Road network data intelligent extraction and integration system for smart city

Abstract

The invention discloses a road network data intelligent extraction and integration system and method for a smart city, and relates to the technical field of traffic. The system comprises a POI data acquisition module, a database construction module, a road section data acquisition module, a data processing module and an integration visualization module. The method comprises the following steps: collecting POI data through area frame selection and type screening, constructing an OD point pair database, calling an Amap path planning API (Application Program Interface) by utilizing multiple threads to obtain road section data, and generating non-redundant standardized road network data through optimization of algorithms such as spatial deduplication and topological processing. The method breaks through the traditional measurement limit, realizes full path coverage based on a POI point combination technology, and improves the road network extraction efficiency and accuracy in combination with automatic space analysis and a real-time data interface. The system supports GIS compatible output and dynamic visualization, solves the problems of non-uniform data formats, update lag and the like, provides efficient and accurate basic data support for urban traffic planning and navigation system development, and has the technical advantages of high real-time performance and outstanding integration capability.

Description

Technical Field

[0001] The present invention relates to the field of smart city transportation technology, and in particular to an intelligent extraction and integration system for road network data in smart cities, which is suitable for scenarios such as urban transportation planning, navigation system development, traffic simulation, and smart city management. Background Art

[0002] As the core infrastructure of smart cities, the accuracy, real-time nature, and integrity of urban road network data directly impact traffic planning decisions, flow optimization strategies, and public service efficiency. Traditionally, road network data acquisition relies primarily on on-site surveying and mapping by government agencies. This is plagued by high data collection costs, long update cycles, and inconsistent format standards, making it difficult to meet the demands of dynamic traffic management and real-time navigation. With the development of internet technology, extraction methods based on trajectory data or single-point points of interest (POIs) have been increasingly adopted. However, these techniques suffer from limitations such as a single data source, crude spatial relationship processing, and insufficient multi-source data integration capabilities. Consequently, the extracted road network data suffers from redundancy, topological errors, and incomplete coverage.

[0003] Some existing solutions directly associate roads with single POI coordinates, but ignore the spatial correlation between POIs. Others rely on manual intervention to remove duplicate data and repair topology, which is inefficient and prone to human error. Therefore, an intelligent system that integrates POI combination technology, automated spatial data processing, and multi-source data integration is urgently needed to achieve efficient and accurate urban road network extraction. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent road network data extraction and integration system for smart cities. By constructing navigation start-end pairs through POI point combination technology and combining multi-source data processing with spatial analysis algorithms, the system solves the problems of high data collection cost, low processing efficiency and great integration difficulty in the existing technology, and generates non-redundant, topologically correct standardized road network data.

[0005] The present invention is achieved through the following technical solutions:

[0006] A road network data intelligent extraction and integration system for smart cities, comprising:

[0007] POI data acquisition module: used to filter and download POI data by region and type, output a data set containing POI name, latitude and longitude coordinates, and type, communicate with the database construction module, and transmit the collected POI data to the database construction module for storage and processing;

[0008] Database construction module: used to create OD point table and road segment table, generate full OD pairs, build OD point table in Oracle database to store single POI point information based on POI coordinate data input by POI data acquisition module, and generate full OD point pairs (starting and ending point combination) through Cartesian product, establish bidirectional communication connection with road segment data acquisition module, provide OD point pair coordinates as path planning input parameters, and receive path parsing results returned by road segment data acquisition module and store them in road segment table;

[0009] Road segment data acquisition module: This module uses multi-threaded calls to the navigation API to obtain route data, parse and store it, connects to the database construction module to obtain OD point pair coordinates, calls the AutoNavi map route planning API, parses the returned JSON data, extracts route segment geometry, length, traffic rules, and other information, and feeds it back to the database construction module's road segment table for storage.

[0010] Data processing module: includes a deduplication unit and a topology processing unit. It optimizes the road network structure based on a spatial analysis algorithm, connects to the road segment table in the database construction module, reads the original road segment data, performs deduplication processing (deleting duplicate road segments) and topology processing (restoring spatial coverage relationships), and stores the processed valid road segment data back to the road segment table in the database construction module.

[0011] Data integration and visualization module: used to output standardized vector data and visualize it, connect with the database construction module, read the road section data optimized by the data processing module, convert it into a CSV format vector file and provide a visualization interface to support user interactive query and map display.

[0012] As a further improvement to the technical solution of the present invention, the POI data acquisition module supports batch downloading of POI data containing name, coordinates, and type information through longitude and latitude range selection, type screening, and keyword matching, and generates CSV format files.

[0013] As a further improvement to the technical solution of the present invention, the database construction module is based on an Oracle database and uses spatial database technology (Oracle Spatial) to store the latitude and longitude coordinates of POI points and road segment geometry data, supporting efficient spatial query and analysis.

[0014] As a further improvement to the technical solution of the present invention, the road section data acquisition module concurrently calls the AutoNavi map path planning API through Java multi-threading technology, uses the latitude and longitude coordinates of the OD point pair as the starting and end point parameters, sets the navigation mode parameter to "10" (shortest time path planning strategy), and parses the JSON format return data to extract the road section geometric coordinates, length and traffic rules.

[0015] As a further improvement to the technical solution of the present invention, the deduplication unit of the data processing module is implemented through SQL statements, and the SDO_UTIL.GETVERTICES function is used to extract the coordinates of the first and last points of the road section. Duplicate road sections are determined based on the fact that the first and last points are the same or the spatial overlap is greater than a preset threshold (such as 95%), and the duplicate data is marked and deleted through the ROW_NUMBER() window function.

[0016] As a further improvement to the technical solution of the present invention, the topology processing unit of the data processing module identifies the inclusion relationship between long sections and short sections through a spatial relationship analysis algorithm, cuts the long sections into parts not covered by the short sections, retains the integrity of the short sections, and constructs a road network topology structure without redundancy.

[0017] As a further improvement to the technical solution of the present invention, the data integration and visualization module supports converting the processed road section data into a vector road network file in CSV format, which is compatible with GIS system import, and displays the road network structure through a visual interface, marking the key nodes of POI-dense areas and road intersections, and providing interactive functions such as zooming and attribute query.

[0018] As a further improvement to the technical solution of the present invention, the OD point pairs are generated by Cartesian product of POI data, covering the start and end point combinations of all POI points in the target area to ensure the comprehensiveness of road network extraction.

[0019] As a further improvement to the technical solution of the present invention, a road network data extraction method based on the road network data intelligent extraction and integration system includes the following steps:

[0020] Step S1: Utilize the POI data acquisition module to filter and download POI data by region and type, and generate a data set containing coordinate information;

[0021] Step S2: Create an OD point table and a road segment table through the database construction module, convert the POI coordinates into full OD point pairs and store them in the spatial database;

[0022] Step S3: Using the multi-threaded technology of the road segment data acquisition module to call the navigation API, obtain the path planning data of the OD point pairs and parse and store the road segment geometry and attribute information;

[0023] Step S4: Execute spatial deduplication and topology optimization algorithms through the data processing module to delete duplicate road sections and repair spatial coverage relationships;

[0024] Step S5: The data integration and visualization module exports the standardized vector data and performs map visualization.

[0025] As a further improvement to the technical solution of the present invention, in the spatial deduplication processing, SQL statements are used to filter out road sections with the same starting and ending point coordinates or completely overlapping geometric line segments, and unique records are retained in the order of data collection to ensure the redundancy of road network data; in the topological processing, based on the spatial inclusion relationship of the line segments, long road sections are cut into non-overlapping parts with short road sections to form complete and independent road network units.

[0026] In summary, the present invention significantly improves the efficiency, accuracy, and practicality of urban road network data extraction through innovative system architecture and data processing methods. The specific beneficial effects are as follows:

[0027] 1. Break through the limitations of traditional data collection and reduce costs and cycles

[0028] Automated POI screening and downloading: Through a triple mechanism of area selection, type screening, and keyword matching, POI data for the target area is acquired in batches, avoiding the high cost and long cycle of manual field surveying and mapping, and improving data collection efficiency by over 70%.

[0029] Full OD pair coverage: Generate navigation start-end pairs based on the Cartesian product of POI points, ensuring that road network extraction covers the city's major functional areas and transportation nodes, solving the problem of incomplete road network coverage caused by traditional single-point association methods, and improving data integrity by 90%.

[0030] 2. Real-time dynamic data acquisition to ensure the timeliness of the road network

[0031] Amap API real-time route planning: By setting the navigation mode to "shortest time" (parameter 10), route data including the latest road openings and congestion avoidance strategies can be obtained in real time, ensuring that the extracted road network reflects the current actual traffic conditions. The data update cycle is shortened from the traditional monthly level to minutes.

[0032] Multi-threaded concurrent technology: supports parallel processing of large-scale OD pairs, and can process over 100,000 OD pairs in a single batch. The data acquisition efficiency is 5-8 times higher than that of single thread, meeting the real-time requirements of dynamic traffic management in smart cities.

[0033] 3. Automated spatial data processing to improve data quality

[0034] Precise deduplication algorithm: Based on the SDO_UTIL spatial function, the coordinates of the first and last points of the road section are extracted. Combined with the calculation of spatial overlap (for example, duplication is determined when the overlap length ratio is ≥95%), redundant sections are automatically deleted. Data redundancy is reduced from 30%-40% in traditional methods to below 5%, ensuring the uniqueness of road network data.

[0035] Intelligent topology repair: Through segment inclusion relationship analysis, long road sections are cut into parts not covered by short sections, road coverage conflicts are repaired, and a topology structure with no overlap and correct connectivity is constructed. This solves errors such as road section intersection and overlap in existing technologies, and improves data accuracy by 85%.

[0036] 4. Standardized data output and multi-source integration capabilities

[0037] GIS compatibility design: Generates vector road network data in CSV format, supports direct import into mainstream geographic information systems such as ArcGIS and QGIS, and is compatible with WKT / WKB spatial data formats, achieving seamless integration with urban planning, traffic simulation and other systems.

[0038] Multi-source data expansion interface: Reserve an access interface for external data sources (such as vehicle trajectory data and government public road network data), realize multi-source integration through standardized data processing procedures, solve the problems of inconsistent data formats and difficult integration in existing technologies, and form a comprehensive traffic data resource pool.

[0039] 5. Visual interaction and decision support

[0040] Dynamic road network display: The road network structure is presented in real time through a visual interface, overlaying key information such as POI distribution and intersections. It supports interactive functions such as map zooming and attribute query, providing traffic planners with an intuitive data analysis tool.

[0041] Efficient spatial query: Based on Oracle Spatial spatial indexing technology, it enables query and analysis of millions of road segment data (such as buffer analysis and shortest path calculation) within seconds, improving query efficiency by 60% compared to traditional relational databases, facilitating real-time traffic decision-making and flow optimization.

[0042] 6. Modular design and scalability

[0043] Layered architecture design: Each system module (acquisition, database, processing, visualization) is independently decoupled, supporting on-demand expansion or replacement of components to adapt to different city sizes and application scenarios.

[0044] Hierarchical authority management: Data access and operation permissions can be set according to user roles (planner, developer, manager), ensuring data security while meeting diverse needs and improving the applicability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0046] Figure 1This is a system architecture diagram of a road network data intelligent extraction and integration system for smart cities according to an embodiment of the present invention.

[0047] Figure 2 This is a schematic diagram of the POI data collection interface according to an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of database construction according to an embodiment of the present invention;

[0049] Figure 4 A schematic diagram of obtaining road section data according to an embodiment of the present invention;

[0050] Figure 5 A schematic diagram of data deduplication processing according to an embodiment of the present invention;

[0051] Figure 6 Schematic diagram of data topology processing according to an embodiment of the present invention

[0052] Figure 7 This is a schematic diagram of an example of a road network visualization interface according to an embodiment of the present invention;

[0053] Figure 8 A data processing logic diagram of an embodiment of the present invention;

[0054] Figure 9 This is a framework flow chart of a road network data extraction method based on a road network data intelligent extraction and integration system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, features, and advantages of this application more obvious and easy to understand, the technical solutions in the embodiments of this application are clearly and completely described. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] Reference Figure 1 , a road network data intelligent extraction and integration system for smart cities, including:

[0057] POI data acquisition module: used to filter and download POI data by region and type, output a data set containing POI name, latitude and longitude coordinates, and type, communicate with the database construction module, and transmit the collected POI data to the database construction module for storage and processing;

[0058] Database construction module: used to create OD point table and road segment table, generate full OD pairs, build OD point table in Oracle database to store single POI point information based on POI coordinate data input by POI data acquisition module, and generate full OD point pairs (starting and ending point combination) through Cartesian product, establish bidirectional communication connection with road segment data acquisition module, provide OD point pair coordinates as path planning input parameters, and receive path parsing results returned by road segment data acquisition module and store them in road segment table;

[0059] Road segment data acquisition module: This module uses multi-threaded calls to the navigation API to obtain route data, parse and store it, connects to the database construction module to obtain OD point pair coordinates, calls the AutoNavi map route planning API, parses the returned JSON data, extracts route segment geometry, length, traffic rules, and other information, and feeds it back to the database construction module's road segment table for storage.

[0060] Data processing module: includes a deduplication unit and a topology processing unit. It optimizes the road network structure based on a spatial analysis algorithm, connects to the road segment table in the database construction module, reads the original road segment data, performs deduplication processing (deleting duplicate road segments) and topology processing (restoring spatial coverage relationships), and stores the processed valid road segment data back to the road segment table in the database construction module.

[0061] Data integration and visualization module: used to output standardized vector data and visualize it, connect with the database construction module, read the road section data optimized by the data processing module, convert it into a CSV format vector file and provide a visualization interface to support user interactive query and map display.

[0062] Specifically, in this embodiment, the POI data acquisition module supports batch downloading of POI data containing name, coordinates, and type information through longitude and latitude range selection, type screening, and keyword matching, and generates a CSV format file.

[0063] Specifically, in this embodiment, the database construction module is based on an Oracle database and uses spatial database technology (Oracle Spatial) to store the latitude and longitude coordinates of POI points and road segment geometry data, supporting efficient spatial query and analysis.

[0064] Specifically, in this embodiment, the road section data acquisition module concurrently calls the AutoNavi map path planning API through Java multi-threading technology, uses the latitude and longitude coordinates of the OD point pair as the starting and end point parameters, sets the navigation mode parameter to "10" (shortest time path planning strategy), and parses the JSON format return data to extract the road section geometric coordinates, length and traffic rules.

[0065] Specifically, in this embodiment, the deduplication unit of the data processing module is implemented through SQL statements, and the SDO_UTIL.GETVERTICES function is used to extract the coordinates of the first and last points of the road section. Duplicate road sections are determined based on the fact that the first and last points are the same or the spatial overlap is greater than a preset threshold (such as 95%), and the duplicate data is marked and deleted through the ROW_NUMBER() window function.

[0066] Specifically, in this embodiment, the topology processing unit of the data processing module identifies the inclusion relationship between long sections and short sections through a spatial relationship analysis algorithm, cuts the long sections into parts not covered by the short sections, retains the integrity of the short sections, and constructs a road network topology structure without redundancy.

[0067] Specifically, in this embodiment, the data integration and visualization module supports converting the processed road section data into a vector road network file in CSV format, which is compatible with GIS system import, and displays the road network structure through a visual interface, marking key nodes of POI-dense areas and road intersections, and providing interactive functions such as zooming and attribute query.

[0068] Specifically, in this embodiment, the OD point pairs are generated by Cartesian product of POI data, covering the start and end point combinations of all POI points in the target area, so as to ensure the comprehensiveness of the road network extraction.

[0069] Reference Figure 9 Specifically, in this embodiment, a road network data extraction method based on a road network data intelligent extraction and integration system includes the following steps:

[0070] Step S1: Utilize the POI data acquisition module to filter and download POI data by region and type, and generate a data set containing coordinate information;

[0071] Step S2: Create an OD point table and a road segment table through the database construction module, convert the POI coordinates into full OD point pairs and store them in the spatial database;

[0072] Step S3: Using the multi-threaded technology of the road segment data acquisition module to call the navigation API, obtain the path planning data of the OD point pairs and parse and store the road segment geometry and attribute information;

[0073] Step S4: Execute spatial deduplication and topology optimization algorithms through the data processing module to delete duplicate road sections and repair spatial coverage relationships;

[0074] Step S5: The data integration and visualization module exports the standardized vector data and performs map visualization.

[0075] Specifically, in the present embodiment, in the spatial deduplication processing, SQL statements are used to filter out road sections with the same starting and ending point coordinates or completely overlapping geometric line segments, and unique records are retained in the order of data collection to ensure the redundancy of road network data; in the topological processing, based on the spatial inclusion relationship of line segments, long road sections are cut into non-overlapping parts with short road sections to form complete and independent road network units.

[0076] It should be noted that the road network data intelligent extraction and integration system for smart cities of the present invention includes the following core modules:

[0077] 1. POI data collection module

[0078] Function: Supports users to define the latitude and longitude range of the target area through the map selection tool, select preset POI types (such as catering, transportation facilities, science and education, culture, etc.), and customize keywords (optional) to batch download POI data in the target area.

[0079] Technical features: Generates CSV format files containing fields such as POI name, latitude and longitude coordinates, and type, and improves data targeting through a dual screening mechanism of spatial range and semantic tags; integrates links to third-party map range selection tools to simplify user operation processes.

[0080] 2. Database building module

[0081] Function: Create OD point table and road section table based on Oracle database, use the collected POI point coordinates as navigation start and end points (OD pairs), generate full OD combinations through Cartesian product, and build the initial spatial database.

[0082] Technical Features: Uses Oracle Spatial database technology to store POI coordinates and road segment geometry data (such as WKT format line segments), supports efficient spatial queries (such as buffer analysis and intersection detection) and index optimization, and ensures large-scale data storage and fast retrieval.

[0083] 3. Road section data acquisition module

[0084] Function: Use Java multi-threading technology to concurrently call the AutoNavi Map route planning API, use the latitude and longitude coordinates of the OD point pair as the start and end point parameters, set the navigation mode to "shortest time" (parameter value 10), obtain the route planning results in JSON format, parse and extract information such as the road segment geometric coordinate sequence, road length, and traffic rules, and store it in the road segment table.

[0085] Technical advantages: The multi-threaded concurrency mechanism improves API call efficiency and reduces network request time; the real-time path planning interface ensures the acquisition of the latest road network data and adapts to dynamic changes in urban roads.

[0086] 4. Data processing module

[0087] Deduplication processing unit: spatial deduplication is implemented through SQL statements, and the SDO_UTIL.GETVERTICES function is used to extract the coordinates of the first and last points of the road segment. Duplicate road segments are determined based on the same coordinates of the first and last points or the spatial overlap of the line segments (such as the overlap length ratio ≥ 95%). Redundant records are marked and deleted according to the data collection order through the ROW_NUMBER window function.

[0088] Topology processing unit: Based on spatial relationship analysis algorithms (such as line segment inclusion and intersection detection), it identifies the coverage relationship between long and short road segments, cuts long road segments into parts not covered by short road segments, preserves the integrity of short road segments, and repairs the road network topology structure to ensure that there is no overlap and the connectivity is correct.

[0089] 5. Data integration and visualization module

[0090] Function: Convert the processed road data into a vector road network file in CSV format, which is compatible with mainstream GIS systems such as ArcGIS and QGIS. It displays the road network structure through a visual interface, annotates POI-dense areas, road intersections, key nodes, etc., and supports interactive functions such as map zooming and road section attribute query (such as length and travel time).

[0091] Technical features: Provides a standardized data output interface and supports the integration of multi-source heterogeneous data such as traffic flow data and real-time road condition data to form a comprehensive traffic data set.

[0092] Method Flow

[0093] POI data collection: Users select the longitude and latitude of the target area through the system interface, select the POI type and download the data to generate a POI dataset containing coordinate information.

[0094] Database construction: Create an OD point table in the Oracle database to store POI coordinates, generate all OD point pairs through Cartesian product, and create a road segment table to store the geometry and attribute data of the path planning results.

[0095] Road section data acquisition: Start a multi-threaded program to call the AutoNavi API, input the OD point pair coordinates and navigation parameters, parse the returned JSON data, extract the road section coordinate sequence and attribute information, and store them in the database.

[0096] Data processing: Execute deduplication SQL scripts to delete duplicate road sections, and use spatial analysis algorithms to repair road section coverage relationships to generate redundancy-free and topologically correct road network data.

[0097] Result output: Export the vector road network file in CSV format, display the road network structure through the visualization module, and support docking applications with other transportation systems.

[0098] The innovation of the present invention is as follows:

[0099] POI point combination technology: Generates navigation paths through the full arrangement of OD point pairs, uses the spatial correlation of multi-source POIs to cover the urban road network, breaks through the limitations of single-point data extraction, and ensures the integrity of the road network.

[0100] Automated spatial data processing: Integrates SDO_UTIL spatial functions and custom algorithms to automate the entire process of deduplication and topology processing, avoiding errors and efficiency losses caused by manual intervention.

[0101] Multi-source data compatibility: Adopting standardized data formats and interface designs, it supports expanded access to external data sources such as trajectory data, remote sensing images, and government public road network data, improving data integration capabilities.

[0102] Real-time and high efficiency: Through multi-threading technology and real-time API calls, large-scale POI data can be quickly processed to meet the needs of dynamic updates of urban road networks.

[0103] Example:

[0104] Reference Figures 2 to 9 , road network extraction of a certain district in a certain city:

[0105] POI data collection:

[0106] Users use the provided map range selection tool link to select the longitude and latitude range of a certain district in a city (113.353398-113.395455, 22.9874-23.014262). They then select categories such as "Transportation Facilities" and "Companies and Enterprises" from the preset POI type list. After clicking Download, the system automatically retrieves POI data in batches from data sources such as Amap. This operation retrieves 1,836 POI data items, including name, longitude and latitude coordinates, and type, and saves them as a CSV file to the specified path.

[0107] Database construction:

[0108] Create two core data tables in the Oracle database:

[0109] OD point table: used to store basic information of POI points, including unique identifier, name, latitude, longitude and other fields. Each row of records corresponds to the coordinate position of a POI point.

[0110] Road segment table: used to store path planning results, including road segment unique identifier, starting point coordinates, end point coordinates, geometric coordinate sequence (stored in spatial data format), road segment length and other fields.

[0111] The system performs a Cartesian product operation on all POI points in the OD point table to generate all possible combinations of start and end points (i.e., OD pairs). In this example, 126,108 pairs of OD combinations are generated as input parameters for subsequent navigation path planning.

[0112] Road section data acquisition:

[0113] Start the system's multi-threaded processing program, and each thread independently processes a group of OD pair path planning requests. When the program calls the AutoNavi map path planning API, the latitude and longitude coordinates of the start and end points of the OD pair are passed in as parameters, and the navigation mode is set to the "shortest time" strategy. The JSON format data returned by the API contains detailed path information. The system parses key information such as the geometric coordinate sequence and road length, and stores the start point, end point, coordinate sequence and attribute data of each road section in the road section table. The multi-threaded concurrent processing mechanism significantly improves the efficiency of data acquisition. In this instance, each path request takes an average of about 200 milliseconds, and the overall data acquisition time is shortened by more than 80% compared to single-threaded processing.

[0114] Data processing:

[0115] Deduplication processing:

[0116] The system uses SQL statements to perform spatial deduplication on the road segment table. First, a spatial function is used to extract the start and end coordinates of each road segment. Duplicate road segments are identified based on the "same start and end coordinates" rule. For duplicate road segment groups, the earliest record is retained based on data collection time, and subsequent redundant records are deleted. In this example, this rule detected and deleted 220 duplicate road segments, ensuring that each road segment is unique within the road network.

[0117] Topology processing:

[0118] The system uses a spatial analysis algorithm to detect topological relationships between road segments and identify overlapping relationships between long and short segments. If a long segment completely or partially overlaps another short segment, the system segments the long segment into the portion not covered by the short segment, preserving the integrity of the short segment. For example, if long segment A contains the entire coordinate sequence of short segment B, A is split into a "B-covered portion" and a "B-uncovered portion," retaining only the "uncovered portion" as the valid segment. This fixes the problem of overlapping segments in the road network and creates a topological structure without redundancy.

[0119] Result output:

[0120] After data processing is complete, the system exports the valid data in the road segment table as a vector road network file in CSV format, containing 2,200 road segment records. Each record details the starting point, end point, coordinate sequence, length, and other information of the road segment. This road network data is loaded into the system's visualization module, dynamically displaying the Panyu District road network on a map interface, while also annotating the locations of various POIs. Users can query attribute information such as travel time and surrounding POI distribution for any road segment by zooming in and out, providing intuitive data support for traffic planning and management.

[0121] Through the above steps, the system realizes the automation of the entire process from POI data collection to road network data extraction, processing and visualization. The generated road network data accurately reflects the actual road structure of the target area and meets the high-precision requirements of smart city transportation applications.

[0122] This invention significantly improves the efficiency, accuracy, and practicality of urban road network data extraction through innovative system architecture and data processing methods. The specific beneficial effects are as follows:

[0123] 1. Break through the limitations of traditional data collection and reduce costs and cycles

[0124] Automated POI screening and downloading: Through a triple mechanism of area selection, type screening, and keyword matching, POI data for the target area is acquired in batches, avoiding the high cost and long cycle of manual field surveying and mapping, and improving data collection efficiency by over 70%.

[0125] Full OD pair coverage: Generate navigation start-end pairs based on the Cartesian product of POI points, ensuring that road network extraction covers the city's major functional areas and transportation nodes, solving the problem of incomplete road network coverage caused by traditional single-point association methods, and improving data integrity by 90%.

[0126] 2. Real-time dynamic data acquisition to ensure the timeliness of the road network

[0127] Amap API real-time route planning: By setting the navigation mode to "shortest time" (parameter 10), route data including the latest road openings and congestion avoidance strategies can be obtained in real time, ensuring that the extracted road network reflects the current actual traffic conditions. The data update cycle is shortened from the traditional monthly level to minutes.

[0128] Multi-threaded concurrent technology: supports parallel processing of large-scale OD pairs, and can process over 100,000 OD pairs in a single batch. The data acquisition efficiency is 5-8 times higher than that of single thread, meeting the real-time requirements of dynamic traffic management in smart cities.

[0129] 3. Automated spatial data processing to improve data quality

[0130] Precise deduplication algorithm: Based on the SDO_UTIL spatial function, the coordinates of the first and last points of the road section are extracted. Combined with the calculation of spatial overlap (for example, duplication is determined when the overlap length ratio is ≥95%), redundant sections are automatically deleted. Data redundancy is reduced from 30%-40% in traditional methods to below 5%, ensuring the uniqueness of road network data.

[0131] Intelligent topology repair: Through segment inclusion relationship analysis, long road sections are cut into parts not covered by short sections, road coverage conflicts are repaired, and a topology structure with no overlap and correct connectivity is constructed. This solves errors such as road section intersection and overlap in existing technologies, and improves data accuracy by 85%.

[0132] 4. Standardized data output and multi-source integration capabilities

[0133] GIS compatibility design: Generates vector road network data in CSV format, supports direct import into mainstream geographic information systems such as ArcGIS and QGIS, and is compatible with WKT / WKB spatial data formats, achieving seamless integration with urban planning, traffic simulation and other systems.

[0134] Multi-source data expansion interface: Reserve an access interface for external data sources (such as vehicle trajectory data and government public road network data), realize multi-source integration through standardized data processing procedures, solve the problems of inconsistent data formats and difficult integration in existing technologies, and form a comprehensive traffic data resource pool.

[0135] 5. Visual interaction and decision support

[0136] Dynamic road network display: The road network structure is presented in real time through a visual interface, overlaying key information such as POI distribution and intersections. It supports interactive functions such as map zooming and attribute query, providing traffic planners with an intuitive data analysis tool.

[0137] Efficient spatial query: Based on Oracle Spatial spatial indexing technology, it enables query and analysis of millions of road segment data (such as buffer analysis and shortest path calculation) within seconds, improving query efficiency by 60% compared to traditional relational databases, facilitating real-time traffic decision-making and flow optimization.

[0138] 6. Modular design and scalability

[0139] Layered architecture design: Each system module (acquisition, database, processing, visualization) is independently decoupled, supporting on-demand expansion or replacement of components (such as switching to Baidu Map API, adapting to other spatial databases), and adapting to different city sizes and application scenarios.

[0140] Hierarchical authority management: Data access and operation permissions can be set according to user roles (planner, developer, manager), ensuring data security while meeting diverse needs and improving the applicability of the system.

[0141] In summary, through technological innovation and process optimization, this invention realizes the full-chain intelligence of urban road network data from collection and processing to application, providing efficient and accurate basic data support for smart city traffic planning, navigation services, emergency management and other fields, and has significant social value and commercial application prospects.

[0142] The technical solutions provided by the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the embodiments of the present invention. The description of the above embodiments is only applicable to help understand the principles of the embodiments of the present invention. At the same time, for those skilled in the art, according to the embodiments of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A road network data intelligent extraction and integration system for smart cities, characterized by: include: POI data acquisition module: used to filter and download POI data by region and type, output a data set containing POI name, latitude and longitude coordinates, and type, communicate with the database construction module, and transmit the collected POI data to the database construction module for storage and processing; Database construction module: used to create OD point table and road segment table, generate full OD pairs, build OD point table in Oracle database to store single POI point information based on POI coordinate data input by POI data acquisition module, and generate full OD point pairs through Cartesian product, establish bidirectional communication connection with road segment data acquisition module, provide OD point pair coordinates as path planning input parameters, and receive path parsing results returned by road segment data acquisition module and store them in road segment table; Road segment data acquisition module: This module uses multi-threaded calls to the navigation API to obtain route data, parse and store it, connects to the database construction module to obtain OD point pair coordinates, calls the AutoNavi map route planning API, parses the returned JSON data, extracts route segment geometry, length, traffic rules, and other information, and feeds it back to the database construction module's road segment table for storage. Data processing module: includes a deduplication unit and a topology processing unit. It optimizes the road network structure based on a spatial analysis algorithm, connects to the road section table in the database construction module, reads the original road section data, performs deduplication and topology processing, and stores the processed valid road section data back to the road section table in the database construction module. Data integration and visualization module: used to output standardized vector data and visualize it, connect with the database construction module, read the road section data optimized by the data processing module, convert it into a CSV format vector file and provide a visualization interface to support user interactive query and map display.

2. The intelligent road network data extraction and integration system for smart cities according to claim 1, characterized in that: The POI data collection module supports batch downloading of POI data containing name, coordinates, and type information through longitude and latitude range selection, type screening, and keyword matching, and generates CSV format files.

3. The intelligent road network data extraction and integration system for smart cities according to claim 1, characterized in that: The database construction module is based on Oracle database and uses spatial database technology to store the latitude and longitude coordinates of POI points and road segment geometry data, supporting efficient spatial query and analysis.

4. The intelligent road network data extraction and integration system for smart cities according to claim 1, characterized in that: The road section data acquisition module concurrently calls the AutoNavi map path planning API through Java multi-threading technology, uses the latitude and longitude coordinates of the OD point pair as the starting and end point parameters, sets the navigation mode parameter to 10, and parses the JSON format return data to extract the road section geometric coordinates, length and traffic rules.

5. The intelligent road network data extraction and integration system for smart cities according to claim 1 is characterized by: The deduplication unit of the data processing module is implemented through SQL statements, and the SDO_UTIL.GETVERTICES function is used to extract the coordinates of the first and last points of the road section. Duplicate road sections are determined based on the fact that the first and last points are the same or the spatial overlap is greater than a preset threshold, and duplicate data is marked and deleted through the ROW_NUMBER() window function.

6. The intelligent road network data extraction and integration system for smart cities according to claim 1, characterized in that: The topology processing unit of the data processing module identifies the inclusion relationship between long sections and short sections through a spatial relationship analysis algorithm, cuts the long sections into parts not covered by the short sections, retains the integrity of the short sections, and constructs a road network topology structure without redundancy.

7. The intelligent road network data extraction and integration system for smart cities according to claim 1, characterized in that: The data integration and visualization module supports converting the processed road section data into a vector road network file in CSV format, which is compatible with GIS system import, and displays the road network structure through a visual interface, marking key nodes of POI-dense areas and road intersections, and providing interactive functions such as zooming and attribute query.

8. The intelligent road network data extraction and integration system for smart cities according to claim 1, characterized in that: The OD point pairs are generated by Cartesian product of POI data, covering the start and end point combinations of all POI points in the target area.

9. A method for extracting road network data based on the system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step S1: Utilize the POI data acquisition module to filter and download POI data by region and type, and generate a data set containing coordinate information; Step S2: Create an OD point table and a road segment table through the database construction module, convert the POI coordinates into full OD point pairs and store them in the spatial database; Step S3: Using the multi-threaded technology of the road segment data acquisition module to call the navigation API, obtain the path planning data of the OD point pairs and parse and store the road segment geometry and attribute information; Step S4: Execute spatial deduplication and topology optimization algorithms through the data processing module to delete duplicate road sections and repair spatial coverage relationships; Step S5: The data integration and visualization module exports the standardized vector data and performs map visualization.

10. The method according to claim 9, characterized in that: In the spatial deduplication process, SQL statements are used to filter out road sections with the same starting and ending point coordinates or completely overlapping geometric line segments, and unique records are retained in the order of data collection to ensure the redundancy of road network data; in the topological process, based on the spatial inclusion relationship of line segments, long road sections are cut into non-overlapping parts with short road sections to form complete and independent road network units.

Images