Intersection traffic flow state identification method and traffic signal control equipment

Abstract

The invention provides an intersection traffic flow state identification method and traffic signal control equipment, and relates to the technical field of intelligent traffic. For each traffic flow steering at the target intersection, the actual saturation of the traffic flow steering in the current signal control period is calculated according to the maximum saturation flow rate of the traffic flow steering and the actual signal control traffic data of the traffic flow steering in the current signal control period; and calculating an actual traffic flow state score of the traffic flow steering in the current signal control period by combining a historical traffic flow state score of the traffic flow steering in a previous signal control period of the current signal control period according to a target traffic flow state scoring rule adapted to the target intersection, and performing traffic flow state identification. Therefore, the influence of the traffic flow volatility in the intersection traffic flow state identification process is deeply considered, and the final traffic flow state identification result is ensured to accurately reflect the overall change trend of the real intersection traffic flow state in the time dimension level.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method for identifying traffic flow status at an intersection and a traffic signal control device. Background Art

[0002] With the continuous improvement of people's living standards and the rapid development of cities, urban transportation systems are also facing increasingly severe tests with the progress of urban modernization. The number of vehicles is increasing year by year, vehicle congestion is getting worse, traffic accidents are frequent, and social resources are wasted. These conditions have seriously affected people's travel efficiency, quality of life, and physical and mental health. Therefore, alleviating traffic congestion in cities has great economic and ecological significance.

[0003] At present, the existing intersection traffic signal control mechanism mainly adjusts the intersection signal timing scheme dynamically according to the real-time changes in the intersection traffic flow to alleviate the intersection traffic congestion phenomenon. However, it is worth noting that due to the different performance of motor vehicles, different driving habits of drivers and other interference factors, the traffic state of the intersection lanes fluctuates significantly between different signal control cycles (for example, the traffic state of the intersection lanes in a certain signal control cycle is identified as unblocked, but if the driver near the intersection stops and distracts during the red light stage in the next signal control cycle, and fails to start to leave the intersection immediately when the green light turns on, it is easy to cause the number of vehicles leaving in the corresponding signal control cycle to decrease, so that the traffic state of the intersection lanes in the signal control cycle is identified as congested). It cannot effectively reflect the overall change trend of the real intersection traffic flow state at the time dimension level, and it is easy to make the signal timing scheme directly determined by the real-time intersection lane traffic state not only fail to improve the traffic efficiency of the intersection, but also cause additional traffic delays for vehicles waiting at the intersection. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a method for identifying traffic flow status at an intersection and a traffic signal control device, which can deeply consider the impact of traffic flow volatility in the process of identifying traffic flow status at an intersection, ensure that the traffic flow status identification results for different vehicle flow turns at any intersection can effectively reflect the overall change trend of the actual traffic flow status at the intersection in the time dimension, improve the accuracy of traffic flow status identification at the intersection, and provide a highly accurate decision-making basis for the signal timing scheme adjustment operation based on the traffic flow status at the intersection.

[0005] In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, the present application provides a method for identifying traffic flow status at an intersection, the method comprising:

[0007] Acquire the maximum saturation flow rate of various traffic flow turns at the target intersection, and the actual signal control traffic data of the various traffic flow turns in the current signal control cycle;

[0008] For each traffic flow turn at the target intersection, according to the maximum saturation flow rate of the traffic flow turn and the actual traffic control data, calculate the actual saturation of the traffic flow turn in the current traffic control cycle;

[0009] According to the target traffic flow state scoring rule adapted to the target intersection, based on the actual saturation of the traffic flow turn and the historical traffic flow state score of the traffic flow turn in the previous signal control cycle of the current signal control cycle, the actual traffic flow state score of the traffic flow turn in the current signal control cycle is calculated;

[0010] The actual traffic flow state score of the traffic flow turn is used to identify the traffic flow state according to the target traffic flow state scoring rule, so as to obtain the overall traffic flow state of the traffic flow turn in the current traffic control cycle.

[0011] In an optional implementation, the step of obtaining the maximum saturation flow rate of various vehicle flow turns at the target intersection includes:

[0012] For each traffic flow turn at the target intersection, a saturation flow rate is calculated according to the lane flow data and green light duration of each traffic flow turn in multiple historical signal control cycles, so as to obtain the historical saturation flow rates corresponding to each traffic flow turn in multiple historical signal control cycles;

[0013] The data distribution statistics of the historical saturation flow rates corresponding to this type of traffic turn in multiple historical signal control cycles are performed, and the 90% quantile saturation flow rate in the corresponding data distribution statistics results is used as the maximum saturation flow rate of this type of traffic turn.

[0014] In an optional implementation manner, the saturation flow rate of the i-th type of vehicle flow turning at the target intersection in the k-th signal control cycle is calculated using the following formula:

[0015]

[0016] in, It is used to represent the saturation flow rate of the i-th type of traffic flow turning in the k-th signal control cycle, It is used to indicate the green light duration of the i-th type of traffic flow turning in the k-th signal control cycle, N i It is used to indicate the total number of lanes where the i-th type of traffic flows turn to the target intersection. Used to represent the traffic flow value of the jth lane in the lane flow data of the kth signal control cycle for the i-th type of traffic flow turning.

[0017] In an optional implementation, the actual signal control traffic data of each traffic flow turn includes the current signal control cycle duration, the actual green light duration and the actual flow value of each lane corresponding to the traffic flow turn, and the traffic saturation of the i-th traffic flow turn at the target intersection in the current signal control cycle is calculated using the following formula:

[0018]

[0019] Among them, p i It is used to indicate the traffic saturation of the i-th traffic flow turn in the current traffic control cycle, S i It is used to represent the maximum saturation flow rate of the i-th type of traffic flow turning, g i It is used to indicate the actual green light duration of the i-th type of traffic flow turning in the current signal control cycle, C i It is used to indicate the duration of the current signal control cycle of the i-th type of traffic flow turning, N i It is used to indicate the total number of lanes where the i-th type of traffic flows turn to the target intersection, q i,j It is used to represent the actual flow value of the jth lane of the i-th type of traffic flow turning in the current signal control cycle, λ i It is used to indicate the green signal ratio of the i-th type of traffic flow turn in the current signal control cycle.

[0020] In an optional implementation, the target traffic flow state scoring rule records the continuous number of the first cycle, and the step of calculating the actual traffic flow state score of the traffic flow turn in the current signal control cycle based on the actual saturation of the traffic flow turn and the historical traffic flow state score of the traffic flow turn in the previous signal control cycle of the current signal control cycle according to the target traffic flow state scoring rule adapted to the target intersection includes:

[0021] For this type of traffic flow steering, a target saturation interval corresponding to the actual saturation is determined in the saturation interval of the slow traffic state, the saturation interval of the smooth traffic state, and the saturation interval of the traffic congestion state;

[0022] According to the target saturation interval, detecting whether the real saturation intervals of the target number of consecutive signal control cycles including the current signal control cycle are consistent, and whether the lane traffic state represented by the target saturation interval is consistent with the historical traffic flow state represented by the historical traffic flow state score, wherein the target number of consecutive cycles is obtained by adding one to the first number of consecutive cycles;

[0023] If it is detected that the actual saturation intervals of a number of consecutive signal control cycles in the target cycle are consistent, and the lane traffic state represented by the target saturation interval is consistent with the historical traffic flow state represented by the historical traffic flow state score, then the historical traffic flow state score is directly used as the actual traffic flow state score of this type of traffic turn in the current signal control cycle; otherwise, a target state score matching the target saturation interval is calculated based on the historical traffic flow state score, and the calculated target state score is used as the actual traffic flow state score of this type of traffic turn in the current signal control cycle.

[0024] In an optional implementation, the target traffic flow state scoring rule records a first score accumulation value directly corresponding to the traffic slow state saturation interval, a second score accumulation value corresponding to the traffic congestion state saturation interval, a first score attenuation value corresponding to the traffic smooth state saturation interval, and a second score attenuation value corresponding to the traffic slow state saturation interval and the congested traffic flow state. Then, the step of calculating the target state score matching the target saturation interval according to the historical traffic flow state score includes:

[0025] When the target saturation interval belongs to the traffic congestion state saturation interval, adding the historical traffic flow state score and the second score accumulation value to obtain the target state score;

[0026] When the target saturation interval belongs to the traffic flow state saturation interval, subtracting the historical traffic flow state score from the first score attenuation value to obtain the target state score;

[0027] In the case where the target saturation interval belongs to the slow-moving traffic state saturation interval, detecting whether the historical traffic flow state represented by the historical traffic flow state score belongs to a congested traffic flow state;

[0028] If it is detected that the historical traffic flow state belongs to a congested traffic flow state, a subtraction operation is performed on the historical traffic flow state score and the second score attenuation value to obtain the target state score; otherwise, an addition operation is performed on the historical traffic flow state score and the first score accumulation value to obtain the target state score.

[0029] In an optional implementation manner, the target traffic flow state scoring rule records a slow-moving traffic flow state score threshold and a congested traffic flow state score threshold, and the step of performing traffic flow state identification according to the target traffic flow state scoring rule based on the actual traffic flow state score of the traffic flow turn to obtain the overall traffic flow state of the traffic flow turn in the current signal control cycle includes:

[0030] Detecting whether the actual traffic flow state score of the vehicle flow turning is greater than or equal to the congested traffic flow state score threshold;

[0031] If it is detected that the actual traffic flow state score of the vehicle flow turn is greater than or equal to the congested traffic flow state score threshold, it is determined that the overall traffic flow state of the vehicle flow turn in the current signal control cycle belongs to the congested traffic flow state, otherwise it is detected whether the actual traffic flow state score of the vehicle flow turn is greater than or equal to the slow-moving traffic flow state score threshold;

[0032] When it is detected that the actual traffic flow state score of the vehicle flow turn is greater than or equal to the slow-moving traffic flow state score threshold, it is determined that the overall traffic flow state of the vehicle flow turn in the current signal control cycle belongs to the slow-moving traffic flow state;

[0033] When it is detected that the actual traffic flow state score of the traffic turn is less than the slow-moving traffic flow state score threshold, it is determined that the overall traffic flow state of the traffic turn in the current traffic control cycle belongs to the smooth traffic flow state.

[0034] In an optional embodiment, the method further comprises:

[0035] Constructing a traffic flow state scoring rule based on multiple preset score distribution constraints to obtain multiple candidate traffic flow state scoring rules;

[0036] Based on at least one week of historical traffic flow data at the target intersection, a signal timing solution library for the target intersection is constructed, wherein the signal timing solution library includes signal timing solutions for the target intersection under different combinations of traffic flow states of vehicle flow turning, and each combination of traffic flow turning is composed of all traffic flow turning states at the target intersection in any one of a slow-moving traffic flow state, a congested traffic flow state, and a smooth traffic flow state;

[0037] The plurality of candidate traffic flow state scoring rules are respectively used as traffic flow state evaluation criteria of the target intersection, and the signal timing solution library is called to perform signal control simulation on the target intersection based on the traffic flow state evaluation criteria to determine the rule adaptability of each of the plurality of candidate traffic flow state scoring rules at the target intersection;

[0038] The candidate traffic flow state scoring rule with the largest corresponding rule adaptability is selected as the target traffic flow state scoring rule adapted to the target intersection.

[0039] In an optional implementation, the step of constructing a signal timing solution library for the target intersection based on at least one week of historical traffic flow data at the target intersection includes:

[0040] For each traffic flow turn at the target intersection, extract the 75% quantile flow value of the off-peak period flow data corresponding to the traffic flow turn in the historical traffic flow data as the overall flow value of the unblocked state of the traffic flow turn, and extract the 50% quantile flow value of the peak period flow data corresponding to the traffic flow turn in the historical traffic flow data as the overall flow value of the congested state of the traffic flow turn;

[0041] Extracting the 50% quantile flow value of the valid flow data corresponding to the traffic flow turning and between the overall flow value of the unblocked state and the overall flow value of the congested state from the historical traffic flow data as the overall flow value of the slow-moving state of the traffic flow turning;

[0042] The overall flow value of the unblocked state, the overall flow value of the slow-moving state, and the overall flow value of the congested state of the traffic flow turn are divided by the total number of lanes at the target intersection for the traffic flow turn, to obtain the reference flow values ​​corresponding to the traffic flow turn in the unblocked traffic flow state, the slow-moving traffic flow state, and the congested traffic flow state, respectively;

[0043] For each traffic flow turning traffic flow state combination, according to the reference flow values ​​of all traffic turns under different traffic flow states, calculate the phase flow values ​​of various traffic phases at the target intersection under the traffic flow turning traffic flow state combination;

[0044] The signal control cycle duration and green light duration are calculated based on the phase flow values ​​of various traffic phases at the target intersection under the combination of traffic flow turning and traffic flow states, and the signal timing plan for the target intersection under the combination of traffic flow turning and traffic flow states is obtained.

[0045] In a second aspect, the present application provides a traffic signal control device, which includes a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the method for identifying the traffic flow state at an intersection as described in any one of the aforementioned embodiments.

[0046] In this case, the beneficial effects of the embodiments of the present application may include the following:

[0047] For each traffic turn at the target intersection, the present application calculates the actual saturation of the traffic turn in the current signal control cycle according to the maximum saturation flow rate of the traffic turn and the actual signal control traffic data of the traffic turn in the current signal control cycle, and combines the historical traffic flow state score of the traffic turn in the previous signal control cycle of the current signal control cycle, and calculates the actual traffic flow state score of the traffic turn in the current signal control cycle according to the target traffic flow state scoring rule adapted to the target intersection, and obtains the overall traffic flow state of the traffic turn in the current signal control cycle, thereby deeply considering the impact of traffic flow volatility in the process of traffic flow state identification at the intersection, ensuring that the final traffic flow state identification results for different traffic turns at any intersection can effectively reflect the overall change trend of the real traffic flow state at the time dimension, so as to improve the accuracy of traffic flow state identification at the intersection, and provide a highly accurate decision-making basis for the signal timing scheme adjustment operation based on the traffic flow state at the intersection.

[0048] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 A schematic diagram of the equipment composition of the traffic signal control device provided in an embodiment of the present application;

[0051] Figure 2 One of the flow charts of the method for identifying the state of traffic flow at an intersection provided in an embodiment of the present application;

[0052] Figure 3 for Figure 2 A schematic flow chart of the sub-steps included in step S210;

[0053] Figure 4 for Figure 2 A schematic flow chart of the sub-steps included in step S230;

[0054] Figure 5 for Figure 2 A schematic flow chart of the sub-steps included in step S240;

[0055] Figure 6A second flow chart of a method for identifying traffic flow status at an intersection provided in an embodiment of the present application;

[0056] Figure 7 for Figure 6 Schematic diagram of the flow chart of the sub-steps included in step S260.

[0057] Icon: 100 - traffic signal control device; 110 - memory; 120 - processor; 130 - communication unit. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0059] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0060] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0061] In the description of the present application, it should be understood that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or are the orientations or positional relationships in which the product of the application is conventionally placed when in use, or are the orientations or positional relationships conventionally understood by those skilled in the art. They are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0062] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0063] In addition, in the description of the present application, it can also be understood that the relational terms such as the term "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also includes other elements that are not clearly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood by specific circumstances.

[0064] The applicant found through painstaking research that the existing solutions for identifying traffic flow status at intersections are mainly based on thresholds determined by artificial experience for status identification, or based on thresholds determined by artificial experience to label traffic flow status, and then use artificial intelligence methods for deep learning in order to use neural network models for status identification. However, it is worth noting that these two implementation methods are essentially learning from artificial experience for status identification, and the corresponding state discrimination accuracy is greatly affected by the personal experience of engineers, which in turn affects the implementation effect of intersection signal control schemes. In other words, existing solutions for identifying traffic flow status at intersections often have low recognition accuracy, making it difficult to provide a highly accurate decision-making basis for adjusting signal timing schemes based on intersection traffic flow status.

[0065] In this case, in order to solve the above problems, the embodiments of the present application provide a method for identifying traffic flow status at an intersection and a traffic signal control device, which can deeply consider the impact of traffic flow volatility in the process of identifying traffic flow status at an intersection, ensure that the traffic flow status identification results for different vehicle flow turns at any intersection can effectively reflect the overall change trend of the actual traffic flow status at the time dimension, improve the accuracy of traffic flow status identification at the intersection, and provide a highly accurate decision-making basis for the signal timing scheme adjustment operation based on the traffic flow status at the intersection.

[0066] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0067] Please refer to Figure 1 , Figure 1 : is a schematic diagram of the equipment composition of the traffic signal control device 100 provided in the embodiment of the present application. In the embodiment of the present application, the traffic signal control device 100 can be respectively connected to the traffic monitoring equipment and the traffic lights deployed at any traffic intersection (for example, a four-lane cross signal intersection) to use the traffic monitoring equipment to monitor the real traffic conditions of the corresponding traffic intersection in different road entrance directions (for example, the north entrance direction, the south entrance direction, the east entrance direction and the west entrance direction included in the four-lane cross signal intersection) in real time, and use the traffic lights to signal the lane release conditions of the traffic intersection in different road entrance directions.

[0068] In an embodiment of the present application, the traffic signal control device 100 can, based on the actual traffic condition data collected in real time by the traffic monitoring device, deeply consider the impact of traffic flow volatility in the process of identifying traffic flow states at intersections, and ensure different traffic flow turns at corresponding traffic intersections (for example, a four-lane cross signal intersection is provided with a left-turn lane, two through lanes and a right-turn lane in the four entrance directions respectively, then the traffic flow turns existing in the four-lane cross signal intersection may include "north entrance left turn flow direction", "north entrance through flow direction", "north entrance right turn flow direction", "south entrance left turn flow direction", "south entrance through flow direction", "south entrance right turn flow direction", "east entrance left turn flow direction", "east entrance through flow direction", "east entrance right turn flow direction", "west entrance left turn flow direction", "west entrance through flow direction" and "west entrance right turn flow direction") The flow state recognition result can effectively reflect the overall change trend of the traffic flow state of the real intersection at the time dimension level, and improve the accuracy of traffic flow state recognition at the intersection, so as to select a specific signal timing scheme adapted to the intersection traffic flow state recognition result of the traffic intersection (composed of the traffic flow state recognition results of all vehicle turns at the traffic intersection) from the signal timing scheme library of the traffic intersection (which includes the signal timing schemes of the corresponding traffic intersection under different traffic flow state combinations of vehicle turns, wherein each traffic flow state combination of vehicle turns is composed of any one of the traffic flow states of the slow-moving traffic flow state, the congested traffic flow state and the unblocked traffic flow state) to control the working state of the traffic signal light, so that the traffic intersection can achieve the expected traffic control effect of improving the traffic operation efficiency of the intersection and giving full play to the traffic operation potential of the intersection as much as possible.

[0069] In the embodiment of the present application, the traffic signal control device 100 may include a memory 110, a processor 120, and a communication unit 130. The memory 110, the processor 120, and the communication unit 130 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, the memory 110, the processor 120, and the communication unit 130 may be electrically connected to each other via one or more communication buses or signal lines.

[0070] In the embodiment of the present application, the memory 110 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), etc. The memory 110 is used to store a computer program, and the processor 120 may execute the computer program accordingly after receiving an execution instruction.

[0071] In addition, in the present embodiment, the memory 110 can also be used to store effective traffic flow state scoring rules adapted for different traffic intersections, wherein the effective traffic flow state scoring rules are used to evaluate the traffic flow state scores of all vehicle turns at the corresponding traffic intersection in any signal control cycle from the time dimension level by considering the volatility of traffic flow, so as to use the evaluated traffic flow state scores to characterize the overall change trend of the real traffic flow state (i.e., slow-moving traffic flow state, congested traffic flow state or unobstructed traffic flow state) in the time dimension level; the effective traffic flow state scoring rules adapted for different traffic intersections all satisfy multiple preset score distribution constraints, wherein each preset score distribution constraint is used to describe the numerical distribution constraint relationship between the traffic flow state score of any signal control cycle, different traffic flow state score thresholds (including slow-moving traffic flow state score thresholds and congested traffic flow state score thresholds) and the saturation distribution conditions of multiple consecutive signal control cycles including the signal control cycle.

[0072] In the embodiment of the present application, the processor 120 may be an integrated circuit chip with signal processing capability. The processor 120 may be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc., which may implement or execute the disclosed methods, steps, and logic block diagrams in the embodiments of the present application.

[0073] In the embodiment of the present application, the communication unit 130 is used to establish a communication connection between the traffic signal control device 100 and other electronic devices through a network, and to send and receive data through the network, wherein the network includes a wired communication network and a wireless communication network.

[0074] In an embodiment of the present application, the traffic signal control device 100 may pre-store a specific computer program related to the intersection traffic flow state recognition function in the memory 110, and by driving the processor 120 to execute the specific computer program stored in the memory 110, deeply consider the impact of traffic flow volatility in the process of identifying the traffic flow state at the intersection, ensure that the traffic flow state recognition results for different vehicle flow turns at any intersection can effectively reflect the overall change trend of the actual intersection traffic flow state at the time dimension level, improve the accuracy of intersection traffic flow state recognition, and provide a highly accurate decision-making basis for the signal timing scheme adjustment operation based on the intersection traffic flow state.

[0075] Understandably, Figure 1 The block diagram shown is only a schematic diagram of a composition of the traffic signal control device 100. The traffic signal control device 100 may also include Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0076] In the present application, in order to ensure that the traffic signal control device 100 can deeply consider the influence of traffic flow volatility in the process of identifying the traffic flow state at the intersection, so that the final traffic flow state identification result can effectively reflect the overall change trend of the real traffic flow state at the time dimension, the embodiment of the present application achieves the above-mentioned purpose by providing a method for identifying the traffic flow state at the intersection. The method for identifying the traffic flow state at the intersection provided by the present application is described in detail below.

[0077] Please refer to Figure 2 , Figure 2 This is one of the flow charts of the method for identifying the state of traffic flow at an intersection provided in the embodiment of the present application. In the embodiment of the present application, the method for identifying the state of traffic flow at an intersection may include steps S210 to S240.

[0078] Step S210, obtaining the maximum saturation flow rate of various traffic turns at the target intersection, and the actual signal control traffic data of various traffic turns in the current signal control cycle.

[0079] In an embodiment of the present application, the target intersection is any traffic intersection monitored in real time by the traffic signal control device 100 through a traffic monitoring device; the maximum saturated flow rate of various traffic turns at the target intersection is used to describe the maximum saturated flow rate generally maintained in the historical traffic records of the corresponding traffic turn before the current signal control cycle; the actual signal control traffic data of various traffic turns at the target intersection in the current signal control cycle include the current signal control cycle duration of the corresponding traffic turn, the actual green light duration of the corresponding traffic turn in the current signal control cycle, and the actual flow value of each lane involved in the corresponding traffic turn at the target intersection in the current signal control cycle.

[0080] Optionally, see Figure 3 , Figure 3 yes Figure 2 Schematic diagram of the flow chart of the sub-steps included in step S210. In an embodiment of the present application, the step of "obtaining the maximum saturated flow rate of various vehicle flow turns at the target intersection" in step S210 may include sub-steps S211 to S212 to effectively extract the maximum saturated flow rate of different vehicle flow turns from the historical traffic records of the target intersection.

[0081] Sub-step S211, for each traffic turn at the target intersection, the saturation flow rate is calculated according to the lane flow data and green light duration of each traffic turn in multiple historical signal control cycles, and the historical saturation flow rates corresponding to each traffic turn in multiple historical signal control cycles are obtained.

[0082] In this embodiment, the multiple historical signal control cycles may be all historical signal control cycles on the same day last week of the current signal control cycle, or may be historical signal control cycles directly adjacent to and continuous with the current signal control cycle; the lane flow data of any type of traffic turn in a certain signal control cycle includes the traffic flow values ​​of all lanes involved in the traffic turn at the target intersection within the signal control cycle.

[0083] In this process, the saturation flow rate of the i-th type of traffic flow turning at the target intersection in the k-th signal control cycle is calculated using the following formula:

[0084]

[0085] in, It is used to represent the saturation flow rate of the i-th type of traffic flow turning in the k-th signal control cycle, It is used to indicate the green light duration of the i-th type of traffic flow turning in the k-th signal control cycle, N i It is used to indicate the total number of lanes where the i-th type of traffic flows turn to the target intersection. Used to represent the traffic flow value of the jth lane in the lane flow data of the kth signal control cycle for the i-th type of traffic flow turning.

[0086] Sub-step S212, performing data distribution statistics on the historical saturation flow rates corresponding to the type of traffic turn in multiple historical signal control cycles, and taking the 90% quantile saturation flow rate in the corresponding data distribution statistics results as the maximum saturation flow rate of the type of traffic turn.

[0087] Therefore, the present application can effectively extract the maximum saturation flow rate of different vehicle flow turns from the historical traffic records of the target intersection by executing the above sub-steps S211 to S212.

[0088] Step S220, for each traffic turn at the target intersection, the actual saturation of the traffic turn in the current traffic control cycle is calculated according to the maximum saturation flow rate of the traffic turn and the actual traffic control data.

[0089] In this embodiment, after obtaining the maximum saturation flow rate of any type of traffic flow turning at the target intersection and the actual signal control traffic data of the traffic flow turning in the current signal control cycle, the traffic signal control device 100 will calculate the actual saturation of the traffic flow turning in the current signal control cycle according to the traffic saturation calculation formula. The traffic saturation of the i-th type of traffic flow turning at the target intersection in the current signal control cycle is calculated using the following formula:

[0090]

[0091] Among them, p iIt is used to indicate the traffic saturation of the i-th traffic flow turn in the current traffic control cycle, S i It is used to represent the maximum saturation flow rate of the i-th type of traffic flow turning, g i It is used to indicate the actual green light duration of the i-th type of traffic flow turning in the current signal control cycle, C i It is used to indicate the duration of the current signal control cycle of the i-th type of traffic flow turning, N i It is used to indicate the total number of lanes where the i-th type of traffic flows turn to the target intersection, q i,j It is used to represent the actual flow value of the jth lane of the i-th type of traffic flow turning in the current signal control cycle, λ i It is used to indicate the green signal ratio of the i-th type of traffic flow turn in the current signal control cycle.

[0092] Step S230, according to the target traffic flow state scoring rule adapted to the target intersection, based on the actual saturation of this type of traffic flow turn and the historical traffic flow state score of this type of traffic flow turn in the previous signal control cycle of the current signal control cycle, calculate the actual traffic flow state score of this type of traffic flow turn in the current signal control cycle.

[0093] In this embodiment, the traffic signal control device 100 can extract the target traffic flow state scoring rule adapted to the target intersection from the pre-stored effective traffic flow state scoring rules adapted to different traffic intersections, and then for each traffic turn at the target intersection, call the target traffic flow state scoring rule to evaluate the traffic flow state score based on the actual saturation of the traffic turn in the current signal control cycle, the historical traffic flow state score of the traffic turn in the previous signal control cycle of the current signal control cycle, and the actual saturation of the traffic turn in multiple historical signal control cycles adjacent to and continuous with the current signal control cycle, so as to consider the impact of traffic flow volatility on the evaluation of the overall change trend of traffic flow from the time dimension level, and ensure that the actual traffic flow state score finally evaluated for the traffic turn can effectively reflect the actual traffic flow conditions.

[0094] In this process, all preset score distribution constraints satisfied by the target traffic flow state scoring rule include at least "if the lane traffic states (traffic states directly identified by saturation) of each of the consecutive m+1 signal control cycles are consistent, then the real traffic flow state score of the last signal control cycle is consistent with the real traffic flow state score of the penultimate signal control cycle (i.e., the previous signal control cycle of the last signal control cycle), and the historical traffic flow state of the penultimate signal control cycle is consistent with the lane traffic state", then the target traffic flow state scoring rule will record the first cycle continuous number (expressed by m), and the sub-steps included in step S230 can be as follows: Figure 4Wherein, the step S230 may include sub-steps S231 to S234, so as to consider the impact of traffic flow volatility on the evaluation of the overall change trend of traffic flow from the time dimension level, and ensure that the actual traffic flow state score finally evaluated for any type of traffic flow turn can effectively reflect the actual traffic flow condition at the target intersection.

[0095] Sub-step S231, for this type of traffic flow turning, determines the target saturation interval corresponding to the actual saturation in the saturation interval of the slow traffic state, the saturation interval of the smooth traffic state and the saturation interval of the congested traffic state.

[0096] In this embodiment, the target traffic flow state scoring rule records the specific interval contents of the traffic slowing state saturation interval (i.e., the saturation value range that needs to be satisfied when the traffic state of the corresponding lane is determined to be a traffic slowing state for any traffic flow turn), the traffic smooth state saturation interval (i.e., the saturation value range that needs to be satisfied when the traffic state of the corresponding lane is determined to be a traffic smooth state for any traffic flow turn) and the traffic congestion state saturation interval (i.e., the saturation value range that needs to be satisfied when the traffic state of the corresponding lane is determined to be a traffic congestion state for any traffic flow turn). (For example, the traffic smooth state saturation interval, the traffic slowing state saturation interval and the traffic congestion state saturation interval are expressed as (0, 0.8), [0.8, 0.9) and [0.9, 1] respectively).

[0097] Therefore, for any type of traffic turn, the traffic signal control device 100 can determine the target saturation interval corresponding to the actual saturation by matching the actual saturation of the traffic turn in the current signal control cycle with the saturation interval of the slow traffic state, the saturation interval of the smooth traffic state and the saturation interval of the traffic congestion state. At this time, the target saturation interval is the real saturation interval of the traffic turn in the current signal control cycle, and the lane traffic state represented by the target saturation interval (i.e., smooth traffic state, slow traffic state or traffic congestion state) is the actual lane traffic state of the traffic turn in the current signal control cycle.

[0098] Sub-step S232, based on the target saturation interval, detects whether the actual saturation intervals of the target number of consecutive signal control cycles including the current signal control cycle are consistent, and whether the lane traffic state represented by the target saturation interval is consistent with the historical traffic flow state represented by the historical traffic flow state score.

[0099] In this embodiment, the target continuous number of cycles is obtained by adding one to the first continuous number of cycles, that is, the target continuous number of cycles is represented by m+1; when there are a target continuous number of consecutive signal control cycles (consisting of the current signal control cycle and m historical signal control cycles adjacent to and continuous with the current signal control cycle), whether their respective real saturation intervals are consistent, it indicates that the lane traffic states of these m+1 signal control cycles are consistent.

[0100] The target traffic flow state scoring rule also records a slow-moving traffic flow state score threshold (which can be represented by e) and a congested traffic flow state score threshold (which can be represented by f), wherein if the traffic flow state score of a certain traffic flow turn is less than the slow-moving traffic flow state score threshold, then the traffic flow state score will correspond to a smooth traffic flow state; and if the traffic flow state score of this type of traffic flow turn is greater than or equal to the slow-moving traffic flow state score threshold but less than the congested traffic flow state score threshold, then the traffic flow state score will correspond to a slow-moving traffic flow state; in addition, if the traffic flow state score of this type of traffic flow turn is greater than or equal to the congested traffic flow state score threshold, then the traffic flow state score will correspond to a congested traffic flow state. Thus, the traffic signal control device 100 can identify the historical traffic flow state represented by the historical traffic flow state score of any one type of traffic flow turn in the previous signal control cycle of the current signal control cycle based on the slow traffic flow state score threshold and the congested traffic flow state score threshold, and then match the lane traffic state of the traffic flow turn in the current signal control cycle with the historical traffic flow state represented by the historical traffic flow state score to determine whether the lane traffic state and the historical traffic flow state are consistent. Wherein, if the lane traffic state belongs to the unimpeded traffic state and the corresponding historical traffic flow state belongs to the unimpeded traffic flow state, the lane traffic state and the historical traffic flow state are consistent; if the lane traffic state belongs to the slow traffic state and the corresponding historical traffic flow state belongs to the slow traffic flow state, the lane traffic state and the historical traffic flow state are consistent; if the lane traffic state belongs to the traffic congestion state and the corresponding historical traffic flow state belongs to the congested traffic flow state, the lane traffic state and the historical traffic flow state are consistent.

[0101] In this case, if it is detected that the real saturation intervals of the target number of consecutive signal control cycles are consistent, and the lane traffic state represented by the target saturation interval is consistent with the historical traffic flow state represented by the historical traffic flow state score, it indicates that the corresponding traffic turn substantially meets the constraint condition in the current signal control cycle: "If the lane traffic state (the traffic state directly identified by saturation) of m+1 consecutive signal control cycles is consistent, then the real traffic flow state score of the last signal control cycle is consistent with the real traffic flow state score of the penultimate signal control cycle (i.e., the previous signal control cycle of the last signal control cycle), and the historical traffic flow state of the penultimate signal control cycle is consistent with the lane traffic state", and the traffic signal control device 100 will execute sub-step S233 accordingly. Otherwise, the traffic signal control device 100 will execute sub-step S234 accordingly.

[0102] Sub-step S233, directly using the historical traffic flow state score as the actual traffic flow state score of the traffic turn in the current traffic control cycle.

[0103] Sub-step S234, calculating a target state score matching the target saturation interval according to the historical traffic flow state score, and using the calculated target state score as the actual traffic flow state score of the traffic turn in the current traffic control cycle.

[0104] In this embodiment, when it is determined that a certain traffic flow turn does not meet the constraint condition "if the lane traffic states of each of the consecutive m+1 signal control cycles remain consistent, the real traffic flow state score of the last signal control cycle is consistent with the real traffic flow state score of the penultimate signal control cycle, wherein the historical traffic flow state of the penultimate signal control cycle is consistent with the lane traffic state", the traffic signal control device 100 will record the first score accumulation value directly corresponding to the traffic slowing state saturation interval based on the target traffic flow state scoring rule (i.e., the positive score that needs to be superimposed on the historical traffic flow state score of the previous signal control cycle when the lane traffic state of the corresponding traffic flow turn in a certain signal control cycle is determined to be a traffic slowing state, which can be represented by a), the second score accumulation value corresponding to the traffic congestion state saturation interval (i.e., the positive score that needs to be superimposed on the historical traffic flow state score of the previous signal control cycle when the lane traffic state of the corresponding traffic flow turn in a certain signal control cycle is determined to be a traffic congestion state) a positive score superimposed on the historical traffic flow state score, which can be represented by b), a first score attenuation value corresponding to the saturation interval of the smooth traffic state (i.e., the positive score that needs to be subtracted from the historical traffic flow state score of the previous signal control cycle when the lane traffic state of the corresponding traffic turn in a certain signal control cycle is determined to be a smooth traffic state, which can be represented by c), and a second score attenuation value corresponding to the saturation interval of the slow traffic state and the congested traffic flow state (i.e., the positive score that needs to be subtracted from the historical traffic flow state score of the previous signal control cycle when the lane traffic state of the corresponding traffic turn in a certain signal control cycle is determined to be a slow traffic state and the historical traffic flow state of the previous signal control cycle belongs to a congested traffic flow state, which can be represented by d), combined with the target saturation interval of the corresponding traffic turn in the current signal control cycle and the historical traffic flow state score of the previous signal control cycle, the target state score of this type of traffic turn in the current signal control cycle that matches the target saturation interval is calculated as the true actual traffic flow state score.

[0105] In this process, the step of "calculating a target state score matching a target saturation interval according to a historical traffic flow state score" in the sub-step S234 may include:

[0106] When the target saturation interval belongs to the traffic congestion state saturation interval, adding the historical traffic flow state score and the second score accumulation value to obtain the target state score;

[0107] When the target saturation interval belongs to the traffic flow state saturation interval, subtracting the historical traffic flow state score from the first score attenuation value to obtain the target state score;

[0108] In the case where the target saturation interval belongs to the slow-moving traffic state saturation interval, detecting whether the historical traffic flow state represented by the historical traffic flow state score belongs to a congested traffic flow state;

[0109] If it is detected that the historical traffic flow state belongs to a congested traffic flow state, a subtraction operation is performed on the historical traffic flow state score and the second score attenuation value to obtain the target state score; otherwise, an addition operation is performed on the historical traffic flow state score and the first score accumulation value to obtain the target state score.

[0110] Therefore, the present application can consider the impact of traffic flow volatility on the evaluation of the overall change trend of traffic flow from the time dimension level by executing the above sub-steps S231 to S234, to ensure that the actual traffic flow state score finally evaluated for any type of traffic flow turn can effectively reflect its actual traffic flow condition at the target intersection.

[0111] Step S240 , performing traffic flow state identification on the actual traffic flow state score of the traffic flow turn according to the target traffic flow state scoring rule, and obtaining the overall traffic flow state of the traffic flow turn in the current signal control cycle.

[0112] In this embodiment, the target traffic flow state scoring rule records a slow-moving traffic flow state score threshold and a congested traffic flow state score threshold, wherein the congested traffic flow state score threshold is greater than the slow-moving traffic flow state score threshold. After determining the actual traffic flow state score of any one type of traffic flow turn at the target intersection in the current signal control cycle, the traffic signal control device 100 can compare the actual traffic flow state score with the slow-moving traffic flow state score threshold and the congested traffic flow state score threshold to accurately identify the overall traffic flow state of the corresponding traffic flow turn in the current signal control cycle. At this time, the sub-steps included in step S240 can be as follows: Figure 5 The step S240 may include sub-steps S241 to S245 to accurately identify the overall traffic flow state of any vehicle flow turn in the current signal control cycle.

[0113] Sub-step S241 , detecting whether the actual traffic flow state score of the vehicle flow turn is greater than or equal to a congested traffic flow state score threshold.

[0114] In this embodiment, if it is detected that the actual traffic flow state score of a certain traffic flow turn in the current signal control cycle is greater than or equal to the congested traffic flow state score threshold, the traffic signal control device 100 will execute sub-step S242 corresponding to the traffic flow turn; otherwise, the traffic signal control device 100 will execute sub-step S243 corresponding to the traffic flow turn.

[0115] Sub-step S242, determining whether the overall traffic flow state of the vehicle flow turn in the current traffic control cycle belongs to a congested traffic flow state.

[0116] Sub-step S243, detecting whether the actual traffic flow state score of the vehicle flow turn is greater than or equal to a slow-moving traffic flow state score threshold.

[0117] In this embodiment, when it is detected that the actual traffic flow state score of a certain traffic flow turn in the current signal control cycle is less than the congested traffic flow state score threshold, the traffic signal control device 100 can further detect whether the actual traffic flow state score of the traffic flow turn is greater than or equal to the slow-moving traffic flow state score threshold, so as to determine whether the overall traffic flow state represented by the actual traffic flow state score belongs to the slow-moving traffic flow state or the smooth traffic flow state. If the actual traffic flow state score of a certain traffic flow turn is greater than or equal to the slow-moving traffic flow state score threshold, the traffic signal control device 100 will execute sub-step S244 for the traffic flow turn, otherwise the traffic signal control device 100 will execute sub-step S245 for the traffic flow turn.

[0118] Sub-step S244, determining whether the overall traffic flow state of the vehicle flow turn in the current signal control cycle belongs to a slow-moving traffic flow state.

[0119] Sub-step S245, determining whether the overall traffic flow state of the vehicle flow turn in the current signal control cycle belongs to a smooth traffic flow state.

[0120] Therefore, the present application can accurately identify the overall traffic flow state of any type of vehicle flow turn in the current signal control cycle by executing the above sub-steps S241 to S245.

[0121] The present application can, by executing the above steps S210 to S240, deeply consider the impact of traffic flow volatility in the process of identifying traffic flow states at intersections, and ensure that the final traffic flow state identification results for different vehicle flow turns at any intersection can effectively reflect the overall change trend of the actual traffic flow state at the time dimension, so as to improve the accuracy of intersection traffic flow state identification, and provide a highly accurate decision-making basis for the signal timing scheme adjustment operation based on the intersection traffic flow state.

[0122] Optionally, see Figure 6 , Figure 6 This is the second flow chart of the method for identifying the state of traffic flow at an intersection provided in the embodiment of the present application. Figure 2 Compared with the intersection traffic flow state recognition method shown in Figure 6The intersection traffic flow state identification method shown may also include steps S250 to S280, to adaptively simulate and select a target traffic flow state scoring rule that is suitable for the target intersection based on the historical traffic data (including historical traffic flow data) of the target intersection, so as to improve the accuracy of identifying the intersection traffic flow state of the target intersection, and provide a highly accurate decision-making basis for the signal timing scheme adjustment operation.

[0123] Step S250 , constructing a traffic flow state scoring rule based on a plurality of preset score distribution constraints to obtain a plurality of candidate traffic flow state scoring rules.

[0124] In this embodiment, the multiple candidate traffic flow state scoring rules all satisfy the multiple preset score distribution constraints, where the multiple preset score distribution constraints may include but are not limited to:

[0125] (1) “If the real saturation intervals of each of m consecutive signal control cycles belong to the slow-moving traffic state saturation interval, then the real traffic flow state score of the last signal control cycle among these m signal control cycles will be no less than the slow-moving traffic flow state score threshold but less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow-moving traffic flow state”. In this case, the constraint condition can be expressed as “e≤m×a <f”;

[0126] (2) “If the real saturation intervals of each of n consecutive signal control cycles belong to the slow-moving traffic state saturation interval, then the real traffic flow state score of the last signal control cycle among the n signal control cycles will be less than the slow-moving traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow-moving traffic flow state, where n is used to represent the second cycle continuous number, and the second cycle continuous number is less than the first cycle continuous number”. In this case, the constraint condition can be expressed as “n×a <e”;

[0127] (3) "If the real saturation intervals of each of m consecutive signal control cycles belong to the traffic congestion state saturation interval, then the real traffic flow state score of the last signal control cycle among these m signal control cycles will not be less than the congestion traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the congestion traffic flow state." In this case, the constraint condition can be expressed as "m×b≥f";

[0128] (4) “If the real saturation intervals of each of the n consecutive signal control cycles belong to the traffic congestion state saturation interval, then the real traffic flow state score of the last signal control cycle among the n signal control cycles will be no less than the slow-moving traffic flow state score threshold but less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow-moving traffic flow state”. In this case, the constraint condition can be expressed as “e≤n×b <f”;

[0129] (5) "If the real saturation intervals of n consecutive signal control cycles all belong to the slow traffic state saturation interval, and then the real saturation intervals of mn consecutive signal control cycles all belong to the traffic congestion state saturation interval, then the real traffic flow state score of the last signal control cycle among these m signal control cycles will be no less than the slow traffic flow state score threshold but less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow traffic flow state." In this case, the constraint condition can be expressed as "e≤n×a+(mn)×b <f”;

[0130] (6) "If the real saturation intervals of mn consecutive signal control cycles all belong to the traffic slowing state saturation interval, and then the real saturation intervals of n consecutive signal control cycles all belong to the traffic congestion state saturation interval, then the real traffic flow state score of the last signal control cycle among these m signal control cycles will not be less than the congestion traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the congestion traffic flow state." In this case, the constraint condition can be expressed as "(mn)×a+n×b≥f";

[0131] (7) “If the overall traffic flow state of a certain signal control cycle belongs to the congested traffic flow state, the real saturation intervals of the n consecutive signal control cycles belong to the saturation interval of the smooth traffic state, then the real traffic flow state score of the last signal control cycle among these n signal control cycles will be no less than the slow-moving traffic flow state score threshold but less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow-moving traffic flow state”. In this case, the constraint condition can be expressed as “e≤m×bn×c <f”;

[0132] (8) "If the overall traffic flow state of a certain signal control cycle belongs to the congested traffic flow state, and the real saturation intervals of the consecutive n-1 signal control cycles belong to the saturation interval of the smooth traffic state, then the real traffic flow state score of the last signal control cycle among these n-1 signal control cycles will not be less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the congested traffic flow state." In this case, the constraint condition can be expressed as "m×b-(n-1)×c≥f";

[0133] (9) “If the overall traffic flow state of a signal control cycle belongs to the slow-moving traffic flow state, and the real saturation intervals of the n-1 consecutive signal control cycles belong to the smooth traffic state saturation interval, then the real traffic flow state score of the last signal control cycle in these n-1 signal control cycles will be no less than the slow-moving traffic flow state score threshold but less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow-moving traffic flow state”. In this case, the constraint condition can be expressed as “e≤m×a-(n-1)×c <f”;

[0134] (10) “If the overall traffic flow state of a signal control cycle belongs to the slow-moving traffic flow state, and the real saturation intervals of the n consecutive signal control cycles belong to the smooth traffic state saturation interval, then the real traffic flow state score of the last signal control cycle among these n signal control cycles will be less than the slow-moving traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the smooth traffic flow state”. In this case, the constraint condition can be expressed as “m×an×c <e”;

[0135] (11) "If the overall traffic flow state of a certain signal control cycle belongs to the congested traffic flow state, and the real saturation intervals of the consecutive n-1 signal control cycles belong to the slow-moving traffic state saturation interval, then the real traffic flow state score of the last signal control cycle among these n-1 signal control cycles will not be less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the congested traffic flow state." In this case, the constraint condition can be expressed as "m×b-(n-1)×d≥f";

[0136] (12) “If the overall traffic flow state of a certain signal control cycle belongs to the congested traffic flow state, and the real saturation intervals of the n consecutive signal control cycles belong to the saturation interval of the smooth traffic state, then the real traffic flow state score of the last signal control cycle among these n signal control cycles will be no less than the slow-moving traffic flow state score threshold but less than the congested traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the slow-moving traffic flow state”. In this case, the constraint condition can be expressed as “e≤m×bn×d <f”;

[0137] (13) “If the overall traffic flow state of a certain signal control cycle belongs to the congested traffic flow state, and the real saturation intervals of the m+1 consecutive signal control cycles belong to the smooth traffic state saturation interval, then the real traffic flow state score of the last signal control cycle in these m+1 signal control cycles will be less than the slow traffic flow state score threshold, and the overall traffic flow state of the last signal control cycle belongs to the smooth traffic flow state.” In this case, the constraint condition can be expressed as “m×b-(m+1)×d <e”;

[0138] (14) “If the lane traffic status of each of the m+1 consecutive signal control cycles remains consistent, then the actual traffic flow status score of the last signal control cycle among the m+1 signal control cycles is consistent with the actual traffic flow status score of the penultimate signal control cycle (i.e., the previous signal control cycle of the last signal control cycle), and the historical traffic flow status of the penultimate signal control cycle is consistent with the lane traffic status.”

[0139] Therefore, the traffic signal control device 100 can, given a plurality of cycle continuous number combinations (wherein each cycle continuous number combination uses two numbers to represent the first cycle continuous number and the second cycle continuous number respectively, for example, the cycle continuous number combination (m, n) can be but not limited to: (3, 2), (4, 3), (6, 4) and (7, 4)), jointly solve the above-mentioned plurality of preset score distribution constraints for each cycle continuous number combination to obtain the first score accumulation value, the second score accumulation value, the first score attenuation value, the second score attenuation value, the slow-moving traffic flow state score threshold and the congested traffic flow state score threshold that match the cycle continuous number combination, so as to integrate the cycle continuous number combination with the matching first score accumulation value, the second score accumulation value, the first score attenuation value, the second score attenuation value, the slow-moving traffic flow state score threshold and the congested traffic flow state score threshold to obtain a candidate traffic flow state scoring rule.

[0140] Step S260: construct a signal timing solution library for the target intersection based on at least one week of historical traffic flow data at the target intersection.

[0141] In this embodiment, the signal timing scheme library includes signal timing schemes for the target intersection under different combinations of vehicle turn traffic flow states, and each combination of vehicle turn traffic flow states is composed of all vehicle turns at the target intersection in any one of the traffic flow states of slow traffic flow state, congested traffic flow state and smooth traffic flow state. For example, taking a four-lane cross signal intersection as an example, it may include a vehicle turn traffic flow state combination "the left turn flow direction of the north entrance, the straight flow direction of the north entrance, the left turn flow direction of the south entrance and the straight flow direction of the south entrance are all in a smooth traffic flow state, while the right turn flow direction of the north entrance and the right turn flow direction of the south entrance are both in a slow traffic flow state; the left turn flow direction of the east entrance, the straight flow direction of the east entrance, the left turn flow direction of the west entrance and the straight flow direction of the west entrance are all in a congested traffic flow state, while the right turn flow direction of the east entrance and the The right-turn flow direction is in a state of unimpeded traffic flow," "The left-turn flow direction at the north entrance, the straight flow direction at the north entrance, and the straight flow direction at the south entrance are all in a state of unimpeded traffic flow, while the right-turn flow direction at the north entrance, the left-turn flow direction at the south entrance, and the right-turn flow direction at the south entrance are all in a state of slow traffic flow; the left-turn flow direction at the east entrance and the straight flow direction at the west entrance are all in a state of congested traffic flow, while the right-turn flow direction at the east entrance, the straight flow direction at the east entrance, the left-turn flow direction at the west entrance, and the right-turn flow direction at the west entrance are all in a state of unimpeded traffic flow."

[0142] Optionally, see Figure 7 , Figure 7 yes Figure 6 In the embodiment of the present application, the step S260 may include sub-steps S261 to S265 to construct a signal timing solution library adapted to the actual traffic conditions of the target intersection based on the historical traffic data (including historical traffic flow data) of the target intersection.

[0143] In sub-step S261, for each traffic turn at the target intersection, the 75% quantile flow value of the off-peak period flow data corresponding to the traffic turn in the historical traffic flow data is extracted as the overall flow value of the unobstructed state of the traffic turn, and the 50% quantile flow value of the peak period flow data corresponding to the traffic turn in the historical traffic flow data is extracted as the overall flow value of the congested state of the traffic turn.

[0144] Sub-step S262, extracting the 50% quantile flow value of the effective flow data corresponding to the traffic turn and between the overall flow value of the unblocked state and the overall flow value of the congested state in the historical traffic flow data as the overall flow value of the slow-moving state of the traffic turn.

[0145] Sub-step S263, divides the overall flow value of the unblocked state, the overall flow value of the slow-moving state and the overall flow value of the congested state of the traffic flow turning by the total number of lanes at the target intersection where the traffic flow turns, to obtain the reference flow values ​​corresponding to the traffic flow turning in the unblocked traffic flow state, the slow-moving traffic flow state and the congested traffic flow state, respectively.

[0146] Sub-step S264, for each traffic turn traffic flow state combination, calculate the phase flow values ​​of various traffic phases at the target intersection under the traffic turn traffic flow state combination according to the reference flow values ​​of all traffic turns under different traffic flow states.

[0147] In this embodiment, for any traffic flow turning traffic flow state combination, the traffic flow state content of the specific traffic flow turning components involved in various traffic phases at the target intersection at the traffic flow turning traffic flow state combination can be determined respectively, and then for each traffic phase, the maximum flow value of all the traffic turns involved in the reference flow values ​​adapted at the traffic flow turning traffic flow state combination is used as the phase flow value of this traffic phase under the corresponding traffic flow turning traffic flow state combination.

[0148] Sub-step S265, calculates the signal control cycle duration and the green light duration based on the phase flow values ​​of various traffic phases at the target intersection under the combination of traffic flow turning and traffic flow states, and obtains the signal timing plan for the target intersection under the combination of traffic flow turning and traffic flow states.

[0149] In this embodiment, the signal timing scheme of the target intersection under any combination of traffic flow turning and traffic flow states includes the signal control cycle duration shared by all traffic phases in the target intersection, and the actual green light duration of all traffic phases in the same signal control cycle. The calculation formula for the duration of a single signal control cycle at the target intersection can be expressed as follows:

[0150]

[0151] Among them, C is used to represent the duration of a single signal control cycle of the target intersection, L is used to represent the total loss duration of the target intersection within a single signal control cycle, and is used to represent the sum of the flow ratios of all traffic phases at the target intersection, wherein the flow ratio of a single traffic phase is the ratio between the phase flow value of that traffic phase and the saturation flow value.

[0152] In addition, the actual green light duration of the i-th traffic phase at the target intersection in a single signal control cycle can be expressed by the following formula:

[0153]

[0154] Wherein, C is used to represent the duration of a single signal control cycle of the target intersection, g i ′ is used to represent the actual green light duration of the i-th traffic phase at the target intersection in a single signal control cycle, y i Used to represent the flow ratio of the i-th traffic phase at the target intersection.

[0155] Therefore, the present application can construct a signal timing solution library adapted to the actual traffic conditions of the target intersection according to the historical traffic data of the target intersection (including historical traffic flow data) by executing the above sub-steps S261 to S265.

[0156] Step S270, using multiple candidate traffic flow state scoring rules as the traffic flow state evaluation criteria of the target intersection, and calling the signal timing solution library to perform signal control simulation on the target intersection based on the traffic flow state evaluation criteria to determine the rule adaptability of each of the multiple candidate traffic flow state scoring rules at the target intersection.

[0157] In this embodiment, the traffic signal control device 100 can use the multiple candidate traffic flow state scoring rules as the traffic flow state evaluation criteria of the target intersection, and then use the determined traffic flow state evaluation criteria to identify the intersection traffic flow results of the target intersection period by period during the signal control simulation process, and then call the signal timing scheme matching the traffic flow result of the intersection in the signal timing scheme library as the signal timing scheme to be used in the next period to perform traffic signal control simulation, so as to evaluate the signal evaluation index value of the corresponding traffic flow state evaluation criteria in the traffic signal control simulation process, so as to use the signal evaluation index value to characterize the rule fitness of the corresponding candidate traffic flow state scoring rule at the target intersection. Among them, if a positive evaluation index (for example, vehicle traffic efficiency) is used to evaluate the signal evaluation index value, the corresponding rule fitness will increase as the signal evaluation index value increases; if a negative evaluation index (for example, total vehicle traffic delay) is used to evaluate the signal evaluation index value, the corresponding rule fitness will decrease as the signal evaluation index value increases.

[0158] Step S280 , selecting the candidate traffic flow state scoring rule with the largest corresponding rule adaptability as the target traffic flow state scoring rule adapted to the target intersection.

[0159] In this embodiment, after determining the rule fitness of each of the multiple candidate traffic flow state scoring rules at the target intersection, the candidate traffic flow state scoring rule with the largest corresponding rule fitness can be selected from the multiple candidate traffic flow state scoring rules as the effective traffic flow state scoring rule (i.e., the target traffic flow state scoring rule) that needs to be stored at the traffic signal control device 100 at the target intersection.

[0160] Therefore, the present application can improve the accuracy of identifying the intersection traffic flow state of the target intersection by executing the above steps S250 to S280, and adaptively simulating the historical traffic data (including historical traffic flow data) of the target intersection to select the target traffic flow state scoring rules that are adapted to the target intersection, so as to provide a highly accurate decision-making basis for the signal timing scheme adjustment operation.

[0161] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic, for example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and a module, a program segment or a part of a code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0162] In addition, each functional module in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the various functions provided by the present application are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a storage medium. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (for example, a server, a personal computer, etc.) to perform all or part of the steps of the method recorded in each embodiment of the present application as the above-mentioned traffic signal control device 100. The aforementioned readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.

[0163] The above are only various implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for identifying traffic flow status at an intersection, characterized in that: The method comprises: Acquire the maximum saturation flow rate of various traffic flow turns at the target intersection, and the actual signal control traffic data of the various traffic flow turns in the current signal control cycle; For each traffic flow turn at the target intersection, according to the maximum saturation flow rate of the traffic flow turn and the actual traffic control data, calculate the actual saturation of the traffic flow turn in the current traffic control cycle; According to the target traffic flow state scoring rule adapted to the target intersection, based on the actual saturation of the traffic flow turn and the historical traffic flow state score of the traffic flow turn in the previous signal control cycle of the current signal control cycle, the actual traffic flow state score of the traffic flow turn in the current signal control cycle is calculated; The actual traffic flow state score of the traffic flow turn is used to identify the traffic flow state according to the target traffic flow state scoring rule, so as to obtain the overall traffic flow state of the traffic flow turn in the current traffic control cycle.

2. The method according to claim 1, characterized in that The step of obtaining the maximum saturation flow rate of various vehicle flow turns at the target intersection includes: For each traffic flow turn at the target intersection, a saturation flow rate is calculated according to the lane flow data and green light duration of each traffic flow turn in multiple historical signal control cycles, so as to obtain the historical saturation flow rates corresponding to each traffic flow turn in multiple historical signal control cycles; The data distribution statistics of the historical saturation flow rates corresponding to this type of traffic turn in multiple historical signal control cycles are performed, and the 90% quantile saturation flow rate in the corresponding data distribution statistics results is used as the maximum saturation flow rate of this type of traffic turn.

3. The method according to claim 1, characterized in that The saturation flow rate of the i-th type of traffic flow turning at the target intersection in the k-th signal control cycle is calculated using the following formula: in, It is used to represent the saturation flow rate of the i-th type of traffic flow turning in the k-th signal control cycle, It is used to indicate the green light duration of the i-th type of traffic flow turning in the k-th signal control cycle, N i It is used to indicate the total number of lanes where the i-th type of traffic flow turns to the target intersection, Used to represent the traffic flow value of the jth lane in the lane flow data of the kth signal control cycle for the i-th type of traffic flow turning.

4. The method according to claim 1, characterized in that: The actual signal control traffic data of each traffic flow turn includes the current signal control cycle duration, the actual green light duration and the actual flow value of each lane corresponding to the traffic flow turn. The traffic saturation of the i-th traffic flow turn at the target intersection in the current signal control cycle is calculated using the following formula: Among them, p i It is used to indicate the traffic saturation of the i-th traffic flow turn in the current traffic control cycle, S i It is used to represent the maximum saturation flow rate of the i-th type of traffic flow turning, g i It is used to indicate the actual green light duration of the i-th type of traffic flow turning in the current signal control cycle, C i It is used to indicate the duration of the current signal control cycle of the i-th type of traffic flow turning, N i It is used to indicate the total number of lanes where the i-th type of traffic flows turn to the target intersection, q i,j It is used to represent the actual flow value of the jth lane of the i-th type of traffic flow turning in the current signal control cycle, λ i It is used to indicate the green signal ratio of the i-th type of traffic flow turn in the current signal control cycle.

5. The method according to claim 1, characterized in that The target traffic flow state scoring rule records the continuous number of the first cycle, and the step of calculating the actual traffic flow state score of the traffic flow turn in the current signal control cycle according to the target traffic flow state scoring rule adapted to the target intersection, based on the actual saturation of the traffic flow turn and the historical traffic flow state score of the traffic flow turn in the previous signal control cycle of the current signal control cycle, includes: For this type of traffic flow steering, a target saturation interval corresponding to the actual saturation is determined in the saturation interval of the slow traffic state, the saturation interval of the smooth traffic state, and the saturation interval of the traffic congestion state; According to the target saturation interval, detecting whether the real saturation intervals of the target number of consecutive signal control cycles including the current signal control cycle are consistent, and whether the lane traffic state represented by the target saturation interval is consistent with the historical traffic flow state represented by the historical traffic flow state score, wherein the target number of consecutive cycles is obtained by adding one to the first number of consecutive cycles; If it is detected that the actual saturation intervals of a number of consecutive signal control cycles in the target cycle are consistent, and the lane traffic state represented by the target saturation interval is consistent with the historical traffic flow state represented by the historical traffic flow state score, then the historical traffic flow state score is directly used as the actual traffic flow state score of this type of traffic turn in the current signal control cycle; otherwise, a target state score matching the target saturation interval is calculated based on the historical traffic flow state score, and the calculated target state score is used as the actual traffic flow state score of this type of traffic turn in the current signal control cycle.

6. The method according to claim 5, characterized in that The target traffic flow state scoring rule records a first score accumulation value directly corresponding to the traffic slow state saturation interval, a second score accumulation value corresponding to the traffic congestion state saturation interval, a first score attenuation value corresponding to the traffic smooth state saturation interval, and a second score attenuation value corresponding to the traffic slow state saturation interval and the congested traffic flow state. The step of calculating the target state score matching the target saturation interval according to the historical traffic flow state score includes: When the target saturation interval belongs to the traffic congestion state saturation interval, adding the historical traffic flow state score and the second score accumulation value to obtain the target state score; When the target saturation interval belongs to the traffic flow state saturation interval, subtracting the historical traffic flow state score from the first score attenuation value to obtain the target state score; In the case where the target saturation interval belongs to the slow-moving traffic state saturation interval, detecting whether the historical traffic flow state represented by the historical traffic flow state score belongs to a congested traffic flow state; If it is detected that the historical traffic flow state belongs to a congested traffic flow state, a subtraction operation is performed on the historical traffic flow state score and the second score attenuation value to obtain the target state score; otherwise, an addition operation is performed on the historical traffic flow state score and the first score accumulation value to obtain the target state score.

7. The method according to claim 1, characterized in that The target traffic flow state scoring rule records a slow-moving traffic flow state scoring threshold and a congested traffic flow state scoring threshold. The step of performing traffic flow state identification based on the actual traffic flow state score of the traffic flow turn according to the target traffic flow state scoring rule to obtain the overall traffic flow state of the traffic flow turn in the current signal control cycle includes: Detecting whether the actual traffic flow state score of the vehicle flow turning is greater than or equal to the congested traffic flow state score threshold; If it is detected that the actual traffic flow state score of the vehicle flow turn is greater than or equal to the congested traffic flow state score threshold, it is determined that the overall traffic flow state of the vehicle flow turn in the current signal control cycle belongs to the congested traffic flow state, otherwise it is detected whether the actual traffic flow state score of the vehicle flow turn is greater than or equal to the slow-moving traffic flow state score threshold; When it is detected that the actual traffic flow state score of the vehicle flow turn is greater than or equal to the slow-moving traffic flow state score threshold, it is determined that the overall traffic flow state of the vehicle flow turn in the current signal control cycle belongs to the slow-moving traffic flow state; When it is detected that the actual traffic flow state score of the traffic turn is less than the slow-moving traffic flow state score threshold, it is determined that the overall traffic flow state of the traffic turn in the current traffic control cycle belongs to the smooth traffic flow state.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Constructing a traffic flow state scoring rule based on multiple preset score distribution constraints to obtain multiple candidate traffic flow state scoring rules; Based on at least one week of historical traffic flow data at the target intersection, a signal timing solution library for the target intersection is constructed, wherein the signal timing solution library includes signal timing solutions for the target intersection under different combinations of traffic flow states of vehicle flow turning, and each combination of traffic flow turning is composed of all traffic flow turning states at the target intersection in any one of a slow-moving traffic flow state, a congested traffic flow state, and a smooth traffic flow state; The plurality of candidate traffic flow state scoring rules are respectively used as traffic flow state evaluation criteria of the target intersection, and the signal timing solution library is called to perform signal control simulation on the target intersection based on the traffic flow state evaluation criteria to determine the rule adaptability of each of the plurality of candidate traffic flow state scoring rules at the target intersection; The candidate traffic flow state scoring rule with the largest corresponding rule adaptability is selected as the target traffic flow state scoring rule adapted to the target intersection.

9. The method according to claim 8, characterized in that The step of constructing a signal timing solution library for the target intersection based on at least one week of historical traffic flow data at the target intersection comprises: For each traffic flow turn at the target intersection, extract the 75% quantile flow value of the off-peak period flow data corresponding to the traffic flow turn in the historical traffic flow data as the overall flow value of the unblocked state of the traffic flow turn, and extract the 50% quantile flow value of the peak period flow data corresponding to the traffic flow turn in the historical traffic flow data as the overall flow value of the congested state of the traffic flow turn; Extracting the 50% quantile flow value of the valid flow data corresponding to the traffic flow turning and between the overall flow value of the unblocked state and the overall flow value of the congested state from the historical traffic flow data as the overall flow value of the slow-moving state of the traffic flow turning; The overall flow value of the unblocked state, the overall flow value of the slow-moving state, and the overall flow value of the congested state of the traffic flow turn are divided by the total number of lanes at the target intersection for the traffic flow turn, to obtain the reference flow values ​​corresponding to the traffic flow turn in the unblocked traffic flow state, the slow-moving traffic flow state, and the congested traffic flow state, respectively; For each traffic flow turning traffic flow state combination, according to the reference flow values ​​of all traffic turns under different traffic flow states, calculate the phase flow values ​​of various traffic phases at the target intersection under the traffic flow turning traffic flow state combination; The signal control cycle duration and green light duration are calculated based on the phase flow values ​​of various traffic phases at the target intersection under the combination of traffic flow turning and traffic flow states, and the signal timing plan for the target intersection under the combination of traffic flow turning and traffic flow states is obtained.

10. A traffic signal control device, characterized in that: The control device includes a processor and a memory, wherein the memory stores a computer program executable by the processor, and the processor can execute the computer program to implement the method for identifying the traffic flow state at an intersection as described in any one of claims 1-9.

Images