Multi-source data fusion driving-based highway traffic guidance and maintenance construction cooperation system and method

Abstract

The invention discloses a highway traffic guidance and maintenance construction cooperation system and method based on multi-source data fusion driving. The system comprises a data acquisition module, a standardized processing module, an association fusion processing module, a guide and modification scheme generation module, a scheme optimization module and a standardized scheme output and visual display module. Through modularized series connection from data acquisition, processing, scheme generation to output display, a traditional fragmented operation mode depending on artificial experience is changed; according to the method, integration and automation of'generation-optimization-display 'of traffic guidance and revision schemes are realized, construction requirements can be quickly responded, a plurality of feasible schemes are generated in a short time and are compared and selected, the scheme making period is greatly shortened, and precious time is gained for quick dispersion and passage recovery of the expressway; through fusion and intelligent processing of real-time and multi-source information, the generated guiding and revising scheme has more data support, and the subjective misjudgment risk is significantly reduced.

Description

Technical Field

[0001] This invention relates to the field of traffic flow management during highway maintenance and construction, and specifically to a highway traffic diversion and maintenance construction collaborative system and method driven by multi-source data fusion. Background Technology

[0002] In highway maintenance and construction, the scientific implementation of road closures and efficient traffic guidance remains a key challenge in traffic management. Improper handling can lead to traffic congestion or even serious accidents. However, traditional traffic diversion schemes rely heavily on manual experience, which has significant limitations.

[0003] First, traditional methods lack sufficient data support. The traffic flow and road network conditions information relied upon for scheme design are often from a single source, outdated, and mostly historical static data, failing to accurately reflect the dynamically changing traffic conditions during construction. This leads to a disconnect between the scheme and the actual situation, making it difficult to cope with complex scenarios such as real-time traffic flow fluctuations, emergencies, and severe weather.

[0004] Secondly, traditional methods suffer from poor reliability and accuracy. Traditional approaches struggle to effectively integrate and calibrate data related to traffic management, and are unable to intelligently compensate for issues such as missing or conflicting data, significantly compromising the reliability and accuracy of decision-making.

[0005] Furthermore, the level of intelligence is low. Traditional methods struggle to systematically and comprehensively consider multi-objective optimization principles such as safety, efficiency, and cost, and also lack a fine distinction between optimization dimensions. Scheme comparison relies heavily on qualitative analysis, lacking quantitative evaluation and visualization methods based on microscopic traffic simulation, which means the final solution may not be optimal and could even pose potential risks.

[0006] As urban road networks become increasingly complex, traffic management during construction is becoming more urgent. Traditional experience-driven models are no longer sufficient to meet the demands of modern traffic management, as they cannot dynamically adjust based on real-time traffic flow and construction progress, and are difficult to comprehensively assess potential risk factors. Therefore, there is an urgent need to introduce a more scientific and precise scheme design mechanism to improve the efficiency and safety of traffic diversion. Summary of the Invention

[0007] The purpose of this invention is to provide a collaborative system and method for highway traffic diversion and maintenance construction driven by multi-source data fusion, so as to solve the above-mentioned problems.

[0008] To address the aforementioned technical problems, this invention provides a collaborative system for highway traffic diversion and maintenance construction driven by multi-source data fusion, comprising:

[0009] The data acquisition module is used to collect multi-source traffic data within the area;

[0010] The standardization processing module is used to standardize multi-source traffic data.

[0011] The correlation and fusion processing module is used to correlate and fuse standardized multi-source traffic data to obtain fused data;

[0012] The guidance and modification scheme generation module is used to generate multiple guidance and modification schemes based on fused data, combined with rules and knowledge base;

[0013] The scheme optimization module is used to optimize multiple guidance and modification schemes based on travel demand and closure type, and with safety, efficiency and cost as optimization principles.

[0014] The standardized solution output and visualization module is used to output and visualize the optimized solution in a standardized manner.

[0015] Furthermore, multi-source traffic data includes: basic road network data, real-time / predictive traffic flow data, surrounding road network information, construction information, environmental data, and traffic control resources.

[0016] Furthermore, the standardized processing module includes:

[0017] The data confidence weight allocation unit is used to dynamically allocate confidence weights to multi-source traffic data from different sources, monitor the quality indicators of each data source in real time, and dynamically fine-tune its current weight according to preset strategies or lightweight models.

[0018] The data missing compensation unit is used to predict and fill in missing data in the data source based on the LSTM neural network.

[0019] The spatiotemporal reference alignment unit is used to unify multi-source data to the same spatiotemporal reference.

[0020] Furthermore, the correlation and fusion processing module includes:

[0021] Directly associated units based on spatial topology are used to uniformly associate all multi-source traffic data with the same structured spatial unit.

[0022] The spatiotemporal event / state-based association unit is used to identify and associate the same traffic event or the same macro traffic state described in multi-source traffic data sources.

[0023] Cross-domain data association unit is used to establish a relationship between traffic flow data and environmental data based on a unified spatial unit and timestamp.

[0024] Furthermore, the rules and knowledge base include:

[0025] The rule base contains national and local traffic management plans and construction specifications.

[0026] The knowledge base contains best practice cases and expert experience.

[0027] Furthermore, travel demand includes both similar and dissimilar travel.

[0028] The method for determining similar trips is as follows: if the real-time or predicted trip destination matches the set of geofences E of the downstream destination area of ​​road segment A, then it is determined to be a similar trip;

[0029] The method for determining outlier travel is as follows: if the travel behavior is to the inaccessible area of ​​road segment A, or if the travel destination has no strong correlation with the geofence set E of the downstream destination area of ​​road segment A, then it is determined to be outlier travel.

[0030] Furthermore, traffic closure types include semi-closed traffic, early warning-based fully closed traffic, and emergency-based fully closed traffic;

[0031] Semi-closed traffic is based on video surveillance, real-time radar lane status and dynamic confirmation of associated traffic flow speed, triggering dynamic adjustment of variable speed limits;

[0032] The early warning-based full-closure traffic system is activated according to the construction plan time window, and traffic diversion and guidance schemes are dynamically determined based on the traffic flow characteristics and road network status during the closure period.

[0033] Emergency-response fully enclosed traffic is triggered by real-time detection of sudden and severe events and identification of traffic flow disruption characteristics, and generates alternative routes based on real-time road network data.

[0034] Furthermore, the standardized solution output and visualization module includes:

[0035] The automated drawing and specification generation unit is used to automatically plan detour routes and generate traffic organization maps based on the geographical and temporal information and real-time traffic data of the construction area; at the same time, it calculates and labels the functional areas and traffic facility plans of the construction area.

[0036] The dynamic traffic simulation visualization unit is used to integrate micro-simulation trajectory data with real-time vehicle positioning information, identify and highlight traffic conflict points around the construction area, and generate a multi-dimensional hierarchical early warning heat map that integrates traffic flow data, meteorological data and construction vehicle GPS trajectories.

[0037] The construction interactive simulation unit is used to bind the construction machinery model with real-time positioning, simulate the interaction process between construction machinery and social vehicles, output the safe operation time window, and generate emergency evacuation plan based on the dynamic simulation of the impact and spread of emergencies.

[0038] The intelligent reporting and 3D expression unit is used to generate construction traffic organization reports based on traffic organization diagrams, and to overlay the traffic diversion plan onto a 3D real-world model for verification of sign visibility and spatial compliance.

[0039] Furthermore, the system also includes:

[0040] The dynamic monitoring and feedback optimization module is used to dynamically monitor and provide feedback on real-time comparison of IoT data and simulation results, trigger multi-level early warnings and dynamically optimize the scheme, forming a self-updating closed loop of the rule base.

[0041] Furthermore, this invention also provides a collaborative method for highway traffic diversion and maintenance construction based on multi-source data fusion, comprising the following steps:

[0042] Collect multi-source traffic data within the region;

[0043] Standardize the processing of multi-source traffic data;

[0044] The standardized multi-source traffic data is correlated and fused to obtain fused data;

[0045] Based on the fused data, multiple modification schemes are generated by combining rules and knowledge base;

[0046] The standardized solution output and visualization module is used to optimize multiple guidance and modification solutions based on travel demand and closure type, and with safety, efficiency and cost as optimization principles.

[0047] Output standardized solutions and present them visually.

[0048] The beneficial effects of this invention are as follows: By modularly connecting data collection, processing, scheme generation to output display, it changes the traditional fragmented operation mode that relies on manual experience, realizes the integration and automation of traffic diversion scheme "generation-optimization-display", can quickly respond to construction needs, generate multiple feasible schemes and compare them in a short time, greatly shortens the scheme formulation cycle, and saves valuable time for the rapid diversion and restoration of traffic on highways; by integrating and intelligently processing real-time and multi-source information, the generated diversion schemes are more data-supported and significantly reduce the risk of subjective misjudgment. Attached Figure Description

[0049] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, use the same reference numerals to denote the same or similar parts. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0050] Figure 1 This is a schematic diagram of one embodiment of the present invention. Detailed Implementation

[0051] like Figure 1The system shown is a collaborative system for highway traffic diversion and maintenance construction driven by multi-source data fusion. The system includes:

[0052] The data acquisition module is used to collect multi-source traffic data within the area;

[0053] The standardization processing module is used to standardize multi-source traffic data.

[0054] The correlation and fusion processing module is used to correlate and fuse standardized multi-source traffic data to obtain fused data;

[0055] The guidance and modification scheme generation module is used to generate multiple guidance and modification schemes based on fused data, combined with rules and knowledge base;

[0056] The scheme optimization module is used to optimize multiple guidance and modification schemes based on travel demand and closure type, and with safety, efficiency and cost as optimization principles.

[0057] The standardized solution output and visualization module is used to output and visualize the optimized solution in a standardized manner.

[0058] This invention, through a modular chain from data acquisition, processing, scheme generation to output display, changes the traditional fragmented operation mode that relies on manual experience. It realizes the integration and automation of traffic diversion scheme "generation-optimization-display", which can quickly respond to construction needs (especially emergency closures). It can generate multiple feasible schemes and compare them in a short time, which greatly shortens the scheme formulation cycle and saves valuable time for the rapid diversion and restoration of traffic on highways. By integrating and intelligently processing real-time, multi-source information, the generated diversion schemes are more data-supported and significantly reduce the risk of subjective misjudgment.

[0059] According to one embodiment of this application, the multi-source traffic data includes: basic road network data, real-time / predictive traffic flow data, surrounding road network information, construction information, environmental data, and traffic control resources.

[0060] Basic road network data: Based on high-precision geographic information system (GIS) map data, it provides detailed road network structure, including physical facility parameters such as the number of lanes, lane width, road slope, curves, entrances and exits, service areas, bridges and tunnels, as well as attribute data such as design speed, historical traffic flow and accident data, which helps to analyze road performance and its impact on traffic flow;

[0061] Real-time / predictive traffic flow data: By collecting and integrating data from multiple sources such as roadside units, checkpoints, floating car GPS, mobile phone signaling data and Internet map APIs, real-time vehicle speed, traffic flow, queue length and OD data are obtained. Combined with historical traffic data, seasonal changes and data on special road sections and time periods, the data are analyzed to predict changes in traffic flow during construction.

[0062] Surrounding road network information: This analyzes the capacity and real-time operational status of surrounding alternative roads, as well as road control information. By accessing real-time data and control information from alternative roads, more scientific detour planning can be provided during construction to ensure smooth traffic flow outside the construction area.

[0063] By analyzing the traffic flow and destination distribution of the surrounding road network, we can optimize the road closure strategy in the construction area, rationally plan the size and scope of the closed area, reduce the impact of the construction area on the surrounding traffic, and improve the overall traffic capacity of the area through the rational use of surrounding parallel alternative roads.

[0064] Construction information includes the type of construction, precise geographic information of the construction area, construction period, and the number of lanes / vehicles that need to be closed during construction.

[0065] Environmental data: including weather forecasts, visibility, lighting conditions, etc.

[0066] Traffic control resources include traffic signs, road markings, cones, crash barriers, warning lights, mobile traffic lights, variable message signs, and breakdown vehicles. Through precise configuration and dynamic adjustment, traffic flow in the construction area can be effectively managed, and support can be provided for handling emergencies.

[0067] According to one embodiment of this application, the standardization processing module includes:

[0068] The data confidence weight allocation unit is used to establish various data weight benchmark rules based on the inherent characteristics of the data source, dynamically allocate confidence weights for multi-source traffic data from different sources, monitor the quality indicators of each data source in real time, and dynamically fine-tune its current weight according to preset strategies or lightweight models.

[0069] The data missing compensation unit is used to predict and fill missing data in the data source based on LSTM neural network. Specifically, it includes: establishing a complete dataset based on LSTM neural network prediction model, which integrates historical time series data of the target location, real-time / historical data of associated spatial units, time features, weather conditions, and status of associated construction areas, etc., training the model to learn the spatiotemporal evolution pattern of traffic flow parameters, and performing high-precision filling of data missing due to equipment failure, communication interruption, signal blockage, etc., to generate complete, predicted and filled traffic flow data.

[0070] The spatiotemporal reference alignment unit is used to unify multi-source data to the same spatiotemporal reference. Specifically, it includes accurately converting WGS84 coordinate system data from devices such as GPS into the national standard CGCS2000 coordinate system data based on a seven-parameter Helmholtz transform model, and mapping the converted point location data to a structured road network or a unified geographic grid; identifying and uniformly parsing the timestamp formats of different data sources, and converting them into an internal high-precision UTC time reference; and resolving inconsistencies in time reference systems, spatial reference systems, and entity associations among multi-source data, achieving accurate matching and fusion of data under a unified spatiotemporal framework, and providing spatiotemporal reference support for data association.

[0071] According to one embodiment of this application, the association fusion processing module includes:

[0072] Directly associated units based on spatial topology, through spatial gridding or road segment mapping technology, are used to uniformly associate all multi-source traffic data into the same structured spatial unit; data from different sources located within the same spatial unit automatically establish association relationships;

[0073] The spatiotemporal event / state-based association unit is used to identify and associate the same traffic event or the same macro-level traffic state described in multi-source traffic data sources. Specifically, it includes: spatiotemporal window matching: under a unified spatiotemporal benchmark, determining whether events reported from different sources have significant overlap in time and space; feature matching: matching using the features of the events; and rule engine or machine learning model-driven fusion: applying predefined rules or training machine learning classifiers to comprehensively determine whether reports from different sources point to the same event or state.

[0074] Cross-domain data association unit is used to establish a relationship between traffic flow data and environmental data based on a unified spatial unit and timestamp; specifically, it includes: based on a predefined construction area geofence and its effective time window, it achieves accurate association between real-time traffic flow dynamic data and static / dynamic information of a specific construction area through spatial relationship calculation and time matching.

[0075] According to one embodiment of this application, the rules and knowledge base include:

[0076] The rule base contains national and local traffic management plans and construction specifications, such as minimum length of work areas and safety standards for buffer zone settings.

[0077] The knowledge base contains best practice cases and expert experience, such as sight distance requirements at different vehicle speeds and turning radii for different vehicle types.

[0078] The rule base and knowledge base provide actionable standardized guidelines; based on real-time construction types, traffic flow characteristics, and environmental data, they dynamically activate and associate subsets of rules.

[0079] According to one embodiment of this application, travel demand includes similar travel and dissimilar travel;

[0080] The method for determining similar trips is as follows: Based on the fused mobile phone signaling and GPS trajectory data, the set of geofences E for the downstream destination area of ​​road segment A is dynamically constructed and updated. Regardless of how the detour route changes, if the real-time or predicted travel destination matches set E, it is determined to be a similar trip.

[0081] The method for determining outlier travel is as follows: if the travel behavior is to the inaccessible area of ​​road segment A, or if the travel destination has no strong correlation with the geofence set E of the downstream destination area of ​​road segment A, then it is determined to be outlier travel.

[0082] According to one embodiment of this application, traffic closure types include semi-closed traffic, early warning fully closed traffic, and emergency fully closed traffic;

[0083] Semi-closed traffic is based on video surveillance, real-time radar lane status and dynamic confirmation of associated traffic flow speed, triggering dynamic adjustment of variable speed limits; the speed limit is dynamically adjusted through variable speed limit signs to ensure the safety and smoothness of vehicles when passing through construction zones or temporary closed sections.

[0084] The pre-warning-based full-closure traffic system is activated according to the construction plan time window. Traffic diversion and guidance schemes are dynamically determined based on the traffic flow characteristics and road network status during the closure period. This includes building a three-level guidance path database covering highways, provincial roads, and county and township roads; setting up temporary traffic maintenance channels; and opening emergency lanes as needed to achieve flexible multi-level path adjustments.

[0085] Emergency-response fully enclosed traffic is triggered by real-time detection of sudden and severe events and identification of traffic flow interruption characteristics, and dynamically assesses the scope of closure; it provides minute-level response, and quickly initiates diversion plans through real-time monitoring and traffic condition analysis; at the same time, it implements dynamic risk prevention and control, and quickly generates multiple alternative routes to guide vehicles to detour through real-time road network data.

[0086] According to one embodiment of this application, the standardized solution output and visualization module includes:

[0087] The automated drawing and specification generation unit is used to automatically plan detour routes and generate traffic organization diagrams based on the geographical (geofence area) and temporal information (effective time window) of the construction area and real-time traffic data (high-precision road network topology and real-time traffic flow prediction data). Simultaneously, it dynamically calculates and labels various functional areas of the construction area (warning area, transition area, buffer zone, work area, termination area, reserved emergency lane area, etc.), and automatically generates traffic facility plans (cone spacing, crash barrier density, variable message sign content, etc.) based on real-time vehicle type and traffic flow ratios. It also dynamically generates lane compression and lane-borrowing schemes based on the BIM lane-level model to ensure that turning radii match the dominant vehicle types.

[0088] The dynamic traffic simulation visualization unit integrates micro-simulation trajectory data with real-time vehicle positioning information. It identifies and highlights traffic conflict points around the construction area in red in 2D / 3D views through a spatiotemporal conflict clustering algorithm. It also generates a multi-dimensional hierarchical early warning heat map that integrates traffic flow data, meteorological data and construction vehicle GPS trajectories, and supports dynamic switching display of congestion index, queue length and accident risk.

[0089] The construction interactive simulation unit is used to bind the BIM model of construction machinery with real-time positioning and simulate its entry and exit paths; it pre-simulates the interaction process with social vehicles through conflict detection algorithms and outputs the safe operation time window; it loads the historical accident pattern library into the digital road network, dynamically simulates the impact and spread of emergencies, and generates emergency lane activation instructions or diversion guidance schemes in a timely manner based on this.

[0090] The intelligent reporting and 3D expression unit is used to generate construction traffic organization reports based on traffic organization diagrams, covering facility parameters, risk points and emergency strategies; it overlays construction area geofences and traffic facility plans onto an oblique photogrammetry real-scene model, and enables 3D field analysis for complex nodes such as interchanges and tunnels to verify sign visibility and spatial compliance.

[0091] According to one embodiment of this application, the system further includes:

[0092] The dynamic monitoring and feedback optimization module is used to dynamically monitor and provide feedback on real-time comparison of IoT data and simulation results, trigger multi-level early warnings and dynamically optimize the scheme, forming a self-updating closed loop of the rule base.

[0093] The dynamic monitoring and feedback optimization module includes:

[0094] The IoT monitoring access unit connects to various IoT devices in the construction area to collect real-time data on traffic conditions, traffic flow, speed, queue length, and accident events, supporting dynamic management and emergency response during the construction period.

[0095] The scheme execution comparison unit compares the running data with the initial simulation results in real time, and quickly identifies deviations and generates optimization suggestions to ensure the consistency between the construction plan and the on-site working conditions.

[0096] The anomaly warning and auxiliary decision-making unit immediately triggers multi-level warnings when actual operation deviates significantly from expectations or when a sudden emergency occurs; at the same time, it dynamically generates emergency adjustment strategies based on real-time fused data.

[0097] The effect evaluation and knowledge accumulation unit automatically generates an effect evaluation report after construction is completed, quantitatively analyzing key indicators such as actual delay time and accident rate; by extracting successful experiences and lessons learned, it continuously updates the rule base parameters and simulation model calibration coefficients, driving iterative improvement in the accuracy and efficiency of intelligent solution generation.

[0098] Furthermore, this invention also provides a collaborative method for highway traffic diversion and maintenance construction based on multi-source data fusion, comprising the following steps:

[0099] Collect multi-source traffic data within the region;

[0100] Standardize the processing of multi-source traffic data;

[0101] The standardized multi-source traffic data is correlated and fused to obtain fused data;

[0102] Based on the fused data, multiple modification schemes are generated by combining rules and knowledge base;

[0103] The standardized solution output and visualization module is used to optimize multiple guidance and modification solutions based on travel demand and closure type, and with safety, efficiency and cost as optimization principles.

[0104] Output standardized solutions and present them visually.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A collaborative system for highway traffic diversion and maintenance construction driven by multi-source data fusion, characterized in that, include: The data acquisition module is used to collect multi-source traffic data within the area; A standardization processing module is used to standardize the multi-source traffic data; The correlation and fusion processing module is used to perform correlation and fusion processing on the standardized multi-source traffic data to obtain fused data. The modification scheme generation module is used to generate multiple modification schemes based on the fused data, combined with rules and a knowledge base. The scheme optimization module is used to optimize multiple guidance and modification schemes based on travel demand and closure type, and with safety, efficiency and cost as optimization principles. The standardized solution output and visualization module is used to output and visualize the optimized solution in a standardized manner.

2. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 1, characterized in that, The multi-source traffic data includes: basic road network data, real-time / predicted traffic flow data, surrounding road network information, construction information, environmental data, and traffic control resources.

3. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 2, characterized in that, The standardization processing module includes: The data confidence weight allocation unit is used to dynamically allocate confidence weights to multi-source traffic data from different sources, monitor the quality indicators of each data source in real time, and dynamically fine-tune its current weight according to preset strategies or lightweight models. The data missing compensation unit is used to predict and fill in missing data in the data source based on the LSTM neural network. The spatiotemporal reference alignment unit is used to unify the multi-source data to the same spatiotemporal reference.

4. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 3, characterized in that, The association fusion processing module includes: Directly associated units based on spatial topology are used to uniformly associate all multi-source traffic data with the same structured spatial unit. The spatiotemporal event / state-based association unit is used to identify and associate the same traffic event or the same macro traffic state described in multi-source traffic data sources. Cross-domain data association unit is used to establish a relationship between traffic flow data and environmental data based on a unified spatial unit and timestamp.

5. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 4, characterized in that, The rules and knowledge base include: The rule base contains national and local traffic management plans and construction specifications. The knowledge base contains best practice cases and expert experience.

6. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 5, characterized in that, The travel demand includes both similar and dissimilar travel; The method for determining similar trips is as follows: if the real-time or predicted trip destination matches the geofence set E of the downstream destination area of ​​road segment A, then it is determined to be a similar trip. The method for determining outlier travel is as follows: if a travel behavior with an inaccessible area of ​​road segment A as the destination, or a flexible demand with no strong correlation between the travel destination and the geographic fence set E of the downstream destination area of ​​road segment A, then it is determined to be outlier travel.

7. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 6, characterized in that, The types of traffic closures include semi-closed traffic, early warning-type fully closed traffic, and emergency-type fully closed traffic. The semi-enclosed traffic system is based on video surveillance, real-time radar lane status, and dynamic confirmation of associated traffic flow speeds, triggering dynamic adjustments to variable speed limits. The early warning-based fully enclosed traffic system is activated according to the construction plan time window, and traffic diversion and guidance schemes are dynamically determined based on the traffic flow characteristics and road network status during the closure period. The emergency-response fully enclosed traffic system is triggered by real-time detection of sudden and severe events and identification of traffic flow interruption characteristics, and generates alternative routes based on real-time road network data.

8. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 7, characterized in that, The standardized solution output and visualization module includes: The automated drawing and specification generation unit is used to automatically plan detour routes and generate traffic organization maps based on the geographical and temporal information and real-time traffic data of the construction area; at the same time, it calculates and labels the functional areas and traffic facility plans of the construction area. The dynamic traffic simulation visualization unit is used to integrate micro-simulation trajectory data with real-time vehicle positioning information, identify and highlight traffic conflict points around the construction area, and generate a multi-dimensional hierarchical early warning heat map that integrates traffic flow data, meteorological data and construction vehicle GPS trajectories. The construction interactive simulation unit is used to bind the construction machinery model with real-time positioning, simulate the interaction process between construction machinery and social vehicles, output the safe operation time window, and generate emergency evacuation plan based on the dynamic simulation of the impact and spread of emergencies. The intelligent reporting and 3D expression unit is used to generate construction traffic organization reports based on traffic organization diagrams, and to overlay the traffic diversion plan onto a 3D real-world model for verification of sign visibility and spatial compliance.

9. The highway traffic diversion and maintenance construction collaborative system based on multi-source data fusion as described in claim 1, characterized in that, The system also includes: The dynamic monitoring and feedback optimization module is used to dynamically monitor and provide feedback on real-time comparison of IoT data and simulation results, trigger multi-level early warnings and dynamically optimize the scheme, forming a self-updating closed loop of the rule base.

10. A collaborative method for highway traffic diversion and maintenance construction driven by multi-source data fusion, characterized in that, Including the following steps: Collect multi-source traffic data within the region; The multi-source traffic data is standardized. The standardized multi-source traffic data is correlated and fused to obtain fused data; Based on the fused data, multiple modification schemes are generated by combining rules and knowledge base; The standardized solution output and visualization module is used to optimize multiple guidance and modification solutions based on travel demand and closure type, and with safety, efficiency and cost as optimization principles. Output standardized solutions and present them visually.

Images