Intelligent traffic light scheduling method and system based on environment interaction

Abstract

The invention discloses an intelligent traffic light scheduling method and system based on environment interaction, and relates to the related field of data processing, and the method comprises the steps: collecting traffic flow data in real time through an environment interaction network disposed at an intersection; preprocessing the traffic flow data to obtain traffic state feature information; on the basis of the traffic state feature information, according to a traffic state prediction model, predicting a traffic state change trend of a future time zone; optimizing and adjusting the traffic light timing scheme of the intersection according to the traffic state change trend to obtain a traffic light timing optimization scheme; and the traffic light timing optimization scheme is issued to an intersection signal machine, and the intersection signal machine controls traffic light switching at the intersection according to the received traffic light timing scheme. The technical problems that traffic light timing is fixed and traffic state changes cannot be dynamically responded in the prior art are solved. The technical effects of carrying out adaptive scheduling on the traffic lights according to the traffic state change, improving the road passing efficiency and reducing the traffic jam are achieved.

Description

Technical Field

[0001] This application relates to the field of data processing, and particularly to an intelligent traffic light scheduling method and system based on environmental interaction. Background Art

[0002] With the acceleration of urbanization and the rapid growth of the number of motor vehicles, the problem of traffic congestion has become increasingly serious, especially at urban intersections. The traditional fixed-duration traffic light timing scheme can no longer meet the dynamically changing traffic demands. The fixed timing scheme lacks the ability to perceive and respond to the real-time traffic state, resulting in low intersection traffic efficiency, increased vehicle queue lengths, and exacerbated traffic congestion.

[0003] In the current related technologies, there is a technical problem that the traffic light timing is fixed and cannot dynamically respond to changes in the traffic state. Summary of the Invention

[0004] This application provides an intelligent traffic light scheduling method and system based on environmental interaction, which solves the technical problem in the prior art that the traffic light timing is fixed and cannot dynamically respond to changes in the traffic state. It achieves the technical effect of adaptively scheduling traffic lights according to changes in the traffic state, improving road traffic efficiency, and reducing traffic congestion.

[0005] This application provides an intelligent traffic light scheduling method based on environmental interaction. The method is applied to an intelligent traffic light scheduling system based on environmental interaction. The method includes: using an environmental interaction network deployed at an intersection to collect traffic flow data in real time; preprocessing the traffic flow data to obtain traffic state characteristic information; based on the traffic state characteristic information, predicting the change trend of the traffic state in the future time zone according to a traffic state prediction model; optimizing and adjusting the traffic light timing scheme at the intersection according to the traffic state change trend to obtain an optimized traffic light timing scheme; sending the optimized traffic light timing scheme to the intersection signal machine, and the intersection signal machine controls the traffic light switching at the intersection according to the received traffic light timing scheme.

[0006] Preferably, using an environmental interaction network deployed at an intersection includes: obtaining the basic information of the intersection; based on the basic information of the intersection, making a decision on the layout of sensing devices for the intersection according to a predetermined sensing device factor to obtain an intersection sensing layout scheme; deploying sensing devices based on the intersection sensing layout scheme and performing interactive connection on the deployed sensing devices to obtain the environmental interaction network.

[0007] Preferably, the predetermined sensing device factor includes cameras, radars, geomagnetic sensors, and infrared sensors.

[0008] Preferably, preprocess the traffic flow data to obtain traffic state feature information, including: perform data cleaning on the traffic flow data to obtain standard traffic flow data; set traffic state feature factors, where the traffic state feature factors include traffic flow, average vehicle speed, occupancy rate of each lane, queue length in each direction, and traffic density; perform feature recognition on the standard traffic flow data according to the traffic state feature factors to obtain the traffic state feature information.

[0009] Preferably, based on the traffic state feature information, predict the traffic state change trend in the future time zone according to the traffic state prediction model, including: obtain the traffic state feature record set of the intersection; perform chronological sorting on the traffic state feature record set according to the time zone length of the future time zone to obtain a traffic state feature sorting set; perform deep learning according to the traffic state feature sorting set to build the traffic state prediction model; input the traffic state feature information and the future time zone into the traffic state prediction model, and output the traffic state change trend.

[0010] Preferably, perform deep learning according to the traffic state feature sorting set to build the traffic state prediction model, including: divide the traffic state feature sorting set according to a predetermined ratio to obtain a traffic state feature training set and a traffic state feature test set; perform supervised learning on the neural network according to the traffic state feature training set to obtain a traffic state prediction network; test the traffic state prediction network according to the traffic state feature test set to obtain traffic state prediction loss data; perform optimization learning on the traffic state prediction network according to the traffic state prediction loss data to obtain the traffic state prediction model.

[0011] Preferably, optimize and adjust the traffic light timing plan of the intersection according to the traffic state change trend to obtain an optimized traffic light timing plan, including: adjust the traffic light timing plan according to the traffic state change trend to obtain a traffic light timing adjustment plan set; set a traffic light timing optimization target, where the traffic light timing optimization target is to maximize the road traffic capacity, and the road traffic capacity is the number of vehicles passing through the intersection per unit time; perform optimization analysis on the traffic light timing adjustment plan set according to the traffic light timing optimization target to obtain the optimized traffic light timing plan.

[0012] The present application also provides an intelligent traffic light scheduling system based on environmental interaction. The system includes: a traffic flow collection module configured to use the environmental interaction network deployed at intersections to collect traffic flow data in real time; a preprocessing module configured to preprocess the traffic flow data to obtain traffic state characteristic information; a traffic state prediction module configured to predict the traffic state change trend in a future time zone based on the traffic state characteristic information according to a traffic state prediction model; a traffic light timing optimization module configured to optimize and adjust the traffic light timing scheme at the intersection according to the traffic state change trend to obtain an optimized traffic light timing scheme; and a traffic light scheduling module configured to send the optimized traffic light timing scheme to an intersection signal machine, and the intersection signal machine controls the traffic light switching at the intersection according to the received traffic light timing scheme.

[0013] The present application proposes an intelligent traffic light scheduling method and system based on environmental interaction. By using the environmental interaction network deployed at intersections, traffic flow data is collected in real time, and the traffic flow data is preprocessed to obtain traffic state characteristic information. The traffic state characteristic information is input into a traffic state prediction model to output the traffic state change trend in a future time zone. The traffic light timing scheme at the intersection is optimized and adjusted according to the traffic state change trend to obtain an optimized traffic light timing scheme. The optimized traffic light timing scheme is sent to an intersection signal machine, and the intersection signal machine controls the traffic light switching at the intersection according to the received traffic light timing scheme. This solves the technical problem in the prior art that the traffic light timing is fixed and cannot dynamically respond to traffic state changes. It achieves the technical effect of adaptively scheduling traffic lights according to traffic state changes, improving road traffic efficiency, and reducing traffic congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 It is a schematic flowchart of the intelligent traffic light scheduling method based on environmental interaction provided by an embodiment of the present application.

[0016] Figure 2 It is a schematic structural diagram of the intelligent traffic light scheduling system based on environmental interaction provided by an embodiment of the present application.

[0017] Description of the drawing reference numerals: Traffic flow collection module 1, preprocessing module 2, traffic status prediction module 3, traffic light timing optimization module 4, traffic light scheduling module 5. Detailed implementation manners

[0018] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the detailed implementation manners of the present application.

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0020] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first\second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] The embodiment of the present application provides an intelligent traffic light scheduling method based on environmental interaction. The method is applied to an intelligent traffic light scheduling system based on environmental interaction, as Figure 1 shown. The method includes:

[0022] Step S100: Use the environmental interaction network deployed at the intersection to collect traffic flow data in real time. Further, step S100 further includes steps S110 to S130. Step S110: Obtain the basic information of the intersection. Step S120: Based on the basic information of the intersection, make a decision on the layout of sensing devices for the intersection according to the predetermined sensing device factors, and obtain an intersection sensing layout plan. Step S130: Based on the intersection sensing layout plan, deploy sensing devices and perform interactive connection on the deployed sensing devices to obtain the environmental interaction network. Among them, the predetermined sensing device factors include cameras, radars, geomagnetic sensors, and infrared sensors.

[0023] It should be noted that basic parameters such as the geographical location of the intersection, the number of lanes, the lane directions, the intersection structure (such as whether it is a crossroads, a T-shaped intersection, etc.), and the surrounding environment (such as schools, commercial areas, etc.) are collected as the basic information of the intersection, so as to provide data support for the subsequent layout of sensing devices and ensure that the layout plan can meet the actual needs of the intersection. Furthermore, based on the basic information of the intersection, analyze the traffic characteristics and monitoring requirements of the intersection. Combine the predetermined sensing device factors (such as cameras, radars, geomagnetic sensors, infrared sensors, etc.) to formulate a reasonable intersection sensing layout plan. The intersection sensing layout plan is a set of scientific and reasonable sensing device deployment plans formulated according to the specific traffic characteristics and monitoring requirements of the intersection, combined with the predetermined sensing device factors (such as cameras, radars, geomagnetic sensors, infrared sensors, etc.). For example, deploy geomagnetic sensors in lanes with heavy traffic to detect vehicle passing and lane occupancy. Deploy cameras and radars at complex intersections to monitor vehicle driving trajectories, speeds, and traffic violations. Deploy infrared sensors at night or in low visibility areas to supplement the functions of other sensors. Thus, ensure that the layout of sensing devices can fully cover the traffic monitoring needs of the intersection and provide a hardware basis for data collection.

[0024] Taking a crossroads as an example, the intersection sensing layout plan includes deploying 1 camera at the entrance and exit of each of the four directions, a total of 8 cameras. Deploy 2 geomagnetic sensors in each lane to detect vehicle passing. Deploy 1 radar on the side of each of the four directions to detect vehicle speed and position. Deploy 2 infrared sensors in the direction with relatively heavy traffic at night to supplement the night monitoring ability. Through such an intersection sensing layout plan, it is possible to achieve comprehensive monitoring and data collection of the intersection traffic status, providing strong support for intelligent traffic light scheduling.

[0025] Install various sensing devices (such as cameras, radars, geomagnetic sensors, infrared sensors, etc.) according to the positions and quantities determined in the intersection sensing layout plan. Connect the deployed various sensing devices by wired (such as optical fiber) or wireless (such as 5G, Wi-Fi) means to obtain an environmental interaction network. The environmental interaction network includes various sensing devices deployed according to the intersection sensing layout plan and communicatively connected. Subsequently, through the environmental interaction network, collect the data of various sensing devices in real time to obtain traffic flow data. The traffic flow data includes parameters such as vehicle driving trajectory information, vehicle speed information, vehicle position information, traffic volume, and lane occupancy rate. Through the deployment and interactive connection of sensing devices based on the intersection sensing layout plan, an efficient and reliable environmental interaction network is constructed. Using the environmental interaction network can collect traffic flow data in real time, providing strong data support for intelligent traffic light scheduling and traffic management, thereby improving traffic efficiency and reducing congestion.

[0026] Step S200: Preprocess the traffic flow data to obtain traffic state characteristic information. Further, step S200 further includes steps S210 to S230. Step S210: Clean the traffic flow data according to the traffic flow data to obtain traffic flow standard data; Step S220: Set traffic state characteristic factors, where the traffic state characteristic factors include traffic flow, average vehicle speed, occupancy rate of each lane, queue length in each direction, and traffic density; Step S230: Identify the characteristics of the traffic flow standard data according to the traffic state characteristic factors to obtain the traffic state characteristic information. Specifically, clean the traffic flow data to obtain the cleaned traffic flow standard data. Data cleaning includes: filtering out abnormal data caused by equipment failures or environmental interferences (such as extremely high or low flow values that suddenly appear), filling in missing data caused by short-term equipment offline or data transmission interruptions (such as using data interpolation at the previous and subsequent time points), unifying data from different sources into the same format and unit (such as unifying vehicle speeds to km / h and flows to vehicles per hour), deleting repeatedly collected data to ensure data uniqueness. Subsequently, extract information related to traffic state characteristic factors from the traffic flow standard data to form structured traffic state characteristic information. Traffic state characteristic factors are key indicators used to describe traffic states and can comprehensively reflect the traffic operation conditions at intersections. Traffic state characteristic factors include traffic flow, average vehicle speed, occupancy rate of each lane, queue length in each direction, and traffic density. Traffic flow is the number of vehicles passing through an intersection per unit time. Average vehicle speed is the average driving speed of vehicles passing through the intersection. The occupancy rate of each lane is the proportion of time each lane is occupied by vehicles. The queue length in each direction is the queue length of vehicles waiting to pass through the intersection in each direction. Traffic density is the number of vehicles per unit road length. Traffic state characteristic information includes traffic flow parameters, average vehicle speed parameters, occupancy rate parameters of each lane, queue length parameters in each direction, and traffic density parameters corresponding to the traffic flow standard data. Through steps S210 to S230, the cleaning, characteristic factor setting, and characteristic identification of traffic flow data are completed, and finally structured traffic state characteristic information is obtained. This process provides a high-quality data basis for intelligent traffic light scheduling and traffic state prediction.

[0027] Step S300: Based on the traffic state characteristic information, predict the traffic state change trend in the future time zone according to the traffic state prediction model. Step S300 further includes steps S310 to S340. Step S310: Obtain the traffic state characteristic record set of the intersection; Step S320: Perform chronological sorting on the traffic state characteristic record set according to the time zone length of the future time zone to obtain a traffic state characteristic sorting set. It should be noted that the traffic state characteristic record set is retrieved from the environmental interaction network. The traffic state characteristic record set includes multiple historical traffic state characteristic records of the intersection within a period of time (such as the past few days, past few weeks, or past few months). Each historical traffic state characteristic record includes the historical time, as well as the historical traffic flow parameter, historical average vehicle speed parameter, historical occupancy rate parameter of each lane, historical queue length parameter in each direction, and historical traffic density parameter corresponding to the historical time. Subsequently, according to actual requirements, determine the length of the future time zone (such as 5 minutes, 15 minutes, 1 hour, etc.). Divide the traffic state characteristic record set into multiple time windows according to the future time zone length. Interpolate or fill in the data that may be missing in some time windows to ensure data continuity. Arrange the sorted data in chronological order to form a traffic state characteristic sorting set.

[0028] By sorting the traffic state characteristic record set in chronological order to form a traffic state characteristic sorting set with time continuity, the accuracy of traffic state prediction is improved, thereby enhancing the adaptability of traffic light scheduling.

[0029] Step S330: Perform deep learning according to the traffic state characteristic sorting set to build the traffic state prediction model; Step S330 further includes steps S331 to S334. Step S331: Divide the traffic state characteristic sorting set according to a predetermined ratio to obtain a traffic state characteristic training set and a traffic state characteristic test set; Step S332: Perform supervised learning on the neural network according to the traffic state characteristic training set to obtain a traffic state prediction network; Step S333: Test the traffic state prediction network according to the traffic state characteristic test set to obtain traffic state prediction loss data; Step S334: Perform optimization learning on the traffic state prediction network according to the traffic state prediction loss data to obtain the traffic state prediction model. Step S340: Input the traffic state characteristic information and the future time zone into the traffic state prediction model, and output the traffic state change trend.

[0030] It should be noted that the traffic state feature sorting set is randomly divided according to a predetermined ratio (such as 80% training set and 20% test set) to obtain a traffic state feature training set and a traffic state feature test set. The traffic state feature training set is used to train the neural network to learn the variation law of the traffic state. The traffic state feature test set is used to evaluate the prediction performance of the model and verify its generalization ability. Subsequently, supervised learning is performed on the neural network according to the traffic state feature training set. The goal of supervised learning is to enable the neural network to learn the relationship between the traffic state features and the future traffic state changes through the traffic state feature training set. The neural network structure includes an input layer, a hidden layer, and an output layer. The supervised learning process includes: inputting the traffic state feature training set into the neural network and calculating the error between the predicted result and the actual result. The backpropagation algorithm is used to adjust the weights and biases of the neural network to gradually reduce the error. The above process is repeated until convergence or a predetermined number of training rounds is reached to obtain a preliminary traffic state prediction network.

[0031] Next, the traffic state feature test set is input into the trained traffic state prediction network to obtain the predicted result. Calculate the error between the predicted result and the actual result (such as mean square error, mean absolute error, etc.) to obtain the traffic state prediction loss data. According to the traffic state prediction loss data, adjust the model parameters or structure (i.e., optimize learning) to further reduce the prediction error and obtain an optimized traffic state prediction model. Optimization learning includes: adjusting hyperparameters such as the learning rate, the number of hidden layers, and the number of neurons; adding L1 or L2 regularization terms to prevent model overfitting; increasing the amount of training set data or introducing noise data to improve the robustness of the model. Subsequently, the traffic state feature information and the future time zone are used as input information and input into the traffic state prediction model. The traffic state prediction model outputs the traffic state change trend in the future time zone according to the learned law. The traffic state change trend includes the predicted traffic flow, predicted average vehicle speed, predicted lane occupancy rate, predicted queue length, predicted traffic density, etc. in the future time zone. The traffic state prediction model is used to reliably predict the traffic state change trend in the future time zone to achieve an intelligent traffic light scheduling that dynamically responds to traffic state changes.

[0032] Step S400, optimize and adjust the traffic light timing plan for the intersection according to the traffic state change trend to obtain an optimized traffic light timing plan. Step S400 further includes steps S410 to S430. Step S410, adjust the traffic light timing plan according to the traffic state change trend to obtain a set of traffic light timing adjustment plans; Step S420, set the traffic light timing optimization goal, where the traffic light timing optimization goal is to maximize the road traffic capacity, and the road traffic capacity is the number of vehicles passing through the intersection per unit time; Step S430, perform optimization analysis on the set of traffic light timing adjustment plans according to the traffic light timing optimization goal to obtain the optimized traffic light timing plan.

[0033] Specifically, the traffic light timing plan is dynamically adjusted according to the changing trend of traffic conditions to adapt to the changes in traffic flow. The traffic light timing adjustment plan set includes multiple traffic light timing adjustment plans. The dynamic adjustment includes queue length priority (if the queue length in a certain direction exceeds a threshold, such as 50 meters, then extend the green light time in that direction), flow priority (if the traffic flow in a certain direction increases significantly, then increase the green light time in that direction), and balance adjustment (if the traffic flow in a certain direction decreases, then appropriately reduce the green light time in that direction and allocate the time to other directions). Subsequently, traffic simulation software (such as SUMO, VISSIM) is used to simulate each traffic light timing adjustment plan, evaluate the road traffic capacity of each traffic light timing adjustment plan, and select the traffic light timing adjustment plan with the maximum road traffic capacity as the traffic light timing optimization plan. The road traffic capacity is the number of vehicles passing through the intersection per unit time. The technical effect of improving the traffic capacity of the intersection and reducing the vehicle waiting time is achieved by optimizing the green light time allocation.

[0034] In step S500, the traffic light timing optimization plan is sent to the intersection signal machine, and the intersection signal machine controls the traffic light switching at the intersection according to the received traffic light timing plan. Specifically, the traffic light timing optimization plan is transmitted to the intersection signal machine through wireless networks such as 5G, Wi-Fi, LoRa. The intersection signal machine adjusts the display time of the traffic lights in real time according to the received traffic light timing optimization plan, so as to realize the adaptive scheduling of traffic lights according to the changes in traffic conditions, improve the road traffic efficiency, and reduce traffic congestion. Among them, the intersection signal machine is an embedded device responsible for controlling the traffic light switching.

[0035] In the above text, reference is made to Figure 1 The intelligent traffic light scheduling method based on environmental interaction according to the embodiments of the present invention is described in detail. Next, reference will be made to Figure 2 Describe the intelligent traffic light scheduling system based on environmental interaction according to the embodiments of the present invention.

[0036] The intelligent traffic light scheduling system based on environmental interaction according to the embodiments of the present invention solves the technical problem that the traffic light timing in the prior art is fixed and cannot dynamically respond to the changes in traffic conditions. The technical effect of realizing the adaptive scheduling of traffic lights according to the changes in traffic conditions, improving the road traffic efficiency, and reducing traffic congestion is achieved.

[0037] Preferably, the intelligent traffic light scheduling system based on environmental interaction according to the embodiments of the present invention includes: a traffic flow collection module 1, a preprocessing module 2, a traffic condition prediction module 3, a traffic light timing optimization module 4, and a traffic light scheduling module 5.

[0038] The traffic flow collection module 1 is used to collect traffic flow data in real time by using the environmental interaction network deployed at the intersection.

[0039] The preprocessing module 2 is used to preprocess the traffic flow data to obtain traffic state feature information.

[0040] The traffic state prediction module 3 is used to predict the change trend of the traffic state in the future time zone based on the traffic state feature information according to the traffic state prediction model.

[0041] The traffic signal timing optimization module 4 is used to optimize and adjust the traffic signal timing scheme at the intersection according to the traffic state change trend to obtain an optimized traffic signal timing scheme.

[0042] The traffic signal scheduling module 5 is used to send the optimized traffic signal timing scheme to the intersection signal machine, and the intersection signal machine controls the traffic signal switching at the intersection according to the received traffic signal timing scheme.

[0043] Furthermore, the traffic flow collection module 1 is further used to: obtain the basic information of the intersection; based on the basic information of the intersection, make a decision on the layout of sensing devices at the intersection according to the predetermined sensing device factors to obtain an intersection sensing layout scheme; perform the layout of sensing devices based on the intersection sensing layout scheme, and perform interactive connection on the laid sensing devices to obtain the environmental interaction network. Wherein, the predetermined sensing device factors include cameras, radars, geomagnetic sensors, and infrared sensors.

[0044] Furthermore, the preprocessing module 2 is further used to: perform data cleaning on the traffic flow data to obtain standard traffic flow data; set traffic state feature factors, where the traffic state feature factors include traffic flow, average vehicle speed, occupancy rate of each lane, queue length in each direction, and traffic density; perform feature recognition on the standard traffic flow data according to the traffic state feature factors to obtain the traffic state feature information.

[0045] Furthermore, the traffic state prediction module 3 is further used to: obtain the traffic state feature record set of the intersection; perform chronological sorting on the traffic state feature record set according to the time zone length of the future time zone to obtain a traffic state feature sorting set; perform deep learning according to the traffic state feature sorting set to build the traffic state prediction model; input the traffic state feature information and the future time zone into the traffic state prediction model, and output the traffic state change trend.

[0046] Furthermore, the traffic state prediction module 3 is further configured to: divide the traffic state feature sorting set according to a predetermined ratio to obtain a traffic state feature training set and a traffic state feature test set; perform supervised learning on the neural network according to the traffic state feature training set to obtain a traffic state prediction network; test the traffic state prediction network according to the traffic state feature test set to obtain traffic state prediction loss data; perform optimization learning on the traffic state prediction network according to the traffic state prediction loss data to obtain the traffic state prediction model.

[0047] Furthermore, the traffic signal timing optimization module 4 is further configured to: adjust the traffic signal timing plan according to the traffic state change trend to obtain a traffic signal timing adjustment plan set; set a traffic signal timing optimization target, where the traffic signal timing optimization target is to maximize the road traffic capacity, and the road traffic capacity is the number of vehicles passing through the intersection per unit time; perform optimization analysis on the traffic signal timing adjustment plan set according to the traffic signal timing optimization target to obtain the traffic signal timing optimization plan.

[0048] The intelligent traffic signal scheduling system based on environment interaction provided by the embodiments of the present invention can execute the intelligent traffic signal scheduling method based on environment interaction provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0049] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0050] The above specific implementation manners do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. An intelligent traffic light scheduling method based on environmental interaction, characterized in that: The method comprises: Using the environmental interactive network deployed at intersections to collect traffic flow data in real time; Preprocessing the traffic flow data to obtain traffic state characteristic information; Based on the traffic state characteristic information, according to the traffic state prediction model, predict the traffic state change trend in the future time zone; According to the traffic state change trend, the traffic light timing scheme at the intersection is optimized and adjusted to obtain the traffic light timing optimization scheme; The traffic light timing optimization plan is sent to the intersection signal machine, and the intersection signal machine controls the switching of the traffic lights at the intersection according to the received traffic light timing plan.

2. The intelligent traffic light scheduling method based on environment interaction as claimed in claim 1, characterized in that: Utilize the environment interaction network deployed at the intersection, including: Obtaining basic intersection information of the intersection; Based on the basic information of the intersection, making a sensor equipment deployment decision for the intersection according to a predetermined sensor equipment factor, and obtaining a sensor deployment plan for the intersection; Based on the intersection sensor deployment plan, sensor equipment is deployed, and the deployed sensor equipment is interactively connected to obtain the environmental interaction network.

3. The intelligent traffic light scheduling method based on environment interaction as claimed in claim 2, characterized in that: The predetermined sensing device factors include cameras, radars, geomagnetic sensors and infrared sensors.

4. The intelligent traffic light scheduling method based on environmental interaction as claimed in claim 1, characterized in that: Preprocessing the traffic flow data to obtain traffic status characteristic information includes: Performing data cleaning according to the traffic flow data to obtain traffic flow standard data; Setting traffic status characteristic factors, wherein the traffic status characteristic factors include traffic flow, average vehicle speed, occupancy rate of each lane, queue length in each direction and traffic density; The traffic flow standard data is characterized by performing feature recognition according to the traffic state characteristic factor to obtain the traffic state characteristic information.

5. The intelligent traffic light scheduling method based on environmental interaction as claimed in claim 1, characterized in that: Based on the traffic state characteristic information, according to the traffic state prediction model, predicting the traffic state change trend in the future time zone includes: Obtaining a traffic status feature record set of the intersection; According to the time zone length of the future time zone, the traffic state feature record set is time-series sorted to obtain a traffic state feature sorted set; Perform deep learning based on the traffic state feature combing set to build the traffic state prediction model; The traffic state characteristic information and the future time zone are input into the traffic state prediction model, and the traffic state change trend is output.

6. The intelligent traffic light scheduling method based on environmental interaction as claimed in claim 5, characterized in that: The traffic state prediction model is constructed by performing deep learning based on the traffic state feature combing set, including: Dividing the traffic state feature combing set according to a predetermined ratio to obtain a traffic state feature training set and a traffic state feature test set; Performing supervised learning on the neural network according to the traffic state feature training set to obtain a traffic state prediction network; Testing the traffic state prediction network according to the traffic state feature test set to obtain traffic state prediction loss data; The traffic state prediction network is optimized and learned according to the traffic state prediction loss data to obtain the traffic state prediction model.

7. The intelligent traffic light scheduling method based on environment interaction as claimed in claim 1, characterized in that: The traffic light timing scheme of the intersection is optimized and adjusted according to the traffic state change trend to obtain the traffic light timing optimization scheme, including: Adjusting the traffic light timing scheme according to the traffic state change trend to obtain a traffic light timing adjustment scheme set; Setting a traffic light timing optimization target, wherein the traffic light timing optimization target is to maximize the road traffic capacity, and the road traffic capacity is the number of vehicles passing through the intersection per unit time; The traffic light timing optimization scheme set is optimized and analyzed according to the traffic light timing optimization target to obtain the traffic light timing optimization scheme.

8. Intelligent traffic light dispatching system based on environmental interaction, characterized in that: The system is used to execute the intelligent traffic light scheduling method based on environment interaction according to any one of claims 1 to 7, and the system comprises: A traffic flow collection module, wherein the traffic flow collection module is used to collect traffic flow data in real time using an environmental interaction network deployed at an intersection; A preprocessing module, the preprocessing module is used to preprocess the traffic flow data to obtain traffic state characteristic information; A traffic state prediction module, the traffic state prediction module is used to predict the traffic state change trend in the future time zone based on the traffic state characteristic information and according to the traffic state prediction model; A traffic light timing optimization module, which is used to optimize the traffic light timing scheme at the intersection according to the traffic state change trend to obtain a traffic light timing optimization scheme; A traffic light scheduling module, wherein the traffic light scheduling module is used to send the traffic light timing optimization plan to the intersection signal machine, and the intersection signal machine controls the traffic light switching at the intersection according to the received traffic light timing plan.

Images