Signal light control method, device, computer equipment and readable storage medium

Abstract

The present application relates to a traffic light control method, device, computer equipment and readable storage medium, including: obtaining road network data and vehicle data of a preset area; performing data division processing on the road network data and vehicle data to obtain multiple minimum computing units, wherein the minimum computing unit is the location information of an intersection and its associated roads; establishing multiple maximum pressure calculation threads according to each minimum computing unit based on a preset parallel programming technology; dynamically adjusting the display strategy of the traffic lights in the minimum computing unit according to the calculation results of the maximum pressure calculation thread; generating a traffic light control strategy within a preset area according to all target display strategies. The present application takes the intersection as the minimum computing unit, creates multiple parallel maximum pressure calculation threads, and dynamically adjusts the display strategy of the traffic lights based on the maximum pressure algorithm, which effectively improves the realism of the traffic light simulation while improving the efficiency of the traffic light simulation.

Description

Technical Field

[0001] The present application relates to the technical field of traffic light control, and in particular to a traffic light control method, device, computer equipment and readable storage medium. Background Art

[0002] In the field of urban traffic simulation, the simulation of traffic lights is an important research method in the fields of traffic control, urban planning, and traffic safety. Compared with field experiments, real-life observations have the advantages of strong controllability, low cost, large sample size, and comprehensive information. However, existing traffic simulation technologies focus more on the accuracy of small-scale simulations, and it is difficult to achieve good results in the prediction of the entire traffic flow in super-large cities. In addition, the operating efficiency is limited and the effectiveness is poor, making it difficult to meet the needs of traffic simulation in large cities. Simulations in super-large cities require processing of millions of data, and improving the realism of traffic flow simulation often leads to an exponential decrease in execution efficiency. Summary of the invention

[0003] Based on this, it is necessary to provide a traffic light control method, device, computer equipment and readable storage medium that can effectively improve the efficiency and realism of traffic light simulation in response to the above technical problems.

[0004] In a first aspect, the present application provides a signal light control method, the method comprising:

[0005] Acquire road network data and vehicle data of a preset area, wherein the road network data includes intersection information and road information, and the vehicle data includes navigation information and driving information;

[0006] Performing data division processing on the road network data and the vehicle data to obtain a plurality of minimum calculation units, wherein the minimum calculation unit is location information of an intersection and its associated roads;

[0007] Establishing a plurality of maximum pressure calculation threads according to each of the minimum calculation units, wherein the maximum pressure calculation threads are used to calculate the pressure of each phase of the intersection according to the road network data and vehicle data of the minimum calculation unit;

[0008] Dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread;

[0009] The traffic light control strategy within the preset area is generated according to the target display strategy of the traffic light in each minimum calculation unit.

[0010] In one embodiment, dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread includes:

[0011] Arrange the calculation results of the maximum pressure calculation thread in order from large to small pressure to obtain the phase where the maximum pressure is located;

[0012] Determine whether the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located;

[0013] If the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located, the traffic light display time of the traffic phase is adjusted to the maximum green light time;

[0014] If the traffic phase of the intersection in the minimum calculation unit at the current moment is not the phase where the maximum pressure is located, the traffic light display time of the traffic phase is adjusted to the minimum green light time.

[0015] In one embodiment, dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread further includes:

[0016] If the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase with the maximum pressure, when the traffic light display time of the traffic phase is equal to the maximum green light time, the phase to be passed is determined according to the pressure value of each phase and the phase passing waiting time, the traffic light of the traffic phase is controlled to switch to yellow light display, and the traffic light of the phase to be passed is controlled to switch to green light display;

[0017] If the traffic phase of the traffic light in the minimum calculation unit at the current moment is not the phase where the maximum pressure is located, when the traffic light display time in the traffic phase is equal to the minimum green light time, the traffic light in the traffic phase is controlled to switch to yellow light display, and the traffic light in the phase where the maximum pressure is located is controlled to switch to green light display.

[0018] In one embodiment, dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread further includes:

[0019] According to the calculation results of multiple maximum pressure calculation threads corresponding to adjacent intersections, the display strategy of the traffic light of the preset minimum unit corresponding to any intersection among the adjacent intersections is dynamically adjusted.

[0020] In one embodiment, after performing data partitioning processing on the road network data and the vehicle data to obtain a plurality of minimum computing units, the method further comprises:

[0021] Obtain the traffic flow information of each minimum computing unit within the target prediction time;

[0022] The maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection within the target prediction time according to the road network data, vehicle data and corresponding traffic flow information of the minimum calculation unit in time stages according to a preset time step;

[0023] According to the calculation results of the maximum pressure calculation thread in each time stage, the display strategy of the traffic lights in the minimum calculation unit in the corresponding time stage is dynamically adjusted to obtain the target display strategy of the minimum calculation unit within the target prediction time.

[0024] In one of the embodiments, after obtaining the traffic flow information of each minimum computing unit within the target prediction time, the method further includes:

[0025] Divide the traffic flow information within the target prediction time into traffic flow information corresponding to each time stage according to the preset time step;

[0026] If any vehicle is at a boundary point of the minimum calculation unit in the current time stage, the relevant information of the vehicle is allocated to the traffic flow information of the next time stage.

[0027] In one embodiment, the method further comprises:

[0028] The road network data and vehicle data of the current time period are updated according to the road network data and vehicle data of the previous time period.

[0029] In a second aspect, the present application further provides a signal light control device, the device comprising:

[0030] A data acquisition module, used to acquire road network data and vehicle data of a preset area, wherein the road network data includes intersection information and road information, and the vehicle data includes navigation information and driving information;

[0031] A data partitioning module, used for performing data partitioning processing on the road network data and the vehicle data to obtain a plurality of minimum calculation units, wherein the minimum calculation unit is location information of an intersection and its associated roads;

[0032] A pressure calculation module, used to establish a plurality of maximum pressure calculation threads according to each of the minimum calculation units, wherein the maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection according to the road network data and vehicle data of the minimum calculation unit;

[0033] A strategy adjustment module, used to dynamically adjust the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread;

[0034] The strategy generation module is used to generate a traffic light control strategy within the preset area according to the target display strategy of the traffic light in each minimum calculation unit.

[0035] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the signal light control method described in the first aspect are implemented.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the signal light control method described in the first aspect are implemented.

[0037] The above-mentioned traffic light control method, device, computer equipment and readable storage medium include: obtaining road network data and vehicle data of a preset area; performing data division processing on the road network data and vehicle data to obtain multiple minimum computing units, wherein the minimum computing unit is the location information of an intersection and its associated roads; establishing multiple maximum pressure calculation threads according to each minimum computing unit based on a preset parallel programming technology; dynamically adjusting the display strategy of the traffic lights in the minimum computing unit according to the calculation results of the maximum pressure calculation thread; generating a traffic light control strategy within a preset area according to all target display strategies. The present application uses intersections as the minimum computing unit, creates multiple parallel maximum pressure calculation threads, and dynamically adjusts the display strategy of traffic lights based on the maximum pressure algorithm, which effectively improves the realism of traffic light simulation while improving the efficiency of traffic light simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart of a signal light control method in one embodiment;

[0039] Figure 2 One of the flowcharts of the steps for dynamically adjusting the display strategy of a traffic light in a minimum computing unit in one embodiment;

[0040] Figure 3 The second schematic diagram of the steps of dynamically adjusting the display strategy of the traffic light in the minimum computing unit in one embodiment;

[0041] Figure 4 is a flow chart of a signal light control method in another embodiment;

[0042] Figure 5 is a structural block diagram of a signal light control device in one embodiment;

[0043] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0045] Traffic light control is a key technology to improve the efficiency of road network transportation. Traditional traffic research lacks the ability to adapt to dynamic traffic conditions. Studies have shown that using reinforcement learning (RL) for traffic research can obtain more effective traffic signal solutions. However, most RL-based studies design key elements (rewards and states) in a heuristic way, which leads to the high sensitivity of traffic light control systems to performance, and complex state definitions increase the time of reinforcement learning.

[0046] In traditional multi-intersection control, a fixed green light start time interval is usually used to achieve signal coordination between multiple intersections on the main road. However, traffic flows in different directions are greatly affected by the environment and usually change irregularly, so traffic flows in different directions cannot usually be optimized at the same time.

[0047] To solve this problem, some optimization control methods based on the green light start time interval have been proposed, aiming to minimize the vehicle's travel time and / or number of stops in multiple intervals. However, these methods still rely on some assumptions to simplify traffic conditions and cannot guarantee the expected results in the real world.

[0048] The maximum pressure control method proposed in this application is not to optimize the green light start time, but to maximize the throughput of the queuing network, thereby reducing the travel time. Among them, each intersection has a separate queue for turning movements, which is called a queuing network. The throughput of the queuing network is the number of vehicles that successfully perform turning movements at the intersection.

[0049] The traffic light control scheme in this embodiment is based on decentralized RL agent nodes to control traffic signals in a multi-intersection system. Each agent node can make decisions based on vehicle data of relevant intersections and roads without centralized decision-making, making the traffic light control scheme in this embodiment more scalable and applicable.

[0050] In one embodiment, Figure 1 As shown, a signal light control method is provided, comprising the following steps:

[0051] S101, obtaining road network data and vehicle data of a preset area, wherein the road network data includes intersection information and road information, and the vehicle data includes navigation information and driving information;

[0052] Specifically, the preset area in this embodiment may be a large area such as a county or city. The range of the preset area may be customized according to the needs of the actual application scenario, and this embodiment does not limit this.

[0053] This embodiment can obtain the road network data and vehicle data of the preset area through a large-scale Internet map database or any open source map database. For example, the road network data and vehicle data of the preset area can be obtained through OpenStreetMap. This embodiment does not specifically limit the acquisition source of the road network data and vehicle data.

[0054] In a specific embodiment, the road network data includes road information composed of lanes and intersection information, etc., wherein the intersection is the intersection of two or more roads. Specifically, the road information includes information such as the length, width, position, maximum speed limit, road type, leading lane and subsequent lane of the road section. Among them, the location of the road information is the latitude and longitude coordinates, which can be obtained through navigation satellites such as GPS or Beidou. The leading lane is the lane that can enter the current lane under the permission of traffic driving regulations, and the subsequent lane is the lane that the current lane can enter under the permission of traffic driving regulations. The intersection information includes information such as traffic lights and conflict points, wherein the conflict point is the intersection formed by the intersection of traffic flows in different driving directions.

[0055] Vehicle data includes navigation information, road network perception information, and driving information, among which navigation information includes route planning, real-time positioning, and other information during the vehicle's navigation process; road network perception information includes information such as the road the vehicle is on and the vehicle's position; and driving information includes initial speed, acceleration, vehicle length, vehicle width, vehicle maximum acceleration, braking acceleration, and other information related to the vehicle's driving process. It should be noted that the driving information of different types of vehicles may be different. As an independent storage unit, vehicle data does not interfere with the vehicle attributes of different vehicles. The vehicle is simulated when it starts driving on the road according to the navigation, and the vehicle is removed after the vehicle navigation is completed.

[0056] In a specific embodiment, the road network data and vehicle data of a preset area obtained in this implementation include real-time road network data, real-time vehicle data and simulated vehicle data.

[0057] Among them, real-time road network data is obtained based on an open source map database; real-time vehicle data is obtained based on an open source map database and navigation software; vehicle data within a target prediction time for a traffic light simulation test is predicted based on the real-time road network data and real-time vehicle data to obtain simulated vehicle data.

[0058] In a specific embodiment, the acquisition of simulated vehicle data may be based on a preset traffic flow prediction algorithm, which is not specifically limited in this embodiment.

[0059] S102, performing data division processing on the road network data and the vehicle data to obtain a plurality of minimum calculation units, wherein the minimum calculation unit is location information of an intersection and its associated roads;

[0060] Specifically, after obtaining the road network data and vehicle data, the road network data and vehicle data are initialized to obtain multiple road network data and vehicle data divided based on geographical locations. In a specific embodiment, in the stage of obtaining the road network data and obtaining the vehicle data, data can be loaded according to the geographical locations divided in advance, so as to obtain multiple road network data and vehicle data divided based on geographical locations. For example, the road network data and vehicle data can be divided based on the protobuf structure design language.

[0061] The minimum computing unit is the minimum unit divided according to the geographical location, and each minimum computing unit includes the road network data and vehicle data in the corresponding geographical location. Each minimum computing unit can establish a separate maximum pressure calculation thread. In some embodiments, a maximum pressure calculation thread can also be established according to multiple minimum computing units, and can be adaptively configured according to the needs of actual application scenarios.

[0062] In actual application, this embodiment can minimize the amount of data that needs to be processed by a single computing node by dividing the road network data and vehicle data into minimum computing units, thereby improving the efficiency of simulation calculations of the traffic light control solution.

[0063] S103, establishing a plurality of maximum pressure calculation threads according to each minimum calculation unit, wherein the maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection according to the road network data and vehicle data of the minimum calculation unit;

[0064] Specifically, each intersection corresponds to a controller, and the controller is used to control the display strategy of the traffic light according to the corresponding signal light control scheme.

[0065] In a specific embodiment, this embodiment uses the message passing interface (MPI) technology to create a parallel maximum pressure calculation thread. Multiple maximum pressure calculations created based on the MPI technology can run in parallel, and the traffic pressure of the corresponding intersections is calculated based on the environmental information of multiple intersections, which effectively improves the efficiency of the simulation signal light control solution.

[0066] When the number of maximum pressure calculation threads is the same as the number of minimum calculation units, one maximum pressure calculation thread corresponds to one minimum calculation unit. In this embodiment, one minimum calculation unit corresponds to one maximum pressure calculation thread, so that the maximum pressure control plan can be refined to each intersection in the preset area, thereby maximizing the authenticity of the simulated traffic light control plan.

[0067] In some embodiments, the number of maximum pressure calculation threads may be less than the number of minimum calculation units, and some maximum pressure calculation threads correspond to multiple minimum calculation units. This embodiment can effectively save computing resources and further improve the efficiency of the simulation signal light control solution by centrally simulating some areas with lower road pressure.

[0068] Specifically, the maximum pressure calculation thread is used to calculate the pressure of all phases of the intersection according to a preset pressure calculation algorithm.

[0069] For example, if the traffic movement from lane l through intersection i to lane m is represented as (, m), the motion signal of the traffic movement (, m) is represented as a(l, m), where the motion signal includes a green light that allows passage and a red light that prohibits passage, a(l, m) = 1 indicates that the motion signal is a permitted motion signal, and a(l, m) = 1 indicates that the motion signal is a prohibited motion signal. A cycle in which a phase in an intersection switches from green light to red light and then to green light is a control stage, and a control stage is represented as p = {(l, m) | a(l, m) = 1}.

[0070] The pressure of traffic movement (l,m) can be calculated by the following formula:

[0071]

[0072] Where w(l,m) is the pressure of traffic movement (l,m), x(l) is the number of vehicles on lane l, x(m) is the number of vehicles on lane m, and x max (l) is the maximum number of vehicles allowed on lane l, x max (m) is the maximum number of vehicles allowed on lane m, is the vehicle density on lane l, is the vehicle density on lane m.

[0073] The pressure at intersection i can be calculated using the following formula:

[0074]

[0075] Where, the pressure P at intersection i is i is the sum of the absolute pressures of all traffic movements within intersection i.

[0076] This embodiment establishes a maximum pressure calculation thread based on a minimum calculation unit, and can refine the traffic light control simulation to each intersection, thereby achieving a dual improvement in efficiency and accuracy.

[0077] S104, dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread;

[0078] Specifically, in traditional traffic light control schemes, the display control of traffic lights is limited to a static traffic environment, which is different from the facts and has low accuracy in large-scale data experiments. For example, the timing phase control scheme and the vehicle drive control scheme. Among them, the timing phase control scheme manually adjusts the display duration of the traffic lights in each phase based on the preset phase change sequence and the traffic flow in different phases. The vehicle drive control scheme determines whether to switch the display of the traffic lights in the current phase based on the observed real-time traffic conditions and the pre-defined traffic light display rules that match various traffic conditions.

[0079] This embodiment is based on the maximum pressure control scheme, and can dynamically adjust the display strategy of traffic lights in the minimum calculation unit according to the pressure conditions of each phase of the intersection. For example, the intersection controller can give priority to adjusting the traffic light display of the phase with the highest pressure among all phases of the intersection to relieve the traffic pressure of this phase, without adjusting the green light start display time interval of each phase according to the fixed signal light switching order.

[0080] In actual applications, the phase division logic used at each intersection may not be the same. The dynamic adjustment scheme applicable to each minimum computing unit can be adaptively configured according to the phase division logic used at the intersection in the actual application scenario, which is not limited in this embodiment.

[0081] For example, if the intersection adopts eight-phase phase division logic, the intersection controller can output eight groups of control signals to optimize the control of the traffic lights under sensing conditions. At this time, the dynamic adjustment measurement of the intersection will jump and switch among the eight groups of control signals according to the pressure of each phase to optimize the display of the traffic lights at the intersection, maximize the network throughput of the intersection, and relieve the pressure of the intersection.

[0082] In the specific application process, for each intersection n, a phase switching decision needs to be made at the phase end time corresponding to each phase to determine the next phase to be controlled. The phase end time is the green light end time, which can also be called the control decision time k n When the time of intersection n reaches k n When , it is necessary to confirm the phase of the maximum pressure at the current intersection n.

[0083] In one embodiment, the formula Determine k n The phase with the maximum pressure at the moment. n represents the control decision time, σ max ( n ) represents k n The phase with the maximum pressure at the moment, Indicates the phase sequence of a cycle of the current intersection. Specifically, the phase sequence is determined according to a preset phase sequence mode. For example, if the phase sequence is an eight-phase sequence, it is divided according to the east, south, west and north. For example, south-north and north-south are determined as one phase mode, and south-west and north-east are determined as one phase mode.

[0084] In one embodiment, at the control decision time, the current traffic phase is dynamically adjusted according to the following dynamic adjustment formula:

[0085]

[0086] Where D n (k n ) represents the decision of the intersection controller, σ * (k n ) indicates the current traffic phase, extension 1 is to extend the green light display time by a first preset time, and the first preset time can be set as the maximum value of the green light extension time. Extension 2 is to extend the green light display time by a second preset time, and the second preset time is less than the first preset time. is the pressure value of the current traffic phase of intersection n, is the pressure value of the phase where the maximum pressure of intersection n is located, δ is the preset percentage, when σ max (k n )≠σ * (k n ), it means that the current passing phase is not the phase with the maximum pressure. and The pressure value of This indicates that the pressure value of the current traffic phase is still high, and the green light display time can be further extended. This indicates that the pressure value of the current passing phase is small, so the current passing phase can be ended and a control signal is sent to activate the next phase for green light display.

[0087] S105: Generate a traffic light control strategy in a preset area according to the target display strategy of the traffic light in each minimum calculation unit.

[0088] Specifically, the target display strategy is the ideal display strategy of the traffic lights in the smallest computing unit after the dynamic adjustment step. In some embodiments, the target display strategy is the ideal display strategy of the traffic lights in the smallest computing unit within the target prediction time.

[0089] According to the target display strategy of the traffic lights output by all the minimum computing units, the control strategy of all the traffic lights in the preset area can be obtained, thereby realizing the simulation test of traffic lights in a large area.

[0090] In summary, the embodiment of the present application proposes a traffic light control scheme based on the maximum pressure algorithm. By dividing the vehicle data and road network data in a preset area according to the geographical location, and establishing multiple maximum pressure calculation threads with the minimum computing unit as the computing node, it is possible to realize the simulation of the traffic light control scheme down to each intersection. In addition, the present application establishes parallel maximum pressure calculation threads through MPI technology, which can effectively improve the computing efficiency and realize the rapid simulation of the traffic light control scheme. Finally, the display strategy of the intersection is optimized based on the maximum pressure control algorithm, which can minimize the congestion of the road network and realize a traffic light simulation that is closer to the real situation when processing large amounts of data.

[0091] In one embodiment, Figure 2 As shown, S104 includes:

[0092] S201, arranging the calculation results of the maximum pressure calculation threads in order of pressure from large to small, and obtaining the phase where the maximum pressure is located;

[0093] S202, determining whether the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located;

[0094] S203, if the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase with the maximum pressure, the traffic light display time of the traffic phase is adjusted to the maximum green light time;

[0095] S204: If the traffic phase of the intersection in the minimum calculation unit at the current moment is not the phase with the maximum pressure, the traffic light display time of the traffic phase is adjusted to the minimum green light time. …

[0096] Specifically, each maximum pressure calculation thread can output the pressure of each phase of the corresponding intersection, and by sorting the pressures of each phase of the intersection, the phase of the maximum pressure of the corresponding intersection can be obtained.

[0097] In the process of dynamically adjusting the display strategy of the traffic lights in each minimum calculation unit, the control signal of the traffic lights can be optimized according to the traffic phase of the intersection at the current moment and the pressure conditions of each phase.

[0098] In this embodiment, the traffic phase at the current moment is the phase corresponding to the control signal of the traffic light at the intersection showing the green light at the current moment.

[0099] For example, if the intersection adopts eight-phase phase division logic, phase 1 corresponds to control signal 1, phase 2 corresponds to control signal 2, phase 3 corresponds to control signal 3, phase 4 corresponds to control signal 4, phase 5 corresponds to control signal 5, phase 6 corresponds to control signal 6, phase 7 corresponds to control signal 7, and phase 8 corresponds to control signal 8. If the traffic light at the current moment is controlled by control signal 3, the current traffic phase is phase 3.

[0100] In actual application scenarios, the green light display time of a traffic light has a certain display range. The minimum green light display time is the shortest time that the traffic light displays green, and the maximum green light display time is the longest time that the traffic light displays green. It should be noted that the minimum green light display time and the maximum green light display time can be adaptively configured according to the needs of the actual application scenario, and are not specifically limited here.

[0101] In one embodiment, if the current traffic phase is phase 3 and the phase with the maximum pressure is phase 3, then the traffic phase is the phase with the maximum pressure, and the green light display time of phase 3 is extended to the maximum green light display time.

[0102] If the current passing phase is phase 3 and the phase with the maximum pressure is phase 5, then the passing phase is not the phase with the maximum pressure, and the green light display time of phase 3 is shortened to the minimum green light display time.

[0103] It should be noted that in some specific embodiments, if the current traffic phase is not the phase with the maximum pressure, but the pressure of the current traffic phase is the phase with the second pressure or the phase with the third pressure, the intersection controller can also adjust the green light display time according to the pressure value of the current traffic phase. For example, if the current traffic phase is the phase with the second pressure, the normal green light display time is 30s, the maximum green light display time is 45s, and the minimum green light display time is 15s, the green light display time of the current traffic phase can be adjusted to 40s.

[0104] In a specific embodiment, before adjusting the green light display time of the traffic light, it may also be determined whether it is necessary to adjust the green light display time of the traffic light in real time according to a preset dynamic adjustment condition.

[0105] For example, the preset dynamic adjustment condition may be to determine whether the pressure value of the phase where the maximum pressure is located is greater than a preset pressure threshold, and only when the pressure value of the phase where the maximum pressure is located is greater than the preset pressure threshold, adjust the green light display time of the traffic light.

[0106] The preset dynamic adjustment condition may also be the duration of the phase where the maximum pressure is located. When the duration of the phase where the maximum pressure is located in a certain phase exceeds a preset time threshold, the green light display time of the traffic light is adjusted.

[0107] In a specific embodiment, the preset dynamic adjustment conditions can be customized according to the traffic light control simulation needs of the actual application scenario, which is not limited here.

[0108] In this embodiment, by obtaining the pressure value of each phase of the intersection and adjusting the green light display time of each phase of the traffic light according to the pressure conditions of each phase of the intersection, the network throughput of the phase with a larger pressure value can be increased, thereby optimizing the traffic efficiency of the intersection.

[0109] In one embodiment, Figure 3 As shown, S104 further includes:

[0110] S205, if the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase with the maximum pressure, when the traffic light display time of the traffic phase is equal to the maximum green light time, the phase to be passed is determined according to the pressure value of each phase and the phase passing waiting time, and the traffic light of the passing phase is controlled to switch to yellow light display, and the traffic light of the phase to be passed is controlled to switch to green light display;

[0111] S206, if the traffic phase of the traffic light in the minimum calculation unit at the current moment is not the phase with the maximum pressure, when the traffic light display time of the traffic phase is equal to the minimum green light time, the traffic light of the traffic phase is controlled to switch to yellow light display, and the traffic light of the phase with the maximum pressure is controlled to switch to green light display.

[0112] In a specific embodiment, the display switching mode of the traffic light from red light to yellow light to green light is configured according to the needs of the actual application scenario, which is not limited in this embodiment.

[0113] In this embodiment, after the traffic light switches from green to yellow, it will switch to red after a preset time.

[0114] In actual application scenarios, this embodiment can preferentially adjust the control signal corresponding to the phase where the maximum pressure is located to the next control signal, thereby realizing maximum pressure control with priority given to the phase where the maximum pressure is located.

[0115] For example, if the current traffic phase is phase 3 and the phase with maximum pressure is phase 5, then the traffic phase is not the phase with maximum pressure. When the green light display time of phase 3 is equal to the minimum green light time, that is, phase 3 reaches the green light switching time.

[0116] In actual application scenarios, this embodiment can also determine the phase to be passed according to the pressure value of each phase and the waiting time for the phase to pass. The specific implementation logic can be to arrange the execution order of the control signals corresponding to each phase according to the order of the pressure values ​​of each phase. For example, if the pressure values ​​of phase 1, phase 2, phase 3 and phase 4 are in descending order, the execution order of the control signals is control signal 1, control signal 2, control signal 3 and control signal 4. If phase 1 is the passing phase, phase 2 can be determined as the phase to be passed.

[0117] The phase pass waiting time is the total length of time that the phase has not yet been converted to the pass state after it has been converted from the pass state to the prohibited pass state. The intersection controller in this embodiment detects the phase pass waiting time of each phase in real time, and sorts the phase pass waiting time of each phase, and arranges the execution order of the control signal corresponding to each phase according to the order of the phase pass waiting time of each phase. For example, if the phase pass waiting time of phase 1, phase 2, phase 3 and phase 4 decreases in sequence, the execution order of the control signal is control signal 1, control signal 2, control signal 3 and control signal 4. If phase 1 is the pass phase, phase 2 can be determined as the phase to be passed.

[0118] It should be noted that when determining the phase to be passed based on the pressure value and the phase waiting time, corresponding priorities can be set for the two judgment logics, for example, the judgment priority of the pressure value is greater than the phase waiting time. This embodiment does not specifically limit the judgment priority of the pressure value and the phase waiting time, and can be adaptively configured according to the needs of the actual application scenario.

[0119] In one embodiment, when determining the phase to be passed based on the phase passing waiting time, the phase passing waiting time can also be compared and judged based on a preset waiting time threshold. If and only if the phase passing waiting time is greater than or equal to the preset waiting time threshold, the corresponding phase is determined as the phase to be passed.

[0120] For example, if the current passing phase is phase 3 and the phase with the maximum pressure is phase 3, then the passing phase at this time is the phase with the maximum pressure. At this time, the phase passing waiting time of phase 2 exceeds the preset waiting threshold, and phase 2 is determined as the phase to be passed.

[0121] This embodiment dynamically adjusts the display strategy of traffic lights in the minimum calculation unit based on the maximum pressure control algorithm, so as to achieve the purpose of giving priority to the phase with the maximum pressure at each intersection, and effectively improve the traffic efficiency of vehicles at the intersection.

[0122] In one embodiment, S104 further includes:

[0123] According to the calculation results of multiple maximum pressure calculation threads corresponding to adjacent intersections, the display strategy of the traffic light of the preset minimum unit corresponding to any intersection among the adjacent intersections is dynamically adjusted.

[0124] In a specific embodiment, since the maximum pressure algorithm makes a judgment based on the queue lengths of the previous lane and the next lane, the update of the signal lights at each intersection will affect the changes of other adjacent signal lights.

[0125] In actual application, the adjacent intersections in this embodiment may be the intersections of the corresponding minimum calculation units when there is an intersection or connection between the positions of different minimum calculation units. It should be noted that when determining adjacent intersections, it can also be determined based on whether the signal light display strategies corresponding to the two intersections affect each other, which is not specifically limited in this embodiment.

[0126] In the dynamic adjustment process of this embodiment, priority is given to the phase with the maximum pressure to increase the throughput of the intersection queuing network. Therefore, the controllers of adjacent intersections can make collaborative judgments and update the display strategy of traffic lights according to the above logic to reduce the queue length at each intersection in the traffic network and improve traffic efficiency.

[0127] In one embodiment, Figure 4 As shown, in one embodiment, after the road network data and the vehicle data are divided and processed to obtain a plurality of minimum computing units, the method further includes:

[0128] S401, obtaining traffic flow information of each minimum computing unit within a target prediction time;

[0129] S402, the maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection within the target prediction time according to the road network data, vehicle data and corresponding traffic flow information of the minimum calculation unit in time stages according to the preset time step;

[0130] S403, dynamically adjusting the display strategy of the traffic lights in the minimum calculation unit of the corresponding time stage according to the calculation results of the maximum pressure calculation thread in each time stage, so as to obtain the target display strategy of the minimum calculation unit within the target prediction time.

[0131] In a specific embodiment, the traffic flow information includes information such as the number of vehicles on the road, the vehicle density carried by the road, and the queue lengths at various turning intersections at the intersection.

[0132] The target prediction time is a preset time period for traffic light control simulation. This embodiment does not specifically limit the target prediction time and can be adaptively configured according to the needs of actual application scenarios.

[0133] In the specific implementation process, this embodiment is based on each minimum computing unit, and obtains the AC flow information, road network data and vehicle data of each minimum computing unit within the target prediction time.

[0134] When calculating the pressure of each phase of the minimum calculation unit, the maximum pressure calculation thread performs corresponding pressure calculations according to the divided time stages, so that the intersection controller of each minimum calculation unit can dynamically adjust the display strategy of the traffic light according to the pressure calculation results of each time stage.

[0135] The setting of the preset time step can be configured based on a complete stage of the display of the signal lights at different intersections, and the complete stage is green light-red light-green light. It should be noted that the setting of the preset time step can be adaptively adjusted according to the needs of the actual application scenario, and this embodiment does not limit this.

[0136] In one embodiment, after obtaining the traffic flow information of each minimum computing unit within the target prediction time, the method further includes:

[0137] Divide the traffic flow information within the target prediction time into traffic flow information corresponding to each time stage according to the preset time step;

[0138] If any vehicle is at the boundary point of the minimum calculation unit in the current time stage, the relevant information of the vehicle is allocated to the traffic flow information of the next time stage.

[0139] In a specific embodiment, the communication flow information and vehicle data are dynamic traffic information in a preset area.

[0140] This embodiment obtains AC flow information and simulated vehicle data within the target prediction time based on a preset traffic flow prediction algorithm, road network data, and vehicle data, and divides the corresponding AC flow information and simulated vehicle data into corresponding time stages according to a preset time step.

[0141] In the specific implementation process, the boundary points of the minimum calculation unit are the boundary points of the road location information. This embodiment can determine the boundary points of each minimum calculation unit by setting a preset boundary area. The setting of the preset boundary area can be adaptively set according to the needs of the actual application scenario, which is not limited here.

[0142] In the process of distributing traffic flow information, data can be transmitted between parallel maximum pressure calculation threads. Since each maximum pressure calculation thread in this embodiment is established according to the minimum calculation unit, only the road network data, vehicle data and communication flow information at the boundary point position need to be transmitted between the maximum pressure calculation threads. In addition, this embodiment establishes the maximum pressure calculation thread based on MPI technology. If data transmission is required, data transmission can be realized based on the gather function of MPI.

[0143] In this embodiment, since the maximum pressure calculation thread only needs to consider the traffic flow information of the partial area location associated with each intersection, there is no need to obtain the traffic flow information of the entire road network data. This can effectively reduce the amount of data that needs to be transmitted between different maximum pressure calculation threads, thereby improving the efficiency of traffic light control simulation.

[0144] In one embodiment, the method further comprises:

[0145] The road network data and vehicle data of the current time period are updated according to the road network data and vehicle data of the previous time period.

[0146] In a specific embodiment, after the maximum pressure calculation thread calculates the pressure results of each phase of the intersection in the previous time period, the intersection controller corresponding to the minimum calculation unit can dynamically adjust the display strategy of the traffic lights at the intersection based on the traffic flow information, road network data and vehicle data in the previous time period.

[0147] After completing the step of dynamically adjusting the display strategy of the traffic lights in the previous time period, the present embodiment further updates the road network data, vehicle data and traffic flow information of the current time period according to the vehicle data, road network data, traffic flow information of the previous time period and the display strategy of the traffic lights at the corresponding intersection.

[0148] This embodiment dynamically adjusts the display strategy of the traffic lights at the intersection of each minimum calculation unit in time stages, and updates the vehicle data and road network data in real time, which can effectively improve the authenticity of the traffic light control simulation.

[0149] In summary, the embodiment of the present application provides a traffic light control method, which uses MPI technology to create multiple parallel maximum pressure calculation threads, can realize process-level parallel computing, quickly process large-scale traffic network data, and generate optimized signal control schemes to improve the traffic efficiency and safety of the traffic network. At the same time, the embodiment of the present application uses distributed technology to store and calculate network data and vehicle data, which can effectively improve the reliability and scalability of the traffic light control system. In addition, the embodiment of the present application uses a maximum pressure control algorithm, which can effectively reduce the queue length at each intersection in the traffic network, thereby alleviating congestion and improving traffic efficiency. The present invention also uses a map partitioning scheme based on physical location to minimize data transmission and maximize computing efficiency.

[0150] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiment of the present application also provides a signal light control device for implementing the signal light control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more signal light control device embodiments provided below can refer to the limitations of the signal light control method above, and will not be repeated here.

[0152] In one embodiment, Figure 5 As shown, a signal light control device 500 is provided, comprising: a data acquisition module 510, a data division module 520, a pressure calculation module 530, a strategy adjustment module 540 and a strategy generation module 550, wherein:

[0153] The data acquisition module 510 is used to acquire the road network data and vehicle data of the preset area, wherein the road network data includes intersection information and road information, and the vehicle data includes navigation information and driving information;

[0154] The data partitioning module 520 is used to perform data partitioning processing on the road network data and the vehicle data to obtain a plurality of minimum calculation units, wherein the minimum calculation unit is the location information of an intersection and its associated roads;

[0155] A pressure calculation module 530 is used to establish a plurality of maximum pressure calculation threads according to each minimum calculation unit, wherein the maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection according to the road network data and vehicle data of the minimum calculation unit;

[0156] A strategy adjustment module 540, used to dynamically adjust the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread;

[0157] The strategy generation module 550 is used to generate a traffic light control strategy in a preset area according to the target display strategy of the traffic light in each minimum calculation unit.

[0158] In one of the embodiments, the strategy adjustment module 540 is specifically used to arrange the calculation results of the maximum pressure calculation thread in order of pressure from large to small to obtain the phase where the maximum pressure is located; determine whether the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located; if the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located, adjust the traffic light display time of the traffic phase to the maximum green light time; if the traffic phase of the intersection in the minimum calculation unit at the current moment is not the phase where the maximum pressure is located, adjust the traffic light display time of the traffic phase to the minimum green light time.

[0159] In one embodiment, the strategy adjustment module 540 is specifically used to control the traffic light of the passing phase to switch to yellow light display, and control the traffic light of the waiting phase to switch to green light display, if the passing phase of the intersection in the minimum calculation unit at the current moment is the phase with the maximum pressure, and when the traffic light display time of the passing phase is equal to the maximum green light time, determine the phase to be passed according to the pressure value of each phase and the phase passing waiting time;

[0160] If the traffic phase of the traffic light in the minimum calculation unit at the current moment is not the phase with the maximum pressure, when the traffic light display time of the traffic phase is equal to the minimum green light time, the traffic light controlling the traffic phase is switched to yellow light display, and the traffic light controlling the phase with the maximum pressure is switched to green light display.

[0161] In one embodiment, the strategy adjustment module 540 is further used to dynamically adjust the display strategy of the traffic light of the preset minimum unit corresponding to any one of the adjacent intersections according to the calculation results of multiple maximum pressure calculation threads corresponding to the adjacent intersections.

[0162] In one embodiment, the data acquisition module 510 is specifically used to obtain the traffic flow information of each minimum computing unit within the target prediction time;

[0163] The pressure calculation module 530 is specifically used for the maximum pressure calculation thread to calculate the pressure of each phase of the intersection within the target prediction time according to the road network data, vehicle data and corresponding traffic flow information of the minimum calculation unit in time stages according to the preset time step;

[0164] The strategy adjustment module 540 is specifically used to dynamically adjust the display strategy of the traffic lights in the minimum computing unit of the corresponding time stage according to the calculation results of the maximum pressure calculation thread in each time stage, so as to obtain the target display strategy of the minimum computing unit within the target prediction time.

[0165] In one embodiment, the data acquisition module 510 is specifically used to divide the traffic flow information within the target prediction time into traffic flow information corresponding to each time stage according to a preset time step;

[0166] If any vehicle is at the boundary point of the minimum calculation unit in the current time stage, the relevant information of the vehicle is allocated to the traffic flow information of the next time stage.

[0167] In one embodiment, the signal light control device 500 further includes:

[0168] The data updating module is used to update the road network data and vehicle data of the current time period according to the road network data and vehicle data of the previous time period.

[0169] In summary, this embodiment provides a traffic light control device, which uses MPI technology to create multiple parallel maximum pressure calculation threads, can realize process-level parallel computing, quickly process large-scale traffic network data, and generate optimized signal control schemes to improve the traffic efficiency and safety of the traffic network. At the same time, the embodiment of the present application uses distributed technology to store and calculate network data and vehicle data, which can effectively improve the reliability and scalability of the traffic light control system. In addition, the embodiment of the present application uses a maximum pressure control algorithm, which can effectively reduce the queue length at each intersection in the traffic network, thereby alleviating congestion and improving traffic efficiency. The present invention also uses a map partitioning scheme based on physical location to minimize data transmission and maximize computing efficiency.

[0170] Each module in the above-mentioned signal light control device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0171] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a signal light control method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0172] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the signal light control method in the above method embodiment when executing the computer program.

[0174] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the signal light control method in the aforementioned method embodiment are implemented.

[0175] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0176] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0177] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A signal light control method, characterized in that: The method comprises: Acquire road network data and vehicle data of a preset area, wherein the road network data includes intersection information and road information, and the vehicle data includes navigation information and driving information; Performing data division processing on the road network data and the vehicle data to obtain a plurality of minimum calculation units, wherein the minimum calculation unit is location information of an intersection and its associated roads; Establishing a plurality of maximum pressure calculation threads according to each of the minimum calculation units based on a preset parallel programming technology, wherein the maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection according to the road network data and vehicle data of the minimum calculation unit, and the preset parallel programming technology is a message passing interface technology; Dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread; Generating a traffic light control strategy within the preset area according to the display strategy of the traffic light in each minimum calculation unit; The dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread includes: Arrange the calculation results of the maximum pressure calculation thread in order from large to small pressure to obtain the phase where the maximum pressure is located; Determine whether the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located; If the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located, the traffic light display time of the traffic phase is adjusted to the maximum green light time; If the traffic phase of the intersection in the minimum calculation unit at the current moment is not the phase where the maximum pressure is located, the traffic light display time of the traffic phase is adjusted to the minimum green light time.

2. The method according to claim 1, characterized in that The dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread also includes: If the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase with the maximum pressure, when the traffic light display time of the traffic phase is equal to the maximum green light time, the phase to be passed is determined according to the pressure value of each phase and the phase passing waiting time, the traffic light of the traffic phase is controlled to switch to yellow light display, and the traffic light of the phase to be passed is controlled to switch to green light display; If the traffic phase of the traffic light in the minimum calculation unit at the current moment is not the phase where the maximum pressure is located, when the traffic light display time in the traffic phase is equal to the minimum green light time, the traffic light in the traffic phase is controlled to switch to yellow light display, and the traffic light in the phase where the maximum pressure is located is controlled to switch to green light display.

3. The method according to claim 1, characterized in that: The dynamically adjusting the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread also includes: According to the calculation results of multiple maximum pressure calculation threads corresponding to adjacent intersections, the display strategy of the traffic light of the preset minimum unit corresponding to any intersection among the adjacent intersections is dynamically adjusted.

4. The method according to claim 1, characterized in that: After the road network data and the vehicle data are subjected to data division processing to obtain a plurality of minimum calculation units, the method further comprises: Obtain the traffic flow information of each minimum computing unit within the target prediction time; The maximum pressure calculation thread is used to calculate the pressure of each phase of the intersection within the target prediction time according to the road network data, vehicle data and corresponding traffic flow information of the minimum calculation unit in time stages according to a preset time step; According to the calculation results of the maximum pressure calculation thread in each time stage, the display strategy of the traffic lights in the minimum calculation unit in the corresponding time stage is dynamically adjusted to obtain the target display strategy of the minimum calculation unit within the target prediction time.

5. The method according to claim 4, characterized in that After obtaining the traffic flow information of each minimum computing unit within the target prediction time, the method further includes: Divide the traffic flow information within the target prediction time into traffic flow information corresponding to each time stage according to the preset time step; If any vehicle is at a boundary point of the minimum calculation unit in the current time stage, the relevant information of the vehicle is allocated to the traffic flow information of the next time stage.

6. The method according to claim 4, characterized in that The method further comprises: The road network data and vehicle data of the current time period are updated according to the road network data and vehicle data of the previous time period.

7. A signal light control device, characterized in that: The device comprises: A data acquisition module, used to acquire road network data and vehicle data of a preset area, wherein the road network data includes intersection information and road information, and the vehicle data includes navigation information and driving information; A data partitioning module, used for performing data partitioning processing on the road network data and the vehicle data to obtain a plurality of minimum calculation units, wherein the minimum calculation unit is location information of an intersection and its associated roads; A pressure calculation module, used for establishing a plurality of maximum pressure calculation threads according to each of the minimum calculation units based on a preset parallel programming technology, wherein the maximum pressure calculation thread is used for calculating the pressure of each phase of the intersection according to the road network data and vehicle data of the minimum calculation unit, and the preset parallel programming technology is a message passing interface technology; A strategy adjustment module, used to dynamically adjust the display strategy of the traffic light in the minimum calculation unit according to the calculation result of the maximum pressure calculation thread; A strategy generation module, used for generating a traffic light control strategy within the preset area according to a target display strategy of the traffic light in each minimum calculation unit; The strategy adjustment module is used to arrange the calculation results of the maximum pressure calculation thread in order from large to small pressure to obtain the phase where the maximum pressure is located; determine whether the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located; if the traffic phase of the intersection in the minimum calculation unit at the current moment is the phase where the maximum pressure is located, adjust the traffic light display time of the traffic phase to the maximum green light time; if the traffic phase of the intersection in the minimum calculation unit at the current moment is not the phase where the maximum pressure is located, adjust the traffic light display time of the traffic phase to the minimum green light time.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images