Smart city data processing system and method

Abstract

The invention discloses a smart city data processing system and method, and relates to the field of city data processing, and the method comprises the steps: obtaining the driving dynamic information of an automatic driving vehicle, and building an intelligent driving data set; acquiring distribution conditions of traffic roads and traffic indicating lamps of the exclusive intelligent driving city, and establishing a basic information set of the traffic roads and the traffic indicating lamps of the existing city; obtaining all-around information of each traffic intersection, and establishing a field image data set; acquiring a starting delay coefficient of the automatic driving vehicle and a passing rate of the automatic driving vehicle on the same lane on the same road per minute; acquiring a congestion delay coefficient of pedestrians in all directions of the traffic intersection; establishing an optimization model of the traffic indicating lamp, and screening out the optimal time setting of the traffic indicating lamp; and a man-machine interaction display platform is established and is used for receiving, displaying, storing and checking traffic information of the whole city. The method has the advantages that the traffic efficiency of intelligent driving is effectively improved, the optimal time setting of the traffic indication lamp is intelligently distributed, and the vehicle congestion phenomenon is reduced.

Description

Technical Field

[0001] The present invention relates to the field of urban data processing, and in particular to a smart city data processing system and method. Background Art

[0002] With the development of the intelligent era and the maturity of intelligent driving systems, more and more intelligent driving vehicles have taken to urban roads. Ensuring the safety and efficiency of intelligent driving is an important task to ensure urban safety. Therefore, while intelligent driving vehicles are adapting to urban rules, cities also need to provide effective technical means and upgrade traffic rules to ensure the safety and efficiency of intelligent driving.

[0003] Existing technologies mainly focus on the multi-dimensional and reasonable evaluation of the quality of urban road traffic. For example, Chinese patent CN117173899A discloses "a smart city data processing method". This technology divides the roads in the city into various levels according to their levels, and selects representative roads from the various levels of roads, and then monitors the road conditions, driving status and road surface status of the representative roads. According to the monitoring results, the traffic congestion index, driving violation index, traffic risk index and road surface quality coefficient of the urban roads are analyzed, and they are used as evaluation parameters for comprehensive evaluation of the quality of traffic. In this way, by fully focusing on people and objects, a multi-dimensional and reasonable evaluation of the quality of urban road traffic is achieved. However, this type of technology focuses on the evaluation of traffic quality, lacks methods to deal with traffic congestion, and is difficult to improve the efficiency and intelligence of intelligent driving, and is difficult to meet the needs of intelligent driving. At the same time, it also greatly increases the management burden of intelligent driving in cities. Summary of the invention

[0004] In order to solve the above-mentioned technical problems, a smart city data processing system and method are provided. This technical solution solves the problem that there is a lack of methods to deal with traffic congestion proposed in the above-mentioned background technology, it is difficult to improve the efficiency and intelligence of intelligent driving, it is difficult to meet the needs of intelligent driving, and it also greatly increases the management burden of intelligent driving in cities.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is: A smart city data processing method, comprising: According to the intelligent driving cloud database, the driving dynamic information of the autonomous driving vehicle is obtained and the intelligent driving data set is established; According to the urban road distribution map, obtain the distribution of intelligent driving-specific urban traffic roads and traffic lights, and establish a basic information set of existing urban traffic roads and traffic lights; According to the distribution of traffic lights, image acquisition devices are set up to obtain all-round information of each traffic intersection and establish a field image data set; Based on the intelligent driving data set, the startup delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute are obtained; According to the on-site image dataset, the congestion delay coefficient of pedestrians in all directions of the traffic intersection is obtained; According to the start-up delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians at all directions at the traffic intersection, an optimization model for the traffic indicator light is established based on the neural network model to screen out the optimal time setting for the traffic indicator light. Establish a human-computer interactive display platform to receive, display, store and view the city's traffic information.

[0006] Preferably, obtaining the driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establishing the intelligent driving data set specifically includes: According to the Zhijia cloud database, the driving dynamic information of the autonomous driving vehicle is obtained, wherein the driving dynamic information of the autonomous driving vehicle includes: vehicle location information, driving speed, road information, start delay time, vehicle body length and vehicle spacing information; Based on the information of the vehicles on the same road, count and organize the number of autonomous driving vehicles in different lanes of the same road; An intelligent driving dataset is established based on the driving dynamics information of autonomous driving vehicles and the number of autonomous driving vehicles in different lanes of the same road.

[0007] Preferably, the obtaining of the distribution of smart driving-specific urban traffic roads and traffic lights according to the urban road distribution map and establishing a basic information set of existing urban traffic roads and traffic lights specifically includes: According to the urban road distribution map, obtain the distribution of intelligent driving-exclusive urban traffic roads and traffic lights, and number each intelligent driving-exclusive urban traffic road and traffic light; Through big data, we can obtain basic information about the city traffic roads and traffic lights that are exclusive to smart driving, including the total length of the road, the positions of the traffic lights, and the waiting time for different colors. Based on the distribution and basic information of intelligent driving-specific urban traffic roads and traffic lights, a basic information set of existing urban traffic roads and traffic lights is established.

[0008] Preferably, the image acquisition device is set according to the distribution of traffic lights to obtain all-round information of each traffic intersection and establish a field image data set, which specifically includes: According to the distribution of traffic lights on smart driving-exclusive urban roads, an image acquisition device is set up at each traffic light intersection; Through the image acquisition device, on-site image information from all directions of the traffic intersection is collected in real time and in all directions, and a on-site image data set is established.

[0009] Preferably, obtaining the startup delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute based on the intelligent driving data set specifically includes: Based on the intelligent driving data set, the driving dynamic information of the autonomous driving vehicle and the number of autonomous driving vehicles in different lanes on the same road are normalized to eliminate the dimensionality impact of the data; Based on the processed driving dynamic information of the autonomous driving vehicle and the number of autonomous driving vehicles in different lanes on the same road, a start delay coefficient of the autonomous driving vehicles in the same lane on the same road is established; Based on the start-up delay coefficient of the autonomous vehicle, the traffic rate of autonomous vehicles on the same road and lane per minute is established; The expression of the start delay coefficient of the automatic driving vehicle on the same road and lane is:

[0010] In the formula, is the start delay coefficient of the autonomous driving vehicle on the same road and lane, is the balance factor, For the The start delay time of an autonomous vehicle (in seconds), is the number of autonomous driving vehicles on the same road and lane, is the distance between autonomous driving vehicles on the same road and lane, is the standard safe vehicle distance, represents the Euclidean norm; The expression for the traffic rate of autonomous driving vehicles on the same road and lane per minute is:

[0011] In the formula, is the traffic rate of autonomous driving vehicles on the same road and lane per minute, is the error factor, For the The time it takes for an autonomous vehicle to pass through a traffic intersection.

[0012] Preferably, obtaining the congestion delay coefficient of pedestrians in all directions of the traffic intersection according to the on-site image data set specifically includes: According to the on-site image data set, grayscale processing is performed on the image data set pictures; According to the grayscale processed on-site image data set, the Gaussian filtering algorithm is used to further optimize the on-site image data set; According to the optimized scene image data set, based on the LBP algorithm, the texture information and shadow area information of pedestrians in each direction in the scene image data set are extracted; According to the texture information and shadow area information of pedestrians in various directions in the field image data set, the congestion delay coefficient of pedestrians in various directions at the traffic intersection is established; The LBP algorithm is:

[0013] In the formula, is the center pixel of the i-th window The value of is the center pixel of the i-th window, is the grayscale value of the p-th pixel in the on-site image dataset, is the symbolic function, is the grayscale value of the scene image dataset of the central pixel of the i-th window, is the pixel other than the center pixel of the window pixels; The congestion delay coefficient expression of pedestrians in various directions at the traffic intersection is:

[0014] In the formula, is the congestion delay coefficient of pedestrians at each direction of the traffic intersection, is the equilibrium constant term, For the The length of the pedestrian crossing on the road, is the average speed of pedestrians, is the number of on-site image data pictures collected from the first pass to the second pass, is the shadow area of ​​pedestrians in each direction in the scene image dataset, It is the standard shadow area of ​​pedestrians in various directions in the scene image dataset.

[0015] Preferably, the optimization model of the traffic indicator light is established based on a neural network model according to the startup delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians in all directions at the traffic intersection, and the optimal time setting of the traffic indicator light is selected, which specifically includes: According to the start-up delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute, an input matrix of the start-up delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute is established based on big data; According to the congestion delay coefficients of pedestrians in various directions at the traffic intersection, a congestion delay coefficient matrix of pedestrians in various directions at the traffic intersection is established based on big data; Combine the start delay coefficient of the autonomous driving vehicle, the traffic rate input matrix of the autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient input matrix of pedestrians in all directions at the traffic intersection as the input matrix of the neural network; According to the generated neural network input matrix, based on the neural network model, an optimization model of the traffic light is established, and the optimal time setting of the traffic light is screened out through the model.

[0016] Preferably, the establishment of a human-computer interactive display platform for receiving, displaying, storing and viewing the city's traffic information specifically includes: Based on digital twin technology, a human-computer interactive display platform is established to receive, display, store and view the city's traffic information; Based on the human-computer interactive display platform, it is used to build an optimized model operating environment for traffic lights to ensure the normal operation of the program; Based on the human-computer interactive display platform, it is used to optimize and update the optimization model of traffic indicator lights, as well as modify and set parameters.

[0017] Furthermore, the present solution proposes a smart city data processing system for implementing the smart city data processing method as described above, comprising: A data acquisition and processing module, which is used to obtain the driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establish an intelligent driving data set; obtain the distribution of intelligent driving-exclusive urban traffic roads and traffic lights according to the urban road distribution map, and establish a basic information set of existing urban traffic roads and traffic lights; according to the distribution of traffic lights, set up an image acquisition device to obtain all-round information of each traffic intersection and establish a field image data set; An optimal time setting module, the optimal time setting module is used to obtain the start delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute according to the intelligent driving data set; obtain the congestion delay coefficient of pedestrians in all directions of the traffic intersection according to the on-site image data set; according to the start delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute and the congestion delay coefficient of pedestrians in all directions of the traffic intersection, establish an optimization model of the traffic indicator light based on the neural network model, and screen out the optimal time setting of the traffic indicator light; A human-computer interaction platform module is used to establish a human-computer interaction display platform for receiving, displaying, storing and viewing the city's traffic information.

[0018] Preferably, the data acquisition and processing module specifically includes: An intelligent driving data unit, wherein the intelligent driving data acquisition unit is used to obtain driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establish an intelligent driving data set; A road and indicator light data unit, which is used to obtain the distribution of smart driving-exclusive urban traffic roads and traffic lights according to the urban road distribution map, and to establish a basic information set of existing urban traffic roads and traffic lights; An image data unit, wherein the image data unit is used to set an image acquisition device according to the distribution of traffic lights, obtain all-round information of each traffic intersection, and establish a field image data set; The optimal time setting module specifically includes: A vehicle delay unit, which is used to obtain all-round information of each traffic intersection based on the intelligent driving data set; A pedestrian delay unit, the pedestrian delay unit is used to obtain a congestion delay coefficient of pedestrians in various directions at the traffic intersection according to the on-site image data set; The optimization model unit is used to establish an optimization model for the traffic indicator light based on a neural network model according to the startup delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians in all directions at the traffic intersection, and screen out the optimal time setting for the traffic indicator light.

[0019] Compared with the prior art, the present invention has the following beneficial effects: By acquiring the driving dynamics information of autonomous driving vehicles, the distribution of intelligent driving-exclusive urban traffic roads and traffic lights, and all-round information of each traffic intersection, the startup delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute, as well as the congestion delay coefficient of pedestrians in all directions at the traffic intersection are established respectively to reflect the impact of intelligent driving vehicles and pedestrians on the time limit of the traffic indicator light. Based on the neural network model, an optimization model of the traffic indicator light is established, so as to effectively screen out the optimal time setting of the traffic indicator light, so as to effectively improve the traffic efficiency of intelligent driving, intelligently allocate the optimal time setting of the traffic indicator light, and reduce vehicle congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of a smart city data processing method of the present invention; Figure 2 A flow chart of obtaining the startup delay coefficient of an autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute according to an intelligent driving data set of the present invention; Figure 3 The present invention is a flow chart of obtaining the congestion delay coefficient of pedestrians in all directions at a traffic intersection based on a live image data set. DETAILED DESCRIPTION

[0021] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0022] Reference Figure 1 As shown, a smart city data processing method includes: According to the intelligent driving cloud database, the driving dynamic information of the autonomous driving vehicle is obtained and the intelligent driving data set is established; According to the urban road distribution map, obtain the distribution of intelligent driving-specific urban traffic roads and traffic lights, and establish a basic information set of existing urban traffic roads and traffic lights; According to the distribution of traffic lights, image acquisition devices are set up to obtain all-round information of each traffic intersection and establish a field image data set; Based on the intelligent driving data set, the startup delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute are obtained; According to the on-site image dataset, the congestion delay coefficient of pedestrians in all directions of the traffic intersection is obtained; According to the start-up delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians at all directions at the traffic intersection, an optimization model for the traffic indicator light is established based on the neural network model to screen out the optimal time setting for the traffic indicator light. Establish a human-computer interactive display platform to receive, display, store and view the city's traffic information.

[0023] It can be explained that this scheme obtains the driving dynamic information of the autonomous driving vehicle, the distribution of urban traffic roads and traffic lights dedicated to intelligent driving, and all-round information of each traffic intersection, and establishes the start-up delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute, as well as the congestion delay coefficient of pedestrians in all directions at the traffic intersection, which are used to reflect the impact of intelligent driving vehicles and pedestrians on the time limit of the traffic indicator light, and establishes an optimization model of the traffic indicator light based on the neural network model, so as to effectively screen out the optimal time setting of the traffic indicator light, so as to effectively improve the traffic efficiency of intelligent driving, intelligently allocate the optimal time setting of the traffic indicator light, and reduce vehicle congestion.

[0024] Reference Figure 2 As shown, the method of obtaining the startup delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute based on the intelligent driving data set specifically includes: Based on the intelligent driving data set, the driving dynamic information of the autonomous driving vehicle and the number of autonomous driving vehicles in different lanes on the same road are normalized to eliminate the dimensionality impact of the data; Based on the processed driving dynamic information of the autonomous driving vehicle and the number of autonomous driving vehicles in different lanes on the same road, a start delay coefficient of the autonomous driving vehicles in the same lane on the same road is established; Based on the start-up delay coefficient of the autonomous vehicle, the traffic rate of autonomous vehicles on the same road and lane per minute is established; The expression of the start delay coefficient of the automatic driving vehicle on the same road and lane is:

[0025] In the formula, is the start delay coefficient of the autonomous driving vehicle on the same road and lane, is the balance factor, For the The start delay time of an autonomous vehicle (in seconds), is the number of autonomous driving vehicles on the same road and lane, is the distance between autonomous driving vehicles on the same road and lane, is the standard safe vehicle distance, represents the Euclidean norm; The expression for the traffic rate of autonomous driving vehicles on the same road and lane per minute is:

[0026] In the formula, is the traffic rate of autonomous driving vehicles on the same road and lane per minute, is the error factor, For the The time it takes for an autonomous vehicle to pass through a traffic intersection.

[0027] It can be explained that when an autonomous driving vehicle is waiting at a red light, there will be a delay time in the starting process. As the number of vehicles in a single channel increases, the cumulative effect of the delay time will become more and more obvious, which will have a greater impact on improving the optimization of traffic indicator light time control. Therefore, this scheme effectively reduces the impact of the cumulative effect of this delay time by establishing the starting delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute, improves the accuracy of autonomous driving vehicle traffic control and traffic indicator light time control, and ensures the accuracy of urban traffic data processing.

[0028] Reference Figure 3 As shown, the method of obtaining the congestion delay coefficient of pedestrians in all directions at the traffic intersection according to the on-site image data set specifically includes: According to the on-site image data set, grayscale processing is performed on the image data set pictures; According to the grayscale processed on-site image data set, the Gaussian filtering algorithm is used to further optimize the on-site image data set; According to the optimized scene image data set, based on the LBP algorithm, the texture information and shadow area information of pedestrians in each direction in the scene image data set are extracted; According to the texture information and shadow area information of pedestrians in various directions in the field image data set, the congestion delay coefficient of pedestrians in various directions at the traffic intersection is established; The LBP algorithm is:

[0029] In the formula, is the center pixel of the i-th window The value of is the center pixel of the i-th window, is the grayscale value of the p-th pixel in the on-site image dataset, is the symbolic function, is the grayscale value of the scene image dataset of the central pixel of the i-th window, is the pixel other than the center pixel of the window pixels; The congestion delay coefficient expression of pedestrians in various directions at the traffic intersection is:

[0030] In the formula, is the congestion delay coefficient of pedestrians at each direction of the traffic intersection, is the equilibrium constant term, For the The length of the pedestrian crossing on the road, is the average speed of pedestrians, is the number of on-site image data pictures collected from the first pass to the second pass, is the shadow area of ​​pedestrians in each direction in the scene image dataset, It is the standard shadow area of ​​pedestrians in various directions in the scene image dataset.

[0031] It can be explained that while considering the start-up delay of smart driving vehicles, it is also necessary to consider the impact of pedestrians on road traffic. The delay caused by the congestion of pedestrians in various directions at traffic intersections will also lead to inaccurate optimization control of the traffic indicator light time. This solution uses an image acquisition device to collect on-site image data of each intersection in real time, and obtains the shadow area of ​​pedestrians in various directions by analyzing the on-site image data, thereby establishing a congestion delay coefficient for pedestrians in various directions at the traffic intersection, thereby reducing the delay caused by pedestrian congestion and further improving the accuracy of autonomous driving vehicle traffic control and traffic indicator light time control.

[0032] Further, based on the same inventive concept as the above-mentioned smart city data processing method, this solution proposes a smart city data processing system, including: A data acquisition and processing module, which is used to obtain the driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establish an intelligent driving data set; obtain the distribution of intelligent driving-exclusive urban traffic roads and traffic lights according to the urban road distribution map, and establish a basic information set of existing urban traffic roads and traffic lights; according to the distribution of traffic lights, set up an image acquisition device to obtain all-round information of each traffic intersection and establish a field image data set; An optimal time setting module, the optimal time setting module is used to obtain the start delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute according to the intelligent driving data set; obtain the congestion delay coefficient of pedestrians in all directions of the traffic intersection according to the on-site image data set; according to the start delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute and the congestion delay coefficient of pedestrians in all directions of the traffic intersection, establish an optimization model of the traffic indicator light based on the neural network model, and screen out the optimal time setting of the traffic indicator light; A human-computer interaction platform module, which is used to establish a human-computer interaction display platform for receiving, displaying, storing and viewing the city's traffic information; The data acquisition and processing modules specifically include: An intelligent driving data unit, wherein the intelligent driving data acquisition unit is used to obtain driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establish an intelligent driving data set; A road and indicator light data unit, which is used to obtain the distribution of smart driving-exclusive urban traffic roads and traffic lights according to the urban road distribution map, and to establish a basic information set of existing urban traffic roads and traffic lights; An image data unit, wherein the image data unit is used to set an image acquisition device according to the distribution of traffic lights, obtain all-round information of each traffic intersection, and establish a field image data set; The optimal time setting module specifically includes: A vehicle delay unit, which is used to obtain all-round information of each traffic intersection based on the intelligent driving data set; A pedestrian delay unit, the pedestrian delay unit is used to obtain a congestion delay coefficient of pedestrians in various directions at the traffic intersection according to the on-site image data set; The optimization model unit is used to establish an optimization model for the traffic indicator light based on a neural network model according to the startup delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians in all directions at the traffic intersection, and screen out the optimal time setting for the traffic indicator light.

[0033] To sum up, the advantages of the present invention are: effectively screening out the optimal time setting of the traffic indicator light, thereby effectively improving the traffic efficiency of intelligent driving, intelligently allocating the optimal time setting of the traffic indicator light, and reducing vehicle congestion.

[0034] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A smart city data processing method, characterized in that: include: According to the intelligent driving cloud database, the driving dynamic information of the autonomous driving vehicle is obtained and the intelligent driving data set is established; According to the urban road distribution map, obtain the distribution of intelligent driving-specific urban traffic roads and traffic lights, and establish a basic information set of existing urban traffic roads and traffic lights; According to the distribution of traffic lights, image acquisition devices are set up to obtain all-round information of each traffic intersection and establish a field image data set; Based on the intelligent driving data set, the startup delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute are obtained; According to the on-site image dataset, the congestion delay coefficient of pedestrians in all directions of the traffic intersection is obtained; According to the start-up delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians at all directions at the traffic intersection, an optimization model for the traffic indicator light is established based on the neural network model to screen out the optimal time setting for the traffic indicator light. Establish a human-computer interactive display platform to receive, display, store and view the city's traffic information.

2. A smart city data processing method according to claim 1, characterized in that: The method of obtaining driving dynamic information of the autonomous driving vehicle based on the intelligent driving cloud database and establishing an intelligent driving data set specifically includes: According to the Zhijia cloud database, the driving dynamic information of the autonomous driving vehicle is obtained, wherein the driving dynamic information of the autonomous driving vehicle includes: vehicle location information, driving speed, road information, start delay time, vehicle body length and vehicle spacing information; Based on the information of the vehicles on the same road, count and organize the number of autonomous driving vehicles in different lanes of the same road; An intelligent driving dataset is established based on the driving dynamics information of autonomous driving vehicles and the number of autonomous driving vehicles in different lanes of the same road.

3. A smart city data processing method according to claim 2, characterized in that: The method of obtaining the distribution of intelligent driving-specific urban traffic roads and traffic lights according to the urban road distribution map and establishing a basic information set of existing urban traffic roads and traffic lights specifically includes: According to the urban road distribution map, obtain the distribution of intelligent driving-exclusive urban traffic roads and traffic lights, and number each intelligent driving-exclusive urban traffic road and traffic light; Through big data, we can obtain basic information about the city traffic roads and traffic lights that are exclusive to smart driving, including the total length of the road, the positions of the traffic lights, and the waiting time for different colors. Based on the distribution and basic information of intelligent driving-specific urban traffic roads and traffic lights, a basic information set of existing urban traffic roads and traffic lights is established.

4. A smart city data processing method according to claim 3, characterized in that: The image acquisition device is set according to the distribution of traffic lights to obtain all-round information of each traffic intersection and establish a field image data set, which specifically includes: According to the distribution of traffic lights on smart driving-exclusive urban roads, an image acquisition device is set up at each traffic light intersection; Through the image acquisition device, on-site image information from all directions of the traffic intersection is collected in real time and in all directions, and a on-site image data set is established.

5. A smart city data processing method according to claim 4, characterized in that: The method of obtaining the startup delay coefficient of the autonomous driving vehicle and the traffic rate of autonomous driving vehicles on the same road and lane per minute based on the intelligent driving data set specifically includes: Based on the intelligent driving data set, the driving dynamic information of the autonomous driving vehicle and the number of autonomous driving vehicles in different lanes on the same road are normalized to eliminate the dimensionality impact of the data; Based on the processed driving dynamic information of the autonomous driving vehicle and the number of autonomous driving vehicles in different lanes on the same road, a start delay coefficient of the autonomous driving vehicles in the same lane on the same road is established; Based on the start-up delay coefficient of the autonomous vehicle, the traffic rate of autonomous vehicles on the same road and lane per minute is established; The expression of the start delay coefficient of the automatic driving vehicle on the same road and lane is: ； In the formula, is the start delay coefficient of the autonomous driving vehicle on the same road and lane, is the balance factor, For the The start delay time of an autonomous vehicle (in seconds), is the number of autonomous driving vehicles on the same road and lane, is the distance between autonomous driving vehicles on the same road and lane, is the standard safe vehicle distance, represents the Euclidean norm; The expression for the traffic rate of autonomous driving vehicles on the same road and lane per minute is: ； In the formula, is the traffic rate of autonomous driving vehicles on the same road and lane per minute, is the error factor, For the The time it takes for an autonomous vehicle to pass through a traffic intersection.

6. A smart city data processing method according to claim 5, characterized in that: The method of obtaining the congestion delay coefficient of pedestrians in all directions at the traffic intersection according to the on-site image data set specifically includes: According to the on-site image data set, grayscale processing is performed on the image data set pictures; According to the grayscale processed on-site image data set, the Gaussian filtering algorithm is used to further optimize the on-site image data set; According to the optimized scene image data set, based on the LBP algorithm, the texture information and shadow area information of pedestrians in each direction in the scene image data set are extracted; According to the texture information and shadow area information of pedestrians in various directions in the field image data set, the congestion delay coefficient of pedestrians in various directions at the traffic intersection is established; The LBP algorithm is: ； In the formula, is the center pixel of the i-th window The value of is the center pixel of the i-th window, is the grayscale value of the p-th pixel in the on-site image dataset, is the symbolic function, is the grayscale value of the scene image dataset of the central pixel of the i-th window, is the pixel other than the center pixel of the window pixels; The congestion delay coefficient expression of pedestrians in various directions at the traffic intersection is: ； In the formula, is the congestion delay coefficient of pedestrians at each direction of the traffic intersection, is the equilibrium constant term, For the The length of the pedestrian crossing on the road, is the average speed of pedestrians, is the number of on-site image data pictures collected from the first pass to the second pass, is the shadow area of ​​pedestrians in each direction in the scene image dataset, It is the standard shadow area of ​​pedestrians in various directions in the scene image dataset.

7. A smart city data processing method according to claim 6, characterized in that: The method of establishing an optimization model for the traffic light based on the neural network model according to the startup delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians in all directions at the traffic intersection, and selecting the optimal time setting of the traffic light specifically includes: According to the start-up delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute, an input matrix of the start-up delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute is established based on big data; According to the congestion delay coefficients of pedestrians in various directions at the traffic intersection, a congestion delay coefficient matrix of pedestrians in various directions at the traffic intersection is established based on big data; Combine the start delay coefficient of the autonomous driving vehicle, the traffic rate input matrix of the autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient input matrix of pedestrians in all directions at the traffic intersection as the input matrix of the neural network; According to the generated neural network input matrix, based on the neural network model, an optimization model of the traffic light is established, and the optimal time setting of the traffic light is screened out through the model.

8. A smart city data processing method according to claim 7, characterized in that: The establishment of a human-computer interactive display platform for receiving, displaying, storing and viewing the city's traffic information specifically includes: Based on digital twin technology, a human-computer interactive display platform is established to receive, display, store and view the city's traffic information; Based on the human-computer interactive display platform, it is used to build an optimized model operating environment for traffic lights to ensure the normal operation of the program; Based on the human-computer interactive display platform, it is used to optimize and update the optimization model of traffic indicator lights, as well as modify and set parameters.

9. A smart city data processing system, characterized in that: A method for processing smart city data according to any one of claims 1 to 8, comprising: A data acquisition and processing module, which is used to obtain the driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establish an intelligent driving data set; obtain the distribution of intelligent driving-exclusive urban traffic roads and traffic lights according to the urban road distribution map, and establish a basic information set of existing urban traffic roads and traffic lights; according to the distribution of traffic lights, set up an image acquisition device to obtain all-round information of each traffic intersection and establish a field image data set; An optimal time setting module, the optimal time setting module is used to obtain the start delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute according to the intelligent driving data set; obtain the congestion delay coefficient of pedestrians in all directions of the traffic intersection according to the on-site image data set; according to the start delay coefficient of the autonomous driving vehicle and the traffic rate of the autonomous driving vehicles on the same road and lane per minute and the congestion delay coefficient of pedestrians in all directions of the traffic intersection, establish an optimization model of the traffic indicator light based on the neural network model, and screen out the optimal time setting of the traffic indicator light; A human-computer interaction platform module is used to establish a human-computer interaction display platform for receiving, displaying, storing and viewing the city's traffic information.

10. A smart city data processing system according to claim 9, characterized in that: The data acquisition and processing module specifically includes: An intelligent driving data unit, wherein the intelligent driving data acquisition unit is used to obtain driving dynamic information of the autonomous driving vehicle according to the intelligent driving cloud database and establish an intelligent driving data set; A road and indicator light data unit, which is used to obtain the distribution of smart driving-exclusive urban traffic roads and traffic lights according to the urban road distribution map, and to establish a basic information set of existing urban traffic roads and traffic lights; An image data unit, wherein the image data unit is used to set an image acquisition device according to the distribution of traffic lights, obtain all-round information of each traffic intersection, and establish a field image data set; The optimal time setting module specifically includes: A vehicle delay unit, the vehicle delay unit is used to obtain a start delay coefficient of the autonomous driving vehicle and a traffic rate of autonomous driving vehicles on the same road and lane per minute according to the intelligent driving data set; A pedestrian delay unit, the pedestrian delay unit is used to obtain a congestion delay coefficient of pedestrians in various directions at the traffic intersection according to the on-site image data set; The optimization model unit is used to establish an optimization model for the traffic indicator light based on a neural network model according to the startup delay coefficient of the autonomous driving vehicle, the traffic rate of autonomous driving vehicles on the same road and lane per minute, and the congestion delay coefficient of pedestrians in all directions at the traffic intersection, and screen out the optimal time setting for the traffic indicator light.

Images