Smart city operation management system and method

Abstract

The present application relates to the technical field of city management, in particular to a smart city operation management system and method, comprising a partition model establishing module, a partition regulation module, a situation obtaining module, a partition matching module, a real-time judgment module, a decision making module, a decision executing module, a decision data storage module and a quick decision pairing module, which can realize accurate and rapid response and collaborative scheduling for sudden traffic events by partition modeling and dynamic correlation analysis of the traffic network, combined with quick matching of historical schemes, effectively improving the overall resilience and operation efficiency of regional traffic.

Description

Technical Field

[0001] This invention relates to the field of urban management technology, and in particular to a smart city operation management system and method. Background Technology

[0002] With the deep integration of IoT, big data and AI technologies, smart city construction has moved from digitalization in a single field to a new stage of comprehensive operation and management across departments and systems. Currently, typical smart city operation and management systems have been widely used in traffic management, public security, environmental monitoring and energy dispatch.

[0003] Existing smart city operation and management systems often fall short when faced with comprehensive emergencies requiring rapid multi-departmental coordination and dynamic resource allocation (such as major event security, extreme weather response, and public safety incidents). The systems are unable to perform global perception, correlation analysis, simulation and deduction, and collaborative command, thus making it difficult to achieve optimal allocation of urban resources and fundamentally improve overall operational efficiency and resilience. Summary of the Invention

[0004] The purpose of this invention is to provide a smart city operation management system and method, which can achieve accurate and rapid response and coordinated scheduling for sudden traffic events by performing zonal modeling and dynamic correlation analysis of the traffic network and combining historical schemes for rapid matching, thereby effectively improving the overall resilience and operational efficiency of regional traffic.

[0005] To achieve the above objectives, the present invention provides a smart city operation and management system, including a zoning model establishment module, a zoning control module, a situation acquisition module, a zoning matching module, a real-time judgment module, a decision generation module, a decision execution module, a decision data storage module, and a rapid decision pairing module; The partition model establishment module interacts with the partition control module, the situation acquisition module, the partition matching module, the real-time judgment module, the decision generation module, the decision data storage module, the fast decision pairing module, and the decision execution module via a system bus. The partition control module is connected to the decision execution module, the situation acquisition module is connected to the partition matching module, the partition matching module is connected to the real-time judgment module, the real-time judgment module is connected to the decision generation module, the decision data storage module, and the fast decision pairing module, the decision generation module is connected to the decision data storage module and the decision execution module, the decision data storage module is connected to the fast decision pairing module, the fast decision pairing module is connected to the decision execution module, and the decision execution module is connected to the partition control module. The partition model building module is used to construct multiple internally closed-loop and mutually independent sub-class traffic network models based on the actual road, traffic light and personnel configuration data of the specified area, and combine these sub-class models into an overall traffic network model of the area according to the actual connection relationship. The zonal control module is used to receive control instructions and, according to the control instructions, independently control the traffic lights and dispatchers of each sub-category of traffic network models in the overall traffic network model of the area. The situation acquisition module is used to collect traffic handling information, including traffic accidents and emergencies, in real time. The partition matching module is used to obtain the processing information collected by the module according to the situation, and determine one or more of the sub-class traffic network models that have experienced an event or are directly affected by the event. The real-time judgment module is used to analyze the dynamic correlation between each of the sub-class traffic network models, and according to the result of the partition matching module, retrieve the real-time traffic data of the affected sub-class traffic network models and other sub-class traffic network models whose correlation is higher than a preset threshold. The decision generation module is used to generate a comprehensive dispatching scheme, including traffic light timing adjustment and dispatcher reassignment, for the affected sub-class traffic network models and their highly correlated related models, based on the real-time traffic data obtained by the real-time judgment module. The decision data storage module is used to store the executed integrated scheduling scheme and the real-time traffic data and correlation analysis results used in its generation process as historical scheme data, and classify and store them according to the sub-category of traffic network model to which they belong. The rapid decision matching module is used to filter similar historical scheme data from the decision data storage module based on the current real-time traffic data obtained by the real-time judgment module. When the correlation between the scheme and the current situation is higher than the set standard, the corresponding historical comprehensive scheduling scheme is directly output as the rapid decision scheme. The decision execution module is used to convert the rapid decision scheme output by the rapid decision pairing module or the comprehensive scheduling scheme generated by the decision generation module into a control instruction, and send the control instruction to the partition control module.

[0006] The partition model establishment module includes a model construction submodule and a network integration submodule, and the model construction submodule is connected to the network integration submodule. The model building submodule is used to build each independent traffic network model of the sub-category based on road, traffic light and personnel configuration data; The network integration submodule is used to integrate multiple sub-class traffic network models into the overall regional traffic network model based on the actual road connection relationships between the sub-class traffic network models.

[0007] The real-time judgment module includes a correlation analysis submodule and a data retrieval submodule. The correlation analysis submodule is connected to the partition matching module and the data retrieval submodule. The correlation analysis submodule is used to dynamically analyze and update the correlation between the various traffic network models based on historical traffic flow data and real-time connection status. The data retrieval submodule is used to retrieve real-time traffic data of the affected model and its highly correlated model based on the results of the partition matching module and the correlation information provided by the correlation analysis submodule.

[0008] The decision generation module includes a scheme calculation submodule and an effect evaluation submodule. The scheme calculation submodule is connected to the real-time judgment module and the effect evaluation submodule. The scheme calculation submodule is used to calculate and generate a preliminary scheduling scheme based on the real-time traffic data using a traffic flow optimization algorithm. The effect evaluation submodule is used to predict and evaluate the effect of the preliminary scheduling scheme through a traffic simulation model, and output the scheme that meets the evaluation requirements as the comprehensive scheduling scheme.

[0009] The fast decision-making matching module includes a feature matching submodule and an association verification submodule. The feature matching submodule is connected to the real-time judgment module and the decision data storage module, respectively, and the association verification submodule is connected to the feature matching submodule. The feature matching submodule is used to extract the feature vector of the current scenario and retrieve the historical scheme data with the highest feature similarity from the decision data storage module; The association verification submodule is used to perform in-depth analysis on the retrieved historical solution data, analyze the key differences between it and the current scenario and the causal chain of solution reproduction, and make a final judgment on whether to adopt it.

[0010] The decision data storage module includes a data archiving submodule and a classification index submodule. The data archiving submodule is connected to the decision generation module and the real-time judgment module, and is also connected to the classification index submodule. The classification index submodule is connected to the fast decision matching module. The data archiving submodule is used to package the data related to each decision execution and add timestamps, model identifiers and event tags; The classification index submodule is used to create an index for archived data based on the sub-category traffic network model identifier, event type, and key feature values ​​to support fast retrieval.

[0011] The decision execution module includes an instruction conversion submodule and an instruction distribution submodule. The instruction conversion submodule is connected to the decision generation module and the fast decision matching module, and is also connected to the instruction distribution submodule. The instruction distribution submodule is connected to the partition control module. The instruction conversion submodule is used to format the input scheduling scheme into a standardized instruction set that can be recognized by the partition control module; The instruction distribution submodule is used to accurately distribute the instruction to the partition control module interface corresponding to the target sub-class traffic network model, based on the instruction content.

[0012] The partition control module includes an instruction parsing submodule and an execution feedback submodule. The instruction parsing submodule is connected to the decision execution module and the execution feedback submodule. The instruction parsing submodule is used to receive and parse the control instructions from the decision execution module to determine the specific traffic light control parameters and the dispatcher's action instructions; The execution feedback submodule is used to send instructions to specific traffic signal controllers and personnel terminals, and to collect the execution status and results of the instructions to form feedback information.

[0013] The feature matching submodule includes a feature extraction unit and an index retrieval unit. The feature extraction unit is connected to the real-time judgment module and the index retrieval unit. The index retrieval unit is connected to the decision data storage module. The feature extraction unit is used to standardize the real-time traffic data and event information into a multi-dimensional feature vector; The index retrieval unit is used to quickly screen the historical scheme data using scenario coding, calculate the similarity between the screened data and the current feature vector, and output a similarity ranking list.

[0014] The smart city operation and management method, employing the aforementioned smart city operation and management system, includes the following steps. The zoning model building module constructs a sub-category of traffic network models containing multiple internal closed loops based on urban construction data of a specified area, and integrates them into an overall traffic network model for the area. When a special situation occurs in a designated area, the partition matching module obtains the processing information collected in real time by the module according to the situation, and determines one or more sub-class traffic network models directly associated with the event; The real-time judgment module analyzes and retrieves real-time traffic data of the affected sub-category traffic network model and other sub-category traffic network models whose dynamic correlation with it is higher than a preset threshold, based on the results of the partition matching module. The rapid decision matching module retrieves similar historical plan data from the decision data storage module based on the real-time traffic data obtained by the real-time judgment module. If there is historical plan data with a correlation higher than the set standard, the corresponding historical comprehensive scheduling plan is output as the rapid decision plan. If no rapid decision-making solution is output, the decision generation module generates a new comprehensive scheduling solution based on the real-time traffic data obtained by the real-time judgment module for the affected minor traffic network model and its highly correlated related models. The decision execution module converts the comprehensive scheduling scheme generated by the decision generation module or the rapid decision matching module into specific control instructions and sends them to the partition control module. The zone control module receives and executes control commands, and performs zoned scheduling of traffic lights and dispatchers for the traffic network model specified in the command.

[0015] The smart city operation management system and method of the present invention, when the situation acquisition module senses a traffic accident or emergency in the area, the partition matching module quickly locates the event to one or more specific sub-class traffic network models. Subsequently, the real-time judgment module not only retrieves the real-time traffic conditions of the incident model but also dynamically calculates and retrieves real-time data from other closely related models. Next, the rapid decision matching module attempts to find similar scenario handling solutions from the historical database. If a highly correlated solution is found, it is directly adopted as the rapid decision. If no solution is found, the decision generation module calculates and generates a new optimized solution based on real-time data. Finally, regardless of the solution, the decision execution module converts it into an executable instruction and sends it to the partition control module to accurately and collaboratively control the traffic lights and on-site dispatchers in the target area. This achieves accurate and rapid response and collaborative dispatching of sudden traffic events by performing partition modeling and dynamic correlation analysis of the traffic network, combined with rapid matching of historical solutions, effectively improving the overall resilience and operational efficiency of regional traffic. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0017] Figure 1 This is a schematic diagram of the overall structure of the smart city operation and management system of the present invention.

[0018] Figure 2This is a schematic diagram of the real-time judgment module of the present invention.

[0019] Figure 3 This is a schematic diagram of the decision generation module of the present invention.

[0020] Figure 4 This is a schematic diagram of the rapid decision-making and matching module of the present invention.

[0021] Figure 5 This is a schematic diagram of the decision data storage module of the present invention.

[0022] Figure 6 This is a schematic diagram of the decision execution module of the present invention.

[0023] Figure 7 This is a schematic diagram of the partition control module of the present invention.

[0024] Figure 8 This is a schematic diagram of the feature matching submodule of the present invention.

[0025] Figure 9 This is a flowchart of the smart city operation and management method of the present invention.

[0026] In the diagram: 1-Partition model establishment module, 2-Partition control module, 3-Situation acquisition module, 4-Partition matching module, 5-Real-time judgment module, 6-Decision generation module, 7-Decision execution module, 8-Decision data storage module, 9-Fast decision pairing module, 11-Model construction sub-module, 12-Network integration sub-module, 21-Instruction parsing sub-module, 22-Execution feedback sub-module, 51-Correlation analysis sub-module, 52-Data retrieval sub-module, 61-Solution calculation sub-module, 62-Effect evaluation sub-module, 71-Instruction conversion sub-module, 72-Instruction distribution sub-module, 81-Data archiving sub-module, 82-Classification index sub-module, 91-Feature matching sub-module, 92-Correlation verification sub-module, 911-Feature extraction unit, 912-Index retrieval unit. Detailed Implementation

[0027] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0028] In the description of this invention, it should be understood that "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] Please see Figures 1 to 8The present invention provides a smart city operation and management system, including a zoning model establishment module 1, a zoning control module 2, a situation acquisition module 3, a zoning matching module 4, a real-time judgment module 5, a decision generation module 6, a decision execution module 7, a decision data storage module 8, and a rapid decision pairing module 9. The partition model establishment module 1 interacts with the partition control module 2, the situation acquisition module 3, the partition matching module 4, the real-time judgment module 5, the decision generation module 6, the decision data storage module 8, the fast decision pairing module 9, and the decision execution module 7 via a system bus. The partition control module 2 is connected to the decision execution module 7, the situation acquisition module 3 is connected to the partition matching module 4, the partition matching module 4 is connected to the real-time judgment module 5, the real-time judgment module 5 is connected to the decision generation module 6, the decision data storage module 8, and the fast decision pairing module 9, the decision generation module 6 is connected to the decision data storage module 8, and the decision execution module 7, the decision data storage module 8 is connected to the fast decision pairing module 9, the fast decision pairing module 9 is connected to the decision execution module 7, and the decision execution module 7 is connected to the partition control module 2. The partition model building module 1 is used to construct multiple internally closed-loop and mutually independent sub-class traffic network models based on the actual road, traffic light and personnel configuration data of the specified area, and combine these sub-class models into an overall traffic network model of the area according to the actual connection relationship. The zoning control module 2 is used to receive control instructions and, according to the control instructions, independently control the traffic lights and dispatchers of each sub-category traffic network model in the overall traffic network model of the area. The situation acquisition module 3 is used to collect traffic processing information, including traffic accidents and emergencies, in real time. The partition matching module 4 is used to obtain the processing information collected by the module 3 according to the situation, and determine one or more of the sub-class traffic network models that have experienced an event or are directly affected by the event. The real-time judgment module 5 is used to analyze the dynamic correlation between each of the sub-class traffic network models, and according to the result of the partition matching module 4, retrieve the real-time traffic data of the affected sub-class traffic network models and other sub-class traffic network models whose correlation is higher than a preset threshold. The decision generation module 6 is used to generate a comprehensive dispatching scheme, including traffic light timing adjustment and dispatcher reassignment, for the affected sub-class traffic network models and their highly correlated related models, based on the real-time traffic data obtained by the real-time judgment module 5. The decision data storage module 8 is used to store the executed integrated scheduling scheme and the real-time traffic data and correlation analysis results used in its generation process as historical scheme data, and classify and store them according to the sub-category of traffic network model to which they belong. The rapid decision matching module 9 is used to filter similar historical scheme data from the decision data storage module 8 based on the current real-time traffic data obtained by the real-time judgment module 5. When the correlation between the scheme and the current situation is higher than the set standard, the corresponding historical comprehensive scheduling scheme is directly output as the rapid decision scheme. The decision execution module 7 is used to convert the rapid decision scheme output by the rapid decision pairing module 9 or the comprehensive scheduling scheme generated by the decision generation module 6 into a control instruction, and send the control instruction to the partition control module 2.

[0030] Specifically, the system first uses the partition model establishment module 1 to divide the urban area into multiple small-class traffic network models with high internal connectivity and limited external connection points based on the urban road network topology and the distribution of traffic management resources, and then integrates them into an overall traffic network model for the area.

[0031] When the situation acquisition module 3 detects a traffic accident or emergency in the area, the partition matching module 4 will quickly locate the event to one or more specific sub-class traffic network models.

[0032] Subsequently, the real-time judgment module 5 not only retrieves the real-time traffic conditions of the incident model, but also dynamically calculates and retrieves real-time data from other closely related models.

[0033] Next, the rapid decision-making matching module 9 will attempt to find solutions for similar scenarios from the historical database.

[0034] If a highly relevant solution is found, it should be adopted directly as a quick decision.

[0035] If no solution is found, the decision generation module 6 will generate a new optimization scheme based on real-time data.

[0036] Ultimately, regardless of the chosen solution, the decision execution module 7 converts it into executable instructions, which are then sent to the zoning control module 2 to precisely and collaboratively control the traffic lights and on-site dispatchers in the target area. This enables precise and rapid response and collaborative dispatching of sudden traffic events by performing zoning modeling and dynamic correlation analysis of the traffic network, combined with rapid matching of historical solutions, effectively improving the overall resilience and operational efficiency of regional traffic.

[0037] For further details, please refer to Figure 1The partition model establishment module 1 includes a model construction submodule 11 and a network integration submodule 12, and the model construction submodule 11 and the network integration submodule 12 are connected. The model building submodule 11 is used to build each independent sub-category of traffic network model based on road, traffic light and personnel configuration data; The network integration submodule 12 is used to integrate multiple sub-class traffic network models into the overall regional traffic network model based on the actual road connection relationships between the sub-class traffic network models.

[0038] In this embodiment, the model construction submodule 11 defines the boundary of each sub-network based on the characteristics of natural convergence of traffic flow to ensure that the traffic correlation of its internal roads is much higher than that of its external roads.

[0039] For further details, please refer to Figure 2 The real-time judgment module 5 includes an association analysis submodule 51 and a data retrieval submodule 52. The association analysis submodule 51 is connected to the partition matching module 4 and is also connected to the data retrieval submodule 52. The correlation analysis submodule 51 is used to dynamically analyze and update the correlation degree between each of the sub-class traffic network models based on historical traffic flow data and real-time connection status. The data retrieval submodule 52 is used to retrieve real-time traffic data of the affected model and its highly correlated model based on the results of the partition matching module 4 and the correlation information provided by the correlation analysis submodule 51.

[0040] In this embodiment, the correlation degree calculation of the correlation analysis submodule 51 is based on the dynamic weighted calculation of the traffic flow OD data of the same historical time period, the real-time GPS floating car data, and the queue length of the boundary intersection, so as to ensure that the system's judgment on the traffic impact range is dynamic and accurate, thereby avoiding over-regulation or under-regulation.

[0041] For further details, please refer to Figure 3 The decision generation module 6 includes a scheme calculation submodule 61 and an effect evaluation submodule 62. The scheme calculation submodule 61 is connected to the real-time judgment module 5 and to the effect evaluation submodule 62. The scheme calculation submodule 61 is used to calculate and generate a preliminary scheduling scheme based on the real-time traffic data and through a traffic flow optimization algorithm. The effect evaluation submodule 62 is used to predict and evaluate the effect of the preliminary scheduling scheme through a traffic simulation model, and output the scheme that meets the requirements of the evaluation results as the comprehensive scheduling scheme.

[0042] In this embodiment, the scheme calculation submodule 61 generates an adjustment scheme for traffic light timing parameters and a deployment suggestion for dispatchers with the goal of minimizing the average delay time of the entire network or the fastest dissipation of queues at bottleneck intersections.

[0043] The effect evaluation submodule 62 uses a digital twin environment built with microscopic traffic simulation software to simulate and extrapolate the preliminary plan and only adopts the plan whose predicted effect is significantly better than the current state.

[0044] The decision generation module 6 mainly transforms the dynamic traffic data provided by the real-time judgment module 5 after correlation analysis into an executable and predictable comprehensive scheduling scheme. This module mainly achieves intelligent generation from data to optimization decisions through the series collaboration and closed-loop verification of two key internal sub-modules, the scheme calculation sub-module 61 and the effect evaluation sub-module 62.

[0045] The scheme calculation submodule 61 mainly generates preliminary strategies based on optimization algorithms. This module uses heuristic algorithms such as genetic algorithms (GA) or particle swarm optimization (PSO) to efficiently search for near-optimal timing parameter combinations in a huge solution space, or uses reinforcement learning (RL) models to directly output control actions that maximize long-term traffic benefits (such as traffic efficiency) based on historical data and the current state. In relatively simple networks or specific scenarios, precise algorithms based on linear programming or network flow theory can also be used. After the calculation is completed, one or more structured "preliminary scheduling schemes" are output, which clearly define the specific control parameter set of each relevant intersection traffic light and the task instructions of each dispatcher.

[0046] The effect evaluation submodule 62 is mainly based on digital twin simulation prediction and optimization. Its core is to perform dynamic simulation of the preliminary plan in a digital twin simulation platform that is highly synchronized with the real traffic environment, covering all elements and the entire process. This digital twin model not only includes accurate road geometry information and traffic light logic, but also loads the current traffic status (such as traffic flow, vehicle speed, and vehicle type composition of each road segment) provided by the real-time judgment module 5 as initial conditions.

[0047] The "preliminary scheduling plan" generated by the scheme calculation submodule 61 is injected into the digital twin model, replacing the control logic of the corresponding traffic signal in the model, and virtual dispatchers are deployed. Subsequently, the system runs the simulation at ultra-real-time speed (e.g., simulating traffic flow for the next 30 minutes takes only a few seconds). During and after the simulation, the system automatically collects and analyzes a series of key performance indicators (KPIs) and compares them with no action taken (baseline scenario) or other alternatives. The evaluation dimensions may include: Efficiency indicators: percentage increase in regional average vehicle speed, reduction in total travel time, and change in average queue length at intersections.

[0048] Safety indicators: predict changes in the number of conflict points and the frequency of sudden braking or acceleration events.

[0049] Robustness index: The tolerance of the scheme to small fluctuations in different traffic flows.

[0050] Meanwhile, the effect evaluation submodule 62 has built-in corresponding evaluation rules. Only when the "total network delay reduction rate" of a certain preliminary scheme simulation exceeds a preset threshold (such as 10%) and does not cause new serious congestion points or safety hazards will the scheme be "adopted" and officially output as a comprehensive scheduling scheme. If multiple schemes meet the criteria, the one with the best effect is selected. If all preliminary schemes fail to meet the criteria, a feedback signal is sent to the scheme calculation submodule 61, requiring it to adjust the optimization target or constraints and recalculate, or directly trigger the fast decision matching module 9 to try to find historical experience and form a decision closed loop.

[0051] For further details, please refer to Figure 4 The fast decision matching module 9 includes a feature matching submodule 91 and an association verification submodule 92. The feature matching submodule 91 is connected to the real-time judgment module 5 and the decision data storage module 8, respectively. The association verification submodule 92 is connected to the feature matching submodule 91. The feature matching submodule 91 is used to extract the feature vector of the current scenario and retrieve the historical scheme data with the highest feature similarity from the decision data storage module 8. The association verification submodule 92 is used to perform in-depth analysis on the retrieved historical solution data, analyze the key differences between it and the current scenario and the causal chain of solution reproduction, and make a final judgment on whether to adopt it.

[0052] In this embodiment, the feature vector extracted by the feature matching submodule 91 includes event type, occurrence time, weather, saturation of the affected area, and traffic capacity margin of the associated area.

[0053] It first performs a fast index by event type and time period, and then calculates the multidimensional feature similarity for sorting.

[0054] The associated verification submodule 92 performs a more refined comparison to ensure that the conditions for historical success are basically met in the present, thereby avoiding the risk of failure that may be caused by mechanical copying.

[0055] For further information, please refer to [link / reference]. Figure 8The feature matching submodule 91 includes a feature extraction unit 911 and an index retrieval unit 912. The feature extraction unit 911 is connected to the real-time judgment module 5 and the index retrieval unit 912. The index retrieval unit 912 is connected to the decision data storage module 8. The feature extraction unit 911 is used to standardize the real-time traffic data and event information into a multi-dimensional feature vector. The index retrieval unit 912 is used to perform rapid initial screening of the historical scheme data using scenario coding, calculate the similarity between the initial screening data and the current feature vector, and output a similarity ranking list.

[0056] In this embodiment, the feature extraction unit 911 normalizes continuous data and performs one-hot encoding on categorical data to form a unified mathematical representation.

[0057] The index retrieval unit 912 uses near nearest neighbor search technology to achieve millisecond-level similar case retrieval in massive historical data to meet the timeliness requirements of emergency response.

[0058] For further details, please refer to Figure 5 The decision data storage module 8 includes a data archiving submodule 81 and a classification index submodule 82. The data archiving submodule 81 is connected to the decision generation module 6 and the real-time judgment module 5, and is also connected to the classification index submodule 82. The classification index submodule 82 is connected to the fast decision matching module 9. The data archiving submodule 81 is used to package the data related to each decision execution and add timestamps, model identifiers and event tags; The classification index submodule 82 is used to create an index for archived data based on the sub-category traffic network model identifier, event type, and key feature values ​​to support fast retrieval.

[0059] In this embodiment, the complete input, decision, and output triples of each successfully executed scheduling scheme are encapsulated into a knowledge package by the data archiving submodule 81 and stored in the database.

[0060] The classification index submodule 82 establishes a multi-level index for the knowledge package so that the system knowledge can be accumulated in an orderly manner and utilized efficiently.

[0061] For further details, please refer to Figure 6 The decision execution module 7 includes an instruction conversion submodule 71 and an instruction distribution submodule 72. The instruction conversion submodule 71 is connected to the decision generation module 6 and the fast decision matching module 9, and is also connected to the instruction distribution submodule 72. The instruction distribution submodule 72 is connected to the partition control module 2. The instruction conversion submodule 71 is used to format the input scheduling scheme into a standardized instruction set that can be recognized by the partition control module 2; The instruction distribution submodule 72 is used to accurately distribute the instruction to the interface of the partition control module 2 corresponding to the target sub-class traffic network model, according to the instruction content.

[0062] In this embodiment, the instruction conversion submodule 71 converts the abstract scheduling scheme into specific control commands that conform to the national standard for traffic signal controller communication protocols.

[0063] The instruction distribution submodule 72 then sends the command group to the signal control server or mobile police terminal in the corresponding area according to the network IDs of each subclass involved in the scheme to ensure the accurate implementation of the instructions.

[0064] For further information, please refer to [link / reference]. Figure 7 The partition control module 2 includes an instruction parsing submodule 21 and an execution feedback submodule 22. The instruction parsing submodule 21 is connected to the decision execution module 7 and is also connected to the execution feedback submodule 22. The instruction parsing submodule 21 is used to receive and parse the control instructions from the decision execution module 7 to determine the specific traffic light control parameters and the dispatcher's action instructions; The execution feedback submodule 22 is used to send instructions to specific traffic signal controllers and personnel terminals, and to collect the execution status and results of the instructions to form feedback information.

[0065] In this embodiment, the instruction parsing submodule 21 verifies the legality and timeliness of the instruction.

[0066] After issuing the dispatch plan to the traffic signal controller, the execution feedback submodule 22 will receive a response indicating whether the plan was successfully received or failed to be executed, and will also confirm whether the dispatcher is in place via the police terminal.

[0067] This feedback information is ultimately incorporated into the system for closed-loop evaluation of this decision and stored as part of the historical data in the decision data storage module 8.

[0068] Please see Figure 9 The smart city operation and management method, using the aforementioned smart city operation and management system, includes the following steps: S1: The zoning model building module 1 constructs a small-class traffic network model containing multiple internal closed loops based on the urban construction data of the specified area, and integrates it into the overall traffic network model of the area. S2: When a special situation occurs in the specified area, the partition matching module 4 obtains the processing information collected in real time by the module 3 according to the situation, and determines one or more sub-class traffic network models directly associated with the event. S3: The real-time judgment module 5 analyzes and retrieves the real-time traffic data of the affected sub-category traffic network model and other sub-category traffic network models whose dynamic correlation with it is higher than the preset threshold, based on the results of the partition matching module 4. S4: The rapid decision matching module 9 retrieves similar historical scheme data from the decision data storage module 8 based on the real-time traffic data obtained by the real-time judgment module 5. If there is historical scheme data with a correlation higher than the set standard, the corresponding historical comprehensive scheduling scheme is output as the rapid decision scheme. S5: If no rapid decision-making scheme is output, the decision generation module 6 generates a new comprehensive scheduling scheme for the affected minor traffic network model and its highly correlated related models based on the real-time traffic data obtained by the real-time judgment module 5. S6: The decision execution module 7 converts the comprehensive scheduling scheme generated by the decision generation module 6 or the rapid decision matching module 9 into specific control instructions and sends them to the partition control module 2. S7: The zone control module 2 receives and executes the control command, and performs zoned scheduling of the traffic lights and dispatchers of the traffic network model specified by the command.

[0069] The above-disclosed embodiments are merely one or more preferred embodiments of this application and should not be construed as limiting the scope of this application. Those skilled in the art can understand that implementing all or part of the above embodiments and making equivalent changes in accordance with the claims of this application still fall within the scope of this application.

Claims

1. A smart city operation and management system, characterized in that, It includes a partition model establishment module, a partition control module, a situation acquisition module, a partition matching module, a real-time judgment module, a decision generation module, a decision execution module, a decision data storage module, and a fast decision pairing module; The partition model establishment module interacts with the partition control module, the situation acquisition module, the partition matching module, the real-time judgment module, the decision generation module, the decision data storage module, the fast decision pairing module, and the decision execution module via a system bus. The partition control module is connected to the decision execution module, the situation acquisition module is connected to the partition matching module, the partition matching module is connected to the real-time judgment module, the real-time judgment module is connected to the decision generation module, the decision data storage module, and the fast decision pairing module, the decision generation module is connected to the decision data storage module and the decision execution module, the decision data storage module is connected to the fast decision pairing module, the fast decision pairing module is connected to the decision execution module, and the decision execution module is connected to the partition control module. The partition model building module is used to construct multiple internally closed-loop and mutually independent sub-class traffic network models based on the actual road, traffic light and personnel configuration data of the specified area, and combine these sub-class models into an overall traffic network model of the area according to the actual connection relationship. The zonal control module is used to receive control instructions and, according to the control instructions, independently control the traffic lights and dispatchers of each sub-category of traffic network models in the overall traffic network model of the area. The situation acquisition module is used to collect traffic handling information, including traffic accidents and emergencies, in real time. The partition matching module is used to obtain the processing information collected by the module according to the situation, and determine one or more of the sub-class traffic network models that have experienced an event or are directly affected by the event. The real-time judgment module is used to analyze the dynamic correlation between each of the sub-class traffic network models, and according to the result of the partition matching module, retrieve the real-time traffic data of the affected sub-class traffic network models and other sub-class traffic network models whose correlation is higher than a preset threshold. The decision generation module is used to generate a comprehensive dispatching scheme, including traffic light timing adjustment and dispatcher reassignment, for the affected sub-class traffic network models and their highly correlated related models, based on the real-time traffic data obtained by the real-time judgment module. The decision data storage module is used to store the executed integrated scheduling scheme and the real-time traffic data and correlation analysis results used in its generation process as historical scheme data, and classify and store them according to the sub-category of traffic network model to which they belong. The rapid decision matching module is used to filter similar historical scheme data from the decision data storage module based on the current real-time traffic data obtained by the real-time judgment module. When the correlation between the scheme and the current situation is higher than the set standard, the corresponding historical comprehensive scheduling scheme is directly output as the rapid decision scheme. The decision execution module is used to convert the rapid decision-making scheme output by the rapid decision-making pairing module or the comprehensive scheduling scheme generated by the decision generation module into a control instruction, and send the control instruction to the partition control module.

2. The smart city operation management system as described in claim 1, characterized in that, The partition model establishment module includes a model construction submodule and a network integration submodule, and the model construction submodule is connected to the network integration submodule; The model building submodule is used to build each independent traffic network model of the sub-category based on road, traffic light and personnel configuration data; The network integration submodule is used to integrate multiple sub-class traffic network models into the overall regional traffic network model based on the actual road connection relationships between the sub-class traffic network models.

3. The smart city operation management system as described in claim 2, characterized in that, The real-time judgment module includes a correlation analysis submodule and a data retrieval submodule. The correlation analysis submodule is connected to the partition matching module and the data retrieval submodule. The correlation analysis submodule is used to dynamically analyze and update the correlation between the various traffic network models based on historical traffic flow data and real-time connection status. The data retrieval submodule is used to retrieve real-time traffic data of the affected model and its highly correlated model based on the results of the partition matching module and the correlation information provided by the correlation analysis submodule.

4. The smart city operation management system as described in claim 3, characterized in that, The decision generation module includes a scheme calculation submodule and an effect evaluation submodule. The scheme calculation submodule is connected to the real-time judgment module and the effect evaluation submodule. The scheme calculation submodule is used to calculate and generate a preliminary scheduling scheme based on the real-time traffic data using a traffic flow optimization algorithm. The effect evaluation submodule is used to predict and evaluate the effect of the preliminary scheduling scheme through a traffic simulation model, and output the scheme that meets the evaluation requirements as the comprehensive scheduling scheme.

5. The smart city operation management system as described in claim 4, characterized in that, The fast decision-making pairing module includes a feature matching submodule and an association verification submodule. The feature matching submodule is connected to the real-time judgment module and the decision data storage module, respectively, and the association verification submodule is connected to the feature matching submodule. The feature matching submodule is used to extract the feature vector of the current scenario and retrieve the historical scheme data with the highest feature similarity from the decision data storage module; The association verification submodule is used to perform in-depth analysis on the retrieved historical solution data, analyze the key differences between it and the current scenario and the causal chain of solution reproduction, and make a final judgment on whether to adopt it.

6. The smart city operation management system as described in claim 5, characterized in that, The decision data storage module includes a data archiving submodule and a classification index submodule. The data archiving submodule is connected to the decision generation module and the real-time judgment module, respectively, and is also connected to the classification index submodule. The classification index submodule is connected to the fast decision matching module. The data archiving submodule is used to package the data related to each decision execution and add timestamps, model identifiers and event tags; The classification index submodule is used to create an index for archived data based on the sub-category traffic network model identifier, event type, and key feature values ​​to support fast retrieval.

7. The smart city operation management system as described in claim 6, characterized in that, The decision execution module includes an instruction conversion submodule and an instruction distribution submodule. The instruction conversion submodule is connected to the decision generation module and the rapid decision matching module, and is also connected to the instruction distribution submodule. The instruction distribution submodule is connected to the partition control module. The instruction conversion submodule is used to format the input scheduling scheme into a standardized instruction set that can be recognized by the partition control module; The instruction distribution submodule is used to accurately distribute the instruction to the partition control module interface corresponding to the target sub-class traffic network model, based on the instruction content.

8. The smart city operation management system as described in claim 7, characterized in that, The partition control module includes an instruction parsing submodule and an execution feedback submodule. The instruction parsing submodule is connected to the decision execution module and is also connected to the execution feedback submodule. The instruction parsing submodule is used to receive and parse the control instructions from the decision execution module to determine the specific traffic light control parameters and the dispatcher's action instructions; The execution feedback submodule is used to send instructions to specific traffic signal controllers and personnel terminals, and to collect the execution status and results of the instructions to form feedback information.

9. The smart city operation management system as described in claim 8, characterized in that, The feature matching submodule includes a feature extraction unit and an index retrieval unit. The feature extraction unit is connected to the real-time judgment module and the index retrieval unit; the index retrieval unit is connected to the decision data storage module. The feature extraction unit is used to standardize the real-time traffic data and event information into a multi-dimensional feature vector; The index retrieval unit is used to perform rapid initial screening of the historical scheme data using scenario coding, calculate the similarity between the initial screened data and the current feature vector, and output a similarity ranking list.

10. A smart city operation and management method, employing the smart city operation and management system as described in claim 1, characterized in that, Includes the following steps, The zoning model building module constructs a sub-category of traffic network models containing multiple internal closed loops based on urban construction data of a specified area, and integrates them into an overall traffic network model for the area. When a special situation occurs in a designated area, the partition matching module obtains the processing information collected in real time by the module according to the situation and determines one or more sub-class traffic network models directly associated with the event. The real-time judgment module analyzes and retrieves real-time traffic data of the affected sub-category traffic network model and other sub-category traffic network models whose dynamic correlation with it is higher than a preset threshold, based on the results of the partition matching module. The rapid decision matching module retrieves similar historical plan data from the decision data storage module based on the real-time traffic data obtained by the real-time judgment module. If there is historical plan data with a correlation higher than the set standard, the corresponding historical comprehensive scheduling plan is output as the rapid decision plan. If no rapid decision-making solution is output, the decision generation module generates a new comprehensive scheduling solution based on the real-time traffic data obtained by the real-time judgment module for the affected minor traffic network model and its highly correlated related models. The decision execution module converts the comprehensive scheduling scheme generated by the decision generation module or the rapid decision matching module into specific control instructions and sends them to the partition control module. The zone control module receives and executes control commands, and performs zoned scheduling of traffic lights and dispatchers for the traffic network model specified in the command.

Images