A traffic signal control method and device, computer equipment and storage medium

Abstract

The application provides a traffic signal control method and device, computer equipment and a storage medium, wherein a signal control algorithm library of a target area is constructed; a target control target of the target area is determined according to a traffic flow running speed, a traffic flow rate and an overflow coefficient of the target area; each control node in the target area is grouped according to a preset neighborhood radius to obtain a plurality of target control objects; for each target control object, a target signal control algorithm set of the target control object is determined from the signal control algorithm library according to the target control object and the target control target; a target signal control algorithm of the target control object is determined from the target signal control algorithm set of the target control object according to a data sensing capability level of the target control object; and the target control object is controlled by using the target control algorithm of the target control object. The above method is used to realize effective traffic signal control.

Description

Technical Field

[0001] This invention relates to the field of traffic signal control technology, and more specifically, to a traffic signal control method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Traffic signal control relies on traffic police or traffic signal control facilities to direct the movement of vehicles and pedestrians according to changes in traffic conditions. Traffic control utilizes modern communication facilities, signaling devices, sensors, monitoring equipment, and computers to accurately organize and regulate vehicles in operation, ensuring their safe and smooth operation.

[0003] In existing technologies, traffic signal control in a given area typically involves personnel surveying and assessing the traffic conditions, then applying experience to implement traffic signal control based on the assessment results. However, research has revealed that this method can be flawed due to subjective human factors during the assessment process, leading to inaccurate results and ultimately hindering effective traffic signal control. Furthermore, relying solely on experience for traffic signal control can also be limited by the limited experience of the personnel involved, resulting in ineffective traffic signal control. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a traffic signal control method, apparatus, computer equipment and storage medium to achieve effective traffic signal control.

[0005] In a first aspect, embodiments of this application provide a traffic signal control method, the method comprising:

[0006] A signal control algorithm library for a target area is constructed, wherein the signal control algorithm library includes multiple signal control algorithm sets capable of controlling different control objects within the target area to achieve different control objectives, and each signal control algorithm set contains multiple selectable signal control algorithms;

[0007] The target control objective for the target area is determined based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area, wherein the overflow coefficient is used to describe the overflow degree of the target area;

[0008] Based on a preset neighborhood radius, each control node within the target area is grouped to obtain multiple target control objects;

[0009] For each target control object, a set of target signal control algorithms for that target control object is determined from the signal control algorithm library based on the target control object and the target control objective.

[0010] The target signal control algorithm for the target controlled object is determined from the set of target signal control algorithms for the target controlled object based on the data perception capability level of the target controlled object.

[0011] The target control algorithm of the target control object is used to control the traffic signal of the target control object.

[0012] Optionally, determining the target control objective for the target area based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area includes:

[0013] A delay coefficient is determined based on the traffic flow speed in the target area to describe the degree of delay in the target area, wherein the traffic flow speed includes the actual traffic flow speed and the preset free flow speed;

[0014] Based on the traffic flow rate of the target area, a trunk line saturation density coefficient is determined to describe the degree of trunk line congestion in the target area, wherein the traffic flow rate includes the actual weighted flow rate and the preset maximum weighted flow rate;

[0015] The regional saturation density coefficient for describing the congestion level of the target area is determined based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, wherein the magnitude of the regional saturation density coefficient is positively correlated with the congestion level of the target area;

[0016] The control target corresponding to the saturation density coefficient of the region is determined from the pre-configured control target database and used as the target control target.

[0017] Optionally, determining the delay coefficient to describe the delay level of the target area based on the traffic flow speed of the target area includes:

[0018] The delay coefficient ρ1 is determined using the following expression:

[0019]

[0020] Among them, v r v is the actual traffic flow velocity. f The preset free-flow velocity;

[0021] The step of determining the arterial saturation density coefficient, which describes the degree of arterial congestion in the target area, based on the traffic flow rate of the target area, includes:

[0022] The saturation density coefficient ρ2 of the trunk line is determined using the following expression:

[0023]

[0024] Where, k r k is the actual weighted flow rate. m The preset maximum weighted flow rate;

[0025] The overflow coefficient ranges from {0,1}, where 0 represents no overflow and 1 represents overflow.

[0026] The step of determining the regional saturation density coefficient for describing the congestion level of the target area based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient includes:

[0027] Determine whether the overflow coefficient is 1;

[0028] If the overflow coefficient is 1, then the overflow coefficient is determined as the saturation density coefficient of the region;

[0029] If the overflow coefficient is not 1, then determine whether the delay coefficient exceeds the trunk line saturation density coefficient;

[0030] If the delay coefficient exceeds the trunk line saturation density coefficient, then the delay coefficient is determined as the regional saturation density coefficient;

[0031] If the delay coefficient does not exceed the trunk line saturation density coefficient, then the trunk line saturation density coefficient is determined as the regional saturation density coefficient.

[0032] Optionally, the step of grouping each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects includes:

[0033] Multiple target control objects are obtained through the following steps:

[0034] Step 1: Initialize the label of each control node in the target area to unclassified, and determine the starting point for grouping the control nodes according to the node level of each control node;

[0035] Step 2: Traverse the labels of each control node and determine whether the label of control node q is unclassified; if not, skip control node q; if so, determine the neighborhood N(q) of control node q according to the following expression:

[0036] N(q)={o|o∈Q,distance(o,q)≤Eps}

[0037] Where Eps is the neighborhood radius of control node q, and control node O is a control node included in the neighborhood N(q) of control node q.

[0038] Step 3: Determine whether the number of control nodes contained in the neighborhood N(q) exceeds the preset standard number MinPts; if so, take the control node q corresponding to the neighborhood N(q) as the core point, and also take the starting point determined in Step 1 as the core point. Create a cluster for the core point, and add the control node q and the control nodes whose density is reachable to the cluster.

[0039] Step 4: Recursively process all control nodes in the cluster. For each control node o, if control node o is not yet classified, add control node o to the cluster and return to steps 2 to 4 to continue finding the neighborhood N(O) of control node o until there are no unclassified control nodes in the target area.

[0040] Step 5: Generate multiple target control objects based on the control nodes contained in the cluster created for each core point.

[0041] Optionally, before determining the target signal control algorithm for the target controlled object from the set of target signal control algorithms based on the data perception capability level of the target controlled object, the method further includes:

[0042] The membership degree f(x) of the data perception capability of the target control object is determined using the following membership function:

[0043] f(x)=sigmod(αx1+βx2+μx3);

[0044] Where x1 represents the cross-sectional data perception capability of the target control object, x2 represents the video data perception capability of the target control object, x3 represents the Internet data perception capability of the target control object, α is the weight coefficient of the cross-sectional data perception capability, β is the weight coefficient of the video data perception capability, and μ is the weight coefficient of the Internet data perception capability.

[0045] The data perception capability level of the target control object is determined based on the membership degree of the target control object's data perception capability and the preset data perception capability level classification rules.

[0046] Optionally, determining the target signal control algorithm for the target controlled object from the set of target signal control algorithms based on the data perception capability level of the target controlled object includes:

[0047] The preferred algorithm category for the target control object is determined based on the data perception capability level of the target control object.

[0048] The signal control algorithm belonging to the preferred algorithm category of the target control object in the target signal control algorithm set is determined as the target signal control algorithm of the target control object.

[0049] Optionally, the controlled objects include single-point signal control units, trunk line signal control units, and area signal control units; the control objectives include preventing overflow deadlock, ensuring traffic capacity, improving traffic efficiency, and ensuring traffic safety.

[0050] Secondly, embodiments of this application provide a traffic signal control device, the device comprising:

[0051] A signal control algorithm library construction module is used to construct a signal control algorithm library for a target area. The signal control algorithm library includes multiple signal control algorithm sets that can control different control objects within the target area to achieve different control objectives. Each signal control algorithm set contains multiple optional signal control algorithms.

[0052] The target control target determination module is used to determine the target control target of the target area based on the traffic flow speed, traffic flow rate and overflow coefficient of the target area, wherein the overflow coefficient is used to describe the overflow degree of the target area;

[0053] The target control object determination module is used to group each control node in the target area according to a preset neighborhood radius to obtain multiple target control objects;

[0054] The target signal control algorithm set determination module is used to determine the target signal control algorithm set of each target control object from the signal control algorithm library based on the target control object and the target control objective.

[0055] The target signal control algorithm determination module is used to determine the target signal control algorithm of the target control object from the target signal control algorithm set of the target control object based on the data perception capability level of the target control object;

[0056] The traffic signal control module is used to perform traffic signal control on the target control object using the target control algorithm of the target control object.

[0057] Optionally, when the target control target determination module determines the target control target of the target area based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area, it is specifically used for:

[0058] A delay coefficient is determined based on the traffic flow speed in the target area to describe the degree of delay in the target area, wherein the traffic flow speed includes the actual traffic flow speed and the preset free flow speed;

[0059] Based on the traffic flow rate of the target area, a trunk line saturation density coefficient is determined to describe the degree of trunk line congestion in the target area, wherein the traffic flow rate includes the actual weighted flow rate and the preset maximum weighted flow rate;

[0060] The regional saturation density coefficient for describing the congestion level of the target area is determined based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, wherein the magnitude of the regional saturation density coefficient is positively correlated with the congestion level of the target area;

[0061] The control target corresponding to the saturation density coefficient of the region is determined from the pre-configured control target database and used as the target control target.

[0062] Optionally, when the target control target determination module determines the delay coefficient describing the delay level of the target area based on the traffic flow speed of the target area, it specifically performs the following:

[0063] The delay coefficient ρ1 is determined using the following expression:

[0064]

[0065] Among them, v r v is the actual traffic flow velocity. f The preset free-flow velocity;

[0066] When the target control target determination module determines the arterial saturation density coefficient, which describes the degree of arterial congestion in the target area, based on the traffic flow rate of the target area, it is specifically used for:

[0067] The saturation density coefficient ρ2 of the trunk line is determined using the following expression:

[0068]

[0069] Where, k r k is the actual weighted flow rate. m The preset maximum weighted flow rate;

[0070] The overflow coefficient ranges from {0, 1}, where 0 represents no overflow and 1 represents overflow.

[0071] When the target control target determination module determines the area saturation density coefficient describing the congestion level of the target area based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, it is specifically used for:

[0072] Determine whether the overflow coefficient is 1;

[0073] If the overflow coefficient is 1, then the overflow coefficient is determined as the saturation density coefficient of the region;

[0074] If the overflow coefficient is not 1, then determine whether the delay coefficient exceeds the trunk line saturation density coefficient;

[0075] If the delay coefficient exceeds the trunk line saturation density coefficient, then the delay coefficient is determined as the regional saturation density coefficient;

[0076] If the delay coefficient does not exceed the trunk line saturation density coefficient, then the trunk line saturation density coefficient is determined as the regional saturation density coefficient.

[0077] Optionally, when the target control object determination module is used to group each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects, it is specifically used for:

[0078] Multiple target control objects are obtained through the following steps:

[0079] Step 1: Initialize the label of each control node in the target area to unclassified, and determine the starting point for grouping the control nodes according to the node level of each control node;

[0080] Step 2: Traverse the labels of each control node and determine whether the label of control node q is unclassified; if not, skip control node q; if so, determine the neighborhood N(q) of control node q according to the following expression:

[0081] N(q)={o|o∈Q,distance(o,q)≤Eps}

[0082] Where Eps is the neighborhood radius of control node q, and control node o is a control node included in the neighborhood N(q) of control node q;

[0083] Step 3: Determine whether the number of control nodes contained in the neighborhood N(q) exceeds the preset standard number MinPts; if so, take the control node q corresponding to the neighborhood N(q) as the core point, and also take the starting point determined in Step 1 as the core point. Create a cluster for the core point, and add the control node q and the control nodes whose density is reachable to the cluster.

[0084] Step 4: Recursively process all control nodes in the cluster. For each control node o, if control node o is not yet classified, add control node o to the cluster and return to steps 2 to 4 to continue finding the neighborhood N(O) of control node o until there are no unclassified control nodes in the target area.

[0085] Step 5: Generate multiple target control objects based on the control nodes contained in the cluster created for each core point.

[0086] Optionally, the device further includes:

[0087] The membership determination module is used to determine the membership degree f(x) of the data perception capability of the target control object using the following membership function before determining the target signal control algorithm of the target control object from the set of target signal control algorithms based on the data perception capability level of the target control object:

[0088] f(x)=sigmod(αx1+βx2+μx2);

[0089] Where x1 represents the cross-sectional data perception capability of the target control object, x2 represents the video data perception capability of the target control object, x3 represents the Internet data perception capability of the target control object, α is the weight coefficient of the cross-sectional data perception capability, β is the weight coefficient of the video data perception capability, and μ is the weight coefficient of the Internet data perception capability.

[0090] The data perception capability level determination module is used to determine the data perception capability level of the target control object based on the membership degree of the target control object's data perception capability and the preset data perception capability level classification rules.

[0091] Optionally, when the target signal control algorithm is used to determine the target signal control algorithm for the target control object from the set of target signal control algorithms for the target control object based on the data perception capability level of the target control object, it is specifically used for:

[0092] The preferred algorithm category for the target control object is determined based on the data perception capability level of the target control object.

[0093] The signal control algorithm belonging to the preferred algorithm category of the target control object in the target signal control algorithm set is determined as the target signal control algorithm of the target control object.

[0094] Optionally, the controlled objects include single-point signal control units, trunk line signal control units, and area signal control units; the control objectives include preventing overflow deadlock, ensuring traffic capacity, improving traffic efficiency, and ensuring traffic safety.

[0095] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the traffic signal control method described in any of the optional embodiments of the first aspect above.

[0096] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the traffic signal control method described in any of the optional embodiments of the first aspect.

[0097] The technical solution provided in this application includes, but is not limited to, the following beneficial effects:

[0098] This application first constructs a signal control algorithm library for target areas based on different control objects and control objectives, providing a foundation and basis for subsequent algorithm selection based on the actual traffic conditions of the target area. Then, based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area, the target control objectives of the target area are determined. Furthermore, each control node within the target area is grouped according to a preset neighborhood radius to obtain multiple target control objects, thereby achieving accurate traffic status based on objectively existing traffic data without requiring personnel to conduct investigations or assessments. Finally, for each target control object, based on the target control object and the target control objective, the following algorithm is used to determine the target control objectives: The system identifies a set of target signal control algorithms for the target controlled object from the signal control algorithm library. Based on the data perception capability level of the target controlled object, it selects the appropriate target signal control algorithm from this set. This avoids the need for personnel to formulate traffic signal control strategies based on their experience for a given area. Instead, it allows for the selection of signal control algorithms that meet specific control objectives for each controlled object within a given area. Finally, the target control algorithm is used to perform traffic signal control on the target controlled object, achieving effective traffic signal control without human intervention.

[0099] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0100] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0101] Figure 1 A flowchart of a traffic signal control method provided in Embodiment 1 of the present invention is shown;

[0102] Figure 2 A flowchart of a target control target determination method provided in Embodiment 1 of the present invention is shown;

[0103] Figure 3 The flowchart of a method for determining the level of data perception capability provided in Embodiment 1 of the present invention is shown;

[0104] Figure 4 A flowchart of a target signal control algorithm determination method provided in Embodiment 1 of the present invention is shown;

[0105] Figure 5 A schematic diagram of the structure of a traffic signal control device provided in Embodiment 2 of the present invention is shown;

[0106] Figure 6 A schematic diagram of the structure of the second type of traffic signal control device provided in Embodiment 2 of the present invention is shown;

[0107] Figure 7 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown. Detailed Implementation

[0108] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0109] Example 1

[0110] To facilitate understanding of this application, the following is combined with... Figure 1The flowchart of a traffic signal control method provided in Embodiment 1 of the present invention illustrates the content of Embodiment 1 in detail.

[0111] See Figure 1 The above, Figure 1 A flowchart of a traffic signal control method according to Embodiment 1 of the present invention is shown, wherein the method includes steps S101 to S106:

[0112] S101: Construct a signal control algorithm library for the target area, wherein the signal control algorithm library includes multiple signal control algorithm sets that can control different control objects within the target area to achieve different control objectives, and each signal control algorithm set contains multiple selectable signal control algorithms.

[0113] Specifically, each control target and each control object are combined to obtain different control combinations. A corresponding set of signal control algorithms is set for each control combination. Then, a signal control algorithm library is constructed using the number of control targets and control objects as the matrix dimension and the corresponding set of signal control algorithms as the matrix elements.

[0114] Construct a signal control strategy algorithm library F. Let the number of control targets be m and the number of control objects be n. Divide the algorithm library into two dimensions: control targets and control objects, resulting in an m×n algorithm matrix. Define the elements in the matrix as f. xy Where x≤m, y≤n, and f belongs to F. The control objectives include four aspects: preventing overflow, ensuring traffic capacity, improving traffic efficiency, and guaranteeing traffic safety. The control objects are divided into single-point signal control units, trunk line signal control units, and area signal control units. The matching table of the constructed signal control strategy algorithm library is shown in the following table:

[0115]

[0116] For element f in the signal control strategy algorithm library xy Expanding the results, we obtain the signal control algorithm set under different control objectives and controlled objects, as shown in the table below:

[0117] element Signal control algorithm set <![CDATA[f 11 ]]> Overflow algorithm, deadlock algorithm <![CDATA[f 12 ]]> Trunk overflow algorithm, trunk green wave algorithm <![CDATA[f 13 ]]> Region slow-in fast-out algorithm <![CDATA[d 21 ]]> Shortest green light time algorithm, tidal control algorithm, phase overlap algorithm <![CDATA[f 22 ]]> Trunk static green wave algorithm, trunk dynamic green wave algorithm, maximum bandwidth algorithm <![CDATA[f 23 ]]> Regional green wave algorithm, sub-region dynamic allocation algorithm, sub-region coordinated control algorithm <![CDATA[f 31 ]]> Single-point center sensing, single-point center adaptive, single-point multi-time period optimization <![CDATA[f 32 ]]> Trunk line dynamic green wave algorithm, trunk line multi-time period optimization, trunk line coordinated control algorithm <![CDATA[f 33 ]]> Regional multi-time period optimization, sub-region dynamic allocation algorithm, and sub-region coordinated control algorithm <![CDATA[f 41 ]]> Bus priority algorithm, pedestrian green light time algorithm <![CDATA[f 42 ]]> Pedestrian crossing branch road sensing control algorithm <![CDATA[f 43 ]]> Regional Inlet Flow Balancing Control Algorithm

[0118] S102: Determine the target control target of the target area based on the traffic flow speed, traffic flow rate and overflow coefficient of the target area, wherein the overflow coefficient is used to describe the overflow degree of the target area.

[0119] Specifically, based on different traffic state dimensions, three different saturation density coefficients are set for the target area: delay coefficient ρ1, trunk line saturation density coefficient ρ2, and overflow coefficient ρ3. Then, the regional saturation density coefficient ρ is determined based on the delay coefficient ρ1, trunk line saturation density coefficient ρ2, and overflow coefficient ρ3. Finally, the target control target for the target area is determined based on the regional saturation density coefficient ρ.

[0120] The following sections explain the delay coefficient ρ1, the trunk line saturation density coefficient ρ2, and the overflow coefficient ρ3:

[0121] 1. Delay coefficient v1 is an indicator used to measure the degree of delay or congestion in a transportation system. The delay coefficient ρ1 is determined using the following expression:

[0122] Among them, v r v is the actual traffic flow velocity. f The preset free-flow velocity. The smaller the value, the lower the traffic efficiency within the target area; the larger the value of ρ1, the more congested the road surface is.

[0123] 2. The arterial road saturation density coefficient ρ2 is an indicator used to measure the relationship between traffic flow and road capacity, serving as a measure of road traffic congestion and efficiency. The arterial road saturation density coefficient ρ2 is determined using the following expression:

[0124] Where, k r k represents the actual weighted flow rate. m The preset maximum weighted flow rate is used. The traffic flow rate is detected and found to be close to the critical point of road network control, that is, if the traffic volume continues to increase, it will cause instability of the traffic system. At this time, the coefficient ρ2 tends to 1.

[0125] 3. ρ3 is the overflow coefficient, with a value range of {0,1}. 0 represents no overflow or deadlock, and 1 represents overflow or deadlock. Here, the overflow control start threshold is defined.

[0126] (1) Based on practical engineering experience, queue overflow detectors are installed 30-80 meters upstream of the bottleneck section from the entrance of the section. If the detector detects stopped vehicles for a long time, it is considered that there is a risk of vehicle queue overflow or is about to occur, and corresponding overflow control measures should be taken in time. At this time, the overflow control start threshold is the distance from the stop line to the queue overflow detector. (2) Queue overflow detectors are deployed by setting an overflow safety factor. The product of the bottleneck section length L and the preset overflow safety factor a is used as the allowable vehicle queue length value of the bottleneck section, that is, the distance from the stop line to the queue overflow detector. The recommended value range of the overflow safety factor is 0.8 to 1.0. Combining the above two methods, considering the upstream vehicle arrival intensity and the downstream queue discharge capacity, the dynamic overflow control start threshold L is defined. safe Calculation method:

[0127]

[0128] Where L represents the length of the bottleneck section; L car γ represents the effective vehicle length, equal to the average headway between vehicles queuing at the intersection entrance. Typically, the empirical values ​​are 17m for large vehicles and 7m for small vehicles. γ is a preset expansion coefficient. Since vehicles have headway when queuing in traffic congestion, this expansion coefficient is set to more accurately match the congestion length. Its suggested value range is [1, 1.2]. s q represents the average arrival rate of vehicles on a road segment. t This represents the saturation flow rate during the green light phase of the overflow phase at the bottleneck intersection, typically taken as an empirical value of 1600-1900 pcu / h; C is the cycle time of the bottleneck intersection; G represents the green light time of the overflow phase at the bottleneck intersection. When the queue length at the intersection > overflow threshold L... safe When the traffic volume at the intersection meets the dynamic overflow control start threshold, the overflow / deadlock coefficient v3 is determined to be 1.

[0129] When ρ3 = 1, it indicates that overflow or deadlock is about to occur, and the regional saturation density coefficient ρ = ρ3. When ρ3 = 0, the larger value between coefficients ρ1 and ρ2 is selected as the regional saturation density coefficient ρ. Based on the obtained regional saturation density coefficient ρ, a threshold is further set to determine the target control objective.

[0130] When the regional saturation density coefficient ρ≥1, it indicates that the road network in the target area is in an oversaturated state, and the target control objective is to prevent overflow; when 0.7<ρ<1, it indicates that the road network in the target area is approaching saturation, and the target control objective is to ensure traffic capacity; when ρ≤0.7, it indicates that the road network in the target area is in an unsaturated state, and the target control objective is to improve traffic efficiency; when an accident is detected or there is a large demand for pedestrian and non-motorized vehicle travel, the target control objective is to ensure traffic safety, and this objective has the highest priority.

[0131] S103: Group each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects.

[0132] Specifically, the set of each control node in the target area is divided according to a certain process to obtain the final control unit (i.e. the target control object). The control units are classified according to the number of control nodes they contain. The categories include single-point signal control unit (containing one control node), trunk signal control unit (containing two control nodes), or area signal control unit (containing more than two control nodes).

[0133] Let the total number of control nodes in the target area be l, and let q represent the number of control nodes. Define the set of control nodes as Q, q z It is the z-th control node in the target region, 1≤z≤l, q z ∈Q. Based on the set partitioning conditions, the final target control object can be obtained as {q1,q2,…q}. i}、{q j ,q j+1 ,…q b}、…、{q b ,q b+1 ,…q l}

[0134] S104: For each target control object, determine the target signal control algorithm set of the target control object from the signal control algorithm library based on the target control object and the target control objective.

[0135] Specifically, the target control target determined in step S102 and the target control object determined in step S103 are matched with multiple target signal control algorithm sets that satisfy the target control target in the signal control algorithm library obtained in step S101.

[0136] S105: Determine the target signal control algorithm of the target control object from the target signal control algorithm set based on the data perception capability level of the target control object.

[0137] Specifically, the optional signal control algorithms are first categorized into four types: fixed timing control, inductive control, adaptive control, and reinforcement learning control. That is, each optional signal control algorithm corresponds to one control category. After obtaining the target signal control algorithm set for each target control object through step S104, the control category of the target control object is determined based on its data perception capability level. Then, the optional signal control algorithms belonging to the control category of the target control object are selected from the target signal control algorithm set as the target signal control algorithms for that target control object.

[0138] The four control categories are explained and described here:

[0139] 1. Fixed Timing Control Category: This category adjusts the duration and phase timing of traffic lights according to a pre-set signal control plan and cycle. Fixed Cycle control is the most typical, where signal phases are executed cyclically according to a fixed time period. Other types include Time-Based algorithms and Actuated Control algorithms, which allow for more flexible adjustments based on traffic flow changes. These include, but are not limited to, arterial filtering algorithms and maximum bandwidth algorithms.

[0140] 2. Sensor-based control: This type of control dynamically adjusts the duration and phase timing of traffic lights based on real-time traffic flow information. It includes single-point control and area control. Single-point control uses traffic detectors to monitor and control traffic flow at a single intersection. Area control considers traffic flow information from multiple adjacent intersections and improves overall traffic efficiency by coordinating and adjusting signal phase timing. This includes, but is not limited to, arterial overflow algorithms and arterial dynamic green wave algorithms.

[0141] 3. Adaptive Control Category: This category dynamically optimizes signal control strategies through real-time monitoring, data analysis, and intelligent algorithms. Common algorithms include signal control based on Cyclic Flow Adjustments, Minimizing Vehicle Delay, and Maximizing Intersection Capacity. These algorithms dynamically adjust the duration, phase timing, and priority of traffic lights based on traffic flow and other factors to maximize traffic efficiency and flow. This includes, but is not limited to, multi-period optimization algorithms for arterial roads.

[0142] 4. Reinforcement learning control category: It learns the optimal signal timing strategy through interaction with the environment. The algorithm selects the optimal action (such as the green light duration of each phase) based on the current state (such as traffic flow, queue length, etc.), and evaluates the quality of each action according to a pre-defined reward function. Through continuous attempts and feedback, the reinforcement learning algorithm can gradually optimize the signal control strategy to maximize the efficiency of the entire traffic network. It includes but is not limited to arterial coordination control algorithms.

[0143] Then, according to the above algorithm classification, different trigger conditions are set to meet the diverse traffic scenario requirements. Here, the data perception ability is set as the trigger condition (the data perception ability refers to the ability of the detection devices deployed at the intersection to obtain various traffic data at the intersection), and the fuzzy control theory is used for analysis. Four membership functions (unable to perceive, local perception, basic perception, holographic perception) configured for the data perception ability are used to represent the membership degree of the input variable (what kind of data can be obtained), and four membership functions (fixed time, induction, multi-period, adaptive) are set to represent the membership degree of the output variable (which algorithm to select). The membership function formula is as follows:

[0144] f(x) = sigmod(αx1 + βx2 + μx3)

[0145] Among them, f(x) is the membership degree of the data perception ability of the target control object, x1 represents the cross-section data perception ability of the target control object, x2 represents the video data perception ability of the target control object, x3 represents the Internet data perception ability of the target control object, α is the weight coefficient of the cross-section data perception ability, β is the weight coefficient of the video data perception ability, and μ is the weight coefficient of the Internet data perception ability.

[0146] When f(x) ≤ 0.2, the data perception ability of the target control object is defined as unable to perceive N1; when 0.2 < f(x) ≤ 0.5, the data perception ability of the target control object is defined as local perception N2; when 0.5 < f(x) ≤ 0.7, the data perception ability of the target control object is defined as basic perception N3; when 0.7 < f(x) ≤ 1, the data perception ability of the target control object is defined as holographic perception N4. According to the above content, a set of fuzzy rules is defined as follows:

[0147] if perception ability == N1, then the control algorithm belongs to the fixed-time control category;

[0148] else if perception ability == N2, then the control algorithm belongs to the induction control category;

[0149] else if perception ability == N3, then the control algorithm belongs to the adaptive control category;

[0150] If the perception capability is equal to N4, then the control algorithm belongs to the reinforcement learning control category.

[0151] Based on the above rule definition, the target signal control algorithm set for each target control object can be determined according to the target control object and the target control objective. Furthermore, the target signal control algorithm can be determined by the data perception capability of each target control object, thus completing the algorithm selection under the perception capability.

[0152] S106: Use the target control algorithm of the target control object to perform traffic signal control on the target control object.

[0153] Specifically, the target area is monitored in real time, and both static and dynamic detection frequencies are set to detect the target control target and the target control object. If either the target control target or the target control object changes, the selected target control algorithm needs to be updated according to steps S102-S105 to complete the automated algorithm scheduling. The static detection frequency is suitable for control areas where traffic changes are not significant, and the frequency is a fixed time interval; the dynamic detection frequency is suitable for control areas where traffic fluctuates significantly, and the frequency is a variable time interval.

[0154] In one feasible implementation plan, see Figure 2 As shown, Figure 2 The flowchart of a target control target determination method provided in Embodiment 1 of the present invention is shown, wherein determining the target control target of the target area based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area includes steps S201 to S204:

[0155] S201: Determine a delay coefficient to describe the degree of delay in the target area based on the traffic flow speed in the target area, wherein the traffic flow speed includes the actual traffic flow speed and the preset free flow speed.

[0156] S202: Determine the trunk line saturation density coefficient to describe the degree of trunk line congestion in the target area based on the traffic flow rate of the target area, wherein the traffic flow rate includes the actual weighted flow rate and the preset maximum weighted flow rate.

[0157] S203: Determine the regional saturation density coefficient to describe the congestion level of the target area based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, wherein the magnitude of the regional saturation density coefficient is positively correlated with the congestion level of the target area.

[0158] S204: Determine the control target corresponding to the saturation density coefficient of the region from the pre-configured control target database as the target control target.

[0159] In one feasible implementation, determining the delay coefficient to describe the degree of delay in the target area based on the traffic flow speed in the target area includes:

[0160] The delay coefficient ρ1 is determined using the following expression:

[0161]

[0162] Among them, v r v is the actual traffic flow velocity. f The preset free-flow velocity.

[0163] The step of determining the arterial saturation density coefficient, which describes the degree of arterial congestion in the target area, based on the traffic flow rate of the target area, includes:

[0164] The saturation density coefficient ρ2 of the trunk line is determined using the following expression:

[0165]

[0166] Where, k r k is the actual weighted flow rate. m The preset maximum weighted flow rate.

[0167] The overflow coefficient ranges from {0, 1}, where 0 represents no overflow and 1 represents overflow.

[0168] The step of determining the regional saturation density coefficient for describing the congestion level of the target area based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient includes:

[0169] Determine whether the overflow coefficient is 1; if the overflow coefficient is 1, then determine the overflow coefficient as the regional saturation density coefficient; if the overflow coefficient is not 1, determine whether the delay coefficient exceeds the trunk line saturation density coefficient; if the delay coefficient exceeds the trunk line saturation density coefficient, then determine the delay coefficient as the regional saturation density coefficient; if the delay coefficient does not exceed the trunk line saturation density coefficient, then determine the trunk line saturation density coefficient as the regional saturation density coefficient.

[0170] In one feasible implementation, grouping each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects includes:

[0171] Multiple target control objects are obtained through the following steps:

[0172] Step 1: Initialize the label of each control node in the target area to unclassified, and determine the starting point for grouping the control nodes according to the node level of each control node.

[0173] Step 2: Traverse the labels of each control node and determine whether the label of control node q is unclassified; if not, skip control node q; if so, determine the neighborhood N(q) of control node q according to the following expression:

[0174] N(q)={o|o∈Q,distance(o,q)≤Eps}

[0175] Where Eps is the neighborhood radius of control node q, and control node o is a control node included in the neighborhood N(q) of control node q.

[0176] Step 3: Determine whether the number of control nodes contained in the neighborhood N(q) exceeds the preset standard number MinPts; if so, take the control node q corresponding to the neighborhood N(q) as the core point, and also take the starting point determined in Step 1 as the core point. Create a cluster for the core point, and add the control node q and the control nodes whose density is reachable to the cluster.

[0177] Step 4: Recursively process all control nodes in the cluster. For each control node o, if control node o is not yet classified, add control node o to the cluster and return to steps 2 to 4 to continue finding the neighborhood N(O) of control node o until there are no unclassified control nodes in the target area.

[0178] Step 5: Generate multiple target control objects based on the control nodes contained in the cluster created for each core point.

[0179] In one feasible implementation plan, see Figure 3 As shown, Figure 3 The flowchart illustrates a method for determining the data perception capability level according to Embodiment 1 of the present invention. Before determining the target signal control algorithm of the target control object from the target signal control algorithm set based on the data perception capability level of the target control object, the method further includes steps S301 to S302:

[0180] S301: Determine the membership degree f(x) of the data perception capability of the target control object using the following membership function:

[0181] f(x)=sigmod(αx1+βx2+μx2);

[0182] Where x1 represents the cross-sectional data perception capability of the target control object, x2 represents the video data perception capability of the target control object, x3 represents the Internet data perception capability of the target control object, α is the weight coefficient of the cross-sectional data perception capability, β is the weight coefficient of the video data perception capability, and μ is the weight coefficient of the Internet data perception capability.

[0183] S302: Determine the data perception capability level of the target control object based on the membership degree of the target control object's data perception capability and the preset data perception capability level classification rules.

[0184] In one feasible implementation plan, see Figure 4 As shown, Figure 4 The flowchart illustrates a method for determining a target signal control algorithm according to Embodiment 1 of the present invention. The step of determining the target signal control algorithm of the target control object from the set of target signal control algorithms for the target control object based on the data sensing capability level of the target control object includes steps S401 to S402:

[0185] S401: Determine the preferred algorithm category for the target control object based on its data perception capability level.

[0186] S402: The signal control algorithm belonging to the preferred algorithm category of the target control object in the target signal control algorithm set of the target control object is determined as the target signal control algorithm of the target control object.

[0187] Specifically, referring to the control category division described in step S105, the control category of the target control object determined based on the data perception capability level of the target control object is determined as the preferred algorithm category.

[0188] In one feasible implementation, the controlled objects include single-point signal control units, trunk line signal control units, and area signal control units; the control objectives include preventing overflow deadlock, ensuring traffic capacity, improving traffic efficiency, and ensuring traffic safety.

[0189] Example 2

[0190] See Figure 5 As shown, Figure 5 A schematic diagram of a traffic signal control device according to Embodiment 2 of the present invention is shown, wherein, as Figure 5 As shown, the traffic signal control device provided in Embodiment 2 of the present invention includes:

[0191] The signal control algorithm library construction module 501 is used to construct a signal control algorithm library for a target area. The signal control algorithm library includes multiple signal control algorithm sets that can control different control objects within the target area to achieve different control objectives. Each signal control algorithm set contains multiple optional signal control algorithms.

[0192] The target control target determination module 502 is used to determine the target control target of the target area based on the traffic flow speed, traffic flow rate and overflow coefficient of the target area, wherein the overflow coefficient is used to describe the overflow degree of the target area;

[0193] The target control object determination module 503 is used to group each control node in the target area according to a preset neighborhood radius to obtain multiple target control objects;

[0194] The target signal control algorithm set determination module 504 is used to determine the target signal control algorithm set of each target control object from the signal control algorithm library based on the target control object and the target control objective.

[0195] The target signal control algorithm determination module 505 is used to determine the target signal control algorithm of the target control object from the target signal control algorithm set of the target control object according to the data perception capability level of the target control object;

[0196] Traffic signal control module 506 is used to perform traffic signal control on the target control object using the target control algorithm of the target control object.

[0197] In one feasible implementation, when the target control target determination module determines the target control target of the target area based on the traffic flow operating speed, traffic flow rate, and overflow coefficient of the target area, it is specifically used for:

[0198] A delay coefficient is determined based on the traffic flow speed in the target area to describe the degree of delay in the target area, wherein the traffic flow speed includes the actual traffic flow speed and the preset free flow speed;

[0199] Based on the traffic flow rate of the target area, a trunk line saturation density coefficient is determined to describe the degree of trunk line congestion in the target area, wherein the traffic flow rate includes the actual weighted flow rate and the preset maximum weighted flow rate;

[0200] The regional saturation density coefficient for describing the congestion level of the target area is determined based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, wherein the magnitude of the regional saturation density coefficient is positively correlated with the congestion level of the target area;

[0201] The control target corresponding to the saturation density coefficient of the region is determined from the pre-configured control target database and used as the target control target.

[0202] In one feasible implementation, when the target control target determination module determines a delay coefficient describing the delay level of the target area based on the traffic flow speed of the target area, it specifically performs the following:

[0203] The delay coefficient ρ1 is determined using the following expression:

[0204]

[0205] Among them, v r v is the actual traffic flow velocity. f The preset free-flow velocity;

[0206] When the target control target determination module determines the arterial saturation density coefficient, which describes the degree of arterial congestion in the target area, based on the traffic flow rate of the target area, it is specifically used for:

[0207] The saturation density coefficient ρ2 of the trunk line is determined using the following expression:

[0208]

[0209] Where, k r k is the actual weighted flow rate. m The preset maximum weighted flow rate;

[0210] The overflow coefficient ranges from {0,1}, where 0 represents no overflow and 1 represents overflow.

[0211] When the target control target determination module determines the area saturation density coefficient describing the congestion level of the target area based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, it is specifically used for:

[0212] Determine whether the overflow coefficient is 1;

[0213] If the overflow coefficient is 1, then the overflow coefficient is determined as the saturation density coefficient of the region;

[0214] If the overflow coefficient is not 1, then determine whether the delay coefficient exceeds the trunk line saturation density coefficient;

[0215] If the delay coefficient exceeds the trunk line saturation density coefficient, then the delay coefficient is determined as the regional saturation density coefficient;

[0216] If the delay coefficient does not exceed the trunk line saturation density coefficient, then the trunk line saturation density coefficient is determined as the regional saturation density coefficient.

[0217] In a feasible implementation, when the target control object determination module is used to group each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects, it is specifically used for:

[0218] Multiple target control objects are obtained through the following steps:

[0219] Step 1: Initialize the label of each control node in the target area to unclassified, and determine the starting point for grouping the control nodes according to the node level of each control node;

[0220] Step 2: Traverse the labels of each control node and determine whether the label of control node q is unclassified; if not, skip control node q; if so, determine the neighborhood N(q) of control node q according to the following expression:

[0221] N(q)={o|o∈Q,distance(o,q)≤Eps}

[0222] Where Eps is the neighborhood radius of control node q, and control node O is a control node included in the neighborhood N(q) of control node q.

[0223] Step 3: Determine whether the number of control nodes contained in the neighborhood N(q) exceeds the preset standard number MinPts; if so, take the control node q corresponding to the neighborhood N(q) as the core point, and also take the starting point determined in Step 1 as the core point. Create a cluster for the core point, and add the control node q and the control nodes whose density is reachable to the cluster.

[0224] Step 4: Recursively process all control nodes in the cluster. For each control node o, if control node o is not yet classified, add control node o to the cluster and return to steps 2 to 4 to continue finding the neighborhood N(O) of control node o until there are no unclassified control nodes in the target area.

[0225] Step 5: Generate multiple target control objects based on the control nodes contained in the cluster created for each core point.

[0226] In one feasible implementation plan, see Figure 6 As shown, Figure 6 A schematic diagram of the structure of a second traffic signal control device provided in Embodiment 2 of the present invention is shown, wherein the device further includes:

[0227] The membership determination module 601 is used to determine the membership degree f(x) of the data perception capability of the target control object using the following membership function before determining the target signal control algorithm of the target control object from the target signal control algorithm set based on the data perception capability level of the target control object:

[0228] f(x)=sigmod(αx1+βx2+μx2);

[0229] Where x1 represents the cross-sectional data perception capability of the target control object, x2 represents the video data perception capability of the target control object, x3 represents the Internet data perception capability of the target control object, α is the weight coefficient of the cross-sectional data perception capability, β is the weight coefficient of the video data perception capability, and μ is the weight coefficient of the Internet data perception capability.

[0230] The data perception capability level determination module 602 is used to determine the data perception capability level of the target control object based on the membership degree of the data perception capability of the target control object and the preset data perception capability level classification rules.

[0231] In one feasible implementation, when the target signal control algorithm is used to determine the target signal control algorithm for the target control object from the set of target signal control algorithms for the target control object based on the data perception capability level of the target control object, it is specifically used for:

[0232] The preferred algorithm category for the target control object is determined based on the data perception capability level of the target control object.

[0233] The signal control algorithm belonging to the preferred algorithm category of the target control object in the target signal control algorithm set is determined as the target signal control algorithm of the target control object.

[0234] In one feasible implementation, the controlled objects include single-point signal control units, trunk line signal control units, and area signal control units; the control objectives include preventing overflow deadlock, ensuring traffic capacity, improving traffic efficiency, and ensuring traffic safety.

[0235] Example 3

[0236] Based on the same application concept, see [link / reference] Figure 7 As shown, Figure 7 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown, wherein, as Figure 7 As shown, the computer device 700 provided in Embodiment 3 of this application includes:

[0237] The computer device 700 includes a processor 701, a memory 702, and a bus 703. The memory 702 stores machine-readable instructions that can be executed by the processor 701. When the computer device 700 is running, the processor 701 communicates with the memory 702 via the bus 703. When the machine-readable instructions are executed by the processor 701, they perform the steps of the traffic signal control method shown in Embodiment 1 above.

[0238] Example 4

[0239] Based on the same concept, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of a traffic signal control method as described in any of the above embodiments.

[0240] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0241] The computer program product for traffic signal control provided in this embodiment of the invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0242] The traffic signal control device provided in this embodiment of the invention can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this embodiment of the invention are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiments can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0243] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0244] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0245] In addition, the functional units in the embodiments provided by the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0246] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0247] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0248] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. All should be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A traffic signal control method characterized by, The method includes: A signal control algorithm library for a target area is constructed, wherein the signal control algorithm library includes multiple signal control algorithm sets capable of controlling different control objects within the target area to achieve different control objectives, and each signal control algorithm set contains multiple selectable signal control algorithms; The target control objective for the target area is determined based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area, wherein the overflow coefficient is used to describe the overflow degree of the target area; Based on a preset neighborhood radius, each control node within the target area is grouped to obtain multiple target control objects; For each target control object, a set of target signal control algorithms for that target control object is determined from the signal control algorithm library based on the target control object and the target control objective. The target signal control algorithm for the target controlled object is determined from the set of target signal control algorithms for the target controlled object based on the data perception capability level of the target controlled object. The target control algorithm of the target control object is used to control traffic signals for the target control object. The step of grouping each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects includes: Multiple target control objects are obtained through the following steps: Step 1: Initialize the label of each control node in the target area to unclassified, and determine the starting point for grouping the control nodes according to the node level of each control node; Step 2: Traverse the label of each control node and determine the control node. Is the label uncategorized? If not, skip the control node. If so, then the control node is determined according to the following expression. neighborhood : in, It is a control node neighborhood radius, control node To include in the control node neighborhood Control nodes within the range; Step 3: Determine the neighborhood Does the number of control nodes included exceed the preset standard number? If so, then the neighboring region corresponding control node As the core point, and also taking the starting point determined in step one as the core point, a cluster is created for the core point, and the control node is... The control nodes, whose density is achievable, are added to the cluster; Step 4: Recursively process all control nodes in the cluster. For each control node... If the control node If it has not yet been categorized, then the control node will be... Join the cluster and return to steps two through four to continue searching for the control node. neighborhood This continues until no unclassified control nodes remain within the target area; Step 5: Generate multiple target control objects based on the control nodes contained in the cluster created for each core point; Before determining the target signal control algorithm for the target controlled object from the set of target signal control algorithms based on the data perception capability level of the target controlled object, the method further includes: The membership degree of the data perception capability of the target control object is determined using the following membership function. : ； in, This indicates the cross-sectional data sensing capability of the target control object. This indicates the video data perception capability of the target control object. This indicates the internet data awareness capability of the target control object. The weighting coefficients for the ability to perceive cross-sectional data. The weighting coefficients represent the perceptual capabilities of video data. Weighting coefficients for internet data perception capabilities; The data perception capability level of the target control object is determined based on the membership degree of the target control object's data perception capability and the preset data perception capability level classification rules.

2. The method according to claim 1, characterized in that, The process of determining the target control objective for the target area based on the traffic flow speed, traffic flow rate, and overflow coefficient of the target area includes: A delay coefficient is determined based on the traffic flow speed in the target area to describe the degree of delay in the target area, wherein the traffic flow speed includes the actual traffic flow speed and the preset free flow speed; Based on the traffic flow rate of the target area, a trunk line saturation density coefficient is determined to describe the degree of trunk line congestion in the target area, wherein the traffic flow rate includes the actual weighted flow rate and the preset maximum weighted flow rate; The regional saturation density coefficient for describing the congestion level of the target area is determined based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient, wherein the magnitude of the regional saturation density coefficient is positively correlated with the congestion level of the target area; The control target corresponding to the saturation density coefficient of the region is determined from the pre-configured control target database and used as the target control target.

3. The method according to claim 2, characterized in that, The step of determining a delay coefficient to describe the degree of delay in the target area based on the traffic flow speed in the target area includes: The delay coefficient is determined using the following expression. : ； in, The actual traffic flow speed, The preset free-flow velocity; The step of determining the arterial saturation density coefficient, which describes the degree of arterial congestion in the target area, based on the traffic flow rate of the target area, includes: The trunk line saturation density coefficient is determined using the following expression. : ； in, The actual weighted flow rate, The preset maximum weighted flow rate; The range of values ​​for the overflow coefficient is: Where 0 represents no overflow and 1 represents overflow; The step of determining the regional saturation density coefficient for describing the congestion level of the target area based on the delay coefficient, the trunk line saturation density coefficient, and the overflow coefficient includes: Determine whether the overflow coefficient is 1; If the overflow coefficient is 1, then the overflow coefficient is determined as the saturation density coefficient of the region; If the overflow coefficient is not 1, then determine whether the delay coefficient exceeds the trunk line saturation density coefficient; If the delay coefficient exceeds the trunk line saturation density coefficient, then the delay coefficient is determined as the regional saturation density coefficient; If the delay coefficient does not exceed the trunk line saturation density coefficient, then the trunk line saturation density coefficient is determined as the regional saturation density coefficient.

4. The method according to claim 1, characterized in that, The step of determining the target signal control algorithm for the target controlled object from the set of target signal control algorithms based on the data perception capability level of the target controlled object includes: The algorithm category of the target control object is determined based on its data perception capability level. The signal control algorithm belonging to the algorithm category of the target control object in the target signal control algorithm set of the target control object is determined as the target signal control algorithm of the target control object.

5. The method according to claim 1, characterized in that, The controlled objects include single-point signal control units, trunk line signal control units, and area signal control units; the control objectives include preventing overflow deadlock, ensuring traffic capacity, improving traffic efficiency, and ensuring traffic safety.

6. A traffic signal control device, characterized in that, The device includes: A signal control algorithm library construction module is used to construct a signal control algorithm library for a target area. The signal control algorithm library includes multiple signal control algorithm sets that can control different control objects within the target area to achieve different control objectives. Each signal control algorithm set contains multiple optional signal control algorithms. The target control target determination module is used to determine the target control target of the target area based on the traffic flow speed, traffic flow rate and overflow coefficient of the target area, wherein the overflow coefficient is used to describe the overflow degree of the target area; The target control object determination module is used to group each control node in the target area according to a preset neighborhood radius to obtain multiple target control objects; The target signal control algorithm set determination module is used to determine the target signal control algorithm set of each target control object from the signal control algorithm library based on the target control object and the target control objective. The target signal control algorithm determination module is used to determine the target signal control algorithm of the target control object from the target signal control algorithm set of the target control object based on the data perception capability level of the target control object; The traffic signal control module is used to perform traffic signal control on the target controlled object using the target control algorithm of the target controlled object. When the target control object determination module is used to group each control node within the target area according to a preset neighborhood radius to obtain multiple target control objects, it is specifically used for: Multiple target control objects are obtained through the following steps: Step 1: Initialize the label of each control node in the target area to unclassified, and determine the starting point for grouping the control nodes according to the node level of each control node; Step 2: Traverse the label of each control node and determine the control node. Is the label uncategorized? If not, skip the control node. If so, then the control node is determined according to the following expression. neighborhood : in, It is a control node neighborhood radius, control node To include in the control node neighborhood Control nodes within the range; Step 3: Determine the neighborhood Does the number of control nodes included exceed the preset standard number? If so, then the neighboring region corresponding control node As the core point, and also taking the starting point determined in step one as the core point, a cluster is created for the core point, and the control node is... The control nodes, whose density is achievable, are added to the cluster; Step 4: Recursively process all control nodes in the cluster. For each control node... If the control node If it has not yet been categorized, then the control node will be... Join the cluster and return to steps two through four to continue searching for the control node. neighborhood This continues until no unclassified control nodes remain within the target area; Step 5: Generate multiple target control objects based on the control nodes contained in the cluster created for each core point; The device further includes a membership determination module, used to determine the membership degree of the data perception capability of the target control object using the following membership function before determining the target signal control algorithm of the target control object from the target signal control algorithm set based on the data perception capability level of the target control object. : ； in, This indicates the cross-sectional data sensing capability of the target control object. This indicates the video data perception capability of the target control object. This indicates the internet data awareness capability of the target control object. The weighting coefficients for the ability to perceive cross-sectional data. The weighting coefficients represent the perceptual capabilities of video data. Weighting coefficients for internet data perception capabilities; The data perception capability level determination module is used to determine the data perception capability level of the target control object based on the membership degree of the target control object's data perception capability and the preset data perception capability level classification rules.

7. A computer device, characterized in that, include: The computer device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the traffic signal control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the traffic signal control method as described in any one of claims 1 to 5.

Images