Multi-field collaborative management and control method and system of urban governance digital twin platform

Abstract

The application is suitable for the field of city management, and provides a multi-field collaborative management method and system of a city management digital twin platform.The method collects street lamp operation state parameters, traffic flow thermal data, and underground pipe network and street lamp cable spatial correlation data through intelligent street lamp Internet of Things; constructs a street lamp-city infrastructure neural correlation graph based on the data; relies on the graph and multi-dimensional data to monitor faults, deduce transmission paths, identify key areas, analyze secondary hidden dangers, and determine risk levels; and finally implements hierarchical collaborative management according to the risk levels.The scheme realizes multi-field data interconnection and resource collaboration in city management, improves fault response and management efficiency, ensures city operation safety, and is suitable for city management digital control scenes.

Description

Technical Field

[0001] This invention belongs to the field of urban governance, and in particular relates to a multi-domain collaborative management and control method and system for a digital twin platform for urban governance. Background Technology

[0002] The digital transformation of urban governance continues to advance, with digital twin platforms becoming a core technological support for improving urban management efficiency due to their advantages in multi-domain data integration and visualization. Smart streetlights, as the most widely distributed infrastructure in cities, are gradually upgrading from simple lighting functions to data collection terminals. By integrating sensors, they achieve operational status monitoring, providing basic data support for urban governance and driving its development towards intelligence and precision.

[0003] Currently, there are solutions in related technologies that utilize smart streetlights to collect operational status data. Some digital twin platforms are also attempting to integrate data from urban transportation, infrastructure, and other fields for the visualization and basic management of urban operations. These solutions acquire single-dimensional or partial-dimensional data such as streetlight operating parameters and traffic flow through sensor collection and cross-platform data access, providing some data support for urban governance.

[0004] Existing technologies lack in-depth integration and correlation analysis of multi-dimensional data, failing to establish a systematic connection between streetlights and urban infrastructure, and thus unable to accurately predict fault propagation paths and comprehensively anticipate secondary safety hazards. Furthermore, control measures lack dynamic adaptation to risk levels, making it difficult to coordinate resources from multiple fields such as transportation, communities, and drone maintenance to form a collaborative control force. This results in delayed fault response and insufficient targeted control, failing to meet the actual needs of multi-field collaborative control in urban governance. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-domain collaborative management and control method and system for a digital twin platform for urban governance, aiming to solve the technical problems existing in the prior art as identified in the background art.

[0006] This invention is implemented as follows: a multi-domain collaborative management and control method for a digital twin platform for urban governance, the method comprising:

[0007] The smart street light IoT monitoring system collects multi-dimensional data, including the operating status parameters of the street light itself, traffic flow thermal data, and spatial correlation data between underground pipelines and street light cables.

[0008] Based on the multi-dimensional data, a neural network map of streetlights and urban infrastructure is constructed. The neural network map of streetlights and urban infrastructure labels the health status parameters of a single streetlight and presents the spatial relationship between streetlights and urban infrastructure, the linkage logic of operating parameters, and the association weights.

[0009] Based on the neural network map of streetlights and urban infrastructure and multi-dimensional data, fault monitoring and prediction are performed, and fault propagation paths are automatically deduced. Preset key areas covered by the fault propagation paths are identified, secondary safety hazards along the fault propagation paths are analyzed, and risk levels are judged by combining traffic flow heat data and time period characteristics.

[0010] Based on risk levels, hierarchical collaborative control is implemented for fault propagation paths of different risk levels.

[0011] As a further aspect of the present invention, the step of collecting multi-dimensional data through intelligent street light IoT monitoring specifically includes:

[0012] By deploying current sensors, voltage sensors, and brightness sensors inside the streetlights, the current values, voltage values, and real-time brightness values ​​are collected and uploaded in real time at a set sampling frequency, and combined to define the operating status parameters of the streetlight body.

[0013] Through wireless communication protocols, the system accesses real-time vehicle and pedestrian traffic statistics data collected by the urban traffic management platform for each road section, and integrates and calculates the vehicle and pedestrian traffic statistics data to generate traffic flow heatmap data characterizing the regional traffic activity.

[0014] By calling the standard data interface of the unified GIS database for urban infrastructure, vector layer data containing geographic coordinates, burial depth, and pipeline attributes are obtained. Then, through spatial topology analysis algorithms, the horizontal distance, vertical distance, and intersection relationship between underground pipelines and street light cables are calculated to form spatial association data between underground pipelines and street light cables.

[0015] As a further aspect of the present invention, the construction of the neural network map of streetlights and urban infrastructure specifically includes:

[0016] In the 3D visualization engine of the digital twin platform, the physical location of each street lamp is instantiated as an independent street lamp node, and the operating status parameters of the street lamp body are dynamically bound to the corresponding street lamp node, which is then visualized in real time as the health status parameters of the street lamp node.

[0017] Based on the facility location information in the city CIM model, in the 3D visualization engine, a virtual connection line is established between each street light node and the corresponding infrastructure node of the urban infrastructure located within the preset physical radius of the street light node, and the spatial location relationship is defined and presented by the connection line.

[0018] Based on historical operational data, the probability and intensity of a chain reaction of state changes in other infrastructure nodes that are spatially related to the street light node when the street light node undergoes a state change are calculated. The probability and intensity are quantified as association weights, and these logical rules are stored in a graph database to construct a neural network graph of street lights and urban infrastructure.

[0019] As a further aspect of the present invention, the analysis of secondary safety hazards along the fault propagation path, combined with traffic flow heatmap data and time-period characteristics to determine the risk level, specifically includes:

[0020] If the operating status parameters of any street light node exceed the predefined normal operating parameter range for more than 5 consecutive sampling cycles, then the street light node is determined to be an initial fault node.

[0021] Starting from the initial fault node, in the street light-urban infrastructure neural network graph, graph traversal calculation is performed along the spatial positional relationship between the street light node and the infrastructure node according to the association weight, to simulate the cascading impact range of the fault and output the fault propagation path composed of continuous nodes.

[0022] The geographic coordinates of the fault propagation path are spatially overlaid with the GIS layer of the urban public activity area boundary to identify the segments where the fault propagation path intersects with and is contained within the area boundary in the GIS layer, and these segments are marked as preset key areas.

[0023] For each fault propagation path and marked key area, traffic flow heat data is called up, and combined with the predefined rule library of functional types of the key area, the potential possibility of various types of traffic accidents caused by lack of lighting is simulated and analyzed, and a specific list of secondary safety hazards is generated.

[0024] Based on the severity of the accident types in the secondary safety hazard list, the value of traffic flow heat data in the current time period, and the time period characteristics of the current time, a comprehensive risk score is calculated, and the risk level of the fault propagation path is set according to the preset score range.

[0025] As a further aspect of the present invention, the step of performing hierarchical collaborative control on fault propagation paths based on risk levels, where the risk level is determined to be high:

[0026] Identify a list of affected intersections based on the geographical coordinates of the fault propagation path;

[0027] For each intersection in the intersection list, the average pedestrian crossing time during the same period in history is used as the base value, and the current pedestrian crossing delay coefficient calculated based on real-time traffic flow heat data is added to generate a specific value for the extension of the green light phase for pedestrian crossing and the flashing duration of the yellow warning light.

[0028] Send a call command containing the preset key area boundary frame to the video management platform to drive the surrounding monitoring equipment so that the monitoring screen completely covers the preset key area boundary frame.

[0029] As a further aspect of the present invention, the step of performing hierarchical collaborative control on fault propagation paths based on risk levels, where the risk level is determined to be medium risk:

[0030] Based on the length of the fault propagation path and the list of secondary safety hazards, the nodes with the highest potential for various types of traffic accidents caused by lighting deficiency in the list of secondary safety hazards are marked as key nodes, and standardized text and synthesized speech content containing specific safety guidelines are generated for the key nodes.

[0031] Standardized text and synthesized speech content are simultaneously sent to all smart community broadcast speakers within the preset geofence along the route via a message queue telemetry transmission protocol.

[0032] Based on the location of the key nodes, the safe hovering altitude and lighting angle of the UAV are calculated, and a UAV flight control mission package containing precise coordinates, altitude, lighting angle and brightness parameters is generated. This package is then sent to the UAV airport via a wireless network, controlling the UAV to fly to the coordinate point along the flight path and perform hovering lighting tasks.

[0033] Another objective of this invention is to provide a multi-domain collaborative management and control system for a digital twin platform for urban governance, the system comprising:

[0034] The multi-dimensional data acquisition module is used to collect multi-dimensional data through the Internet of Things for smart streetlights. The multi-dimensional data includes the operating status parameters of the streetlight body, traffic flow thermal data, and spatial correlation data between underground pipelines and streetlight cables.

[0035] The neural network graph construction module is used to construct a neural network graph of streetlights and urban infrastructure based on the multi-dimensional data. The neural network graph of streetlights and urban infrastructure labels the health status parameters of a single streetlight and presents the spatial relationship between streetlights and urban infrastructure, the linkage logic of operating parameters, and the association weights.

[0036] The fault propagation path analysis module is used to monitor and predict faults based on the neural network map of the street light-urban infrastructure and multi-dimensional data, automatically deduce the fault propagation path, identify the preset key areas covered by the fault propagation path, analyze the secondary safety hazards along the fault propagation path, and judge the risk level by combining traffic flow heat data and time period characteristics.

[0037] The hierarchical collaborative management module is used to perform hierarchical collaborative management of fault propagation paths based on risk levels.

[0038] As a further embodiment of the present invention, the neural association map construction module includes:

[0039] The street light node instantiation and state binding module is used in the 3D visualization engine of the digital twin platform to instantiate the physical location of each street light as an independent street light node, and dynamically bind the running status parameters of the street light body to the corresponding street light node, so as to present the health status parameters of the street light node in real time.

[0040] The node connection establishment module is used to establish virtual connection lines between each street light node and the corresponding infrastructure nodes of urban infrastructure located within a preset physical radius of the street light node in the 3D visualization engine, based on the facility location information in the city CIM model. The connection lines define and present the spatial location relationship.

[0041] The association weight quantification and storage module is used to calculate the probability and intensity of the chain change of the state of other infrastructure nodes that have a spatial relationship with the street light node when the state of the street light node changes, based on historical operation data. The probability and intensity are quantified as association weights, and these logical rules are stored in the graph database to construct a neural association graph of street light-urban infrastructure.

[0042] As a further embodiment of the present invention, the fault propagation path analysis module includes:

[0043] The initial fault node determination module is used to determine that a street light node is an initial fault node when the operating status parameters of the street light body of any street light node exceed the predefined normal operating parameter range for more than 5 consecutive sampling cycles.

[0044] The propagation path simulation module is used to perform graph traversal calculations in the street light-urban infrastructure neural network graph, starting from the initial fault node, according to the association weights, along the spatial positional relationship between the street light node and the infrastructure node, to simulate the cascading impact range of the fault and output the fault propagation path composed of continuous nodes.

[0045] The spatial overlay analysis module is used to perform spatial overlay analysis on the geographic coordinate information of the fault propagation path and the GIS layer of the boundary of the urban public activity area, identify the segments where the fault propagation path intersects with and is contained in the regional boundary of the GIS layer, and mark them as preset key areas.

[0046] The secondary safety hazard analysis module is used to analyze the potential for various types of traffic accidents caused by lighting deficiencies by calling traffic flow heat data and combining it with the predefined rule library of functional types of the predefined key areas for each fault propagation path and marked key areas, and generate a specific list of secondary safety hazards.

[0047] The risk level setting module is used to calculate a comprehensive risk score based on the severity of the accident types in the secondary safety hazard list, the value of traffic flow heat data in the current time period, and the time period characteristics of the current time, and to set the risk level of the fault propagation path according to the preset score range.

[0048] The beneficial effects of this invention are:

[0049] By incorporating IoT monitoring and multi-dimensional data acquisition technologies for smart streetlights, this method enables real-time monitoring of the operational status and spatial relationships of streetlights and urban infrastructure. Because smart IoT technology can acquire data from various aspects in real time, it allows for real-time monitoring of the health status of streetlights and other urban infrastructure. In this context, a detailed neural network map of streetlights and urban infrastructure can be established. This map labels the health status parameters of individual streetlights and presents their spatial relationship with urban infrastructure, as well as the linkage logic and correlation weights between their operational parameters. Therefore, this technical feature plays a crucial role in comprehensively understanding the health status of facilities, thereby enabling effective monitoring and prediction of malfunctions.

[0050] Based on the neural network map of streetlights and urban infrastructure and multi-dimensional data, fault monitoring and prediction can automatically deduce the propagation path of faults, identify and analyze the affected key areas and secondary safety hazards along the route. By combining traffic flow heatmap data and time-of-day characteristics to determine risk levels, this system can provide timely risk assessment and tiered control strategies. Therefore, such a detailed risk analysis and tiered control mechanism can comprehensively improve the intelligence level of urban governance, respond to various urban infrastructure faults in a timely and effective manner, thereby effectively preventing secondary safety accidents and enhancing public safety and the efficiency of urban governance. Attached Figure Description

[0051] Figure 1 A flowchart illustrating the multi-domain collaborative management and control method of the urban governance digital twin platform provided in this embodiment of the invention;

[0052] Figure 2 This is a flowchart of a process for monitoring and collecting multi-dimensional data through the Internet of Things for smart streetlights, provided in an embodiment of the present invention.

[0053] Figure 3 This is a flowchart illustrating the construction of a neural network map of streetlights and urban infrastructure, provided in an embodiment of the present invention.

[0054] Figure 4 A flowchart for determining risk levels by combining traffic flow thermal data and time period characteristics is provided in an embodiment of the present invention;

[0055] Figure 5 This is a structural block diagram of a multi-domain collaborative management and control system for an urban governance digital twin platform provided in an embodiment of the present invention;

[0056] Figure 6 This is a structural block diagram of the neural association map construction module provided in an embodiment of the present invention;

[0057] Figure 7 This is a structural block diagram of the fault propagation path analysis module provided in an embodiment of the present invention. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0059] Figure 1 The flowchart of the multi-domain collaborative management and control method of the urban governance digital twin platform provided in the embodiments of the present invention is as follows: Figure 1 As shown, the method includes:

[0060] S100 collects multi-dimensional data through the Internet of Things for intelligent streetlights. The multi-dimensional data includes the operating status parameters of the streetlight body, traffic flow thermal data, and spatial correlation data between underground pipelines and streetlight cables.

[0061] The acquisition of street light operating status parameters relies on multiple types of sensors integrated inside the street light. The sensors are deeply integrated with the street light structure to form a stable acquisition unit. According to the set sampling frequency, the current value, voltage value and real-time brightness value are continuously captured. These parameters are dynamically uploaded through the Internet of Things transmission channel to build a real-time data chain for the street light operating status, which can fully reflect the working status and health level of the street light.

[0062] Traffic flow heat map data is generated based on a cross-platform data interoperability mechanism. It achieves seamless connection with the urban traffic management platform through wireless communication protocols, gathers vehicle and pedestrian flow data from various road sections, and forms heat map data that reflects the regional traffic activity through fusion calculation. This data fusion logic takes into account the flow characteristics of different traffic participants and can accurately present the real-time status of regional traffic.

[0063] The acquisition of spatial correlation data between underground pipelines and street light cables is achieved by using the standardized interface of the unified GIS database for urban infrastructure. Vector layer data containing geographic coordinates, burial depth, and pipeline attributes are extracted. Spatial topology analysis algorithms are used to quantify the relative positional relationship between underground pipelines and street light cables, clarifying the horizontal and vertical distances and intersection relationships between the two, thus transforming the originally implicit spatial correlation into standardized data.

[0064] S200, Based on the multi-dimensional data, construct a neural network map of streetlights and urban infrastructure. The neural network map of streetlights and urban infrastructure labels the health status parameters of a single streetlight and presents the spatial relationship between streetlights and urban infrastructure, the linkage logic of operating parameters, and the association weights.

[0065] In the 3D visualization engine of the digital twin platform, the physical location of each street light is transformed into an independent street light node. The operating status parameters are dynamically bound to the nodes and visualized in real time, giving the originally scattered physical facilities a digital identity and enabling managers to intuitively grasp the health status of individual facilities.

[0066] Based on the facility location information of the city CIM model, street light nodes establish virtual connection lines with urban infrastructure nodes within a preset physical radius, incorporating various previously isolated facilities into a unified spatial association network, clarifying the location association logic between facilities in different fields, and forming a cross-facility topology.

[0067] Based on historical operational data, the probability and intensity of chain reactions in other infrastructure nodes caused by changes in the status of street light nodes are calculated. These correlation characteristics are quantified into correlation weights and stored in the graph database, enabling the graph to have the logical ability to simulate state transmission, and making the linkage between facilities change from implicit to explicit, and from qualitative to quantitative.

[0068] This construction process can adapt to the facility distribution characteristics of different areas of the city. Whether it is the core urban area with dense infrastructure or the suburbs with relatively sparse infrastructure, it can form a correlation map that fits the actual scenario by adjusting the preset physical radius and weight calculation dimension. It covers a variety of urban infrastructure such as traffic signal facilities, underground pipelines, bus station monitoring equipment, etc., and builds a multi-domain correlation network with full coverage.

[0069] S300 performs fault monitoring and prediction based on the neural network map of streetlights and urban infrastructure and multi-dimensional data, automatically infers the fault propagation path, identifies the preset key areas covered by the fault propagation path, analyzes the secondary safety hazards along the fault propagation path, and judges the risk level by combining traffic flow heat data and time period characteristics.

[0070] The initial fault node is determined by monitoring the operating status parameters over multiple consecutive sampling periods. By continuously tracking data and filtering out instantaneous interference factors, the accuracy and reliability of fault determination are ensured, allowing control actions to be initiated based on real faults and avoiding ineffective responses.

[0071] Starting from the initial fault node, and leveraging the association weights and spatial relationships in the neural network graph, the cascading impact range of the simulated fault is calculated through graph traversal. This ensures that the deduced fault propagation path closely matches the actual correlation strength between facilities, accurately representing the trajectory of the fault spreading from a single node to multiple infrastructure areas. Spatially overlaying the geographic coordinates of the fault propagation path with a GIS layer of urban public activity areas allows for a focus on densely populated public activity areas within the fault's impact range, clearly identifying the core targets for control.

[0072] For each transmission path and key area, the system utilizes traffic flow heatmap data and a predefined rule base for regional function types to analyze the potential for various traffic accidents caused by lighting deficiencies. This generates a comprehensive list of secondary safety hazards, allowing administrators to clearly understand the multi-faceted risks that the malfunction may generate. By combining the severity of accident types in the secondary safety hazard list, current-time traffic flow heatmap data, and time-specific characteristics, a comprehensive risk score is generated through quantitative evaluation, and risk levels are categorized based on preset intervals.

[0073] This analysis process can adapt to the diverse characteristics of urban scenarios. Whether it is a main road with heavy traffic, a commercial area with frequent public activities, or an old city with complex facilities, it can achieve accurate analysis of fault risks through data fusion and logical deduction, covering collaborative considerations in multiple fields such as traffic operation, public safety, and infrastructure operation and maintenance.

[0074] S400 implements hierarchical collaborative control over fault propagation paths based on risk levels.

[0075] For high-risk fault propagation paths, the first step is to identify the affected intersections based on their geographical coordinates. These areas, as the core intersections of people and vehicles, are key hubs for multi-domain management and control. By clearly defining the control targets, resources can be precisely focused.

[0076] Based on the delay coefficient derived from the historical pedestrian crossing time and real-time traffic flow heat map data of the intersection, the duration of the green light phase for pedestrian crossing and the duration of the yellow warning light flashing are dynamically adjusted to achieve real-time adaptation of traffic signal control and fault scenarios, and to optimize traffic order in conjunction with the field of traffic management.

[0077] Simultaneously, it sends a command to the video management platform to call the boundary boxes of preset key areas, driving the surrounding monitoring equipment to achieve full coverage, opening up the collaborative link between video surveillance and fault control, and providing visual support for real-time situation control and emergency decision-making.

[0078] For medium-risk fault propagation paths, key nodes are marked by combining fault propagation length and a list of secondary safety hazards. Standardized safety guidance text and synthesized voice are generated focusing on the core locations where risks are most concentrated. These are then distributed to smart community broadcast speakers along the path via message queue telemetry transmission protocol, enabling rapid delivery of safety warnings in the community governance field.

[0079] Based on the location of key nodes, parameters such as the safe hovering altitude and lighting angle of the drone are calculated, a precise flight control task package is generated and sent to the drone airport, and temporary lighting is provided in conjunction with the drone operation and maintenance field to meet the management and control requirements while avoiding resource waste.

[0080] This control system can be adapted to different risk scenarios in the city. High-risk scenarios can cover densely trafficked areas such as the city's core main roads and the surrounding business districts, while medium-risk scenarios can cover areas with relatively flat traffic flow such as suburban community roads and secondary roads. Through the flexible allocation and collaborative operation of resources from multiple fields, precise control can be achieved under different risk levels.

[0081] like Figure 2 As shown, the collection of multi-dimensional data through the Internet of Things (IoT) monitoring of smart streetlights specifically includes:

[0082] S110 uses current sensors, voltage sensors, and brightness sensors deployed inside the streetlight to collect and upload current values, voltage values, and real-time brightness values ​​in real time at a set sampling frequency, and combines them to define the operating status parameters of the streetlight body.

[0083] S120, through a wireless communication protocol, accesses real-time vehicle and pedestrian flow statistics data collected by the urban traffic management platform for each road section, and integrates the vehicle and pedestrian flow statistics data to generate traffic flow heat data characterizing the regional traffic activity.

[0084] ;

[0085] in:

[0086] Traffic flow heatmap data is a quantitative value representing the regional traffic activity, with a value range of [0,1]. The larger the value, the more active the traffic.

[0087] The traffic flow weighting coefficient is a weighting coefficient preset based on urban traffic management rules, reflecting the proportion of traffic flow's contribution to traffic activity. The pedestrian flow weighting coefficient is a weighting coefficient preset based on urban traffic management rules. It reflects the proportion of pedestrian flow's contribution to traffic activity and meets the following requirements. ;

[0088] Real-time traffic flow refers to the number of vehicles passing through a current road section per unit time, as aggregated by the urban traffic management platform. The maximum traffic flow threshold for a road section is the maximum capacity preset based on the road design standards and historical peak data.

[0089] Real-time pedestrian flow refers to the number of pedestrians passing through a current road section per unit time, as aggregated by the urban traffic management platform. The maximum pedestrian flow threshold for a road cross-section is the maximum carrying capacity preset based on the road's sidewalk design standards and historical peak data.

[0090] S130 obtains vector layer data containing geographic coordinates, burial depth, and pipeline attributes by calling the standard data interface of the unified GIS database for urban infrastructure. It then calculates the horizontal distance, vertical distance, and intersection relationship between the underground pipeline network and the street light cable through a spatial topology analysis algorithm, forming spatial association data between the underground pipeline network and the street light cable.

[0091] like Figure 3 As shown, the construction of the neural network map between streetlights and urban infrastructure specifically includes:

[0092] S210, in the 3D visualization engine of the digital twin platform, instantiates the physical location of each street lamp as an independent street lamp node, and dynamically binds the operating status parameters of the street lamp body to the corresponding street lamp node, which is then visualized in real time as the health status parameters of the street lamp node.

[0093] S220, Based on the facility location information in the city CIM model, in the 3D visualization engine, establish a virtual connection line between each street light node and the infrastructure node corresponding to the urban infrastructure within the preset physical radius of the street light node, and define and present the spatial location relationship with the connection line.

[0094] Specifically:

[0095] Extract the physical coordinates (latitude, longitude, and altitude) of all street light nodes from the city CIM model and the preset physical radius threshold (based on the power supply radius of the street lights and the influence range of the infrastructure).

[0096] In the 3D visualization engine of the digital twin platform, urban infrastructure (such as underground pipe networks, traffic lights, monitoring equipment, bus stops, etc.) located within the preset physical radius of each street light node are selected and these infrastructures are instantiated as independent infrastructure nodes.

[0097] Using a 3D drawing algorithm, virtual line segments are drawn between street light nodes and matched infrastructure nodes, and the line segment attributes are bound to the node attributes and stored in the graph database.

[0098] The spatial relationship between streetlights and urban infrastructure (such as the close parallel laying of streetlight cables and underground water pipes) is implicit and cannot be directly observed through physical entities. It is necessary to visualize the abstract relationship through virtual connection lines. Furthermore, the calculation of the probability and intensity of state chain changes requires clear node relationships as a prerequisite. Virtual connection lines define the scope of the associated objects and clarify the reachability between nodes. Subsequent fault propagation path analysis can be directly based on graph traversal of connection lines without the need to repeatedly calculate spatial position relationships.

[0099] S230, based on historical operation data, calculate the probability and intensity of a chain reaction of changes in the states of other infrastructure nodes that have a spatial relationship with the street light node when the street light node changes state. Quantify the probability and intensity as association weights and store these logical rules in the graph database to construct a neural association graph of street light-urban infrastructure.

[0100] ;

[0101] in:

[0102] Streetlight nodes With infrastructure nodes The association weight quantifies the overall strength of the chain change between the two states, and the value range is [0,1]. The larger the value, the stronger the association and the higher the probability of fault propagation.

[0103] The probability weighting coefficient is a preset coefficient calibrated based on historical data, used to balance the contribution ratio of probability and intensity. The probability of a chain reaction of states, for the street light node. When a state change occurs, infrastructure nodes The probability of synchronous state changes. ; The number of historical chain changes refers to the number of street light nodes in historical operation data. State changes and infrastructure nodes The total number of synchronous state changes; Streetlight nodes The total number of historical state changes refers to the number of street light nodes in the historical operation data. The total number of times the status changes occurred (such as current exceeding the range, abnormal brightness);

[0104] The intensity of state chain changes refers to the street light node. After the state change, the infrastructure nodes The standardized value of the magnitude of the state change. ; The average state change magnitude refers to the average state change magnitude of infrastructure nodes during a historical chain of change events. The average change in operating parameters relative to normal thresholds; For nodes Maximum permissible range of change refers to the range based on infrastructure. The design standard pre-sets the maximum range of safety variations.

[0105] like Figure 4 As shown, the analysis of secondary safety hazards along the fault propagation path, combined with traffic flow heatmap data and time-period characteristics to determine the risk level, specifically includes:

[0106] S310: When the operating status parameters of any street light node are monitored and the values ​​of the street light body exceed the predefined normal operating parameter range for more than 5 consecutive sampling cycles, the street light node is determined to be an initial fault node.

[0107] Transient interference may occur during street light operation. Single or a few sampling periods exceeding the range are mostly accidental events, not real faults. A threshold of 5 consecutive sampling periods can effectively eliminate this type of interference. The core fault type of street lights is a persistent fault, which will not recover instantly once it occurs, consistent with the characteristics of abnormality in multiple consecutive sampling periods.

[0108] In the field of IoT device fault monitoring, the continuous sampling period threshold is a mature anti-interference design method. The threshold is usually set to 3-10 periods. In this embodiment, 5 periods are used to balance sensitivity and anti-interference capability.

[0109] S320, starting from the initial fault node, in the street light-urban infrastructure neural network graph, according to the association weight, the graph traversal calculation is performed along the spatial positional relationship between the street light node and the infrastructure node to simulate the cascading impact range of the fault and output the fault propagation path composed of continuous nodes.

[0110] Specifically:

[0111] 1. Identify the initial fault node Set the association weight threshold (Filtering weakly related nodes), path length threshold (Avoid excessive path extension);

[0112] 2. Based on the neural network graph of streetlights and urban infrastructure, generate an adjacency matrix between nodes. ,in ( (when), otherwise ;

[0113] 3. Employ the weighted breadth-first search (BFS) algorithm to... Starting from the first point, prioritize traversing the associated weights. The largest adjacent node records all nodes along the traversal path;

[0114] 4. Remove items with a length exceeding [a certain value]. The path consists of non-contiguous nodes, and the continuous path consisting of the initial fault node → adjacent node → next adjacent node is retained.

[0115] 5. Sort the filtered paths in descending order of total weight (the higher the total weight, the greater the possibility of fault propagation), and output the top 3 paths as the core control objects.

[0116] ;

[0117] in:

[0118] For the first The total weight of each fault propagation path represents the fault propagation intensity of that path; the larger the value, the more priority it needs to be controlled. For the first The total number of nodes along a path refers to the total number of street light nodes and infrastructure nodes included in the path. For the first The first path The node and the first The association weights of each node are extracted from the adjacency matrix and must satisfy the following conditions: ≥ .

[0119] S330, Spatial overlay analysis is performed on the geographic coordinate information of the fault propagation path and the GIS layer of the urban public activity area boundary to identify the segments where the fault propagation path intersects with and is included in the area boundary of the GIS layer, and these segments are marked as preset key areas.

[0120] S340, for each fault propagation path and marked preset key area, calls traffic flow heat data, combines the preset key area's functional type predefined rule library, simulates and analyzes the potential possibility of various types of traffic accidents caused by lighting deficiency, and generates a specific list of secondary safety hazards.

[0121] ;

[0122] in:

[0123] To assess the potential for secondary safety hazards, the probability of a certain type of traffic accident caused by lighting deficiency is quantified, with a value range of [0,1].

[0124] This is the traffic flow heat map weighting coefficient, reflecting the impact of traffic activity on the probability of accidents;

[0125] The regional functional weighting coefficient is a coefficient based on the preset key regional functional types. The regional functional risk coefficient is a regional functional risk value defined in the preset rule base. The denser the functions, the higher the risk.

[0126] The lighting deficiency impact coefficient reflects the direct impact of lighting deficiency on accidents; The degree of lighting deficiency refers to the ratio of the actual brightness value of a street light node to the normal brightness threshold.

[0127] The historical accident weighting coefficient is a preset coefficient that reflects the reference value of historical data for current risks. Historical accident rate refers to the ratio of the number of similar accidents occurring in the area under the same lighting deficiency conditions to the total number of days in the past year.

[0128] S350, calculate the comprehensive risk score based on the severity of the accident type in the secondary safety hazard list, the value of traffic flow heat data in the current time period, and the time period characteristics of the current time, and set the risk level of the fault propagation path according to the preset score range.

[0129] Time period characteristics are time interval attributes divided according to urban traffic flow, intensity of public activities, and population density. They are primarily used to reflect the risk amplification effect of fault propagation under different time dimensions and are a key adjustment factor in the calculation of comprehensive risk scores.

[0130] The time periods are categorized into three types: peak hours, leisure hours, and off-peak hours at night. Examples of peak hours include morning rush hour (7:00-9:00), evening rush hour (17:00-19:00), and peak hours in commercial areas on holidays (10:00-20:00). The core characteristics are high traffic volume, dense crowds, and frequent public activities. Secondary accidents caused by malfunctions have a wide impact and cause significant losses. Examples of leisure hours include off-peak weekdays (9:00-17:00) and weekend non-commercial areas (9:00-10:00, 17:00-20:00). The core characteristics are moderate traffic volume, dispersed population distribution, and moderate public activities. The risk of secondary accidents is relatively controllable. Examples of off-peak hours at night include 22:00-6:00 the next day (non-commercial areas). The core characteristics are extremely low traffic volume and sparse crowds. The impact of malfunctions is small, but the lack of lighting may lead to low visibility of accidents.

[0131] Through time period characteristic coefficients Adjust the overall risk score to make the risk level assessment more closely match the actual scenario.

[0132] ;

[0133] in:

[0134] The overall risk score quantifies the risk of the fault propagation path and is used to classify risk levels. ≥8 indicates high risk, 5≤ <8 indicates medium risk);

[0135] This is the weighting coefficient for the severity of the accident, reflecting the core impact of the accident type on risk; This is the severity coefficient of the accident type, which is a coefficient defined in the preset rule base. The higher the level, the larger the coefficient.

[0136] This is the traffic flow heat map weighting coefficient, reflecting the impact of current traffic activity on risk; The traffic flow heat standardization value is the standardized result of the traffic flow heat data H. The value range is [0, 10].

[0137] The time period characteristic weighting coefficient reflects the moderating effect of time period attributes on risk; This is a time-period characteristic coefficient, a preset value based on the time period type (peak period). =10. Leisure Time =5. Nighttime off-peak period =3).

[0138] In this embodiment, based on risk level, hierarchical collaborative control is performed on fault propagation paths of different risk levels. When the risk level is determined to be high risk:

[0139] Identify a list of affected intersections based on the geographical coordinates of the fault propagation path;

[0140] For each intersection in the intersection list, the average pedestrian crossing time during the same period in history is used as the base value, and the current pedestrian crossing delay coefficient calculated based on real-time traffic flow heat data is added to generate a specific value for the extension of the green light phase for pedestrian crossing and the flashing duration of the yellow warning light.

[0141] Extended green light phase duration for pedestrians :

[0142] ;

[0143] Yellow warning light flashing duration :

[0144] ;

[0145] in:

[0146] Extending the green light phase for pedestrians refers to the additional time required on top of the original green light duration. The average pedestrian crossing time for the same period in history refers to the average time it takes for pedestrians to cross the street at this intersection during the same period over the past three months. The current pedestrian crossing delay coefficient is a coefficient calculated based on real-time traffic flow heatmap data. The calculation formula is as follows: ;

[0147] The duration of the yellow warning light flashing refers to the length of time the yellow light flashes after the green light ends, ensuring that vehicles stop smoothly and pedestrians cross the street safely; This is the percentage of yellow light duration, set based on traffic signal control regulations (usually 30%-50% of the extended green light duration).

[0148] Send a call command containing the preset key area boundary frame to the video management platform to drive the surrounding monitoring equipment so that the monitoring screen completely covers the preset key area boundary frame.

[0149] In this embodiment, based on risk level, hierarchical collaborative control is performed on fault propagation paths of different risk levels. When the risk level is determined to be medium risk:

[0150] Based on the length of the fault propagation path and the list of secondary safety hazards, the nodes with the highest potential for various types of traffic accidents caused by lighting deficiency in the list of secondary safety hazards are marked as key nodes, and standardized text and synthesized speech content containing specific safety guidelines are generated for the key nodes.

[0151] Standardized text and synthesized speech content are simultaneously sent to all smart community broadcast speakers within the preset geofence along the route via a message queue telemetry transmission protocol.

[0152] Based on the location of the key nodes, the safe hovering altitude and lighting angle of the UAV are calculated, and a UAV flight control mission package containing precise coordinates, altitude, lighting angle and brightness parameters is generated. This package is then sent to the UAV airport via a wireless network, controlling the UAV to fly to the coordinate point along the flight path and perform hovering lighting tasks.

[0153] For high-risk level control:

[0154] The list of affected intersections is identified because intersections are core areas where people and vehicles converge. Lack of lighting can easily lead to serious accidents such as collisions and congestion, making them a high-risk control focus. The expected effect is to accurately identify the core control targets, avoid an overly large control area or omission of key areas, and the core purpose is to focus on high-risk locations and improve the targeting of control.

[0155] The extension of the green light phase for pedestrian crossings, combined with flashing yellow warning lights, is implemented because during high-risk periods, pedestrians and vehicles are densely packed, and insufficient lighting obstructs visibility. The extended crossing time and flashing yellow lights remind drivers to be cautious and avoid the area. The expected effect is that pedestrians have sufficient time to cross the street safely, vehicles slow down smoothly, and the probability of collisions is reduced. The core objective is to directly reduce the risk of secondary accidents at intersections and protect people's lives.

[0156] The purpose of deploying surrounding monitoring equipment to cover pre-defined key areas is to address the possibility that high-risk faults may trigger a chain reaction, necessitating real-time monitoring of the situation. The expected outcome is that maintenance personnel can remotely view the on-site situation and adjust control strategies in a timely manner. The core objective is to improve the timeliness and flexibility of emergency response and prevent the impact of faults from escalating.

[0157] For medium-risk level control:

[0158] The reason for implementing the marking of key nodes and generating safety guidance text and voice is that medium-risk faults have a small impact range and do not require full-path control. The focus is on controlling the nodes with the highest probability of secondary hazards. The dual guidance of voice and text can cover different groups of people. The expected effect is that people in the vicinity will quickly know the safety risks and take the initiative to avoid the hazard area. The core purpose is to reduce the risk of personnel contact through warnings and realize the transformation from passive control to active avoidance.

[0159] The MQTT protocol is used to send instructions to smart community loudspeakers. The reason for this implementation is that the MQTT protocol supports low-bandwidth, highly reliable message transmission, which is compatible with the IoT communication needs of the community loudspeakers. Furthermore, the broadcast coverage matches the preset geofence, allowing for precise reach to affected individuals. The expected effect is that the instructions are quickly and completely delivered to people along the route, with a response delay of ≤3 seconds. The core objective is to improve the coverage efficiency and accuracy of safety instructions and reduce communication costs. Drone hovering lighting is implemented because medium-risk faults do not require long-term emergency lighting. Drones can be quickly deployed and can flexibly adjust the lighting position and angle, making it lower in cost and more efficient than temporarily setting up lights. The expected effect is to restore temporary lighting in key areas, compensating for lighting loss caused by street light failures. The core objective is to locally improve lighting conditions, reduce the risk of nighttime accidents, and control emergency maintenance costs.

[0160] High-risk management focuses on mandatory intervention and real-time monitoring, targeting key areas such as intersections to minimize the risk of serious accidents. Medium-risk management focuses on precise warnings and temporary backup measures, balancing management effectiveness and cost. Both systems operate on the logic of "fault propagation path → secondary hazards → risk level," achieving tiered, categorized, precise, and efficient collaborative management. The ultimate goal is to ensure the safe operation of urban infrastructure and the safety of public travel.

[0161] Figure 5 This is a structural block diagram of the multi-domain collaborative management and control system of the urban governance digital twin platform provided in an embodiment of the present invention, as shown in the figure. Figure 5 As shown, the system includes:

[0162] The multi-dimensional data acquisition module 100 is used to collect multi-dimensional data through the Internet of Things for monitoring smart streetlights. The multi-dimensional data includes the operating status parameters of the streetlight body, traffic flow thermal data, and spatial correlation data between underground pipelines and streetlight cables.

[0163] The neural network graph construction module 200 is used to construct a neural network graph of streetlights and urban infrastructure based on the multi-dimensional data. The neural network graph of streetlights and urban infrastructure labels the health status parameters of a single streetlight and presents the spatial position relationship between streetlights and urban infrastructure, the linkage logic of operating parameters, and the association weights.

[0164] The fault propagation path analysis module 300 is used to monitor and predict faults based on the neural network map of the street light-urban infrastructure and multi-dimensional data, automatically deduce the fault propagation path, identify the preset key areas covered by the fault propagation path, analyze the secondary safety hazards along the fault propagation path, and judge the risk level by combining traffic flow heat data and time period characteristics.

[0165] The hierarchical collaborative management module 400 is used to perform hierarchical collaborative management of fault propagation paths based on risk levels.

[0166] like Figure 6 As shown, the neural network mapping construction module includes:

[0167] The street light node instantiation and state binding module 210 is used to instantiate the physical position of each street light as an independent street light node in the 3D visualization engine of the digital twin platform, and dynamically bind the running state parameters of the street light body to the corresponding street light node, so as to present the health status parameters of the street light node in real time.

[0168] The node connection establishment module 220 is used to establish a virtual connection line between each street light node and the infrastructure node corresponding to the urban infrastructure within the preset physical radius of the street light node in the three-dimensional visualization engine, based on the facility location information in the urban CIM model, so as to define and present the spatial location relationship.

[0169] The association weight quantification and storage module 230 is used to calculate the probability and intensity of the chain change of the state of other infrastructure nodes that have a spatial relationship with the street light node when the state of the street light node changes based on historical operation data. The probability and intensity are quantified as association weights, and these logical rules are stored in the graph database to construct a neural association graph of street light-urban infrastructure.

[0170] like Figure 7 As shown, the fault propagation path analysis module includes:

[0171] The initial fault node determination module 310 is used to determine that a street light node is an initial fault node when the operating status parameters of the street light body of any street light node exceed the predefined normal operating parameter range for more than 5 consecutive sampling cycles.

[0172] The propagation path simulation module 320 is used to perform graph traversal calculations in the street light-urban infrastructure neural network graph, starting from the initial fault node, according to the association weight along the spatial positional relationship between the street light node and the infrastructure node, to simulate the cascading impact range of the fault and output the fault propagation path composed of continuous nodes.

[0173] The spatial overlay analysis module 330 is used to perform spatial overlay analysis on the geographic coordinate information of the fault propagation path and the GIS layer of the boundary of the urban public activity area, identify the segments where the fault propagation path intersects with and is included in the regional boundary of the GIS layer, and mark them as preset key areas.

[0174] The secondary safety hazard analysis module 340 is used to analyze the potential for various types of traffic accidents caused by lighting deficiencies by calling traffic flow heat data and combining it with the predefined rule library of functional types of the predefined key areas for each fault propagation path and marked key areas, and to generate a specific list of secondary safety hazards.

[0175] The risk level setting module 350 is used to calculate a comprehensive risk score based on the severity of the accident type in the secondary safety hazard list, the value of traffic flow heat data in the current time period, and the time period characteristics of the current time, and to set the risk level of the fault propagation path according to the preset score range.

[0176] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0178] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-domain collaborative management and control method for a digital twin platform for urban governance, characterized in that: The method includes: The smart street light IoT monitoring system collects multi-dimensional data, including the operating status parameters of the street light itself, traffic flow thermal data, and spatial correlation data between underground pipelines and street light cables. Based on the multi-dimensional data, a neural network map of streetlights and urban infrastructure is constructed. The neural network map of streetlights and urban infrastructure labels the health status parameters of a single streetlight and presents the spatial relationship between streetlights and urban infrastructure, the linkage logic of operating parameters, and the association weights. Based on the neural network map of streetlights and urban infrastructure and multi-dimensional data, fault monitoring and prediction are performed, and fault propagation paths are automatically deduced. Preset key areas covered by the fault propagation paths are identified, secondary safety hazards along the fault propagation paths are analyzed, and risk levels are judged by combining traffic flow heat data and time period characteristics. Based on risk levels, hierarchical collaborative control is implemented for fault propagation paths of different risk levels.

2. The method according to claim 1, characterized in that, The collection of multi-dimensional data through the Internet of Things (IoT) monitoring of smart streetlights specifically includes: By deploying current sensors, voltage sensors, and brightness sensors inside the streetlights, the current values, voltage values, and real-time brightness values ​​are collected and uploaded in real time at a set sampling frequency, and combined to define the operating status parameters of the streetlight body. Through wireless communication protocols, the system accesses real-time vehicle and pedestrian traffic statistics data collected by the urban traffic management platform for each road section, and integrates and calculates the vehicle and pedestrian traffic statistics data to generate traffic flow heatmap data characterizing the regional traffic activity. By calling the standard data interface of the unified GIS database for urban infrastructure, vector layer data containing geographic coordinates, burial depth, and pipeline attributes are obtained. Then, through spatial topology analysis algorithms, the horizontal distance, vertical distance, and intersection relationship between underground pipelines and street light cables are calculated to form spatial association data between underground pipelines and street light cables.

3. The method according to claim 2, characterized in that, The construction of the neural network map between streetlights and urban infrastructure specifically includes: In the 3D visualization engine of the digital twin platform, the physical location of each street lamp is instantiated as an independent street lamp node, and the operating status parameters of the street lamp body are dynamically bound to the corresponding street lamp node, which is then visualized in real time as the health status parameters of the street lamp node. Based on the facility location information in the city CIM model, in the 3D visualization engine, a virtual connection line is established between each street light node and the corresponding infrastructure node of the urban infrastructure located within the preset physical radius of the street light node, and the spatial location relationship is defined and presented by the connection line. Based on historical operational data, the probability and intensity of a chain reaction of state changes in other infrastructure nodes that are spatially related to the street light node when the street light node undergoes a state change are calculated. The probability and intensity are quantified as association weights, and these logical rules are stored in a graph database to construct a neural network graph of street lights and urban infrastructure.

4. The method according to claim 3, characterized in that, The analysis of secondary safety hazards along the fault propagation path, combined with traffic flow heatmap data and time-period characteristics, determines the risk level, specifically including: If the operating status parameters of any street light node exceed the predefined normal operating parameter range for more than 5 consecutive sampling cycles, then the street light node is determined to be an initial fault node. Starting from the initial fault node, in the street light-urban infrastructure neural network graph, graph traversal calculation is performed along the spatial positional relationship between the street light node and the infrastructure node according to the association weight, to simulate the cascading impact range of the fault and output the fault propagation path composed of continuous nodes. The geographic coordinates of the fault propagation path are spatially overlaid with the GIS layer of the urban public activity area boundary to identify the segments where the fault propagation path intersects with and is contained within the area boundary in the GIS layer, and these segments are marked as preset key areas. For each fault propagation path and marked key area, traffic flow heat data is called up, and combined with the predefined rule library of functional types of the key area, the potential possibility of various types of traffic accidents caused by lack of lighting is simulated and analyzed, and a specific list of secondary safety hazards is generated. Based on the severity of the accident types in the secondary safety hazard list, the value of traffic flow heat data in the current time period, and the time period characteristics of the current time, a comprehensive risk score is calculated, and the risk level of the fault propagation path is set according to the preset score range.

5. The method according to claim 4, characterized in that, The system implements tiered collaborative control over fault propagation paths based on risk levels. When the risk level is determined to be high risk: Identify a list of affected intersections based on the geographical coordinates of the fault propagation path; For each intersection in the intersection list, the average pedestrian crossing time during the same period in history is used as the base value, and the current pedestrian crossing delay coefficient calculated based on real-time traffic flow heat data is added to generate a specific value for the extension of the green light phase for pedestrian crossing and the flashing duration of the yellow warning light. Send a call command containing the preset key area boundary frame to the video management platform to drive the surrounding monitoring equipment so that the monitoring screen completely covers the preset key area boundary frame.

6. The method according to claim 4, characterized in that, The system implements tiered collaborative control over fault propagation paths based on risk levels. When the risk level is determined to be medium risk: Based on the length of the fault propagation path and the list of secondary safety hazards, the nodes with the highest potential for various types of traffic accidents caused by lighting deficiency in the list of secondary safety hazards are marked as key nodes, and standardized text and synthesized speech content containing specific safety guidelines are generated for the key nodes. Standardized text and synthesized speech content are simultaneously sent to all smart community broadcast speakers within the preset geofence along the route via a message queue telemetry transmission protocol. Based on the location of the key nodes, the safe hovering altitude and lighting angle of the UAV are calculated, and a UAV flight control mission package containing precise coordinates, altitude, lighting angle and brightness parameters is generated. This package is then sent to the UAV airport via a wireless network, controlling the UAV to fly to the coordinate point along the flight path and perform hovering lighting tasks.

7. A multi-domain collaborative management and control system for a digital twin platform for urban governance, characterized in that: The system includes: The multi-dimensional data acquisition module is used to collect multi-dimensional data through the Internet of Things for smart streetlights. The multi-dimensional data includes the operating status parameters of the streetlight body, traffic flow thermal data, and spatial correlation data between underground pipelines and streetlight cables. The neural network graph construction module is used to construct a neural network graph of streetlights and urban infrastructure based on the multi-dimensional data. The neural network graph of streetlights and urban infrastructure labels the health status parameters of a single streetlight and presents the spatial relationship between streetlights and urban infrastructure, the linkage logic of operating parameters, and the association weights. The fault propagation path analysis module is used to monitor and predict faults based on the neural network map of the street light-urban infrastructure and multi-dimensional data, automatically deduce the fault propagation path, identify the preset key areas covered by the fault propagation path, analyze the secondary safety hazards along the fault propagation path, and judge the risk level by combining traffic flow heat data and time period characteristics. The hierarchical collaborative management module is used to perform hierarchical collaborative management of fault propagation paths based on risk levels.

8. The system according to claim 7, characterized in that, The neural network mapping construction module includes: The street light node instantiation and state binding module is used in the 3D visualization engine of the digital twin platform to instantiate the physical location of each street light as an independent street light node, and dynamically bind the running status parameters of the street light body to the corresponding street light node, so as to present the health status parameters of the street light node in real time. The node connection establishment module is used to establish virtual connection lines between each street light node and the corresponding infrastructure nodes of urban infrastructure located within a preset physical radius of the street light node in the 3D visualization engine, based on the facility location information in the city CIM model. The connection lines define and present the spatial location relationship. The association weight quantification and storage module is used to calculate the probability and intensity of the chain change of the state of other infrastructure nodes that have a spatial relationship with the street light node when the state of the street light node changes, based on historical operation data. The probability and intensity are quantified as association weights, and these logical rules are stored in the graph database to construct a neural association graph of street light-urban infrastructure.

9. The system according to claim 8, characterized in that, The fault propagation path analysis module includes: The initial fault node determination module is used to determine that a street light node is an initial fault node when the operating status parameters of the street light body of any street light node exceed the predefined normal operating parameter range for more than 5 consecutive sampling cycles. The propagation path simulation module is used to perform graph traversal calculations in the street light-urban infrastructure neural network graph, starting from the initial fault node, according to the association weights, along the spatial positional relationship between the street light node and the infrastructure node, to simulate the cascading impact range of the fault and output the fault propagation path composed of continuous nodes. The spatial overlay analysis module is used to perform spatial overlay analysis on the geographic coordinate information of the fault propagation path and the GIS layer of the boundary of the urban public activity area, identify the segments where the fault propagation path intersects with and is contained in the regional boundary of the GIS layer, and mark them as preset key areas. The secondary safety hazard analysis module is used to analyze the potential for various types of traffic accidents caused by lighting deficiencies by calling traffic flow heat data and combining it with the predefined rule library of functional types of the predefined key areas for each fault propagation path and marked key areas, and generate a specific list of secondary safety hazards. The risk level setting module is used to calculate a comprehensive risk score based on the severity of the accident types in the secondary safety hazard list, the value of traffic flow heat data in the current time period, and the time period characteristics of the current time, and to set the risk level of the fault propagation path according to the preset score range.

Images