Intelligent urban management system and method based on three-dimensional live-action

Abstract

The invention relates to the technical field of smart city management, and discloses a smart city management system based on three-dimensional live-action, and the system comprises a data extraction unit, the output end of the data extraction unit is in signal connection with a model construction unit, and the output end of the model construction unit is in signal connection with a constraint management unit. According to the intelligent urban management system and method based on the three-dimensional live-action, an actual use scene is generated in combination with real data, the accuracy of predicted value data is improved, a manager can make a decision conveniently, distribution plans of different to-be-adjusted regions in different time periods on the same day are met, a three-dimensional live-action management model is richer, different scene use environments are met, and the user experience is improved. Therefore, the adjustment scheme is more sufficient and flexible, the distribution plans of different to-be-adjusted regions on that day are improved, the consumption rate of the jurisdiction region is more visually observed through the establishment of the three-dimensional real scene, the manual management pressure is relieved, the total system operation cost is reduced, and sufficient scheduling and distribution of resources are met.

Description

Technical Field

[0001] The present invention relates to the field of smart urban management technology, and specifically to a smart urban management system and method based on three-dimensional real-scene. Background Art

[0002] Digital city management is the application and integration of multiple digital city technologies, using a combination of two- and three-dimensional integrated geographic information and urban component management methods to achieve the refinement of urban management space and the precision of management objects.

[0003] At present, the most widely used 3D real scene is the urban street view map. Companies such as Microsoft, Google, Tencent, and Baidu have spent huge amounts of money to build their own 3D real scene maps, which are more intuitive than the original two-dimensional maps. However, there is no 3D real scene display system combined with digital urban management on the market. This is mainly because the high-definition 3D real scene image display data processing volume is large, and the smart urban management system has strong real-time requirements and cannot be reasonably allocated according to local finances. Therefore, it is necessary to invent a smart urban management system and method based on 3D real scene to solve the above problems. Summary of the invention

[0004] (I) Technical solution

[0005] In order to realize the above-mentioned generation of actual usage scenarios in combination with real data, simulate and predict the consumption forecast values ​​of various distributed areas, rely on data-driven unsupervised generation of close-to-real scenarios, have wide adaptability, increase scenario simulation from the initial segment of data, improve the accuracy of prediction value data, facilitate managers to make decisions, meet the daily allocation plans of different areas to be adjusted in different time periods, make the three-dimensional real scene management model richer, meet the use environment of different scenarios, so that the adjustment plan is more sufficient and flexible, improve the daily allocation plan of different areas to be adjusted, and the establishment of three-dimensional real scenes more intuitively observes the consumption rate of the area under jurisdiction, relieves the pressure of manual management, reduces the total cost of system operation, and meets the full scheduling and allocation of resources. The present invention provides the following technical solutions:

[0006] A smart urban management system based on three-dimensional reality includes a data extraction unit, an output end signal of the data extraction unit is connected to a model construction unit, and an output end signal of the model construction unit is connected to a constraint management unit.

[0007] Preferably, the data extraction unit includes a map acquisition data module, the output end signal of the map acquisition data module is connected to a road information acquisition module, the output end signal of the road information acquisition module is connected to a three-dimensional data acquisition module, the output end signal of the three-dimensional data acquisition module is connected to a monitoring data module, the output end signal of the monitoring data module is connected to an electrical data module, the output end signal of the electrical data module is connected to an independent feature module, and the output end signal of the independent feature module is connected to a data storage module.

[0008] Preferably, the model building unit includes a data processing module, the output end signal of the data processing module is connected to the government data module, the output end signal of the government data module is connected to the operating cost module, the output end signal of the operating cost module is connected to the risk cost module, and the output end signal of the risk cost module is connected to the equipment control module.

[0009] Preferably, the constraint management unit includes a power supply termination module, the output end signal of the power supply termination module is connected to the system constraint module, the output end signal of the system constraint module is connected to the constraint equation module, the output end signal of the constraint equation module is connected to the line safety constraint module, the output end signal of the line safety constraint module is connected to the grade scoring constraint module, and the output end signal of the grade scoring constraint module is connected to the adjustment time termination module.

[0010] A smart urban management method based on three-dimensional real-scene, comprising the following steps:

[0011] S1. Data Collection

[0012] Responsible for the collection of real-life 3D data, including the use of various technologies and tools to obtain real-life data from every corner of the city, such as using drones for aerial photography, combined with ground photography and measurement equipment to ensure the comprehensiveness and accuracy of the data;

[0013] S2. Data Processing

[0014] Processing the collected raw data, using image recognition, application of Geographic Information System (GIS) technology, as well as cleaning, correcting and optimizing the data;

[0015] S3. Information Management

[0016] Responsible for managing and publishing processed data, integrating the processed 3D data into a visual platform, so that managers and users can intuitively view and analyze various aspects of urban management, such as traffic flow, building distribution, environmental conditions, etc.;

[0017] S4. Build a management model

[0018] Using 3D modeling software such as smart3D and Capture, a 3D real-scene management model of the corresponding area is constructed based on 2D map data, and real-time 3D real-scene display is performed in conjunction with camera monitoring;

[0019] S5. Algorithm solution

[0020] The area is divided by routes and independent objects. According to the predicted values ​​of electricity, manpower and other demand in each distributed area, the NSGA algorithm is used to solve the scheduling optimization model and determine the Pareto algorithm set.

[0021] S6. Optimization and adjustment

[0022] According to the daily scheduling optimization target data of the distributed area to be adjusted, the optimal solution that meets the daily adjustment optimization target is selected from the Pareto algorithm set as the daily adjustment optimization plan for the distributed area to be adjusted.

[0023] Preferably, in step S1, during the collection of real-scene three-dimensional data, data collection is performed based on high-precision two-dimensional map information of roads and independent features, and elevation information of roads and longitudinal distribution information of bridges, tunnels or intersecting and overlapping roads are collected at the same time.

[0024] Preferably, in step S2, a high-precision three-dimensional terrain scene is established, and road screening and parameter setting are performed based on two-dimensional map information and longitudinal distribution information to form initial linear data of the road. The acquired road parameters are then analyzed and fused with the three-dimensional scene coordinate data to construct a three-dimensional model based on the road space. The three-dimensional real-scene model of the target area is obtained by using drone oblique photography technology. Finally, image recognition and geographic information system (GIS) technology are used to complete data cleaning, correction and optimization.

[0025] Preferably, in step S4, when constructing the management model, specifically including

[0026] Min=(C power ex +C gas buy +C equ om +C load dr )

[0027] =∑ 24 t＝1 {(C t buy +C t sell ) t EX / 2+(C t buy-C t sell ) t EX / 2}+∑ 24 t＝1 G t CHP C gas +∑ 24 t＝1 ∑ Np t＝1 δ t i f(P t i )+∑ 24 t＝1 c dr P t dr

[0028] Where C power ex is the regional electricity usage, C gas buy is the gas consumption, C equ om The cost of operating and maintaining the power-consuming equipment on the previous day is C load dr P is the labor subsidy for participating in the day-ahead scheduling. t EX is the interconnection line power at time t, C t buy and C t sell is the time-of-use electricity purchase and sale price, G t CHP is the gas purchasing power from the natural gas supplier at time t, C gas is the gas purchase price, i is the number of power supply equipment included in the power system, Np is the number of power consumption equipment, δ t i is the working state of each power consumption at time t, P t i is the power consumption value of each power-consuming device at time t, f(P t i ) is the quadratic function of the operation and maintenance cost of each power-consuming equipment, P t dr is the electric power participating in demand response at time t, c dr The cost of artificial subsidies for participating in demand response.

[0029] Preferably, in step S5, during the algorithm solving process, an adversarial network is generated based on the Wasserstein distance to generate usage scenarios, a generator and a discriminator are constructed, and the historical power consumption data, the gas consumption data and the artificial consumption data are input into the discriminator for training. The training is stopped when the set maximum number of training times is reached or the Wasserstein distance used to describe the distribution gap between the generated scenario and the real scenario meets the requirements. The distribution law of the real data is obtained unsupervisedly through the generator, and finally a scenario with a probability distribution close to the real scenario is generated. The scenario with a probability distribution close to the real scenario is the actual usage scenario.

[0030] (II) Beneficial effects

[0031] Compared with the prior art, the present invention provides a smart urban management system and method based on three-dimensional real-scene, which has the following beneficial effects:

[0032] 1. The three-dimensional real-life smart urban management system and method generates an adversarial network based on the Wasserstein distance and combines real data to generate actual usage scenarios, simulates and predicts consumption forecasts for various distributed areas, and relies on data-driven unsupervised generation of close-to-real scenarios. It has wide adaptability, increases scenario simulation from the initial data segment, improves the accuracy of prediction data, and facilitates managers to make decisions.

[0033] 2. The three-dimensional real-scene-based smart urban management system and method determines the Pareto algorithm set to meet the daily allocation plan of different areas to be adjusted in different time periods, making the three-dimensional real-scene management model richer and meeting the use environment of different scenarios, thereby making the adjustment plan more comprehensive and flexible.

[0034] 3. The smart urban management system and method based on three-dimensional real-life scenarios has established a more comprehensive day-ahead optimization scheduling objective function, thereby improving the daily allocation plan for different areas to be adjusted. The establishment of three-dimensional real-life scenarios can more intuitively observe the consumption rate of the areas under its jurisdiction, alleviate the pressure of manual management, reduce the total cost of system operation, and meet the full scheduling and allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of the three-dimensional real-scene smart urban management system of the present invention;

[0036] Figure 2 It is a flow chart of the three-dimensional real-scene smart urban management method of the present invention.

[0037] In the figure: 1. Extract data unit; 11. Map acquisition data module; 12. Road information collection module; 13. Three-dimensional data acquisition module; 14. Monitoring data module; 15. Electrical data module; 16. Independent feature module; 17. Data storage module; 2. Model building unit; 21. Data processing module; 22. Government data module; 23. Operation cost module; 24. Risk cost module; 25. Equipment control module; 3. Constraint management unit; 31. Power end module; 32. System constraint module; 33. Constraint equation module; 34. Line safety constraint module; 35. Grade scoring constraint module; 36. Adjust time end module. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0039] See also Figure 1-2 , the present invention provides a technical solution:

[0040] A smart urban management system based on three-dimensional reality includes a data extraction unit 1, the output end signal of the data extraction unit 1 is connected to a model construction unit 2, and the output end signal of the model construction unit 2 is connected to a constraint management unit 3.

[0041] Furthermore, the data extraction unit 1 includes a map acquisition data module 11, the output end signal of the map acquisition data module 11 is connected to the road information acquisition module 12, the output end signal of the road information acquisition module 12 is connected to the three-dimensional data acquisition module 13, the output end signal of the three-dimensional data acquisition module 13 is connected to the monitoring data module 14, the output end signal of the monitoring data module 14 is connected to the electrical data module 15, the output end signal of the electrical data module 15 is connected to the independent terrain module 16, and the output end signal of the independent terrain module 16 is connected to the data storage module 17.

[0042] Furthermore, the model building unit 2 includes a data processing module 21, the output end signal of the data processing module 21 is connected to the government data module 22, the output end signal of the government data module 22 is connected to the operating cost module 23, the output end signal of the operating cost module 23 is connected to the risk cost module 24, and the output end signal of the risk cost module 24 is connected to the equipment control module 25.

[0043] Furthermore, the constraint management unit 3 includes a power supply termination module 31, the output end signal of the power supply termination module 31 is connected to the system constraint module 32, the output end signal of the system constraint module 32 is connected to the constraint equation module 33, the output end signal of the constraint equation module 33 is connected to the line safety constraint module 34, the output end signal of the line safety constraint module 34 is connected to the grade scoring constraint module 35, and the output end signal of the grade scoring constraint module 35 is connected to the adjustment time termination module 36.

[0044] A smart urban management method based on three-dimensional real-scene, comprising the following steps:

[0045] S1. Data Collection

[0046] Responsible for the collection of real-life 3D data, including the use of various technologies and tools to obtain real-life data from every corner of the city, such as using drones for aerial photography, combined with ground photography and measurement equipment to ensure the comprehensiveness and accuracy of the data. In the process of collecting real-life 3D data, data collection is based on high-precision 2D map information of roads and independent features, while also collecting road elevation information and longitudinal distribution information of bridges, tunnels or overlapping roads;

[0047] S2. Data Processing

[0048] Processing the collected raw data, using image recognition, application of Geographic Information System (GIS) technology, as well as cleaning, correcting and optimizing the data;

[0049] S3. Information Management

[0050] Responsible for managing and publishing processed data, integrating the processed 3D data into a visual platform, so that managers and users can intuitively view and analyze various aspects of urban management, such as traffic flow, building distribution, environmental conditions, etc., establish high-precision 3D terrain scenes, and perform road screening and parameter setting based on 2D map information and longitudinal distribution information to form the initial linear data of the road. Then, the acquired road parameters and 3D scene coordinate data are analyzed and integrated to construct a 3D model based on the road space. The 3D real-life model of the target area is obtained by using drone oblique photography technology. Finally, image recognition and geographic information system (GIS) technology are used to clean, correct and optimize the data.

[0051] S4. Build a management model

[0052] Using 3D modeling software such as smart3D and Capture, a 3D real-scene management model of the corresponding area is constructed based on 2D map data, and real-time 3D real-scene display is performed in conjunction with camera monitoring. The management model is constructed, specifically including

[0053] Min=(C power ex +C gas buy +C equ om +C load dr )

[0054] =∑ 24 t＝1 {(C t buy +C t sell ) t EX / 2+(C t buy -C t sell ) t EX / 2}+∑ 24 t＝1 G t CHP C gas +∑ 24 t＝1 ∑ Np t＝1 δ t i f(P t i )+∑ 24 t＝1 c dr P t dr

[0055] Where C power ex is the regional electricity usage, C gas buy is the gas consumption, C equ om The cost of operating and maintaining the power-consuming equipment on the previous day is C load dr P is the labor subsidy for participating in the day-ahead scheduling. t EX is the interconnection line power at time t, C t buy and C t sell is the time-of-use electricity purchase and sale price, G t CHP is the gas purchasing power from the natural gas supplier at time t, C gas is the gas purchase price, i is the number of power supply equipment included in the power system, Np is the number of power consumption equipment, δ ti is the working state of each power consumption at time t, P t i is the power consumption value of each power-consuming device at time t, f(P t i ) is the quadratic function of the operation and maintenance cost of each power-consuming equipment, P t dr is the electric power participating in demand response at time t, c dr Subsidy costs for demand response participation;

[0056] S5. Algorithm solution

[0057] The area is divided by routes and independent objects. According to the predicted values ​​of electricity, manpower and other demand in each distributed area, the NSGA algorithm is used to solve the scheduling optimization model and determine the Pareto algorithm set.

[0058] S6. Optimization and adjustment

[0059] According to the daily scheduling optimization target data of the distributed area to be adjusted, the optimal solution that meets the daily adjustment optimization target is selected from the Pareto algorithm set as the daily adjustment optimization plan for the distributed area to be adjusted. In the algorithm solving process, an adversarial network is generated based on the Wasserstein distance to generate usage scenarios, and a generator and a discriminator are constructed. The historical power consumption data, gas consumption data, and labor consumption data are input into the discriminator for training. The training is stopped when the set maximum number of training times is reached or the Wasserstein distance used to describe the distribution gap between the generated scenario and the real scenario meets the requirements. The distribution law of the real data is obtained unsupervisedly through the generator, and finally a scenario with a probability distribution close to the real scenario is generated. The scenario with a probability distribution close to the real scenario is the actual usage scenario.

[0060] The three-dimensional real-life intelligent urban management system and method generates an adversarial network based on the Wasserstein distance and combines real data to generate actual usage scenarios, simulates and predicts consumption forecast values ​​for each distributed area, and relies on data-driven unsupervised generation of close-to-real scenarios. It has wide adaptability, increases scenario simulation from the initial data segment, improves the accuracy of the prediction value data, and facilitates managers to make decisions. By determining the Pareto algorithm set, the daily allocation plan of different areas to be adjusted in different time periods is met, making the three-dimensional real-life management model richer and meeting the use environment of different scenarios, so that the adjustment plan is more sufficient and flexible. By establishing a more comprehensive day-ahead optimization scheduling objective function, the daily allocation plan of different areas to be adjusted is improved, and the establishment of a three-dimensional real scene more intuitively observes the consumption rate of the area under its jurisdiction, relieves the pressure of manual management, reduces the total cost of system operation, and meets the full scheduling and allocation of resources.

[0061] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart urban management system based on three-dimensional real-life scene, comprising a data extraction unit (1), characterized in that: The output end signal of the data extraction unit (1) is connected to the model construction unit (2), and the output end signal of the model construction unit (2) is connected to the constraint management unit (3).

2. According to claim 1, a three-dimensional real-scene intelligent urban management system is characterized by: The data extraction unit (1) comprises a map acquisition data module (11), the output end signal of the map acquisition data module (11) is connected to a road information acquisition module (12), the output end signal of the road information acquisition module (12) is connected to a three-dimensional data acquisition module (13), the output end signal of the three-dimensional data acquisition module (13) is connected to a monitoring data module (14), the output end signal of the monitoring data module (14) is connected to an electrical data module (15), the output end signal of the electrical data module (15) is connected to an independent land feature module (16), and the output end signal of the independent land feature module (16) is connected to a data storage module (17).

3. According to claim 1, a three-dimensional real-scene intelligent urban management system is characterized by: The model building unit (2) comprises a data processing module (21), the output end signal of the data processing module (21) is connected to a government data module (22), the output end signal of the government data module (22) is connected to an operating cost module (23), the output end signal of the operating cost module (23) is connected to a risk cost module (24), and the output end signal of the risk cost module (24) is connected to an equipment control module (25).

4. The three-dimensional real-scene smart urban management system according to claim 1 is characterized in that: The constraint management unit (3) comprises a power end module (31), the output end signal of the power end module (31) is connected to a system constraint module (32), the output end signal of the system constraint module (32) is connected to a constraint equation module (33), the output end signal of the constraint equation module (33) is connected to a line safety constraint module (34), the output end signal of the line safety constraint module (34) is connected to a grade scoring constraint module (35), and the output end signal of the grade scoring constraint module (35) is connected to an adjustment time end module (36).

5. A smart urban management method based on three-dimensional real-life scene, characterized in that: The following steps are involved: S1. Data Collection Responsible for the collection of real-life 3D data, including the use of various technologies and tools to obtain real-life data from every corner of the city, such as using drones for aerial photography, combined with ground photography and measurement equipment to ensure the comprehensiveness and accuracy of the data; S2. Data Processing Processing the collected raw data, using image recognition, application of Geographic Information System (GIS) technology, as well as cleaning, correcting and optimizing the data; S3. Information Management Responsible for managing and publishing processed data, integrating the processed 3D data into a visual platform, so that managers and users can intuitively view and analyze various aspects of urban management, such as traffic flow, building distribution, environmental conditions, etc.; S4. Build a management model Using 3D modeling software such as smart3D and Capture, a 3D real-scene management model of the corresponding area is constructed based on 2D map data, and real-time 3D real-scene display is performed in conjunction with camera monitoring; S5. Algorithm solution The area is divided by routes and independent objects. According to the predicted values ​​of electricity, manpower and other demand in each distributed area, the NSGA algorithm is used to solve the scheduling optimization model and determine the Pareto algorithm set. S6. Optimization and adjustment According to the daily scheduling optimization target data of the distributed area to be adjusted, the optimal solution that meets the daily adjustment optimization target is selected from the Pareto algorithm set as the daily adjustment optimization plan for the distributed area to be adjusted.

6. A smart urban management method based on three-dimensional real scene according to claim 5, characterized in that: In step S1, during the collection of real-scene three-dimensional data, data collection is performed based on high-precision two-dimensional map information of roads and independent objects, and at the same time, elevation information of roads and longitudinal distribution information of bridges, tunnels or intersecting and overlapping roads are collected.

7. The method of intelligent urban management based on three-dimensional real scene according to claim 5 is characterized in that: In the step S2, a high-precision three-dimensional terrain scene is established, and road screening and parameter setting are performed based on the two-dimensional map information and the longitudinal distribution information to form the initial linear data of the road. The acquired road parameters are then analyzed and integrated with the three-dimensional scene coordinate data to construct a three-dimensional model based on the road space. The three-dimensional real-scene model of the target area is obtained by using the drone oblique photography technology. Finally, the data is cleaned, corrected and optimized by using image recognition and geographic information system (GIS) technology.

8. The method of intelligent urban management based on three-dimensional real scene according to claim 5 is characterized in that: In step S4, when constructing the management model, specifically including Min=(C power ex +C gas buy +C equ om +C load dr ) =∑ 24 t＝1 {(C t buy +C t sell )P t EX / 2+(C t buy -C t sell )P t EX / 2}+∑ 24 t＝1 G t CHP C gas +∑ 24 t＝1 ∑ Np t＝1 δ t i f(P t i )+∑ 24 t＝1 c dr P t dr Where C power ex is the regional electricity usage, C gas buy is the gas consumption, C equ om The cost of operating and maintaining the power-consuming equipment on the previous day is C load dr P is the labor subsidy for participating in the day-ahead scheduling. t EX is the interconnection line power at time t, C t buy and C t sell is the time-of-use electricity purchase and sale price, G t CHP is the gas purchasing power from the natural gas supplier at time t, C gas is the gas purchase price, i is the number of power supply equipment included in the power system, Np is the number of power consumption equipment, δ t i is the working state of each power consumption at time t, P t i is the power consumption value of each power-consuming device at time t, f(P t i ) is the quadratic function of the operation and maintenance cost of each power-consuming equipment, P t dr is the electric power participating in demand response at time t, c dr The cost of artificial subsidies for participating in demand response.

9. The method of intelligent urban management based on three-dimensional real scene according to claim 5 is characterized in that: In the step S5, during the algorithm solving process, an adversarial network is generated based on the Wasserstein distance to generate usage scenarios, a generator and a discriminator are constructed, and the historical power consumption data, the gas consumption data and the artificial consumption data are input into the discriminator for training. The training is stopped when the set maximum number of training times is reached or the Wasserstein distance used to describe the distribution gap between the generated scenario and the real scenario meets the requirements. The distribution law of the real data is obtained unsupervisedly through the generator, and finally a scenario with a probability distribution close to the real scenario is generated. The scenario with a probability distribution close to the real scenario is the actual usage scenario.

Images