Intersection signal control strategy evaluation method and device, electronic equipment and storage medium

Abstract

The invention discloses an intersection signal control strategy evaluation method and device, electronic equipment and a storage medium, and relates to the field of computers, in particular to the field of artificial intelligence such as deep learning and intelligent traffic. According to the specific implementation scheme, the method comprises the steps of determining traffic performance index data of a target intersection in each flow direction according to target flow data of the target intersection in a target time period and a to-be-evaluated signal control strategy; wherein the target flow data comprises the flow direction flow of each flow direction; performing feature extraction on the flow direction flow and the traffic performance index data to obtain a first flow feature and a flow direction traffic feature; obtaining the flow direction delay time of the flow direction according to the first flow characteristic and the flow direction traffic characteristic; determining the intersection delay time of the target intersection according to the flow direction delay time of each flow direction; and evaluating the to-be-evaluated signal control strategy according to the intersection delay time.

Description

Technical Field

[0001] The present application relates to the field of computer technology, in particular to artificial intelligence fields such as deep learning and intelligent transportation, and specifically to a method, device, electronic device and storage medium for evaluating intersection signal control strategies. Background Art

[0002] In the field of traffic signal control, in order to avoid wasting resources and time on inappropriate signal control strategies and reduce the negative impact caused by the implementation of inappropriate signal control strategies, a priori evaluation of signal control strategies can be performed. Summary of the invention

[0003] The present application provides a method, device, electronic device and storage medium for evaluating a signal control strategy at an intersection.

[0004] According to one aspect of the present application, a method for evaluating a traffic signal control strategy at an intersection is provided, comprising:

[0005] Determine the traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated; wherein the target flow data includes the flow volume of each flow direction;

[0006] Extracting features from the flow direction flow and the traffic performance index data respectively to obtain a first flow feature and a flow direction traffic feature;

[0007] Obtaining a flow delay time of the flow direction according to the first flow characteristic and the flow direction traffic characteristic;

[0008] Determining the intersection delay time of the target intersection according to the flow delay time of each flow direction;

[0009] The signal control strategy to be evaluated is evaluated according to the intersection delay time.

[0010] According to another aspect of the present application, a device for evaluating a road intersection signal control strategy is provided, comprising:

[0011] A first acquisition module is used to acquire traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated; wherein the target flow data includes the flow flow of each flow direction;

[0012] A feature extraction module, used to extract features from the flow direction flow and the traffic performance index data respectively to obtain a first flow feature and a flow direction traffic feature;

[0013] A second acquisition module, configured to obtain a flow delay time of the flow direction according to the first flow characteristics and the flow direction traffic characteristics;

[0014] A first determining module, configured to determine an intersection delay time of the target intersection according to the flow delay time of each flow direction;

[0015] An evaluation module is used to evaluate the signal control strategy to be evaluated according to the intersection delay time.

[0016] According to another aspect of the present application, there is provided an electronic device, including:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor so that the at least one processor can perform the method described in the above embodiment.

[0020] According to another aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method according to the above embodiment.

[0021] According to another aspect of the present application, a computer program product is provided, including a computer program, wherein the computer program implements the steps of the method described in the above embodiment when executed by a processor.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present application.

[0024] Figure 1 A schematic diagram of a flow chart of a method for evaluating a signal control strategy for an intersection provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of a flow chart of a method for evaluating a signal control strategy for an intersection provided by another embodiment of the present application;

[0026] Figure 3 An illustration of the path through which traffic is provided for this application;

[0027] Figure 4A schematic diagram of a flow chart of a method for evaluating a signal control strategy for an intersection provided by another embodiment of the present application;

[0028] Figure 5 An intention of a deep learning-based intersection signal control strategy evaluation process provided in an embodiment of the present application;

[0029] Figure 6 A schematic diagram of the structure of a delay prediction model provided for this application;

[0030] Figure 7 A schematic diagram of the structure of a device for evaluating a signal control strategy at an intersection provided in one embodiment of the present application;

[0031] Figure 8 It is a block diagram of an electronic device used to implement the intersection signal control strategy evaluation method of an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0033] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations and do not violate public order and good morals.

[0034] The following describes the intersection signal control strategy evaluation method, device, electronic device and storage medium of the embodiments of the present application with reference to the accompanying drawings.

[0035] In some embodiments, traffic simulation software is usually used to establish a simulation model, in which a signal control strategy is issued to simulate its operating effect under specified traffic conditions, and the intersection delay time of each intersection is recorded. The intersection delay time is used to evaluate the signal control strategy.

[0036] However, there are often significant differences between the idealized simulation environment and the complex and changeable real traffic conditions, which will affect the accuracy of the evaluation results.

[0037] Based on this, an embodiment of the present application provides a method for evaluating intersection signal control strategy.

[0038] Figure 1 A flowchart of a method for evaluating intersection signal control strategy provided in one embodiment of the present application.

[0039] The intersection signal control strategy evaluation method of the embodiment of the present application may be executed by the intersection signal control strategy evaluation device of the embodiment of the present application, and the device may be configured in an electronic device.

[0040] Among them, the electronic device can be any device with computing capabilities, such as a personal computer, a mobile terminal, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and other hardware devices with various operating systems, touch screens and / or display screens.

[0041] like Figure 1 As shown, the intersection signal control strategy evaluation method includes:

[0042] Step 101, determining the traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated.

[0043] Among them, the target flow data can be used to characterize the traffic flow demand and can be specified according to actual needs.

[0044] The target traffic data may include the directional traffic of each direction at the target intersection within the target time period. The flow direction can be used to describe the direction of movement of vehicles on the road. For example, at an intersection, different flow directions such as straight, left turn and right turn can be distinguished. In addition, the directional traffic of a flow direction can be understood as the traffic flow of the flow direction.

[0045] Among them, the signal control strategies to be evaluated may include the intersection cycle, the green light time for each direction of flow, the yellow light time for each direction of flow, the red light time for each direction of flow, whether there is green wave band coordinated control, etc.

[0046] In the present application, for each flow direction of the target intersection, the traffic performance index data of each flow direction can be determined according to the target flow data and the signal control strategy to be evaluated.

[0047] The traffic performance index data may include the index values ​​of the saturation flow rate, saturation, green-to-signal ratio, etc. The saturation flow rate may refer to the maximum flow rate of vehicles in one direction that can continuously pass through the intersection under ideal conditions. The saturation may be the ratio of the actual traffic flow to the saturation flow rate, which may reflect the degree of congestion at the intersection. The higher the saturation, the more congested the intersection. The green-to-signal ratio may refer to the ratio of the green light time to the signal cycle, which may reflect the degree of effective utilization of the green light time.

[0048] For example, the traffic performance index data of each flow direction may be calculated using the number of lanes and channelization characteristics of the intersection, the flow rate of each flow direction, the signal control strategy to be evaluated, etc.

[0049] Step 102, extracting features from the directional flow rate and traffic performance index data respectively to obtain first flow rate features and directional traffic features.

[0050] For example, for each flow direction, one or more residual networks may be used to extract features of the flow direction traffic to obtain a first traffic feature, wherein the first traffic feature may be used to characterize the traffic feature of the flow direction.

[0051] Exemplarily, one or more residual networks may be used to extract features from traffic performance index data to obtain flow traffic features.

[0052] Step 103, obtaining the flow delay time of the flow direction according to the first flow characteristic and the flow direction traffic characteristic.

[0053] In the present application, for each flow direction, the flow delay time of the flow direction can be obtained according to the first flow characteristic and the flow direction traffic characteristic corresponding to the flow direction. For example, the first flow characteristic and the flow direction traffic characteristic can be spliced ​​and decoded to obtain the flow delay time.

[0054] The flow delay time of a flow direction may refer to the average delay time of vehicles in the flow direction.

[0055] Step 104, determining the intersection delay time of the target intersection according to the flow delay time of each flow direction.

[0056] For example, the sum of the flow delay times of each flow direction may be divided by the sum of the number of flows at the target intersection to obtain the intersection delay time of the target intersection. The intersection delay time may refer to the average delay time of vehicles at the target intersection.

[0057] Step 105: Evaluate the signal control strategy to be evaluated according to the intersection delay time.

[0058] In this application, the intersection delay time can be used as an evaluation index of the signal control strategy, and the signal control strategy to be evaluated can be evaluated using the intersection delay time. The longer the intersection delay time is, the worse the control efficiency of the signal control strategy to be evaluated is.

[0059] In addition, the signal control strategy to be evaluated may be one or more. If there are multiple signal control strategies to be evaluated, each signal control strategy to be evaluated may be evaluated separately.

[0060] In the embodiment of the present application, the traffic performance index data of each flow direction of the target intersection is obtained according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated, and the flow flow and traffic performance index data of each flow direction are respectively extracted. Based on the extracted flow characteristics and flow direction traffic characteristics, the flow delay time of the flow direction is obtained, and then the intersection delay time is obtained according to the delay time of each flow direction. The signal control strategy to be evaluated is evaluated using the intersection delay time. Thus, the flow delay time is predicted based on the extracted flow characteristics and flow direction traffic characteristics, which can improve the accuracy of the flow delay time prediction and the intersection delay time prediction, thereby improving the accuracy of the signal control strategy evaluation. In addition, different signal control strategies can be quickly evaluated under a specified flow rate, reducing the difficulty and cost of evaluation.

[0061] Figure 2 A flowchart of a method for evaluating intersection signal control strategy provided in another embodiment of the present application.

[0062] like Figure 2 As shown, the intersection signal control strategy evaluation method includes:

[0063] Step 201, determining the traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated.

[0064] Step 202 , extracting features from the directional flow rate and traffic performance index data respectively to obtain first flow rate features and directional traffic features.

[0065] In the present application, step 201-step 202 can be implemented in any of the embodiments of the present application, so they will not be described in detail.

[0066] Step 203, determining the flow coordination ratio of the path through flow according to the first flow characteristic and the flow direction traffic characteristic.

[0067] In the present application, the target flow data may also include the flow through the path corresponding to each flow direction.

[0068] Since there may be multiple other intersections upstream of the target intersection, a flow direction of the target intersection will correspond to multiple paths, and one of the multiple paths may be a coordinated path, such as a path with a green wave band. Exemplarily, if there is a coordinated path among the multiple paths corresponding to a flow direction, it is considered that the flow direction has a path flow through the coordinated direction, that is, the path flow through the flow direction is non-zero; if there is no coordinated path among the multiple paths corresponding to a flow direction, it means that the flow direction does not have a path flow through the coordinated direction, and the path flow through the flow direction can be considered to be zero.

[0069] for example, Figure 3In the figure, A, B, C, D, E, and F represent intersections. Assuming that the target intersection is intersection C, taking the flow direction from intersection B to intersection C as an example, the paths corresponding to intersection C are E->B->C->D, A->B->C->D, and F->B->C->D. If A->B->C->D is a coordinated path, then the flow direction from intersection B to intersection C has a path flow in a coordinated direction. The path flow can refer to the number of vehicles that go straight from intersection A through intersections B and C in sequence and head to intersection D.

[0070] Due to the influence of actual traffic flow, there may be uncoordinated traffic in the path flow of the coordination direction, that is, there may be delayed vehicles passing through the target intersection. Therefore, in this application, the flow coordination ratio of the path flow can be determined. Among them, the flow coordination ratio can refer to the proportion of the coordinated flow in the path flow to the path flow.

[0071] As a possible implementation method, the first flow feature and the flow direction traffic feature may be fused to obtain a fused feature, and the fused feature may be decoded to obtain a flow coordination ratio.

[0072] Due to the different time periods at the same intersection, the coordinated flow in the path flow may be different. For example, the coordinated flow in the path flow during rush hour is less than that in other time periods. In this regard, as another possible implementation method, the time attribute information of the target time can be determined, and the time attribute information can be feature extracted to obtain the time attribute feature, and the first flow feature, the flow direction traffic feature and the time attribute feature can be fused to obtain the first fused feature, and then the first fused feature can be decoded to obtain the flow coordination ratio.

[0073] Exemplarily, the time attribute information may include but is not limited to date attribute, hour attribute, working day or rest day, etc. For example, the date attribute may refer to the day of the week to which the target time period belongs.

[0074] Exemplarily, the time attribute information may be vectorized to obtain the time attribute features.

[0075] Exemplarily, the first flow feature, the flow direction traffic feature and the time attribute feature may be concatenated to obtain the first fusion feature.

[0076] For example, the traffic coordination ratio can be obtained using the following formula (1):

[0077] h gate =Sigmoid(Linear(Concat(h v ;h f ;h time ))) (1)

[0078] Among them, h gate represents the flow coordination ratio, h v represents the first flow characteristic, h f Indicates the flow characteristics, h time Represents the time attribute feature, Concat() represents the concatenation of features, Linear() represents the linear layer, and Sigmoid() represents the activation function.

[0079] Therefore, by combining the time attribute information of the target time period to determine the flow coordination ratio, the accuracy of the flow coordination ratio can be improved.

[0080] It can be understood that if the flow rate through the path is zero, it can be determined that the flow coordination ratio is zero.

[0081] Step 204 , determining the coordinated flow and the non-coordinated flow in the flow according to the flow coordination ratio and the flow through the path.

[0082] For example, the coordinated flow can be obtained by multiplying the flow through the path by the flow coordination ratio, and the uncoordinated flow can be obtained by the difference between the flow direction flow and the coordinated flow. The coordinated flow can refer to the flow that passes through the target intersection without delay in the flow direction flow, and the uncoordinated flow can refer to the flow that passes through the target intersection with a delay in the flow direction flow.

[0083] For example, the coordinated flow and the uncoordinated flow can be calculated using the following formulas (2) and (3):

[0084] X c =h gate *X r (2)

[0085] X cu =X f -X c (3)

[0086] Among them, X r represents the flow through the path, X f Indicates the flow rate, X c represents the coordinated flow, X cu Indicates uncoordinated traffic.

[0087] Therefore, based on the product of the flow coordination ratio and the path passing flow, the coordinated flow is determined from the path passing flow, and the uncoordinated flow is obtained by subtracting the coordinated flow from the flow direction flow, thereby decomposing the flow direction flow into coordinated flow and uncoordinated flow, thereby improving the accuracy of the flow direction flow decomposition.

[0088] It can be understood that if the flow through the path corresponding to a flow direction is zero, it can be determined that the flow coordination ratio is zero, and the flow flow of the flow direction is all non-coordinated flow.

[0089] Step 205, obtaining a first parking delay time according to the coordinated flow, the first flow characteristics and the flow direction traffic characteristics.

[0090] The first parking delay time may refer to the average delay time of the coordinated traffic.

[0091] Since the coordinated vehicles may be affected by the overall flow of vehicles, causing time delays, for example, the coordinated traffic can be feature extracted to obtain a second traffic feature, and the first traffic feature, the flow traffic feature and the second traffic feature can be fused to obtain a second fused feature, and the second fused feature can be decoded to obtain the first parking delay time.

[0092] Exemplarily, a linear layer may be used to extract features of the coordinated traffic to obtain a second traffic feature.

[0093] Exemplarily, the first flow feature, the flow direction traffic feature and the second flow feature may be concatenated to obtain a second fusion feature.

[0094] Therefore, based on the fusion of the first flow characteristic, the flow direction traffic characteristic, and the second flow characteristic of the coordinated flow, the average delay time of the coordinated flow is predicted, thereby improving the accuracy of the prediction of the average delay time of the coordinated flow.

[0095] Step 206, obtaining a second parking delay time according to the non-coordinated flow, the first flow characteristics and the flow direction traffic characteristics.

[0096] The second parking delay time may refer to the average delay time of non-coordinated traffic.

[0097] Since the intersection cycle and the overall flow of vehicles may have an impact on the uncoordinated traffic, based on this, for example, the intersection cycle of the target intersection can be obtained according to the signal control strategy to be evaluated, and the intersection cycle can be feature extracted to obtain the signal cycle feature, the uncoordinated traffic can be feature extracted to obtain the third flow feature, and the first flow feature, the flow traffic feature, the third flow feature and the signal cycle feature can be fused to obtain the third fused feature, and the third fused feature can be decoded to obtain the second parking delay time.

[0098] Exemplarily, a linear layer may be used to extract features of the intersection periodicity and the non-coordinated traffic flow, respectively, to obtain a signal periodicity feature and a second traffic flow feature.

[0099] Exemplarily, the first flow feature, the flow direction traffic feature, the third flow feature and the signal period feature may be concatenated to obtain a third fusion feature.

[0100] Therefore, the average delay time of the non-coordinated traffic flow is predicted in combination with the intersection cycle of the target intersection, which can improve the prediction accuracy of the average delay time of the non-coordinated traffic flow.

[0101] Step 207: Obtain the flow delay time according to the first parking delay time and the second parking delay time.

[0102] For example, the average of the first parking delay time and the second parking delay time corresponding to any flow direction may be used as the flow direction delay time of the flow direction, wherein the flow direction delay time may refer to the average delay time of the flow direction.

[0103] Exemplarily, the first parking delay time and the second parking delay time can be weighted according to the coordinated flow and the uncoordinated flow to obtain the total delay time of the flow direction, and then the flow delay time can be obtained according to the ratio of the total delay time of the flow direction to the flow direction flow.

[0104] For example, the following formula (4) can be used to calculate the flow delay time:

[0105]

[0106] Where, d represents the flow delay time, d c represents the first stop delay time, d cu Indicates the second parking delay time.

[0107] Therefore, based on the coordinated flow and uncoordinated flow in a single flow direction, the total delay time of a single flow direction is obtained by weighting, and then based on the total delay time of a single flow direction and the flow direction flow, the delay time of a single flow direction is calculated, thereby improving the accuracy of the delay time prediction for a single flow direction.

[0108] Step 208, determining the intersection delay time of the target intersection according to the flow delay time of each flow direction.

[0109] Step 209: Evaluate the signal control strategy to be evaluated according to the intersection delay time.

[0110] In the present application, step 208-step 209 can be implemented in any of the embodiments of the present application, so they will not be described in detail.

[0111] In an embodiment of the present application, the target traffic data may also include the path traffic corresponding to each flow direction. The traffic coordination ratio of the path traffic is determined based on the first traffic characteristic and the flow direction traffic characteristic, and the influence of the actual traffic environment is taken into account. The flow direction traffic is divided into coordinated traffic and uncoordinated traffic through the traffic coordination ratio, and the average delay time of the coordinated traffic and the average delay time of the uncoordinated traffic are predicted. Based on the two average delay times, the flow direction delay time is obtained, thereby improving the prediction accuracy of the flow direction delay time.

[0112] Figure 4 A flowchart of a method for evaluating intersection signal control strategy provided in another embodiment of the present application.

[0113] like Figure 4 As shown, the intersection signal control strategy evaluation method includes:

[0114] Step 401, determining the traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated.

[0115] Step 402 , extracting features from the directional flow rate and traffic performance index data respectively to obtain first flow rate features and directional traffic features.

[0116] Step 403, obtaining the flow delay time of the flow direction according to the first flow characteristic and the flow direction traffic characteristic.

[0117] In the present application, steps 401 to 403 may be implemented in any of the embodiments of the present application, and thus will not be described in detail.

[0118] Step 404 , weighting the directional delay time of each flow direction according to the directional flow rate of each flow direction, and obtaining a first total delay time of the target intersection within the target time period.

[0119] Exemplarily, for the target time period, the directional flow rate of each flow direction may be multiplied by the directional delay time, and then the multiplication results of each flow direction may be added together to obtain a first total delay time of the target intersection.

[0120] Step 405 , obtaining a first total flow rate at the target intersection within the target time period according to the sum of the flow rates of each direction.

[0121] In the present application, the flow rates of each flow direction may be added together to obtain a first total flow rate of the target intersection.

[0122] Step 406, obtaining the intersection delay time according to the ratio of the first total delay time to the first total flow rate.

[0123] In the present application, the first total delay time of the target intersection may be divided by the first total flow rate of the target intersection to obtain the average delay time of the target intersection, that is, the intersection delay time of the target intersection.

[0124] Step 407: Evaluate the signal control strategy to be evaluated according to the intersection delay time.

[0125] In the present application, step 407 can be implemented in any of the embodiments of the present application, so it will not be described in detail.

[0126] In an embodiment of the present application, the total delay time of the target intersection is obtained by weighting the directional flow rate and the flow delay time of each flow direction, the total flow rate of the target intersection is obtained by adding the directional flow rates of each flow direction, and then the intersection delay time is obtained by taking the ratio of the total delay time of the target intersection to the total flow rate of the target intersection, thereby improving the accuracy of the intersection delay time prediction.

[0127] In one embodiment of the present application, there can be multiple target time periods. For each target time period, the second total delay time of the same flow direction in multiple target time periods can be obtained according to the flow vector and flow delay time of the same flow direction in multiple target time periods. The third total delay time of the target intersection in multiple target time periods can be obtained according to the sum of the second total delay times corresponding to each flow direction. The second total flow of the same flow direction in multiple time periods can be obtained according to the flow vector of the same flow direction in multiple target time periods. The third total flow of the target intersection in multiple target time periods can be obtained according to the sum of the second total flow corresponding to each flow direction. Then, the intersection delay time of the target intersection is determined according to the ratio of the third total delay time to the third total flow.

[0128] For example, if the target time period is 30 minutes, the intersection delay time of four 30-minute time periods within 2 hours can be predicted. Here, 2 hours can be regarded as a time period, and the target time period of 30 minutes can be regarded as a sub-time period within the time period.

[0129] For example, if there are multiple target time periods, the following formula (5) can be used to calculate the intersection delay time:

[0130]

[0131] Among them, D cross represents the intersection delay time, i represents the flow direction of the intersection, j represents the target time period, represents the flow delay time of direction i in target time period j, It represents the flow rate to direction i in target time period j.

[0132] Therefore, the intersection delay time in multiple sub-time periods within a time period under the signal control strategy to be evaluated can be predicted separately, and then the intersection delay time of the target intersection within the time period can be obtained, thereby improving the accuracy of the intersection delay time prediction and further improving the evaluation accuracy of the signal control strategy.

[0133] On the basis of the above embodiment, optionally, there may be multiple signal control strategies to be evaluated, and the above method is used to obtain the intersection delay time corresponding to each signal control strategy to be evaluated. According to the intersection delay times corresponding to the multiple signal control strategies to be evaluated, a target signal control strategy is determined from the multiple signal control strategies to be evaluated, and the traffic lights at the target intersection are controlled using the target signal control strategy.

[0134] For example, the signal control strategy to be evaluated with the smallest intersection delay time can be used as the target signal control strategy.

[0135] Therefore, a reasonable signal control strategy can be screened out according to the intersection delay time of multiple signal control strategies, thereby improving the accuracy of signal control strategy screening.

[0136] In order to facilitate understanding of the intersection signal control strategy evaluation method of the present application embodiment, the following is combined with Figure 5 and Figure 6 To explain, Figure 5 A deep learning-based intersection signal control strategy evaluation process is provided in the embodiment of the present application. Figure 6 A schematic diagram of the structure of a delay prediction model provided in this application.

[0137] like Figure 5 As shown in the figure, the process is divided into three parts: data processing, model training, and model reasoning.

[0138] 1. Data processing

[0139] (1) Traffic status indicator processing

[0140] For example, the actual road network data, traffic status data and signal control strategy can be combined to calculate the index values ​​of flow level index, intersection level index, path level index and the like to characterize the traffic status in each time period.

[0141] The flow-level index may refer to the traffic status index of the flow-level, and the flow-level index may include the flow volume, the traffic performance index of the flow, etc. The intersection-level index may include the intersection cycle, and the path-level index may include the path flow volume of the coordinated direction. The traffic performance index may include the saturation flow rate, saturation, green-signal ratio, etc.

[0142] For traffic at intersections, whether the upstream and downstream intersections are affected by coordination has a significant impact on the evaluation indicators. For example, vehicles that are coordinated within the green wave band usually have lower parking delays when passing the downstream intersection, while vehicles that are not coordinated may need to stop and wait more.

[0143] Therefore, on the one hand, we can use various types of information such as the number of lanes and channelization characteristics at the intersection, real-time traffic flow distribution, signal control strategies, etc. to calculate the traffic performance indicators and intersection cycles of the flow direction to describe the traffic status of a single intersection; on the other hand, based on the overall information of the road network, we can trace the traffic status of the upstream and downstream intersections, and based on the coordination direction bandwidth and path flow, calculate the path flow in the coordination direction to reflect the traffic characteristics of a single intersection coordinated by the upstream intersection.

[0144] (2) Evaluation indicator processing

[0145] For example, the trajectory data of floating vehicles can be used to evaluate the effect of traffic control at intersections. For example, the real-time vehicle position data collected by the vehicle positioning device at a fixed frequency can be analyzed, the vehicle driving trajectory can be extracted within the target time interval, and then the evaluation index of the flow direction can be calculated according to the trajectory position of the floating vehicle. Among them, the evaluation index can be the delay time. The delay time can be calculated by comparing the actual vehicle travel time with the travel time under the unblocked state at night.

[0146] It should be noted that since the trajectory data of the floating car is a sampling of all real data, when the data sample is too small, abnormal values ​​may appear due to the fluctuation of values. Therefore, before model training, the evaluation indicators can be processed to avoid such data affecting the accuracy of model training.

[0147] (3) Data Filtering

[0148] In order to improve the stability and accuracy of model training, the indicator anomaly detection method can be used to identify and process abnormal values, thereby reducing the impact of abnormal data on the model and improving the evaluation accuracy of the model under different signal control strategies.

[0149] Due to the limitation of the collection accuracy of the sensing device, anomalies may exist in the collected data. The abnormal values ​​in the flow traffic can be identified and the data can be filtered to ensure the credibility of the sensed traffic.

[0150] Since the evaluation index is calculated based on sampled data, it may have certain volatility. We can filter data with low accumulation samples and high delay, and data with low delay and no obvious coordination flowing to multi-track samples. This helps to improve the credibility of the data, ensure that the model can learn parameters based on accurate labels during training, and reduce large errors caused by sampling individual data.

[0151] 2. Model training

[0152] (1) Data feature extraction

[0153] In the target time period, the flow delay time can be predicted. The model input is as follows: Figure 6 For example, a time period of 30 minutes can be used to build a model based on the traffic flow and traffic indicator data of the path in the time period to predict the flow delay time.

[0154] (2) Delay prediction model

[0155] like Figure 6 As shown, the model mainly includes three parts: traffic decomposition part, coordinated network and uncoordinated network.

[0156] The flow flow and traffic performance index data can be extracted through the residual network to obtain the first flow feature and the flow traffic feature, and the time attribute information can be vectorized to obtain the time attribute feature. Then, based on the feature fused by the three features ( Figure 6 ), and obtain the flow coordination ratio.

[0157] Based on the flow coordination ratio and the flow through the path, the flow direction flow is decomposed to obtain the coordinated flow and the uncoordinated flow, and based on the coordinated flow, the first flow characteristics and the flow direction traffic characteristics, the parking delay time of the coordinated flow is obtained, and based on the uncoordinated flow, the first flow characteristics, the flow direction traffic characteristics and the signal cycle characteristics, the parking delay time of the uncoordinated flow is obtained, and then the two parking delay times are combined to obtain the flow direction delay time. The specific process can be referred to the above embodiment.

[0158] (3) Model training

[0159] Model training can use the flow delay time obtained by sampling floating vehicle trajectory samples as a label, calculate the loss between the predicted flow delay time and the actual flow delay time, and perform model training based on the loss.

[0160] 3. Model Reasoning

[0161] Model reasoning can be calculated on an intersection basis. By predicting and aggregating all flow delays at the target intersection in a specified time period, the intersection delay time under a specified flow rate can be obtained.

[0162] In this application, the delay prediction model can collect historical traffic status data, issued signal control strategies and evaluation indicators in the real environment, learn the changes in signal control effects under different traffic conditions and signal control strategies, and realize a priori evaluation of the effects of different signal control strategies under specified traffic conditions.

[0163] The signal control strategy evaluation process of the present application is mainly divided into three parts: data processing, model training and model reasoning. In the data processing part, the data can be cleaned and aggregated to ensure the accuracy and reliability of traffic status indicators and evaluation indicators. Taking into account the obvious difference in the evaluation indicators of traffic flow when it can be coordinated and when it cannot be coordinated, the present application analyzes and processes the characteristics of traffic flow during model building, and predicts the evaluation indicators of the traffic flow that can be coordinated and the traffic flow that cannot be coordinated, and combines the two to obtain the evaluation indicators of the intersection. During model training, the model parameters are trained through the traffic status indicators of a large number of intersections, the issued signal control strategies and evaluation indicators. During model reasoning, different signal control strategies can be input based on the specified traffic flow to obtain the evaluation indicators of the signal control strategy, and the signal control strategy can be screened according to the evaluation indicators.

[0164] In order to implement the above embodiment, the embodiment of the present application also proposes a road intersection signal control strategy evaluation device. Figure 7 A schematic diagram of the structure of an intersection signal control strategy evaluation device provided in one embodiment of the present application.

[0165] like Figure 7 As shown, the intersection signal control strategy evaluation device 700 includes:

[0166] The first acquisition module 710 is used to acquire the traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated; wherein the target flow data includes the flow volume of each flow direction;

[0167] A feature extraction module 720 is used to extract features from the flow direction flow and the traffic performance index data to obtain a first flow feature and a flow direction traffic feature;

[0168] A second acquisition module 730 is used to obtain a flow delay time of the flow direction according to the first flow characteristics and the flow direction traffic characteristics;

[0169] A first determining module 740, configured to determine an intersection delay time of the target intersection according to the flow delay time of each flow direction;

[0170] The evaluation module 750 is used to evaluate the signal control strategy to be evaluated according to the intersection delay time.

[0171] Optionally, the target flow data further includes the flow through the paths corresponding to the respective flow directions, and the second acquisition module 730 is used to:

[0172] Determining a flow coordination ratio of the flow through the path according to the first flow characteristic and the flow direction traffic characteristic;

[0173] Determine the coordinated flow and the non-coordinated flow in the flow direction flow according to the flow coordination ratio and the flow through the path;

[0174] Obtaining a first parking delay time according to the coordinated flow, the first flow characteristics, and the flow direction traffic characteristics;

[0175] Obtaining the second parking delay time according to the non-coordinated flow, the first flow characteristics and the flow direction traffic characteristics;

[0176] The flow delay time is obtained according to the first parking delay time and the second parking delay time.

[0177] Optionally, the second acquisition module 730 is used to:

[0178] Determining time attribute information of the target time period;

[0179] Extracting features from the time attribute information to obtain the time attribute features;

[0180] The first flow feature, the flow direction traffic feature and the time attribute feature are fused to obtain a first fused feature;

[0181] The traffic coordination ratio is determined according to the first fusion feature.

[0182] Optionally, the second acquisition module 730 is used to:

[0183] Obtaining the coordinated flow according to the product of the flow through the path and the flow coordination ratio;

[0184] The non-coordinated flow is obtained according to the difference between the flow direction flow and the coordinated flow.

[0185] Optionally, the second acquisition module 730 is used to:

[0186] Extracting features of the coordinated traffic to obtain a second traffic feature;

[0187] fusing the first flow feature, the flow direction traffic feature, and the second flow feature to obtain a second fused feature;

[0188] The first parking delay time is obtained according to the second fusion feature.

[0189] Optionally, the second acquisition module 730 is used to:

[0190] According to the signal control strategy to be evaluated, obtaining the intersection cycle of the target intersection;

[0191] Extracting features of the intersection cycle to obtain signal cycle features;

[0192] Extracting features of the non-coordinated traffic to obtain a third traffic feature;

[0193] fusing the first flow feature, the flow direction traffic feature, the third flow feature, and the signal period feature to obtain a third fused feature;

[0194] The second parking delay time is obtained according to the third fusion feature.

[0195] Optionally, the second acquisition module 730 is used to:

[0196] According to the coordinated flow and the non-coordinated flow, weighting the first parking delay time and the second parking delay time to obtain a total delay time of the flow direction;

[0197] The delay time of the flow direction is obtained according to the ratio of the total delay time of the flow direction to the flow rate of the flow direction.

[0198] Optionally, the first determining module 740 is configured to:

[0199] According to the directional flow rates of the respective directions, the directional delay times of the respective directions are weighted to obtain a first total delay time of the target intersection within the target time period;

[0200] Obtaining a first total flow rate of the target intersection within the target time period according to the sum of the flow rates of each flow direction;

[0201] The intersection delay time is obtained according to the ratio of the first total delay time to the first total flow rate.

[0202] Optionally, there are multiple target time periods, and the first determining module 740 is configured to:

[0203] Obtaining a second total delay time of the same flow direction within the plurality of target time periods according to the flow vectors and flow delay times of the same flow direction within the plurality of target time periods;

[0204] Obtaining a third total delay time of the target intersection within a plurality of the target time periods according to the sum of the second total delay times corresponding to the respective flow directions;

[0205] Obtaining a second total flow rate of the same flow direction in the plurality of target time periods according to the flow vectors of the same flow direction in the plurality of target time periods;

[0206] Obtaining a third total flow rate of the target intersection within a plurality of target time periods according to the sum of the second total flow rates corresponding to the respective flow directions;

[0207] The intersection delay time of the target intersection is determined according to the third total delay time and the third total flow rate.

[0208] Optionally, there are multiple signal control strategies to be evaluated, and the device may further include:

[0209] A second determination module is used to determine a target signal control strategy from the plurality of signal control strategies to be evaluated according to the intersection delay times corresponding to the plurality of signal control strategies to be evaluated;

[0210] A control module is used to control the traffic light at the target intersection according to the target signal control strategy.

[0211] It should be noted that the explanation of the aforementioned intersection signal control strategy evaluation method embodiment is also applicable to the intersection signal control strategy evaluation device of this embodiment, so it will not be repeated here.

[0212] In the embodiment of the present application, the traffic performance index data of each flow direction of the target intersection is obtained according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated, and the flow flow and traffic performance index data of each flow direction are respectively extracted. Based on the extracted flow characteristics and flow direction traffic characteristics, the flow delay time of the flow direction is obtained, and then the intersection delay time is obtained according to the delay time of each flow direction. The signal control strategy to be evaluated is evaluated using the intersection delay time. Thus, the flow delay time is predicted based on the extracted flow characteristics and flow direction traffic characteristics, which can improve the accuracy of the flow delay time prediction and the intersection delay time prediction, thereby improving the accuracy of the signal control strategy evaluation. In addition, different signal control strategies can be quickly evaluated under a specified flow rate, reducing the difficulty and cost of evaluation.

[0213] According to an embodiment of the present application, the present application also provides an electronic device, a readable storage medium and a computer program product.

[0214] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0215] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 802 or a computer program loaded from a storage unit 808 to a RAM (Random Access Memory) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An I / O (Input / Output) interface 805 is also connected to the bus 804.

[0216] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0217] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, CPU (Central Processing Unit), GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the intersection signal control strategy evaluation method. For example, in some embodiments, the intersection signal control strategy evaluation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the intersection signal control strategy evaluation method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the intersection signal control strategy evaluation method in any other appropriate manner (eg, by means of firmware).

[0218] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0219] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0220] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0221] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0222] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0223] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services (Virtual Private Server). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0224] According to an embodiment of the present application, the present application further provides a computer program product, which, when an instruction processor in the computer program product is executed, executes the intersection signal control strategy evaluation method proposed in the above embodiment of the present application.

[0225] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0226] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for evaluating a traffic signal control strategy at an intersection, comprising: Determine the traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated; wherein the target flow data includes the flow volume of each flow direction; Extracting features from the flow direction flow and the traffic performance index data respectively to obtain a first flow feature and a flow direction traffic feature; Obtaining a flow delay time of the flow direction according to the first flow characteristic and the flow direction traffic characteristic; Determining the intersection delay time of the target intersection according to the flow delay time of each flow direction; The signal control strategy to be evaluated is evaluated according to the intersection delay time.

2. The method of claim 1, wherein: The target flow data also includes the flow of the paths corresponding to the respective flow directions. The flow delay time of the flow direction is obtained according to the first flow characteristics and the flow direction traffic characteristics, including: Determining a flow coordination ratio of the flow through the path according to the first flow characteristic and the flow direction traffic characteristic; Determine the coordinated flow and the non-coordinated flow in the flow direction flow according to the flow coordination ratio and the flow through the path; Obtaining a first parking delay time according to the coordinated flow, the first flow characteristics, and the flow direction traffic characteristics; Obtaining the second parking delay time according to the non-coordinated flow, the first flow characteristics and the flow direction traffic characteristics; The flow delay time is obtained according to the first parking delay time and the second parking delay time.

3. The method of claim 2, wherein: The determining, according to the first flow characteristic and the flow direction traffic characteristic, the flow coordination ratio of the flow through the path includes: Determining time attribute information of the target time period; Extracting features from the time attribute information to obtain the time attribute features; The first flow feature, the flow direction traffic feature and the time attribute feature are fused to obtain a first fused feature; The traffic coordination ratio is determined according to the first fusion feature.

4. The method of claim 2, wherein: The determining, according to the flow coordination ratio and the flow passing through the path, of the coordinated flow and the non-coordinated flow in the flow direction flow comprises: Obtaining the coordinated flow according to the product of the flow through the path and the flow coordination ratio; The non-coordinated flow is obtained according to the difference between the flow direction flow and the coordinated flow.

5. The method of claim 2, wherein: The obtaining of a first parking delay time according to the coordinated flow, the first flow characteristic and the flow direction traffic characteristic comprises: Extracting features of the coordinated traffic to obtain a second traffic feature; fusing the first flow feature, the flow direction traffic feature, and the second flow feature to obtain a second fused feature; The first parking delay time is obtained according to the second fusion feature.

6. The method of claim 2, wherein: The obtaining of the second parking delay time according to the non-coordinated flow, the first flow characteristic and the flow direction traffic characteristic comprises: According to the signal control strategy to be evaluated, obtaining the intersection cycle of the target intersection; Extracting features of the intersection cycle to obtain signal cycle features; Extracting features of the non-coordinated traffic to obtain a third traffic feature; fusing the first flow feature, the flow direction traffic feature, the third flow feature and the signal period feature to obtain a third fused feature; The second parking delay time is obtained according to the third fusion feature.

7. The method of claim 2, wherein: The obtaining the flow delay time according to the first parking delay time and the second parking delay time includes: According to the coordinated flow and the non-coordinated flow, weighting the first parking delay time and the second parking delay time to obtain a total delay time of the flow direction; The delay time of the flow direction is obtained according to the ratio of the total delay time of the flow direction to the flow rate of the flow direction.

8. The method of claim 1, wherein: Determining the intersection delay time of the target intersection according to the flow delay time of each flow direction includes: According to the directional flow rates of the respective directions, the directional delay times of the respective directions are weighted to obtain a first total delay time of the target intersection within the target time period; Obtaining a first total flow rate of the target intersection within the target time period according to the sum of the flow rates of each flow direction; The intersection delay time is obtained according to the ratio of the first total delay time to the first total flow rate.

9. The method of claim 1, wherein: There are multiple target time periods, and determining the intersection delay time of the target intersection according to the flow delay time of each flow direction includes: Obtaining a second total delay time of the same flow direction within the plurality of target time periods according to the flow vectors and flow delay times of the same flow direction within the plurality of target time periods; Obtaining a third total delay time of the target intersection within a plurality of target time periods according to the sum of the second total delay times corresponding to the respective flow directions; Obtaining a second total flow rate of the same flow direction in the plurality of target time periods according to the flow vectors of the same flow direction in the plurality of target time periods; Obtaining a third total flow rate of the target intersection within a plurality of target time periods according to the sum of the second total flow rates corresponding to the respective flow directions; The intersection delay time of the target intersection is determined according to the third total delay time and the third total flow rate.

10. The method according to any one of claims 1 to 9, wherein: There are multiple signal control strategies to be evaluated, and the method further includes: Determining a target signal control strategy from the plurality of signal control strategies to be evaluated according to the intersection delay times corresponding to the plurality of signal control strategies to be evaluated; According to the target signal control strategy, the traffic light at the target intersection is controlled.

11. A device for evaluating a traffic signal control strategy at an intersection, comprising: A first acquisition module is used to acquire traffic performance index data of each flow direction of the target intersection according to the target flow data of the target intersection in the target time period and the signal control strategy to be evaluated; wherein the target flow data includes the flow flow of each flow direction; A feature extraction module, used to extract features from the flow direction flow and the traffic performance index data respectively to obtain a first flow feature and a flow direction traffic feature; A second acquisition module, configured to obtain a flow delay time of the flow direction according to the first flow characteristics and the flow direction traffic characteristics; A first determining module, configured to determine an intersection delay time of the target intersection according to the flow delay time of each flow direction; An evaluation module is used to evaluate the signal control strategy to be evaluated according to the intersection delay time.

12. The device of claim 11, wherein: The target flow data also includes the flow through the paths corresponding to the respective flow directions, and the second acquisition module is used to: Determining a flow coordination ratio of the flow through the path according to the first flow characteristic and the flow direction traffic characteristic; Determine the coordinated flow and the non-coordinated flow in the flow direction flow according to the flow coordination ratio and the flow through the path; Obtaining a first parking delay time according to the coordinated flow, the first flow characteristics, and the flow direction traffic characteristics; Obtaining the second parking delay time according to the non-coordinated flow, the first flow characteristics and the flow direction traffic characteristics; The flow delay time is obtained according to the first parking delay time and the second parking delay time.

13. The device of claim 12, wherein: The second acquisition module is used to: Determining time attribute information of the target time period; Extracting features from the time attribute information to obtain the time attribute features; The first flow feature, the flow direction traffic feature and the time attribute feature are fused to obtain a first fused feature; The traffic coordination ratio is determined according to the first fusion feature.

14. The device of claim 12, wherein: The second acquisition module is used to: Obtaining the coordinated flow according to the product of the flow through the path and the flow coordination ratio; The non-coordinated flow is obtained according to the difference between the flow direction flow and the coordinated flow.

15. The device of claim 12, wherein: The second acquisition module is used to: Extracting features of the coordinated traffic to obtain a second traffic feature; fusing the first flow feature, the flow direction traffic feature, and the second flow feature to obtain a second fused feature; The first parking delay time is obtained according to the second fusion feature.

16. The device of claim 12, wherein: The second acquisition module is used to: According to the signal control strategy to be evaluated, obtaining the intersection cycle of the target intersection; Extracting features of the intersection cycle to obtain signal cycle features; Extracting features of the non-coordinated traffic to obtain a third traffic feature; fusing the first flow feature, the flow direction traffic feature, the third flow feature and the signal period feature to obtain a third fused feature; The second parking delay time is obtained according to the third fusion feature.

17. The device of claim 12, wherein: The second acquisition module is used to: According to the coordinated flow and the non-coordinated flow, weighting the first parking delay time and the second parking delay time to obtain a total delay time of the flow direction; The delay time of the flow direction is obtained according to the ratio of the total delay time of the flow direction to the flow rate of the flow direction.

18. The device of claim 11, wherein: The first determining module is used to: According to the directional flow rates of the respective directions, the directional delay times of the respective directions are weighted to obtain a first total delay time of the target intersection within the target time period; Obtaining a first total flow rate of the target intersection within the target time period according to the sum of the flow rates of each flow direction; The intersection delay time is obtained according to the ratio of the first total delay time to the first total flow rate.

19. The device of claim 11, wherein: The target time period is multiple, and the first determining module is used to: Obtaining a second total delay time of the same flow direction within the plurality of target time periods according to the flow vectors and flow delay times of the same flow direction within the plurality of target time periods; Obtaining a third total delay time of the target intersection within a plurality of target time periods according to the sum of the second total delay times corresponding to the respective flow directions; Obtaining a second total flow rate of the same flow direction in the plurality of target time periods according to the flow vectors of the same flow direction in the plurality of target time periods; Obtaining a third total flow rate of the target intersection within a plurality of target time periods according to the sum of the second total flow rates corresponding to the respective flow directions; The intersection delay time of the target intersection is determined according to the third total delay time and the third total flow rate.

20. The device according to any one of claims 11 to 19, wherein the signal control strategy to be evaluated is multiple, and the device further comprises: A second determination module is used to determine a target signal control strategy from the plurality of signal control strategies to be evaluated according to the intersection delay times corresponding to the plurality of signal control strategies to be evaluated; A control module is used to control the traffic light at the target intersection according to the target signal control strategy.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

Images