Traffic control cooperation method and system based on artificial intelligence
Through the traffic control collaborative system based on artificial intelligence, the traffic conditions of pass-through sections are monitored and predicted in real time and the signal lights are dynamically regulated, which solves the problem of inability to effectively monitor and clear traffic congestion in the existing technology, and has achieved the optimization of traffic flow and the improvement of road traffic efficiency.
Patent Information
- Application Number
- CN202510168187.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-17
- Publication Date
- 2025-05-27
AI Technical Summary
The prior art cannot effectively monitor and predict traffic conditions in pass-through sections in real time, and fixed traffic lights are difficult to effectively clear traffic congested sections, resulting in vehicle stranding and traffic congestion.
Using a traffic control collaboration system based on artificial intelligence, through the connection between the traffic collaborative command platform and the cloud network information collection module, the traffic efficiency evaluation module, the signal light setting evaluation module, and the signal light regulation module, the vehicle pass information is obtained in real time, the traffic obstacle coefficient is generated, the road section is divided, and the signal light is dynamically controlled based on the analysis results.
Real-time effective monitoring and prediction of pass-through sections is achieved, dynamically regulating signal lights, reducing vehicle waiting time, optimizing traffic flow, improving road traffic efficiency, and reducing congestion and accidents.
Smart Images
Figure CN120048135A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of vehicle intelligent traffic control, and more specifically, to a traffic control coordination method and system based on artificial intelligence. Background Art
[0002] Urban road intersections are important nodes in the urban road system. As an important part of urban traffic at the micro level, they connect roads in different directions to form a road network, allowing vehicles from all directions in the road network to turn freely and cross each other.
[0003] Intersections are high-risk points where vehicles and pedestrians converge. The function of traffic lights is to divert traffic, but intersections, or crossroads, often result in a large number of vehicles being stranded as they wait for the traffic lights to change, causing traffic jams. This is mainly because it is impossible to effectively monitor and predict the traffic conditions on the road sections in real time, and the diversion time of traditional traffic lights is mostly fixed, so it is impossible to automatically adjust accurately according to traffic flow. There will be a situation where both vehicles and no vehicles are directed in the same direction at the same time, which increases the driving burden on sections with heavy traffic and makes it impossible to reasonably direct traffic.
[0004] To this end, we propose an artificial intelligence-based traffic control collaboration method and system to address the above issues. Summary of the invention
[0005] The purpose of the present invention is to solve the problem that the traffic conditions of the existing road sections cannot be effectively monitored and predicted in real time and the diversion time of fixed traffic lights is difficult to effectively clear the traffic jam sections. Compared with the existing technology, an artificial intelligence-based traffic control coordination method and system are provided.
[0006] The purpose of the present invention can be achieved through the following technical solutions:
[0007] A traffic control coordination system based on artificial intelligence, comprising a traffic coordination command platform, wherein the traffic coordination command platform is communicatively connected with a cloud network information collection module, a traffic efficiency evaluation module, a signal light setting evaluation module, and a signal light control module;
[0008] The traffic coordination command platform marks the traffic section between two adjacent traffic intersections as a traffic control section. The cloud network information collection module is used to obtain vehicle traffic information on the traffic control section, including traffic retention and traffic speed reduction values, and sends the vehicle traffic information to the traffic efficiency evaluation module;
[0009] The traffic efficiency evaluation module generates a traffic barrier coefficient according to vehicle traffic information, analyzes and evaluates the traffic efficiency of the traffic control section with the traffic barrier coefficient, and divides the traffic control section into an inefficient traffic section, a stable traffic section, and an efficient traffic section;
[0010] The signal light setting evaluation module is used to obtain the average waiting time of vehicles on the inefficient traffic section, determine whether the signal light setting at the intersection of the inefficient traffic section meets the traffic convenience demand according to the waiting time, and retrieve the traffic retention volume of vehicles on the inefficient traffic section and the adjacent efficient traffic section from the cloud network information collection module, generate a multi-level green light extension signal through comprehensive analysis, and send the multi-level green light extension signal to the signal light control module via the traffic coordination command platform;
[0011] The traffic light control module dynamically adjusts the timing of traffic lights on inefficient traffic sections and adjacent efficient traffic sections based on multi-level green light extension signals.
[0012] As a preferred embodiment of the present invention, the process of acquiring vehicle traffic information of a traffic control section includes: setting two vehicle detectors connected to the cloud network information acquisition module signal in the front and rear directions of one side of the traffic control section, marking the two vehicle detectors as detector A and detector B respectively, and detector A and detector B are respectively set near the two traffic intersections before and after the traffic control section, and marking the section between detector A and detector B as a monitoring and prediction section;
[0013] Detector A obtains the traffic volume entering the monitoring and prediction section and the average driving speed of passing vehicles within a preset unit time, and detector B obtains the traffic volume leaving the monitoring and prediction section and the average driving speed of passing vehicles within a preset unit time, which are marked as the first entry flow, the first entry speed and the second entry flow, and the second entry speed respectively. The difference between the first entry flow and the second entry flow is calculated to obtain the traffic retention amount, and the difference between the first entry speed and the second entry speed is calculated to obtain the traffic speed reduction value.
[0014] As a preferred embodiment of the present invention, the process of evaluating the traffic efficiency of the traffic control section by the traffic efficiency evaluation module includes: obtaining the traffic obstacle coefficient according to the traffic retention volume, the traffic speed reduction value and the monitored and predicted section length analysis;
[0015] The traffic obstacle coefficient is compared with the preset traffic obstacle coefficient threshold interval. When the traffic obstacle coefficient is greater than the maximum value of the preset traffic obstacle coefficient threshold interval, the traffic on the traffic control section is determined to be inefficient, and the traffic control section is divided into an inefficient traffic section. When the traffic obstacle coefficient is within the preset traffic obstacle coefficient threshold interval, the traffic on the traffic control section is determined to be stable, and the traffic control section is divided into a stable traffic section. When the traffic obstacle coefficient is less than the minimum value of the preset traffic obstacle coefficient threshold interval, the traffic on the traffic control section is determined to be efficient, and the traffic control section is divided into an efficient traffic section.
[0016] As a preferred embodiment of the present invention, the process of determining whether the signal light setting at the intersection of an inefficient road section meets the traffic convenience demand includes: obtaining the vehicle's entry time at the secondary entry speed of each driving zone in the inefficient road section and the vehicle's exit time when it completely exits the intersection of the inefficient road section, calculating the difference between the two to obtain the vehicle waiting time of each driving section, summing and averaging the vehicle waiting time of each driving section to obtain the average traffic waiting time, comparing the average traffic waiting time with a preset traffic waiting time threshold, and when the average traffic waiting time is greater than or equal to the preset traffic waiting time threshold, determining that the signal light setting at the intersection of the inefficient road section does not meet the traffic convenience demand.
[0017] As a preferred embodiment of the present invention, the acquisition process of the multi-level green light extension signal includes: the signal light setting evaluation module retrieves the traffic retention volume of the inefficient traffic section and the adjacent efficient traffic section, marks them as inefficient retention volume and efficient retention volume respectively, calculates the difference between the inefficient retention volume and the efficient retention volume, and obtains the retention volume deviation value;
[0018] The retention volume deviation value is compared with the preset retention volume floating threshold value. When the retention volume deviation value is greater than or equal to the preset retention volume floating threshold value, a first-level green light extension signal is generated. When the retention volume deviation value is less than the preset retention volume floating threshold value, a second-level green light extension signal is generated.
[0019] As a preferred embodiment of the present invention, when the signal light control module receives the first-level green light extension signal, the green light of the inefficient road section is extended by (bc) seconds, and the green light of the efficient road section is reduced by (bc) seconds; when the second-level green light extension signal is received, the green light of the inefficient road section is extended by (ab) seconds, and the green light of the efficient road section is reduced by (ab) seconds, wherein a <b<c。
[0020] A traffic control coordination method based on artificial intelligence comprises the following steps:
[0021] Step 1: Mark the traffic section between two adjacent traffic intersections as a traffic control section, and obtain vehicle traffic information of the traffic control section;
[0022] Step 2: Generate a traffic barrier coefficient based on vehicle traffic information, and use the traffic barrier coefficient to analyze and evaluate the traffic efficiency of the traffic control section, so as to divide the traffic control section into an inefficient traffic section, a stable traffic section, and an efficient traffic section;
[0023] Step 3: Obtain the average waiting time of vehicles on the inefficient road section, and use this to determine whether the signal light setting at the intersection of the inefficient road section meets the traffic convenience demand;
[0024] Step 4: When it is determined that the signal light setting of the traffic intersection of the inefficient traffic section does not meet the requirements, the traffic retention volume of vehicles in the inefficient traffic section and the adjacent efficient traffic section is retrieved and marked as inefficient retention volume and efficient retention volume respectively, and the difference between the two is calculated to obtain the retention volume deviation value, and a multi-level green light extension signal is generated according to the retention volume deviation value;
[0025] Step 5: Dynamically coordinate the traffic lights on inefficient traffic sections and adjacent efficient traffic sections based on multi-level green light extension signals.
[0026] Compared with the prior art, the advantages of the present invention are:
[0027] (1) This solution obtains vehicle traffic information of the traffic control section between two adjacent traffic intersections through the cloud network information collection module, generates a traffic barrier coefficient based on the vehicle traffic information, and uses the traffic barrier coefficient to analyze and evaluate the traffic efficiency of the traffic control section. According to the analysis results, the traffic conditions of the traffic section can be effectively monitored and predicted in real time, and the traffic control section is divided into inefficient traffic sections, stable traffic sections, and efficient traffic sections. The inefficient traffic section is used as the main control section, and the adjacent efficient traffic section is used as the coordinated control section. The traffic lights are dynamically timed, and the optimal traffic light control scheme is selected with the goal of reducing the average waiting time of vehicles in the inefficient traffic section. This scheme has good prediction and decision-making capabilities.
[0028] (2) This scheme sets two vehicle detectors connected to the cloud network information collection module signal in the front and rear directions on one side of the traffic control section, marked as detector A and detector B respectively. Detector A and detector B are respectively set near the two traffic intersections before and after the traffic control section, and the section between detector A and detector B is marked as the monitoring and prediction section. The detectors obtain the traffic flow and the average driving speed of the passing vehicles before and after the monitoring and prediction section, so as to obtain the traffic retention volume and traffic speed reduction value of the monitoring and prediction section, and combine the analysis of the length of the monitoring and prediction section to obtain the traffic obstacle coefficient TZX. The traffic obstacle coefficient is used to effectively monitor and predict the traffic conditions of the traffic control section, and the traffic efficiency is divided. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 is a system structure block diagram of the present invention;
[0030] Figure 2 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION
[0031] The following will combine 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 the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work based on the embodiments of the present invention belong to the scope of protection of the present invention.
[0032] Example 1: The present invention discloses a traffic control coordination system based on artificial intelligence, please refer to Figure 1 , including a traffic coordination and command platform, which is connected to a cloud network information collection module, a traffic efficiency evaluation module, a traffic light setting evaluation module, and a traffic light control module.
[0033] The traffic coordination command platform marks the passage section between two adjacent traffic intersections as a traffic control section. The cloud network information collection module is used to obtain vehicle traffic information on the traffic control section. Two vehicle detectors connected to the cloud network information collection module signal are set in the front and rear directions on one side of the traffic control section. The two vehicle detectors are marked as detector A and detector B respectively. Detector A and detector B are respectively set near the two traffic intersections before and after the traffic control section, and the section between detector A and detector B is marked as a monitoring and prediction section.
[0034] Detector A obtains the traffic volume entering the monitoring and prediction section and the average speed of the passing vehicles within a preset unit time, and detector B obtains the traffic volume leaving the monitoring and prediction section and the average speed of the passing vehicles within a preset unit time, which are marked as the first entry flow, the first entry speed and the second entry flow, the second entry speed respectively. The first entry flow and the second entry flow within the preset unit time are calculated to obtain the traffic retention amount, marked as ZL, and the first entry speed and the second entry speed are calculated to obtain the traffic speed reduction value, marked as GS. The traffic retention amount and the traffic speed reduction value constitute the vehicle traffic information, and the vehicle traffic information is sent to the traffic efficiency evaluation module.
[0035] The traffic efficiency evaluation module receives vehicle traffic information, and obtains the traffic obstacle coefficient TZX according to the traffic retention volume, traffic speed reduction value and monitoring and prediction section length analysis, through the formula TZX = (α × ZL + β × GS) × (TL / γ), where TL represents the monitoring and prediction section length, α> β> γ> 1, α, β, γ are the preset proportional coefficients of traffic retention volume, traffic speed reduction value and monitoring and prediction section length respectively;
[0036] The traffic efficiency of the traffic control section is analyzed and evaluated by using the traffic obstacle coefficient, specifically: comparing the traffic obstacle coefficient TZX with the preset traffic obstacle coefficient threshold range;
[0037] When the traffic barrier coefficient is greater than the maximum value of the preset traffic barrier coefficient threshold interval, the traffic control section is judged to be inefficient, and the traffic control section is divided into an inefficient traffic section, indicating that the retention volume and speed reduction value of the monitoring and prediction section are relatively large, there are many vehicles entering, and the speed of vehicles leaving the intersection is slow, resulting in traffic congestion;
[0038] When the traffic barrier coefficient is within the preset traffic barrier coefficient threshold range, the traffic on the traffic control section is determined to be stable, and the traffic control section is divided into a stable traffic section, indicating that vehicles entering and leaving the traffic control section have reached a relatively balanced state, traffic congestion has not occurred, and vehicles can pass through the intersection in an orderly manner;
[0039] When the traffic obstacle coefficient is less than the minimum value of the preset traffic obstacle coefficient threshold range, the traffic control section is determined to be efficient and the traffic control section is divided into an efficient traffic section, indicating that the traffic volume on the traffic control section is small, and the speed detected on the front and rear sides has not decreased too much. This section is a very smooth section.
[0040] The signal light setting evaluation module is used to obtain the average waiting time of vehicles on the inefficient road section, and determine whether the signal light setting at the intersection of the inefficient road section meets the traffic convenience demand based on the waiting time;
[0041] Specifically, the entry time of the vehicle at the secondary entry speed of each driving zone of the inefficient road section and the exit time of the vehicle completely exiting the intersection of the inefficient road section are obtained, the difference between the two is calculated to obtain the vehicle waiting time of each driving section, the vehicle waiting time of each driving section is summed and averaged to obtain the average waiting time, the average waiting time is compared with the preset waiting time threshold, and when the average waiting time is greater than or equal to the preset waiting time threshold, it is determined that the signal light setting of the intersection of the inefficient road section does not meet the traffic convenience demand;
[0042] When it is determined that the signal light setting at the intersection of the inefficient traffic section does not meet the traffic convenience demand, the traffic detention volume of vehicles in the inefficient traffic section and the adjacent efficient traffic section is retrieved and marked as inefficient detention volume and efficient detention volume respectively, and the difference between the inefficient detention volume and the efficient detention volume is calculated to obtain the detention volume deviation value;
[0043] The detention volume deviation value is compared with the preset detention volume floating threshold. When the detention volume deviation value is greater than or equal to the preset detention volume floating threshold, a first-level green light extension signal is generated. When the detention volume deviation value is less than the preset detention volume floating threshold, a second-level green light extension signal is generated. The first-level green light extension signal and the second-level green light extension signal are sent to the signal light control module via the traffic coordination command platform.
[0044] Embodiment 2: In this embodiment, in combination with the generated first-level green light extension signal and second-level green light extension signal, the signal light control module receives the first-level green light extension signal and the second-level green light extension signal sent by the traffic coordination command platform, and performs dynamic timing on the signal lights of the low-efficiency traffic section and the adjacent high-efficiency traffic section, specifically including:
[0045] When the signal light control module receives the first-level green light extension signal, it performs a set control for the green light extension (b - c) second interval of the low-efficiency traffic section, and a set control for the green light reduction (b - c) second interval of the high-efficiency traffic section;
[0046] When receiving the second-level green light extension signal, it performs a set control for the green light extension (a - b) second interval of the low-efficiency traffic section, and a set control for the green light reduction (a - b) second interval of the high-efficiency traffic section, where a < b < c. As the retention deviation value increases, the green light on time of the low-efficiency traffic section is gradually extended until it reaches the maximum value of the green light extension interval, and at the same time, the green light on time of the high-efficiency traffic section is gradually reduced until it reaches the maximum value of the green light extension interval. According to the traffic flow and traffic waiting time at the traffic intersection, taking the low-efficiency traffic section as the main control section and the adjacent high-efficiency traffic section as the collaborative control section, the signal lights at the traffic intersections of the low-efficiency traffic section and the high-efficiency traffic section are intelligently controlled and timed, extending the green light on time of the driving direction with a large traffic flow and shortening the green light on time of the driving direction with a small traffic flow. When the vehicle traffic information in the two driving directions gradually approaches, the traffic coordination command platform gradually resumes the preset command to control the signal lights to work.
[0047] Embodiment 3: Combining Embodiment 1 and Embodiment 2, an artificial intelligence-based traffic control collaboration method, please refer to Figure 2 , including the following steps:
[0048] Step 1: Mark the traffic section between two adjacent traffic intersections as the driving control section, and obtain the vehicle traffic information of the driving control section;
[0049] Step 2: Generate a traffic obstacle coefficient according to the vehicle traffic information, analyze and evaluate the traffic efficiency of the driving control section with the traffic obstacle coefficient, and thereby divide the driving control section into a low-efficiency traffic section, a stable traffic section, and a high-efficiency traffic section;
[0050] Step 3: Obtain the average traffic waiting time of the vehicle in the low-efficiency traffic section, and thereby determine whether the signal light setting at the traffic intersection of the low-efficiency traffic section meets the traffic convenience requirements;
[0051] Step 4: When it is determined that the signal light setting of the traffic intersection of the inefficient traffic section does not meet the requirements, the traffic retention volume of vehicles in the inefficient traffic section and the adjacent efficient traffic section is retrieved and marked as inefficient retention volume and efficient retention volume respectively, and the difference between the two is calculated to obtain the retention volume deviation value, and a multi-level green light extension signal is generated according to the retention volume deviation value;
[0052] Step 5: Dynamically coordinate the traffic lights on inefficient traffic sections and adjacent efficient traffic sections based on multi-level green light extension signals.
[0053] In summary: the present invention utilizes a traffic coordination command platform to mark a traffic section between two adjacent traffic intersections as a traffic control section, obtains vehicle traffic information of the traffic control section between two adjacent traffic intersections through a cloud network information acquisition module, generates a traffic barrier coefficient based on the vehicle traffic information, analyzes and evaluates the traffic efficiency of the traffic control section based on the traffic barrier coefficient, and realizes real-time and effective monitoring and prediction of the traffic conditions of the traffic section based on the analysis results, and divides the traffic control section into an inefficient traffic section, a stable traffic section, and an efficient traffic section, with the inefficient traffic section as the main control section and the adjacent efficient traffic section as the coordinated control section, dynamically time-matches the traffic lights, selects the optimal traffic light duration control scheme with the goal of reducing the average waiting time of vehicles in the inefficient traffic section, and optimizes traffic flow, improves road traffic efficiency, and reduces congestion and accidents through intelligent means.
[0054] The above is only a preferred specific implementation manner of the present invention; but the protection scope of the present invention is not limited thereto; any technician familiar with the technical field within the technical scope disclosed by the present invention; any equivalent replacement or change based on the technical solution and improved concept of the present invention shall be covered by the protection scope of the present invention.
Claims
1. A traffic control coordination system based on artificial intelligence, characterized by: It includes a traffic coordination command platform, which is connected to a cloud network information collection module, a traffic efficiency evaluation module, a signal light setting evaluation module, and a signal light control module; The traffic coordination command platform marks the traffic section between two adjacent traffic intersections as a traffic control section. The cloud network information collection module is used to obtain vehicle traffic information on the traffic control section, including traffic retention and traffic speed reduction values, and sends the vehicle traffic information to the traffic efficiency evaluation module; The traffic efficiency evaluation module generates a traffic barrier coefficient according to vehicle traffic information, analyzes and evaluates the traffic efficiency of the traffic control section with the traffic barrier coefficient, and divides the traffic control section into an inefficient traffic section, a stable traffic section, and an efficient traffic section; The signal light setting evaluation module is used to obtain the average waiting time of vehicles on the inefficient traffic section, determine whether the signal light setting at the intersection of the inefficient traffic section meets the traffic convenience demand according to the waiting time, and retrieve the traffic retention volume of vehicles on the inefficient traffic section and the adjacent efficient traffic section from the cloud network information collection module, generate a multi-level green light extension signal through comprehensive analysis, and send the multi-level green light extension signal to the signal light control module via the traffic coordination command platform; The traffic light control module dynamically adjusts the timing of traffic lights on inefficient traffic sections and adjacent efficient traffic sections based on multi-level green light extension signals.
2. The traffic control coordination system based on artificial intelligence according to claim 1, characterized in that: The process of acquiring vehicle traffic information of the traffic control section includes: setting two vehicle detectors connected to the cloud network information collection module signal in the front and rear directions of one side of the traffic control section, marking the two vehicle detectors as detector A and detector B respectively, and setting detector A and detector B near the two traffic intersections before and after the traffic control section respectively, and marking the section between detector A and detector B as a monitoring and prediction section; Detector A obtains the traffic volume entering the monitoring and prediction section and the average driving speed of passing vehicles within a preset unit time, and detector B obtains the traffic volume leaving the monitoring and prediction section and the average driving speed of passing vehicles within a preset unit time, which are marked as the first entry flow, the first entry speed and the second entry flow, and the second entry speed respectively. The difference between the first entry flow and the second entry flow is calculated to obtain the traffic retention amount, and the difference between the first entry speed and the second entry speed is calculated to obtain the traffic speed reduction value.
3. The traffic control coordination system based on artificial intelligence according to claim 2 is characterized in that: The process of evaluating the traffic efficiency of the traffic control section by the traffic efficiency evaluation module includes: obtaining the traffic obstacle coefficient according to the traffic retention volume, the traffic speed reduction value and the monitored and predicted section length analysis; The traffic obstacle coefficient is compared with the preset traffic obstacle coefficient threshold interval. When the traffic obstacle coefficient is greater than the maximum value of the preset traffic obstacle coefficient threshold interval, the traffic on the traffic control section is determined to be inefficient, and the traffic control section is divided into an inefficient traffic section. When the traffic obstacle coefficient is within the preset traffic obstacle coefficient threshold interval, the traffic on the traffic control section is determined to be stable, and the traffic control section is divided into a stable traffic section. When the traffic obstacle coefficient is less than the minimum value of the preset traffic obstacle coefficient threshold interval, the traffic on the traffic control section is determined to be efficient, and the traffic control section is divided into an efficient traffic section.
4. The traffic control coordination system based on artificial intelligence according to claim 3 is characterized by: The process of determining whether the signal light setting at the intersection of an inefficient road section meets the traffic convenience demand includes: obtaining the vehicle's entry time at the secondary entry speed of each driving zone in the inefficient road section and the vehicle's exit time when it completely exits the intersection of the inefficient road section, calculating the difference between the two to obtain the vehicle waiting time of each driving section, summing and averaging the vehicle waiting time of each driving section to obtain the average traffic waiting time, comparing the average traffic waiting time with a preset traffic waiting time threshold, and when the average traffic waiting time is greater than or equal to the preset traffic waiting time threshold, determining that the signal light setting at the intersection of the inefficient road section does not meet the traffic convenience demand.
5. The traffic control coordination system based on artificial intelligence according to claim 4 is characterized in that: The process of obtaining the multi-level green light extension signal includes: the signal light setting evaluation module retrieves the traffic retention volume of the inefficient traffic section and the adjacent efficient traffic section, marks them as inefficient retention volume and efficient retention volume respectively, calculates the difference between the inefficient retention volume and the efficient retention volume, and obtains the retention volume deviation value; The retention volume deviation value is compared with the preset retention volume floating threshold value. When the retention volume deviation value is greater than or equal to the preset retention volume floating threshold value, a first-level green light extension signal is generated. When the retention volume deviation value is less than the preset retention volume floating threshold value, a second-level green light extension signal is generated.
6. The traffic control coordination system based on artificial intelligence according to claim 5 is characterized by: When the signal light control module receives the first-level green light extension signal, it adjusts the setting of the green light extension interval (bc) seconds for the inefficient traffic section, and reduces the green light interval (bc) seconds for the efficient traffic section; when the second-level green light extension signal is received, it adjusts the setting of the green light extension interval (ab) seconds for the inefficient traffic section, and reduces the green light interval (ab) seconds for the efficient traffic section, where a <b<c。 7. A traffic control coordination method based on artificial intelligence, using a traffic control coordination system based on artificial intelligence as claimed in any one of claims 1 to 6, characterized in that: The following steps are involved: Step 1: Mark the traffic section between two adjacent traffic intersections as a traffic control section, and obtain vehicle traffic information of the traffic control section; Step 2: Generate a traffic barrier coefficient based on vehicle traffic information, and use the traffic barrier coefficient to analyze and evaluate the traffic efficiency of the traffic control section, so as to divide the traffic control section into an inefficient traffic section, a stable traffic section, and an efficient traffic section; Step 3: Obtain the average waiting time of vehicles on the inefficient road section, and use this to determine whether the signal light setting at the intersection of the inefficient road section meets the traffic convenience demand; Step 4: When it is determined that the signal light setting of the traffic intersection of the inefficient traffic section does not meet the requirements, the traffic retention volume of vehicles in the inefficient traffic section and the adjacent efficient traffic section is retrieved and marked as inefficient retention volume and efficient retention volume respectively, and the difference between the two is calculated to obtain the retention volume deviation value, and a multi-level green light extension signal is generated according to the retention volume deviation value; Step 5: Dynamically coordinate the traffic lights on inefficient traffic sections and adjacent efficient traffic sections based on multi-level green light extension signals.