Scheduling method and system for improving passenger waiting efficiency of commercial vehicle in railway station

Abstract

The invention discloses a scheduling method and system for improving the efficiency of an operating vehicle waiting for passengers at a railway station, and relates to the technical field of intelligent traffic scheduling, and the method comprises the steps: obtaining the license plate number of an entrance vehicle when an online car enters a roundabout for queuing; determining a vehicle state and reservation information according to the license plate number, judging whether the vehicle enters a fast channel, recording vehicle enqueue time, and judging and generating a shunting decision; acquiring positions and queuing durations of all roundabout queuing vehicles, and calculating an integral starting threshold value and an integral demand for entering a fast channel; after the online car-hailing waiting time exceeds the point starting threshold value, the passenger gets on the car, a map service is called to determine the destination of the passenger, and the obtained point is calculated; after a driver submits a quick channel reservation application, verification of the application is carried out, and parameter optimization of the next day is carried out after operation of one day is completed; and abnormal operation is classified, and maintenance personnel are linked to carry out offline processing. According to the invention, the train station running vehicle waiting efficiency is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent traffic dispatching technology, and in particular to a dispatching method and system for improving the efficiency of operating vehicles waiting for passengers at railway stations. Background Technology

[0002] In the scenario of waiting for ride-hailing passengers at high-speed rail stations, traditional vehicle diversion management mainly relies on manual duty and fixed rules for queuing and release. Common methods include allowing entry through entrance gates based on paper or electronic reservation lists, and allocating fast lane quotas through static time slot windows; some stations use GPS positioning or electronic queue screens to display queue lengths in real time.

[0003] However, these traditional methods show two shortcomings under high load conditions: First, static rules are difficult to respond to queuing pressure and waiting changes in real time, resulting in a disconnect between traffic resource allocation and actual demand; second, there is a lack of refined incentives based on drop-off areas and waiting contributions, and conventional practices are difficult to encourage drivers to choose to queue or make reservations during critical periods based on their own benefits and the overall order, thus making it difficult to balance system efficiency and fairness. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a scheduling method to improve the efficiency of operating vehicles waiting for passengers at railway stations, solving the problem of the lack of static rules and incentive mechanisms in existing scheduling technologies.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations, which includes obtaining the license plate number of the vehicle entering the roundabout when a ride-hailing vehicle enters the roundabout to queue.

[0007] The system determines the vehicle's status and reservation information based on the license plate number, decides whether the vehicle should enter the fast lane, records the vehicle's entry time, and generates a diversion decision.

[0008] Obtain the location and queuing time of all vehicles queuing at the roundabout, calculate the starting threshold for points and the points required to enter the fast lane.

[0009] If a passenger boards a ride-hailing vehicle after the waiting time exceeds the threshold for earning points, the map service is called to determine the passenger's destination and the points earned are calculated.

[0010] After a driver submits a fast lane reservation application, the application is verified, and after completing a day's operation, the parameters are optimized for the following day.

[0011] Abnormal operations are categorized, and maintenance personnel are coordinated to handle them offline.

[0012] As a preferred embodiment of the scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in this invention, the method for obtaining the license plate number of the vehicle entering the roundabout when the ride-hailing vehicle enters the roundabout includes configuring ground inductive loops and millimeter-wave radar to monitor and identify vehicle entry events in real time.

[0013] The system simultaneously captures license plate images and point cloud data from the front and rear of the vehicle using a pillar-mounted vision camera and a top-mounted LiDAR, and then processes the data.

[0014] The processed license plate image is input into the license plate recognition hybrid architecture for character recognition. After successful recognition, the ride-hailing vehicle's license plate number and collection timestamp are recorded in the local log database.

[0015] As a preferred embodiment of the scheduling method for improving the efficiency of passenger waiting at railway stations described in this invention, the step of determining the vehicle status and reservation information based on the license plate number and judging whether the vehicle has entered the fast lane includes identifying and reading the reservation entry corresponding to the license plate. If there is no reservation record, the license plate number and timestamp are written into the roundabout queuing record table as the entry time.

[0016] If a reservation exists and the timestamp is within the reservation period, and there are sufficient remaining slots, a prompt will appear on the screen indicating that you will be transferred to the fast track.

[0017] As a preferred embodiment of the scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in this invention, the step of obtaining the location and queuing time of all vehicles queuing in the roundabout, and calculating the points starting threshold and the points requirement for entering the fast lane includes periodically collecting the number and waiting time of all vehicles queuing in the roundabout, and dynamically adjusting the points starting threshold and the points requirement for entering the fast lane for the next reservation time interval based on the current congestion ratio and the average waiting time coefficient.

[0018] As a preferred embodiment of the dispatching method for improving the efficiency of passenger waiting at train stations described in this invention, the following steps are taken: after the waiting time of the ride-hailing vehicle exceeds the points calculation threshold, the passenger boards the vehicle, the map service is invoked to determine the passenger's destination, and the points are calculated. This includes invoking the map service to obtain the passenger's destination coordinates for ride-hailing vehicles that have exceeded the points calculation threshold and have already boarded the vehicle, and classifying them into first, second, and third-level fences. Different fence coefficients are assigned according to the fence level, and the points increment is calculated in combination with the time exceeding the points calculation threshold, and the driver's points account is updated.

[0019] As a preferred embodiment of the scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in this invention, the following steps are taken: after the driver submits a fast track reservation application, the application is verified, and after completing one day's operation, the parameters for the next day are optimized. This includes the driver selecting a reservation time range and submitting the application, and then sequentially verifying the blacklist status, availability of slots, balance of points, and no-show behavior. If the verification is successful, the required points are deducted and the reservation slot is locked.

[0020] After a day's operations are completed, the baseline points requirement for the following day will be adjusted based on the day's reservation rate.

[0021] As a preferred embodiment of the scheduling method for improving the efficiency of passenger waiting at railway stations described in this invention, the step of classifying abnormal operations and coordinating with maintenance personnel for offline processing includes: treating sensor misidentification, unauthorized entry through barriers, excessively long waiting times, and failed verification as abnormal events; triggering abnormal events; extracting the corresponding license plate number; locating the column-mounted visual camera that triggered the abnormality; and informing maintenance personnel of the type of abnormal event for offline processing.

[0022] Secondly, the present invention provides a dispatching system for improving the efficiency of passenger waiting at railway stations for operating vehicles, including a license plate recognition module, a diversion decision module, a threshold correction module, an points calculation module, a reservation verification module, and an anomaly location module.

[0023] The license plate recognition module is used to obtain the license plate number of the vehicle entering the roundabout when a ride-hailing vehicle enters the roundabout to queue.

[0024] The diversion decision module is used to determine the vehicle status and reservation information based on the license plate number, determine whether the vehicle enters the fast lane, record the vehicle's entry time, and make and generate a diversion decision.

[0025] The threshold correction module is used to obtain the location and queuing time of all vehicles queuing at the roundabout, calculate the points starting threshold and the points required to enter the fast lane.

[0026] The points calculation module is used to determine the passenger's destination and calculate the points after the waiting time for a ride-hailing vehicle exceeds the points calculation threshold.

[0027] The reservation verification module is used to verify the application after the driver submits the fast lane reservation application, and to optimize the parameters for the next day after completing one day of operation.

[0028] The anomaly location module is used to classify abnormal operations and coordinate with maintenance personnel for offline handling.

[0029] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the scheduling method for improving the efficiency of waiting for passengers at a railway station as described in the first aspect of the present invention.

[0030] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the scheduling method for improving the efficiency of waiting for passengers at a railway station as described in the first aspect of the present invention.

[0031] The beneficial effects of this invention are as follows: By acquiring the location and queuing time of all vehicles queuing at roundabouts, calculating the points threshold and the points required to enter the fast lane, this invention achieves dynamic quantitative adjustment of real-time queuing pressure and waiting time, simultaneously driving diversion decisions and points costs. It can automatically adjust the incentive threshold based on peak or off-peak times, achieving precise matching of fast lane resources and driver behavior, thus improving overall queuing efficiency. By adjusting the number of points earned by using the user's destination location as a boundary, this invention ensures that ride-hailing drivers can quickly pick up the next passenger based on points even after long queues and receiving only a small fare, achieving positive vehicle dispatch, reducing driver dissatisfaction with picking up short-distance passengers, fully utilizing fast lane resources, and improving station operational efficiency. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a flowchart of a scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations.

[0034] Figure 2 This is a schematic diagram of a dispatching system for improving the efficiency of passenger waiting at train stations.

[0035] Figure 3 A flowchart illustrating a vehicle license plate recognition method for improving the efficiency of passenger dispatching at train stations. Detailed Implementation

[0036] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0037] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0038] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0039] Reference Figures 1-3 As one embodiment of the present invention, this embodiment provides a scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations, including the following steps: S1. When a ride-hailing vehicle enters the roundabout and queues, it obtains the license plate number of the vehicle at the entrance.

[0040] Specifically, when ride-hailing vehicles enter the roundabout to queue, the system obtains the license plate number of the vehicle entering the roundabout by configuring ground inductive loops and millimeter-wave radar to monitor and identify vehicle entry events in real time.

[0041] The system simultaneously captures license plate images and point cloud data from the front and rear of the vehicle using a pillar-mounted vision camera and a top-mounted LiDAR, and then processes the data.

[0042] The processed license plate image is input into the license plate recognition hybrid architecture for character recognition. After successful recognition, the ride-hailing vehicle's license plate number and collection timestamp are recorded in the local log database.

[0043] Furthermore, at the entrance area of ​​the high-speed rail station, a multimodal sensor network is first deployed, including ground-based inductive loops, millimeter-wave radar, and pillar-mounted vision cameras, to capture the license plates of entering vehicles. The ground-based inductive loops are buried before and after the barrier gate, while the millimeter-wave radar is mounted above the barrier gate to detect approaching vehicles. A LiDAR unit is mounted on top of the pillar-mounted vision camera.

[0044] The barrier gates are located at the entrances to the expressway and the roundabout.

[0045] When any ground-based inductive loop or millimeter-wave radar is triggered, it is identified as a vehicle entry event. The system activates the pillar-type visual cameras located on both sides and in the center of the barrier to acquire license plate images. Simultaneously, LiDAR acquires raw point cloud data. After the ride-hailing vehicle passes through the barrier, it triggers the ground inductive loop detector again, which is then identified as a vehicle entry event. The pillar-mounted visual camera and LiDAR, located opposite to the barrier gate, once again acquire the license plate image and raw point cloud data of the ride-hailing vehicle's rear.

[0046] By employing edge computing, distortion correction and geometric alignment between the license plate image and the original point cloud data are performed locally. Specifically, an OpenCV-based adaptive ROI extraction algorithm for license plate regions is used to generate license plate cropping box images based on the vehicle front plane estimation results provided by LiDAR.

[0047] After preprocessing, the license plate cropping image is fed into a hybrid model consisting of a pre-trained deep convolutional neural network (CNN) as the feature extraction backbone and a bidirectional long short-term memory network (Bi-LSTM) as the sequence modeler. The license plate cropping image is input to extract multi-scale spatial features. The feature map is then compressed by channels and expanded column-wise into a one-dimensional feature sequence, which is fed into a two-layer Bi-LSTM to capture the temporal dependencies of the license plate characters. Finally, unaligned character decoding is performed through a connected temporal classification (CTC) layer to complete the recognition.

[0048] During the training phase, based on historically collected labeled samples containing both Chinese and English characters, under different lighting conditions and shooting angles, the dataset was divided into training, validation, and test sets in an 8:1:1 ratio. The Adam optimizer was used, with an initial learning rate of 1e-3. After the validation set accuracy plateaued for five epochs, the learning rate was decayed by 0.1, and the batch size was set to 64. The total training iterations were 50, and an early stopping strategy was implemented to prevent overfitting.

[0049] After successful identification, the license plate of the ride-hailing vehicle will be displayed. The timestamp is stored in the local log via the station's intranet, and the license plate number is retained. The system collects the timestamp of the license plate and the serial number of the pillar-mounted vision camera used for the data collection. Location matching is performed based on the camera's serial number, and the obtained location information is used to support on-site maintenance by maintenance personnel.

[0050] S2. Determine the vehicle status and reservation information based on the license plate number, determine whether the vehicle has entered the fast lane, record the vehicle's entry time, and generate a diversion decision.

[0051] Specifically, the vehicle status and reservation information are determined based on the license plate number. To determine whether a vehicle can enter the fast lane, the system identifies and reads the reservation entry corresponding to the license plate. If there is no reservation record, the license plate number and timestamp are written into the roundabout queuing record table as the entry time.

[0052] If a reservation exists and the timestamp is within the reservation period, and there are sufficient remaining slots, a prompt will appear on the screen indicating that you will be transferred to the fast track.

[0053] Furthermore, if ride-hailing services want to avoid queuing and use the fast lane, they need to make a reservation in advance. The time is divided into reservation time intervals, and each reservation time interval has a limited number of slots. Once the quota is full, no more reservations can be made.

[0054] Read The corresponding vehicle reservation entry includes the reservation time range ( ) and reservation slots, This is the start time of the reserved time interval. This is the end time of the reservation time interval.

[0055] like If the corresponding vehicle has no reservation entry, it will directly enter the roundabout to queue, and the entry time will be determined based on the vehicle's entry event. The timestamp of the recorded license plate is used as the start time of the queue.

[0056] like If the corresponding vehicle has a reservation entry and the timestamp of the license plate collection is within the reservation time range, the license plate will be displayed on the screen to indicate that the vehicle can be transferred to the fast lane.

[0057] During peak travel periods, such as the Spring Festival travel rush and other holidays, train stations experience high passenger volumes and a large number of ride-hailing vehicles. In such situations, the division of traffic into roundabouts and expressways may lead to severe congestion at the roundabouts. Therefore, it is necessary to choose a diversion strategy and adapt the diversion method accordingly.

[0058] Every Three types of real-time indicators were collected and normalized.

[0059] The three types of real-time indicators include congestion ratio, congestion growth rate, and average waiting time coefficient.

[0060] Congestion ratio as follows: ; in, This represents the total number of vehicles currently queuing within the roundabout. This is the maximum capacity for vehicles in the roundabout.

[0061] Congestion growth rate as follows: ; in, This refers to the monitoring interval.

[0062] Average waiting time coefficient as follows: ; in, The average waiting time for all vehicles in the queue. To set a long waiting benchmark, it is determined based on the average waiting time on non-holidays.

[0063] The three types of real-time indicators are combined to form an emergency diversion index. , represented as: ; in, This indicates a response only to positive growth (continuous worsening of congestion). Indicates restriction No more than 1.

[0064] Set emergency diversion thresholds based on the operator's service level objectives. ,when ≥ Emergency diversion will be initiated. Historical data on the emergency diversion index will be continuously collected during weekdays. All samples will be sorted by size, and then, based on the operator's statistics on the maximum acceptable waiting level of drivers, a quantile will be calculated and selected as the initial emergency diversion threshold. Continuously monitor and collect the emergency diversion index corresponding to the emergency diversion channel reaching full capacity when emergency diversion begins. , and The interval is The range of values ​​for .

[0065] In emergency diversion mode, a token distribution and release operation is initiated to alleviate roundabout congestion as quickly as possible. First, a list of vehicles awaiting release is generated from the current roundabout queue list according to the order in which vehicles entered the queue. Then, according to the number of tokens allocated, the corresponding number of vehicles are taken from the front of the list in sequence, and an emergency release token is issued to each vehicle.

[0066] Once the tokens are distributed, the fast lane becomes an emergency lane. When the vehicle encounters the barrier again, a vehicle entry event is triggered. The system identifies license plates, and when a vehicle is identified as holding a token, the display shows the license plate number to indicate that the driver can enter the fast lane.

[0067] To avoid frequent switching, in already smaller than In such cases, the emergency diversion mode will continue until the next monitoring interval ends.

[0068] S3. Obtain the location and queuing time of all vehicles queuing at the roundabout, calculate the starting threshold for points and the points required to enter the fast lane.

[0069] Specifically, obtaining the location and queuing time of all vehicles queuing in the roundabout, and calculating the points threshold and points requirement for entering the fast lane includes periodically collecting the number of vehicles queuing in the roundabout and the waiting time, and dynamically adjusting the points threshold and points requirement for entering the fast lane for the next reservation time interval based on the current congestion ratio and average waiting time coefficient.

[0070] Furthermore, based on the current congestion ratio and average waiting time coefficient within the roundabout, these two dynamic parameters generate the integration threshold for the next booking time interval. .

[0071] Integral start threshold Represented as: ; in, The baseline threshold can be selected as the average score threshold for non-holiday periods or set by the operator.

[0072] Dynamic integration threshold To ensure that when the number of queues or the average waiting time exceeds operational expectations, the threshold decreases proportionally, making it easier for drivers to earn points and reducing their resistance to queuing. Conversely, when the queue is empty or the average waiting time is lower than operational expectations, drivers pick up passengers more frequently, and the threshold for earning points increases.

[0073] Next, the points required to enter the fast lane are adjusted according to the congestion ratio, as shown below: ; in, Points required to enter the fast track for the next scheduled time slot. The baseline points requirement for entering the fast lane is set by the operator. Indicates limitation exist[ , Within the range, Minimum redemption points, This is the maximum number of points that can be redeemed.

[0074] The minimum and maximum redemption points are determined by the ride-hailing driver's score, using the points earned from completing a short trip to a destination within the secondary fence while the current queue time is active. The points earned for completing a short trip to a destination within the first-level fence while the current queuing time is being used as [points / rewards]. This ensures that the exchange frequency remains within a controllable range despite various queuing pressures.

[0075] S4. After a passenger boards a ride-hailing vehicle when the waiting time exceeds the threshold for accumulating points, the map service is invoked to determine the passenger's destination and the points earned are calculated.

[0076] Specifically, when a passenger boards a ride-hailing vehicle after the waiting time exceeds the points calculation threshold, the map service is called to determine the passenger's destination. The points are calculated by calling the map service to obtain the passenger's destination coordinates for ride-hailing vehicles that have exceeded the points calculation threshold and have already boarded the vehicle, and classifying them into first, second, and third level fences. Different fence coefficients are assigned according to the fence level, and the points increment is calculated in combination with the time exceeding the points calculation threshold, and the driver's points account is updated.

[0077] Furthermore, some drivers who do not have enough points or wish to accumulate points enter the roundabout to queue.

[0078] The queuing time for a ride-hailing service is calculated from the time the license plate is collected to the time the passenger boards the vehicle. This queuing time is then compared with the points calculation threshold. The comparison only applies when the queuing time exceeds the threshold for calculating points. Points will be awarded for seeing off this guest.

[0079] The operator sets up three levels of fencing: primary, secondary, and tertiary. The level 1 fencing has the smallest area and the highest coefficient. The maximum value for a secondary fence is between that of a primary fence and a tertiary fence, with a secondary fence coefficient. Less than the first-level fence coefficient Greater than the coefficient of a level 3 fence The third-level fence has the largest area, and the coefficient of the third-level fence is... At the very least, if a passenger's destination is outside the level 3 fence area, it is considered a long-distance passenger drop-off and no points will be awarded.

[0080] The points system for ride-hailing drivers after completing a passenger drop-off is as follows: ; in, This is the increase in points for this event. This is the fence coefficient. Corresponding to 1, 2 and 3, This is the overthreshold gain coefficient. , Queueing time.

[0081] like If no one boards the bus, it is considered an excessively long waiting time, and no points will be awarded for this queue regardless of which fence the passenger's destination is located in.

[0082] when If the error is found, it will be considered an error in the points calculation, reported to the operations and maintenance level, and an emergency release token will be issued to the corresponding vehicle.

[0083] S5. After the driver submits the fast lane reservation application, the application is verified, and after completing one day of operation, the parameters are optimized for the next day.

[0084] Specifically, after a driver submits a fast track reservation application, the application is verified. After completing one day of operation, the parameters for the next day are optimized. This includes verifying the driver's blacklist status, availability of slots, points balance, and no-show behavior in sequence after the driver selects the reservation time range and submits the application. If the verification is successful, the required points are deducted and the reservation slot is locked.

[0085] After a day's operations are completed, the baseline points requirement for the following day will be adjusted based on the day's reservation rate.

[0086] Furthermore, some drivers with sufficient points can reserve fast lane slots, and when making a fast lane reservation, they can obtain the remaining slots for each time slot. Points required to enter the fast track for the next appointment time slot. And the points required to enter the fast track for subsequent booking time slots. .

[0087] Driver selects the booking time range Submit an appointment request and record the request time. And generate a temporary identifier.

[0088] The booking process analyzes ride-hailing information and rejects the booking if any step fails.

[0089] The first step is a blacklist check. If the ride-hailing vehicle has been marked as blacklisted, the ride will be rejected and the user's eligibility will be frozen.

[0090] Next, the availability of slots will be checked. If there are no remaining slots, a message will be displayed indicating that the slots are full.

[0091] Next, check the points balance and read the current points. ,like If the score is insufficient, a message will be displayed.

[0092] Finally, there is the no-show detection. If there is a no-show on the day of the read, a message will be displayed asking you to try again the next day.

[0093] If a ride-hailing driver fails to show up for the first time on the same day, all points will be refunded. If a driver fails to show up for the second time, no points will be refunded.

[0094] If all checks pass, then deduct. The points.

[0095] After completing a day's operations, calculate the daily reservation rate. , is represented as: ; in, This represents the total number of reservations for the day. This represents the total number of slots available for the day.

[0096] Based on the daily reservation rate The baseline integral requirement for entering the fast lane the following day is adjusted as follows: ; in, Redeem points based on the updated benchmark. The integral adjustment sensitivity coefficient has a range of [0, 1].

[0097] S6. Classify abnormal operations and coordinate with maintenance personnel for offline handling.

[0098] Specifically, abnormal operation is classified and offline processing is carried out in conjunction with maintenance personnel. This includes classifying sensor misidentification, unauthorized entry through barriers, excessively long waiting times, and failed verification as abnormal events. Once an abnormal event is triggered, the corresponding license plate number is extracted, the column-mounted vision camera that triggered the abnormality is located, and the maintenance personnel are informed of the type of abnormal event for offline processing.

[0099] Furthermore, identify all abnormal operational issues, including sensor misidentification, unauthorized entry through barriers, excessively long waiting times, and failed verification. Extract the license plate numbers of all abnormal ride-hailing vehicles. If a ride-hailing vehicle enters an event... and vehicle entry incident If the identified license plate number is different, the location of the pillar-type vision camera is extracted and sent to the maintenance personnel.

[0100] For vehicles that attempt to breach the barrier without prior notice, the corresponding vehicles will be blacklisted, and the location of the pillar-mounted vision camera used for identification will be sent to maintenance personnel when such vehicles are subsequently detected.

[0101] If the verification fails, check whether the barrier gate is open. If the barrier gate is open, the undeducted points will be deducted through manual review. If the barrier gate is not open, retrieve the location of the pillar-type visual camera that recognizes the license plate and send it to the maintenance personnel.

[0102] The pillar-mounted vision camera identifies the license plate numbers of vehicles with excessively long waiting times. When a license plate is identified, the location of the pillar-mounted vision camera is sent to maintenance personnel, who then issue a warning.

[0103] This embodiment also provides a dispatching system for improving the efficiency of operating vehicles waiting for passengers at railway stations, including: a license plate recognition module, a diversion decision module, a threshold correction module, an points calculation module, a reservation verification module, and an anomaly location module.

[0104] The license plate recognition module is used to obtain the license plate number of the vehicle entering the roundabout when a ride-hailing vehicle enters the roundabout to queue.

[0105] The diversion decision module is used to determine the vehicle status and reservation information based on the license plate number, determine whether the vehicle should enter the fast lane, record the vehicle's entry time, and make and generate diversion decisions.

[0106] The threshold correction module is used to obtain the location and queuing time of all vehicles queuing at the roundabout, calculate the starting threshold for points calculation and the points required to enter the fast lane.

[0107] The points calculation module is used when a passenger boards a ride-hailing vehicle after the waiting time exceeds the points threshold. It calls the map service to determine the passenger's destination and calculates the points to be earned.

[0108] The reservation verification module is used to verify the application submitted by the driver for the fast lane reservation, and to optimize the parameters for the next day after completing one day of operation.

[0109] The anomaly location module is used to classify abnormal operations and coordinate with maintenance personnel for offline handling.

[0110] This embodiment also provides a computer device applicable to the scheduling method for improving the efficiency of passenger waiting at railway stations for operating vehicles, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the scheduling method for improving the efficiency of passenger waiting at railway stations for operating vehicles as proposed in the above embodiment.

[0111] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0112] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the scheduling method for improving the efficiency of passenger waiting at railway stations as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0113] In summary, this invention achieves dynamic quantitative adjustment of real-time queuing pressure and waiting time by acquiring the location and queuing time of all vehicles queuing at roundabouts, calculating the points threshold and the points required to enter the fast lane, and simultaneously driving diversion decisions and points costs. It can automatically adjust the incentive threshold based on peak or off-peak hours, achieving precise matching of fast lane resources and driver behavior, thus improving overall queuing efficiency. By adjusting the points earned by locating the user's destination, it ensures that ride-hailing drivers can quickly pick up the next passenger based on points even after long queues and receiving only a small fare, achieving positive vehicle dispatch, reducing driver dissatisfaction with picking up short-distance passengers, fully utilizing fast lane resources, and improving station operational efficiency.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations, characterized in that: include, When a ride-hailing vehicle enters the roundabout and queues, it obtains the license plate number of the vehicle entering the roundabout. The system determines the vehicle status and reservation information based on the license plate number, decides whether the vehicle should enter the fast lane, records the vehicle's entry time, and generates a diversion decision. Obtain the location and queuing time of all vehicles queuing at the roundabout, and calculate the points threshold and points required to enter the fast lane; If a passenger boards a ride-hailing vehicle after the waiting time exceeds the threshold for earning points, the map service is called to determine the passenger's destination and the points earned are calculated. After a driver submits a fast lane reservation application, the application is verified, and after completing a day's operation, the parameters are optimized for the following day. Abnormal operations are categorized, and maintenance personnel are coordinated to handle them offline.

2. The dispatching method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in claim 1, characterized in that: The method of obtaining the license plate number of the vehicle entering the roundabout when the ride-hailing vehicle enters the queue includes configuring ground inductive loops and millimeter-wave radar to monitor and identify vehicle entry events in real time. The system simultaneously captures license plate images and point cloud data from the front and rear of the vehicle using a pillar-mounted vision camera and a top-mounted LiDAR, and then processes the data. The processed license plate image is input into the license plate recognition hybrid architecture for character recognition. After successful recognition, the ride-hailing vehicle's license plate number and collection timestamp are recorded in the local log database.

3. The dispatching method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in claim 2, characterized in that: The step of determining the vehicle status and reservation information based on the license plate number and judging whether the vehicle has entered the fast lane includes identifying and reading the reservation entry corresponding to the license plate. If there is no reservation record, the license plate number and timestamp are written into the roundabout queuing record table as the entry time. If a reservation exists and the timestamp is within the reservation period, and there are sufficient remaining slots, a prompt will appear on the screen indicating that you will be transferred to the fast track.

4. The dispatching method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in claim 3, characterized in that: The process of obtaining the location and queuing time of all vehicles queuing at the roundabout, and calculating the points threshold and points requirement for entering the fast lane, includes periodically collecting the number of vehicles queuing at the roundabout and their waiting time, and dynamically adjusting the points threshold and points requirement for entering the fast lane for the next reservation time interval based on the current congestion ratio and average waiting time coefficient.

5. The dispatching method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in claim 4, characterized in that: When a passenger boards a ride-hailing vehicle after the waiting time exceeds the points calculation threshold, the map service is invoked to determine the passenger's destination. The points are calculated by invoking the map service to obtain the passenger's destination coordinates for ride-hailing vehicles that have already boarded the vehicle and whose queuing time exceeds the points calculation threshold. The vehicles are then classified into three levels of fences. Different fence coefficients are assigned based on the fence level, and the points increment is calculated in combination with the time exceeding the points calculation threshold. The driver's points account is then updated.

6. The dispatching method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in claim 5, characterized in that: After the driver submits a fast track reservation application, the application is verified. After completing one day of operation, the parameters for the next day are optimized. This includes the driver selecting a reservation time range and submitting the application, and then verifying the blacklist status, availability of slots, points balance, and no-show behavior. If the verification is successful, the required points are deducted and the reservation slot is locked. After a day's operations are completed, the baseline points requirement for the following day will be adjusted based on the day's reservation rate.

7. The dispatching method for improving the efficiency of operating vehicles waiting for passengers at railway stations as described in claim 6, characterized in that: The process of classifying abnormal operations and coordinating with maintenance personnel for offline handling includes classifying sensor misidentification, unauthorized entry through barriers, excessively long waiting times, and failed verification as abnormal events. When an abnormal event is triggered, the corresponding license plate number is extracted, the column-mounted vision camera that triggered the abnormality is located, and the maintenance personnel are informed of the type of abnormal event for offline handling.

8. A dispatching system for improving the efficiency of passenger waiting areas for operating vehicles at railway stations, based on the dispatching method for improving the efficiency of passenger waiting areas for operating vehicles at railway stations as described in any one of claims 1 to 7, characterized in that: This includes a license plate recognition module, a diversion decision module, a threshold correction module, a points calculation module, a reservation verification module, and an anomaly location module; The license plate recognition module is used to obtain the license plate number of the vehicle entering the roundabout when a ride-hailing vehicle enters the roundabout to queue. The diversion decision module is used to determine the vehicle status and reservation information based on the license plate number, determine whether the vehicle enters the fast lane, record the vehicle entry time, and make and generate diversion decisions. The threshold correction module is used to obtain the location and queuing time of all vehicles queuing at the roundabout, calculate the starting threshold for points calculation and the points required to enter the fast lane; The points calculation module is used to determine the passenger's destination and calculate the points after the waiting time for the ride-hailing service exceeds the points calculation threshold. The reservation verification module is used to verify the application after the driver submits the fast lane reservation application, and to optimize the parameters for the next day after completing one day of operation. The anomaly location module is used to classify abnormal operations and coordinate with maintenance personnel for offline handling.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the scheduling method for improving the efficiency of waiting for passengers at railway stations as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the scheduling method for improving the efficiency of waiting for passengers at railway stations as described in any one of claims 1 to 7.

Images