Methods for alleviating road traffic congestion, computer equipment and readable storage media

Abstract

This application discloses a method, computer equipment, and storage medium for alleviating road traffic congestion. The method includes: acquiring road traffic data of a target road collected by an unmanned aerial vehicle (UAV); extracting traffic parameters from the road traffic data to obtain first traffic parameters of the target road in the current time period; performing time-series prediction of the traffic parameters of the target road based on the first traffic parameters to obtain second traffic parameters of the target road in a future first time period; predicting the traffic congestion state of the target road based on the second traffic parameters to obtain the probability of traffic congestion of the target road in the future first time period; if the probability of traffic congestion in a consecutive second time period is greater than or equal to a preset probability within the future first time period, determining an emergency lane opening strategy for the target road; and executing the emergency lane opening strategy. This method can provide efficient and accurate traffic congestion monitoring and emergency lane opening strategies, effectively addressing complex traffic congestion problems.

Description

Technical Field

[0001] This application relates to the field of traffic management technology, and in particular to a method for alleviating road traffic congestion, a computer device, and a computer-readable storage medium. Background Technology

[0002] While existing technologies have made some progress in traffic congestion monitoring and mitigation, they still have significant shortcomings in monitoring, predicting, making decisions, and mitigating traffic congestion. The monitoring scope suffers from sampling bias, and the response speed to sudden events or unconventional congestion is slow, making it difficult to effectively address complex traffic congestion problems. Summary of the Invention

[0003] This application provides a method for alleviating road traffic congestion, a computer device, and a computer-readable storage medium, which can provide efficient and accurate traffic congestion monitoring and emergency lane opening strategies, and can effectively address complex traffic congestion problems.

[0004] Firstly, this application provides a method for alleviating road traffic congestion, the method comprising:

[0005] Acquire road traffic data of the target road by drone;

[0006] Traffic parameters are extracted from the road traffic data to obtain the first traffic parameters of the target road in the current time period;

[0007] Based on the first traffic parameters, the traffic parameters of the target road are predicted in a time series to obtain the second traffic parameters of the target road in the future first time period;

[0008] Based on the second traffic parameters, the traffic congestion status of the target road is predicted to obtain the traffic congestion probability of the target road in the first future time period.

[0009] If the probability of traffic congestion in a consecutive second time period within the first future time period is greater than or equal to a preset probability, then the emergency lane opening strategy for the target road is determined.

[0010] Implement the emergency lane opening strategy.

[0011] Secondly, this application also provides a computer device, which includes a memory and a processor;

[0012] The memory is used to store computer programs;

[0013] The processor is used to execute the computer program and, in executing the computer program, implement the road traffic congestion relief method as described above.

[0014] Thirdly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the road traffic congestion relief method described above.

[0015] This application discloses a method for alleviating road traffic congestion, a computer device, and a computer-readable storage medium. By acquiring road traffic data of a target road collected by a drone, it can collect road traffic data covering the entire area of ​​the road, comprehensively reflecting the behavior of all vehicles on the target road and greatly reducing sampling bias. By extracting traffic parameters from the road traffic data, the first traffic parameter of the target road in the current time period is obtained. Based on the first traffic parameter, the traffic parameters of the target road are predicted in time series to obtain the second traffic parameter of the target road in the next first time period. Based on the second traffic parameter, the traffic congestion state of the target road is predicted to obtain the traffic congestion of the target road in the next first time period. Probability-based analysis enables accurate assessment of traffic congestion based on traffic density and average speed, and accurate prediction of traffic congestion probability in future time periods. It reflects the continuity and ambiguity of road congestion, providing efficient and precise traffic congestion monitoring. By determining and executing an emergency lane opening strategy for a target road when the probability of traffic congestion in a second consecutive time period is greater than or equal to a preset probability within a first future time period, it allows for the determination of emergency lane opening strategies based on short-term traffic congestion probabilities. This improves the monitoring and response speed to sudden events or unconventional congestion, providing efficient and precise emergency lane opening strategies and effectively addressing complex traffic congestion problems. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application;

[0018] Figure 2 This is a schematic flowchart of a road traffic congestion relief method provided in an embodiment of this application;

[0019] Figure 3 This is a schematic flowchart illustrating a sub-step for extracting traffic parameters provided in an embodiment of this application;

[0020] Figure 4This is a schematic flowchart illustrating a sub-step of timing prediction provided in an embodiment of this application;

[0021] Figure 5 This is a schematic flowchart illustrating a sub-step of traffic congestion state prediction provided in an embodiment of this application;

[0022] Figure 6 This is a schematic flowchart illustrating a sub-step for determining the stability of an initial activation scheme, as provided in an embodiment of this application.

[0023] Figure 7 This is a schematic diagram of the overall process of a road traffic congestion relief method provided in the embodiments of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0026] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0027] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0028] Currently, although existing technologies have made some progress in traffic congestion monitoring and mitigation, they still have significant shortcomings in the monitoring, prediction, decision-making, and mitigation of traffic congestion.

[0029] In terms of detection, fixed monitoring equipment has limited installation locations and cannot cover the entire road network, resulting in slow response times to sudden events or unusual congestion. While floating car data acquisition technology expands the monitoring range, it suffers from sampling bias, cannot comprehensively reflect all vehicle behaviors, and experiences time delays in data transmission and processing, making it difficult to support real-time decision-making.

[0030] In terms of forecasting, traditional forecasting models have limited ability to predict sudden events and unconventional congestion, lack the ability to comprehensively utilize multi-source data, and have insufficient reliability in their forecast results, making them unsuitable as a basis for key decisions. In particular, for short-term (e.g., 30 seconds) traffic condition forecasts, existing forecasting models have low accuracy and cannot meet the needs of emergency decision-making.

[0031] Regarding emergency lane opening strategies, current decision-making relies primarily on experience-based judgment or simple threshold rules, lacking precise quantitative methods for determining the timing and duration of emergency lane openings. This makes it impossible to dynamically adapt to changes in traffic flow and adjust opening strategies accordingly. Furthermore, existing traffic management strategies lack theoretical support, making stability difficult to guarantee. It is also impossible to assess the long-term effects and risks of traffic management measures, and there is a lack of prediction and control over the post-reopening traffic flow recovery process.

[0032] Furthermore, existing systems generally lack systematic solutions; the monitoring, prediction, decision-making, and execution processes are not tightly integrated, failing to form a closed-loop optimization mechanism and hindering the continuous improvement of relocation effectiveness. Simultaneously, the lack of effective verification and evaluation mechanisms for decision-making results makes it difficult to objectively assess the effectiveness of relocation strategies and thus optimize decision parameters.

[0033] To address at least one of the aforementioned problems, embodiments of this application provide a road traffic congestion relief method, a computer device, and a computer-readable storage medium. The road traffic congestion relief method can be applied to a computer device, enabling the determination of emergency lane opening strategies based on short-term traffic congestion probabilities. This improves the monitoring and response speed to sudden events or unconventional congestion, provides efficient and accurate emergency lane opening strategies, and effectively addresses complex traffic congestion problems.

[0034] It should be noted that the road traffic congestion relief method provided in this application is mainly applicable to the technical fields of Intelligent Transport Systems (ITS), urban traffic management, highway traffic control, big data-driven traffic optimization, emergency management and emergency response, and artificial intelligence-assisted traffic decision-making. In terms of industrial applications, this application can be widely used in traffic management and monitoring, smart city construction, highway management and operation, traffic big data analysis services, traffic safety assurance services, and emergency response services. Typical products achievable with this application include highway intelligent traffic management systems, urban traffic command center decision support systems, traffic congestion early warning and relief platforms, unmanned aerial vehicle (UAV) traffic situation awareness systems, cloud computing-based traffic big data analysis platforms, and traffic relief simulation verification systems.

[0035] For example, a computer device can be a server or a terminal. The server can be a standalone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal can be an electronic device such as a smartphone, tablet, laptop, or desktop computer.

[0036] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of a computer device 1000 provided in an embodiment of this application. The computer device 1000 may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 can be connected by a bus, which can be any applicable bus such as an Inter-integrated Circuit (I2C) bus.

[0037] The memory 1002 may include a storage medium and internal memory. The storage medium may be a non-volatile storage medium or a volatile storage medium. The storage medium may store an operating system and computer programs, while the internal memory provides an environment for the execution of the computer programs stored in the storage medium. The computer programs include program instructions that, when executed, cause the processor to perform the road traffic congestion relief method described in any embodiment.

[0038] The processor 1001 provides computing and control capabilities to support the operation of the entire computer device 1000.

[0039] The processor 1001 can be a Central Processing Unit (CPU), but it can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or it can be any conventional processor.

[0040] In one embodiment, the processor 1001 is configured to run a computer program stored in the memory 1002 to perform the following steps:

[0041] Acquire road traffic data of the target road collected by drone; extract traffic parameters from the road traffic data to obtain the first traffic parameters of the target road in the current time period; perform time-series prediction of the traffic parameters of the target road based on the first traffic parameters to obtain the second traffic parameters of the target road in the next first time period; predict the traffic congestion status of the target road based on the second traffic parameters to obtain the traffic congestion probability of the target road in the next first time period; if there is a traffic congestion probability in the next second time period that is greater than or equal to a preset probability, determine the emergency lane opening strategy for the target road; execute the emergency lane opening strategy.

[0042] In one embodiment, when implementing the emergency lane opening strategy for determining the target road, the processor 1001 is used to implement:

[0043] The process involves determining the initial opening parameters for the emergency lane and establishing an initial opening plan based on these parameters; determining the stability of the initial opening plan; if the stability of the initial opening plan is greater than or equal to a preset stability threshold, then determining a target opening plan based on the initial opening plan; if the stability of the initial opening plan is less than the stability threshold, then updating the initial opening parameters and returning to the step of determining the initial opening plan based on the initial opening parameters, until the stability of the initial opening plan is greater than or equal to the stability threshold, then determining the target opening plan based on the current initial opening plan; and finally, determining the emergency lane opening strategy based on the target opening plan.

[0044] In one embodiment, the initial opening parameters include the opening time, the initial opening duration, the time window length, and the iteration step size; based on the initial opening parameters, the processor 1001 determines the initial opening scheme for the emergency lane, and in implementing the initial opening scheme for the emergency lane based on the initial opening parameters, it is used to implement:

[0045] Based on the rolling time window mechanism, the initial opening duration is iteratively optimized according to the opening time, time window length and iteration step size, and the traffic congestion status of the target road after the emergency lane is closed is predicted until the traffic congestion status meets the preset conditions, at which point the iterative optimization stops and the current initial opening duration is determined as the target opening duration; the initial opening plan is determined based on the opening time and the target opening duration.

[0046] In one embodiment, the processor 1001, when determining the stability of the initial startup scheme, is configured to:

[0047] Construct a state transition probability matrix for the target road, which includes the first probability of the target road transitioning from free flow to free flow, the second probability of transitioning from free flow to traffic congestion, the third probability of transitioning from traffic congestion to free flow, and the fourth probability of transitioning from traffic congestion to traffic congestion. Based on the state transition probability matrix, determine the corrected state transition probability matrix for the target road after the emergency lane is opened. Based on the corrected state transition probability matrix, calculate the free flow probability of the target road in the third time period after the initial opening plan is completed. Determine the stability of the initial opening plan based on the free flow probability.

[0048] In one embodiment, before determining the emergency lane opening strategy based on the target opening scheme, the processor 1001 is further configured to implement:

[0049] A simulation environment identical to the target road is constructed on a pre-defined traffic simulation software, and the road network data, vehicle parameters, and driving behavior parameters in the simulation environment are determined. The road network data, vehicle parameters, and driving behavior parameters are imported into the traffic simulation software for simulation testing to obtain the first traffic indicator data of the target road in the baseline scenario. The road network data, vehicle parameters, driving behavior parameters, and the target opening scheme are imported into the traffic simulation software for simulation testing to obtain the second traffic indicator data of the target road in the scenario of opening the emergency lane. The improvement of the second traffic indicator data relative to the first traffic indicator data is determined. If the improvement is greater than a pre-defined improvement threshold, the target opening scheme is deemed to have passed the simulation verification.

[0050] In one embodiment, when the processor 1001 determines the emergency lane opening strategy based on the target opening scheme, it is used to:

[0051] Once the target opening scheme passes simulation verification, an emergency lane opening strategy is generated based on the target opening scheme and preset implementation suggestion information.

[0052] In one embodiment, the first traffic parameters include a first traffic density and a first average traffic speed; when the processor 1001 extracts traffic parameters from road traffic data to obtain the first traffic parameters of the target road in the current time period, it is used to:

[0053] The road traffic data is filtered by vehicle trajectory to obtain the vehicle trajectory information corresponding to the target road; the vehicle identification number and driving data of each vehicle on the target road are extracted from the vehicle trajectory information; the first traffic flow density corresponding to the target road is determined based on the vehicle identification number of each vehicle, and the average speed of the first traffic flow corresponding to the target road is determined based on the driving data of each vehicle.

[0054] In one embodiment, when the processor 1001 determines the first traffic flow density corresponding to the target road based on the vehicle identification number of each vehicle, it is configured to:

[0055] Vehicle type identification is performed based on the vehicle identification number of each vehicle, and the number of vehicles corresponding to each type of vehicle on the target road is counted; the number of vehicles corresponding to each type of vehicle is converted to obtain the equivalent number of vehicles corresponding to the target road; the traffic flow density is calculated based on the equivalent number of vehicles and the number of vehicles corresponding to each type of vehicle to obtain the first traffic flow density.

[0056] In one embodiment, when the processor 1001 determines the first average speed of traffic flow corresponding to the target road based on the driving data of each vehicle, it is configured to:

[0057] The driving speed of each vehicle in the driving direction is calculated based on the driving data of each vehicle within a preset time period; anomaly detection of the driving speed of each vehicle is performed based on the interquartile range method, and outliers in the driving speed of each vehicle are deleted; the average speed of the driving speed after deleting outliers is calculated to obtain the average speed of the first traffic flow.

[0058] In one embodiment, when the processor 1001 calculates the speed of each vehicle in the driving direction within a preset time period based on the driving data of each vehicle, it is also configured to:

[0059] For each vehicle, a missing value detection is performed on its speed, and the target vehicle with a missing speed at the first moment is identified. It is then determined whether the speed of the target vehicle at the moment adjacent to the first moment exists in the driving data. If it exists, the speed of the target vehicle at the first moment is determined based on the speed of the target vehicle at the moment adjacent to the first moment. If it does not exist, the speed of the target vehicle at the first moment is determined based on the speed of other vehicles in the adjacent lanes of the target vehicle.

[0060] In one embodiment, the first traffic parameters include a first traffic density, a first average traffic speed, and the temporal and spatial characteristics corresponding to the target road; when the processor 1001 performs time-series prediction of the traffic parameters of the target road based on the first traffic parameters to obtain the second traffic parameters of the target road in a future first time period, it is used to implement:

[0061] Based on the first traffic flow density, the first traffic flow average speed, time characteristics, and spatial characteristics, an input sequence matrix is ​​generated; the input sequence matrix is ​​then input into a preset time series prediction model for time series prediction to obtain the second traffic parameters.

[0062] In one embodiment, when the processor 1001 performs time-series prediction by inputting the input sequence matrix into a preset time-series prediction model to obtain the second traffic parameters, it is used to:

[0063] Based on a bidirectional encoding layer, the input sequence matrix is ​​bidirectionally encoded to obtain first and second encoding information. The first and second encoding information are concatenated to obtain the bidirectional hidden states corresponding to different time points. The bidirectional hidden states corresponding to the last time point are subjected to average pooling to obtain aggregated features. Based on multiple fully connected layers, the aggregated features are processed multiple times to obtain the fully connected processing results. The second traffic parameter is determined based on the fully connected processing results.

[0064] In one embodiment, the second traffic parameter includes a second traffic density and a second average traffic speed; the processor 1001, when performing traffic congestion state prediction of the target road based on the second traffic parameter to obtain the traffic congestion probability of the target road in a future first time period, is used to implement:

[0065] Based on the triangular membership function, the second traffic flow density and the second traffic flow average speed are fuzzified to obtain the first fuzzy membership set corresponding to the second traffic flow density and the second fuzzy membership set corresponding to the second traffic flow average speed. Each fuzzy rule in the preset fuzzy rule base is activated according to the first and second fuzzy membership sets to obtain the initial activation degree of each fuzzy rule. The initial activation degree of each fuzzy rule is then clipped according to the first and second fuzzy membership sets to obtain the target activation degree of each fuzzy rule. The target activation degrees of each fuzzy rule are then aggregated to obtain the target activation degree of each fuzzy rule under different traffic congestion states. Finally, the target activation degrees of each fuzzy rule under different traffic congestion states are defuzzified to obtain the traffic congestion probability.

[0066] In one embodiment, before the processor 1001 performs rule activation on each fuzzy rule in the preset fuzzy rule base according to the first fuzzy membership set and the second fuzzy membership set to obtain the initial activation degree corresponding to each fuzzy rule, it is also used to perform the following:

[0067] Based on the triangular membership function, traffic flow density, average traffic speed, and traffic congestion probability of different values ​​are classified to obtain multiple fuzzy subsets of traffic flow density, average traffic speed, and traffic congestion status. Based on these subsets, a fuzzy rule base is constructed, which includes at least one fuzzy rule. Each fuzzy rule is used to indicate the mapping relationship between traffic flow density, average traffic speed, and traffic congestion status.

[0068] The following detailed description, in conjunction with the accompanying drawings, outlines some embodiments of this application. Unless otherwise specified, the following embodiments and features described herein can be combined with each other. Please refer to... Figure 2 , Figure 2 This is a schematic flowchart illustrating a road traffic congestion relief method provided in an embodiment of this application. Figure 2 As shown, the road traffic congestion relief method may include steps S10 to S60.

[0069] Step S10: Obtain road traffic data of the target road collected by the drone.

[0070] It should be noted that, in this embodiment, a drone can be used to collect road traffic data of the target road. The drone can be equipped with 4K high-definition camera equipment and 5G real-time transmission technology, and can execute autonomously planned flight paths to fully cover the monitoring area. Furthermore, the drone integrates Real-Time Kinematic (RTK) technology to achieve centimeter-level positioning accuracy, supports multi-drone collaborative operation and dynamic path adjustment, and can acquire high-quality overhead images at a flight altitude of 80-120 meters, realizing macro and micro monitoring of traffic flow and providing the system with a real-time, high-precision data source.

[0071] For example, a quadcopter or hexacopter drone platform can be used, flying at an altitude of 80-120 meters, equipped with 4K high-definition cameras to collect road traffic data of the target road, and achieving high-bandwidth real-time data transmission through a 5G network. Straight road sections are scanned from above, while complex road sections are covered by 30-degree oblique shots, with a 30% flight path overlap rate to ensure comprehensive monitoring. The data captured by the drone includes three files: xx_recordingMeta.csv, xx_tracks.csv, and xx_tracksMeta.csv, providing video metadata, vehicle trajectory data, and trajectory metadata, respectively. In this embodiment, road traffic data of the target road can be extracted from these three key files: xx_recordingMeta.csv (video metadata), xx_tracks.csv (vehicle trajectory data), and xx_tracksMeta.csv (trajectory metadata). The target road can be one or more specified roads, such as a road in a city or region.

[0072] The above embodiments, by acquiring road traffic data of the target road collected by drones, can achieve the collection of road traffic data covering the entire area of ​​the road, which can comprehensively reflect the behavior of all vehicles on the target road, thereby greatly reducing sampling bias.

[0073] Step S20: Extract traffic parameters from the road traffic data to obtain the first traffic parameters of the target road in the current time period.

[0074] In some embodiments, before extracting traffic parameters from road traffic data, the road traffic data may be preprocessed, such as denoising, enhancement, perspective correction, and image stitching, to improve the quality of the road traffic data.

[0075] In some embodiments, after acquiring road traffic data for the target road, traffic parameters can be extracted from the road traffic data to obtain the first traffic parameters of the target road in the current time period. The first traffic parameters may include the first traffic flow density and the first average traffic flow speed of the target road in the current time period, and may also include the temporal and spatial characteristics corresponding to the target road. The temporal characteristics may be features such as daily cycle sine and cosine, weekday / weekend, etc., while the spatial characteristics include the number of lanes and lane labels of the target road.

[0076] It should be noted that the relevant technologies only consider single traffic parameters (such as average speed or flow rate), ignoring multi-dimensional information such as traffic density and vehicle type distribution, and failing to fully utilize the rich information contained in multi-dimensional traffic data. In particular, the lack of differentiated processing for the impact of different vehicle types (passenger cars, trucks, etc.) reduces the prediction accuracy of traffic congestion status.

[0077] In this embodiment, by extracting two core traffic parameters—vehicle density and average vehicle speed—from road traffic data, and fully utilizing the rich information contained in multidimensional traffic data to predict traffic congestion, the prediction accuracy can be effectively improved. The following will explain in detail how to extract these traffic parameters.

[0078] Please see Figure 3 , Figure 3 This is a schematic flowchart illustrating a sub-step for extracting traffic parameters provided in an embodiment of this application. For example... Figure 3 As shown, step S20 involves extracting traffic parameters from the road traffic data to obtain the first traffic parameters of the target road in the current time period, which may include steps S201 to S203.

[0079] Step S201: Filter the vehicle trajectory of the road traffic data to obtain the vehicle trajectory information corresponding to the target road.

[0080] For example, vehicle trajectory information for a target road can be obtained by filtering road traffic data based on the lane identifier of each vehicle.

[0081] Step S202: Extract the vehicle identification number and driving data of each vehicle on the target road from the vehicle trajectory information.

[0082] For example, the vehicle identification number can be the vehicle's license plate number or serial number, and driving data can include driving direction and speed, etc.

[0083] In some embodiments, the YOLOv8 object detection algorithm and the DeepSORT tracking algorithm can be used to extract the vehicle identification number (VIN) and driving data of each vehicle on the target road from road traffic data or vehicle trajectory information. It should be noted that using the YOLOv8 object detection algorithm and the DeepSORT tracking algorithm can achieve accurate vehicle identification and trajectory tracking in road traffic data, simultaneously identify different types of vehicles and assign a unique identification number to each vehicle, and maintain a detection accuracy of over 95% and a tracking success rate of over 90% in complex road environments.

[0084] Step S203: Determine the first traffic flow density corresponding to the target road based on the vehicle identification number of each vehicle, and determine the average speed of the first traffic flow corresponding to the target road based on the driving data of each vehicle.

[0085] In some embodiments, determining the first traffic flow density corresponding to the target road based on the vehicle identification number of each vehicle includes: identifying the vehicle type based on the vehicle identification number of each vehicle and counting the number of vehicles corresponding to each vehicle type on the target road; converting the number of vehicles corresponding to each vehicle type to obtain the equivalent number of vehicles corresponding to the target road; and calculating the traffic flow density based on the equivalent number of vehicles and the number of vehicles corresponding to each vehicle type to obtain the first traffic flow density.

[0086] For example, since each vehicle's vehicle identification number (VIN) is unique, the vehicle type can be identified using its VIN, such as car, bus, or truck. Then, the number of vehicles of each type on the target road can be counted; for example, the number of vehicles of each type can be counted within a 5-minute period or other time intervals.

[0087] It should be noted that, considering the different impacts of different vehicle types on traffic flow, the vehicle equivalent method needs to be used when calculating traffic flow density, to convert different vehicle types into the same type of vehicle. For example, all vehicle types should be converted into passenger cars.

[0088] For example, the number of vehicles corresponding to each vehicle type is converted to the equivalent number of vehicles for the target road; the traffic flow density is calculated based on the equivalent number of vehicles and the number of vehicles corresponding to each vehicle type to obtain the first traffic flow density. Specifically, the equivalent number of vehicles can be divided by the total number of vehicles corresponding to all vehicle types to obtain the first traffic flow density, which can be represented as k(t).

[0089] The above embodiments, by converting the number of vehicles corresponding to each type of vehicle, obtain the equivalent number of vehicles corresponding to the target road. Based on the equivalent number of vehicles and the number of vehicles corresponding to each type of vehicle, traffic flow density is calculated. This allows for differentiated processing of the impact on different types of vehicles (buses, trucks, etc.), thereby ensuring the accuracy of the first traffic flow density and improving the prediction accuracy of subsequent traffic congestion status.

[0090] In some embodiments, determining the first average speed of traffic flow corresponding to the target road based on the driving data of each vehicle may include: calculating the driving speed of each vehicle in the driving direction within a preset time period based on the driving data of each vehicle; performing anomaly detection on the driving speed of each vehicle based on the interquartile range method, and deleting outliers in the driving speed of each vehicle; and calculating the average of the driving speeds after deleting outliers to obtain the first average speed of traffic flow.

[0091] Exemplarily, the preset duration can be set according to the actual situation, and the specific value is not limited herein. For example, the preset duration can be 1 second. The driving speed of each vehicle in the driving direction can be statistically calculated every 1 second based on the driving data of each vehicle. Then, based on the interquartile range method, the abnormal detection of the driving speed of each vehicle is performed, and the abnormal values in the driving speed of each vehicle are deleted. For example, the first quartile Q1 and the third quartile Q3 of the driving speed v can be calculated by using the interquartile range method (IQR) to obtain the interquartile range IQR = Q3 - Q1. If the driving speed v of a certain vehicle deviates from the median by more than 1.5 times IQR (i.e., v < Q1 - 1.5IQR or v > Q3 + 1.5IQR), then the driving speed v is marked as an abnormal value and excluded. Finally, the average value of the driving speed after deleting the abnormal values is calculated to obtain the average speed of the first traffic flow, and the first traffic flow density can be expressed as v(t).

[0092] In the above embodiment, by performing abnormal detection on the driving speed of each vehicle based on the interquartile range method and deleting the abnormal values in the driving speed of each vehicle, the reliability of the data can be improved.

[0093] In the embodiments of the present application, in order to improve the data quality, during the process of extracting parameters such as the first traffic flow density and the average speed of the first traffic flow, the relevant parameters need to be preprocessed, such as standardizing the parameters and filling in the missing values, etc. Among them, standardization means unifying the parameters with different dimensions to the interval [0, 1], and filling in the missing values means performing intelligent interpolation in combination with time proximity and spatial correlation to ensure the continuity of the parameters. The following will take filling in the missing values of the driving speed as an example for detailed description.

[0094] In some embodiments, according to the driving data of each vehicle, the driving speed of each vehicle in the driving direction within the preset duration is statistically calculated, and further includes: detecting the missing values of the driving speed of each vehicle, and determining the target vehicle whose driving speed is missing at the first moment; determining whether there is the driving speed of the target vehicle at the adjacent moment of the first moment in the driving data; if so, determining the driving speed of the target vehicle at the first moment according to the driving speed of the target vehicle at the adjacent moment; if not, determining the driving speed of the target vehicle at the first moment according to the driving speed of other vehicles in the adjacent lane of the target vehicle at the first moment.

[0095] Exemplarily, at the first moment t, if the driving speed of the target vehicle in lane 2 is missing, first check the driving speeds at the adjacent moments (t - 1 and t + 1) in the same lane. If these data do not exist, then examine the driving speeds in the adjacent lanes (lanes 1 and 3) at the moment t. The driving speed of other vehicles in lane 1 or lane 3 at the first moment t can be determined as the driving speed of the target vehicle at the first moment t.

[0096] In the above embodiment, by detecting missing values ​​for the driving speed of each vehicle and identifying the target vehicle whose driving speed is missing at the first moment, the missing value of the driving speed of the target vehicle can be filled in, thus ensuring the continuity of driving speed.

[0097] In some embodiments, the preprocessed data can also undergo multi-dimensional quality assessment, including integrity, accuracy, and consistency checks. When data quality is detected to be substandard, a feedback loop is triggered to adjust the preprocessing strategy, forming a closed-loop data quality assurance mechanism, thereby effectively improving data quality.

[0098] Step S30: Based on the first traffic parameters, perform time-series prediction of the traffic parameters of the target road to obtain the second traffic parameters of the target road in the first time period in the future.

[0099] For example, after extracting traffic parameters from road traffic data to obtain the first traffic parameters of the target road in the current time period, time-series prediction of the target road's traffic parameters can be performed based on the first traffic parameters to obtain the second traffic parameters of the target road in future time periods. The following will explain in detail how to predict the second traffic parameters for future time periods based on the traffic parameters of the current time period.

[0100] In some embodiments, the first traffic parameters include a first traffic density, a first average traffic speed, and the temporal and spatial characteristics corresponding to the target road; performing time-series prediction of the traffic parameters of the target road based on the first traffic parameters to obtain the second traffic parameters of the target road in the future first time period may include: generating an input sequence matrix based on the first traffic density, the first average traffic speed, the temporal characteristics, and the spatial characteristics; and inputting the input sequence matrix into a preset time-series prediction model for time-series prediction to obtain the second traffic parameters.

[0101] For example, the preset time-series prediction model can be a Bi-LSTM time-series prediction model. The Bi-LSTM model can simultaneously consider both forward and backward information flows from historical data, capturing the complete temporal dependencies in traffic data. It provides a more comprehensive feature representation than a unidirectional LSTM model, making it particularly suitable for time-series data like traffic flow, which exhibits periodicity and sequential correlation. Compared to traditional models, the Bi-LSTM time-series prediction model can provide confidence intervals for prediction results, offering a reliability assessment for emergency decision-making.

[0102] The Bi-LSTM time-series prediction model comprises an input layer, a bidirectional LSTM layer, a fully connected layer, and an output layer. It can predict traffic parameters for the next 30 seconds or other future time periods using traffic parameters from the past 300 seconds. When predicting traffic parameters, the input can include an input sequence matrix consisting of a first traffic flow density, a first traffic flow average speed, temporal features, and spatial features. The output includes a second traffic flow density, a second traffic flow average speed, and a prediction confidence interval for the future time period.

[0103] For example, an input sequence matrix can be generated based on the first traffic flow density, the first traffic flow average speed, temporal features, and spatial features. Here, the historical length T = 300, the prediction step size H = 30, and the input vector at each time t is:

[0104]

[0105] Where K(t) is the traffic density and V(t) is the average speed. φ time (t) includes time features such as daily cycle sine and cosine, weekday / weekend, etc. φ space (t) represents the spatial features of the target road (e.g., one-hot encoding of road segment numbers). The input vectors from the past 300 seconds are stacked into an input sequence matrix:

[0106]

[0107] Please see Figure 4 , Figure 4 This is a schematic flowchart illustrating a sub-step of timing prediction provided in an embodiment of this application. For example... Figure 4 As shown, it may include steps S301 to S305.

[0108] Step S301: Based on the bidirectional coding layer, the input sequence matrix is ​​bidirectionally encoded to obtain the first coding information and the second coding information.

[0109] For example, the input sequence matrix X can be... t The input is encoded by two LSTM links in a bidirectional coding layer, one forward and one backward, to obtain the first and second encoded information as follows:

[0110]

[0111] In the formula, Indicates the first encoded information, This represents the second encoded information, and k represents the time.

[0112] Step S302: Concatenate the first encoded information and the second encoded information to obtain the bidirectional hidden state corresponding to different times.

[0113] For example, bidirectional encoding is performed on the input sequence matrix to obtain the first encoded information. Second encoding information Then, the first encoded information can be... Second encoding information By concatenating the results, we obtain the bidirectional hidden states corresponding to k at different times:

[0114]

[0115] In the formula, h is the number of hidden units in a unidirectional LSTM.

[0116] Step S303: Perform average pooling on the bidirectional hidden states corresponding to the last time step to obtain aggregated features.

[0117] For example, the bidirectional hidden state h corresponding to the last time step can be... T Perform average pooling to obtain aggregated features:

[0118]

[0119] It should be noted that the features of the final time step include the features of all the preceding time steps.

[0120] Step S304: Based on multiple fully connected layers, perform multiple fully connected processing on the aggregated features to obtain the fully connected processing result.

[0121] For example, after obtaining the aggregation feature h agg Subsequently, aggregated features h can be performed based on multiple fully connected layers. agg Perform multiple fully connected operations to obtain the fully connected result:

[0122]

[0123] In the formula, W z b represents the weights of the fully connected layer. z σ represents the bias of the fully connected layer, m is the dimension of the hidden representation, and σ represents the ReLU activation function (max(0,x)).

[0124] Step S305: Determine the second traffic parameter based on the results of the fully connected processing.

[0125] For example, the fully connected processing result is input into the output layer to obtain the second traffic parameter, which is represented as follows:

[0126]

[0127] In the formula, Indicates the second traffic density in the future time period. W represents the average speed of the second traffic flow over a future time period. y and b y The linear mapping parameters are used to predict the mean.

[0128] Step S40: Based on the second traffic parameters, predict the traffic congestion status of the target road to obtain the traffic congestion probability of the target road in the first time period in the future.

[0129] For example, the future time period can be set according to the actual situation. For example, the future time period can be 0-5 minutes in the future, or 0-120 minutes in the future, etc.

[0130] For example, the Mamdani fuzzy inference system can be used to predict the traffic congestion status of a target road based on the second traffic flow density and the second traffic flow average speed obtained from time-series prediction. This enables accurate quantification of the traffic congestion status in future time periods and uses fuzzy inference logic to process the nonlinear and complex relationship between traffic flow parameters and congestion status.

[0131] It should be noted that the Mamdani fuzzy inference system comprises four steps: fuzzification, rule activation, rule aggregation, and defuzzification. Fuzzification is achieved using a triangular membership function; rule activation uses the min operator to perform an AND operation; rule aggregation uses the max operator to perform an OR operation; and defuzzification uses the centroid method, thus realizing the entire process from precise input to fuzzy inference and then to precise output. The following will detail how to use the Mamdani fuzzy inference system to predict traffic congestion status of a target road based on a second traffic flow density and a second average traffic flow speed.

[0132] Please see Figure 5 , Figure 5 This is a schematic flowchart illustrating the sub-steps of traffic congestion state prediction provided in an embodiment of this application. Figure 5 As shown, step S40 may include steps S401 to S405.

[0133] Step S401: Based on the triangular membership function, the second traffic flow density and the second traffic flow average speed are fuzzified to obtain the first fuzzy membership set corresponding to the second traffic flow density and the second fuzzy membership set corresponding to the second traffic flow average speed.

[0134] For example, based on the triangular membership function, the first fuzzy membership set corresponding to the second traffic flow density and the second fuzzy membership set corresponding to the second traffic flow average speed can be calculated, where the first fuzzy membership set can be represented as μ. i (k), the second fuzzy membership set can be represented as μ i (v).

[0135] Step S402: Activate each fuzzy rule in the preset fuzzy rule base according to the first fuzzy membership set and the second fuzzy membership set to obtain the initial activation degree corresponding to each fuzzy rule.

[0136] For example, rule activation refers to calculating the activation degree of each fuzzy rule. The formula for calculating the initial activation degree of the r-th fuzzy rule is as follows:

[0137] α r =min(μ i (k),μ i (v))

[0138] In the formula, α r This indicates the initial activation level.

[0139] In some embodiments, before activating each fuzzy rule in a preset fuzzy rule base according to a first fuzzy membership set and a second fuzzy membership set to obtain the initial activation degree corresponding to each fuzzy rule, the method further includes: classifying different values ​​of traffic flow density, average traffic flow speed, and traffic congestion probability based on a triangular membership function to obtain multiple fuzzy subsets of traffic flow density, multiple fuzzy subsets of average traffic flow speed, and multiple fuzzy subsets of traffic congestion status; constructing a fuzzy rule base based on the multiple fuzzy subsets of traffic flow density, multiple fuzzy subsets of average traffic flow speed, and multiple fuzzy subsets of traffic congestion status, wherein the fuzzy rule base includes at least one fuzzy rule, and each fuzzy rule is used to indicate the mapping relationship between traffic flow density, average traffic flow speed, and traffic congestion status.

[0140] For example, a triangular membership function can be designed to divide traffic flow density into three fuzzy subsets: "low," "medium," and "high"; average traffic flow speed into three fuzzy subsets: "low," "medium," and "high"; and traffic congestion probability into four fuzzy subsets: "low," "medium," "high," and "completely congested." A fuzzy rule base containing nine IF-THEN fuzzy rules is constructed, forming a nine-grid inference structure, as shown in Table 1.

[0141] Table 1. Fuzzy Rules in the Fuzzy Rule Base

[0142] Serial number Fuzzy rule Rule 1 If(k(t)is low)and(v(t)is low)then(P(t)is medium) Rule 2 If(k(t)is low)and(v(t)is medium)then(P(t)is low) Rule 3 If(k(t)is low)and(v(t)is high)then(P(t)is low) Rule 4 If(k(t)is medium)and(v(t)is low)then(P(t)is high) Rule 5 If(k(t)is medium)and(v(t)is medium)then(P(t)is medium) Rule 6 If(k(t)is medium)and(v(t)is high)then(P(t)is low) Rule 7 If(k(t)is high)and(v(t)is low)then(P(t)is full Rule 8 If(k(t)is high)and(v(t)is medium)then(P(t)is high) Rule 9 If(k(t)is high)and(v(t)is high)then(P(t)is medium)

[0143] In Table 1, P(t) represents the probability of traffic congestion; low indicates low, medium indicates medium, high indicates high, and full indicates complete congestion. For example, the fuzzy rule Rule 1: If (k(t) is low) and (v(t) is low) then (P(t) is medium) means that if the traffic density is "low" and the average traffic speed is "low", then the probability of traffic congestion is "medium".

[0144] Step S403: Cut the initial activation of each fuzzy rule according to the first fuzzy membership set and the second fuzzy membership set to obtain the target activation of each fuzzy rule.

[0145] It should be noted that step S403 is optional. In some embodiments, after activating each fuzzy rule in the fuzzy rule base and obtaining the initial activation degree corresponding to each fuzzy rule, step S404 can be executed directly instead of step S403.

[0146] For example, based on the first fuzzy membership set μ i (k), the second fuzzy membership set μ i (v) The initial activation α of the r-th fuzzy rule r After cropping, the formula for calculating the target activation degree corresponding to the r-th fuzzy rule is as follows:

[0147] μ r ′(x)=min(μ r (x),α r )

[0148] In the formula, μ(x) represents the first fuzzy membership set μ i (k), the second fuzzy membership set μ i Any value in (v).

[0149] It should be noted that the pruning operation uses the activation degree of the fuzzy rule as an upper limit to "truncate" the membership function of the output fuzzy membership set, thus controlling the impact of activation strength on the output result. In other words, it limits the maximum value of the membership function of the output fuzzy membership set to the activation level of the fuzzy rule.

[0150] Step S404: Aggregate the target activation degree corresponding to each fuzzy rule to obtain the target activation degree of each fuzzy rule under different traffic congestion states.

[0151] For example, the formula for calculating the target activation degree of each fuzzy rule under different traffic congestion states is as follows:

[0152]

[0153] In the formula, n represents the number of fuzzy rules, and m represents the number of target activations, which is the number of fuzzy subsets of different traffic congestion states (namely, the four fuzzy subsets of traffic congestion states: "low", "medium", "high" and "completely congested").

[0154] Step S405: Defuzzify the target activation degree of each fuzzy rule under different traffic congestion states to obtain the traffic congestion probability.

[0155] For example, after obtaining the target activation degree of each fuzzy rule under different traffic congestion states, the centroid method can be used to defuzzify the target activation degree of each fuzzy rule under different traffic congestion states to obtain the traffic congestion probability.

[0156] The output traffic congestion probability P(t)∈[0,1] is calculated using the centroid method, and the formula is as follows:

[0157]

[0158] In the formula, represents the center of the four fuzzy subsets of traffic congestion status.

[0159] In some implementations, taking a second traffic density of k = 30 vehicles / km and an average speed of v = 45km / h as an example, we can illustrate how to predict the probability of traffic congestion.

[0160] 1. Fuzzification: Using triangular membership functions to map precise values ​​to fuzzy sets.

[0161] For the second traffic density k = 30 vehicles / km, the first fuzzy membership set is: μlow(k) = 0.2, μmedium(k) = 0.7, μhigh(k) = 0.1.

[0162] For the second traffic flow with an average speed of v = 45 km / h, the second fuzzy membership set is: μlow(v) = 0.1, μmedium(v) = 0.8, μhigh(v) = 0.1.

[0163] 2. Rule Activation: Use the min operator to implement the AND operation. Take rule 5 in Table 1 above as an example:

[0164] Rule 5: If the traffic density is medium and the average traffic speed is medium, then the probability of traffic congestion is medium.

[0165] The calculated activation level α5 = min(0.7, 0.8) = 0.7.

[0166] 3. Rule aggregation: Use the max operator to implement the "OR" operation and aggregate the output of all active rules.

[0167] If rules 5 and 6 are activated at levels of 0.7 and 0.1 respectively, the aggregate output for "moderate congestion" is max(0.7,0) = 0.7, and the aggregate output for "low congestion" is max(0,0.1) = 0.1.

[0168] 4. Defuzzification: The centroid method is used to calculate the final accurate traffic congestion probability value.

[0169] The above embodiments, by sequentially performing operations such as fuzzification, rule activation, rule aggregation, and defuzzification based on the second traffic flow density and the second average traffic flow speed, can achieve accurate quantification of the traffic congestion probability of the target road in the future time period. This can reflect the continuity and fuzziness characteristics of road congestion, and solve the problem that related technologies usually use simple threshold methods to define the road congestion state, which lacks accurate quantification of the degree of road congestion and cannot accurately reflect the continuity and fuzziness characteristics of road congestion, thus leading to a large deviation between the road congestion assessment results and the actual situation. This can effectively improve the accuracy of traffic congestion prediction.

[0170] Step S50: If the probability of traffic congestion in the second consecutive time period is greater than or equal to the preset probability in the first time period in the future, then determine the emergency lane opening strategy for the target road.

[0171] In this embodiment, when the probability of traffic congestion in a second consecutive time period is greater than or equal to a preset probability within a first time period in the future, the emergency lane opening strategy for the target road is determined and executed. This enables the determination of the emergency lane opening strategy based on the probability of traffic congestion in a short period of time, improves the monitoring and response speed to sudden events or unconventional congestion, provides an efficient and accurate emergency lane opening strategy, and can effectively cope with complex traffic congestion problems.

[0172] For example, after predicting the traffic congestion status of the target road based on the second traffic parameters and obtaining the traffic congestion probability P(t) of the target road in the first time period in the future, it can be determined whether there is a second time period in the first time period where the traffic congestion probability P(t) is greater than or equal to a preset probability. If so, the emergency lane opening strategy for the target road is determined. For example, the first time period in the future can be 30 seconds; the second time period can be set according to the actual situation, such as 10 seconds, that is, it is determined whether there is a 10-second period in the next 30 seconds where the traffic congestion probability P(t) is greater than or equal to the preset probability P. m Wherein, the preset probability P m The value can be set according to the actual situation; the specific value is not limited here. For example, the preset probability P m It can be 0.75.

[0173] In some embodiments, determining the emergency lane opening strategy for a target road may include: determining initial opening parameters for the emergency lane and determining an initial opening scheme for the emergency lane based on the initial opening parameters; determining the stability of the initial opening scheme; if the stability of the initial opening scheme is greater than or equal to a preset stability threshold, determining a target opening scheme based on the initial opening scheme; if the stability of the initial opening scheme is less than the stability threshold, updating the initial opening parameters and returning to the step of determining the initial opening scheme for the emergency lane based on the initial opening parameters, until the stability of the initial opening scheme is greater than or equal to the stability threshold, determining the target opening scheme based on the current initial opening scheme; and determining the emergency lane opening strategy based on the target opening scheme.

[0174] For example, the preset stability threshold can be set according to the actual situation, and the stability threshold can be 0.95.

[0175] For example, when the stability of the initial activation plan is greater than or equal to a preset stability threshold, a target activation plan can be determined based on the current initial activation plan. It is understood that the current initial activation plan is the activation plan after updating the initial activation parameters, such as the activation plan after updating the initial activation duration. The target activation plan may include the activation time and duration of the emergency lane, and may also include the activation location and length of the emergency lane.

[0176] The initial opening parameters include the opening time, initial opening duration, time window length, and iteration step size. Determining the initial opening scheme for the emergency lane based on these parameters can include: using a rolling time window mechanism, iteratively optimizing the initial opening duration according to the opening time, time window length, and iteration step size, and predicting the traffic congestion status of the target road after closing the emergency lane, until the traffic congestion status meets preset conditions, stopping the iterative optimization, and determining the current initial opening duration as the target opening duration; and determining the initial opening scheme based on the opening time and the target opening duration.

[0177] It should be noted that the opening time refers to the moment when the emergency lane is opened; the initial opening duration refers to the initial value of the duration during which the emergency lane is opened, which can be optimized later; the time window length is the size of the window used to iteratively optimize the initial opening duration; and the iteration step size refers to the duration added each time the initial opening duration is optimized.

[0178] For example, the initial opening duration T0 can be set to 5 seconds, the time window length W to 300 seconds, and the iteration step size β to 1 second. The historical dataset and the dataset after the emergency lane is opened are initialized. Based on a rolling time window mechanism, the initial opening duration T0 is iteratively optimized. The composite dataset is updated in each iteration to predict the traffic congestion state of the target road after the emergency lane closes at time tc. Iterative optimization stops when the traffic congestion state meets the preset conditions, and the current initial opening duration is determined as the target opening duration.

[0179] The preset condition is that within the third time period after the emergency lane is closed, the probability of traffic congestion on the target road not exceeding or equal to the preset probability for a consecutive fourth time period. The third and fourth time periods can be set according to actual circumstances. This application does not limit this. For example, the third time period is 30 seconds and the fourth time period is 10 seconds. If, after the emergency lane is closed, the probability of traffic congestion on the target road within [tc+1, tc+30] is greater than or equal to the preset probability P for 10 consecutive seconds... m If so, increase the initial opening duration: T0(k+1) = T0(k) + β. Iterate until the traffic congestion state satisfies the condition that there are no consecutive 10-second congestion periods in the next 30 seconds.

[0180] For example, after stopping iterative optimization, the current initial startup duration can be determined as the target startup duration, and the initial startup scheme can be determined based on the startup time and the target startup duration.

[0181] It should be noted that existing decision-making regarding emergency lane opening strategies mainly relies on experience-based judgment or simple threshold rules, lacking precise quantification methods for the timing and duration of emergency lane opening, and failing to dynamically adapt to changes in traffic flow and adjust the opening strategy. However, in this embodiment, by using a rolling time window mechanism, the initial opening duration is iteratively optimized based on the opening time, time window length, and iteration step size, and the traffic congestion status of the target road after the emergency lane is closed is predicted until the traffic congestion status meets preset conditions. This allows for precise quantification of the emergency lane opening time and duration, enabling dynamic adaptation to changes in traffic flow, while avoiding the uncertainty of experience-based judgment and ensuring maximum traffic flow relief.

[0182] In this embodiment, after determining the initial opening scheme of the emergency lane based on the initial opening parameters, it is also necessary to determine the stability of the initial opening scheme. Specifically, the stability of the initial opening scheme of the emergency lane can be evaluated based on Markov chain theory, thereby determining the target opening scheme. The following will explain in detail how to determine the stability of the initial opening scheme.

[0183] Please see Figure 6 , Figure  6This is a schematic flowchart illustrating a sub-step for determining the stability of an initial startup scheme, as provided in an embodiment of this application. Figure 6 As shown, it may include steps S501 to S504.

[0184] Step S501: Construct the state transition probability matrix of the target road. The state transition probability matrix includes the first probability of the target road going from free flow to free flow, the second probability of going from free flow to traffic congestion, the third probability of going from traffic congestion to free flow, and the fourth probability of going from traffic congestion to traffic congestion.

[0185] For example, the state transition probability matrix is ​​shown below:

[0186]

[0187] In the formula, P ff Let P be the first probability of moving from free flow to free flow. fc The second probability, P, represents the transition from free flow to congestion. cf P represents the third probability of transitioning from traffic congestion to free flow. cc This represents the fourth probability of traffic congestion leading to further traffic congestion.

[0188] Step S502: Based on the state transition probability matrix, determine the corrected state transition probability matrix of the target road after the emergency lane is opened.

[0189] For example, the corrected state transition probability matrix can be derived from the traffic flow density function, as shown below:

[0190]

[0191] In the formula, P′ ff Let P′ be the first probability of moving from free flow to free flow. fc Let P′ be the second probability of transitioning from free flow to congestion. cf Let P′ be the third probability from traffic congestion to free flow. cc This represents the fourth probability of traffic congestion leading to further traffic congestion.

[0192] Step S503: Based on the modified state transition probability matrix, calculate the free flow probability of the target road in the third time period after the initial activation scheme is completed.

[0193] It should be noted that the initial opening direction is completed, which is also the closing time of the emergency lane. The closing time can be represented as t2, and the congestion state at closing time t2 is S(t2) = S free This refers to the free-flow state.

[0194] For example, taking a third time period of 30 seconds, this illustrates how to calculate the free-flow probability of the target road when the emergency lane is closed. The free-flow probability can be calculated using the following formula:

[0195]

[0196] For example, if the free-flow probability P after 30 seconds... free If (30) = 0.93, which is less than the stability threshold of 0.95, then return to the step of determining the initial opening scheme for the emergency lane based on the initial opening parameters, and extend the initial opening duration to improve the stability of the initial opening scheme. For example, when the initial opening duration is extended by 5 seconds, the calculated free-flow probability P free (30) = 0.96, which is greater than the stability threshold of 0.95. Therefore, the target opening scheme is determined based on the current initial opening scheme.

[0197] Step S504: Determine the stability of the initial start-up scheme based on the free flow probability.

[0198] For example, the free-flow probability can be used to determine the stability of the initial start scheme, that is, the free-flow probability can be used to measure the stability of the initial start scheme.

[0199] It should be noted that existing traffic diversion strategies lack theoretical support, their stability is difficult to guarantee, the long-term effects and risks of diversion measures cannot be assessed, and the recovery process of traffic conditions after diversion is lacking in prediction and control. In contrast, the embodiments of this application, based on Markov chain theory, evaluate the stability of the initial opening scheme of the emergency lane, and then determine the target opening scheme. This provides theoretical support and stability assurance for the opening of the emergency lane, and enables prediction and control of the recovery process of traffic conditions after diversion.

[0200] In this embodiment, before determining the emergency lane opening strategy based on the target opening scheme, the target opening scheme can be simulated and verified. After the target opening scheme passes the simulation verification, the emergency lane opening strategy is generated based on the target opening scheme. It should be noted that the simulation verification stage is optional, and the emergency lane opening strategy can also be generated directly based on the target opening scheme.

[0201] In some embodiments, determining an emergency lane opening strategy based on a target opening scheme includes: constructing a simulation environment identical to the target road on preset traffic simulation software, and determining road network data, vehicle parameters, and driving behavior parameters in the simulation environment; importing the road network data, vehicle parameters, and driving behavior parameters into the traffic simulation software for simulation testing to obtain first traffic indicator data for the target road in a baseline scenario; importing the road network data, vehicle parameters, driving behavior parameters, and the target opening scheme into the traffic simulation software for simulation testing to obtain second traffic indicator data for the target road in an emergency lane opening scenario; determining the improvement amount of the second traffic indicator data relative to the first traffic indicator data; and if the improvement amount is greater than a preset improvement threshold, determining that the target opening scheme has passed simulation verification.

[0202] For example, the preset traffic simulation software can be SUMO micro traffic simulation software, or other traffic simulation software.

[0203] For example, road network data may include: lane number and width settings, road length and connectivity, speed limit settings, and physical attributes of emergency lanes (width, location), etc. Vehicle parameters may include: vehicle type distribution, such as car, bus, and truck, with different equivalent coefficients; maximum speed distribution, which can be set based on the speed range observed in the AD4CHE dataset; acceleration characteristics, with different acceleration and deceleration capabilities set according to different vehicle types; vehicle length, set according to vehicle type, 4-5m for cars and 12-18m for trucks; driver imperfection factor: 0.3-0.8. Driving behavior parameters may include: lane change model parameters: LC2013; lane change intention threshold: 0.5-1.5; random lane change probability: 0.05-0.2; vehicle following model: Krauss model; reaction time: 0.5-1.5s.

[0204] In this embodiment, a comparative test can be performed, including a baseline scenario (i.e., emergency lanes not open) and an intervention scenario (emergency lanes open according to the target opening plan), and traffic indicator data can be collected under each scenario. Traffic indicator data can include macroscopic traffic flow parameters, microscopic traffic flow parameters, and time efficiency indicators. Macroscopic traffic flow parameters include: vehicle density (veh / km): spatial segment average and standard deviation; average vehicle speed (km / h): statistical values ​​in spatial and temporal dimensions; traffic flow (veh / h): throughput of each road segment and the overall network; lane utilization rate (%): the relative usage ratio of each lane. Microscopic traffic flow parameters can include: headway distribution (s): statistical values ​​for different vehicle types and traffic flow states; headway distribution (m): spatial distribution characteristics; acceleration / deceleration behavior distribution (m / s²): characterizing changes in vehicle motion state. Time efficiency indicators can include: average travel time (min): statistics for the entire road segment and segments; average delay time (min): time loss compared to free-flow conditions.

[0205] For example, road network data, vehicle parameters, and driving behavior parameters can be imported into traffic simulation software for simulation testing to obtain the first traffic indicator data of the target road under a baseline scenario; and road network data, vehicle parameters, driving behavior parameters, and the target lane opening scheme can be imported into traffic simulation software for simulation testing to obtain the second traffic indicator data of the target road under the scenario of opening the emergency lane. The specific process of the simulation testing can be found in relevant technologies and will not be elaborated here.

[0206] For example, when determining the improvement amount of the second traffic indicator data relative to the first traffic indicator data, the improvement amount between the second and first traffic indicator data can be calculated. It should be noted that in this embodiment, the success of the simulation verification of the target opening scheme can be determined based on one or more improvement amounts. For example, by comparing the average traffic speed in the second traffic indicator data with the average traffic speed in the first traffic indicator data, the improvement rate of the average traffic speed under the emergency lane opening scenario is obtained. When the improvement rate of the average traffic speed is greater than a preset improvement rate threshold (e.g., 20%), the target opening scheme is confirmed to have passed the simulation verification. As another example, by comparing the traffic flow in the second traffic indicator data with the traffic flow in the first traffic indicator data, the increase rate of traffic flow under the emergency lane opening scenario is obtained. When the increase rate of traffic flow is greater than a preset increase rate threshold (e.g., 10%), the target opening scheme is confirmed to have passed the simulation verification. As yet another example, when the improvement rate of the average traffic speed is greater than a preset improvement rate threshold (e.g., 20%), and the increase rate of traffic flow is greater than a preset increase rate threshold (e.g., 10%), the target opening scheme is confirmed to have passed the simulation verification.

[0207] For example, if the target opening scheme fails the simulation verification, the process returns to the initial opening scheme for determining the emergency lane based on the initial opening parameters, and determines the stability of the initial opening scheme. If the stability of the initial opening scheme is greater than or equal to a preset stability threshold, the process continues to determine the target opening scheme based on the initial opening scheme until the target opening scheme passes the simulation verification.

[0208] For example, when the target opening scheme passes simulation verification, an emergency lane opening strategy is generated based on the target opening scheme and preset implementation suggestion information.

[0209] The preset implementation suggestions may include: activating the emergency lane within 10-15 seconds after the traffic congestion probability first reaches the warning threshold (0.6); issuing an emergency lane activation warning through Intelligent Variable Message Sign (VMS) 15 seconds in advance; activating the warning light strips on both sides of the road at a frequency of 2Hz 10 seconds before activation; and pushing the message of activating the emergency vehicle to the vehicle equipment through Dedicated Short Range Communications (DSRC), etc.

[0210] It should be noted that existing systems generally lack systematic solutions, with a lack of tight integration between monitoring, prediction, decision-making, and execution, failing to form a closed-loop optimization mechanism and hindering continuous improvement in traffic flow. Furthermore, the lack of effective verification and evaluation mechanisms for decision-making results makes it difficult to objectively assess the effectiveness of traffic flow strategies and optimize decision parameters. In contrast, this application's embodiment establishes a traffic flow evaluation index system by simulating and verifying emergency lane opening schemes, achieving an effective verification and evaluation mechanism for the opening schemes. Based on the evaluation results, the opening schemes are optimized, forming a closed-loop optimization mechanism that significantly improves the effectiveness and adaptability of emergency lane opening strategies.

[0211] Step S60: Implement the emergency lane opening strategy.

[0212] For example, after determining the emergency lane opening strategy for the target road, the emergency lane opening strategy can be executed. For instance, the emergency lane opening strategy may include the opening time and duration of the emergency lane, as well as the opening location and length of the emergency lane. The emergency lane can be opened according to the opening time and location, and closed when the opening duration is reached. In this embodiment, when executing the emergency lane opening strategy, it can also be pushed to the traffic management system through a system interface, and the traffic management system will execute the emergency lane opening strategy.

[0213] Please see Figure 7 , Figure 7This is a schematic diagram of the overall process of a road traffic congestion relief method provided in an embodiment of this application. Figure 7 As shown, the steps S601 to S614 may be included.

[0214] S601: The drone autonomously plans and collects road sections, and collects road traffic data in real time.

[0215] Step S601 corresponds to step S10 above.

[0216] S602, Inspecting road vehicles.

[0217] S603, Extract the first traffic parameter for the current time period.

[0218] Step S603 corresponds to step S20 above. For example, traffic parameters can be extracted from road traffic data to obtain the first traffic parameters for the current time period.

[0219] S604, the second traffic parameter for predicting the first time period in the future.

[0220] Step S604 corresponds to step S30 above.

[0221] S605. Calculate the probability of traffic congestion in the first time period in the future.

[0222] Step S605 corresponds to step S40 above. For example, traffic congestion status can be predicted based on the second traffic parameters to obtain the probability of traffic congestion in the first time period in the future.

[0223] S606. Determine whether there is a probability of traffic congestion in a second consecutive time period within the first time period that is greater than or equal to a preset probability. If yes, proceed to step S607; otherwise, return to step S602.

[0224] S607. Initialize the initial opening parameters of the emergency lane.

[0225] For example, the initial start parameters may include the start time, the initial start duration, the time window length, and the iteration step size.

[0226] S608. Determine the initial opening scheme for the emergency lane based on the initial opening parameters.

[0227] For example, based on a rolling time window mechanism, the initial opening duration can be iteratively optimized according to the opening time, time window length, and iteration step size, and the traffic congestion status of the target road after the emergency lane is closed can be predicted until the traffic congestion status meets the preset conditions, at which point the iterative optimization stops, and the current initial opening duration is determined as the target opening duration; based on the opening time and the target opening duration, the initial opening plan is determined.

[0228] S609, Markov chain stability analysis.

[0229] Step S609 corresponds to steps S501 to S504 above.

[0230] S610. Determine whether the stability is greater than or equal to the preset stability threshold. If yes, proceed to step S611; otherwise, return to step S608.

[0231] S611. Determine the target activation plan.

[0232] For example, when the stability of the initial activation scheme is greater than or equal to a preset stability threshold, the target activation scheme is determined based on the initial activation scheme.

[0233] S612. Simulate and verify the target activation scheme.

[0234] For example, a simulation environment identical to the target road can be constructed on pre-set traffic simulation software, and the road network data, vehicle parameters, and driving behavior parameters in the simulation environment can be determined. The road network data, vehicle parameters, and driving behavior parameters are then imported into the traffic simulation software for simulation testing to obtain the first traffic indicator data of the target road in the baseline scenario. The road network data, vehicle parameters, driving behavior parameters, and the target opening scheme are then imported into the traffic simulation software for simulation testing to obtain the second traffic indicator data of the target road in the scenario of opening the emergency lane. The improvement of the second traffic indicator data relative to the first traffic indicator data is determined. If the improvement is greater than a pre-set improvement threshold, the target opening scheme is determined to have passed simulation verification.

[0235] S613. Determine whether the target activation scheme has passed simulation verification. If yes, proceed to step S614; otherwise, return to step S607.

[0236] S614, Generate emergency lane opening strategy.

[0237] The embodiments of this application also provide a computer-readable storage medium storing a computer program, the computer program including program instructions, and a processor executing the program instructions to implement any of the road traffic congestion relief methods provided in the embodiments of this application.

[0238] For example, when the program is loaded by the processor, it can perform the following steps:

[0239] Acquire road traffic data of the target road collected by drone; extract traffic parameters from the road traffic data to obtain the first traffic parameters of the target road in the current time period; perform time-series prediction of the traffic parameters of the target road based on the first traffic parameters to obtain the second traffic parameters of the target road in the next first time period; predict the traffic congestion status of the target road based on the second traffic parameters to obtain the traffic congestion probability of the target road in the next first time period; if there is a traffic congestion probability in the next second time period that is greater than or equal to a preset probability, determine the emergency lane opening strategy for the target road; execute the emergency lane opening strategy.

[0240] The computer-readable storage medium can be an internal storage unit of the computer device described in the foregoing embodiments, such as a hard disk or memory of the computer device. The computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD card), flash card, etc., provided on the computer device.

[0241] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0242] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0243] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for alleviating road traffic congestion, characterized in that, The method includes: Acquire road traffic data of the target road by drone; Traffic parameters are extracted from the road traffic data to obtain the first traffic parameters of the target road in the current time period; Based on the first traffic parameters, the traffic parameters of the target road are predicted in a time series to obtain the second traffic parameters of the target road in the future first time period; Based on the second traffic parameters, the traffic congestion status of the target road is predicted to obtain the traffic congestion probability of the target road in the first future time period. If the probability of traffic congestion in a consecutive second time period within the first future time period is greater than or equal to a preset probability, then the emergency lane opening strategy for the target road is determined. Implement the emergency lane opening strategy; The step of determining the emergency lane opening strategy for the target road includes: determining initial opening parameters for the emergency lane, and determining an initial opening scheme for the emergency lane based on the initial opening parameters; determining the stability of the initial opening scheme; if the stability of the initial opening scheme is greater than or equal to a preset stability threshold, then determining the target opening scheme based on the initial opening scheme; if the stability of the initial opening scheme is less than the stability threshold, then updating the initial opening parameters, and returning to the step of determining the initial opening scheme for the emergency lane based on the initial opening parameters, until the stability of the initial opening scheme is greater than or equal to the stability threshold, then determining the target opening scheme based on the current initial opening scheme; and determining the emergency lane opening strategy based on the target opening scheme. Determining the stability of the initial opening scheme includes: constructing a state transition probability matrix for the target road, the state transition probability matrix including a first probability of the target road transitioning from free flow to free flow, a second probability of transitioning from free flow to traffic congestion, a third probability of transitioning from traffic congestion to free flow, and a fourth probability of transitioning from traffic congestion to traffic congestion; determining a corrected state transition probability matrix for the target road after opening the emergency lane based on the state transition probability matrix; calculating the free flow probability of the target road in a third time period after the initial opening scheme is completed based on the corrected state transition probability matrix; and determining the stability of the initial opening scheme based on the free flow probability.

2. The method for alleviating road traffic congestion according to claim 1, characterized in that, The initial opening parameters include the opening time, initial opening duration, time window length, and iteration step size; determining the initial opening scheme of the emergency lane based on the initial opening parameters includes: Based on the rolling time window mechanism, the initial opening duration is iteratively optimized according to the opening time, the time window length and the iteration step size, and the traffic congestion status of the target road after the emergency lane is closed is predicted until the traffic congestion status meets the preset conditions, at which point the iterative optimization stops and the current initial opening duration is determined as the target opening duration. The initial activation scheme is determined based on the activation time and the target activation duration.

3. The method for alleviating road traffic congestion according to claim 1, characterized in that, Before determining the emergency lane opening strategy based on the target opening scheme, the method further includes: A simulation environment identical to the target road is constructed on a pre-set traffic simulation software, and road network data, vehicle parameters, and driving behavior parameters are determined in the simulation environment. The road network data, vehicle parameters, and driving behavior parameters are imported into the traffic simulation software for simulation testing to obtain the first traffic index data of the target road under the benchmark scenario. The road network data, vehicle parameters, driving behavior parameters, and target opening scheme are imported into the traffic simulation software for simulation testing to obtain the second traffic indicator data of the target road under the scenario of opening the emergency lane. Determine the improvement of the second traffic indicator data relative to the first traffic indicator data; If the increase in the indicator is greater than the preset increase threshold, then the target activation scheme is determined to have passed the simulation verification. The step of determining the emergency lane opening strategy based on the target opening plan includes: When the target opening scheme passes simulation verification, the emergency lane opening strategy is generated based on the target opening scheme and preset implementation suggestion information.

4. The method for alleviating road traffic congestion according to claim 1, characterized in that, The first traffic parameters include a first traffic density and a first average traffic speed; the step of extracting traffic parameters from the road traffic data to obtain the first traffic parameters of the target road in the current time period includes: The road traffic data is filtered by vehicle trajectory to obtain the vehicle trajectory information corresponding to the target road; Extract the vehicle identification number and driving data of each vehicle on the target road from the vehicle trajectory information; The first traffic density corresponding to the target road is determined based on the vehicle identification number of each vehicle, and the average speed of the first traffic flow corresponding to the target road is determined based on the driving data of each vehicle.

5. The method for alleviating road traffic congestion according to claim 4, characterized in that, Determining the first traffic density corresponding to the target road based on the vehicle identification number of each vehicle includes: Vehicle type identification is performed based on the vehicle identification number of each vehicle, and the number of vehicles corresponding to each vehicle type on the target road is counted. The number of vehicles corresponding to each of the aforementioned vehicle types is converted to the vehicle type number to obtain the equivalent number of vehicles corresponding to the target road. The first traffic flow density is obtained by calculating the traffic flow density based on the equivalent number of vehicles and the number of vehicles corresponding to each type of vehicle.

6. The method for alleviating road traffic congestion according to claim 4, characterized in that, Determining the average speed of the first traffic flow corresponding to the target road based on the driving data of each vehicle includes: The driving speed of each vehicle in the driving direction is calculated within a preset time period based on the driving data of each vehicle. The interquartile range method is used to detect anomalies in the driving speed of each vehicle, and outliers in the driving speed of each vehicle are deleted. The average speed of the first traffic flow is obtained by averaging the driving speeds after removing outliers.

7. The method for alleviating road traffic congestion according to claim 6, characterized in that, The method further includes: calculating the speed of each vehicle in the driving direction within a preset time period based on the driving data of each vehicle. For each vehicle, a missing value detection is performed on its driving speed, and the target vehicle with a missing driving speed at the first moment is identified. Determine whether the driving data contains the driving speed of the target vehicle at a time adjacent to the first time. If it exists, then the speed of the target vehicle at the first moment is determined based on the speed of the target vehicle at the adjacent time. If it does not exist, the speed of the target vehicle at the first moment is determined based on the speed of other vehicles in the adjacent lanes of the target vehicle at the first moment.

8. The method for alleviating road traffic congestion according to claim 1, characterized in that, The first traffic parameters include the first traffic density, the first average traffic speed, and the temporal and spatial characteristics of the target road; The step of performing time-series prediction of the traffic parameters of the target road based on the first traffic parameters to obtain the second traffic parameters of the target road in the future first time period includes: An input sequence matrix is ​​generated based on the first traffic flow density, the first traffic flow average speed, the time characteristics, and the spatial characteristics. The input sequence matrix is ​​input into a preset time series prediction model for time series prediction to obtain the second traffic parameter.

9. The method for alleviating road traffic congestion according to claim 8, characterized in that, The step of inputting the input sequence matrix into a preset time-series prediction model for time-series prediction to obtain the second traffic parameters includes: Based on the bidirectional coding layer, the input sequence matrix is ​​bidirectionally encoded to obtain first coding information and second coding information; By concatenating the first encoded information and the second encoded information, the bidirectional hidden states corresponding to different times are obtained; The bidirectional hidden states corresponding to the last time step are subjected to average pooling to obtain aggregated features; Based on multiple fully connected layers, the aggregated features are processed multiple times to obtain the fully connected processing result; The second traffic parameter is determined based on the results of the fully connected processing.

10. The method for alleviating road traffic congestion according to claim 1, characterized in that, The second traffic parameters include a second traffic density and a second average traffic speed; the step of predicting the traffic congestion status of the target road based on the second traffic parameters to obtain the traffic congestion probability of the target road in the future first time period includes: Based on the triangular membership function, the second traffic flow density and the second traffic flow average speed are fuzzified to obtain the first fuzzy membership set corresponding to the second traffic flow density and the second fuzzy membership set corresponding to the second traffic flow average speed. Based on the first fuzzy membership set and the second fuzzy membership set, each fuzzy rule in the preset fuzzy rule base is activated to obtain the initial activation degree corresponding to each fuzzy rule; The initial activation degree of each fuzzy rule is cut according to the first fuzzy membership degree set and the second fuzzy membership degree set to obtain the target activation degree corresponding to each fuzzy rule; Aggregate the target activation degree corresponding to each fuzzy rule to obtain the target activation degree of each fuzzy rule under different traffic congestion states; The target activation degree of each fuzzy rule under different traffic congestion states is defuzzified to obtain the traffic congestion probability.

11. The method for alleviating road traffic congestion according to claim 10, characterized in that, Before activating each fuzzy rule in the preset fuzzy rule base according to the first fuzzy membership set and the second fuzzy membership set to obtain the initial activation degree corresponding to each fuzzy rule, the method further includes: Based on the triangular membership function, different values ​​of traffic density, average traffic speed and traffic congestion probability are classified to obtain multiple fuzzy subsets of traffic density, multiple fuzzy subsets of average traffic speed and multiple fuzzy subsets of traffic congestion status. The fuzzy rule base is constructed based on multiple fuzzy subsets of traffic flow density, multiple fuzzy subsets of average traffic flow speed, and multiple fuzzy subsets of traffic congestion status. The fuzzy rule base includes at least one fuzzy rule, and each fuzzy rule is used to indicate the mapping relationship between the traffic flow density, the average traffic flow speed, and the traffic congestion status.

12. A computer device, characterized in that, The computer device includes a processor and memory; The memory is used to store computer programs; The processor is configured to execute the computer program and, in executing the computer program, implement the road traffic congestion relief method as described in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to implement the road traffic congestion relief method as described in any one of claims 1 to 11.

Images