A dynamic updating and fusing system and method for map data
By processing and fusing data at the network edge, the real-time performance and multi-source data fusion quality issues of the map data update system are resolved, enabling efficient and real-time map data updates and fusion to meet the needs of scenarios such as autonomous driving.
Patent Information
- Application Number
- CN202610411137.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-31
- Publication Date
- 2026-07-21
Smart Images
Figure CN122432259A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of digital map technology, specifically to a system and method for the dynamic updating and fusion utilization of map data. Background Technology
[0002] With the rapid development of intelligent transportation, autonomous driving, and smart cities, high-precision, real-time updated map data has become a key infrastructure supporting these technologies. Traditional map data mainly relies on professional surveying and mapping institutions or crowdsourcing for collection, acquiring static geographic information through satellite imagery, aerial photography, MMS, and other means, and then generating map products through manual or semi-automated processing. However, the update cycle of traditional map data is relatively long, usually on a monthly or quarterly basis, making it difficult to meet real-time requirements.
[0003] In recent years, with the advancement of technologies such as the Internet of Things (IoT), 5G communication, and edge computing, dynamic map data updating technology has gradually emerged. Especially in the fields of smart cities and autonomous driving, the value of dynamic map data is becoming increasingly prominent. For example, autonomous vehicles need to perceive changes in their surrounding environment in real time, such as temporary construction, traffic accidents, and road closures, information that traditional static maps cannot provide. Therefore, the integration of high-precision maps (HD maps) with real-time dynamic data has become a research hotspot. Simultaneously, the fusion and utilization of multi-source heterogeneous data is also becoming a technological trend. Map data not only comes from professional surveying equipment but may also originate from smartphones, in-vehicle terminals, drones, traffic monitoring cameras, etc. How to efficiently integrate these data with varying degrees of precision and timeliness, while ensuring data consistency and reliability, is a key focus of current research.
[0004] Despite some progress in dynamic map update technology, existing systems still have the following problems: First, there is an architectural flaw that results in insufficient real-time performance. Current systems generally adopt a serial processing flow of "data acquisition - cloud processing - distribution," where data must be processed by a remote server to complete an update. This architectural design itself introduces unavoidable network transmission delays and processing latency. Furthermore, many systems still rely on periodic batch updates rather than true streaming processing, thus failing to achieve truly real-time updates and making it difficult to meet the millisecond-level response requirements of scenarios such as autonomous driving.
[0005] Secondly, there are quality defects in multi-source data fusion. Map data comes from various channels, including professional surveying equipment, smartphones, vehicle terminals, drones, and traffic monitoring cameras. These different sources of data vary significantly in accuracy, and this inconsistency in accuracy can introduce errors during data fusion, affecting the overall quality and reliability of the map data. Furthermore, the collection and update frequencies of data from different sources also differ. Some data sources (such as traffic monitoring cameras) may provide real-time or near-real-time information, while other data sources (such as professional surveying data) may be updated at longer intervals. This difference in timeliness can lead to inconsistencies or outdated information during data fusion. Existing systems lack efficient standardization and fusion mechanisms, which can easily lead to data redundancy or conflicts. Summary of the Invention
[0006] The purpose of this invention is to provide a system and method for dynamic updating and fusion utilization of map data, so as to solve the problems mentioned in the background art.
[0007] To achieve the above objectives, the present invention provides the following technical solution: On one hand, it provides a system for the dynamic updating and fusion utilization of map data, comprising: Data acquisition module: responsible for collecting geographic information data from various data sources in real time or periodically; Data preprocessing module: responsible for preprocessing the collected multi-source heterogeneous data by cleaning, denoising, and format conversion to make it conform to a unified data format and standard; Core processing module: Adopting a streaming processing architecture, it pushes data processing tasks from the cloud to the network edge, enabling real-time data reception, processing, and updating; The data fusion module is responsible for receiving data from the core processing module, using multi-source data fusion algorithms (such as weighted average, Kalman filtering, etc.) to perform weighted fusion based on the characteristics and reliability of different data sources, and generating comprehensive map data updates. The data fusion module integrates a multi-source data fusion algorithm library, performs fusion processing on the input data through algorithms, and outputs the fused result. Conflict detection module: responsible for detecting conflicts and contradictions between different data sources during the data fusion process, and processing them according to preset strategies to ensure data consistency and reliability; Quality assessment module: responsible for establishing data quality assessment indicators and systems, conducting quality assessment and verification of the fused data, and ensuring the overall quality of map data; the quality assessment module receives data from the data fusion module, assesses the data according to preset quality assessment indicators (such as accuracy, completeness, etc.), generates an assessment report, and feeds back the assessment results to the data fusion module for optimization; Storage management module: responsible for storing and managing the merged map data, providing data query, retrieval and update services; the storage management module receives updated data from the core processing module or data fusion module, stores it in a database or file system, and provides data access interfaces for other modules or external systems to call; User Interface: This provides users with a user-friendly interface and interaction methods, facilitating viewing map data, submitting update requests, or performing other operations. The user interface receives user operation requests, converts them into internal system instructions, sends them to the corresponding modules for processing, and displays the processing results to the user. In practice, a web application or mobile application is developed as the user interface, and a front-end / back-end separation architecture is used to achieve user interaction with the system.
[0008] Furthermore, the data acquisition module connects to the data source through API interfaces, data stream subscriptions, and periodic polling to ensure the real-time performance and integrity of the data. Supported data source types include, but are not limited to, professional surveying equipment, smartphones, vehicle terminals, drones, and traffic monitoring cameras. Professional surveying equipment, such as total stations and GPS receivers, provides high-precision geographic information data, but with a low update frequency. Smartphones: Smartphones have built-in GPS modules and sensors that provide users with real-time location information. The accuracy is relatively low, but the amount of data is large and the updates are frequent. Vehicle-mounted terminals: Vehicle-mounted GPS terminals and OBD (On-Board Diagnostics) provide vehicle driving trajectory and status information, which are of great significance for traffic flow analysis and road condition monitoring; Drones: Drones are equipped with high-resolution cameras and sensors that can acquire geographic information data from the air, making them suitable for fields such as terrain mapping and environmental monitoring; Traffic surveillance cameras: capture real-time traffic conditions on the road, such as traffic flow, vehicle speed, and traffic accidents, providing important information for updating dynamic map data.
[0009] Furthermore, the data acquisition module's acquisition logic is as follows: it continuously monitors each data source, and once new data arrives or the update conditions are met, it immediately triggers the data acquisition process and transmits the data to the data preprocessing module. For data sources that support API interfaces, the data acquisition module connects to the data source via the API and allows the module to directly call the services provided by the data source to obtain the latest geographic information data; API interfaces typically have standardized data formats and protocols, which facilitate data parsing and processing; For data sources that support data stream subscription, the data acquisition module subscribes to specific data streams, and once new data is generated by the data source, it is automatically pushed to the data acquisition module. For data sources that do not support API interfaces or data stream subscriptions, the data acquisition module uses a periodic polling method to obtain data. That is, the module sends requests to the data source at preset time intervals to obtain the latest geographic information data.
[0010] Furthermore, the data preprocessing module receives data from the data acquisition module, processes the data according to preset data cleaning rules and format conversion templates, and sends the processed data to the core processing module. The process is as follows: Data reception: Receives raw geographic information data from the data acquisition module; Data cleaning: removing noise, errors, and redundant information from data, specifically including: 1) Outlier detection and handling: Use methods such as Z-score and IQR (interquartile range) to detect outliers, and correct or delete them according to the actual situation; 2) Handling missing values: For missing values in the data, interpolation methods (such as linear interpolation, polynomial interpolation), mean / median imputation, or model-based prediction imputation are used to handle them; 3) Duplicate value handling: Detect and delete duplicate records in the data to ensure data uniqueness; Data denoising: eliminating random and systematic errors in data, specifically including: 1) Smoothing filters: such as moving average filters and median filters, are used to eliminate short-term fluctuations and noise in data; 2) Trend analysis: Identify and remove long-term trends or periodic changes in the data through methods such as time series analysis to highlight the essential characteristics of the data; Format conversion: Converting data from different data sources into a unified data format, specifically including: 1) Data parsing: Write a parser based on the specific format of the data source (such as JSON, XML, CSV, binary format, etc.) to parse the raw data into structured data; 2) Data mapping: Establish mapping relationships between different data formats, mapping the parsed data to a unified data model or format; 3) Data standardization: Standardize the data, such as by unifying the coordinate system, timestamp format, and units, to ensure data consistency and comparability; Data transmission: The cleaned, denoised, and format-converted data will be sent to the core processing module, and data verification and checks must be performed before transmission.
[0011] Furthermore, the data preprocessing module utilizes regular expressions, data conversion scripts, and data processing libraries to achieve data standardization and preprocessing. Regular expressions are used for data parsing and validation, data conversion scripts (such as Python scripts) are used for format conversion and standardization, and data processing libraries (such as Pandas, NumPy, etc.) are used for complex data cleaning and noise reduction operations. The implementation of data preprocessing modules typically relies on data processing algorithms and tools, such as regular expressions for data parsing and validation, data transformation scripts (e.g., Python scripts) for format conversion and standardization, and specialized data processing libraries (e.g., Pandas, NumPy) for complex data cleaning and noise reduction operations. Furthermore, machine learning algorithms can be used for more advanced data cleaning and anomaly detection tasks.
[0012] Furthermore, the core processing module includes the following sub-modules: Streaming processing submodule: Utilizes streaming processing frameworks (such as Apache Kafka, Apache Flink, etc.) to build data processing pipelines, enabling real-time data reception, processing, and forwarding; Edge computing submodule: Deploys edge computing nodes, utilizes edge computing platforms and tools (such as KubernetesEdge, OpenEdge, etc.) for resource management and task scheduling, performs localized processing (such as data cleaning, preliminary fusion, etc.) and analysis near the data source, reduces data transmission latency, and improves processing efficiency; quickly generates map data updates based on the processing results, without needing to transmit all data to the cloud for processing, directly applying the processing results to map data updates, or sending them to the data fusion module for further fusion processing; The scheduling and management submodule is responsible for task scheduling and resource management within the core processing module, ensuring efficient collaboration among all submodules.
[0013] Furthermore, the streaming processing submodule parses the received data stream into structured data and uses streaming processing technology to perform real-time analysis on the data, including filtering, aggregation, and transformation operations, and generates updated map data fragments or incremental information based on the analysis results.
[0014] Furthermore, the scheduling management submodule dynamically allocates computing resources and schedules processing tasks based on the characteristics of the data stream and processing requirements, as follows: Resource monitoring: Real-time monitoring of the resource usage of edge computing nodes, such as CPU, memory, network bandwidth, etc. Task scheduling: Based on resource monitoring results and processing needs, tasks are dynamically scheduled to ensure timely completion and efficient resource utilization. Fault recovery: Automatic fault recovery and task rescheduling are performed when a node fails or a task fails, ensuring system stability and reliability.
[0015] Furthermore, the conflict detection module monitors data conflicts in real time during the data fusion process. Once a conflict is detected, it immediately triggers the conflict resolution mechanism and processes the data according to preset strategies (such as prioritizing the use of highly reliable data sources or manual intervention). The module designs conflict detection algorithms and rule bases, and combines them with preset resolution strategies to achieve automatic detection and resolution of conflicts.
[0016] On the other hand, a method for dynamic updating and fusion utilization of map data is provided, applied to the aforementioned system for dynamic updating and fusion utilization of map data, including the following steps: S1. The data acquisition module collects geographic information data from multiple sources in real time through API interfaces, data stream subscriptions, or periodic polling. The data preprocessing module cleans, denoises, and converts the collected data to ensure that the data is uniform and conforms to standard formats. S2. The core processing module receives the pre-processed data, the streaming processing submodule realizes the real-time reception, processing and forwarding of data, the edge computing submodule performs resource management and task scheduling, and performs localized processing and analysis near the data source. At the same time, the scheduling management submodule is responsible for the coordination between the streaming processing submodule and the edge computing submodule, and performs task scheduling and resource management. S3. The data fusion module uses a multi-source data fusion algorithm to perform weighted fusion based on the characteristics and reliability of the data sources, and generates a comprehensive update. S4. The conflict detection module detects conflicts and contradictions between different data sources during the data fusion process and processes them according to preset strategies. S5. The quality assessment module performs quality assessment on the fused data, while the storage management module stores and manages the fused map data, providing data query, retrieval and update services. S6. Users receive operation requests through the user interface, and the processing results are displayed, enabling interaction between users and the system.
[0017] This invention provides a system and method for dynamic updating and fusion utilization of map data, which has the following beneficial effects: 1. This invention replaces the traditional periodic batch update method and adopts a streaming processing architecture, enabling the system to continuously and in real time receive and process data update requests, achieving millisecond-level response speed. At the same time, it pushes data processing tasks from the cloud to the network edge to significantly reduce data transmission latency, improve processing efficiency, and achieve faster map data updates.
[0018] 2. This invention establishes a unified data format and standard, preprocesses and transforms data from different sources, and, in conjunction with a multi-source data fusion algorithm, performs weighted fusion based on the characteristics and reliability of different data sources, significantly improving the quality of multi-source data fusion. Furthermore, it uses data quality assessment indicators and a system to evaluate and verify the quality of the fused data, promptly identifying and correcting errors and redundancies to ensure the overall quality of the map data. Attached Figure Description
[0019] Figure 1 This is a schematic diagram of the architecture of a system for dynamic updating and fusion utilization of map data according to the present invention; Figure 2 This is a flowchart illustrating the steps of a method for dynamically updating and integrating map data according to the present invention. Detailed Implementation
[0020] The embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and should not be construed as limiting the scope of the invention.
[0021] Example 1: Dynamic Updating and Integration of Map Data in Smart City Traffic Management In smart city traffic management systems, this map data dynamic updating and fusion utilization system and method are applied to update road traffic conditions in real time, including information such as traffic flow, traffic accidents, and road construction. The system configuration is as follows: Data Acquisition Module: Connects to multiple data sources, including traffic monitoring cameras, vehicle-mounted GPS terminals, and smartphone app user feedback. In this embodiment, the traffic monitoring cameras upload road traffic flow data every 5 seconds in JSON format, including camera ID, timestamp, and traffic flow count. The vehicle-mounted GPS terminals upload vehicle location information every 30 seconds in CSV format, including vehicle ID, latitude and longitude, speed, and direction. The smartphone app user feedback allows users to report traffic accidents or road construction information via the app, in custom text format, including event type, location description, and time.
[0022] Data preprocessing module: 1) For traffic monitoring camera data, perform outlier detection (e.g., negative traffic flow) and missing value handling (e.g., filling in with data from the previous time point). 2) For vehicle-mounted GPS terminal data, perform coordinate transformation to unify the coordinate system to WGS84 and filter out points with abnormal speeds (e.g., exceeding 200km / h). 3) For user feedback data from smartphone apps, use regular expressions to parse out key information and convert it into structured data.
[0023] Core processing module: Streaming processing submodule: Uses the Apache Flink framework to receive and process data streams in real time, generating traffic flow heatmap images.
[0024] Edge computing submodule: Deploy edge computing nodes near traffic monitoring cameras to perform preliminary data aggregation and analysis, reducing data transmission volume.
[0025] Scheduling and management submodule: Dynamically allocates computing resources to ensure that high-priority tasks (such as traffic accident handling) are executed first.
[0026] Data fusion module: It integrates traffic monitoring camera data, vehicle GPS terminal data, and smartphone APP user feedback data, and uses a weighted average algorithm to assign different weights based on the reliability and timeliness of the data source.
[0027] Conflict detection module: When it detects that the traffic flow reported by different data sources on the same road segment is too different, it triggers the conflict resolution mechanism and prioritizes the use of traffic monitoring camera data (because of its higher accuracy).
[0028] Quality assessment module: assesses the accuracy, completeness, and timeliness of the merged data, generates an assessment report, and points out potential data quality issues.
[0029] Storage management module: Stores the merged map data in the distributed file system HDFS, providing efficient query and retrieval services.
[0030] User interface: Develop a web application to display a real-time traffic map, allowing users to query information such as traffic flow and traffic accidents on specific road sections.
[0031] Implementation Results It achieves millisecond-level response speeds, with traffic condition updates delayed by no more than one second. After multi-source data fusion, the accuracy of traffic flow heatmaps has improved by 30%, and the traffic accident detection rate has increased by 20%. User feedback shows that the traffic information provided by the system significantly helps with travel planning and reduces commuting time.
[0032] Example 2: Dynamic Updating of High-Precision Maps for Autonomous Vehicles In the high-precision map dynamic update system for autonomous vehicles, the system and method for dynamically updating and fusing map data are applied to update road information in real time, including lane lines, traffic signs, obstacles, etc. The system configuration is as follows: Data Acquisition Module: Connects to multiple data sources, including vehicle-mounted LiDAR, vehicle-mounted cameras, professional surveying vehicles, and drones. In this embodiment, the vehicle-mounted LiDAR uploads point cloud data every 100 milliseconds in LAS format, containing detailed 3D information about the vehicle's surrounding environment. The vehicle-mounted camera uploads image data every second in JPEG format, containing visual information such as lane lines and traffic signs. The professional surveying vehicle periodically (e.g., monthly) uploads high-precision map data in SHP format, containing road geometry and attribute information. The drone conducts regular inspections in specific areas (e.g., construction areas) and uploads aerial image data in TIFF format.
[0033] Data preprocessing module: 1) Denoise and filter the vehicle-mounted LiDAR point cloud data to remove ground points and invalid points. 2) Enhance and extract features from the vehicle-mounted camera image data to identify key information such as lane lines and traffic signs. 3) Perform coordinate transformation and format conversion on the professional surveying vehicle data to unify it into a format compatible with vehicle-mounted data. 4) Perform geometric correction and stitching processing on the UAV aerial image data to generate orthophoto maps.
[0034] Core processing module: The streaming processing submodule uses the Apache Kafka framework to receive and process point cloud data and image data streams in real time, generating local map update fragments.
[0035] Edge computing submodule: Deploy edge computing nodes on the vehicle computing platform to perform preliminary data fusion and obstacle detection.
[0036] The scheduling and management submodule dynamically adjusts the priority and resource allocation of data processing tasks based on vehicle speed and the complexity of the surrounding environment.
[0037] Data fusion module: It integrates data from vehicle-mounted LiDAR, vehicle-mounted cameras, professional surveying vehicles, and drone aerial images, and uses the Kalman filter algorithm to generate high-precision map updates.
[0038] Conflict detection module: When it detects that the lane line positions reported by different data sources are too different, it triggers the conflict resolution mechanism and prioritizes the use of professional survey vehicle data (because of its highest accuracy).
[0039] Quality assessment module: Evaluates the accuracy, completeness, and consistency of the merged map data, generates a quality assessment report, and guides subsequent data collection and processing.
[0040] Storage management module: Stores the merged high-precision map data in the vehicle's solid-state drive, and simultaneously uploads it to the cloud server for backup and sharing.
[0041] User interface: Develop an in-vehicle HUD (Head-Up Display) system to display high-precision maps and surrounding environment information in real time, assisting drivers or autonomous driving systems in making decisions.
[0042] Implementation Results Centimeter-level map update accuracy has been achieved, meeting the needs of autonomous vehicles. After multi-source data fusion, the integrity and consistency of map data have been significantly improved, reducing misjudgments and omissions in autonomous driving systems. The application of the in-vehicle HUD system has enhanced driving safety and comfort, receiving positive feedback from users.
[0043] The embodiments of the present invention are given for illustrative and descriptive purposes only, and are not intended to be exhaustive or to limit the invention to the forms disclosed. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of the invention, and to enable those skilled in the art to understand the invention and to design various embodiments with various modifications suitable for a particular purpose.
Claims
1. A system for dynamic updating and fusion utilization of map data, characterized in that, include: Data acquisition module: responsible for collecting geographic information data from various data sources in real time or periodically; Data preprocessing module: responsible for cleaning, denoising, and format conversion of the collected multi-source heterogeneous data to make it conform to a unified data format and standard; Core processing module: Adopting a streaming processing architecture, it pushes data processing tasks from the cloud to the network edge, enabling real-time data reception, processing, and updating; Data fusion module: Responsible for receiving data from the core processing module, using multi-source data fusion algorithms, weighting and fusing data according to the characteristics and reliability of different data sources, and generating comprehensive map data updates; The data fusion module integrates a multi-source data fusion algorithm library, performs fusion processing on the input data through algorithms, and outputs the fused result; Conflict detection module: responsible for detecting conflicts and contradictions between different data sources during the data fusion process, and handling them according to preset strategies; The core processing module includes the following sub-modules: Streaming processing submodule: Utilizes the streaming processing framework to build a data processing pipeline, enabling real-time data reception, processing, and forwarding; Edge computing submodule: Deploys edge computing nodes, utilizes edge computing platforms and tools for resource management and task scheduling, and performs localized processing and analysis near the data source; Scheduling and Management Submodule: Responsible for task scheduling and resource management within the core processing module.
2. The system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, The data acquisition module connects to the data source through API interfaces, data stream subscriptions, and periodic polling. Supported data source types include, but are not limited to, professional surveying equipment, smartphones, vehicle terminals, drones, and traffic monitoring cameras.
3. The system for dynamic updating and fusion utilization of map data according to claim 2, characterized in that, The data acquisition module's acquisition logic is as follows: it continuously monitors each data source, and once new data arrives or the update conditions are met, it immediately triggers the data acquisition process and transmits the data to the data preprocessing module. For data sources that support API interfaces, the data acquisition module connects to the data source via the API and allows the module to directly call the services provided by the data source to obtain the latest geographic information data; For data sources that support data stream subscription, the data acquisition module subscribes to specific data streams, and once new data is generated by the data source, it is automatically pushed to the data acquisition module. For data sources that do not support API interfaces or data stream subscriptions, the data acquisition module uses a periodic polling method to obtain data. That is, the module sends requests to the data source at preset time intervals to obtain the latest geographic information data.
4. The system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, The data preprocessing module receives data from the data acquisition module, processes the data according to preset data cleaning rules and format conversion templates, and sends the processed data to the core processing module. The process is as follows: Data reception: Receives raw geographic information data from the data acquisition module; Data cleaning: removing noise, errors, and redundant information from data, specifically including: 1) Outlier detection and handling: Use Z-score and IQR methods to detect outliers and correct or delete them according to the actual situation; 2) Missing value handling: For missing values in the data, interpolation, mean / median imputation, or model-based prediction imputation methods are used for handling; 3) Duplicate value handling: Detect and delete duplicate records in the data; Data denoising: eliminating random and systematic errors in data, specifically including: 1) Smoothing filtering: Used to eliminate short-term fluctuations and noise in data; 2) Trend analysis: Identifying and removing long-term trends or periodic changes in the data through time series analysis methods; Format conversion: Converting data from different data sources into a unified data format, specifically including: 1) Data parsing: Write a parser based on the specific format of the data source to parse the raw data into structured data; 2) Data mapping: Establish mapping relationships between different data formats, mapping the parsed data to a unified data model or format; 3) Data standardization: Standardize the data; Data transmission: The cleaned, denoised, and format-converted data will be sent to the core processing module, and data verification and checks must be performed before transmission.
5. The system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, The data preprocessing module utilizes regular expressions, data conversion scripts, and a data processing library to standardize and preprocess the data. Regular expressions are used for data parsing and validation, data conversion scripts are used for format conversion and standardization, and the data processing library is used for data cleaning and noise reduction.
6. The system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, The streaming processing submodule parses the received data stream into structured data and uses streaming processing technology to perform real-time analysis on the data, including filtering, aggregation, and transformation operations, and generates updated map data fragments or incremental information based on the analysis results.
7. The system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, The scheduling management submodule dynamically allocates computing resources and schedules processing tasks based on the characteristics of the data stream and processing requirements. The process is as follows: Resource monitoring: Real-time monitoring of resource usage of edge computing nodes; Task scheduling: Dynamically schedule tasks based on resource monitoring results and processing needs; Fault recovery: Automatically recover from faults and reschedule tasks when a node fails or a task fails.
8. The system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, The conflict detection module monitors data conflicts in real time during the data fusion process. Once a conflict is detected, it immediately triggers the conflict resolution mechanism and processes the data according to a preset strategy.
9. A system for dynamic updating and fusion utilization of map data according to claim 1, characterized in that, Also includes: Quality assessment module: responsible for establishing data quality assessment indicators and systems, and conducting quality assessment and verification of the merged data; Storage management module: Responsible for storing and managing the merged map data, and providing data query, retrieval and update services; User interface: Provides users with a user-friendly interface and interaction methods, making it convenient for users to view map data, submit update requests or perform other operations.
10. A method for dynamically updating and integrating map data, applied to the system for dynamically updating and integrating map data as described in any one of claims 1-9, characterized in that, Includes the following steps: S1. The data acquisition module collects geographic information data from multiple sources in real time through API interfaces, data stream subscriptions, or periodic polling, and the data preprocessing module cleans, denoises, and converts the format of the collected data. S2. The core processing module receives the pre-processed data, the streaming processing submodule realizes the real-time reception, processing and forwarding of data, the edge computing submodule performs resource management and task scheduling, and performs localized processing and analysis near the data source. At the same time, the scheduling management submodule is responsible for the coordination between the streaming processing submodule and the edge computing submodule, and performs task scheduling and resource management. S3. The data fusion module uses a multi-source data fusion algorithm to perform weighted fusion based on the characteristics and reliability of the data sources, and generates a comprehensive update. S4. The conflict detection module detects conflicts and contradictions between different data sources during the data fusion process and processes them according to preset strategies. S5. The quality assessment module performs quality assessment on the fused data, while the storage management module stores and manages the fused map data, providing data query, retrieval and update services. S6. Users receive operation requests through the user interface, and the processing results are displayed, enabling interaction between users and the system.