decision matrix for intervention programs;

[0083] Figure 5 This is a radar chart showing the distribution of the comprehensive index of the spectral map. Detailed Implementation

[0084] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0085] See Figure 1 The system receives and integrates various element data from the national land and space information platform, performs spatial gridding and attribute layering on the data, generates standardized element layers, and then inputs all standardized element layers into a multi-element correlation analysis model. This model performs interaction impact analysis and weight iteration calculation between layers. Based on the model's output, it can identify a set of bottleneck areas that pose a key constraint on the carrying capacity of the transportation network. For each area in this set, the system initiates a parallel multi-scenario carrying capacity simulation process to generate multiple potential spatial intervention schemes. The simulation results of each potential spatial intervention scheme are verified and stability is labeled using a historical performance comparison database. Then, the verification and labeling results are merged to construct an intervention scheme decision matrix and perform multi-level screening and optimization within it. Based on the screening and optimization results, a recommended spatial intervention scheme is determined and transformed into a specific set of national land and space element adjustment parameters. Finally, this parameter set is coupled with the basic transportation network data to output the final transportation network carrying capacity assessment map.

[0086] See Figure 2In one embodiment of the present invention, the step of receiving and integrating multiple element data from a national land spatial information platform, performing spatial gridding and attribute layering processing on them, and generating a standardized element layer involves receiving and integrating multiple element data from the national land spatial information platform. These element data cover spatial control zoning data, land use classification data, and ecological protection red line data, constructing an initial fused data set, performing spatial gridding and attribute layering processing on the initial fused data set according to a preset national land spatial planning classification system, forming multiple interrelated element data layers, extracting spatial control zoning rules, land use classification rules, and ecological protection red line rules from the preset national land spatial planning classification system, using the spatial control zoning rules to perform administrative and functional zoning on the initial fused data set to generate a spatial control zoning layer, using the land use classification rules to perform land use nature stripping on the initial fused data set to generate a land use status layer, and using the ecological protection red line rules to identify ecologically sensitive areas on the initial fused data set to generate an ecological constraint layer. In some embodiments, spatial gridding processing employs a unified geographic grid unit, such as dividing the assessment area into a regular grid of 100 meters by 100 meters. Each grid unit is associated with corresponding attribute data. Attribute hierarchical processing is based on the hierarchical structure of the national spatial planning classification system, storing data hierarchically according to administrative management, land use type, and ecological sensitivity level. Spatial associations and attribute indexes are established between the spatial control zoning layer, the land use status layer, and the ecological constraint layer in the spatial database. Layer synchronization is achieved by sharing a unique spatial unit identifier, ensuring that attribute changes in any geographic spatial unit can be synchronously updated in all related feature data layers. The multiple interconnected feature data layers include the spatial control zoning layer, the land use status layer, and the ecological constraint layer. Optionally, spatial association uses spatial join operations to link geometric objects in different layers based on their positional relationships. The attribute index uses a B-tree structure to accelerate queries, supporting efficient data retrieval and updates.

[0087] Specifically, spatial control zoning rules, land use classification rules, and ecological protection red line rules are extracted from a pre-defined national spatial planning classification system. The specific steps involve the system pre-integrating national or local national spatial planning standards, technical regulations, or management rules, which together constitute the pre-defined national spatial planning classification system. Spatial control zoning rules are a collection of standards and boundary definitions extracted from this system regarding urban development boundaries, permanent basic farmland protection red lines, ecological protection red lines, and various spatial control zoning standards and boundary definitions for urban, agricultural, and ecological spaces. Land use classification rules are extracted from national standards for land use status classification within this system, clarifying the primary and secondary land use classification systems, coding rules, and descriptions of various land use attributes. Ecological protection red line rules are extracted from specific technical criteria for identifying ecologically important and ecologically sensitive and vulnerable areas within the system, including assessment indicators and thresholds for the importance of ecological functions such as water conservation and biodiversity maintenance, as well as assessment indicators and thresholds for ecological sensitivity such as soil erosion and desertification.

[0088] The initial fused dataset is segmented into administrative and functional zones using spatial control zoning rules to generate a spatial control zoning layer. Specifically, the system reads data fields from the initial fused dataset related to administrative boundaries, main functional area locations, and various spatial control boundaries. Based on the administrative division levels and functional area boundary delineation logic defined in the extracted spatial control zoning rules, the system segments continuous geographic space to generate polygonal regions with clear administrative affiliations and functional attributes. Each polygonal region is assigned a corresponding zoning type code and name attribute, such as being identified as a concentrated urban development area in a certain city and district, ultimately forming a separate spatial control zoning layer in the spatial database.

[0089] The initial fused dataset is stripped of land use characteristics using land use classification rules to generate a land use status layer. Specifically, the system iterates through the original attribute fields recording the land use of each geographic unit in the initial fused dataset. Based on the classification standards and corresponding relationships of the primary categories defined in the extracted land use classification rules (such as cultivated land, forest land, and urban and rural construction land), and the more detailed secondary categories (such as irrigated land, arbor forest land, and retail commercial land), the system standardizes and maps the original, potentially mixed or descriptive land use information onto the classification codes explicitly defined in the rules. For each geographic unit, its dominant land use type is determined and assigned a value, forming a spatial patch with the standardized classification code as its attribute, thus generating a land use status layer that accurately reflects the actual situation on the ground.

[0090] The system uses ecological protection red line rules to identify ecologically sensitive areas in the initial fused dataset to generate an ecological constraint layer. Specifically, the system analyzes relevant data in the initial fused dataset, such as vegetation cover index, water conservation importance assessment results, and soil erosion sensitivity classification data, based on the extracted ecological function importance assessment indicators and ecological environment sensitivity assessment indicators defined in the ecological protection red line rules. Through rule-defined thresholds or spatial overlay analysis, the system identifies areas that meet the criteria for inclusion in the ecological protection red line, such as catchment areas with extremely important water conservation functions or areas extremely sensitive to soil erosion. These identified areas are extracted and formed into separate spatial layers, whose attributes indicate the type and level of ecological constraints, thus generating an ecological constraint layer for subsequent analysis of traffic carrying capacity constraints.

[0091] Spatial registration and data standardization are performed on each feature data layer. An independent spatial coordinate transformation engine is configured for each feature data layer. Based on a seven-parameter transformation model, this engine uniformly transforms all vector and raster data within the feature data layer to the preset national geodetic coordinate system. Within each feature data layer, all spatial patches and attribute fields are traversed to extract the original spatial geometric information and attribute values. A preset attribute normalization processor is then invoked. This processor performs dimensionless processing and statistical distribution adjustment on the extracted attribute values. Dimensionless processing eliminates the influence of different attribute dimensions, and statistical distribution adjustment ensures that the attribute values ​​conform to a standard normal distribution. In practice, the attribute normalization processor uses the following formula to standardize the attribute values:

[0092]

[0093] in: Indicates the first The spatial map patch in the first The original values ​​of each attribute field It is the first The average value of each attribute field across all spatial patches. It is the first The standard deviation of each attribute field across all spatial patches This refers to the standardized attribute values. The normalized attribute values ​​are re-associated with the corresponding spatial geometric information, and basic constraints from national land spatial planning standards are injected. These constraints include land use compatibility rules and the rule that ecological protection red line boundaries cannot be crossed. Data integrity checks and logical consistency corrections are performed. Data integrity checks verify that attribute fields have no missing values, and logical consistency corrections ensure that spatial patch boundaries do not overlap and that attribute values ​​conform to planning logic. The output is spatial data with unified spatial reference and standardized attribute values, processed through spatial registration and data standardization, serving as a standardized element layer. In some embodiments, data standardization processing also includes one-hot encoding of categorical attributes, converting textual attributes into numerical attributes to facilitate subsequent model analysis. Optionally, a control point matching method is used during spatial registration, optimizing coordinate transformation accuracy by selecting control points with known coordinates to ensure spatial alignment between different layers. Specifically, the implementation is as follows: First, the system identifies a set of feature points with the same geographical location and which can be accurately located on both layers from the feature data layer to be registered and the reference layer. These feature points are used as control points with known coordinates. These control points are usually derived from high-precision measurement data, such as national geodetic control points or verified topographic map feature points. Then, the system uses the coordinates of these control points to calculate coordinate transformation parameters based on a seven-parameter transformation model. The parameters are iteratively adjusted using the least squares optimization method until the sum of squared residuals between the transformed coordinates and the reference coordinates of the control points is minimized, thereby optimizing the coordinate transformation accuracy. Finally, the system applies the optimized transformation parameters to the entire feature data layer to perform coordinate transformation, so that all vector and raster data are unified to the preset national geodetic coordinate system, achieving accurate spatial alignment of different layers under the same geographic reference frame.

[0094] In one embodiment of the present invention, the initialization steps of the multi-factor association analysis model include creating a public weight pool for storing intermediate analysis results and multiple private element analyzers corresponding one-to-one with standardized element layers. Each private element analyzer reads the corresponding standardized element layer and preliminarily calculates the influence intensity value of the element based on the attributes of the standardized element layer itself. Specifically, a private element analyzer is a dedicated calculation module directly bound to each standardized element layer in the multi-factor association analysis model. During the initialization of the multi-factor association analysis model, the system dynamically creates an equal number of private element analyzers based on the types and quantities of standardized element layers generated in the previous steps. For example, when the standardized element layers include a spatial control zoning layer, a land use status layer, and an ecological constraint layer, the system will instantiate three private element analyzers accordingly. Each private element analyzer is assigned a unique identifier upon creation and establishes a strong association with a specific standardized element layer, enabling each analyzer to independently access and process all spatial geometric information and normalized attribute values ​​of its bound layer. The core function of a private feature analyzer is to calculate the initial influence intensity value based on the attributes of its associated layer. This calculation process considers the statistical characteristics and spatial autocorrelation of the layer attribute values. For example, for a layer representing development intensity, its corresponding private feature analyzer may generate the initial influence intensity value of that cell by calculating the weighted average of the attribute values ​​of each spatial grid cell and the attribute values ​​of its surrounding neighboring cells. These private feature analyzers, together with a common weight pool, constitute the core architecture of the multi-factor association analysis model. They exchange data through a predefined communication protocol. Specifically, all private feature analyzers write the calculated initial influence intensity value into the common weight pool and receive inter-feature facilitation or inhibition signals generated by global interaction calculations from the common weight pool, thereby dynamically adjusting their internal calculation parameters to update the influence intensity value. In some embodiments, when calculating the influence intensity value based on layer attributes, the private feature analyzer considers the statistical characteristics and spatial autocorrelation of the attribute values. For a standardized feature layer named "Commercial Development Intensity Layer," the private feature analyzer may calculate the weighted average of the development intensity value of each grid cell and the development intensity value of its neighboring cells, using this as the initial influence intensity value. All private feature analyzers write their respective influence intensity values ​​into a common weight pool, triggering a round of feature interaction intensity calculation based on spatial overlay analysis within the common weight pool. The common weight pool spatially aligns all received influence intensity values, unifying data from different layers onto the same spatial grid, and performs overlay operations based on grid cell locations. In essence, spatial overlay analysis calculates the combined effect of influence intensity values ​​from different features at the same geographic location; this combined effect is quantified through an interaction weight matrix.

[0095] In practice, the interaction intensity of features can be calculated using the following formula to quantify the interaction effect between two feature layers:

[0096]

[0097] in: Indicates the first In the round of iteration, elements With elements The interaction strength value between them It assesses the total number of grid cells within the region. and Representing elements respectively and elements In the In the round of iteration, in the grid cell The influence intensity value on, It is a predefined spatial covariance relation in the grid cell. upper element With elements The correlation coefficient is calculated. Based on the results of the interaction strength calculation, facilitating and inhibiting signals between elements are generated and fed back to each private element analyzer. For example, when the interaction strength value between the "road density layer" and the "land use mixing layer" is positive, a facilitating signal is generated; when the interaction strength value between the "ecological sensitivity layer" and the "construction intensity layer" is negative, an inhibiting signal is generated. Each private element analyzer dynamically corrects and recalculates its calculated influence strength value based on the received facilitating and inhibiting signals. The correction process adjusts the calculation parameters within the private element analyzer proportionally according to the direction and intensity of the signal. The process of writing influence strength values, calculating interaction strength, feeding back signals, and correcting values ​​is repeated until the rate of change of influence strength values ​​of each element in the public weight pool is lower than a preset threshold, and finally, a set of stable element comprehensive weights that reflect the interaction relationships is output.

[0098] The process begins with identifying bottleneck area sets based on the output of the multi-factor correlation analysis model. According to the comprehensive weights of the factors output by the model, the entire assessment area covered by the traffic network is spatially rasterized, and a comprehensive constraint intensity index is calculated for each raster cell. The comprehensive constraint intensity index is obtained by summing the standardized attribute values ​​of each factor in that raster cell multiplied by its corresponding comprehensive weight. The comprehensive constraint intensity index is then spatially overlaid with the basic traffic flow data of the traffic network to simulate the theoretical capacity of traffic flow under different constraint conditions. In some embodiments, the basic traffic flow data includes the free-flow travel time and design capacity of road segments. The simulation of theoretical capacity is achieved by inputting the comprehensive constraint intensity index as an impedance correction factor into a gravity model or a user equilibrium model. All raster cells whose theoretical capacity is lower than a preset carrying capacity threshold during the simulation are identified and marked as preliminary bottleneck cells. The preset carrying capacity threshold is set according to road grade and planning standards. For example, the saturation threshold for urban arterial roads is set to 0.85; raster cells covered by road segments with saturation exceeding this value are identified as preliminary bottleneck cells. Spatial clustering analysis is performed on the initial bottleneck units. Distance-based clustering algorithms are used to merge spatially continuous initial bottleneck units with similar constraining causes, forming several bottleneck regions with clear spatial boundaries. Optionally, the similarity of constraining causes is determined by comparing the comprehensive weight composition of the dominant factors within the initial bottleneck units. The types of dominant constraining factors and their spatial distribution patterns within each bottleneck region are analyzed to determine the set of bottleneck regions. For example, a bottleneck region may be dominated by both high ecological constraints and low road network density, and its spatial distribution pattern may present as a strip-shaped area along the river basin.

[0099] In one embodiment of the present invention, an independent scenario simulation sandbox is created for each region in the bottleneck region set. Each scenario simulation sandbox loads complete standardized feature layer data and transportation network data for the region. In each scenario simulation sandbox, one or more adjustment strategies targeting the dominant constraint factors of the region are selected from a predefined land space element adjustment strategy library. In some embodiments, the land space element adjustment strategy library contains structured strategy entries, the contents of which involve land use adjustment, development intensity change, ecological corridor restoration, or transportation infrastructure expansion. For a bottleneck region where the dominant constraint factor is "insufficient road network density" accompanied by "low land use mix", a combination strategy of "increasing the development intensity of land parcels" and "adding a branch road network" may be selected from the land space element adjustment strategy library. The selected adjustment strategies are combined with different implementation intensities and implementation sequences to construct multiple specific scenario parameter combinations. The implementation intensity is expressed as a percentage or absolute value, and the implementation sequence defines the order or parallel relationship of different adjustment operations. Optionally, the scenario parameter combinations are stored in a structured format in JSON or XML format, including a strategy identifier, a set of action space units, intensity parameters, and a time sequence number.

[0100] In the scenario simulation sandbox, the corresponding standardized feature layer data is dynamically modified according to each combination of scenario parameters, driving a traffic flow assignment model to simulate the carrying capacity of the transportation network under new spatial feature conditions. Specifically, the traffic flow assignment model is a calibrated macroscopic transportation model used to simulate the distribution of traffic demand on the road network and the carrying capacity of the road network under given land spatial feature conditions. The model is created based on the existing traffic network data and historical traffic survey data of the assessment area, and the parameter calibration process ensures that it reflects actual traffic travel patterns. In practice, the model typically adopts a four-stage model or an activity-based model structure, the core of which lies in dynamically matching and calculating the traffic demand derived from land spatial features with the supply capacity of the transportation network.

[0101] The model creation process begins with data preparation and basic model construction. First, it's necessary to collect basic data on the current traffic network of the assessment area, including the geometry, road class, number of lanes, design speed, and capacity of all road segments, as well as the geometric layout, signal timing schemes, and turning restrictions of traffic nodes such as intersections. Simultaneously, historical traffic survey data needs to be collected, such as origin-destination (OD) matrices, flow count data for key road segments, and travel time survey data. Based on this data, an initial traffic network model is constructed. This model is represented as a graph structure in the computer, where nodes represent intersections or area centroids, edges represent road segments, and each edge includes attributes such as free-flow travel time and capacity. Next, the model's parameters are calibrated. This step uses historical traffic survey data to calibrate the model's key parameters to ensure that the model's output matches the actual observed data. Specifically, during calibration, the historical OD matrix is ​​used as input and loaded into the initial traffic network model. A traffic flow allocation algorithm, such as a user-balanced allocation algorithm, is run to obtain simulated road segment flow. By comparing simulated traffic flow with historical observed traffic flow for the corresponding road segments, and iteratively adjusting the distribution parameters of the OD matrix or the impedance function parameters of the road segments, the error indicators between simulated and observed traffic flow, such as root mean square error or GEH statistic, are brought within a preset threshold. This calibration process ensures that the model can reliably reflect the operational characteristics of the current traffic system. After completing the basic model construction and calibration, the key to integrating the traffic flow assignment model with specific domains lies in the dynamic setting of its input data. When driving the model in a scenario simulation sandbox, its input is not fixed historical OD data, but rather generated from dynamically modified standardized feature layer data. Specifically, the model first reads the predicted feature layer generated after modification according to the scenario parameter combination, and extracts the attribute data of each traffic analysis zone from the layer, such as land use, development intensity, number of jobs, and resident population. These attribute data are used to calculate the traffic generation and attraction of each zone under the new spatial feature conditions through a pre-calibrated traffic generation rate model, thereby generating a predicted OD matrix corresponding to the scenario. This predicted OD matrix characterizes the traffic demand generated under the new national land spatial planning scenario. Another part of the model's input comes from the existing traffic network infrastructure data, but the capacity attributes of some road segments may be modified according to the adjustment strategies for traffic infrastructure in the scenario parameter combinations, such as adding new roads or expanding existing roads. The model inputs the predicted OD matrix along with the potentially updated road network supply data, and runs algorithms such as user equilibrium allocation again to simulate travelers' path selection behavior under new supply and demand conditions. Finally, it outputs the predicted traffic flow, road segment saturation, and service level data of key nodes for each road segment. This process clearly demonstrates that adjustments to land spatial elements, by changing the spatial distribution of traffic demand and road network supply conditions, inherently drive traffic flow assignment models to produce different simulation results, thereby assessing the impact of spatial intervention schemes on traffic carrying capacity.

[0102] Dynamically modifying standardized feature layer data can be understood as temporarily adjusting the attribute values ​​of specified spatial units in memory without changing the original data storage. The traffic flow allocation model can be a static user equilibrium model or a dynamic traffic simulation model. Key indicators such as changes in regional traffic network capacity and traffic distribution are recorded at the end of each scenario simulation. Scenario parameters are combined and encapsulated with the simulation results to form a potential spatial intervention plan. Capacity changes are determined by comparing road segment saturation or V / C ratios before and after the simulation, while traffic distribution changes are derived by comparing changes in the path selection ratio of the OD matrix. Historical performance comparison databases are used to verify the simulation results and label the stability of each potential spatial intervention plan, extracting core feature parameters for each plan. These core feature parameters include the type of adjusted features, spatial range, adjustment magnitude, and simulated capacity changes. In implementation, the simulated capacity changes are quantified as a comprehensive improvement rate. The core feature parameters are structured and encoded, and a similar case search is performed in the historical performance comparison database to find historical records of cases that have taken similar intervention measures in similar spatial locations. Similarity judgment is based on multi-dimensional distance calculations considering spatial location characteristics, element type, and adjustment magnitude. For each retrieved case record, long-term monitoring performance data after actual implementation and uncertainties that arose during implementation are extracted. Long-term monitoring performance data comes from post-project evaluation reports, including traffic operation monitoring data from different years after implementation. Uncertainty records include textual descriptions of construction delays, investment changes, or policy environment changes.

[0103] The expected effectiveness achievement confidence level of potential spatial intervention schemes is calculated by comparing simulated changes in traffic capacity with long-term monitoring effectiveness data from case studies. In some embodiments, the calculation of the expected effectiveness achievement confidence level considers the trend matching degree and numerical deviation between the simulation results and historical monitoring data. The expected effectiveness achievement confidence level can be calculated using the following formula:

[0104]

[0105] in: This indicates the confidence level in achieving the expected performance. It is the change in traffic capacity (such as the percentage reduction in saturation) derived from simulations of potential spatial intervention schemes. It is the average of the actual changes in traffic capacity over long-term monitoring of all similar cases retrieved. It is a very small constant used to prevent the denominator from being zero. It is the number of feature points for trend matching. This refers to the total number of feature points used for comparison. By analyzing uncertainties in case records, the volatility risk level faced by potential spatial intervention schemes during implementation is assessed. The volatility risk level is graded according to the type, frequency, and impact of uncertainties. Optionally, the volatility risk level is divided into three levels: high, medium, and low, corresponding to numerical values ​​of 3, 2, and 1. The expected effectiveness realization confidence level and volatility risk level are used as labels and assigned to the corresponding potential spatial intervention schemes to complete the simulation result verification and stability labeling. Specifically, in the process of verifying and labeling potential spatial intervention schemes in the historical effectiveness comparison database, the classification of volatility risk level is based on the analysis of uncertainties recorded in similar case records. The specific analysis process is as follows: Extract textual descriptions of uncertainties that occur during implementation from each similar case record. Classify these textual descriptions and divide them into different categories according to their nature. The patent points out that uncertainties include construction delays, investment changes, or changes in the policy environment. Secondly, the frequency of each type of uncertainty in historical cases is statistically analyzed. The frequency of occurrence is obtained by analyzing all case records stored in the historical performance comparison database that are similar to the dominant constraints and proposed adjustment strategies of the current bottleneck area. The frequency of occurrence is quantified by calculating the proportion of occurrences of a certain type of uncertainty in the set of similar cases out of the total number of cases. Next, the impact of each uncertainty on the actual implementation effect of the case is assessed. The impact is quantified by comparing the deviation between the long-term monitoring performance data recorded in the case records and the initial expected goals. For example, analyzing the length of the delay in opening time due to construction delays, or the proportion of project scale reduction due to investment changes, will translate into a reduction in the improvement of traffic carrying capacity, thereby calculating the specific impact value. Based on the three indicators of type, frequency of occurrence, and impact obtained from the above analysis, the system performs a grading operation. Grading is completed through a built-in evaluation function that takes the three indicators as input. Although the patent does not explicitly give the mathematical form of this function, its logic is: the higher the inherent risk of a certain type of uncertainty, the higher its frequency of occurrence in history, and the greater its impact on project performance, the higher the risk value contributed by that factor. For a potential spatial intervention scheme, its overall volatility risk level is determined by the risk value calculated from the uncertainties identified in all related and similar cases.

[0106] Specifically, a risk quantification formula can be constructed to characterize this process. All symbols in the formula are defined in this section and do not repeat in other embodiments:

[0107]

[0108] Among them, symbols This represents the comprehensive risk value calculated from potential space intervention schemes. (Symbol) This represents the total number of valid uncertainty factor entries extracted from similar cases. (Symbol) It is an index for traversing these uncertainties. (Symbol) Representing the Each type of uncertainty factor The inherent risk coefficient, which is preset according to the category definition. (Symbol) Representing the The frequency of occurrence of each uncertain factor. (Symbol) Representing the The numerical value representing the degree of influence of an uncertain factor.

[0109] Calculate the overall risk value The system then maps these risk levels to discrete risk levels. The patent explicitly states that volatility risk levels are divided into three categories: high, medium, and low. Therefore, the system presets two risk thresholds. and .when At that time, the volatility risk level was set as high and assigned a value of three. At that time, the volatility risk level is set to low and assigned a value of one. Between and During this period, the volatility risk level is defined as medium and assigned a value of two. Ultimately, this level value will be used as part of the stability labeling for the robustness dimension of the subsequent intervention plan decision matrix.

[0110] See Figure 3 This is a spatiotemporal heatmap of traffic carrying capacity efficiency evolution, used to display the changes in the traffic network carrying capacity efficiency index of different regions from January to June. In the context of land space and traffic network carrying capacity efficiency assessment, the core value of this heatmap lies in its ability to quickly identify spatiotemporally coupled low-efficiency areas such as the "northern area in May" and the "western residential area in January-February," providing a basis for accurately formulating spatial intervention plans. By analyzing the monthly trends of each region, the evolution direction of carrying capacity efficiency can be predicted, for example, to proactively address the periodic peak pressure in the central core area. It provides spatiotemporal priority guidance for traffic control and infrastructure optimization measures, such as prioritizing capacity during peak hours in the central core area. It can be used to track the implementation effectiveness of spatial intervention plans, such as comparing the efficiency changes before and after intervention in the western residential area to evaluate the effectiveness of the measures.

[0111] In one embodiment of the present invention, the step of integrating simulation results verification and stability annotation results to construct an intervention scheme decision matrix involves using each potential spatial intervention scheme as a candidate point, its expected effectiveness realization confidence level as the effectiveness dimension, and the reciprocal of its volatility risk level as the robustness dimension, thus constructing a two-dimensional intervention scheme decision matrix. In some embodiments, the intervention scheme decision matrix is ​​implemented in computer memory as a two-dimensional array or database table, where each candidate point corresponds to a coordinate position or record in the matrix, with the horizontal axis representing the effectiveness dimension and the vertical axis representing the robustness dimension. Optionally, the reciprocal of the volatility risk level is calculated using a formula... Calculated, where Assign values ​​to volatility risk levels. This refers to the robustness dimension value used to construct the matrix. In the intervention scheme decision matrix, priority-oriented weights from the current territorial spatial planning are introduced to weight the effectiveness and robustness dimensions, calculating the comprehensive priority score for each candidate point. These priority-oriented weights are derived from higher-level planning documents and represent the degree of importance attached to different planning objectives in vector form. Specifically, the acquisition of priority-oriented weights begins with retrieving the electronic text of currently valid higher-level planning documents from the territorial spatial basic information platform. These documents include overall plans, special plans, and policy documents. The system has a built-in planning text parser. This parser first scans the documents according to the standard objective dictionary in the territorial spatial planning classification system, identifying and extracting all declarative statements related to planning objectives. Subsequently, the text parser performs structured encoding on the extracted statements, transforming the unstructured text into structured records containing fields such as objective type, associated spatial level, and intensity modifiers. The system sets an initial importance accumulator for each type of planning objective. When the parser identifies an objective statement, it adds an importance score to the corresponding accumulator according to predefined rules, based on the effectiveness level of the document containing the statement, the intensity of the statement's sentence structure, and the frequency of the objective's appearance in the document. After traversing and parsing all relevant higher-level planning documents, the system obtains a raw set containing multiple planning objectives and their corresponding cumulative scores. Next, the system invokes an attribute normalization processor, similar to that used in the data processing phase, to perform dimensionless processing on all cumulative scores in the raw set, transforming the scores of each objective to the same dimension. Finally, the normalized scores are arranged sequentially to form a formal priority-oriented weight vector. The dimension of this vector is consistent with the number of planning objectives, and the value at each position in the vector represents the degree of importance given to the corresponding planning objective. This weight vector will be directly substituted into the comprehensive priority score calculation formula of the intervention scheme decision matrix to weight the effectiveness and robustness dimensions.

[0112] The overall priority score for each candidate point can be calculated using the following formula:

[0113]

[0114] in: Indicates the first The overall priority score of each candidate point It is the first The expected performance of each candidate point achieves the confidence level. It is the first Assigning volatility risk levels to each candidate point and These are priority-oriented weight coefficients assigned to the effectiveness and robustness dimensions, respectively. This is a scaling constant used to balance the orders of magnitude of the two terms. Based on the comprehensive priority score, a sequential elimination and optimization iteration is performed: in each round, some candidate points with the lowest comprehensive priority score are eliminated, and the policy parameters of the remaining candidate points are fine-tuned and cross-combined to generate new candidate points added to the intervention scheme decision matrix. Fine-tuning of policy parameters refers to making small random perturbations to the adjustment magnitude or timing based on the original scenario parameter combination; cross-combination refers to exchanging and recombining some policy parameters of two remaining candidate points. The elimination and iteration cycle is repeated until the average comprehensive priority score of the candidate points in the intervention scheme decision matrix no longer increases significantly. It can be understood that the criterion for the average comprehensive priority score no longer increasing significantly is that the average score growth rate of three consecutive iterations is less than a set threshold. From the final set of remaining candidate points, the scheme corresponding to the candidate point with the highest comprehensive priority score is selected as the final output of screening and optimization. To clearly illustrate this process, refer to Table 1, a simplified example of intermediate state decision matrix data.

[0115] Table 1: Example Data Table of Candidate Points in the Decision Matrix of Intervention Programs Candidate point number Confidence level of expected performance Volatility Risk Level robustness dimension value Overall Priority Score A1 0.85 2 0.50 0.74 A2 0.92 3 0.33 0.72 B1 0.78 1 1.00 0.81 B2 0.80 2 0.50 0.70 C1 0.88 2 0.50 0.76

[0116] After determining the recommended spatial intervention scheme based on the screening and optimization results, the final recommended spatial intervention scheme output from the screening and optimization is analyzed to obtain its complete scenario parameter combination. The scenario parameter combination is broken down into operational instructions for specific land spatial elements, including land use change instructions, development intensity adjustment instructions, or ecological space restoration instructions. In some embodiments, a "land use change instruction" includes a clear description of changing a designated plot from "industrial land (M1)" to "commercial and service facility land (B1)". Each operational instruction is matched with its corresponding geospatial unit, and the element attribute values, spatial boundaries, and implementation timing requirements before and after the operation are clearly defined. Geospatial units are associated through their unique identifiers, and implementation timing requirements are represented by stage numbers or absolute time points. All operational instructions with spatiotemporal constraints are formatted and encoded according to the land spatial planning data standard to form structured parameter data blocks. Optionally, each parameter data block includes an instruction header, instruction body, and instruction tail. All parameter data blocks undergo logical consistency review and spatial conflict detection to ensure there are no contradictions between parameters. Logical consistency review checks for attribute logic conflicts between instructions, while spatial conflict detection checks for geometric overlap in the scope of different instructions and contradictions in attribute change directions. Finally, these are integrated into a set of land spatial element adjustment parameters. This set is typically output as a file package or database transaction log, ensuring all changes are treated as a complete data update set.

[0117] See Figure 4 This is a scatter plot of the intervention scheme decision matrix, used in the scheme selection stage of the assessment of the carrying capacity effectiveness of land space and transportation networks. The visualization based on quantitative indicators reduces the interference of decision-makers' subjective experience in scheme selection, making the decision more objective and traceable. For medium-priority blue-green scatter points, scores can be improved by enhancing robustness or effectiveness; for low-priority blue-purple scatter points, direct elimination or adjustment of risk control strategies is possible. This approach breaks through the limitations of traditional single-indicator assessments, integrating the two core dimensions of "effectiveness credibility" and "risk stability," meeting the professional requirements of "multi-element integration" in land space planning. Through the comprehensive score of color mapping, quantifiable comparisons between different schemes are achieved, providing clear quantitative basis for subsequent sequential elimination and optimization iterations.

[0118] In one embodiment of the present invention, the step of coupling the set of land space element adjustment parameters with the basic data of the transportation network first involves applying the parameter data blocks in the set of land space element adjustment parameters one by one to the standardized element layer corresponding to the assessment area, generating a set of predictive element layers reflecting the post-intervention state. This process uses operation instructions encoded in the parameter data blocks to batch modify attribute values ​​and geometric information on a copy of the original standardized element layer. For example, based on a development intensity adjustment instruction, the "floor area ratio" attribute value of a specified grid cell is increased from 2.0 to 3.5, thereby generating an updated "land use status quo_predictive layer". In some embodiments, the generation of the predictive element layer is performed under the transaction management of the spatial database, ensuring that the application of all parameter data blocks either succeeds completely or is rolled back completely, maintaining data consistency. The predictive element layer is spatially overlaid with the current basic data of the transportation network and input into a calibrated macro-transport model for overall road network carrying capacity simulation. The macro-transport model, such as a four-stage model or an activity-based model, has its parameters calibrated using historical traffic survey data. It is understandable that spatial overlay operations establish the relationship between spatial element conditions and the traffic network, enabling the macro-traffic model to read new attribute values ​​from the predictive element layer within the coverage area of ​​each traffic analysis cell as model input.

[0119] The simulation results yield predicted traffic flow, road segment saturation, and node service level data for each traffic analysis unit within the evaluation area. These data represent the standard output of the macroscopic traffic model. To comprehensively characterize the carrying capacity of a traffic analysis unit, an optional map composite index can be calculated. The map composite index can be calculated using the following formula:

[0120]

[0121] in: Represents traffic analysis unit The comprehensive index of the map, It is located in the unit The collection of all road segments within the area. It is a section of road The predicted saturation It is a section of road The weight of the level, It is located in the unit The set of all traffic nodes within the area. It is a node The predictive service level level, It is a node Importance weight, and These represent the number of elements within the set. Predicted traffic flow, road segment saturation, and node service level data, or calculated map composite indices, are combined with their spatial location information and rendered onto a geographic base map to generate a thematic map containing multi-layered carrying capacity information. In some embodiments, the rendering process employs a hierarchical color scheme; for example, a gradient from green to red represents changes in road segment saturation from low to high, and circles of different sizes represent the map composite index values ​​of traffic analysis units. The thematic map undergoes symbolic refinement and legend labeling. Symbolic refinement includes selecting appropriate point, line, and polygon symbol styles for different categories of data, and the legend clearly explains the meaning and grading standards of each color and symbol, forming a visually appealing traffic network carrying capacity assessment map that demonstrates the changes and spatial distribution of the traffic network's carrying capacity after adjustments to land space elements.

[0122] See Figure 5 This is a radar chart showing the distribution of comprehensive indices across multiple zones, used for quantitative comparison of indicators. It simultaneously presents the differences in indicators across 10 zones, avoiding the limitations of single-dimensional assessments and enabling comprehensive quantitative comparison across multiple regions. Through clear high and low value zones, it can quickly identify advantageous and disadvantageous areas, providing direct evidence for resource allocation and scheme optimization. In the scenario of assessing the carrying capacity efficiency of land space and transportation networks, this radar chart can be used to compare the carrying capacity differences of different control zones, identifying advantageous and disadvantageous areas. It provides a basis for prioritizing zones in the formulation of subsequent spatial intervention plans. It intuitively displays the comprehensive assessment results of multiple zones, supporting cross-regional collaborative decision-making. The radar chart's circular structure and color contrast make cross-departmental communication more intuitive and facilitate understanding of the assessment results of multiple zones for non-technical personnel.

[0123] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A method for evaluating the carrying capacity of a transportation network that integrates multiple elements of national land space, characterized in that, include: It receives and integrates various element data from the national land and space basic information platform, performs spatial gridding and attribute layering processing on it, and generates standardized element layers; All the standardized feature layers are input into a multi-feature association analysis model to perform interaction influence analysis and weight iteration calculation between layers; Based on the output of the multi-factor correlation analysis model, a set of bottleneck areas that pose a key constraint on the carrying capacity of the transportation network is identified. For each region in the bottleneck region set, a parallel multi-scenario carrying capacity simulation process is initiated to generate multiple potential spatial intervention schemes; The simulation results and stability annotations for each potential spatial intervention scheme were performed using a historical performance comparison database. By integrating the simulation results verification and stability annotation results, an intervention scheme decision matrix is ​​constructed, and multi-level screening and optimization are performed within the intervention scheme decision matrix; Based on the screening and optimization results, a recommended spatial intervention scheme is determined and transformed into a specific set of adjustment parameters for national land space elements; The set of adjusted parameters for land and space elements is coupled with basic data of the transportation network to output the final transportation network carrying capacity assessment map.

2. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 1, characterized in that, The process of receiving and integrating various element data from the national land spatial information platform, performing spatial gridding and attribute layering processing on them, and generating standardized element layers includes: Receive and integrate various element data from the national land and space basic information platform to construct an initial fused data set; Based on the preset land spatial planning classification system, the initial fused data set is spatially gridded and attribute-layered to form multiple interrelated element data layers; Spatial registration and data standardization are performed on each of the aforementioned feature data layers to generate standardized feature layers with unified coordinate references and dimensions; The initial fused data set is spatially gridded and attribute-layered according to a preset land spatial planning classification system, forming multiple interrelated element data layers, including: Spatial control zoning rules, land use classification rules, and ecological protection red line rules are extracted from the preset national spatial planning classification system. The initial fused data set is divided into administrative and functional partitions using the aforementioned spatial control partitioning rules to generate a spatial control partitioning layer; The land use classification rules are used to strip the land use properties from the initial fused dataset to generate a current land use layer. The ecological protection red line rules are used to identify ecologically sensitive areas in the initial fused dataset, generating an ecological constraint layer. Establish spatial associations and attribute indexes between the spatial control zoning layer, the land use status layer, and the ecological constraint layer in the spatial database to ensure that attribute changes of any geospatial unit can be synchronously updated in all relevant feature data layers; The multiple interconnected element data layers include the spatial control zoning layer, the land use status layer, and the ecological constraint layer.

3. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 2, characterized in that, The step of performing spatial registration and data standardization on each of the feature data layers to generate a standardized feature layer with a unified coordinate reference and unit includes: Each feature data layer is configured with an independent spatial coordinate transformation engine to uniformly transform all vector and raster data within the feature data layer to a preset national geodetic coordinate system; In each feature data layer, all spatial patches and attribute fields contained therein are traversed to extract the original spatial geometric information and attribute values; The preset attribute normalization processor is invoked to perform dimensionless processing and statistical distribution adjustment on the extracted attribute values; The normalized attribute values ​​are re-associated with the corresponding spatial geometric information, and basic constraints from the national land spatial planning standards are injected to perform data integrity checks and logical consistency corrections. The output spatial data, which has undergone spatial registration and data standardization, and has unified spatial reference and standardized attribute values, serves as the standardized feature layer.

4. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 1, characterized in that, The step of inputting all the standardized feature layers into a multi-factor association analysis model for interaction influence analysis and weight iteration calculation between layers includes: Initialize the multi-factor correlation analysis model, which includes a public weight pool for storing intermediate analysis results and multiple private feature analyzers that correspond one-to-one with the standardized feature layers; Each of the private feature analyzers reads the corresponding standardized feature layer and preliminarily calculates the influence intensity value of the feature based on the attributes of the standardized feature layer itself; All the private feature analyzers write their respective influence intensity values ​​into the public weight pool, and trigger a round of feature interaction intensity calculation based on spatial overlay analysis within the public weight pool; Based on the results of the element interaction strength calculation, promotion and inhibition signals between elements are generated, and the promotion and inhibition signals between elements are fed back to each of the private element analyzers. Each of the private element analyzers dynamically corrects and recalculates the influence intensity value it has calculated based on the received promoting and inhibiting signals; The process of writing influence intensity values, calculating interaction intensity, signal feedback, and numerical correction is repeated until the rate of change of influence intensity values ​​of each element in the public weight pool is lower than a preset threshold. Finally, a set of stable element comprehensive weights that reflect interaction relationships is output.

5. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 4, characterized in that, Based on the output of the multi-factor correlation analysis model, a set of bottleneck areas that pose a key constraint on the carrying capacity of the transportation network is identified, including: Based on the comprehensive weights of the elements output by the multi-element correlation analysis model, the entire assessment area covered by the transportation network is spatially rasterized, and a comprehensive constraint intensity index is calculated for each raster unit. The comprehensive constraint intensity index is spatially superimposed with the basic traffic flow data of the traffic network to simulate the theoretical traffic flow capacity under different constraint conditions. All grid cells whose theoretical capacity is lower than the preset carrying capacity threshold during the simulation are identified and marked as preliminary bottleneck cells. Spatial clustering analysis is performed on the initial bottleneck units to merge spatially continuous initial bottleneck units with similar constraints, forming several bottleneck regions with clear spatial boundaries. The set of bottleneck regions is determined by analyzing the dominant constraint types and their spatial distribution patterns within each bottleneck region.

6. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 5, characterized in that, For each region in the bottleneck region set, a parallel multi-scenario carrying capacity simulation process is initiated to generate multiple potential spatial intervention schemes, including: Create an independent scenario simulation sandbox for each region in the bottleneck region set, and load the complete standardized feature layer data and traffic network data of the region into each scenario simulation sandbox. In each of the scenario simulation sandboxes, one or more adjustment strategies for the dominant constraints of the region are selected from a predefined library of land space element adjustment strategies. The selected adjustment strategies are combined with different implementation intensities and implementation sequences to construct multiple specific scenario parameter combinations; In the scenario simulation sandbox, the corresponding standardized element layer data is dynamically modified according to each scenario parameter combination, and a traffic flow allocation model is driven to simulate the carrying capacity of the traffic network under new spatial element conditions. Record key indicators such as changes in the traffic capacity and flow distribution of the regional traffic network at the end of each scenario simulation, and encapsulate the scenario parameters and simulation results to form a potential spatial intervention scheme.

7. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 6, characterized in that, The process of using a historical performance comparison database to verify the simulation results and label the stability of each potential spatial intervention scheme includes: Extract the core feature parameters of each potential spatial intervention scheme, including the type of element to be adjusted, the spatial range, the adjustment magnitude, and the simulated changes in traffic capacity; The core feature parameters are structured and encoded, and a similar case retrieval is performed in the historical performance comparison database to find historical records of cases that have taken similar intervention measures in similar spatial locations. For each of the aforementioned case records retrieved, extract its long-term monitoring effectiveness data after actual implementation and the uncertainties that arose during the implementation process; By comparing the simulated traffic capacity changes of the potential spatial intervention schemes with the long-term monitoring effectiveness data recorded in the case studies, the confidence level of the expected effectiveness of the potential spatial intervention schemes is calculated. By analyzing the uncertainties in the case records, the volatility risk level faced by the potential spatial intervention schemes during implementation is assessed. The expected performance confidence level and the volatility risk level are used as labels to assign corresponding potential spatial intervention schemes, thereby completing the simulation result verification and stability labeling.

8. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 7, characterized in that, The simulation results are integrated with the stability annotation results to construct an intervention plan decision matrix. Multi-level screening and optimization are then performed within this matrix, including: Using each potential spatial intervention scheme as a candidate point, its expected effectiveness realization confidence level as the effectiveness dimension, and its volatility risk level as the robustness dimension, a two-dimensional decision matrix for the intervention scheme is constructed. In the intervention scheme decision matrix, the priority-oriented weight of the current territorial spatial planning is introduced to weight the effectiveness and robustness dimensions, and the comprehensive priority score of each candidate point is calculated. Based on the comprehensive priority score, sequential elimination and optimization iteration are performed: in each round, some candidate points with the lowest comprehensive priority score are eliminated, and the strategy parameters of the remaining candidate points are fine-tuned and cross-combined to generate new candidate points to be added to the intervention scheme decision matrix. Repeat the elimination and iterative generation process until the average comprehensive priority score of the candidate points in the intervention scheme decision matrix no longer significantly improves; From the final set of retained candidate points, the solution corresponding to the candidate point with the highest comprehensive priority score is selected as the final output of screening and optimization.

9. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 8, characterized in that, Based on the results of screening and optimization, a recommended spatial intervention scheme is determined and transformed into a specific set of land space element adjustment parameters, including: Analyze, filter, and optimize the recommended spatial intervention schemes in the final output to obtain their complete combination of scenario parameters; The scenario parameter combination is broken down into operational instructions for specific land space elements, including land use change instructions, development intensity adjustment instructions, or ecological space restoration instructions. For each of the aforementioned operation instructions, match the geospatial unit to which it applies, and specify the element attribute values, spatial boundaries, and implementation timing requirements before and after the operation. All the operation instructions with spatiotemporal constraints are formatted and encoded according to the national land spatial planning data standard to form structured parameter data blocks; All parameter data blocks undergo logical consistency review and spatial conflict detection to ensure that there are no contradictions between parameters, and are finally integrated into the set of adjustment parameters for land and space elements.

10. The method for evaluating the carrying capacity of a transportation network integrating multiple elements of national land space according to claim 9, characterized in that, The process of coupling the set of adjusted parameters for land spatial elements with basic transportation network data to output the final transportation network carrying capacity assessment map includes: The parameter data blocks in the set of adjustment parameters for the land and space elements are applied one by one to the standardized element layer corresponding to the assessment area to generate a set of predictive element layers that reflect the state after intervention. The predicted feature layer is spatially overlaid with the existing traffic network basic data and input into the calibrated macro traffic model to simulate the overall road network carrying capacity. Obtain the predicted traffic flow, road segment saturation, and node service level data for each traffic analysis unit within the evaluation area from the simulation results; The predicted traffic flow, road segment saturation, and node service level data are combined with their spatial location information and rendered onto a geographic base map to generate a thematic map containing multi-layer carrying capacity information. The thematic maps are symbolized and labeled with legends to form a transportation network carrying capacity assessment map that intuitively displays the changes in carrying capacity and spatial distribution of the transportation network after adjustments to land space elements.

Images