Urban planning information display method and system based on digital twinning

Abstract

The invention discloses a city planning information display method and system based on digital twinning, and relates to the technical field of city planning. Static data and dynamic data of a city are collected, a three-dimensional model of the city is constructed through the static data, and the dynamic data and the three-dimensional model are combined to construct a digital twinning model of the city; the method comprises the following steps: setting a random data generation pool to generate random data, importing the random data into a digital twinborn model, and monitoring and optimizing a chaos current situation in the digital twinborn model to obtain an optimization scheme; by constructing a public voting platform, public opinions are imported into city planning to obtain a final optimization scheme; according to the method, the digital twinborn model of the city is constructed, more random scenes are provided for city planning by using the random data generation pool, potential changes and uncertainty of the city are fully simulated, and in combination with public opinions, the perspectiveness and flexibility of the digital twinborn technology in the city planning are improved, and a new direction is brought to the city planning.

Description

Technical Field

[0001] The present invention relates to the technical field of urban planning, and in particular to a method and system for displaying urban planning information based on digital twins. Background Art

[0002] As cities continue to expand, urban planning needs become increasingly complex, and traditional urban planning methods face many challenges. As a cutting-edge intelligent solution, digital twin technology has gradually attracted the attention of urban managers and planners and has been widely used in all aspects of urban planning.

[0003] However, the existing digital twin technology in urban planning usually focuses on data mapping in specific scenarios, lacks the ability to conduct scenario analysis for different possible scenarios, and cannot fully simulate potential changes and uncertainties, resulting in a lack of necessary foresight and flexibility in the planning process. At the same time, the technology is too complex for the general public to understand and participate, leading to public distrust of planning decisions. Therefore, it is of great significance to develop a flexible, forward-looking and adaptable digital twin urban planning information display method. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for displaying urban planning information based on digital twins to address the shortcomings of the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a method for displaying urban planning information based on digital twins, comprising:

[0006] Collect static and dynamic data of the city, where static data includes urban layout data, infrastructure data and demographic data, and dynamic data includes traffic flow data, environmental monitoring data and population migration and flow data;

[0007] Use static data and dynamic data to build a digital twin model of the city and perform visualization processing to obtain a visualized offline digital model and an online digital model;

[0008] Construct a random data generation pool, use the random data generation pool to generate random static data and random dynamic data and randomly input them into the offline digital model;

[0009] Obtain the city data after random static data and random dynamic data are put into the offline digital model, and optimize based on the neural network to obtain the optimization plan;

[0010] Sort the chaos status of each area of ​​the offline digital model and generate a difficulty assessment report of the optimization plan;

[0011] Based on the chaotic status quo ranking table, appropriate optimization directions and plans are selected to obtain the optimization plan, which is then updated to the online digital model and displayed. The final optimization plan is determined based on public voting.

[0012] In a new embodiment, the steps of collecting static data and dynamic data of a city are:

[0013] Collect static and dynamic data of the city through sensors;

[0014] Static data include urban layout data, infrastructure data and demographic data. Urban layout data include land use data and road network data. Infrastructure data include transportation infrastructure, power and communication infrastructure. Demographic data include total population, population structure and regional population density.

[0015] Dynamic data include traffic flow data, environmental monitoring data and population migration and mobility data. Traffic flow data include vehicle flow, public transportation usage, traffic accident data and traffic congestion. Environmental monitoring data include air quality monitoring, noise monitoring and temperature and humidity.

[0016] In a new embodiment, the steps of constructing a digital twin model of a city using static data and dynamic data and performing visualization processing are:

[0017] Build a digital 3D model of the city based on static data, simulate the city layout, and add the city’s infrastructure and population range;

[0018] The dynamic data is put into the digital 3D model, and the association between the dynamic data and the digital 3D model is built through the simulation engine to perform dynamic simulation of the city to obtain the digital twin model of the city;

[0019] At the same time, a data interface is built in the transportation hub area in the digital twin model. The data interface is used to communicate with other city digital twin models and has data standardization and data transmission functions.

[0020] The digital twin model is visualized through the visualization platform to obtain visualized offline digital models and online digital models.

[0021] In a new embodiment, the steps of constructing a random data generation pool, using the random data generation pool to generate random static data and random dynamic data and randomly inputting them into the offline digital model are:

[0022] Clean and pre-process the city's static data and dynamic data to obtain standard static data and standard dynamic data;

[0023] Define spatial and temporal correlation constraints, and the generated random static data and random dynamic data are subject to spatial and temporal correlation constraints;

[0024] Generate random static data and random dynamic data using neural network based on standard static data and standard dynamic data;

[0025] Construct a generation database to store random static data and random dynamic data, and combine the neural network, generation database, spatial and temporal correlation constraints to obtain a random data generation pool;

[0026] The existing static data and dynamic data of the city are input into the random data generation pool to obtain random static data and random dynamic data, and the random static data and random dynamic data are randomly imported into the offline digital model.

[0027] In a new embodiment, the steps of obtaining the city data after random static data and random dynamic data are put into the offline digital model, and optimizing based on the neural network to obtain the optimization solution are:

[0028] An input set consisting of random static data and random dynamic data is imported into the offline digital model, and output data is obtained by running the offline digital model as a preliminary data set reflecting the city state;

[0029] Construct a neural network optimization model and define the objective functions including minimizing traffic congestion, minimizing population congestion, optimizing environmental quality, and optimizing public service distribution;

[0030] The preliminary data set is input into the neural network optimization model to obtain the optimization solution for each objective function.

[0031] In a new embodiment, the steps of sorting the disorder status of each area of ​​the offline digital model and generating a difficulty assessment report of the optimization solution are:

[0032] The evaluation indicators that define the chaotic status include traffic congestion index, population congestion index, environmental quality index, and public service accessibility. Each evaluation indicator is given a value of 1-5, and the larger the value, the more chaotic it is;

[0033] The offline digital model of the city is divided into limited areas based on the urban layout data;

[0034] The weights of the evaluation indicators are defined as follows: traffic congestion index w 1 , population congestion index w 2 , Environmental Quality Index 3 , public service accessibility 4 , and w 1 +w 2 +w 3 +w 4 =1;

[0035] The comprehensive score of each area is calculated using the weighted average method based on the evaluation indicators;

[0036] First, the evaluation indicators are standardized:

[0037]

[0038] Where X represents the evaluation index value of the region, min is the minimum value of the evaluation index of the region, X max represents the maximum value of the evaluation index of the region, and X′ is the standardized value of the evaluation index;

[0039] Then calculate the comprehensive score S of the region i :

[0040] S i =w 1 ×TCI i′ +w 2 ×PDI i′ +w 3 ×EQI i′ +w 4 ×PSA i′

[0041] TCI i′ represents the normalized value of the traffic congestion index of area (i), PDI i′ represents the normalized value of population congestion index of region (i), EQI i′ represents the standardized value of the environmental quality index of region (i), PSA i′ represents the normalized value of public service accessibility of area (i);

[0042] According to the comprehensive scores of each area, the disorder status ranking table is obtained from high to low;

[0043] Define the quantitative evaluation indicators of the optimization plan, including cost, time, technical requirements, social impact, and resource requirements. Provide a score of 1-5 for each quantitative evaluation indicator. The larger the score, the greater the difficulty of optimization.

[0044] The weights of the quantitative evaluation indicators for defining the optimization scheme include the cost weight w 5 , time weight w 6 , technical requirement weight w 7 and social influence weight w 8 ;

[0045] The optimization difficulty evaluation report D is obtained using the weighted average method:

[0046] D=w 5 ·C+w 6·T+w 7 ·R+w 8 ·S

[0047] Among them, C is the cost score, T is the time score, R is the technical requirement score, and S is the social impact score.

[0048] In a new embodiment, the steps of selecting a suitable optimization direction and plan based on the disorder status ranking table to obtain an optimization plan, updating the optimization plan to an online digital model and displaying it, and determining the final optimization plan based on public voting are as follows:

[0049] Obtain the disorder status ranking table and optimization difficulty assessment report to identify key areas with high disorder and low optimization difficulty, and derive optimization plans for key areas;

[0050] Importing the optimization plan into the online digital model to obtain the optimized online digital model, and refining the optimization plan into specific strategies, including implementation steps, required resources and expected results;

[0051] The optimized online digital model and specific strategies will be presented to the public, a public voting platform will be built to collect public opinions and suggestions, and online voting decisions will be made;

[0052] The final optimization plan is obtained by combining online voting decisions and imported into the online digital model.

[0053] The present invention also provides an urban planning information display system based on digital twins, comprising:

[0054] Data collection module: collects static and dynamic data of the city, where static data includes urban layout data, infrastructure data and demographic data, and dynamic data includes traffic flow data, environmental monitoring data and population migration and flow data;

[0055] Digital twin model module: connected with the data acquisition module, using static data and dynamic data to build a digital twin model of the city and perform visualization processing to obtain a visualized offline digital model and an online digital model;

[0056] Random data generation pool module: connected with the digital twin model module, constructs a random data generation pool, uses the random data generation pool to generate random static data and random dynamic data and randomly inputs them into the offline digital model;

[0057] Optimization module: connected with the random data generation pool module, obtains the urban data after random static data and random dynamic data are put into the offline digital model, and optimizes based on the neural network to obtain the optimization plan;

[0058] Sorting module: connected with the optimization module, sorting the chaotic status of each area of ​​the offline digital model, and generating a difficulty assessment report of the optimization solution;

[0059] Evaluation module: connected with the sorting module, it selects the appropriate optimization direction and plan based on the chaotic status quo sorting table to obtain the optimization plan, updates the optimization plan to the online digital model and displays it, and determines the final optimization plan based on public voting.

[0060] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0061] 1. The present invention constructs a random data generation pool to randomly generate a large amount of urban data based on existing urban data, and defines constraints to ensure that the generated random urban data has practical significance. At the same time, a large amount of random urban data is randomly imported into the digital twin model, which increases the uncertainty of scenario simulation and tests the upper limit of the city, adding more directions and options for urban planning;

[0062] 2. The present invention ensures the interconnectivity of urban planning by constructing a data interface. By reserving a data interface and setting a data standardization function, the digital twin models of multiple cities can be exchanged for data, providing a new direction for urban planning based on digital twins. At the same time, the chaos of offline digital models and the difficulty of optimization are sorted, which can identify areas with planning potential in the city and obtain efficient urban planning solutions through public participation. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0064] Figure 1 is a flow chart of the method of the present invention;

[0065] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Example 1, please refer to Figure 1 As shown, the urban planning information display method based on digital twins described in this embodiment includes:

[0068] S1. Collect static and dynamic data of the city, where static data includes urban layout data, infrastructure data and demographic data, and dynamic data includes traffic flow data, environmental monitoring data and population migration and flow data;

[0069] S2. Use static data and dynamic data to build a digital twin model of the city and perform visualization processing to obtain a visualized offline digital model and an online digital model;

[0070] S3, building a random data generation pool, using the random data generation pool to generate random static data and random dynamic data and randomly inputting them into the offline digital model;

[0071] S4, obtaining urban data after random static data and random dynamic data are put into the offline digital model, and optimizing based on the neural network to obtain an optimization solution;

[0072] S5, sorting the disorder status of each area of ​​the offline digital model, and generating a difficulty assessment report of the optimization plan;

[0073] S6. Based on the disorder status ranking table, appropriate optimization directions and plans are selected to obtain optimization solutions, the optimization solutions are updated to the online digital model and displayed, and the final optimization solutions are determined based on public voting;

[0074] As described in the above steps S1-S6, as the scale of cities continues to expand, urban planning needs become increasingly complex, and traditional urban planning methods face many challenges. Digital twin technology, as a cutting-edge intelligent solution, has gradually attracted the attention of urban managers and planners, and has been widely used in all aspects of urban planning; however, the existing digital twin technology in urban planning usually focuses on data mapping under specific scenarios, lacks the ability to perform scenario analysis on different possible scenarios, and cannot fully simulate potential changes and uncertainties, resulting in a lack of necessary foresight and flexibility in the planning process. At the same time, because the technology is too complex, it is difficult for the general public to understand and participate, resulting in the public's distrust of planning decisions. The present invention constructs a random data generation pool based on the existing A large amount of random urban data is randomly generated from the urban data, and constraints are defined to ensure that the generated random urban data has practical significance. At the same time, a large amount of random urban data is randomly imported into the digital twin model to increase the uncertainty of the scenario simulation and test the upper limit of the city, adding more directions and choices for urban planning. At the same time, by building a data interface, the interconnectivity of urban planning is guaranteed. By reserving data interfaces and setting data standardization functions, data exchange among digital twin models of multiple cities is realized, providing a new direction for urban planning based on digital twins. At the same time, the chaos of offline digital models and the difficulty of optimization are sorted to identify areas with planning potential in the city, and obtain efficient urban planning solutions through public participation.

[0075] In one embodiment, the step S1 of collecting static data and dynamic data of a city includes:

[0076] S11, collect static and dynamic data of the city through sensors;

[0077] S12. Static data include urban layout data, infrastructure data and demographic data. Urban layout data include land use data and road network data. Infrastructure data include transportation infrastructure, power and communication infrastructure. Demographic data include total population, population structure and regional population density.

[0078] S13. Dynamic data include traffic flow data, environmental monitoring data and population migration and mobility data. Traffic flow data include vehicle flow, public transportation usage, traffic accident data and traffic congestion. Environmental monitoring data include air quality monitoring, noise monitoring and temperature and humidity.

[0079] As described in the above steps S11-S13, for the static data of the city, geographic information system technology is used to collect information on land use and road network, and satellite images and drones are used to divide plots and analyze road networks to obtain urban layout data. Infrastructure data is obtained by deploying IoT sensors to monitor the operating status of power and communication infrastructure. The total population, structure and population density are collected through government databases, questionnaires and social media analysis methods to obtain demographic data. For the dynamic data of the city, road surface sensors are installed at major traffic intersections to obtain vehicle flow data. Real-time passenger data is collected by installing GPS and ticketing system controllers on public transportation equipment to obtain public transportation usage. Cooperation with the local traffic management center is carried out to obtain traffic accident data and traffic congestion conditions. At the same time, air quality monitors and noise sensors are set up, and communication with the meteorological department is carried out to obtain the city's environmental monitoring data.

[0080] In one embodiment, the step S2 of constructing a digital twin model of a city using static data and dynamic data and performing visualization processing includes:

[0081] S21. Build a digital 3D model of the city based on static data, simulate the city layout, and add the city’s infrastructure and population range;

[0082] S22, inputting the dynamic data into the digital three-dimensional model, building an association between the dynamic data and the digital three-dimensional model through a simulation engine, and performing a dynamic simulation of the city to obtain a digital twin model of the city;

[0083] S23. At the same time, a data interface is constructed in the transportation hub area in the digital twin model, wherein the data interface is used to communicate with other city digital twin models and has data standardization and data transmission functions;

[0084] S24, performing visualization processing on the digital twin model through a visualization platform to obtain a visualized offline digital model and an online digital model;

[0085] As described in the above steps S21-S24, a three-dimensional model of the city is constructed through urban modeling software, and the city's land use and road network data are imported through the collected GIS data to construct the basic urban terrain. According to the infrastructure data, three-dimensional models of transportation, water supply, power supply and communication facilities are added to the three-dimensional model of the city. Residents are modeled and invested according to demographic data. After the three-dimensional model of the city built based on static data is completed, the dynamic data is associated with the three-dimensional model to build a city digital twin model that can run in real time. A simulation engine that supports real-time data processing is selected, and the collected dynamic data is unified in format. Dynamic endpoints are added to the three-dimensional model for the parts that need to be dynamically updated, such as at traffic nodes and monitoring stations. Markers or entities are added at points as dynamic endpoints to receive updated data. Data binding of dynamic endpoints in the scripting model can be used to update the status according to dynamic data. The specific values ​​of the dynamic data are then mapped to specific parameters of the 3D model. For example, real-time traffic flow data can be used to adjust the status of traffic flow indicators and dynamically generate traffic congestion icons. After the dynamic data and the 3D model are associated, the WebSocket protocol is used to connect to the real-time data stream to ensure that the data can be synchronized to the 3D model every time it is updated, and the data monitoring function is implemented in the digital twin model to ensure that the model update can be triggered once the data changes. After obtaining the digital twin model of the city, the dynamic interactive effect of the digital twin model is created using visualization platforms such as Unity and Unreal Engine, combining animation and real-time data streams to display the dynamically changing status of the city, such as traffic flow, population flow, etc.

[0086] In one embodiment, the step S3 of constructing a random data generation pool, using the random data generation pool to generate random static data and random dynamic data and randomly inputting them into the offline digital model includes:

[0087] S31, cleaning and preprocessing the static data and dynamic data of the city to obtain standard static data and standard dynamic data;

[0088] S32, defining spatial and temporal correlation constraints, whereby the generated random static data and random dynamic data are both subject to spatial and temporal correlation constraints;

[0089] S33, generating random static data and random dynamic data using a neural network based on standard static data and standard dynamic data;

[0090] S34, constructing a generation database for storing random static data and random dynamic data, and integrating the neural network, the generation database, and the spatial and temporal correlation constraints to obtain a random data generation pool;

[0091] S35, inputting the existing static data and dynamic data of the city into a random data generation pool to obtain random static data and random dynamic data, and randomly importing the random static data and random dynamic data into an offline digital model;

[0092] As described in the above steps S31-S35, the acquired urban static data and dynamic data are subjected to data standardization processing, standard static data and standard dynamic data, and spatial and temporal correlation constraints are defined at the same time. The random data generated by the random data generation pool needs to meet the spatial and temporal correlation constraints, where the spatial and temporal correlation constraints represent the constraints on the random data. For example, if the randomly generated data is vehicle data, the vehicle will only be generated on the road network or in parking lots where the vehicle should be stored. When it is put into the digital twin model, the vehicle will not appear in the house or other places where it should not appear. That is, the randomly generated data is constrained by the real environment and has practical significance. For example, the generated random data is the infrastructure traffic light, so the traffic light satisfies the practical significance. That is, it will appear at the intersection of the road network, and will not appear randomly in one-way streets or rivers and lakes. The randomly generated data meets the constraints of spatial and temporal correlation to ensure the applicability and accuracy of the data. A large amount of random data is generated through neural network training based on the existing urban static data and dynamic data to ensure that the random data meets the constraints and is stored in the constructed generation database. The neural network can choose to generate an adversarial network. The neural network, constraints and generation database set is the random data generation pool. Through the random data generation pool, a large amount of random data with practical significance can be generated based on the existing data, and then the random data is put into the offline digital model to monitor the operation of the offline digital model, and the planning direction and area are found from the operation trajectory of the offline digital model.

[0093] In one embodiment, the step S4 of acquiring the city data after random static data and random dynamic data are input into the offline digital model and optimizing based on the neural network to obtain the optimization solution includes:

[0094] S41, importing the input set consisting of random static data and random dynamic data into the offline digital model, and obtaining output data by running the offline digital model as a preliminary data set reflecting the city state;

[0095] S42. Construct a neural network optimization model and define the objective functions including minimizing traffic congestion, minimizing population congestion, optimizing environmental quality and optimizing public service distribution;

[0096] S43, inputting the preliminary data set into the neural network optimization model to obtain an optimization solution for each objective function;

[0097] As described in the above steps S41-S43, the random data generated by the random data generation pool is imported into the offline digital model as an input set, and the operating data of the offline digital model is obtained as output data as a preliminary data set. The preliminary data set includes static data and dynamic data generated by the offline digital model of the city after the random data is imported. Randomly importing random data into the offline digital model of the city will cause confusion in the offline digital model of the city. For example, a road area can accommodate the smooth entry of 500 vehicles. After importing 500 vehicles, the area will inevitably cause congestion. Therefore, it is necessary to build a neural network optimization model to optimize each area of ​​the offline digital model of the city. The neural network optimization model can select a multi-layer perceptron model to achieve different optimization goals by constructing different objective functions, including minimum To improve traffic congestion, minimize population congestion, optimize environmental quality and optimize the distribution of public services, the existing urban data can be used to train the multi-layer perceptron model, and then the preliminary data set can be imported as input into the neural network optimization model to obtain the optimization plan, such as generating a traffic dispatch optimization plan, optimizing the congested areas in the offline digital model. The optimization plan may be to adjust the timing of traffic lights, reasonably set bus priority, add pedestrian streets and overpasses in high-density pedestrian areas, and set up signs to divert pedestrian and vehicle traffic. The overall design process is to import random data into the offline digital model of the city, causing unknown chaos in the offline digital model of the city. The neural network optimization model is used to optimize the chaotic area and output the optimization plan. The overall idea is to find order from the disordered chaos of the city.

[0098] In one embodiment, the step S5 of sorting the disorder status of each area of ​​the offline digital model and generating a difficulty assessment report of the optimization solution includes:

[0099] S51. Define the evaluation indicators of the chaotic status, including traffic congestion index, population congestion index, environmental quality index, and public service accessibility. Provide a value of 1-5 for each evaluation indicator, with the larger the value, the more chaotic it is;

[0100] S52, dividing the offline digital model of the city into limited areas based on the urban layout data;

[0101] S53, define the weights of the evaluation indicators including the traffic congestion index w 1 , population congestion index w 2 , Environmental Quality Index 3 , public service accessibility 4 , and w 1 +w 2 +w 3 +w 4 =1;

[0102] S54. Calculate the comprehensive score of each area using the weighted average method based on the evaluation indicators;

[0103] S55. First, standardize the evaluation indicators:

[0104]

[0105] S56, where X represents the evaluation index value of the region, min is the minimum value of the evaluation index of the region, X max represents the maximum value of the evaluation index of the region, and X′ is the standardized value of the evaluation index;

[0106] S57, then calculate the comprehensive score S of the area i :

[0107] S i =w 1 ×TCI i′ +w 2 ×PDI i′ +w 3 ×EQI i′ +w 4 ×PSA i′

[0108] S58, among which TCI i′ represents the normalized value of the traffic congestion index of area (i), PDI i′ represents the normalized value of population congestion index of region (i), EQI i′ represents the standardized value of the environmental quality index of region (i), PSA i′ represents the normalized value of public service accessibility of area (i);

[0109] S59, sorting the comprehensive scores of the regions from high to low to obtain a ranking table of the current chaos status;

[0110] S510, defining quantitative evaluation indicators of the optimization solution including cost, time, technical requirements, social impact, and resource requirements, and providing a score of 1-5 for each quantitative evaluation indicator, where a larger score indicates a greater optimization difficulty;

[0111] S511. Define the weights of the quantitative evaluation indicators of the optimization scheme, including the cost weight w 5 , time weight w 6 , technical requirement weight w 7 and social influence weight w 8 ;

[0112] S512. Use the weighted average method to obtain the optimization difficulty evaluation report D:

[0113] D=w 5·C+w 6 ·T+w 7 ·R+w 8 ·S

[0114] S513, where C is the cost score, T is the time score, R is the technical requirement score, and S is the social impact score;

[0115] As described in the above steps S51-S513, the offline digital model of the city is divided into a limited number of areas based on the urban layout data. For example, the divided areas include industrial areas, residential areas and commercial areas. At the same time, the judgment condition of the segmentation can be based on urban planning. That is, when it is necessary to plan the road network of the city, the area can be divided based on traffic flow. Then, the evaluation indicators of the current chaos status are defined, including traffic congestion index, population congestion index, environmental quality index, and public service accessibility. The severity of the chaos is judged in the form of scores. For example, if an area is particularly congested, the traffic congestion index score is the highest five points. If the traffic is very smooth, the traffic congestion index score is the lowest one point. Based on the planning needs of each area, a weight is defined for each evaluation indicator. If the area is a transportation hub area, the weight of the traffic congestion index must be greater than that of other evaluation indicators. After completing the indicators, After the scores and weights are defined, the weighted average method is used to calculate the comprehensive score of each area, and the scores are sorted from high to low to obtain a ranking table of the current chaos status. The same method is used to generate an optimization difficulty assessment report for the optimization plan. The quantitative evaluation indicators of the optimization plan are defined, including cost, time, technical requirements, social impact, and resource requirements. At the same time, a score of 1-5 points is provided for each quantitative evaluation indicator. The larger the score, the greater the difficulty of optimization. The cost represents the financial expenditure required for the implementation plan, the time represents the time period required to complete the optimization, the technical requirements represent the technical level and professional skills required for the implementation plan, the social impact represents the social repercussions or public acceptance that the optimization plan may cause, and the resource requirements represent the availability of the required human, material and information resources. A weight is defined for each quantitative evaluation indicator, and the optimization difficulty assessment report for the optimization plan of each region is generated by the weighted average method.

[0116] In one embodiment, the step S6 of selecting a suitable optimization direction and plan based on the disorder status ranking table to obtain an optimization solution, updating the optimization solution to an online digital model and displaying it, and determining the final optimization solution based on public voting includes:

[0117] S61, obtaining a disorder status ranking table and an optimization difficulty assessment report to obtain key areas with high disorder and low optimization difficulty, and deriving optimization plans for the key areas as key optimization plans;

[0118] S62, importing the key optimization plan into the online digital model to obtain an optimized online digital model, and refining the key optimization plan into specific strategies, including implementation steps, required resources, and expected results;

[0119] S63. Present the optimized online digital model and specific strategies to the public, build a public voting platform, collect public opinions and suggestions, and make online voting decisions;

[0120] S64, combining online voting decisions to obtain a final optimization solution, and importing it into an online digital model;

[0121] As described in the above steps S61-S64, based on the obtained chaos status ranking table and optimization difficulty assessment report, the areas with high chaos and low optimization difficulty in the city offline digital model are selected as key areas. These areas may be more important directions in the urban planning process. The areas with high chaos indicate that the areas have poor anti-interference ability and cannot cope with emergencies in the city. The areas with low optimization difficulty can achieve urban optimization at a very low cost, providing a clearer direction for current urban planning, obtaining the optimization plan for the key areas and importing it into the online digital model to obtain the optimized online digital model, and refining the optimization plan into specific strategies, including the optimization implementation steps, required resources and optimization The specific strategies can be output in the form of text, and the visualized optimization online digital model and the optimization plan output in text form can be presented to the public. A public voting platform can be built to make online voting decisions and collect public opinions and suggestions. After the voting, data can be collected and sorted, and the votes of each optimization plan can be analyzed to judge the public's preference for different optimization plans. The voting results can be combined with the feasibility and expected effects of the optimization plans using the weighted average method to analyze which optimization plans are more in line with the public's expectations and can gain higher support in actual implementation. These optimization plans will be used as the final optimization plans, and the final optimization plans will be imported into the online digital model to monitor the optimization effect.

[0122] Example 2, please refer to Figure 2 As shown, the urban planning information display system based on digital twins described in this embodiment includes:

[0123] Data collection module: collects static and dynamic data of the city, where static data includes urban layout data, infrastructure data and demographic data, and dynamic data includes traffic flow data, environmental monitoring data and population migration and flow data;

[0124] Digital twin model module: connected with the data acquisition module, using static data and dynamic data to build a digital twin model of the city and perform visualization processing to obtain a visualized offline digital model and an online digital model;

[0125] Random data generation pool module: connected with the digital twin model module, constructs a random data generation pool, uses the random data generation pool to generate random static data and random dynamic data and randomly inputs them into the offline digital model;

[0126] Optimization module: connected with the random data generation pool module, obtains the urban data after random static data and random dynamic data are put into the offline digital model, and optimizes based on the neural network to obtain the optimization plan;

[0127] Sorting module: connected with the optimization module, sorting the chaotic status of each area of ​​the offline digital model, and generating a difficulty assessment report of the optimization solution;

[0128] Evaluation module: connected with the sorting module, it selects the appropriate optimization direction and plan based on the chaotic status quo sorting table to obtain the optimization plan, updates the optimization plan to the online digital model and displays it, and determines the final optimization plan based on public voting.

[0129] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for displaying urban planning information based on digital twins, characterized in that: Collect static and dynamic data of the city, where static data includes urban layout data, infrastructure data and demographic data, and dynamic data includes traffic flow data, environmental monitoring data and population migration and flow data; Use static data and dynamic data to build a digital twin model of the city and perform visualization processing to obtain a visualized offline digital model and an online digital model; Construct a random data generation pool, use the random data generation pool to generate random static data and random dynamic data and randomly input them into the offline digital model; Obtain the city data after random static data and random dynamic data are put into the offline digital model, and optimize based on the neural network to obtain the optimization plan; Sort the chaos status of each area of ​​the offline digital model and generate a difficulty assessment report of the optimization plan; Based on the chaotic status quo ranking table, appropriate optimization directions and plans are selected to obtain the optimization plan, which is then updated to the online digital model and displayed. The final optimization plan is determined based on public voting.

2. The method for displaying urban planning information based on digital twins according to claim 1, characterized in that: The steps of collecting static data and dynamic data of the city are: Collect static and dynamic data of the city through sensors; Static data include urban layout data, infrastructure data and demographic data. Urban layout data include land use data and road network data. Infrastructure data include transportation infrastructure, power and communication infrastructure. Demographic data include total population, population structure and regional population density. Dynamic data include traffic flow data, environmental monitoring data and population migration and mobility data. Traffic flow data include vehicle flow, public transportation usage, traffic accident data and traffic congestion. Environmental monitoring data include air quality monitoring, noise monitoring and temperature and humidity.

3. The method for displaying urban planning information based on digital twins according to claim 1, characterized in that: The steps of using static data and dynamic data to construct a digital twin model of a city and perform visualization processing are: Build a digital 3D model of the city based on static data, simulate the city layout, and add the city’s infrastructure and population range; The dynamic data is put into the digital 3D model, and the association between the dynamic data and the digital 3D model is built through the simulation engine to perform dynamic simulation of the city to obtain the digital twin model of the city; At the same time, a data interface is built in the transportation hub area in the digital twin model. The data interface is used to communicate with other city digital twin models and has data standardization and data transmission functions. The digital twin model is visualized through the visualization platform to obtain visualized offline digital models and online digital models.

4. The method for displaying urban planning information based on digital twins according to claim 1, characterized in that: The steps of constructing a random data generation pool, using the random data generation pool to generate random static data and random dynamic data and randomly inputting them into the offline digital model are as follows: Clean and pre-process the city's static data and dynamic data to obtain standard static data and standard dynamic data; Define spatial and temporal correlation constraints, and the generated random static data and random dynamic data are subject to spatial and temporal correlation constraints; Generate random static data and random dynamic data using neural network based on standard static data and standard dynamic data; Construct a generation database to store random static data and random dynamic data, and combine the neural network, generation database, spatial and temporal correlation constraints to obtain a random data generation pool; The existing static data and dynamic data of the city are input into the random data generation pool to obtain random static data and random dynamic data, and the random static data and random dynamic data are randomly imported into the offline digital model.

5. The method for displaying urban planning information based on digital twins according to claim 1, characterized in that: The steps of obtaining the city data after random static data and random dynamic data are put into the offline digital model, and optimizing based on the neural network to obtain the optimization solution are: An input set consisting of random static data and random dynamic data is imported into the offline digital model, and output data is obtained by running the offline digital model as a preliminary data set reflecting the city state; Construct a neural network optimization model and define the objective functions including minimizing traffic congestion, minimizing population congestion, optimizing environmental quality, and optimizing public service distribution; The preliminary data set is input into the neural network optimization model to obtain the optimization solution for each objective function.

6. The method for displaying urban planning information based on digital twins according to claim 1, characterized in that: The steps of sorting the disorder status of each area of ​​the offline digital model and generating a difficulty assessment report of the optimization solution are: The evaluation indicators that define the chaotic status include traffic congestion index, population congestion index, environmental quality index, and public service accessibility. Each evaluation indicator is given a value of 1-5, and the larger the value, the more chaotic it is; The offline digital model of the city is divided into limited areas based on the urban layout data; The weights of the evaluation indicators are defined as traffic congestion index w1, population congestion index w2, environmental quality index w3, and public service accessibility w4, and w1+w2+w3+w4=1; The comprehensive score of each area is calculated using the weighted average method based on the evaluation indicators; First, the evaluation indicators are standardized: Where X represents the evaluation index value of the region, min is the minimum value of the evaluation index of the region, X max represents the maximum value of the evaluation index of the region, and X′ is the standardized value of the evaluation index; Then calculate the comprehensive score S of the region i : S i =w1×TCI i′ +w2×PDI i′ +w3×EQI i′ +w4×PSA i′ TCI i′ represents the normalized value of the traffic congestion index of region (i), PDI i′ represents the normalized value of population congestion index of region (i), EQI i′ represents the standardized value of the environmental quality index of region (i), PSA i′ represents the normalized value of public service accessibility of area (i); According to the comprehensive scores of each area, the disorder status ranking table is obtained from high to low; Define the quantitative evaluation indicators of the optimization plan, including cost, time, technical requirements, social impact, and resource requirements. Provide a score of 1-5 for each quantitative evaluation indicator. The larger the score, the greater the difficulty of optimization. The weights of the quantitative evaluation indicators for defining the optimization scheme include cost weight w5, time weight w6, technical requirement weight w7, and social impact weight w8; The optimization difficulty evaluation report D is obtained using the weighted average method: D=w5·C+w6·T+w7·R+w8·S Among them, C is the cost score, T is the time score, R is the technical requirement score, and S is the social impact score.

7. The method for displaying urban planning information based on digital twins according to claim 1, characterized in that: The steps of selecting appropriate optimization directions and plans based on the disorder status ranking table to obtain an optimization plan, updating the optimization plan to the online digital model and displaying it, and determining the final optimization plan based on public voting are as follows: Obtain the disorder status ranking table and optimization difficulty assessment report to obtain key areas with high disorder and low optimization difficulty, and derive optimization plans for key areas; Importing the optimization plan into the online digital model to obtain the optimized online digital model, and refining the optimization plan into specific strategies, including implementation steps, required resources and expected results; The optimized online digital model and specific strategies will be presented to the public, a public voting platform will be built to collect public opinions and suggestions, and online voting decisions will be made; The final optimization plan is obtained by combining online voting decisions and imported into the online digital model.

8. A city planning information display system based on digital twins, used to implement a city planning information display method based on digital twins as described in any one of claims 1 to 7, characterized in that: Data collection module: collects static and dynamic data of the city, where static data includes urban layout data, infrastructure data and demographic data, and dynamic data includes traffic flow data, environmental monitoring data and population migration and flow data; Digital twin model module: connected with the data acquisition module, using static data and dynamic data to build a digital twin model of the city and perform visualization processing to obtain a visualized offline digital model and an online digital model; Random data generation pool module: connected with the digital twin model module, constructs a random data generation pool, uses the random data generation pool to generate random static data and random dynamic data and randomly inputs them into the offline digital model; Optimization module: connected with the random data generation pool module, obtains the urban data after random static data and random dynamic data are put into the offline digital model, and optimizes based on the neural network to obtain the optimization plan; Sorting module: connected with the optimization module, sorting the chaotic status of each area of ​​the offline digital model, and generating a difficulty assessment report of the optimization solution; Evaluation module: connected with the sorting module, it selects the appropriate optimization direction and plan based on the chaotic status quo sorting table to obtain the optimization plan, updates the optimization plan to the online digital model and displays it, and determines the final optimization plan based on public voting.

Images