A processing method and device for single-point intersection traffic signal timing

Abstract

The embodiment of the present application relates to a kind of processing method and device for single point intersection traffic signal timing, the method comprises: periodically obtaining the traffic data set of all turns of intersection by internet data interface, and it is preprocessed;And predict the traffic data of all turns future signal period based on traffic data set;And based on the prediction data set, turn green light duration estimation is carried out, and the estimated data set is revised;And based on the estimated data set and double-ring configuration relationship, the timing optimization of current intersection is carried out;And the traffic data dispersion coefficient of each turn is identified on the two observation time after this optimization, and whether the optimization this time has caused traffic deterioration is confirmed based on the identification result, if confirming that traffic deterioration has been caused, then switch back to historical scheme and carry out timing.Adaptive optimization can be carried out to the intersection signal timing of real road network based on the present application, and the intelligent traffic management cost of road network can be effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a processing method and apparatus for traffic signal timing at single-point intersections. Background Technology

[0002] Currently, the technical solutions for adaptive optimization of traffic signal timing at single intersections based on detector data sources (such as induction coil detectors and geomagnetic detectors) are relatively mature. However, due to the cost of detector deployment, it is difficult to achieve full intersection coverage in real traffic networks. In other words, relying solely on detector data sources makes it difficult to ensure that adaptive traffic signal timing can be achieved at every single intersection in a real road network.

[0003] Internet data sources represent a new type of traffic sensing data source. The advantage of internet data sources is their ability to provide full network coverage of traffic data for all turning lanes at all intersections, with convenient and low-cost acquisition methods. If traffic signal timing at individual intersections in a real road network can be adaptively optimized based on internet data sources, the cost of intelligent traffic management for the road network can undoubtedly be reduced. However, compared to detector data sources, internet data has a lower average reliability. Directly adopting optimization schemes from detector data sources is highly likely to cause significant optimization errors, thereby reducing the accuracy of intelligent traffic management for the road network. Therefore, a separate traffic signal timing optimization scheme needs to be customized for internet data sources, which is the technical problem that this invention aims to solve. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by providing a method, apparatus, electronic device, and computer-readable storage medium for processing traffic signal timing at single-point intersections. This invention periodically acquires a traffic dataset from the delay duration, queue length, and number of stops for all traffic flows turning at a single-point intersection over the most recent signal cycles via an internet data interface, and preprocesses this dataset. Then, based on the preprocessed traffic dataset, it predicts the delay duration, queue length, and number of stops for all turns in future signal cycles. Next, it estimates the green light duration for all turns based on the predicted dataset and corrects the estimated dataset. Then, it optimizes the timing based on the estimated dataset and the current double-ring configuration of the intersection. Finally, it saves the signal timing scheme executed in the current signal cycle as a historical scheme and performs timing based on the optimized scheme. Then, at the next two observation times, it identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic deterioration based on the identification results. If it confirms that traffic deterioration has occurred, it switches back to the historical scheme for timing in the next signal cycle. This invention designs a traffic signal timing optimization scheme based on Internet data sources. Based on this invention, the traffic signal timing of all single-point intersections in the real road network can be adaptively optimized, which can effectively reduce the cost of intelligent traffic management of the road network.

[0005] To achieve the above objectives, a first aspect of the present invention provides a method for processing traffic signal timing at a single-point intersection, the method comprising:

[0006] Each single-point intersection is designated as the current intersection; the current intersection includes N signal phases, where the total number of phases N is a positive integer greater than 1; the i-th phase includes M... i Traffic flow turns, total number of turns M i The value is a positive integer, 1 ≤ phase index i ≤ N; the phase signal duration configuration relationship of the current intersection follows a double-ring configuration relationship;

[0007] The traffic dataset is formed by periodically obtaining the delay time, queue length and number of stops of all traffic flows turning at the current intersection in the most recent K signal cycles through the Internet data interface; the total number of cycles K is a positive integer greater than 1.

[0008] The traffic dataset is preprocessed;

[0009] Based on the traffic dataset, the delay time, queue length and number of stops for all future turning signal cycles are predicted to obtain the corresponding prediction dataset;

[0010] Based on the predicted dataset, the green light duration for turning is estimated to obtain the corresponding estimated dataset;

[0011] The estimated dataset is corrected based on the preset green light duration range for each turn;

[0012] Based on the estimated dataset and the dual-ring configuration relationship, the timing of the current intersection is optimized to obtain an optimized timing scheme;

[0013] Save the signal timing scheme executed in the current signal cycle as a historical scheme; and use the start time of the next signal cycle as the optimization time t. opt Based on the current optimization time t opt and the preset observation duration L obs Set two observation times t obs1 t obs2 ; and at the current optimization time t opt Timing is performed based on the optimized timing scheme described above; t obs1 =t opt +L obs , t obs2 =t obs1 +L obs ;

[0014] At the subsequent observation time t obs1 t obs2The system identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic congestion based on the identification results; if traffic congestion is confirmed, then at observation time t... obs2 The next signal cycle will then switch back to the historical scheme for timing.

[0015] Preferably, the duration of the steering signal for the j-th steering in the i-th phase is denoted as G. i,j G i,j =g i,j +y i,j ; 1 ≤ turning index j ≤ M i g i,j y i,j These represent the green light duration and yellow light duration for the current turn, respectively; g i,j >y i,j >0; Yellow light duration y i,j The default setting is 3 seconds;

[0016] The duration of the phase signal of the i-th phase is denoted as P. i P i =max(G i,j );

[0017] The dual-ring configuration includes a primary ring and a secondary ring; the primary and secondary rings are each composed of multiple phase signal durations P. i The signals are ordered sequentially; the total duration of the main and secondary loops is equal, denoted as the intersection signal cycle C. total The intersection signal period C total The left and right rings are divided into two semi-ring periods, denoted as the left ring signal period C. left Right loop signal period C right ;

[0018] The traffic dataset includes multiple data sequences X i,j The data sequence X i,j The data sequence X corresponds one-to-one with the traffic flow direction; i,j Given K traffic data x i,j,k Composition, 1 ≤ periodic index k ≤ K; the traffic data x i,j,k Including delay duration e i,j,k Queue length l i,j,k Number of stops (s) i,j,k Confidence level c i,j,k The confidence level c i,j,k The value of is between 0 and 1;

[0019] The prediction dataset includes multiple traffic prediction data. The predicted traffic data The predicted traffic data corresponds one-to-one with the traffic flow direction. Including predicted delay duration Predicting queue length Predicted number of parking times

[0020] The estimation dataset includes multiple estimated green light durations. The estimated green light duration Each corresponds one-to-one with the traffic flow direction;

[0021] The optimized timing scheme includes the intersection signal cycle C' total Left loop signal period C' left Right loop signal period C' right and the duration of multiple turn signals G' i,j The duration of the steering signal G' i,j Corresponding one-to-one with the traffic flow direction; G' i,j =g' i,j +y' i,j ;g' i,j y' i,j These are the optimized green light duration and yellow light duration for the current turn, respectively; g' i,j >y' i,j >0; Yellow light duration y' i,j The default setting is 3 seconds.

[0022] Preferably, the preprocessing of the traffic dataset specifically includes:

[0023] Step 31, divide the traffic dataset into its constituent data sequences X. i,j As the current sequence;

[0024] Step 32: Filter the current sequence for low-confidence data based on a preset confidence threshold, specifically as follows:

[0025] The confidence scores c of all sequences in the current sequence that are less than the confidence threshold are... i,j,k Set all to 0;

[0026] Step 33: Set queue length correction rules based on traffic data relationship method;

[0027] The queue length correction rule is as follows:

[0028] s i,j,k When >1, if Then correct

[0029] s i,j,k When ≤1, if Then correct

[0030] g i,jFor the green light duration of the j-th turn in the i-th phase of the signal timing scheme executed in the current signal cycle, O i,j Let d be the saturation flow rate of the i-th phase and the j-th turn, and d be the queuing headway.

[0031] Step 34: Correct the queue length of the current sequence based on the queue length correction rule, specifically as follows:

[0032] Each confidence level c in the current sequence i,j,k The traffic data x that is not zero i,j,k As the corresponding current data; and the queue length l of the current data. i,j,k The number of stops s i,j,k The current queue length and the current number of stops are used as the basis for determining whether the current queue length needs to be corrected based on the current number of stops and the queue length correction rule. If it is determined that correction is needed, the current queue length is corrected according to the correction method corresponding to the current number of stops in the queue length correction rule.

[0033] Step 35: Filter traffic data with abnormal queue lengths or delay times in the current sequence based on the standard deviation method, specifically as follows:

[0034] All the confidence levels c in the current sequence i,j,k The traffic data x that is not zero i,k All are recorded as data samples; and the delay duration e of all said data samples is... i,j,k The average value μ e and standard deviation σ e Perform calculations; and calculate the queue length l for all said data samples. i,j,k The average value μ l and standard deviation σ l Perform calculations; and based on the average value μ e and the standard deviation σ e Set the delay duration range to [|μ e -σ e |,|μ e +σ e |]; and based on the average value μ l and the standard deviation σ l Set the queue length range to [|μ l -σ l |,|μ l +σ l |]; and the delay duration e i,j,k The delay time interval or the queue length l is not satisfied. i,j,kData samples that do not meet the specified queue length range are recorded as anomalous samples; and the confidence level c of all anomalous samples is... i,j,k Set to 0.

[0035] Furthermore, the method of setting queue length correction rules based on traffic data relationships specifically includes:

[0036] Step 41, confirm the known prior conditions:

[0037]

[0038] Where n1 and n0 are the number of stops s i,j,k The total number of vehicles in the queue and the total number of vehicles not in the queue for the corresponding i-th phase and j-th turn;

[0039] Step 42, by We can obtain:

[0040]

[0041] Step 43, Substitute the prior conditions We can obtain:

[0042]

[0043] Step 44, convert the prior conditions into:

[0044]

[0045] Step 45: The product of the distance between the front of the queued vehicles (d) and the total number of vehicles in the queue (n1) is taken as the corresponding queue length (l). i,j,k =n1×d, then the prior conditions are transformed into:

[0046]

[0047] Step 46, setting boundaries based on the prior conditions, specifically:

[0048] s i,j,k When >1, l i,j,k The minimum value is set as

[0049] s i,j,k When ≤1, l i,j,k The maximum value is set to

[0050] Step 47, based on the boundary settings, set the queue length correction rule as follows:

[0051] s i,j,k When >1, if Then correct

[0052] s i,j,k When ≤1, if Then correct

[0053] Preferably, the step of predicting the delay duration, queue length, and number of stops for all future turning signal cycles based on the traffic dataset to obtain the corresponding prediction dataset specifically includes:

[0054] The traffic dataset contains various data sequences X. i,j As the current sequence; and the confidence level c in the current sequence i,j,k The traffic data x that is not zero i,k Extract the data to form a corresponding valid data sequence; and combine all the delay durations e in the valid data sequence. i,j,k All queue lengths l i,j,k All the number of stops mentioned in s i,j,k The delay duration sequence, queue length sequence, and number of stops sequence are extracted to form corresponding delay duration sequences, queue length sequences, and number of stops sequences. Then, using a quadratic exponential smoothing method, the delay duration, queue length, and number of stops for a specified future signal period are predicted based on these sequences to obtain the predicted delay duration. The predicted queue length The predicted number of parking times And the predicted delay duration corresponding to the current sequence. The predicted queue length The predicted number of parking times The corresponding predicted traffic data constitutes the data. And from all the predicted traffic data obtained The corresponding prediction dataset is then formed.

[0055] Preferably, the step of estimating the green light duration based on the predicted dataset to obtain the corresponding estimated dataset specifically includes:

[0056] Step 61, combine the predicted traffic data from the predicted dataset. As current forecast data;

[0057] Step 62, the prediction delay time of the current prediction data. The predicted queue length The predicted number of parking times Let e ​​be the corresponding e now l now s now ;

[0058] Step 63: The green light duration g of the i-th phase and j-th turn in the signal timing scheme executed in the current signal cycle is... i,j The duration of the yellow light, y i,j Let g be the corresponding g now y now Based on the intersection signal period C total Calculate the red light duration r for the i-th phase and j-th turn. now ;

[0059] Where, r now =C total -(g now +y now );

[0060] Step 64, adjust the saturation flow rate O of the i-th phase and j-th direction. i,j Denote as O now ; and based on saturation flow rate O now Calculate the corresponding saturated headway H no ;

[0061] Among them, H now =3600 / O now ;

[0062] Step 65, based on the queue length l now The number of stops s now The queuing headway d is used to estimate the turning traffic flow q in a single cycle. * ; and based on the turning traffic flow q * and the saturated headway H now Estimate the corresponding green light duration g a Based on the green light duration g now Set the green light duration g a The boundary constraints; and the green light duration g based on the boundary constraints. a Make corrections;

[0063] in,

[0064] The turning traffic flow q * The estimation method is as follows:

[0065] The green light duration g a The estimation method is as follows: g a =q * ×H now +δ1;

[0066] The boundary constraint is: g a ∈[g now -δ2,g now+δ2];

[0067] The green light duration g a The correction rule is:

[0068] If g a <g now -δ2, then correct g a =g now -δ2;

[0069] If g a >g now +δ2, then modify g a =g now +δ2;

[0070] δ1 is the preset loss duration, which is set to 3 seconds by default; δ2 is the preset duration optimization range, which is set to 5 seconds by default.

[0071] Step 66, based on the delay duration e now and the red light duration r now Estimate the delay index f now ; and based on the delay index f now and the green light duration g now Estimate the corresponding green light duration g b ;

[0072] in,

[0073] The delay index f now The estimation method is as follows:

[0074] The green light duration g b The estimation method is as follows:

[0075]

[0076] δ3 is the preset single-step increment / decrement duration, set to 3 seconds by default;

[0077] f now A value ≥1 indicates that the queue length in a single signal cycle is insufficient to clear the vehicles, resulting in secondary queuing; the green light duration should be increased. now A value ≤0.2 indicates that the green light duration per single signal cycle is sufficient, and the green light duration should be reduced.

[0078] Step 67, based on the green light duration g a g b Estimate the corresponding green light duration

[0079] Among them, the green light duration The estimation method is as follows:

[0080]

[0081] Step 68, based on all the obtained green light durations The corresponding estimation dataset is then constructed.

[0082] Preferably, the step of correcting the estimated dataset based on the preset green light duration range for each turn specifically includes:

[0083] Step 71, calculate the green light duration of each item in the estimated dataset. As the current duration g * ;

[0084] Step 72, set the current duration g * The corresponding traffic flow direction is taken as the current direction; and the green light duration g corresponding to the current direction in the signal timing scheme executed in the current signal cycle is taken as the current direction. i,j Let g0 be the threshold value; and let the lower limit and upper limit of the preset green light duration range corresponding to the current turn be the corresponding green light duration g. min Green light duration (g) max ;

[0085] Step 73, based on the green light duration g min g max g0 sets the correction boundary

[0086] Wherein, the correction boundary Including lower boundary Boundary Lower Boundary

[0087] δ4 is the preset increment / decrement duration, with a default setting of 15 seconds;

[0088] Step 74, based on the corrected boundary For the current duration g * The following corrections have been made:

[0089] Preferably, the step of optimizing the timing of the current intersection based on the estimated dataset and the dual-ring configuration relationship to obtain an optimized timing scheme specifically includes:

[0090] Step 81, based on the M corresponding to the i-th phase i The green light duration mentioned above Estimate the corresponding M i The duration of each turn signal and M i The duration of the aforementioned turn signal The maximum value in the value is used as the corresponding phase signal duration. And the duration of the N phase signals obtained Forming a corresponding set of phase durations;

[0091] in,

[0092] y i,j The duration of the yellow light for the j-th turn in the i-th phase;

[0093] Step 82: Based on the left and right ring barriers, the main and secondary rings are divided into left and right half-rings, denoted as the corresponding left main half-ring, right main half-ring, left secondary half-ring, and right secondary half-ring; and the phase sets corresponding to each of the four half-rings are denoted as the corresponding first, second, third, and fourth phase sets; and the phase signal durations corresponding to the first, second, third, and fourth phase sets in the phase duration sets are... Extract these values ​​to form corresponding first, second, third, and fourth duration sets; and calculate the total duration of each of the first, second, third, and fourth duration sets.

[0094] Step 83: Identify the preset signal period modulation configuration;

[0095] The signal period modulation configuration includes a non-adjustable period and an adjustable period.

[0096] Step 84: If the signal period modulation configuration is set to have a non-adjustable period, then the left loop signal period C' under the fixed period condition is determined based on the sum of the four durations. left The right loop signal period C' right and the intersection signal period C' total Configure settings;

[0097] Step 85: If the signal period modulation configuration is periodically adjustable, then the sum of the durations corresponding to the left and right main half-loops is used. Set the left loop signal period C' left The right loop signal period C' right And calculate the corresponding intersection signal period C' based on the setting result. total ;

[0098] in, C' total =C' left +C' right ;

[0099] Step 86, based on the left loop signal period C' left The total duration corresponding to the left main half-loop And the green light duration corresponding to each phase turn of the left main half-loop in the estimated dataset. Calculate the corresponding green light duration g' i,j ; and based on the right loop signal period C' right The total duration corresponding to the right main half-loop And the green light duration corresponding to each phase turn of the right main half-loop in the estimated dataset. Calculate the corresponding green light duration g' i,j ; and based on the left loop signal period C' left The total duration corresponding to the left second half ring And the green light duration corresponding to each phase turn of the left secondary half-ring in the estimated dataset. Calculate the corresponding green light duration g' i,j ; and based on the right loop signal period C' right The total duration of the right secondary half-loop And the green light duration corresponding to each phase turn of the right secondary half-ring in the estimated dataset. Calculate the corresponding green light duration g' i,j ;

[0100] in,

[0101] The green light duration g' corresponding to each phase turn within the left main half-ring i,j for:

[0102]

[0103] The green light duration g' corresponding to each phase turn within the right main half-ring i,j for:

[0104]

[0105] The green light duration g' corresponding to each phase turn within the left secondary half-ring i,j for:

[0106]

[0107] The green light duration g' corresponding to each phase turn within the right secondary half-ring i,j for:

[0108]

[0109] Step 87: The duration y of each yellow light in the signal timing scheme executed in the current signal cycle is... i,j The corresponding yellow light duration y' i,j ; and determined by the green light duration g' of each of the aforementioned green lights i,j and the corresponding yellow light duration y' i,j Calculate the corresponding steering signal duration G'i,j G' i,j =g' i,j +y' i,j ;

[0110] Step 88, based on the obtained intersection signal period C' total The left loop signal period C' le ft, the right loop signal period C' right and the duration G' of all the aforementioned turn signals i,j The corresponding optimized timing scheme is then formed.

[0111] Furthermore, the left loop signal period C' under fixed period conditions is based on the sum of four durations. left The right loop signal period C' right and the intersection signal period C' total The settings include:

[0112] Step 91: The phase signal duration P corresponding to the first, second, third, and fourth phase sets in the signal timing scheme executed in the current signal period is... i Extract these values ​​to form the corresponding fifth, sixth, seventh, and eighth duration sets; and calculate the total duration C for each of the fifth, sixth, seventh, and eighth duration sets. l1 C r1 C l2 C r2 ;

[0113] Step 92, based on the sum of the four durations Calculate the four corresponding proportional parameters;

[0114] Among them, the four proportional parameters are a l1 a r1 a l2 a r2 :

[0115]

[0116] Step 93, if a l1 a l2 If ≥1, then a l1 a l2 The sum of the durations corresponding to the maximum values ​​in the range is used as the estimation period. If a l1 a l2 If ≤1, then a l1 a l2 The sum of the durations corresponding to the minimum values ​​in the range is used as the estimation period. If a l1 <1<al2 or a l2 <1<a l1 Then a l1 a l2 The average of the sums of the two corresponding durations is used as the estimated period.

[0117] Step 94, if a r1 a r2 If ≥1, then a r1 a r2 The sum of the durations corresponding to the maximum values ​​in the range is used as the estimation period. If a r1 a r2 If ≤1, then a r1 a r2 The sum of the durations corresponding to the minimum values ​​in the range is used as the estimation period. If a r1 <1<a r2 or a r2 <1<a r1 Then a r1 a r2 The average of the sums of the two corresponding durations is used as the estimated period.

[0118] Step 95, based on the estimated period and the intersection signal period C of the current signal period total Set the left loop signal period C' left The right loop signal period C' right ;

[0119] in,

[0120] Step 96, set the intersection signal period C total The intersection signal period C' total .

[0121] Preferably, at the subsequent observation time t obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and, based on the identification results, confirms whether the optimization has caused traffic congestion. Specifically, this includes:

[0122] Step 101, at the observation time t obs1 Above, set the first time period as [t] opt -L obs ,t opt The second time period is [t] opt ,t obs1The system obtains the delay durations of all signal cycles within the first and second time periods of each turn through the internet data interface to form corresponding first and second sets, and obtains the queue lengths of all signal cycles within the first and second time periods of each turn to form corresponding third and fourth sets; and calculates the corresponding delay duration dispersion coefficients based on the first and second sets of each turn. The corresponding queue length discrepancy coefficients are calculated based on the third and fourth sets for each turning point. And the discrete coefficient of the delay time for each turn. and the queuing length discrete coefficient Perform identification; if and Then set the corresponding first steering observation result as deterioration; if or Then the corresponding first steering observation result is set to non-deterioration;

[0123] The first steering observation results include deterioration and non-deterioration;

[0124] Step 102, at the observation time t obs2 Above, set the third time period as [t] obs1 ,t obs2 The system obtains the delay duration of all signal cycles within the third time period for each turn through the internet data interface to form a fifth set, and obtains the queue length of all signal cycles within the third time period for each turn to form a sixth set; and calculates the corresponding delay duration dispersion coefficient based on the fifth set for each turn. And calculate the corresponding queue length discrepancy coefficient based on the sixth set for each turn. And the discrete coefficient of the delay time for each turn. and the queuing length discrete coefficient Perform identification; if and Then set the corresponding second steering observation result as deterioration; if or Then, the corresponding second steering observation result is set to non-deterioration; and it is identified whether the first and second steering observation results for all steering are deterioration; if not, it is confirmed that traffic has not yet deteriorated; if so, it is confirmed that traffic has deteriorated.

[0125] The second observation result includes deterioration and non-deterioration.

[0126] A second aspect of the present invention provides an apparatus for implementing the processing method for traffic signal timing at a single intersection as described in the first aspect above. The apparatus includes: an intersection confirmation module, a traffic data acquisition module, a traffic data preprocessing module, a traffic data prediction module, a green light duration estimation module, an estimation data correction module, a timing scheme optimization module, a timing optimization module, and an optimization evaluation module.

[0127] The intersection confirmation module is used to identify each single-point intersection as the current intersection; the current intersection includes N signal phases, where the total number of phases N is a positive integer greater than 1; the i-th phase includes M... i Traffic flow turns, total number of turns M i The value is a positive integer, 1 ≤ phase index i ≤ N; the phase signal duration configuration relationship of the current intersection follows a double-ring configuration relationship;

[0128] The traffic data acquisition module is used to periodically acquire, via an Internet data interface, the delay time, queue length, and number of stops of all traffic flows turning at the current intersection over the most recent K signal cycles to form a corresponding traffic dataset; the total number of cycles K is a positive integer greater than 1;

[0129] The traffic data preprocessing module is used to preprocess the traffic dataset;

[0130] The traffic data prediction module predicts the delay time, queue length, and number of stops for all future turning signal cycles based on the traffic dataset to obtain the corresponding prediction dataset.

[0131] The green light duration estimation module estimates the turning green light duration based on the predicted dataset to obtain the corresponding estimated dataset.

[0132] The estimated data correction module corrects the estimated dataset based on the preset green light duration range for each turn;

[0133] The timing scheme optimization module performs timing optimization on the current intersection based on the estimated dataset and the dual-ring configuration relationship to obtain an optimized timing scheme;

[0134] The timing optimization module is used to save the signal timing scheme executed in the current signal cycle as a historical scheme; and to use the start time of the next signal cycle as the current optimization time t. opt Based on the current optimization time t opt and the preset observation duration L obs Set two observation times t obs1 t obs2 ; and at the current optimization time t opt Timing is performed based on the optimized timing scheme described above; t obs1 =topt +L obs , t obs2 =t obs1 +L obs ;

[0135] The optimization evaluation module is used to evaluate the results at subsequent observation times t. obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic congestion based on the identification results; if traffic congestion is confirmed, then at observation time t... obs2 The next signal cycle will then switch back to the historical scheme for timing.

[0136] A third aspect of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0137] The processor is used to couple with the memory, read and execute instructions in the memory to implement the steps of the method described in the first aspect above;

[0138] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0139] A fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a computer, cause the computer to perform the instructions described in the first aspect.

[0140] This invention provides a method, apparatus, electronic device, and computer-readable storage medium for processing traffic signal timing at a single-point intersection. As described above, this invention periodically acquires a traffic dataset from the delay duration, queue length, and number of stops for all traffic flows turning at a single-point intersection over the most recent signal cycles via an internet data interface, and preprocesses this dataset. Then, based on the preprocessed traffic dataset, it predicts the delay duration, queue length, and number of stops for all turns in future signal cycles. Next, it estimates the green light duration for all turns based on the predicted dataset and corrects the estimated dataset. Then, it optimizes the timing based on the estimated dataset and the current double-ring configuration of the intersection. Finally, it saves the signal timing scheme executed in the current signal cycle as a historical scheme and performs timing based on the optimized scheme. Then, at the next two observation times, it identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic deterioration based on the identification results. If it confirms that traffic deterioration has occurred, it switches back to the historical scheme for timing in the next signal cycle. This invention presents a traffic signal timing optimization scheme based on Internet data sources. Based on this invention, the traffic signal timing of all single-point intersections in the real road network can be adaptively optimized, effectively reducing the cost of intelligent traffic management. Attached Figure Description

[0141] Figure 1 This is a schematic diagram of a processing method for traffic signal timing at a single-point intersection provided in Embodiment 1 of the present invention;

[0142] Figure 2 This is a schematic diagram of the dual-ring configuration relationship provided in Embodiment 1 of the present invention;

[0143] Figure 3 This is a module structure diagram of a processing device for traffic signal timing at a single intersection, provided in Embodiment 2 of the present invention.

[0144] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0145] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0146] Embodiment 1 of the present invention provides a processing method for traffic signal timing at a single-point intersection, such as... Figure 1The schematic diagram of a processing method for traffic signal timing at a single intersection provided in Embodiment 1 of the present invention includes the following main steps:

[0147] Step 1: Designate each single intersection as the current intersection.

[0148] Here, in this embodiment of the invention, the current intersection includes N signal phases, where the total number of phases N is a positive integer greater than 1; the i-th phase includes M... i Traffic flow turns, total number of turns M i The value is a positive integer, 1 ≤ phase index i ≤ N; the phase signal duration configuration relationship at the current intersection follows a double-ring configuration relationship.

[0149] like Figure 2 As shown in the schematic diagram of the dual-ring configuration provided in Embodiment 1 of the present invention, the duration of the steering signal for the j-th steering in the i-th phase of the present invention is denoted as G. i,j G i,j =g i,j +y i,j ; 1 ≤ turning index j ≤ M i g i,j y i,j These represent the green light duration and yellow light duration for the current turn, respectively; g i,j >y i,j >0; Yellow light duration y i,j The default setting is 3 seconds. The duration of the phase signal of the i-th phase is denoted as P. i P i =max(G i,j ).

[0150] like Figure 2 As shown, the dual-ring configuration of this embodiment includes a primary ring and a secondary ring. The primary and secondary rings each consist of multiple phase signal durations P. i The signals are ordered sequentially. The total duration of the main and secondary loops is equal, denoted as the intersection signal cycle C. total Intersection signal cycle C total The left and right rings are divided into two semi-ring periods, denoted as the left ring signal period C. left Right loop signal period C right .

[0151] Step 2: Periodically obtain the delay time, queue length and number of stops of all traffic flows turning at the current intersection in the most recent K signal cycles through the Internet data interface to form the corresponding traffic dataset;

[0152] Specifically, the traffic dataset is generated by periodically acquiring the delay time, queue length, and number of stops of all traffic flows turning at the current intersection over the most recent K signal cycles via an internet data interface at a preset first time frequency.

[0153] Here, the first time frequency in this embodiment of the invention is a pre-set time frequency parameter, and the total number of periods K is a positive integer greater than 1. The traffic dataset in this embodiment of the invention includes multiple data sequences X. i,j Data sequence X i,j One-to-one correspondence with traffic flow direction; data sequence X i,j Given K traffic data x i,j,k Composition, 1 ≤ periodic index k ≤ K; traffic data x i,j,k Including delay duration e i,j,k Queue length l i,j,k Number of stops (s) i,j,k Confidence level c i,j,k Confidence level c i,j,k The value of is between 0 and 1.

[0154] Step 3: Preprocess the traffic dataset;

[0155] Specifically, this includes: Step 31, dividing the traffic dataset into its various data sequences X. i,j As the current sequence;

[0156] Step 32: Filter low-confidence data in the current sequence based on a preset confidence threshold;

[0157] Specifically, this involves: assigning confidence scores c to all sequences in the current sequence that are less than the confidence threshold. i,j,k All are set to 0; here, the confidence threshold in this embodiment of the invention is a pre-set threshold parameter;

[0158] Step 33: Set queue length correction rules based on traffic data relationship method;

[0159] The queue length correction rule is as follows:

[0160] s i,j,k When >1, if Then correct

[0161] s i,j,k When ≤1, if Then correct

[0162] g i,j For the green light duration of the j-th turn in the i-th phase of the signal timing scheme executed in the current signal cycle, O i,j Let d be the saturation flow rate of the i-th phase and the j-th turn, and d be the queuing headway.

[0163] The process of setting the queue length correction rule in this embodiment of the invention is as follows:

[0164] Step 331, confirm the known prior conditions:

[0165]

[0166] Where n1 and n0 are the number of stops s i,j,k The total number of vehicles in the queue and the total number of vehicles not in the queue for the corresponding i-th phase and j-th turn;

[0167] Step 332, by We can obtain:

[0168]

[0169] Step 333, will Substitute prior conditions We can obtain:

[0170]

[0171] Step 334, transform the prior conditions into:

[0172]

[0173] Step 335: The product of the distance between the front of the queued vehicles, d, and the total number of vehicles in the queue, n1, is taken as the corresponding queue length, l. i,j,k =n1×d, then the prior conditions are transformed into:

[0174]

[0175] Step 336, setting boundaries based on prior conditions, specifically:

[0176] s i,j,k When >1, l i,j,k The minimum value is set as

[0177] s i,j,k When ≤1, l i,j,k The maximum value is set to

[0178] Step 337, based on boundary settings, set the queue length correction rule as follows:

[0179] s i,j,k When >1, if Then correct

[0180] s i,j,k When ≤1, if Then correct

[0181] Step 34: Adjust the queue length of the current sequence based on the queue length adjustment rule;

[0182] Specifically, this involves: assigning each confidence level c in the current sequence... i,j,k Non-zero traffic data x i,j,k As the corresponding current data; and set the queue length l of the current data as... i,j,k Number of stops (s) i,j,k The current queue length and the current number of stops are used as the basis for determining whether the current queue length needs to be adjusted based on the current number of stops and the queue length adjustment rules. If it is determined that adjustment is needed, the current queue length is adjusted according to the adjustment method corresponding to the current number of stops in the queue length adjustment rules.

[0183] Step 35: Filter traffic data with abnormal queue lengths or delay times in the current sequence based on the standard deviation method;

[0184] Specifically, this involves: calculating all confidence levels c in the current sequence. i,j,k Non-zero traffic data x i,k All are recorded as data samples; and the delay duration e for all data samples is calculated. i,j,k The average value μ e and standard deviation σ e Perform calculations; and calculate the queue length l for all data samples. i,j,k The average value μ l and standard deviation σ l Perform calculations; and based on the average value μ e and standard deviation σ e Set the delay duration range to [|μ e -σ e |,|μ e +σ e |];and based on the average value μ l and standard deviation σ l Set the queue length range to [|μ l -σ l |,|μ l +σ l |]; and will delay e i,j,k The delay time range or queue length does not meet the requirements. i,j,k Data samples that do not meet the queue length range are marked as outliers; and the confidence level c of all outliers is calculated. i,j,k Set to 0.

[0185] Step 4: Based on the traffic dataset, predict the delay duration, queue length, and number of stops for all future turning signal cycles to obtain the corresponding prediction dataset.

[0186] Here, the prediction dataset in this embodiment of the invention includes multiple predicted traffic data. Predicted traffic data One-to-one correspondence with traffic flow direction; predictive traffic data Including predicted delay duration Predicting queue length Predicted number of parking times

[0187] The current step 4 specifically includes: processing each data sequence X of the traffic dataset. i,j This is used as the current sequence; and the confidence level c in the current sequence is... i,j,k Non-zero traffic data x i,k Extract the data to form the corresponding valid data sequence; and combine all delay durations e in the valid data sequence. i,j,k All queue lengths l i,j,k Total number of stops (s) i,j,k The delay duration, queue length, and number of stops are extracted to form corresponding delay duration sequences, queue length sequences, and stop count sequences. Then, using a quadratic exponential smoothing method, the delay duration, queue length, and number of stops for a specified future signal period are predicted based on these sequences to obtain the predicted delay duration. Predicting queue length Predicted number of parking times And based on the predicted delay duration corresponding to the current sequence. Predicting queue length Predicted number of parking times Composition of corresponding predicted traffic data And from all the predicted traffic data obtained This forms the corresponding prediction dataset.

[0188] Step 5: Estimate the green light duration based on the predicted dataset to obtain the corresponding estimated dataset.

[0189] Here, the estimation dataset in this embodiment of the invention includes multiple estimated green light durations. Estimating green light duration It corresponds one-to-one with the direction of traffic flow.

[0190] The current step 5 specifically includes:

[0191] Step 51: Combine the various predicted traffic data from the prediction dataset. As current forecast data;

[0192] Step 52: Calculate the prediction delay time of the current prediction data. Predicting queue length Predicted number of parking times Let e ​​be the corresponding e now l now s now ;

[0193] Step 53: Calculate the green light duration g for the j-th turn in the i-th phase of the signal timing scheme executed in the current signal cycle. i,j Yellow light duration y i,j Let g be the corresponding g now y now Based on the intersection signal cycle C total Calculate the red light duration r for the i-th phase and j-th turn. now ;

[0194] Where, r now =C total -(g now +y now );

[0195] Step 54, adjust the saturation flow rate O of the i-th phase and j-th direction. i,j Denote as O now ; and based on saturation flow rate O now Calculate the corresponding saturated headway H no ;

[0196] Among them, H now =3600 / O now ;

[0197] Step 55, based on queue length l now Number of stops (s) now The queuing headway d is used to estimate the turning traffic flow q in a single cycle. * And based on the turning traffic flow q * and the distance H between the saturated front end now Estimate the corresponding green light duration g a And based on the green light duration g now Set green light duration (g) a Boundary constraints; and based on the boundary constraints, the green light duration g a Make corrections;

[0198] in,

[0199] Turning traffic flow q * The estimation method is as follows:

[0200] Green light duration (g) a The estimation method is as follows: g a =q * ×H now +δ1;

[0201] The boundary constraint is: g a ∈[g now -δ2,g now +δ2];

[0202] Green light duration (g)a The correction rule is as follows:

[0203] If g a <g now -δ2, then correct g a =g now -δ2;

[0204] If g a >g now +δ2, then modify g a =g now +δ2;

[0205] δ1 is the preset loss duration, which is set to 3 seconds by default; δ2 is the preset duration optimization range, which is set to 5 seconds by default.

[0206] Step 56, based on delay duration e now and red light duration r now Estimating the delay index f now Based on the delay index f now and green light duration g now Estimate the corresponding green light duration g b ;

[0207] in,

[0208] Delay index f now The estimation method is as follows:

[0209] Green light duration (g) b The estimation method is as follows:

[0210]

[0211] δ3 is the preset single-step increment / decrement duration, set to 3 seconds by default;

[0212] f now A value ≥1 indicates that the queue length in a single signal cycle is insufficient to clear the vehicles, resulting in secondary queuing; the green light duration should be increased. now A value ≤0.2 indicates that the green light duration per single signal cycle is sufficient, and the green light duration should be reduced.

[0213] Step 57, based on the green light duration g a g b Estimate the corresponding green light duration

[0214] Among them, green light duration The estimation method is as follows:

[0215]

[0216] Step 58, based on the obtained green light durations This forms the corresponding estimation dataset.

[0217] Step 6: Correct the estimated dataset based on the preset green light duration range for each turn;

[0218] Specifically, this includes: Step 61, estimating the duration of each green light in the dataset. As the current duration g * ;

[0219] Step 62, set the current duration g * The corresponding traffic flow direction is taken as the current direction; and the green light duration g corresponding to the current direction in the signal timing scheme executed in the current signal cycle is used. i,j Let g0 be the value of the green light; and let the lower limit and upper limit of the preset green light duration range corresponding to the current turn be the corresponding green light duration g. min Green light duration (g) max ;

[0220] Here, in this embodiment of the invention, a corresponding green light duration range is pre-set for the green light duration of each traffic flow turning;

[0221] Step 63, based on the green light duration g min g max g0 sets the correction boundary

[0222] Among them, the correction boundary Including lower boundary Boundary Lower Limit

[0223] δ4 is the preset increment / decrement duration, with a default setting of 15 seconds;

[0224] Step 64, based on the corrected boundary For the current duration g * The following corrections have been made:

[0225] Step 7: Optimize the timing of the current intersection based on the estimated dataset and the dual-ring configuration relationship to obtain the optimized timing scheme.

[0226] Here, the optimized timing scheme of this invention includes the intersection signal period C' total Left loop signal period C' left Right loop signal period C' right and the duration of multiple turn signals G' i,j Turn signal duration G' i,j Corresponding one-to-one with the direction of traffic flow; G' i,j =g' i,j +y'i,j ;g' i,j y' i,j These are the optimized green light duration and yellow light duration for the current turn, respectively; g' i,j >y' i,j >0; Yellow light duration y' i,j The default setting is 3 seconds.

[0227] The current step 7 specifically includes:

[0228] Step 71, based on the M corresponding to the i-th phase i Green light duration Estimate the corresponding M i The duration of each turn signal and M i The duration of each turn signal The maximum value in the value is used as the corresponding phase signal duration. And the duration of the obtained N phase signals Forming a corresponding set of phase durations;

[0229] in,

[0230] y i,j The duration of the yellow light for the j-th turn in the i-th phase;

[0231] Step 72: Based on the left and right ring barriers, divide the main and secondary rings into two half-rings, denoted as the left main half-ring, right main half-ring, left secondary half-ring, and right secondary half-ring; and denot the phase sets corresponding to each of the four half-rings as the corresponding first, second, third, and fourth phase sets; and denot the phase signal durations in the phase duration sets that correspond to the first, second, third, and fourth phase sets. Extract these values ​​to form corresponding first, second, third, and fourth duration sets; and calculate the total duration of each of the first, second, third, and fourth duration sets.

[0232] Step 73: Identify the preset signal period modulation configuration;

[0233] Among them, the signal period modulation configuration includes non-adjustable period and adjustable period;

[0234] Step 74: If the signal period modulation configuration is set to non-adjustable period, then the left loop signal period C' under the fixed period condition is determined based on the sum of the four durations. left Right loop signal period C' right and intersection signal cycle C' total Configure settings;

[0235] Specifically, this includes step 741, which involves determining the phase signal duration P corresponding to the first, second, third, and fourth phase sets in the signal timing scheme executed during the current signal period. i Extract these values ​​to form the corresponding fifth, sixth, seventh, and eighth duration sets; and calculate the total duration C for each of the fifth, sixth, seventh, and eighth duration sets. l1 C r1 C l2 C r2 ;

[0236] Step 742, based on the sum of the four durations Calculate the four corresponding proportional parameters;

[0237] Among them, the four proportional parameters are a l1 a r1 a l2 a r2 :

[0238]

[0239] Step 743, if a l1 a l2 If ≥1, then a l1 a l2 The sum of the durations corresponding to the maximum values ​​in the range is used as the estimation period. If a l1 a l2 If ≤1, then a l1 a l2 The sum of the durations corresponding to the minimum values ​​in the range is used as the estimation period. If a l1 <1<a l2 or a l2 <1<a l1 Then a l1 a l2 The average of the two corresponding durations is used as the estimation period.

[0240] Here, if a l1 a l2 ≥1 indicates that the trend of change in the main and secondary half-rings within the left half-ring region (the left side of the left and right ring barriers) is towards increasing the green light duration. If a l1 a l2 ≤1 indicates that the main and secondary semi-rings in the left barrier region are both trending towards reducing green light duration. In both cases, the sum of durations with the largest change ratio is selected as the estimation period. If a l1 <1<a l2 or a l2<1<a l1 This indicates that the main and secondary semicircles in the left barrier region have opposite trends. In this case, the average of the sum of the two durations is used as the estimated period.

[0241] Step 744, if a r1 a r2 If ≥1, then a r1 a r2 The sum of the durations corresponding to the maximum values ​​in the range is used as the estimation period. If a r1 a r2 If ≤1, then a r1 a r2 The sum of the durations corresponding to the minimum values ​​in the range is used as the estimation period. If a r1 <1<a r2 or a r2 <1<a r1 Then a r1 a r2 The average of the two corresponding durations is used as the estimation period.

[0242] Here, if a r1 a r2 ≥1 indicates that the main and secondary half-rings in the right half-ring region (the right side of the left and right ring barriers) are changing in the direction of increasing the green light duration. If a r1 a r2 ≤1 indicates that the main and secondary semi-rings in the right barrier region are both trending towards reducing green light duration. In both cases, the sum of durations with the largest change ratio is selected as the estimation period. If a r1 <1<a r2 or a r2 <1<a r1 This indicates that the main and secondary semicircles in the right barrier region have opposite trends. In this case, the average of the sum of the two durations is used as the estimated period.

[0243] Step 745, based on the estimated period and the intersection signal cycle C of the current signal cycle total Set the left loop signal period C' left Right loop signal period C' right ;

[0244]

[0245] Step 746, change the intersection signal cycle C total As the intersection signal cycle C t 'otal ;

[0246] Step 75: If the signal period modulation is configured to be periodically adjustable, then the sum of the durations corresponding to the left and right main half-loops is used. Set the left loop signal period C' left Right loop signal period C' right And calculate the corresponding intersection signal cycle C based on the setting results. t ' otal ;

[0247] in, C' total =C' left +C' right ;

[0248] Step 76, based on the left loop signal period C' left The total duration corresponding to the left main half-ring And estimate the green light duration corresponding to each phase turn of the left main half-loop in the dataset. Calculate the corresponding green light duration g' i,j ; and based on the right loop signal period C' right The total duration corresponding to the right main half-ring And estimate the green light duration corresponding to each phase turn of the right main half-loop in the dataset. Calculate the corresponding green light duration g' i,j ; and based on the left loop signal period C' left The total duration corresponding to the left second half ring And estimate the green light duration corresponding to each phase turn of the left secondary half-ring in the dataset. Calculate the corresponding green light duration g' i,j ; and based on the right loop signal period C' right The total duration of the right second half ring And estimate the green light duration corresponding to each phase turn of the right secondary half-ring in the dataset. Calculate the corresponding green light duration g' i,j ;

[0249] Here, in this embodiment of the invention, the green light duration g' corresponding to each phase turn within the left main half-ring is as follows: i,j for:

[0250]

[0251] In this embodiment of the invention, the green light duration g' corresponding to each phase turn within the right main half-ring i,j for:

[0252]

[0253] In this embodiment of the invention, the green light duration g' corresponding to each phase turn within the left secondary half-ring i,j for:

[0254]

[0255] In this embodiment of the invention, the green light duration g' corresponding to each phase turn within the right secondary half-ring i,j for:

[0256]

[0257] Step 77: Set the duration y of each yellow light in the signal timing scheme executed in the current signal cycle. i,j The corresponding yellow light duration y' i,j ; and determined by the duration of each green light g' i,j and its corresponding yellow light duration y' i,j Calculate the corresponding turn signal duration G' i,j G' i,j =g' i,j +y' i,j ;

[0258] Step 78, from the obtained intersection signal period C' total Left loop signal period C' left Right loop signal period C' ri ght and duration of all turn signals G' i,j To form a corresponding optimized timing scheme.

[0259] Step 8: Save the signal timing scheme executed in the current signal cycle as a historical scheme; and use the start time of the next signal cycle as the optimization time t. opt Based on the optimization time t opt and the preset observation duration L obs Set two observation times t obs1 t obs2 ; and at this optimization time t opt Timing is based on an optimized timing scheme.

[0260] Among them, t obs1 =t opt +L obs , t obs2 =t obs1 +L obs .

[0261] The observation duration L in this embodiment of the invention obs This is a preset time length, with the default value being 5 minutes.

[0262] Step 9, at the subsequent observation time t obs1 tobs2 The system identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic congestion based on the identification results; if traffic congestion is confirmed, then at observation time t... obs2 The timing will be switched back to the historical scheme in the next signal cycle.

[0263] Among them, at the subsequent observation time t obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and, based on the identification results, confirms whether the optimization has caused traffic congestion. Specifically, this includes:

[0264] At observation time t obs1 Above, set the first time period as [t] opt -L obs ,t opt The second time period is [t] opt ,t obs1 The system obtains the delay durations of all signal cycles within the first and second time periods for each turn via an internet data interface, forming the corresponding first and second sets. It also obtains the queue lengths of all signal cycles within the first and second time periods for each turn, forming the corresponding third and fourth sets. Finally, it calculates the corresponding delay duration dispersion coefficients based on the first and second sets for each turn. The corresponding queue length discrepancy coefficients are calculated based on the third and fourth sets for each turning direction. And the dispersion coefficient of delay time for each turn. and queue length dispersion coefficient Perform identification; if and Then set the corresponding first steering observation result as deterioration; if or Then the corresponding first steering observation result is set to non-deterioration; where the first steering observation result includes deterioration and non-deterioration;

[0265] At observation time t obs2 Above, set the third time period as [t] obs1 ,t obs2 The system obtains the delay duration of all signal cycles within the third time period of each turn through the internet data interface to form a fifth set, and obtains the queue length of all signal cycles within the third time period of each turn to form a sixth set; and calculates the corresponding delay duration dispersion coefficient based on the fifth set for each turn. And calculate the corresponding queue length discrepancy coefficient based on the sixth set of each turning point. And the dispersion coefficient of delay time for each turn. and queue length dispersion coefficient Perform identification; if and Then set the corresponding second steering observation result as deterioration; if or The corresponding second steering observation result is set to non-deterioration; and the first and second steering observation results for all steerings are identified as deterioration; if not, it is confirmed that traffic has not yet deteriorated; if so, it is confirmed that traffic has deteriorated; wherein, the second observation result includes deterioration and non-deterioration.

[0266] Figure 3 This is a module structure diagram of a processing device for traffic signal timing at a single intersection, provided in Embodiment 2 of the present invention. This device can be a terminal device or server implementing the aforementioned method embodiments, or it can be a device that enables the aforementioned terminal device or server to implement the aforementioned method embodiments. For example, the device can be a device or chip system of the aforementioned terminal device or server. Figure 3 As shown, the processing device for traffic signal timing at a single intersection provided in Embodiment 2 of the present invention includes: an intersection confirmation module 201, a traffic data acquisition module 202, a traffic data preprocessing module 203, a traffic data prediction module 204, a green light duration estimation module 205, an estimation data correction module 206, a timing scheme optimization module 207, a timing optimization module 208, and an optimization evaluation module 209.

[0267] The intersection confirmation module 201 is used to identify each single-point intersection as the current intersection; the current intersection includes N signal phases, where the total number of phases N is a positive integer greater than 1; the i-th phase includes M... i Traffic flow turns, total number of turns M i The value is a positive integer, 1 ≤ phase index i ≤ N; the phase signal duration configuration relationship at the current intersection follows a double-ring configuration relationship.

[0268] The traffic data acquisition module 202 is used to periodically acquire the delay time, queue length and number of stops of all traffic flows turning at the current intersection in the most recent K signal cycles through the Internet data interface to form a corresponding traffic dataset; the total number of cycles K is a positive integer greater than 1.

[0269] The traffic data preprocessing module 203 is used to preprocess the traffic dataset.

[0270] The traffic data prediction module 204 predicts the delay time, queue length and number of stops for all future turning signal cycles based on the traffic dataset, thus obtaining the corresponding prediction dataset.

[0271] The green light duration estimation module 205 estimates the turning green light duration based on the predicted dataset to obtain the corresponding estimated dataset.

[0272] The estimated data correction module 206 corrects the estimated dataset based on the preset green light duration range for each turn.

[0273] The timing scheme optimization module 207 optimizes the timing of the current intersection based on the estimated dataset and the dual-ring configuration relationship to obtain an optimized timing scheme.

[0274] The timing optimization module 208 is used to save the signal timing scheme executed in the current signal cycle as a historical scheme; and to use the start time of the next signal cycle as the current optimization time t. opt Based on the optimization time t opt and the preset observation duration L obs Set two observation times t obs1 t obs2 ; and at this optimization time t opt Timing is based on an optimized timing scheme; t obs1 =t opt +L obs , t obs2 =t obs1 +L obs .

[0275] The optimization evaluation module 209 is used for subsequent observation time t. obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic congestion based on the identification results; if traffic congestion is confirmed, then at observation time t... obs2 The timing will be switched back to the historical scheme in the next signal cycle.

[0276] The present invention provides a processing device for traffic signal timing at a single intersection, which can execute the method steps in the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0277] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, the traffic data acquisition module can be a separate processing element, or it can be integrated into a chip within the above device. Alternatively, it can be stored as program code in the device's memory, and called and executed by a processing element. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0278] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-on-a-Chip (SOC).

[0279] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the foregoing method embodiments are generated. The computer described above can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The aforementioned computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the aforementioned computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, Bluetooth, microwave, etc.) means. The aforementioned computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0280] Figure 4 This is a schematic diagram of an electronic device provided in Embodiment 3 of the present invention. This electronic device can be a terminal device or server implementing the methods of the aforementioned embodiments, or it can be a terminal device or server connected to the aforementioned terminal device or server implementing the methods of the aforementioned embodiments. Figure 4 As shown, the electronic device may include: a processor 301 (e.g., CPU), a memory 302, and a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transmission and reception operations of the transceiver 303. The memory 302 may store various instructions for performing various processing functions and implementing the processing steps described in the foregoing embodiments. Preferably, the electronic device involved in the embodiments of the present invention further includes: a power supply 304, a system bus 305, and a communication port 306. The system bus 305 is used to realize communication connections between components. The communication port 306 is used for communication between the electronic device and other peripherals.

[0281] exist Figure 4The system bus 305 mentioned can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, it is represented by only one thick line in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0282] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), graphics processing units (GPUs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0283] It should be noted that the embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when run on a computer, cause the computer to perform the methods and processes provided in the above embodiments.

[0284] This invention provides a method, apparatus, electronic device, and computer-readable storage medium for processing traffic signal timing at a single-point intersection. The invention periodically acquires a traffic dataset from the delay duration, queue length, and number of stops for all traffic flows turning at a single-point intersection over the most recent signal cycles via an internet data interface, and preprocesses this dataset. Then, based on the preprocessed traffic dataset, it predicts the delay duration, queue length, and number of stops for all turns in future signal cycles. Next, it estimates the green light duration for all turns based on the predicted dataset and corrects the estimated dataset. Then, it optimizes the timing based on the estimated dataset and the current double-ring configuration of the intersection. Finally, it saves the signal timing scheme executed in the current signal cycle as a historical scheme and performs timing based on the optimized scheme. Then, at the next two observation times, it identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic deterioration based on the identification results. If it confirms that traffic deterioration has occurred, it switches back to the historical scheme for timing in the next signal cycle. This invention presents a traffic signal timing optimization scheme based on Internet data sources. Based on this invention, the traffic signal timing of all single-point intersections in the real road network can be adaptively optimized, effectively reducing the cost of intelligent traffic management.

[0285] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0286] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A processing method for traffic signal timing at a single-point intersection, characterized in that, The method includes: Each single-point intersection is designated as the current intersection; the current intersection includes N signal phases, where the total number of phases N is a positive integer greater than 1; the i-th phase includes M... i Traffic flow turns, total number of turns M i The value is a positive integer, 1 ≤ phase index i ≤ N; the phase signal duration configuration relationship of the current intersection follows a double-ring configuration relationship; The traffic dataset is formed by periodically obtaining the delay time, queue length and number of stops of all traffic flows turning at the current intersection in the most recent K signal cycles through the Internet data interface; the total number of cycles K is a positive integer greater than 1. The traffic dataset is preprocessed; Based on the traffic dataset, the delay time, queue length and number of stops for all future turning signal cycles are predicted to obtain the corresponding prediction dataset; Based on the predicted dataset, the green light duration for turning is estimated to obtain the corresponding estimated dataset; The estimated dataset is corrected based on the preset green light duration range for each turn; Based on the estimated dataset and the dual-ring configuration relationship, the timing of the current intersection is optimized to obtain an optimized timing scheme; Save the signal timing scheme executed in the current signal cycle as a historical scheme; and use the start time of the next signal cycle as the optimization time t. opt Based on the current optimization time t opt and the preset observation duration L obs Set two observation times t obs1 t obs2 ; and at the current optimization time t opt Timing is performed based on the optimized timing scheme described above; t obs1 =t opt +L obs , t obs2 =t obs1 +L obs ; At the subsequent observation time t obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic congestion based on the identification results; if traffic congestion is confirmed, then at observation time t... obs2 The next signal cycle will then switch back to the historical scheme for timing. Wherein, the duration of the steering signal for the j-th steering in the i-th phase is denoted as G. i,j G i,j =g i,j +y i,j ; 1 ≤ turning index j ≤ M i g i,j y i,j These represent the green light duration and yellow light duration for the current turn, respectively; g i,j >y i,j >0; Yellow light duration y i,j The default setting is 3 seconds; The duration of the phase signal of the i-th phase is denoted as P. i P i =max(G i,j ); The dual-ring configuration includes a primary ring and a secondary ring; the primary and secondary rings are each composed of multiple phase signal durations P. i The signals are ordered sequentially; the total duration of the main and secondary loops is equal, denoted as the intersection signal cycle C. total The intersection signal period C total The left and right rings are divided into two semi-ring periods, denoted as the left ring signal period C. left Right loop signal period C right ; The traffic dataset includes multiple data sequences X i,j The data sequence X i,j The data sequence X corresponds one-to-one with the traffic flow direction; i,j Given K traffic data x i,j,k Composition, 1 ≤ periodic index k ≤ K; the traffic data x i,j,k Including delay duration e i,j,k Queue length l i,j,k Number of stops (s) i,j,k Confidence level c i,j,k The confidence level c i,j,k The value of is between 0 and 1; The prediction dataset includes multiple traffic prediction data. The predicted traffic data The predicted traffic data corresponds one-to-one with the traffic flow direction. Including predicted delay duration Predicting queue length Predicting the number of parking times ; The estimation dataset includes multiple estimated green light durations. The estimated green light duration Each corresponds one-to-one with the traffic flow direction; The optimized timing scheme includes intersection signal cycles. Left loop signal period Right loop signal period and duration of multiple turn signals The duration of the steering signal Each corresponds one-to-one with the traffic flow direction; = + ; , These are the optimized green light duration and yellow light duration for the current turn; > >0; Yellow light duration The default setting is 3 seconds.

2. The processing method for traffic signal timing at a single intersection according to claim 1, characterized in that, The preprocessing of the traffic dataset specifically includes: Step 31, divide the traffic dataset into its constituent data sequences X. i,j As the current sequence; Step 32: Filter the current sequence for low-confidence data based on a preset confidence threshold, specifically as follows: The confidence scores c of all sequences in the current sequence that are less than the confidence threshold are... i,j,k Set all to 0; Step 33: Set queue length correction rules based on traffic data relationship method; The queue length correction rule is as follows: ， ； g i,j For the green light duration of the j-th turn in the i-th phase of the signal timing scheme executed in the current signal cycle, O i,j Let d be the saturation flow rate of the i-th phase and the j-th turn, and d be the queuing headway. Step 34: Correct the queue length of the current sequence based on the queue length correction rule, specifically as follows: Each confidence level c in the current sequence i,j,k The traffic data x that is not zero i,j,k As the corresponding current data; and the queue length l of the current data. i,j,k The number of stops s i,j,k The current queue length and the current number of stops are used as the basis for determining whether the current queue length needs to be corrected based on the current number of stops and the queue length correction rule. If it is determined that correction is needed, the current queue length is corrected according to the correction method corresponding to the current number of stops in the queue length correction rule. Step 35: Filter traffic data with abnormal queue lengths or delay times in the current sequence based on the standard deviation method, specifically as follows: All the confidence levels c in the current sequence i,j,k The traffic data x that is not zero i,k All are recorded as data samples; and the delay duration e of all said data samples is... i,j,k The average value µ e and standard deviation σ e Perform calculations; and calculate the queue length l for all said data samples. i,j,k The average value µ l and standard deviation σ l Perform calculations; and based on the average value µ e and the standard deviation σ e Set the delay duration range to [|µ e -σ e |,|µ e +σ e |]; and based on the average value µ l and the standard deviation σ l Set the queue length range to [|µ l -σ l |,|µ l +σ l |]; and the delay duration e i,j,k The delay time interval or the queue length l is not satisfied. i,j,k Data samples that do not meet the specified queue length range are recorded as anomalous samples; and the confidence level c of all anomalous samples is... i,j,k Set to 0.

3. The processing method for traffic signal timing at a single intersection according to claim 2, characterized in that, The queue length correction rule based on traffic data relationship method specifically includes: Step 41, confirm the known prior conditions: ； Where n1 and n0 are the number of stops s i,j,k The total number of vehicles in the queue and the total number of vehicles not in the queue for the corresponding i-th phase and j-th turn; Step 42, by We can obtain: ; Step 43, Substitute the prior conditions We can obtain: ； Step 44, convert the prior conditions into: ； Step 45: The product of the distance between the front of the queued vehicles (d) and the total number of vehicles in the queue (n1) is taken as the corresponding queue length (l). i,j,k =n1×d, then the prior condition is transformed into: ； Step 46, setting boundaries based on the prior conditions, specifically: ， ； Step 47, based on the boundary settings, set the queue length correction rule as follows: ， 。 4. The processing method for traffic signal timing at a single intersection according to claim 1, characterized in that, The process of predicting the delay duration, queue length, and number of stops for all future turning signal cycles based on the traffic dataset to obtain the corresponding prediction dataset specifically includes: The traffic dataset contains various data sequences X. i,j As the current sequence; and the confidence level c in the current sequence i,j,k The traffic data x that is not zero i,k Extract the data to form a corresponding valid data sequence; and combine all the delay durations e in the valid data sequence. i,j,k All queue lengths l i,j,k All the number of stops mentioned in s i,j,k The delay duration sequence, queue length sequence, and number of stops sequence are extracted to form corresponding delay duration sequences, queue length sequences, and number of stops sequences. Then, using a quadratic exponential smoothing method, the delay duration, queue length, and number of stops for a specified future signal period are predicted based on these sequences to obtain the predicted delay duration. The predicted queue length The predicted number of parking times ; and the predicted delay duration corresponding to the current sequence. The predicted queue length The predicted number of parking times The corresponding predicted traffic data constitutes the data. ; and from all the predicted traffic data obtained The corresponding prediction dataset is then formed.

5. The processing method for traffic signal timing at a single intersection according to claim 1, characterized in that, The step of estimating the green light duration based on the predicted dataset to obtain the corresponding estimated dataset specifically includes: Step 61, combine the predicted traffic data from the predicted dataset. As current forecast data; Step 62, the prediction delay time of the current prediction data. The predicted queue length The predicted number of parking times Let e ​​be the corresponding e now l now s now ; Step 63: The green light duration g of the i-th phase and j-th turn in the signal timing scheme executed in the current signal cycle is... i,j The duration of the yellow light, y i,j Let g be the corresponding g now y now Based on the intersection signal period C total Calculate the red light duration r for the i-th phase and j-th turn. now ; in, ; Step 64, adjust the saturation flow rate O of the i-th phase and j-th direction. i,j Denote as O now ; and based on saturation flow rate O now Calculate the corresponding saturated headway H now ; in, ; Step 65, based on the queue length l now The number of stops s now The queuing headway d is used to estimate the turning traffic flow q in a single cycle. * ; and based on the turning traffic flow q * and the saturated headway H now Estimate the corresponding green light duration g a Based on the green light duration g now Set the green light duration g a The boundary constraints; and the green light duration g based on the boundary constraints. a Make corrections; in, The turning traffic flow q * The estimation method is as follows: ; The green light duration g a The estimation method is as follows: ; The boundary restrictions are as follows: ; The green light duration g a The correction rule is: If g a <g now -δ2, then correct g a =g now -δ2; If g a >g now +δ2, then modify g a =g now +δ2; δ1 is the preset loss duration, which is set to 3 seconds by default; δ2 is the preset duration optimization range, which is set to 5 seconds by default. Step 66, based on the delay duration e now and the red light duration r now Estimating the delay index f now ; and based on the delay index f now and the green light duration g now Estimate the corresponding green light duration g b ; in, The delay index f now The estimation method is as follows: ; The green light duration g b The estimation method is as follows: ； δ3 is the preset single-step increment / decrement duration, set to 3 seconds by default; f now A value ≥1 indicates that the queue length in a single signal cycle is insufficient to clear the vehicles, resulting in secondary queuing; the green light duration should be increased. now A value ≤0.2 indicates that the green light duration per single signal cycle is sufficient, and the green light duration should be reduced. Step 67, based on the green light duration g a g b Estimate the corresponding green light duration ; Among them, the green light duration The estimation method is as follows: ； Step 68, based on all the obtained green light durations The corresponding estimation dataset is then constructed.

6. The processing method for traffic signal timing at a single intersection according to claim 1, characterized in that, The process of correcting the estimated dataset based on the preset green light duration range for each turn specifically includes: Step 71, calculate the green light duration of each item in the estimated dataset. As the current duration g * ; Step 72, set the current duration g * The corresponding traffic flow direction is taken as the current direction; and the green light duration g corresponding to the current direction in the signal timing scheme executed in the current signal cycle is taken as the current direction. i,j Let g0 be the value of the green light duration; and let the lower limit and upper limit of the preset green light duration range corresponding to the current turn be the corresponding green light duration g. min Green light duration (g) max ; Step 73, based on the green light duration g min g max g0 sets the correction boundary[ , ]; Wherein, the correction boundary [ , Including lower boundary Lower boundary ; ， ; δ4 is the preset increment / decrement duration, with a default setting of 15 seconds; Step 74, based on the corrected boundary [ , [Regarding the current duration g] * The following corrections have been made: .

7. The processing method for traffic signal timing at a single intersection according to claim 1, characterized in that, The optimized timing scheme for the current intersection, based on the estimated dataset and the dual-ring configuration relationship, specifically includes: Step 81, based on the M corresponding to the i-th phase i The green light duration mentioned above Estimate the corresponding M i The duration of each turn signal and M i The duration of the aforementioned turn signal The maximum value in the value is used as the corresponding phase signal duration. ; and the duration of the N phase signals obtained Form a corresponding set of phase durations; in, ; ; y i,j The duration of the yellow light for the j-th turn in the i-th phase; Step 82: Based on the left and right ring barriers, the main and secondary rings are divided into left and right half-rings, denoted as the corresponding left main half-ring, right main half-ring, left secondary half-ring, and right secondary half-ring; and the phase sets corresponding to each of the four half-rings are denoted as the corresponding first, second, third, and fourth phase sets; and the phase signal durations corresponding to the first, second, third, and fourth phase sets in the phase duration sets are... The extracted data forms the corresponding first, second, third, and fourth duration sets; and the total duration of each of the first, second, third, and fourth duration sets is calculated to obtain the corresponding total duration. , , , ; Step 83: Identify the preset signal period modulation configuration; The signal period modulation configuration includes a non-adjustable period and an adjustable period. Step 84: If the signal period modulation configuration is set to have a non-adjustable period, then the left loop signal period under the fixed period condition is determined based on the sum of four durations. The right loop signal period and the intersection signal period Configure settings; Step 85: If the signal period modulation configuration is periodically adjustable, then the sum of the durations corresponding to the left and right main half-loops is used. , Set the left loop signal period The right loop signal period And calculate the corresponding intersection signal cycle based on the setting results. ; in, , , ; Step 86, based on the left loop signal period The total duration corresponding to the left main half-loop And the green light duration corresponding to each phase turn of the left main half-loop in the estimated dataset. Calculate the corresponding green light duration Based on the right loop signal period The total duration corresponding to the right main half-loop And the green light duration corresponding to each phase turn of the right main half-loop in the estimated dataset. Calculate the corresponding green light duration Based on the left loop signal period The total duration corresponding to the left second half ring And the green light duration corresponding to each phase turn of the left secondary half-ring in the estimated dataset. Calculate the corresponding green light duration Based on the right loop signal period The total duration of the right secondary half-loop And the green light duration corresponding to each phase turn of the right secondary half-ring in the estimated dataset. Calculate the corresponding green light duration ; The green light duration corresponding to each phase turn within the left main half-ring. for: ； The green light duration corresponding to each phase turn within the right main half-ring for: ； The green light duration corresponding to each phase turn within the left secondary half-ring for: ； The green light duration corresponding to each phase turn within the right secondary half-ring for: ； Step 87: The duration y of each yellow light in the signal timing scheme executed in the current signal cycle is... i,j The corresponding yellow light duration ; and determined by the green light duration of each of the aforementioned green lights. and the corresponding yellow light duration Calculate the corresponding turn signal duration , = + ; Step 88, based on the obtained intersection signal period The left loop signal period The right loop signal period and the duration of all stated turn signals The corresponding optimized timing scheme is then formed.

8. The processing method for traffic signal timing at a single intersection according to claim 7, characterized in that, The left loop signal period under fixed period conditions is based on the sum of four durations. The right loop signal period and the intersection signal period The settings include: Step 91: The phase signal duration P corresponding to the first, second, third, and fourth phase sets in the signal timing scheme executed in the current signal period is... i Extract these values ​​to form the corresponding fifth, sixth, seventh, and eighth duration sets; and calculate the total duration C for each of the fifth, sixth, seventh, and eighth duration sets. l1 C r1 C l2 C r2 ; Step 92, based on the sum of the four durations ( C l1 ), ( C r1 ), ( C l2 ), ( C r2 Calculate the four corresponding proportional parameters; Among them, the four proportional parameters are a l1 a r1 a l2 a r2 : ， ， ， ； Step 93, if a l1 a l2 If ≥1, then a l1 a l2 The sum of the durations corresponding to the maximum values ​​in the range is used as the estimation period. If a l1 a l2 If ≤1, then a l1 a l2 The sum of the durations corresponding to the minimum values ​​in the range is used as the estimation period. If a l1 <1<a l2 or a l2 <1<a l1 Then a l1 a l2 The average of the sums of the two corresponding durations is used as the estimated period. ; Step 94, if a r1 a r2 If ≥1, then a r1 a r2 The sum of the durations corresponding to the maximum values ​​in the range is used as the estimation period. If a r1 a r2 If ≤1, then a r1 a r2 The sum of the durations corresponding to the minimum values ​​in the range is used as the estimation period. If a r1 <1<a r2 or a r2 <1<a r1 Then a r1 a r2 The average of the sums of the two corresponding durations is used as the estimated period. ; Step 95, based on the estimated period , and the intersection signal period C of the current signal period total Set the left loop signal period The right loop signal period ; in, , ; Step 96, set the intersection signal period C total As the intersection signal period .

9. The processing method for traffic signal timing at a single intersection according to claim 1, characterized in that, The following is mentioned at the subsequent observation time t obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and, based on the identification results, confirms whether the optimization has caused traffic congestion. Specifically, this includes: Step 101, at the observation time t obs1 Above, set the first time period as [t] opt -L obs ,t opt The second time period is [t] opt ,t obs1 The system obtains the delay durations of all signal cycles within the first and second time periods of each turn through the internet data interface to form corresponding first and second sets, and obtains the queue lengths of all signal cycles within the first and second time periods of each turn to form corresponding third and fourth sets; and calculates the corresponding delay duration dispersion coefficients based on the first and second sets of each turn. , And calculate the corresponding queue length discrepancy coefficients based on the third and fourth sets for each turning point. , ; and the discrete coefficient of the delay time for each turn. , and the queuing length discrete coefficient , Perform identification; if < and < If so, then the corresponding first steering observation result is set to deterioration; if ≥ or ≥ If so, then the corresponding first steering observation result is set to non-deterioration; The first steering observation results include deterioration and non-deterioration; Step 102, at the observation time t obs2 Above, set the third time period as [t] obs1 ,t obs2 The system obtains the delay duration of all signal cycles within the third time period for each turn through the internet data interface to form a fifth set, and obtains the queue length of all signal cycles within the third time period for each turn to form a sixth set; and calculates the corresponding delay duration dispersion coefficient based on the fifth set for each turn. And based on the sixth set for each turn, calculate the corresponding queue length discrepancy coefficient. ; and the discrete coefficient of the delay time for each turn. , and the queuing length discrete coefficient , Perform identification; if < and < If so, then the corresponding second steering observation result is set to deterioration; if ≥ or ≥ If the second steering observation result is not worsened, then the corresponding second steering observation result is set to non-worsening; and the first and second steering observation results for all steerings are identified as worsening; if not, then it is confirmed that traffic has not yet worsened; if so, then it is confirmed that traffic has worsened. The second turning observation result includes deterioration and non-deterioration.

10. An apparatus for performing the processing method for traffic signal timing at a single intersection as described in any one of claims 1-9, characterized in that, The device includes: an intersection confirmation module, a traffic data acquisition module, a traffic data preprocessing module, a traffic data prediction module, a green light duration estimation module, an estimated data correction module, a timing scheme optimization module, a timing optimization module, and an optimization evaluation module; The intersection confirmation module is used to identify each single-point intersection as the current intersection; the current intersection includes N signal phases, where the total number of phases N is a positive integer greater than 1; the i-th phase includes M... i Traffic flow turns, total number of turns M i The value is a positive integer, 1 ≤ phase index i ≤ N; the phase signal duration configuration relationship of the current intersection follows a double-ring configuration relationship; The traffic data acquisition module is used to periodically acquire, via an Internet data interface, the delay time, queue length, and number of stops of all traffic flows turning at the current intersection over the most recent K signal cycles to form a corresponding traffic dataset; the total number of cycles K is a positive integer greater than 1; The traffic data preprocessing module is used to preprocess the traffic dataset; The traffic data prediction module predicts the delay time, queue length, and number of stops for all future turning signal cycles based on the traffic dataset to obtain the corresponding prediction dataset. The green light duration estimation module estimates the turning green light duration based on the predicted dataset to obtain the corresponding estimated dataset. The estimated data correction module corrects the estimated dataset based on the preset green light duration range for each turn; The timing scheme optimization module performs timing optimization on the current intersection based on the estimated dataset and the dual-ring configuration relationship to obtain an optimized timing scheme; The timing optimization module is used to save the signal timing scheme executed in the current signal cycle as a historical scheme; and to use the start time of the next signal cycle as the current optimization time t. opt Based on the current optimization time t opt and the preset observation duration L obs Set two observation times t obs1 t obs2 ; and at the current optimization time t opt Timing is performed based on the optimized timing scheme described above; t obs1 =t opt +L obs , t obs2 =t obs1 +L obs ; The optimization evaluation module is used to evaluate the results at subsequent observation times t. obs1 t obs2 The system identifies the queue length and delay index dispersion coefficient for each turn and confirms whether the optimization has caused traffic congestion based on the identification results; if traffic congestion is confirmed, then at observation time t... obs2 The next signal cycle will then switch back to the historical scheme for timing.

11. An electronic device, characterized in that, include: Memory, processor, and transceiver; The processor is configured to be coupled to the memory, read and execute instructions in the memory to implement the method according to any one of claims 1-9; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a computer, cause the computer to perform the method described in any one of claims 1-9.

Images