Traffic station area land utilization efficiency evaluation method

Abstract

The invention belongs to the technical field of urban planning, and particularly relates to a traffic station region land utilization efficiency evaluation method, which comprises the following steps of: acquiring and preprocessing point-of-interest data and a traffic station region in an analysis region; extracting land utilization layout features based on the null data set; constructing a multi-mode traffic network including walking, bicycles, buses and rail transit based on the layout features; establishing a land coupling simulation model of traffic based on the regional reachability index; causal inference and model calibration are carried out based on historical traffic intervention events of dynamic evolution; adopting a multi-objective optimization algorithm to generate traffic and land utilization configuration schemes meeting different planning objectives; according to the method, the evaluation result is subjected to visual display and decision output, unified modeling of traffic and social economic data is achieved through multi-source heterogeneous data fusion and standardization processing, and the effect of improving data space-time matching precision and calculation reliability is achieved.

Description

Technical Field

[0001] This invention belongs to the field of urban planning technology, specifically a method for evaluating the land use efficiency of transportation hub areas. Background Technology

[0002] Urban land use efficiency directly impacts sustainable urban development and residents' travel convenience. With the advancement of urbanization, the relationship between public transportation infrastructure layout and land use is becoming increasingly close. How to rationally plan land use around transportation hubs has become a key issue in urban management. Traditional land use assessment methods often focus on static data and single transportation modes, lacking a comprehensive assessment of multi-modal public transportation networks and land use.

[0003] In related technologies, due to the different data sources used, these data exhibit inconsistencies in format, temporal granularity, and spatial scale. This heterogeneity prevents the data from being effectively fused directly, thereby affecting the accuracy and reliability of the model input.

[0004] Therefore, the present invention provides a method for evaluating land use efficiency in transportation hub areas. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0006] The technical solution adopted by this invention to solve its technical problem is: a method for evaluating land use efficiency in transportation hub areas, comprising the following steps:

[0007] Acquire and preprocess point-of-interest data and transportation station areas within the analysis area, and then construct multi-source data.

[0008] Land use layout features are extracted from empty datasets, and these features are used to calculate functional density, spatial mixing, and vitality index.

[0009] Based on the layout characteristics, a multimodal transportation network including walking, cycling, public transportation and rail transit is constructed, and regional accessibility indicators are calculated.

[0010] A land-based coupling simulation model for transportation is established based on regional accessibility indicators, using changes in transportation accessibility to drive the dynamic evolution of land use and economic variables.

[0011] Causal inference and model calibration are performed based on historical traffic intervention events with dynamic evolution to ensure that simulation results are consistent with actual trends.

[0012] A multi-objective optimization algorithm is used to generate traffic and land use configuration schemes that meet different planning objectives;

[0013] The assessment results are visualized and used for decision-making, generating an assessment report that includes accessibility heatmaps and land use recommendations.

[0014] As a further expansion of the above, the first step is to acquire Points of Interest (POI) data within the analysis area, and then determine the land use characteristics of that area based on the POI data. By acquiring POI data within the analysis area, the land use types within that area can be accurately identified. POI data reflects the geographical distribution of various socio-economic activities in the city, such as public transportation stations, commercial areas, residential areas, and cultural and educational facilities. This information is crucial for understanding the functional zoning of the city and serves as fundamental data for assessing land use efficiency.

[0015] Based on the aforementioned land use characteristics, a composite network accessibility model is constructed by combining the accessibility of multimodal public transport networks. This model utilizes the accessibility of multimodal public transport networks (including buses, subways, walking, and other modes of transportation) to construct a composite network accessibility model. This model can consider the linkage effects between different levels of the public transport network and travel modes, helping to assess the accessibility of transport station areas and the complementarity of land use. Multimodal public transport network accessibility is one of the key factors in land use efficiency assessment; it can effectively evaluate the impact of transport facility layout on land development and promote a positive interaction between public transport services and land use.

[0016] The land use efficiency of the analyzed area is quantitatively assessed using a composite network accessibility model. This model quantitatively evaluates regional land use efficiency. By calculating the composite network accessibility values ​​for different areas, the service level of transportation stations, the effectiveness of land use, and the coverage of public facilities in those areas can be analyzed. This assessment method considers not only the coverage of the transportation network but also the supply and demand of different types of land, ensuring the comprehensiveness and accuracy of the assessment results.

[0017] Based on the assessment results, a land use optimization plan is generated to guide rational land development and transportation infrastructure layout optimization. This plan proposes targeted optimization suggestions based on the scope of public transportation services and the balance between land demand and supply, aiming to promote efficient land use within the region and facilitate the rational allocation of public transportation facilities. This optimization plan can effectively guide the decision-making of urban planning departments and ensure the coordinated development of land use.

[0018] In this implementation, acquiring Points of Interest (POI) data within the analysis area includes: selecting POI data from a preset data platform within the analysis area to ensure the authenticity and objectivity of the data and reflect the characteristics of the analysis area. POI data not only provides geographic coordinate information but also includes multi-dimensional information such as POI function, consumption level, and type, which can further refine land use types and their spatial distribution. By acquiring POI data, different types of land use characteristics can be accurately identified and classified, providing accurate basic data for subsequent analysis.

[0019] Land use efficiency assessment based on network accessibility and the MGWR model: When analyzing land use efficiency, a composite network accessibility model is first constructed to assess the transportation service levels of different areas. Then, a multi-scale geographically weighted regression (MGWR) model is used to analyze the spatial differentiation characteristics of different types of land use (such as residential areas, commercial areas, and industrial areas). The MGWR model can consider multi-scale spatial heterogeneity within a region, revealing the relationship between land use and public transportation accessibility. The MGWR model is more flexible and accurate than the traditional geographically weighted regression (GWR) model, capable of simultaneously considering effects at multiple spatial scales and adapting to complex urban geographical environments.

[0020] Preferably, the acquisition of point-of-interest (POI) data within the analysis area includes selecting POI data within the analysis area from a preset data platform and analyzing land use types and spatial distribution based on the POI data;

[0021] The multi-source data includes geospatial data, traffic operation data, and socioeconomic data, forming a standardized multidimensional spatiotemporal dataset. The multi-source data further includes static geographic data, dynamic operation data, and socioeconomic data. The static geographic data includes points of interest, current land use status, and road and rail networks. The dynamic operation data includes mobile signaling, public transport and rail passenger flow, and shared travel trajectories. The socioeconomic data includes population density, employment density, housing prices, and income levels.

[0022] Preferably, the land use layout features include extracting category information from the POI data, further including category, function, and service level; and determining the land use type and its corresponding accessibility service range based on the category information.

[0023] Preferably, the land use layout features include:

[0024] Spatial density calculation based on POI data;

[0025] The functional mixing index is based on Shannon entropy and its value ranges from 0 to 1.

[0026] The vitality index is combined with POI density and pedestrian flow intensity, and spatial units of different functional types are identified by DBSCAN or K-Means clustering algorithms;

[0027] The method of generating a composite network accessibility model based on land use layout characteristics includes: combining the distribution of transportation stations, accessibility indicators, land use density, etc. within the analysis area to construct a comprehensive multimodal transportation network model.

[0028] Preferably, the generated land use optimization scheme includes optimizing land use layout and improving the service level of public transportation facilities and land use efficiency based on a multi-objective optimization model, including the maximum coverage site selection problem, combined with the accessibility assessment results of composite networks.

[0029] Preferably, during the causal inference and model calibration, the difference-in-differences method or the synthetic control method is used to identify the causal impact of traffic facility intervention on land use efficiency, and the simulation model parameters are calibrated using the causal inference results as constraints. The model parameter estimation adopts Bayesian inference or least squares fitting.

[0030] The evaluation of land use efficiency based on the composite network accessibility model includes: comparing the evaluation results output by the composite network accessibility model with the land use demand in the region to determine the suitability of the current land use and the coverage of public transportation facilities.

[0031] A land use efficiency assessment device for transportation hub areas, comprising:

[0032] The acquisition unit is used to acquire POI data within the analysis area and determine the land use characteristics of the area based on the POI data.

[0033] The processing unit is used to construct a composite network accessibility model and preprocess multi-source data based on the land use characteristics and traffic accessibility data.

[0034] Spatial feature analysis unit, used to extract land use structure features and calculate functional mixing degree and vitality index;

[0035] The traffic accessibility calculation unit is used to construct a multimodal transportation network and calculate accessibility indicators.

[0036] Coupled simulation unit, used for the linkage evolution simulation of transportation and land systems;

[0037] An optimized decision-making unit is used for multi-objective optimization calculations;

[0038] The evaluation unit is used to assess land use efficiency based on the composite network accessibility model and generate land use optimization schemes.

[0039] A chip, which is part of a land use efficiency assessment device for transportation station areas, includes a processor, a memory, and an input / output interface connected to the processor; when a program in the memory is executed, any step of the method is performed.

[0040] A computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to perform the method according to any one of claims 1-6.

[0041] A computer program product comprising a computer program that, when run on a computer, causes the computer to perform the method according to any one of claims 1-6.

[0042] The beneficial effects of this invention are as follows:

[0043] 1. This invention achieves unified modeling of traffic, land use, and socio-economic data through the fusion and standardized processing of multi-source heterogeneous data, thereby improving the accuracy of data spatiotemporal matching and computational reliability, and enhancing the integrity of assessment data and the accuracy of model input.

[0044] 2. This invention, by constructing a composite network accessibility model integrating walking, cycling, public transportation, and rail transit, accurately reflects the spatial coupling relationship between multimodal transportation and land use, and improves the accuracy and spatial interpretation capability of regional transportation accessibility assessment compared to related technologies.

[0045] 3. This invention, by introducing causal inference and model calibration mechanisms, uses historical traffic intervention events to correct simulation model parameters, thereby improving the model's fit accuracy and dynamic prediction capabilities. Compared with related technologies, it enhances the credibility of land use efficiency assessment results and its decision support value. Attached Figure Description

[0046] The invention will now be further described with reference to the accompanying drawings.

[0047] Figure 1 This is a schematic diagram of the structure of a land use efficiency assessment system provided in an embodiment of this application;

[0048] Figure 2 This is a schematic diagram of POI reclassification provided in an embodiment of this application;

[0049] Figure 3 This is a schematic diagram of a composite network reachability calculation method provided in an embodiment of this application;

[0050] Figure 4 This application provides a flowchart for urban land use efficiency assessment based on the GWR model.

[0051] Figure 5 This is a schematic diagram of the structure of a land use efficiency assessment system provided in an embodiment of this application;

[0052] Figure 6 This is a schematic diagram of a land use efficiency assessment device for transportation station areas provided in an embodiment of this application;

[0053] Figure 7 This is a schematic diagram of the land use efficiency assessment device of the present invention;

[0054] Figure 8 This is a flowchart of the method of the present invention;

[0055] Figure 9 This is a schematic diagram of the device module architecture of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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.

[0057] Specific implementation examples are given below.

[0058] like Figures 1 to 8 As shown in the figure, an embodiment of the present invention provides a method for evaluating land use efficiency in transportation hub areas, comprising the following steps:

[0059] Acquire and preprocess point-of-interest data and transportation station areas within the analysis area, and then construct multi-source data.

[0060] Land use layout features are extracted from empty datasets and used to calculate functional density, spatial mixing, and vitality index.

[0061] Based on the layout characteristics, a multimodal transportation network including walking, cycling, public transportation and rail transit is constructed, and regional accessibility indicators are calculated.

[0062] A land-based coupling simulation model for transportation is established based on regional accessibility indicators, using changes in transportation accessibility to drive the dynamic evolution of land use and economic variables.

[0063] Causal inference and model calibration are performed based on historical traffic intervention events with dynamic evolution to ensure that simulation results are consistent with actual trends.

[0064] A multi-objective optimization algorithm is used to generate traffic and land use configuration schemes that meet different planning objectives;

[0065] The assessment results are visualized and used for decision-making, generating an assessment report that includes accessibility heatmaps and land use recommendations.

[0066] Acquiring point-of-interest (POI) data within the analysis area includes selecting POI data from a preset data platform within the analysis area and analyzing land use types and spatial distribution based on the POI data;

[0067] Multi-source data includes geospatial data, traffic operation data, and socioeconomic data, forming a standardized multidimensional spatiotemporal dataset. Multi-source data further includes: static geographic data, dynamic operation data, and socioeconomic data. Static geographic data includes points of interest, current land use, and road and rail networks. Dynamic operation data includes mobile signaling, public transport and rail passenger flow, and shared mobility trajectories. Socioeconomic data includes population density, employment density, housing prices, and income levels.

[0068] Specifically, the first step is to acquire Points of Interest (POI) data within the analysis area. POI data originates from a pre-defined data platform, and its spatial coordinates, categories, and service attributes are extracted by defining a specific area. Based on this data, different land use types and their spatial distribution can be identified. POIs are a fine-grained expression of regional functional supply; their density, type, and mixed structure directly reflect land use vitality and spatial functional layout. This invention reveals micro-level land use differences that cannot be reflected in traditional land parcel statistics through POI data, improving the accuracy of land use identification and spatial interpretability. It constructs a multi-source data system in one step, including geospatial data, traffic operation data, and socioeconomic data, forming a standardized multi-dimensional spatiotemporal dataset through unified scale processing. Static data is used to characterize the spatial structure and land features of the region; dynamic data reflects population flow and traffic operation status; and socioeconomic data describes the region's development level and activity intensity. By combining these two types of data, this invention forms a comprehensive data framework that is fine-grained, dynamic, and interpretable, providing a key data innovation foundation for land use efficiency assessment in transportation hub areas and laying a unified data logic for subsequent model construction and optimization decisions.

[0069] Land use layout characteristics include extracting category information from POI data, further including category, function, and service level; and determining the land use type and its corresponding accessibility service range based on the category information.

[0070] Specifically, the extraction of land use layout characteristics includes obtaining information such as category, function, and service level from Points of Interest (POI) data. By classifying, statistically analyzing, and spatially aggregating different categories of POIs, different functional types such as commercial, residential, and public service can be identified, and the corresponding land use types and service areas can be determined accordingly. Based on the spatial distribution characteristics of different categories, the influence radius and accessibility range of various functions around transportation hubs are further defined, providing a quantitative basis for the spatial evaluation of land use efficiency. This enables the assessment model to dynamically identify the radiation effect of transportation hubs on different functional land uses, reveal the spatial adaptation relationship between transportation facilities and land use, and improve the accuracy and interpretability of land use efficiency assessment.

[0071] Land use layout characteristics include:

[0072] Spatial density calculation based on POI data;

[0073] The functional mixing index is based on Shannon entropy and its value ranges from 0 to 1.

[0074] The vitality index is combined with POI density and pedestrian flow intensity, and spatial units of different functional types are identified by DBSCAN or K-Means clustering algorithms;

[0075] A composite network accessibility model is generated based on land use layout characteristics, including: combining the distribution of transportation stations, accessibility indicators, land use density, etc. in the analysis area to construct a comprehensive multimodal transportation network model.

[0076] Specifically, the construction of land use layout characteristics includes: calculating spatial density based on Points of Interest (POI) data to reflect the agglomeration degree and distribution pattern of different functional types; calculating the functional mixing index (range 0–1) using the Shannon entropy method to measure the diversity and balance of functional types within the region; calculating the vitality index by combining POI density and pedestrian flow intensity; and identifying spatial units with different functional characteristics through DBSCAN or K-Means clustering algorithms to achieve automatic classification and identification of land use patterns. Based on the land use layout characteristics, a composite network accessibility model is generated. This model comprehensively considers the distribution of transportation stations, land use density, and accessibility indicators to construct a multi-modal transportation network including walking, cycling, public transportation, and rail transit, achieving integrated modeling of transportation network structure and land use characteristics.

[0077] The generated land use optimization schemes include a multi-objective optimization model, including the maximum coverage site selection problem, combined with the results of composite network accessibility assessment, to optimize land use layout, improve the service level of public transportation facilities and land use efficiency.

[0078] Specifically, by employing a multi-objective optimization method that comprehensively considers the balance between transportation accessibility and land use efficiency, the optimal land use configuration can be accurately identified. By optimizing the location of transportation hubs and the layout of land use, the service quality of public transportation within the region can be significantly improved, while simultaneously promoting efficient land use and maximizing economic benefits. This mechanism effectively solves the problem of simultaneously balancing transportation services and land use efficiency in traditional planning methods, enhancing the overall adaptability and sustainability of the plan.

[0079] When performing causal inference and model calibration, the difference-in-differences method or synthetic control method is used to identify the causal impact of traffic facility intervention on land use efficiency, and the simulation model parameters are calibrated with the causal inference results as constraints. The model parameters are estimated using Bayesian inference or least squares fitting.

[0080] The evaluation of land use efficiency based on the composite network accessibility model includes comparing the evaluation results output by the composite network accessibility model with the land use demand in the region to determine the suitability of current land use and the coverage of public transportation facilities.

[0081] Specifically, the causal inference and model calibration sections employ the difference-in-differences method or the synthetic control method to identify the causal impact of transportation infrastructure intervention on land use efficiency. By comparing the land use change patterns before and after the intervention in the intervention area and the control area, the net effect brought about by transportation infrastructure construction is extracted. Based on the causal inference results, the simulation model parameters are calibrated to ensure that the model can truly reflect the actual impact process of transportation intervention. Parameter estimation uses Bayesian inference or least squares fitting methods to improve the model's accuracy and stability. On this basis, a comprehensive evaluation of land use efficiency is conducted based on a composite network accessibility model. The accessibility assessment results output by the model are compared with regional land use demand to determine the suitability of the current land use layout and the coverage of public transportation facilities. This process, through a closed-loop mechanism of causal identification and model calibration, achieves quantitative analysis from transportation intervention to land response, effectively revealing the path of transportation infrastructure optimization in improving land use efficiency, and providing a scientific basis for urban spatial structure optimization and transportation planning decisions.

[0082] like Figure 9 As shown, a land use efficiency assessment device for transportation station areas includes:

[0083] The acquisition unit is used to acquire POI data within the analysis area and determine the land use characteristics of the area based on the POI data.

[0084] The processing unit is used to construct a composite network accessibility model and preprocess multi-source data based on land use characteristics and traffic accessibility data;

[0085] Spatial feature analysis unit, used to extract land use structure features and calculate functional mixing degree and vitality index;

[0086] The traffic accessibility calculation unit is used to construct a multimodal transportation network and calculate accessibility indicators.

[0087] Coupled simulation unit, used for the linkage evolution simulation of transportation and land systems;

[0088] An optimized decision-making unit is used for multi-objective optimization calculations;

[0089] The evaluation unit is used to assess land use efficiency based on the composite network accessibility model and generate land use optimization schemes.

[0090] Specifically, the acquisition unit is used to acquire point of interest (POI) data within the analysis area and determine the land use characteristics of the area based on its spatial distribution, category, and service attributes;

[0091] The processing unit is used to construct a composite network accessibility model based on land use characteristics and traffic accessibility data, and to perform unified preprocessing on multi-source spatial data.

[0092] The spatial feature analysis unit is used to extract land use structure characteristics and calculate functional mixing degree and vitality index, reflecting the diversity and activity of regional spatial functions;

[0093] The transportation accessibility calculation unit is used to construct a multimodal transportation network that includes walking, cycling, public transportation, and rail transit, and to calculate accessibility indicators.

[0094] Coupled simulation unit is used to simulate the coordinated evolution of transportation and land systems and analyze the dynamic impact of changes in transportation facilities on land use efficiency.

[0095] The optimization decision-making unit is used to perform calculations based on a multi-objective optimization model to generate the optimal land use and transportation layout scheme.

[0096] The evaluation unit is used to comprehensively evaluate land use efficiency based on the output of the composite network accessibility model and to propose optimization suggestions.

[0097] This device integrates multi-source data, coupled simulation and optimization decision-making, and realizes collaborative analysis and dynamic optimization of transportation and land use systems, effectively improving the level of public transportation services and land use efficiency, and providing scientific support for urban spatial planning.

[0098] A chip, which is part of a land use efficiency assessment device for transportation station areas, includes a processor, a memory, and an input / output interface connected to the processor; when a program in the memory is executed, any step of the method is executed.

[0099] A computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to perform the method of any one of claims 1-6.

[0100] A computer program product comprising a computer program that, when run on a computer, causes the computer to perform the method of any one of claims 1-6.

[0101] At work, Figure 1 This is a schematic diagram 100 of a land use efficiency assessment system for transportation hub areas provided in this application. As shown in the system architecture 100, the system includes components such as a data acquisition device 106, a database 108, feature engineering 109, and an execution device 110. The data acquisition device 106 is used to collect and analyze various data within the area, including but not limited to point of interest (POI) data, transportation network data, and land use feature data. All of this data will be transmitted to the database 108 for storage, ensuring centralized management and efficient retrieval of the data. The data in the database 108 can come from different data sources, not limited to data collected by the data acquisition device 106, but may also be obtained through other channels (such as external databases, cloud services, etc.). After being stored in the database 108, the data is used for subsequent processing and evaluation.

[0102] In this embodiment, feature engineering 109 performs feature extraction and processing based on data in database 108. The main task of feature engineering is to extract key features from the raw data that can effectively describe land use efficiency. Through analysis of historical data, feature engineering 109 can generate a feature model for land use efficiency assessment. This feature model may include features such as traffic accessibility, land use density, and distribution of public facilities. These features will serve as input data to help the execution device 110 perform a more accurate land use efficiency assessment.

[0103] Feature engineering 109 processes historical data extracted from database 108 to generate a feature model, which can be used to analyze land use efficiency in different regions. The feature engineering process includes extracting relevant features from multiple sources (such as accessibility to transportation stations, land use types, and population distribution) and performing necessary data preprocessing such as normalization and standardization to ensure the data meets the requirements of the subsequent model. Feature engineering 109 not only processes data from database 108 but can also obtain external datasets from the cloud or other devices for feature extraction and processing.

[0104] Based on the feature model generated by feature engineering 109, the generated features can be input into the subsequent execution device 110. The execution device 110 can be a terminal device (such as a mobile terminal, tablet computer, laptop computer, vehicle terminal, etc.), or a server or cloud device. Figure 1 In the process, the execution device 110 is equipped with an I / O interface 102 for data interaction with external devices. Users can input data to the I / O interface 102 through the client device 104.

[0105] The preprocessing module 103 of the execution device 110 is used to preprocess the input data received from the I / O interface 102. In this embodiment, the preprocessing module 103 can perform normalization or other necessary data processing on the input data to ensure that the input data can be accurately processed by the target feature model. The preprocessing process may include standardizing or other format conversion of the regional feature variables of each unit region to match the model input requirements.

[0106] After the execution device 110 preprocesses the input data, the calculation module 111 will perform the core calculation task of land use efficiency assessment. This module will call the generated feature model to quantitatively assess the land use efficiency of each unit area. The land use efficiency assessment results are based on input factors such as accessibility of the multimodal transportation network, POI data, and regional characteristics, and output the land use efficiency value for each unit area through the target model. The execution device 110 can call the data, models, and code stored in the data storage system 105 to complete the assessment process and generate relevant assessment results. The calculated assessment results will be stored in the data storage system 105 for subsequent querying and optimization scheme generation.

[0107] Finally, the execution device 110 will generate a land use optimization plan based on the assessment results and feed the processing results back to the user through the I / O interface 102. The client device 104 obtains the land use efficiency assessment results from the system by inputting data and querying requests, and makes appropriate decisions on land development, public transportation facility layout, etc., based on these results. This optimization plan can provide urban planners with precise decision support, help rationally allocate land resources, optimize the layout of transportation facilities, and improve the efficiency of regional land use.

[0108] Figure 1 This is merely a schematic diagram of a system architecture provided by an embodiment of the present invention. The positional relationships between the devices, modules, and components shown in the diagram do not constitute any limitation. For example, in Figure 1In this embodiment, the data storage system 105 is described as an external memory. However, in other embodiments, the data storage system 105 can also be integrated into the execution device 110 to form a more compact system architecture. Furthermore, the I / O interface 102, computing module 111, and other components can be adjusted according to specific needs to adapt to different application scenarios and computing resource configurations.

[0109] Figure 2 This is a classification diagram of comfort items. Figure 2 This diagram illustrates the application of Point of Interest (POI) data in urban land use classification, as provided in this embodiment. POI data is core data for refining and classifying urban land use types. Reclassifying POI data allows for more accurate identification and description of land use characteristics in different functional areas. In urban land use assessment, POI data provides fine-grained information for land use efficiency evaluation by dividing various functional areas. This data reflects important characteristics of daily activities, commercial services, and traffic flow in the city. Based on this information, urban planners can gain a clearer understanding of the functional distribution of different areas and optimize land use accordingly. By reclassifying this POI data, we can identify the following types of regional characteristics:

[0110] Natural areas of interest (POI) include parks, green spaces, wetlands, mountains, and other natural environmental elements. These areas are typically used to improve the quality of the urban ecological environment, provide spaces for residents' leisure and recreation, enhance the city's ecosystem services, and improve urban air quality and biodiversity. Natural areas are an important component of urban green infrastructure, providing vital ecological support to the city, effectively mitigating the urban heat island effect, and improving residents' quality of life.

[0111] Residential POIs include residential areas such as houses, residential communities, and villa areas, reflecting characteristics such as population density, housing type, and quality of life in the region. In land use efficiency assessment, the optimization of the layout of residential areas and transportation facilities is crucial. Through detailed subdivision and analysis of residential areas, the spatial configuration of residential areas can be optimized, thereby improving the quality of life in the region.

[0112] Commercial area POIs include consumer service facilities such as shopping malls, supermarkets, restaurants, and shopping centers.

[0113] Public facility zones (POIs) include hospitals, schools, libraries, and sports facilities. These are fundamental infrastructures for residents' daily lives, directly impacting their quality of life and social welfare. Public facility zones significantly enhance urban livability and convenience. In land use efficiency assessments, the accessibility and coverage of public facilities are crucial factors in optimizing urban resource allocation. Layout analysis of public facility zones can identify service gaps, providing data support for improving the distribution of public service facilities and enhancing the efficiency of public services within the area.

[0114] Points of Interest (POIs) categorized as transportation facilities include subway stations, bus stops, parking lots, and other facilities related to transportation. The layout and accessibility of transportation facilities directly impact regional traffic flow and land use efficiency. Effective transportation facility layout not only improves regional accessibility but also promotes the rational development and utilization of land. Therefore, in land use efficiency assessment, the density, distribution, and relationship with other land use functions of transportation facilities are key factors. By analyzing the distribution of transportation facilities, transportation networks can be further optimized, and the level of public transportation services can be improved.

[0115] Cultural and entertainment zones (POIs) include museums, cinemas, art galleries, and performing arts centers. Reclassifying these different types of POIs allows for a clearer identification of the distribution and characteristics of different functional areas within a city, providing accurate data support for land use efficiency assessment. This classification method not only helps improve the precise allocation of urban resources but also assists urban planners in identifying the strengths and weaknesses of each area, thereby optimizing resource allocation and layout and promoting sustainable urban development.

[0116] Figure 3 This is a schematic diagram of a composite network reachability calculation method, which includes, but is not limited to, the following steps:

[0117] First, in the data input phase, the system collects and inputs relevant data, primarily including urban transportation network data, Points of Interest (POI) data, and other regional characteristic data related to land use. Through data acquisition equipment, the system obtains accessibility information for various modes of transportation (such as subway, bus, and walking) and inputs this data into the computational model for processing. Based on bus and subway line data, the system establishes a composite urban network. This composite network integrates data from multiple transportation modes, including buses and subways, forming a comprehensive transportation network. This network, by representing the connections between various transportation stations, helps calculate the accessibility of each area under different transportation modes.

[0118] During the calculation, the system performs a composite network accessibility analysis for each grid (e.g., a 400m x 400m grid). For a given grid Gn, the system first calculates the number of directly accessible grids (AG0T), i.e., the number of other grids directly accessible from stations within that grid. Then, the system continues to analyze the number of grids accessible with one transfer (AG1T) and two transfers (AG2T), i.e., the number of grids accessible with one or two transfers. This process helps assess the coverage of public transport stations and their service capacity to the area under different numbers of transfers.

[0119] The formula for calculating the reachability AGe of any grid Gi in the study area is shown below:

[0120] AG i =AG0T+AG1T(1- )+AG2T(1- (1)

[0121] In the formula, n represents the total number of grid cells within the study area (e.g., 7826 grid cells in Shanghai). β1 and β2 are standardized constants used to represent the decreasing willingness of residents to choose public transportation as the number of transfers increases; the more transfers, the lower the convenience of travel, and thus its influence gradually diminishes. Through this method, the system can comprehensively evaluate the composite network accessibility of each grid cell and provide accessibility assessment results for different areas based on different traffic modes and transfer demands. These calculation results provide effective data support for land use efficiency assessment.

[0122] Figure 4 This application provides a flowchart for urban land use efficiency assessment based on the MGWR model. The MGWR model is an extension of Geographically Weighted Regression (GWR) to address the multi-scale spatial heterogeneity problem in geospatial analysis. By combining multiple spatial scales to optimize regression coefficients, the MGWR model can more accurately capture the relationship between land use efficiency and public transportation accessibility, especially when dealing with areas with different spatial scales, providing more representative and accurate analytical results. The following are the detailed steps and explanations for applying the MGWR model to urban land use efficiency assessment.

[0123] Step S401: Multicollinearity test

[0124] Before performing spatial regression analysis using the MGWR model, a multicollinearity test is necessary. Multicollinearity refers to a high degree of linear correlation among the independent variables in a regression model, which can affect the model's stability and estimation accuracy. In the MGWR model, to ensure the accuracy and reasonableness of the regression analysis, the selected independent variables must be tested for multicollinearity. The variance inflation factor (VIF) is typically used to test for multicollinearity. The formula for calculating the VIF value is as follows:

[0125] VIF=1 / (1-r 2 (2)

[0126] In the formula, r² is the coefficient of determination for linear regression, representing the percentage of change in the dependent variable explained by the linear regression equation. If the VIF value is too high (usually greater than 10), it indicates strong collinearity, requiring further data processing or the selection of other independent variables.

[0127] Step S402: Regression Model Establishment and Parameter Estimation

[0128] In the MGWR model, the regression parameters are spatially related. Unlike the traditional least squares (OLS) regression model, the regression coefficients in the MGWR model have different values ​​for each geographical location. The regression formula for the MGWR model is as follows:

[0129] (3)

[0130] In the formula, ui,vi are the coordinates (e.g., spatial latitude and longitude) of the i-th sample point; β0ui,vi is a constant term; βkui,vi represents the regression coefficient of the k-th explanatory variable of the i-th sample point, which is a function of geographic location; Xik is the k-th explanatory variable of the i-th sample point; εi~N0,δ2 is the random error. Unlike the OLS model, the regression coefficients in the MGWR model are functions of geographic location. The regression coefficients of each sample point change according to geographic location, reflecting the non-stationary relationship between land use characteristics and public transportation accessibility in different regions. Therefore, the MGWR model can more accurately capture the spatial heterogeneity between land use efficiency and transportation network accessibility in different regions. In the MGWR model, the regression coefficients are weighted by a spatial weight matrix, making the regression coefficients of each location more consistent with the actual situation of the region, thereby optimizing the estimation of land use efficiency.

[0131] Step S403: Determining the Spatial Weighting Function and Bandwidth

[0132] The spatial weight matrix plays a crucial role in the MGWR model, reflecting the similarity and influence between different geographical locations. Commonly used spatial weight functions in the MGWR model include the distance threshold method, the inverse distance method, the Gaussian function method, and the truncated function method. Among these, the Gaussian function is frequently used to calculate the spatial weight matrix due to its smoothness and universality. The form of the Gaussian function is as follows:

[0133] W ij =exp(-(d ij / b) 2 (4)

[0134] In the formula, dij represents the distance between data points i and j, typically the Manhattan distance or Euclidean distance; b is the bandwidth, representing the non-negative decay function between spatial distance and spatial weights. The choice of bandwidth b directly affects the accuracy of the spatial weight matrix. If the bandwidth is too small, the spatial weights decay too quickly, potentially ignoring the influence of distant points; conversely, if the bandwidth is too large, too many influential points may be included, thus affecting the accuracy of the regression results. The bandwidth is usually optimized using cross-validation (CV) or the Akaike Information Criterion (AIC). Cross-validation selects the bandwidth by minimizing the prediction error, while AIC optimizes the model by minimizing the information criterion. These methods can find the optimal bandwidth, ensuring the effectiveness of the spatial weight matrix.

[0135] Taking Shanghai as an example, the descriptive statistical results of various types of POI data are shown in Table 1. Due to the large study area and the widespread unevenness in grid development levels, the influence of different types of POI data on the accessibility of composite grid networks exhibits significant spatial heterogeneity, resulting in both positive and negative regression coefficients in the MGWR model. Meanwhile, the average sign of the MGWR model coefficients for each type of POI data is positive, and the numerical differences are small. This result indicates that the influence of different types of POI data on most sample grids within the entire study area is consistent.

[0136] Table 1 Calculation results of MGWR model

[0137] POI type average value Minimum value Maximum value Standard deviation median bandwidth Business Services 0.023 -0.361 0.405 0.125 0.015 48 Transportation facilities 0.122 -0.188 0.691 0.111 0.104 150 residential type 0.113 -1.377 1.929 0.243 0.056 101 Industrial type 0.016 -0.152 0.549 0.073 0.008 69 Greenland Plaza 0.112 -1.282 3.135 0.525 0.034 301 Public services 0.073 -0.425 0.918 0.177 0.051 130

[0138] The regression coefficients of the MGWR model reflect the degree of influence of different types of POI data (spatial distribution characteristics of urban land use) on the accessibility of the grid's composite network. That is, under the current accessibility of the multimodal public transport network, the regression coefficient values ​​of the MGWR model for different types of POI data reflect the sufficiency of that type of land use.

[0139] (1) Overall, the composite network located in the grid of the central urban area of ​​Shanghai has good accessibility (the public transportation facilities in the central urban area are well-developed and the service level is high). At the same time, the regression coefficients of the MGWR model of different types of POI data are positive and small (the POIs of various types in the region are relatively sufficient), which is consistent with the expectations of this study, indicating that the socio-economic development and public transportation infrastructure in the central urban area of ​​Shanghai are relatively good.

[0140] (2) For grids located outside the central urban area, the larger the positive value of the regression coefficient of a certain type of POI in the MGWR model within the grid, the more the POI of that type needs to be further improved within the grid; the smaller the positive value of the coefficient, the more sufficient the POI of that type is within the grid; when the coefficient is negative, it indicates that the POI of that type within the grid is negatively correlated with the accessibility of the composite network.

[0141] Step S404: MGWR Model Result Analysis and Verification

[0142] After completing the MGWR regression analysis, the model results need to be tested. Testing the MGWR model includes several aspects such as regression coefficients, residuals, and goodness of fit. The residuals in the model results represent the difference between actual observed values ​​and predicted values; the smaller the sum of squared residuals, the better the model fit. Other testing indicators for the MGWR model include the AIC (Akaike Information Criterion) and the R² value. The AIC is used to evaluate the model's fit; the lower the AIC value, the better the model fit. The R² value measures the model's explanatory power; the closer the R² is to 1, the better the model fit. Analysis of the MGWR model results reveals the spatial heterogeneity of different regions under different transportation infrastructure layouts and land use characteristics. For example, in the analysis of Shanghai, the city center may show strong positive regression coefficients for commercial service POIs and transportation facility POIs, while the suburbs may have lower regression coefficients due to relatively insufficient transportation infrastructure. The spatial distribution of these regression coefficients can provide urban planners with in-depth insights into land use efficiency, thereby helping to optimize land resource allocation and transportation infrastructure layout.

[0143] Step S405: Application of Results to Urban Land Use Optimization

[0144] The residuals of the MGWR model represent the difference between the estimated and actual values ​​of the dependent variable. The residuals for each grid cell indicate the deviation between the MGWR model's assessment of the grid's composite network accessibility based on different types of Points of Interest (POIs) within the grid and the actual accessibility. A positive residual for a grid cell indicates that the MGWR model's estimated accessibility is less than the actual composite network accessibility of the current grid cell: that is, the current grid cell has a high level of public transportation service, meeting the travel needs of urban residents arising from land use within and around the grid cell. Conversely, a negative residual for a grid cell indicates that the MGWR model's estimated accessibility is greater than the actual composite network accessibility of the current grid cell: that is, the current grid cell has a relatively low level of public services, which does not match residents' travel needs.

[0145] The results of the MGWR model analysis can reveal the land use efficiency of different regions. Based on the regression coefficients of different regions, the impact of land use types such as commercial services, transportation facilities, and residential types on the accessibility of the composite network can be further analyzed.

[0146] Figure 5 This application provides a flowchart for assessing public transportation accessibility and land use efficiency based on the MGWR model. The method includes, but is not limited to, the following steps:

[0147] Step S501: Obtain POI data within the analysis area and determine the land use efficiency composition based on the POI data. In the first step, the system collects Points of Interest (POI) data for the analysis area (e.g., the area surrounding a subway station in Shanghai). This data typically comes from data sources such as map POIs and Dianping (a Chinese review platform), and contains information about land use types, facility functions, and consumption levels. By analyzing this data, the system determines the land use efficiency composition of the area. Specifically, the land use efficiency composition refers to the quantity and distribution of different types of land use facilities within the area, including commercial facilities, residential facilities, public service facilities, and transportation facilities. For example, POI data for the area surrounding a subway station in Shanghai might include shopping malls, supermarkets, restaurants, residential buildings, parks, schools, and hospitals. These facilities represent different aspects of the land use efficiency of the area. The system obtains the land use efficiency composition of the area by integrating and analyzing this POI data.

[0148] Step S502: Based on the land use efficiency composition, determine the regional characteristic variables within the analysis area. In step S502, the system extracts regional characteristic variables based on the land use efficiency composition data obtained in the previous step. These characteristic variables reflect the land use characteristics of each area, such as the density of commercial facilities, the distribution of transportation facilities, and the density of residential areas. Through the calculation and normalization of the regional characteristic variables, the system can obtain the overall characteristics of each area in terms of land use efficiency, which facilitates subsequent evaluation and analysis. For example, if the analysis area is the area surrounding a subway station in Shanghai, the system will count the number of various facilities in the area and generate characteristic variables, such as the number of commercial facilities, the number of residential areas, and the number of transportation facilities. These characteristic variables will be used as input data for further construction of the subsequent evaluation model.

[0149] Step S503: Generate a public transportation accessibility and land use efficiency evaluation model based on the aforementioned regional characteristic variables. In step S503, the system, based on the aforementioned regional characteristic variables and combined with public transportation accessibility data (e.g., service range of subway stations, accessibility of bus stops, etc.), generates an evaluation model for public transportation accessibility and land use efficiency through machine learning or regression models. This model can quantitatively analyze the land use efficiency of each region and provide strong support for planning and decision-making. For example, the system combines public transportation network data and land use efficiency components of Shanghai and uses the MGWR model to generate an evaluation model. Through the model, the system can predict the impact of different types of land use facilities (such as commercial, residential, and transportation facilities) on transportation accessibility, thereby evaluating the land use efficiency of the region.

[0150] Step S504: Test the generated public transport accessibility and land use efficiency evaluation model to obtain its accuracy. After model generation, the system will test the evaluation model using a test dataset. By inputting the regional feature variables from the test dataset into the model, the system calculates the prediction results and compares them with the actual results to obtain the model's accuracy evaluation results. Specifically, the evaluation metrics include accuracy, precision, and recall. For example, suppose that in the test dataset, out of 200 regional feature variables, 165 are labeled as efficient regions and 35 are labeled as inefficient regions. Inputting these data into the model for classification, suppose the classification results are: 105 data points labeled as efficient regions are correctly classified as efficient regions, 60 data points labeled as efficient regions are incorrectly classified as inefficient regions, 23 data points labeled as inefficient regions are correctly classified as inefficient regions, and 12 data points labeled as inefficient regions are incorrectly classified as efficient regions. Using this data, the system can calculate accuracy, precision, and recall to evaluate the model's performance.

[0151] Step S505: Determine if the accuracy rate is greater than the preset value. If it is greater than the preset value, proceed to S506; if it is less than or equal to the preset value, proceed to S507. In step S505, the system determines whether the model's accuracy rate exceeds the preset value based on the test results of step S504. If the test result is greater than the preset value, the system proceeds to S506, that is, using the model to conduct a detailed evaluation of the land use efficiency of the analysis area; if the test result does not meet expectations, proceed to step S507 to further optimize the model.

[0152] Step S506: Evaluate the land use efficiency of the analysis area based on the public transportation accessibility and land use efficiency evaluation model. If the model's accuracy reaches the preset standard, the system proceeds to S506. At this point, the system will conduct a detailed land use efficiency assessment of each unit area within the analysis area.

[0153] Step S507: Add feature variables to each unit area, and obtain the number and status of feature variables in each unit area within the added analysis area. If the model test results in step S505 do not meet the preset standards, the system will optimize the model by adding new feature variables. Regional socioeconomic data (such as regional GDP, housing prices, population distribution, etc.) can be introduced, and these newly added feature variables can be processed. These new variables will provide more information to the model, helping to improve its accuracy. For example, in a certain area of ​​Shanghai, in addition to using POI data, the system can also introduce the region's economic indicators, residents' income levels, etc., as new feature variables for analysis. Through these additional variables, the system will recalculate the feature variables of each unit area and output more accurate land use efficiency assessment results based on the new feature variables.

[0154] Figure 6 This is a schematic diagram of the structure of a land use efficiency assessment system 600 for transportation hub areas provided in an embodiment of this application. The system includes an acquisition unit 601 and a processing unit 602, wherein the detailed description of each unit is as follows:

[0155] Acquisition Unit 601: Used to acquire POI data within the analysis area and determine the land use efficiency composition based on the POI data. Specifically, Acquisition Unit 601 can acquire Points of Interest (POI) data related to the analysis area from various preset data platforms. POI data may include, but is not limited to, map POI data, commercial review data, public service facility data, etc. By collecting this data, Acquisition Unit 601 can determine the land use efficiency composition of the analysis area, covering the distribution and quantity of different types of facilities such as commercial, residential, transportation, and public services.

[0156] Processing unit 602 is used to determine regional characteristic variables within the analysis area based on the land use efficiency composition; generate a land use efficiency evaluation model based on the regional characteristic variables; and evaluate the land use efficiency of the analysis area based on the evaluation model. Processing unit 602 first extracts category information from the acquired POI data. This category information mainly includes function and consumption level, such as functional categories (e.g., commercial, transportation, residential, cultural, etc.) and consumption levels (e.g., low-end, mid-range, high-end). Based on this data, processing unit 602 can further analyze the spatial distribution of each facility category and its contribution to land use efficiency. After obtaining the category information, processing unit 602 determines the quantity and distribution of various facilities within the area based on different functions and consumption levels. The land use efficiency composition reflects the spatial configuration of different types of facilities within the analysis area and provides a data foundation for subsequent analysis. Based on the land use efficiency composition, processing unit 602 further calculates regional characteristic variables for each unit area. These characteristic variables include, but are not limited to, commercial facility density, transportation facility accessibility, and public service facility coverage. These regional characteristic variables will serve as input data for land use efficiency assessment, helping the system to quantitatively evaluate the land use efficiency of each region. Based on the MGWR model, processing unit 602 combines the regional characteristic variables to generate an evaluation model for assessing the land use efficiency of each region. This model can predict and evaluate the land use efficiency level of a region based on the input characteristic variables, providing support for urban planning and decision-making.

[0157] It should be noted that the implementation and beneficial effects of each unit can be found by referring to [the relevant documentation / reference]. Figure 4 and Figure 5 The corresponding description of the method embodiments shown.

[0158] Figure 7 This is a schematic diagram of a land use efficiency assessment device 700 for transportation hub areas provided in an embodiment of this application. The device 700 includes a processor 701, a memory 702, a transceiver 703, and the components connected to each other via a bus 704. Details are as follows:

[0159] Memory 702: Memory 702 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), and other storage media. Memory 702 is used to store program code and data for executing the method, ensuring the correct execution of various operations.

[0160] Transceiver 703: Used to receive and transmit data, ensuring that POI data in the analysis area can be acquired from external sources and communicate with the processing unit. Transceiver 703 can connect to a preset data platform to obtain the required POI data and other necessary information.

[0161] Processor 701: Processor 701 can be one or more central processing units (CPUs). During execution, processor 701 executes tasks such as acquiring POI data, extracting feature variables, and generating evaluation models according to the program code in memory 702. Processor 701 can also process data acquired through transceiver 703 for analysis and calculation.

[0162] Optional: Cooperative operation of memory 702 and processor 701: Memory 702 stores program code. When the program code runs on processor 701, processor 701 performs the following operations:

[0163] Acquire POI data: Use transceiver 703 to acquire POI data within the analysis area and determine the composition of land use efficiency.

[0164] Extracting feature variables: Based on the land use efficiency composition, processor 701 calculates and generates regional feature variables.

[0165] Generate evaluation model: Based on regional characteristic variables, the processor 701 combines machine learning methods to generate a land use efficiency evaluation model.

[0166] Assessing land use efficiency: Input regional characteristic variables into the generated model to obtain the corresponding land use efficiency score, and conduct the corresponding assessment.

[0167] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating land use efficiency in transportation hub areas, characterized in that, Includes the following steps: Acquire and preprocess point-of-interest data and transportation station areas within the analysis area, and then construct multi-source data. Land use layout features are extracted from empty datasets, and these features are used to calculate functional density, spatial mixing, and vitality index. Based on the layout characteristics, a multimodal transportation network including walking, cycling, public transportation and rail transit is constructed, and regional accessibility indicators are calculated. A land-based coupling simulation model for transportation is established based on regional accessibility indicators, using changes in transportation accessibility to drive the dynamic evolution of land use and economic variables. Causal inference and model calibration are performed based on historical traffic intervention events with dynamic evolution to ensure that simulation results are consistent with actual trends. A multi-objective optimization algorithm is used to generate traffic and land use configuration schemes that meet different planning objectives; The assessment results are visualized and used for decision-making, generating an assessment report that includes accessibility heatmaps and land use recommendations.

2. The method for evaluating land use efficiency in transportation hub areas according to claim 1, characterized in that: The acquisition of point-of-interest (POI) data within the analysis area includes selecting POI data from a preset data platform within the analysis area and analyzing land use types and spatial distribution based on the POI data; The multi-source data includes geospatial data, traffic operation data, and socioeconomic data, forming a standardized multidimensional spatiotemporal dataset. The multi-source data further includes static geographic data, dynamic operation data, and socioeconomic data. The static geographic data includes points of interest, current land use status, and road and rail networks. The dynamic operation data includes mobile signaling, public transport and rail passenger flow, and shared travel trajectories. The socioeconomic data includes population density, employment density, housing prices, and income levels.

3. The method for evaluating land use efficiency in transportation hub areas according to claim 1, characterized in that: The land use layout features include extracting category information from the POI data, further including category, function, and service level; and determining the land use type and its corresponding accessibility service range based on the category information.

4. The method for evaluating land use efficiency in transportation hub areas according to claim 1, characterized in that: The land use layout characteristics include: Spatial density calculation based on POI data; The functional mixing index is based on Shannon entropy and its value ranges from 0 to 1. The vitality index is combined with POI density and pedestrian flow intensity, and spatial units of different functional types are identified by DBSCAN or K-Means clustering algorithms; The method of generating a composite network accessibility model based on land use layout characteristics includes: combining the distribution of transportation stations, accessibility indicators, land use density, etc. within the analysis area to construct a comprehensive multimodal transportation network model.

5. The method for evaluating land use efficiency in transportation hub areas according to claim 1, characterized in that: The generated land use optimization scheme includes a multi-objective optimization model, including the maximum coverage site selection problem, combined with the results of composite network accessibility assessment, to optimize land use layout, improve the service level of public transportation facilities and land use efficiency.

6. The method for evaluating land use efficiency in transportation hub areas according to claim 1, characterized in that: During the causal inference and model calibration, the difference-in-differences method or the synthetic control method is used to identify the causal impact of traffic facility intervention on land use efficiency, and the simulation model parameters are calibrated with the causal inference results as constraints. The model parameter estimation adopts Bayesian inference or least squares fitting. The evaluation of land use efficiency based on the composite network accessibility model includes: comparing the evaluation results output by the composite network accessibility model with the land use demand in the region to determine the suitability of the current land use and the coverage of public transportation facilities.

7. A land use efficiency assessment device for transportation hub areas, applied to a land use efficiency assessment method for transportation hub areas according to any one of claims 1-6, characterized in that, include: The acquisition unit is used to acquire POI data within the analysis area and determine the land use characteristics of the area based on the POI data. The processing unit is used to construct a composite network accessibility model and preprocess multi-source data based on the land use characteristics and traffic accessibility data. Spatial feature analysis unit, used to extract land use structure features and calculate functional mixing degree and vitality index; The traffic accessibility calculation unit is used to construct a multimodal transportation network and calculate accessibility indicators. Coupled simulation unit, used for the linkage evolution simulation of transportation and land systems; An optimized decision-making unit is used for multi-objective optimization calculations; The evaluation unit is used to assess land use efficiency based on the composite network accessibility model and generate land use optimization schemes.

8. A chip, characterized in that, The chip is a chip in the land use efficiency assessment device for transportation station areas. The chip includes a processor, a memory, and an input / output interface connected to the processor. When the program in the memory is executed, any step of the method is executed.

9. A computer-readable storage medium, characterized in that, Used to store computer programs, which, when run on a computer, cause the computer to perform the method described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when run on a computer, causes the computer to perform the method described in any one of claims 1-6.

Images