Simulation-based hub linear passenger area parking space layout method and system

Abstract

The invention discloses a hub linear passenger area parking space layout method and system based on simulation, and relates to the technical field of urban traffic planning. According to the method, real traffic flow data is obtained based on a monitoring video, analysis on the duration time and the occurrence frequency of the human-vehicle behaviors is combined, a fitting model of the behavior duration time and a relation model of the occurrence frequency of the human-vehicle behaviors and the traffic flow are established, and therefore the complexity and the randomness of the human-vehicle interaction behaviors in the actual traffic environment can be accurately reflected. On the basis, a plurality of temporary parking space layout schemes are generated in the available space, and the schemes are simulated by using the established model, so that traffic efficiency data closer to the actual operation condition can be obtained. And finally, by optimizing the layout scheme, the space occupation minimization is realized on the premise of ensuring the passing efficiency, so that the parking space layout of the boarding area achieves the optimal balance between the space utilization and the passing capacity.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban traffic planning, in particular to a simulation-based hub linear passenger pickup area parking space layout method and system. BACKGROUND

[0002] The urban traffic hub is a key connection point in the urban traffic network, plays a key role in connecting different traffic modes and realizing efficient gathering and dispersing of passenger flow, and with the development of mobile Internet and the popularization of the sharing economy concept, the connection service of network car-hailing has become an important traffic means for hub transfer. Parking facilities are an indispensable part of the hub, and the implementation of passenger pickup (especially pickup) by hub parking lots is a common management method. There are usually multiple passenger pickup areas for network car-hailing in the parking lot, and once the passenger pickup area runs out of stability and disorder, it will not only cause overall congestion in the parking lot, but also may affect the urban road traffic, thereby significantly reducing the service level of the hub.

[0003] The main research directions of the existing hub passenger pickup area are two kinds. On the one hand, quantitative research is carried out by using queuing theory model to calculate the passing time or queue length, and on the other hand, qualitative research is mainly carried out from the management mode, analyzes the use of different management modes and makes improvements. However, the pedestrians randomly walk through the traffic flow, the vehicles need to constantly yield, and there will be vehicles changing lanes and other behaviors, and the traffic flow is slow; the interaction between people and vehicles is not only limited to mutual recognition, but also needs to consider the influence of carrying luggage on the delay time, and the diversification of people and vehicle purposes makes it difficult to predict their behavior. The design scheme based on the existing idealized model is difficult to accurately predict the running efficiency under the real traffic flow, so that the parking space layout of the passenger pickup area cannot achieve the optimal balance between space utilization and traffic capacity. SUMMARY

[0004] The present application provides a simulation-based hub linear passenger pickup area parking space layout method and system, which can achieve the optimal balance between space utilization and traffic capacity of the parking space layout of the passenger pickup area.

[0005] In a first aspect, the present application provides a simulation-based hub linear passenger pickup area parking space layout method, which comprises: obtaining a plan view and a monitoring video of a hub parking lot linear passenger pickup area, and determining traffic flow data according to the monitoring video; analyzing the monitoring video to obtain people-vehicle behavior duration data and people-vehicle behavior frequency data, establishing a behavior duration fitting model based on the people-vehicle behavior duration data, and establishing a relationship model between people-vehicle behavior frequency and traffic flow based on the people-vehicle behavior frequency data; The available space of the right lane of the passenger drop-off area is determined according to the plan view, and a plurality of layout schemes of temporary parking spaces are generated in the available space, wherein adjacent temporary parking spaces are spaced apart by a preset interval; Based on the traffic flow data, the fitting model and the relationship model, each of the layout schemes is simulated to obtain the traffic efficiency of each layout scheme. Each of the layout schemes is optimized according to the traffic efficiency to obtain a target layout scheme that meets the traffic efficiency and occupies the minimum space.

[0006] By adopting the above technical solutions, based on the real traffic flow data obtained from the monitoring video, combined with the analysis of the duration and frequency of human-vehicle behaviors, a fitting model of behavior duration and a relationship model of human-vehicle behavior frequency and traffic flow are established, so as to accurately reflect the complexity and randomness of human-vehicle interaction behaviors in the actual traffic environment. On this basis, by generating a plurality of temporary parking space layout schemes in the available space and simulating each scheme by using the established model, traffic efficiency data closer to the actual operating conditions can be obtained. Finally, by optimizing the layout scheme, the space occupation is minimized under the premise of ensuring the traffic efficiency, so that the layout of the parking spaces in the passenger drop-off area achieves an optimal balance between space utilization and traffic capacity, avoiding the problem that the traditional idealized model is difficult to accurately predict the running efficiency of the real traffic flow.

[0007] In a second aspect of the present application, a simulation-based hub straight passenger drop-off area parking space layout system is provided, which comprises: A data acquisition module is configured to acquire a plan view of a hub parking lot straight passenger drop-off area and monitoring video, and determine traffic flow data according to the monitoring video; A model establishment module is configured to analyze the monitoring video to obtain human-vehicle behavior duration data and human-vehicle behavior frequency data, establish a fitting model of behavior duration based on the human-vehicle behavior duration data, and establish a relationship model of human-vehicle behavior frequency and traffic flow based on the human-vehicle behavior frequency data; A scheme generation module is configured to determine the available space of the right lane of the passenger drop-off area according to the plan view, and generate a plurality of layout schemes of temporary parking spaces in the available space, wherein adjacent temporary parking spaces are spaced apart by a preset interval; A scheme simulation module is configured to simulate each of the layout schemes based on the traffic flow data, the fitting model and the relationship model to obtain the traffic efficiency of each layout scheme. A scheme optimization module is configured to optimize each of the layout schemes according to the traffic efficiency to obtain a target layout scheme that meets the traffic efficiency and occupies the minimum space.

[0008] In a third aspect of the present application, a computer storage medium is provided, which stores a plurality of instructions suitable for being loaded and executed by a processor to perform the method steps described above.

[0009] In a fourth aspect of the present application, an electronic device is provided, which comprises a processor and a memory; wherein the memory stores a computer program suitable for being loaded and executed by the processor to perform the method steps described above.

[0010] To sum up, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: Based on the real traffic flow data obtained from the monitoring video, and in combination with the analysis of the duration and frequency of the human-vehicle behavior, the fitting model of the behavior duration and the relationship model between the human-vehicle behavior frequency and the traffic flow are established, so as to accurately reflect the complexity and randomness of the human-vehicle interaction behavior in the actual traffic environment. On this basis, by generating a plurality of temporary parking space layout schemes in the available space, and using the established model to simulate each scheme, the traffic efficiency data closer to the actual operation condition can be obtained. Finally, through the optimization of the layout scheme, the space occupation is minimized under the premise of ensuring the traffic efficiency, so that the parking space layout of the passenger drop-off area reaches the optimal balance between the space utilization and the traffic capacity, thereby avoiding the problem that the traditional idealized model is difficult to accurately predict the real traffic flow operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 is a flowchart of a simulation-based hub straight-line type passenger drop-off area parking space layout method provided by the embodiments of the present application; Figure 2 is a parking lot and passenger drop-off area monitoring range distribution diagram provided by the embodiments of the present application; Figure 3 is a traffic time, parking space number and vehicle spacing relationship diagram provided by the embodiments of the present application; Figure 4 is a module schematic diagram of a simulation-based hub straight-line type passenger drop-off area parking space layout system provided by the embodiments of the present application; Figure 5 is a structural schematic diagram of an electronic device provided by the embodiments of the present application.

[0012] Explanation of reference signs: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0013] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in combination with the accompanying drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0014] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0015] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used only for the purpose of description, and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0016] Please refer to Figure 1 , a flowchart of a simulation-based hub linear passenger pickup area parking space layout method is specifically proposed. The method can be realized by relying on a computer program, can be realized by relying on a single-chip microcomputer, and can run on a simulation-based hub linear passenger pickup area parking space layout system. The computer program can be integrated in a computer device or run as an independent tool application. Specifically, the method includes steps 10 to 50, and the steps are as follows: Step 10: Obtain the plan view and monitoring video of the hub parking lot linear passenger pickup area, and determine the traffic flow data according to the monitoring video.

[0017] The embodiments of the present application can be applied to large traffic hub parking lots that need to manage the pickup of online car-hailing, such as the online car-hailing dedicated pickup area in the parking lot of a traffic hub such as a train station, an airport, a passenger station, etc.

[0018] Specifically, in order to obtain traffic flow data for subsequent analysis and optimization, the plan of the straight passenger pickup area of the hub parking lot and the monitoring video need to be obtained. First, the plan can be obtained from the parking lot management department, which contains the specific size and layout information of the passenger pickup area. Second, at least 7 days of real-time monitoring video is retrieved from the monitoring system deployed in the parking lot, such as the peak period video from 7:00 to 22:00 every day. Through video analysis software, vehicle recognition and counting are performed on the monitoring video, and the number of vehicles entering the passenger pickup area, the stay time and the leaving time per hour are recorded, so as to obtain the traffic flow data. This way can accurately obtain the actual operation data, which provides the basis for subsequent optimization.

[0019] As an optional embodiment, the step of obtaining the plan of the straight passenger pickup area of the hub parking lot and the monitoring video, and determining the traffic flow data according to the monitoring video, further comprises the following steps: Step 101: Obtain the plan of the hub parking lot, and determine the straight channels according to the plan, and judge whether each straight channel meets the preset passenger pickup area condition, which at least includes: the straight channel has no widening, the straight channel has at least two one-way lanes, the lane width of the straight channel is greater than the preset width, and the longitudinal length of the straight channel is greater than the preset length.

[0020] Step 102: The straight channel meeting the preset passenger pickup area condition is taken as the passenger pickup area.

[0021] Specifically, in order to select a suitable straight channel as a passenger pickup area, first, the plan obtained from the parking lot management department is needed, which contains the specific size and layout information of all channels in the parking lot. According to the road identification in the plan, the position and direction of all straight channels can be identified, and each straight channel can be measured and judged to determine whether it meets the preset passenger pickup area condition: using CAD measurement tool to check whether the two side lines of the channel are parallel without widening; confirming whether the channel has at least two same-direction lanes; measuring whether the width of each lane is greater than the preset 3.5 meters; measuring whether the longitudinal length of the channel is greater than the preset 20 meters; comparing the measurement data with the preset condition to screen out the straight channel meeting all conditions, and taking the straight channel meeting the preset passenger pickup area condition as the passenger pickup area.

[0022] Step 103: Obtain the number and time point of vehicles entering the passenger pickup area in the monitoring video of the passenger pickup area, and convert it into traffic flow data per unit time.

[0023] Specifically, in order to obtain accurate traffic data, it is necessary to analyze the monitoring video of the pick-up area. First, the high-definition video of the entrance of the pick-up area for 7 consecutive days is called from the parking lot monitoring system, such as selecting the operation period of 7:00-22:00 every day. The video is processed using video analysis software: identify each vehicle entering the pick-up area through a vehicle detection algorithm, record the entry time point; the recorded time point data is counted by hour, and the number of vehicles entering each hour is calculated; the hourly vehicle number is converted into the traffic unit of vehicles / hour. This automatic analysis method can accurately obtain the traffic variation law and provide data support for subsequent optimization.

[0024] Step 20: Analyze the monitoring video to obtain the duration data and frequency data of the human-vehicle behavior, establish a fitting model of the behavior duration based on the duration data, and establish a relationship model between the behavior frequency and traffic based on the behavior frequency data.

[0025] In the embodiments of the present application, the fitting model refers to fitting the actually collected traffic data points with the theoretical curve by mathematical statistical method, and establishing a mathematical model describing the variation law of traffic with time. For example, polynomial regression, exponential smoothing and other methods can be used to fit discrete traffic data into continuous function curves.

[0026] The relationship model refers to the corresponding relationship between traffic and service level established by data analysis, which is used to evaluate the running state of the pick-up area under different traffic. The model takes traffic data as input variable, and takes parking space occupancy rate, waiting time and other service indicators as output variable, reflecting the quantitative relationship between them.

[0027] As an optional embodiment, the step of analyzing the monitoring video to obtain the duration data and frequency data of the human-vehicle behavior, establishing a fitting model of the behavior duration based on the duration data, and establishing a relationship model between the behavior frequency and traffic based on the behavior frequency data, further includes the following steps: Step 201: Determine the type of human-vehicle behavior that affects the delay of the channel by scene induction of the monitoring video, and the type of human-vehicle behavior includes at least pick-up parking and parking for picking up.

[0028] Specifically, in order to study the specific reasons for the channel delay, it is necessary to analyze the behavior patterns of people and vehicles in the monitoring video. By observing the monitoring video for several consecutive days, the typical scenes causing channel delay are focused on. Based on video analysis, the behavior of people and vehicles is summarized into two main types: pick-up parking behavior (referring to the case where passengers directly get on the vehicle after the vehicle stops) and parking waiting for passengers behavior (referring to the case where the vehicle waits for passengers after stopping), and other lane changing behaviors, and the overall delay caused is mainly related to the frequency of the above behaviors and the influence time. In actual observation, the pick-up parking behavior is manifested as a complete process of vehicle arrival, passenger boarding, luggage loading, and vehicle departure; the parking waiting for passengers behavior is manifested as a process of waiting for passengers after the vehicle arrives. Through this behavior classification, the influence degree of different types of behaviors on channel delay can be accurately identified.

[0029] Step 202: Statistically analyze the duration data and frequency data of each type of people and vehicle behavior.

[0030] Specifically, after determining the type of people and vehicle behavior, the time characteristics of each type of behavior need to be quantitatively analyzed. Using video analysis software, the duration from the time when the vehicle stops to the time when it leaves for each pick-up parking behavior is recorded, and the duration from the time when the vehicle stops to the time when the passenger arrives for each parking waiting for passengers behavior is recorded. At the same time, the number of times each type of behavior occurs in each hour is counted as frequency data. In specific operation, the behavior in each time period is marked: the start time and end time of the pick-up parking behavior are recorded, and the duration is calculated; the waiting time of the parking waiting for passengers behavior is recorded; the number of times each type of behavior occurs in each hour is counted. This accurate data collection method can provide a reliable data basis for subsequent modeling.

[0031] Step 203: Based on the duration data of each type of people and vehicle behavior, a linear regression model for pick-up parking behavior and a probability distribution model for parking waiting for passengers behavior are established.

[0032] Specifically, with the increase of traffic flow, the frequency of pick-up parking behavior shows a gradual upward trend. When the traffic flow is small, the road is relatively smooth, and due to the relatively small passenger source, the frequency of pick-up parking behavior is low. With the continuous increase of traffic flow, the number of vehicles on the road increases, and the demand for pick-up also increases. The relationship between the frequency of pick-up parking behavior and the traffic flow is fitted using a decision tree model, and the goodness of fit R² value is 0.882. The frequency of pick-up parking behavior is mainly dominated by traffic flow. Using the results of the decision tree model, the frequency of pick-up parking behavior is generated under the corresponding traffic flow, and the frequency of pick-up parking behavior is converted into the probability of pick-up parking for vehicles entering the pick-up area at that time.

[0033] The frequency of waiting for passengers initially increases and then decreases with increasing traffic volume, showing a significant reduction in waiting behavior during periods of high traffic volume. The frequency of waiting for passengers is determined using the same method as above, employing a decision tree model for fitting. The goodness-of-fit R² value is 0.518. The frequency of waiting for passengers is generated for each corresponding traffic flow, and this frequency is converted into the probability of a vehicle entering the pick-up area stopping to wait for passengers at that moment. Based on this probability, the destination is determined for each vehicle upon entry.

[0034] To calculate the delay time caused by the two types of vehicle behavior mentioned above, this application embodiment summarizes the influencing factors through scenario induction, calculates their duration, and allocates them to specific vehicles according to probability distribution. For passenger pick-up parking behavior, since its process is relatively fixed, a linear regression model is used: factors such as the number of passengers and the amount of luggage are used as independent variables, and the parking duration is used as the dependent variable. The linear equation is obtained by fitting the model using the least squares method. For parking and waiting for passengers behavior, due to its randomness, a probability distribution model is used: the collected waiting time data is subjected to histogram analysis, and the most suitable probability distribution type (such as negative exponential distribution or Weiber distribution) is determined through chi-square test. The distribution parameters are calculated. These models can accurately describe the time characteristics of different behaviors and provide a theoretical basis for assessing channel delays.

[0035] As an optional implementation, the step of establishing a linear regression model for passenger pick-up parking behavior and a probability distribution model for parking and waiting for passengers based on the duration data of each type of passenger and vehicle behavior further includes the following steps: Step 301: Extract factors that influence the duration of passenger pick-up and parking behavior, including the number of passengers getting in the car, whether passengers open the trunk to put their luggage in, and whether the driver gets out of the car to help with the luggage.

[0036] Specifically, to accurately analyze the factors influencing the duration of passenger pick-up and parking behavior, key influencing factors were extracted through monitoring video data analysis and on-site observation. First, the number of passengers boarding the vehicle during each pick-up process was recorded and categorized into five cases: 1 person, 2 people, 3 people, 4 people, and 5 people. Second, whether passengers opened the trunk to place luggage was observed and recorded, marked as yes (1) or no (0). Finally, whether the driver got out of the vehicle to assist in carrying luggage was observed and also marked as yes (1) or no (0). This multi-dimensional factor extraction method can comprehensively reflect the key variables affecting parking time.

[0037] Step 302: Establish a linear regression model of influencing factors and the duration of passenger pick-up parking.

[0038] Specifically, for passenger pick-up and parking behavior, the main influencing factors include: the number of passengers getting into the car, whether passengers open the trunk to put luggage in the car, and whether the driver gets out of the car to help with the luggage. In this embodiment, a linear regression model is used to describe its duration characteristics, and the regression formula is as follows: ; In the formula, T is the time of picking up passengers, n is the number of passengers getting on the vehicle, and n can take values 1, 2, 3, 4, 5...n; t passenger represents whether the passenger opens the trunk to put luggage on the vehicle (1 for yes and 0 for no); t driver is whether the driver gets off the vehicle to help carry the luggage (1 for yes and 0 for no).

[0039] Exemplarily, in a parking lot of a certain train station, the probabilities of the number of passengers being 1, 2, 3, 4, and 5 are 0.579, 0.337, 0.036, 0.036, and 0.012, respectively. The probability of the passenger opening the trunk to put luggage on the vehicle is 0.216, and the probability of the passenger not opening the trunk is 0.784. The probability of the driver getting off the vehicle to help carry the luggage is 0.096, and the probability of the driver not getting off the vehicle to help carry the luggage is 0.904. According to the above probabilities, random values of the three parameters are taken, and the time of parking and waiting for passengers is finally calculated and assigned to a random vehicle.

[0040] Step 303: Perform distribution characteristic analysis on the duration data of the parking and waiting for passengers behavior to determine the long-tail distribution characteristic of the parking and waiting for passengers behavior.

[0041] Specifically, in order to determine the time distribution characteristic of the parking and waiting for passengers behavior, statistical analysis is performed on the collected duration data. Through statistical analysis on the parking and waiting for passengers time data collected for 7 consecutive days, it is found that the data distribution presents a clear long-tail characteristic: about 80% of the parking and waiting for passengers time is concentrated in the 10-30 second interval, but there are a small number of extreme cases with a duration of more than 60 seconds. The skewness and kurtosis coefficients of the data are calculated to confirm that it has a significant right-skewed distribution characteristic, and the distribution curve rapidly decreases in a short time interval and presents a slow decay "long tail" phenomenon in a long time interval. The identification of this distribution characteristic provides a basis for subsequent selection of a suitable probability distribution model.

[0042] Step 304: Based on the long-tail distribution characteristic, use the Cauchy distribution to fit the duration data of the parking and waiting for passengers behavior to obtain a probability distribution model with a location parameter and a scale parameter.

[0043] Specifically, for the long-tail distribution characteristic of the parking and waiting for passengers behavior, the Cauchy distribution is used for data fitting, and the Cauchy probability distribution is as follows: ; In the formula, μ is the location parameter, which determines the center position of the distribution, and in this formula, the value is 16.114; γ is the scale parameter, which determines the width of the distribution, and in this formula, the value is 6.084; π is the circular constant, which is approximately equal to 3.14159; P(X) is the probability of the parking time being x.

[0044] The goodness of fit is obtained: R2= 0.842, and the parking time is assigned to the vehicle waiting for passengers in the simulation according to the probability distribution curve, and it should be noted that the parking time generated by the Cauchy distribution may tend to infinity, while in the actual situation, the waiting time for passengers is generally not more than two minutes, so the generated parking time greater than two minutes is regenerated.

[0045] Step 204: Based on the frequency data of each person's vehicle behavior type, a decision tree model is used to establish the relationship model between the frequency of picking up passengers and the traffic volume.

[0046] Specifically, in order to accurately describe the relationship between the frequency of human-vehicle behavior and the traffic volume, a decision tree model is used to model the two behavior types. For the behavior of picking up passengers, the hourly traffic volume is used as the input variable, and the behavior frequency is used as the output variable, which is fitted by the decision tree algorithm, and the goodness of fit R2=0.882 is obtained. The analysis results show that the frequency of picking up passengers gradually increases with the increase of traffic volume: in the low traffic period, due to the lack of passengers, the frequency of picking up passengers is low; with the increase of traffic volume, the demand for picking up passengers increases, and the frequency of behavior improves.

[0047] For the behavior of waiting for passengers, the same decision tree model is used for fitting, and the goodness of fit R2=0.518 is obtained. The analysis results show that its frequency increases first and then decreases with the change of traffic volume: it reaches the peak in the medium traffic volume, and it decreases significantly in the high traffic environment. Based on these two relationship models, the corresponding behavior frequency can be calculated according to the current traffic volume, and it is converted into the behavior probability of the vehicle entering the passenger pickup area, which is used to determine the specific behavior type of each entering vehicle. This modeling method based on decision tree can effectively reflect the nonlinear relationship between human-vehicle behavior and traffic volume.

[0048] Step 30: Determine the available space of the right lane of the passenger pickup area according to the plan view, and generate multiple temporary parking space layout schemes in the available space, wherein the adjacent temporary parking spaces are separated by a preset interval.

[0049] Specifically, in order to meet the demand for temporary parking, first obtain the plan view of the right lane of the passenger pickup area, and measure the length of the available space. Under the premise of ensuring the smoothness of the fire access, the available space is divided into multiple temporary parking spaces. Considering the convenience of vehicle entry and exit, a preset interval of 2.5 meters is set between adjacent temporary parking spaces. According to the size of the standard vehicle and the length of the available space, the maximum number of parking spaces that can be arranged is calculated, and multiple parking space layout schemes are generated. This layout method not only ensures the safe distance of vehicle parking, but also realizes the efficient use of space.

[0050] As an optional embodiment, based on the duration data of each type of vehicle behavior, the step of generating a plurality of layout schemes of temporary parking spaces in the available space further comprises the following steps: Step 401: Calculate the maximum number of parking spaces that can be accommodated in the available space according to the preset length of a single temporary parking space and the preset interval.

[0051] Specifically, according to the straight plan of the pick-up area, temporary parking spaces are set in the right lane. Through the add.xml configuration file of the SUMO simulation software, each temporary parking space type is set to busStop, and the length of a single parking space is set to 5 meters. Considering the safety interval requirement for vehicle entry and exit, the preset interval between adjacent parking spaces is set to 2-5 meters. Assuming that the total length of the available space in the right lane is L meters, the maximum number of parking spaces that can be accommodated is calculated according to the formula: maximum parking space number N = L / (5+d) down rounding (where d is the preset interval). This calculation method not only ensures sufficient operating space, but also avoids space waste.

[0052] Step 402: Simulate within the maximum number of parking spaces to generate a plurality of different layout schemes, each layout scheme including a plurality of different layouts of temporary parking spaces and waiting areas for parking vehicles when temporary parking spaces are insufficient.

[0053] Specifically, based on the maximum number of parking spaces N, a plurality of layout schemes are generated in the SUMO environment. First, 3 meters at the beginning of the right lane are reserved as a buffer zone, and then the remaining space is divided into a parking area and a waiting area. 2-5 temporary parking spaces are set in the parking area, each parking space is 5 meters long, the interval between adjacent parking spaces is 2-5 meters, and all parking spaces are arranged on the right to ensure the smoothness of the left lane. A waiting area is set upstream of the parking area, with a length equal to the length of the remaining available space, to queue vehicles when temporary parking spaces are insufficient during peak hours, avoiding overflow vehicles occupying the left lane. Through SUMO simulation, the vehicle traffic efficiency under different layout schemes is tested to provide a basis for determining the optimal layout.

[0054] Step 40: Based on the traffic data, the fitting model and the relationship model, simulate each layout scheme to obtain the traffic efficiency of each layout scheme.

[0055] Specifically, to evaluate the effects of different layout schemes, a pick-up area model is established using the SUMO simulation software. The measured traffic data is input, the vehicle parking time is determined according to the previously established fitting model, and the behavior type of the vehicle is assigned through the relationship model. Each layout scheme is simulated, and indicators such as passing time, queue length, and vehicle delay are recorded. The number of vehicles successfully passing through per unit time is calculated to obtain the traffic efficiency of each scheme. This multi-model joint simulation method can comprehensively evaluate the actual operation effect of the layout scheme.

[0056] As an optional embodiment, based on the traffic data, the fitting model and the relationship model, the simulation of each layout scheme is performed to obtain the traffic efficiency of each layout scheme, and the step further includes the following steps. Step 501: setting the vehicle generation frequency according to the traffic data, and setting the behavior type and behavior duration of each vehicle according to the fitting model and the relationship model.

[0057] Specifically, based on the peak traffic data, the generation frequency of the entering vehicles is set to be 4 vehicles per minute, that is, the probability of generating a vehicle per simulation second is 0.067. When the vehicle is generated, the initial position of the vehicle entering the left lane or the right lane is randomly allocated. According to the previously established decision tree relationship model, it is determined whether each vehicle needs to stop, and for the vehicle that needs to stop, the behavior type (pick-up parking or parking to wait for passengers) and the corresponding parking duration are allocated through the linear regression fitting model and the Cauchy distribution model. The parameter setting based on the measured data ensures the consistency of the simulation process with the actual operation.

[0058] Step 502: according to the vehicle generation frequency, the behavior type and the behavior duration of each vehicle, the following simulation steps are performed for each layout scheme: controlling the vehicles to randomly enter any lane of the pick-up area, when the vehicle drives into a preset distance of any target temporary parking space, for the vehicle located in the right lane, keeping straight driving; for the vehicle located in the left lane, detecting whether there is a lane changing opportunity in the right lane, when the lane changing opportunity is detected, changing the lane, and when the lane changing opportunity is not detected, keeping straight driving and continuously detecting the lane changing opportunity until driving into the target temporary parking space or the waiting area.

[0059] Specifically, the following simulation steps are performed for each layout scheme: control each vehicle to enter the passenger pickup area randomly into any lane, when the vehicle enters a preset distance, such as 10 meters, of any target temporary parking space, trigger the behavior control logic under different scenarios: for vehicles in the right lane, directly adopt the straight-through strategy to approach the target parking space. If the target parking space is occupied, continue to drive to the waiting area to queue. The system monitors the vehicle position in real time through the vehicle detector to ensure that the vehicle can accurately park in the designated position. For vehicles in the left lane that need to park, the right lane state is detected every 0.1 seconds. The detection range includes the vehicle gap within 15 meters before and after the target position in the right lane. When the distance between the front and rear vehicles is greater than 8 meters and 5 meters respectively, it is determined that there is a safe opportunity to change lanes. The lane changing process adopts a gradual method to complete the lateral position change within 2 seconds to ensure the smoothness of lane changing. If no lane changing opportunity is detected, the vehicle continues to drive and keeps detecting until it enters the target temporary parking space or the waiting area. For vehicles waiting in the right lane, when an empty parking space appears in front of them, the bypass mechanism is triggered: first, detect whether there is a safe gap of more than 10 meters in the left lane, if so, change lanes to the left, drive quickly to the target parking position, and then detect whether it is safe to change lanes to the right to enter the parking space. During the entire bypass process, safety gap detection is continuously performed to ensure that lane changing operations do not affect other vehicle traffic.

[0060] Step 503: Within a preset simulation time, count the vehicle traffic data of each layout scheme, and calculate the traffic efficiency of each layout scheme based on the vehicle traffic data.

[0061] Specifically, within a preset simulation time, such as 24 hours, comprehensive data collection and efficiency evaluation are performed for each layout scheme. The entire process data of each vehicle from entering the passenger pickup area to leaving is recorded, including time node information such as entry time, parking time, and exit time, as well as vehicle behavior trajectory data. When there is serious congestion in the passenger pickup area (e.g., the waiting area is full and spills over to the upstream road section), the recording is directly stopped. The total number of vehicles entering the system and the number of vehicles successfully completing the parking task are counted to calculate the parking success rate. At the same time, the number of lane changing requests and the number of successful lane changes are recorded to obtain the lane changing success rate. Based on the ratio of the actual travel time of each vehicle to the theoretical shortest travel time, the time utilization efficiency is calculated. In addition, the turnover rate of each parking space is calculated, i.e., the number of parking services completed by each parking space within 24 hours. The above multiple efficiency indicators are weighted and calculated, such as the parking success rate weight is 0.4, the lane changing success rate weight is 0.2, the time utilization efficiency weight is 0.2, and the parking space turnover rate weight is 0.2, to obtain the comprehensive traffic efficiency of the layout scheme.

[0062] Step 50: According to the traffic efficiency, optimize each layout scheme to obtain a target layout scheme that meets the traffic efficiency and occupies the smallest space.

[0063] Specifically, based on the traffic efficiency score of each layout scheme, an iterative optimization method is used to determine the target layout. First, schemes with traffic efficiency of 90% or more are screened, and the occupied space (including the total length of parking space length, spacing, and waiting area length) of these schemes is calculated. Then, by gradually adjusting the parking space spacing (within 2-5 meters) and waiting area length, multiple improved schemes are generated. For the improved schemes, re-simulation evaluation is performed, and when the traffic efficiency decreases by less than 5%, the scheme with the smallest occupied space is selected as the optimization result. This progressive optimization method ensures both traffic efficiency and maximization of space utilization.

[0064] As an optional embodiment, the step of optimizing each layout scheme according to traffic efficiency to obtain a target layout scheme that meets traffic efficiency and has the smallest occupied space further includes the following steps: Step 601: Screen out layout schemes with traffic efficiency greater than a preset traffic efficiency threshold as candidate layout schemes.

[0065] Specifically, to ensure the basic feasibility of the layout scheme, a preset traffic efficiency threshold is first set, which can be set according to actual conditions or experience. The comprehensive traffic efficiency of all layout schemes is evaluated, including the weighted calculation results of parking success rate, lane changing success rate, time utilization efficiency, and parking space turnover rate. The evaluation results are sorted from high to low according to the efficiency value, and the schemes with traffic efficiency greater than the preset traffic efficiency threshold are selected as candidate layout schemes. This threshold-based preliminary screening can effectively reduce the computational load of subsequent optimization, while ensuring that the final scheme meets the basic operational requirements.

[0066] Step 602: Optimize the temporary parking space spacing and the number of temporary parking spaces in each candidate layout scheme.

[0067] Specifically, the selected candidate layout schemes are refined and optimized. First, the basic layout form of each scheme is kept unchanged, and the temporary parking space spacing is adjusted within the range of 2-5 meters with a step of 0.5 meters. At the same time, considering the space constraint condition, the number of temporary parking spaces is adjusted to vary within the range of 2-5. For each spacing and number combination, the total occupied space length is calculated. To improve optimization efficiency, a grid search method is used to form an optimization matrix of spacing and number combinations, systematically generating multiple optimization schemes. This fine-tuned parameter adjustment ensures the comprehensiveness and feasibility of scheme optimization.

[0068] Step 603: Simulate and evaluate each optimized candidate layout scheme, and select the layout scheme with the smallest space occupation under the condition of meeting the preset traffic efficiency threshold as the target layout scheme.

[0069] Specifically, the optimized candidate solutions undergo a 24-hour simulation evaluation. During the evaluation, the traffic efficiency index of each solution is monitored in real time to ensure it remains above 90%. Simultaneously, the space occupancy of each solution is calculated, including the total length of parking spaces, the total spacing, and the length of the waiting area. Solutions meeting the traffic efficiency requirements are sorted by space occupancy from smallest to largest, and the solution with the smallest space occupancy is selected as the target layout. If multiple solutions have similar space occupancy (difference less than 1 meter), their traffic efficiency is further compared, and the more efficient solution is selected. This multi-dimensional evaluation and selection method ensures both the operational efficiency of the solutions and the optimal utilization of space resources.

[0070] In another feasible embodiment, the layout schemes can be optimized using the following methods to obtain a target layout scheme that satisfies traffic efficiency and occupies minimal space: Specifically, the simulation system first analyzes the passenger pick-up area traffic status by controlling the variable method, that is, by changing only the number of temporary parking spaces or only the spacing between temporary parking spaces. Then, it considers the impact of both on the length and traffic status of the passenger pick-up area, controls the overall length of the passenger pick-up area, and improves the traffic status of the passenger pick-up area as much as possible to obtain the overall optimization result.

[0071] Please refer to Table 1 for the classification of passage status in the passenger pick-up area. The passage status in the passenger pick-up area can be defined as the following four levels:

[0072] The occupancy length of parking spaces in the passenger pick-up area is calculated using the following formula: In the formula, L is the total length of the boarding area; n parking s represents the number of parking spaces; s represents the distance between adjacent parking spaces.

[0073] The formula for calculating the delay time in the boarding area is as follows: In the formula, T represents the delay time for passing through the boarding area; P parking P waitting、 P lanechange These refer to the frequency of passenger pick-up parking, parking while waiting for passengers, and lane changing under the corresponding traffic flow conditions; t parking t waitting、 t lanechange These are the delays caused by picking up passengers, waiting for passengers, and changing lanes.

[0074] The number of temporary parking spaces was varied from 3 to 5, with a distance of no less than 7.5m between spaces and a variation range of 0.5m. The simulation was run multiple times to explore the impact of s on the total length L of the passenger pick-up area and the travel time T, in order to find the optimal solution. The solution was then verified under actual traffic flow. If the traffic flow level can be significantly improved, the temporary parking space layout method of the passenger pick-up area in the simulation system is considered to have played a beneficial role.

[0075] Exemplarily, in order to better understand the scheme provided by the embodiments of the present application, taking the related data of a 100m-long drop-off area and a parking lot as an example, the specific implementation steps are as follows: Firstly, the straight drop-off area plan and the related parameters such as the number of lanes and the lane width are obtained, as shown in Figure 2 Figure 2 is the monitoring range distribution diagram of the parking lot and the drop-off area provided by the embodiments of the present application; the drop-off area adopts a double-lane design and is divided into four functional zones A, B, C and D as a whole, and is provided with independent vehicle entrances and exits. The specific layout of the drop-off point for network car, the civil air defense facilities (including window gates and stairs), the column position, the ordinary parking space and the barrier-free parking space is indicated in the figure. In order to realize omnidirectional monitoring, 18 monitoring points (numbered 1-18) are arranged at key positions, the coverage range of each monitoring point is indicated by a triangular area, and the monitoring ranges form an overlap to ensure that there is no monitoring blind area. The plan layout diagram provides the basic data required for subsequent optimization, including the lane width, the parking space size, the passing space and other key parameters, which provides specific basis for the generation and optimization of the next layout scheme.

[0076] Then, the delay time and the occurrence frequency caused by the behavior of people and vehicles are counted through the drop-off area monitoring video, and the behavior duration fitting model and the relationship model between the occurrence frequency of people and vehicle behavior and the traffic volume are established.

[0077] In the simulation, a straight drop-off area is constructed, and temporary parking spaces are arranged in the right lane, a distance is arranged between each temporary parking space, and the specific number of parking spaces and the distance length are adjusted later, and a waiting area is arranged upstream of the temporary parking space.

[0078] The peak traffic is generated into the field, and the vehicles that need to be temporarily parked try to change lanes to the right lane in advance to prepare for parking, the vehicle behavior and the behavior duration are set according to the fitting model, when the drop-off area produces serious congestion overflow, the simulation system is evaluated and analyzed, the number and spacing of temporary parking spaces are adjusted and analyzed, the optimal number and spacing of parking spaces are determined, and the appropriate drop-off area length and passing state are ensured.

[0079] Please refer to Table 2 for the relationship between the parking space spacing, the number of parking spaces and the drop-off area length.

[0080] ; Please refer to Table 3 for the relationship between the parking space spacing, the number of parking spaces and the drop-off area passing time.

[0081] ; Please refer to Figure 3 ​The relationship diagram between the passing time and the number of parking spaces and the distance between the parking spaces provided for the embodiments of the present application shows the trend of the change of the passing time under the conditions of different numbers of temporary parking spaces (3, 4 and 5) and different distances between the parking spaces (7.5 meters to 9.5 meters). In combination with Figure 3 It can be seen that when the number of temporary parking spaces is 3, the passing time fluctuates greatly with the change of the distance between the parking spaces, and reaches a peak of about 85 seconds when the distance is 8 meters, and then gradually decreases to about 70 seconds when the distance is 9.5 meters. When the number of temporary parking spaces is 4, the passing time is generally lower than that when the number of temporary parking spaces is 3, and the fluctuation range is relatively small. In the distance range of 7.5 meters to 9.5 meters, the passing time remains between 45-55 seconds. When the number of temporary parking spaces is 5, the passing time is the most stable, the curve fluctuation is the smallest, and the passing time basically remains between 40-45 seconds, showing the best passing efficiency.

[0082] According to the results of Tables 2 and 3 above, if the passenger boarding area space is relatively sufficient, four parking spaces with a distance of 8 meters should be taken, at this time the total length of the passenger boarding area is 29 meters, and the passing level is B. For the case of small traffic flow or insufficient passenger boarding area space, three parking spaces with a distance of 3.5 meters can be considered, only 20 meters of occupied space is needed, and the passing level can reach C.

[0083] Please refer to Figure 4 A module schematic diagram of a hub linear passenger boarding area parking space layout system based on simulation provided for the embodiments of the present application, wherein the system comprises: A data acquisition module, configured to acquire a plan view and a monitoring video of a hub parking lot linear passenger boarding area, and determine traffic flow data according to the monitoring video; A model establishment module, configured to analyze the monitoring video to obtain human-vehicle behavior duration data and human-vehicle behavior frequency data, establish a fitting model of behavior duration based on the human-vehicle behavior duration data, and establish a relationship model of human-vehicle behavior frequency and traffic flow based on the human-vehicle behavior frequency data; A scheme generation module, configured to determine the available space of the right lane of the passenger boarding area according to the plan view, and generate a plurality of layout schemes of temporary parking spaces in the available space, wherein the adjacent temporary parking spaces are spaced apart by a preset distance; A scheme simulation module, configured to simulate each of the layout schemes based on the traffic flow data, the fitting model and the relationship model to obtain the passing efficiency of each layout scheme; A scheme optimization module, configured to optimize each of the layout schemes according to the passing efficiency to obtain a target layout scheme that meets the passing efficiency and occupies the minimum space.

[0084] Optionally, the data acquisition module is further configured to acquire a plan of the hub parking lot, and determine straight passages according to the plan, and determine whether each straight passage meets preset passenger pickup area conditions, the preset passenger pickup area conditions including at least that the straight passage has no width expansion, the straight passage has at least two one-way lanes, a lane width of the straight passage is greater than a preset width, and a longitudinal length of the straight passage is greater than a preset length. The straight passage meeting the preset passenger pickup area conditions is taken as a passenger pickup area. The data acquisition module is further configured to acquire a number and a time point of vehicles entering the passenger pickup area in a monitoring video of the passenger pickup area, and convert the number and the time point into traffic flow data in a unit time.

[0085] Optionally, the model establishment module is further configured to determine types of human-vehicle behaviors affecting passage delay by scene induction on the monitoring video, the types of human-vehicle behaviors including at least passenger pickup parking and passenger pickup waiting. The model establishment module is further configured to statistically acquire duration data and frequency data of each type of human-vehicle behavior. The model establishment module is further configured to establish a linear regression model of the passenger pickup parking behavior and a probability distribution model of the passenger pickup waiting behavior based on the duration data of each type of human-vehicle behavior. The model establishment module is further configured to establish a relationship model of the frequency of the passenger pickup parking behavior and the traffic flow and a relationship model of the frequency of the passenger pickup waiting behavior and the traffic flow by using a decision tree model based on the frequency data of each type of human-vehicle behavior.

[0086] Optionally, the model establishment module is further configured to extract factors affecting the duration data of the passenger pickup parking behavior, including a number of passengers getting on a vehicle, whether a trunk of the vehicle is opened to put luggage, and whether a driver gets off the vehicle to help carry the luggage. The model establishment module is further configured to establish a linear regression model of the factors and the duration of the passenger pickup parking behavior. The model establishment module is further configured to analyze distribution characteristics of the duration data of the passenger pickup waiting behavior, and determine long-tail distribution characteristics of the passenger pickup waiting behavior. The model establishment module is further configured to fit the duration data of the passenger pickup waiting behavior by using a Cauchy distribution based on the long-tail distribution characteristics, and obtain a probability distribution model with a location parameter and a scale parameter.

[0087] Optionally, the scheme generation module is further configured to calculate a maximum number of parking spaces accommodated in the available space according to a preset length of a single temporary parking space and a preset interval. The scheme generation module is further configured to simulate in a range of the maximum number of parking spaces, and generate a plurality of different layout schemes, each of the layout schemes including a plurality of different layouts of temporary parking spaces and waiting areas, the waiting areas being used to park vehicles when the temporary parking spaces are insufficient.

[0088] Optionally, the scheme simulation module is further configured to set a vehicle generation frequency according to the traffic flow data, and set a behavior type and a behavior duration of each vehicle according to the fitting model and the relationship model; According to the vehicle generation frequency, the behavior type and the behavior duration of each vehicle, the following simulation steps are performed on each layout scheme: controlling each vehicle to randomly enter any lane of the passenger drop-off area, keeping straight for a vehicle located in a right lane when the vehicle drives into a preset distance of a target temporary parking space, detecting whether there is a lane-changing opportunity for a vehicle located in a left lane, changing lane when the lane-changing opportunity is detected, keeping straight and continuously detecting the lane-changing opportunity when the lane-changing opportunity is not detected, and driving into the target temporary parking space or a waiting area. Within a preset simulation duration, vehicle traffic data of each layout scheme is counted, and traffic efficiency of each layout scheme is calculated according to the vehicle traffic data.

[0089] Optionally, the scheme optimization module is further configured to select a layout scheme with traffic efficiency greater than a preset traffic efficiency threshold as a candidate layout scheme. The distance between temporary parking spaces and the number of temporary parking spaces in each candidate layout scheme are optimized. The optimized candidate layout schemes are simulated and evaluated, and a layout scheme with the smallest space occupation under the condition of meeting the preset traffic efficiency threshold is selected as a target layout scheme.

[0090] It should be noted that: the system provided in the above embodiments, in order to realize its function, only the above-mentioned division of each functional module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be described here.

[0091] The computer storage medium provided in the embodiments of the present application can store a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above-mentioned simulation-based hub straight passenger drop-off area parking space layout method. The specific execution process can be referred to the specific description of the above-mentioned embodiments, which will not be described here.

[0092] Please refer to Figure 5 The present application also discloses an electronic device. Figure 5 is a structural schematic diagram of an electronic device disclosed by the embodiments of the present application. The electronic device 300 can include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0093] The communication bus 302 is configured to realize the connection communication between the components.

[0094] The user interface 303 can include a display and a camera. Optionally, the user interface 303 can further include a standard wired interface and a wireless interface.

[0095] The network interface 304 can optionally include a standard wired interface and a wireless interface (e.g., a WI-FI interface).

[0096] The processor 301 can include one or more processing cores. The processor 301 is connected to various parts of the server through various interfaces and lines, and performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one of a digital signal processing, a field programmable gate array, and a programmable logic array. The processor 301 can be integrated with one or a combination of a central processing unit, an image processor, and a modem. The CPU is mainly used to process an operating system, a user interface, and an application program. The GPU is used to render and draw the content to be displayed on the display. The modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be implemented by a separate chip.

[0097] The memory 305 can include a random access memory and a read-only memory. Optionally, the memory 305 includes a non-transitory computer readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 can include a program storage area and a data storage area. The program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 305 can optionally be at least one storage device located away from the above-mentioned processor 301. Referring to Figure 5 The memory 305, as a computer storage medium, can include an operating system, a network communication module, a user interface module, and an application program of the simulated hub linear passenger boarding area parking space layout method.

[0098] In Figure 5In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 301 can be used to invoke an application program of a simulated hub straight passenger boarding area parking space layout method stored in the memory 305, which, when executed by one or more processors 301, causes the electronic device 300 to perform the method of one or more of the above-described embodiments. It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0099] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0100] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, and the division of units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some service interface, device or unit, and can be electrical or other forms.

[0101] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0102] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0103] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned memory includes: a U disk, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0104] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the specification and the practical true disclosure.

[0105] The present application is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field not recorded in the present disclosure.

Claims

1. A simulation-based hub linear passenger pick-up area parking space layout method, characterized in that, The method comprises: acquiring a plan view and monitoring video of a straight passenger pickup area of a hub parking lot, and determining vehicle flow data from the monitoring video; analyzing the monitoring video to obtain human-vehicle behavior duration data and human-vehicle behavior frequency data, establishing a fitting model of behavior duration based on the human-vehicle behavior duration data, and establishing a relationship model of human-vehicle behavior frequency and vehicle flow based on the human-vehicle behavior frequency data; determining available space of a right lane of the passenger pickup area from the plan view, and generating a plurality of layout schemes of temporary parking spaces in the available space, wherein adjacent temporary parking spaces are spaced apart by a preset interval; based on the vehicle flow data, the fitting model and the relationship model, simulating each layout scheme to obtain a traffic efficiency of each layout scheme; optimizing each layout scheme according to the traffic efficiency to obtain a target layout scheme that meets the traffic efficiency and occupies the minimum space.

2. The simulated-based hub linear-type passenger boarding area parking space layout method according to claim 1, characterized in that, The acquisition of the plan view and the monitoring video of the straight passenger pickup area of the hub parking lot, and the determination of the vehicle flow data from the monitoring video, comprises: acquiring a plan view of a hub parking lot, and determining straight passages from the plan view, and judging whether each straight passage meets a preset passenger pickup area condition, the preset passenger pickup area condition at least including that the straight passage has no widening, the straight passage has at least two one-way lanes, the lane width of the straight passage is greater than a preset width, and the longitudinal length of the straight passage is greater than a preset length; regarding the straight passage meeting the preset passenger pickup area condition as a passenger pickup area; acquiring the number and time point of vehicles entering the passenger pickup area in the monitoring video of the passenger pickup area, and converting them into vehicle flow data per unit time.

3. The simulated-based hub linear-type passenger boarding area parking space layout method according to claim 1, characterized in that, The analysis of the monitoring video to obtain human-vehicle behavior duration data and human-vehicle behavior frequency data, the establishment of a fitting model of behavior duration based on the human-vehicle behavior duration data, and the establishment of a relationship model of human-vehicle behavior frequency and vehicle flow based on the human-vehicle behavior frequency data, comprises: determining human-vehicle behavior types affecting passage delay by scene induction of the monitoring video, the human-vehicle behavior types at least including passenger pickup parking and passenger pickup waiting; statistically analyzing duration data and frequency data of each human-vehicle behavior type; based on the duration data of each human-vehicle behavior type, establishing a linear regression model of passenger pickup parking behavior and a probability distribution model of passenger pickup waiting behavior; based on the frequency data of each human-vehicle behavior type, establishing a relationship model of the frequency of passenger pickup parking behavior and passenger pickup waiting behavior and vehicle flow by using a decision tree model.

4. The simulated-based hub linear-type passenger boarding area parking space layout method according to claim 3, characterized in that, The establishment of a linear regression model of passenger pickup parking behavior and a probability distribution model of passenger pickup waiting behavior based on the duration data of each human-vehicle behavior type, comprises: extracting influencing factors of the duration data of passenger pickup parking behavior, including the number of passengers getting on the vehicle, whether the passengers open the trunk to put luggage, and whether the driver gets off the vehicle to help carry the luggage; establishing a linear regression model of the influencing factors and the duration of passenger pickup parking behavior; The duration data of the parking and waiting behavior is analyzed to determine the long-tail distribution characteristics of the parking and waiting behavior. Based on the long-tail distribution characteristics, the duration data of the parking and waiting behavior is fitted using the Cauchy distribution to obtain a probability distribution model with a location parameter and a scale parameter.

5. The simulated-based hub linear-type passenger boarding area parking space layout method according to claim 1, characterized in that In the available space, a plurality of layout schemes of temporary parking spaces are generated, including: According to the preset length of a single temporary parking space and the preset interval, the maximum number of parking spaces that can be accommodated in the available space is calculated. In the range of the maximum number of parking spaces, simulation is performed to generate a plurality of different layout schemes, each of which includes a plurality of temporary parking spaces and waiting areas in different layouts, and the waiting areas are used to park vehicles when there is not enough temporary parking space.

6. The simulated-based hub linear-type passenger boarding area parking space layout method according to claim 1, characterized in that, The simulation of each layout scheme is performed based on the traffic flow data, the fitted model, and the relationship model to obtain the traffic efficiency of each layout scheme, including: According to the traffic flow data, the vehicle generation frequency is set, and the behavior type and behavior duration of each vehicle are set according to the fitted model and the relationship model; According to the vehicle generation frequency, the behavior type and behavior duration of each vehicle, the following simulation steps are performed for each layout scheme: control each vehicle to randomly enter any lane of the passenger pickup area, when a vehicle enters a preset distance of any target temporary parking space, for vehicles located in the right lane, keep straight; for vehicles located in the left lane, detect whether there is a lane-changing opportunity on the right lane, and when a lane-changing opportunity is detected, change lanes, and when no lane-changing opportunity is detected, keep straight and continue to detect the lane-changing opportunity until the vehicle enters the target temporary parking space or the waiting area; Within a preset simulation time, the vehicle traffic data of each layout scheme is counted, and the traffic efficiency of each layout scheme is calculated based on the vehicle traffic data.

7. The simulated-based hub linear-type passenger boarding area parking space layout method according to claim 1, characterized in that, According to the traffic efficiency, each layout scheme is optimized to obtain a target layout scheme that satisfies the traffic efficiency and has the smallest space occupation, including: Filtering out layout schemes with a traffic efficiency greater than a preset traffic efficiency threshold as candidate layout schemes; Optimizing the interval between temporary parking spaces and the number of temporary parking spaces in each candidate layout scheme; Simulating and evaluating each optimized candidate layout scheme, and selecting a layout scheme that satisfies the preset traffic efficiency threshold and has the smallest space occupation as the target layout scheme.

8. A simulation-based hub linear passenger pick-up area parking space layout system, characterized in that, The system includes: A data acquisition module for acquiring a plan view of a straight passenger pickup area of a hub parking lot and monitoring video, and determining traffic flow data based on the monitoring video; A model establishment module for analyzing the monitoring video to obtain human-vehicle behavior duration data and human-vehicle behavior frequency data, establishing a fitted model of behavior duration based on the human-vehicle behavior duration data, and establishing a relationship model of human-vehicle behavior frequency and traffic flow based on the human-vehicle behavior frequency data; A scheme generation module for determining the available space of the right lane of the passenger pickup area according to the plan view, and generating a plurality of layout schemes of temporary parking spaces in the available space, wherein adjacent temporary parking spaces are separated by a preset interval; A scheme simulation module is configured to simulate each layout scheme based on the traffic flow data, the fitting model and the relationship model to obtain a traffic efficiency of each layout scheme. A scheme optimization module is configured to optimize each layout scheme according to the traffic efficiency to obtain a target layout scheme that meets the traffic efficiency and has the minimum occupied space.

9. A computer-readable storage medium, characterized in that, A computer readable storage medium stores a plurality of instructions, which are adapted to be loaded and executed by a processor to implement the method of any one of claims 1-7.

10. An electronic device, comprising: An electronic device includes a processor, a memory, a user interface and a network interface. The memory is configured to store instructions. The user interface and the network interface are configured to communicate with other devices. The processor is configured to execute the instructions stored in the memory to enable the electronic device to implement the method of any one of claims 1-7.

Images