A scheduling method and system for improving the efficiency of a service vehicle at a railway station

Abstract

The application discloses a kind of operation vehicle in train station waiting to promote the efficiency of scheduling method and system, it is related to intelligent traffic scheduling technical field, including, when getting into roundabout queue, entrance vehicle license plate number is obtained;Vehicle state and reservation information are determined according to license plate number, whether vehicle enters express channel is judged, vehicle queuing time is recorded, and shunt decision is generated and judged;The position and queue time of all roundabout queue vehicles are obtained, and the integral starting threshold and the integral demand of entering express channel are calculated;After the waiting time of online car-hailing exceeds the integral starting threshold, passenger gets on, map service is called to determine passenger destination, and the obtained integral is calculated;After driver submits express channel reservation application, application verification is carried out, and the next day parameter optimization is carried out after a day operation;Abnormal operation is classified, and maintenance personnel are linked to carry out offline processing.The application effectively improves the efficiency of train station operation vehicle waiting.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent traffic scheduling, in particular to a scheduling method and system for improving the efficiency of operating vehicles waiting for passengers at a train station. BACKGROUND

[0002] In the high-speed rail station network car waiting scene, the traditional vehicle shunting management mainly relies on manual duty and fixed rules to carry out queuing and release. Common methods include releasing by paper or electronic reservation list at the entrance gate, and allocating fast lane quotas in static time period windows; some stations use GPS positioning or electronic queue screens to display the queuing length in real time.

[0003] However, these traditional methods have 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 mismatch between traffic resource allocation and actual demand; second, there is a lack of fine incentive means based on passenger drop-off areas and waiting contributions, and the conventional approach is difficult to encourage drivers to choose queuing or reservation according to their own benefits and overall order balance during critical periods, thus making it difficult to balance system efficiency and fairness. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a scheduling method for improving the efficiency of operating vehicles waiting for passengers at a train station, which solves the problem of the lack of static rules and incentive mechanisms in existing scheduling technology.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a scheduling method for improving the efficiency of operating vehicles waiting for passengers at a train station, which includes obtaining the vehicle license plate number when a network car enters the roundabout queue.

[0008] The vehicle state and reservation information are determined according to the license plate number, the vehicle is judged whether to enter the fast lane, the vehicle entry time is recorded, and the shunting decision is generated.

[0009] The positions and queuing times of all roundabout queued vehicles are obtained, and the integral starting threshold and integral requirement for entering the fast lane are calculated.

[0010] After the waiting time of the network car exceeds the integral starting threshold, the passenger gets on the car, the map service is called to determine the passenger's destination, and the obtained integral is calculated.

[0011] After the driver submits the fast lane reservation application, the application is verified, and the next day's parameter optimization is completed after a day of operation.

[0012] Abnormal operation is classified, and maintenance personnel are linked to handle it offline.

[0013] As a preferred scheme of the scheduling method for improving the efficiency of the passenger waiting for the train in the train station of the operating vehicle, wherein: the entry vehicle license plate number obtained by the ride-hailing vehicle entering the roundabout queue includes configuring ground inductive coils and millimeter wave radars to monitor and identify vehicle entry events in real time.

[0014] The license plate image and point cloud raw data of the vehicle head and tail are captured synchronously by the column type visual camera and the top LiDAR, and data processing is performed.

[0015] The processed license plate image is input into the license plate recognition hybrid architecture for character recognition, and the license plate number and collection timestamp of the ride-hailing vehicle are recorded in the local log database after successful recognition.

[0016] As a preferred scheme of the scheduling method for improving the efficiency of the passenger waiting for the train in the train station of the operating vehicle, wherein: the vehicle state and reservation information are determined according to the license plate number, and it is judged whether the vehicle enters the fast lane, including identifying and reading the reservation item corresponding to the license plate, and if there is no reservation record, the license plate number and timestamp are written into the roundabout queue record table as the entry time.

[0017] If there is a reservation and the timestamp is within the reservation interval and the remaining seats are sufficient, the display screen is prompted to turn into the fast lane.

[0018] As a preferred scheme of the scheduling method for improving the efficiency of the passenger waiting for the train in the train station of the operating vehicle, wherein: the position and queue time of all roundabout queue vehicles are obtained, and the integral starting threshold and the integral requirement for entering the fast lane are calculated, including periodically collecting the number and waiting time of all vehicles queuing in the roundabout, and dynamically adjusting the integral starting threshold and the integral requirement for entering the fast lane of the next reservation time interval according to the current congestion ratio and the average waiting time coefficient.

[0019] As a preferred scheme of the scheduling method for improving the efficiency of the passenger waiting for the train in the train station of the operating vehicle, wherein: the ride-hailing vehicle waiting time exceeds the integral starting threshold, the passenger gets on the vehicle, the map service is called to determine the passenger's destination, and the obtained integral includes calling the map service to obtain the passenger's destination coordinates for the ride-hailing vehicle that has been waiting for more than the integral starting threshold and has been on the vehicle, and dividing it into a fence, a fence, and a third fence, assigning different fence coefficients according to the fence level, and calculating the integral increment this time combined with the time exceeding the integral starting threshold, and updating the driver's integral account.

[0020] As a preferred scheme of the scheduling method for improving the efficiency of the passenger waiting for the operating vehicle in the railway station, after the driver submits the application for reserving the fast channel, the application is checked, and after the operation of the day is completed, the parameter optimization of the next day is performed, including, after the driver selects the reservation time interval and submits the application, the blacklist state, the availability of the quota, the balance of the points and the default behavior are checked in sequence, and after the verification is passed, the required points are deducted and the reserved quota is locked.

[0021] After the operation of the day is completed, the base point requirement of the next day is corrected according to the reservation rate of the day.

[0022] As a preferred scheme of the scheduling method for improving the efficiency of the passenger waiting for the operating vehicle in the railway station, after the driver submits the application for reserving the fast channel, the application is checked, and after the operation of the day is completed, the parameter optimization of the next day is performed, including, after the driver selects the reservation time interval and submits the application, the blacklist state, the availability of the quota, the balance of the points and the default behavior are checked in sequence, and after the verification is passed, the required points are deducted and the reserved quota is locked.

[0023] In a second aspect, the application provides a scheduling system for improving the efficiency of the passenger waiting for the operating vehicle in the railway station, including a license plate recognition module, a shunt decision module, a threshold correction module, a point calculation module, a reservation checking module and an abnormal positioning module.

[0024] The license plate recognition module is used to obtain the entrance vehicle license plate number when the online car-hailing vehicle enters the roundabout queue.

[0025] The shunt decision module is used to determine the vehicle state and reservation information according to the license plate number, judge whether the vehicle enters the fast channel, record the vehicle queue time, and judge and generate the shunt decision.

[0026] The threshold correction module is used to obtain the position and queue time of all roundabout queued vehicles, calculate the point starting threshold and the point requirement for entering the fast channel.

[0027] The point calculation module is used to calculate the points obtained after the online car-hailing vehicle waiting time exceeds the point starting threshold and the passenger gets on the vehicle.

[0028] The reservation checking module is used to check the application after the driver submits the application for reserving the fast channel, and perform the parameter optimization of the next day after the operation of the day is completed.

[0029] The abnormal positioning module is used to classify the abnormal operation and link the maintenance personnel for offline processing.

[0030] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the computer program, when executed by the processor, implements any step of the method for scheduling a vehicle for passenger pickup at a train station to improve efficiency according to the first aspect of the present application.

[0031] In a fourth aspect, the present application provides a computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any step of the method for scheduling a vehicle for passenger pickup at a train station to improve efficiency according to the first aspect of the present application.

[0032] The present application has the following beneficial effects: By obtaining the positions and queuing time of all roundabouts, calculating the integral starting threshold and the integral requirement for entering the fast lane, the present application realizes dynamic quantitative adjustment of real-time queuing pressure and waiting time, synchronously drives the shunt decision and integral cost, can automatically float the incentive threshold according to the peak or valley, realizes precise matching of fast lane resources and driver behavior, improves the overall queuing efficiency. By adjusting the number of obtained points through the fence where the user's destination is located, it is ensured that the net car driver can quickly get the next passenger based on the points in the case of long queuing and obtaining a small amount of fare, realizing positive scheduling of vehicles, reducing the dissatisfaction of drivers who pull short-distance passengers, fully utilizing the fast lane resources, and improving the operation efficiency of the station. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0034] Fig. 1 A flowchart of a method for scheduling a vehicle for passenger pickup at a train station to improve efficiency.

[0035] Fig. 2 A schematic diagram of a scheduling system for a vehicle for passenger pickup at a train station to improve efficiency.

[0036] Fig. 3 A vehicle license plate recognition flowchart of a method for scheduling a vehicle for passenger pickup at a train station to improve efficiency. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0038] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without the specific details set forth in this description. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the present application.

[0039] Second, the "one embodiment" or "an embodiment" referred to herein means a specific feature, structure, or characteristic under discussion. Thus, "one embodiment" does not mean a single embodiment nor is it to be taken individually or selectively from other embodiments.

[0040] Reference Figs. 1-3 For one embodiment of the present application, the embodiment provides a scheduling method for improving the efficiency of taxi vehicles at a train station, comprising the following steps:

[0041] S1, the entry vehicle license plate number is obtained when the online car-hailing vehicle enters the roundabout queue.

[0042] Specifically, the entry vehicle license plate number is obtained when the online car-hailing vehicle enters the roundabout queue, which includes configuring ground inductive coils and millimeter wave radars to monitor and identify vehicle entry events in real time.

[0043] The license plate image and point cloud raw data of the vehicle head and tail are captured synchronously by the columnar visual camera and the top LiDAR, and data processing is performed.

[0044] The processed license plate image is input into a license plate recognition hybrid architecture for character recognition, and after successful recognition, the online car-hailing vehicle license plate number and collection timestamp are recorded to the local log database.

[0045] Further, at the entrance area of the high-speed rail station, a multi-modal sensor network is first laid out, including ground inductive coils, millimeter wave radars, and columnar visual cameras, to capture the license plates of vehicles entering. The ground inductive coils are buried before and after the gate, and the millimeter wave radars are hung above the gate to perceive the approaching vehicles, and the columnar visual cameras are equipped with a set of LiDARs on top.

[0046] The gate is located at the entrance of the fast lane and the entrance of the roundabout.

[0047] When any ground inductive coil or millimeter wave radar is triggered, it is identified as a vehicle entry event and the columnar visual cameras located on both sides of the gate and the center are started to obtain the license plate image, and the LiDAR synchronously obtains the point cloud raw data. The ground inductive coil is triggered again after the online car-hailing vehicle passes through the gate, and it is identified as a vehicle entry event and the columnar visual cameras and LiDARs in the opposite direction of the gate again obtain the license plate image and point cloud raw data of the tail of the online car-hailing vehicle.

[0048] Through edge computing, the distortion and geometric alignment of the license plate image and the point cloud raw data are completed locally. Specifically, an adaptive ROI extraction algorithm based on OpenCV is adopted, and a license plate cropping frame image is generated according to the head plane estimation result provided by LiDAR.

[0049] After preprocessing, the license plate cropping frame image enters a hybrid model composed of a deep convolutional neural network (CNN) that has completed training as a feature extraction backbone and a bidirectional long short-term memory network (Bi-LSTM) as a sequence modeler. The license plate cropping frame image is input, multi-scale spatial features are extracted, the feature map is compressed in the channel and then expanded into a one-dimensional feature sequence by column, and then fed into two layers of Bi-LSTM to capture the time sequence dependence of the license plate characters; finally, the recognition is completed by connecting the time sequence classification (CTC) layer for non-aligned character decoding.

[0050] In the training phase, according to the historical collection of labeled samples containing Chinese and English characters, different light and shooting angles, the samples are divided into training set, validation set and test set according to the ratio of 8:1:1. The Adam optimizer is used, the initial learning rate is set to 1e-3, and after the validation set recognition accuracy stagnates for five epochs, the learning rate is decayed by 0.1, the batch size is set to 64; the total training rounds are 50 rounds, and the early stopping strategy is enabled to prevent overfitting.

[0051] After successful recognition, the online car-hailing license plate and the timestamp are stored in the local log through the station intranet, retaining the license plate number , the timestamp of collecting the license plate, and the number of the column visual camera that collects the license plate. According to the number of the column visual camera, the position is matched to support offline maintenance by maintenance personnel.

[0052] S2, according to the license plate number, determine the vehicle state and reservation information, judge whether the vehicle enters the fast channel, record the vehicle queue time, and judge and generate the shunt decision.

[0053] Specifically, according to the license plate number, determine the vehicle state and reservation information, and judge whether the vehicle enters the fast channel, including identifying and reading the reservation item corresponding to the license plate, and if there is no reservation record, writing the license plate number and timestamp into the roundabout queue record table as the queue time.

[0054] If there is a reservation and the timestamp is within the reservation interval and the remaining quota is sufficient, prompt the driver to enter the fast channel on the display screen.

[0055] Further, if the online car-hailing driver wants to avoid queuing through the fast channel, the driver needs to make a reservation in advance, divide the time into reservation time intervals, set the reservation quota for each reservation time interval, and cannot make a reservation if the quota is full.

[0056] read the reservation entry corresponding to the vehicle, including the reservation time interval (T ) and the reservation quota (Q ), the start time of the reservation time interval (T ), and the end time of the reservation time interval (T

[0057] If there is no reservation entry corresponding to the vehicle, the vehicle directly enters the roundabout queue, and the time stamp of the collected license plate is recorded as the queue start time according to the vehicle entry event.

[0058] If there is a reservation entry corresponding to the vehicle and the time stamp of the collected license plate is within the reservation time interval, the license plate is displayed on the display screen to inform the vehicle to enter the fast lane.

[0059] During intervals such as the Spring Festival and holidays, the number of people at the train station is large, and the number of online car-hailing vehicles is also large. In this case, the division of the roundabout and the fast lane may cause serious traffic jams in the roundabout, so a shunting decision needs to be made to adaptively change the shunting method.

[0060] Every three types of real-time indicators are collected and normalized.

[0061] The three types of real-time indicators include the congestion ratio, the congestion growth ratio, and the average waiting time coefficient.

[0062] The congestion ratio is as follows:

[0063] ;

[0064] wherein, N is the total number of vehicles queuing in the roundabout, Nmax is the maximum number of vehicles that the roundabout can accommodate.

[0065] The congestion growth ratio is as follows:

[0066] ;

[0067] wherein, T is the monitoring interval.

[0068] The average waiting time coefficient is as follows:

[0069] ;

[0070] wherein, T is the average waiting time of all queuing vehicles, ​To set the long waiting benchmark, the average waiting time on non-holidays is confirmed.

[0071] Combine the three real-time indicators into the emergency diversion index , denoted as:

[0072] ;

[0073] Among them, only for positive growth (continuous congestion deterioration) response, limit No more than 1.

[0074] According to the service level target of the operator to set the emergency diversion threshold , when ≥ , start emergency diversion. Continuously collect historical data of emergency diversion index in working days, sort all samples according to size, and then combine the maximum acceptable waiting level of drivers counted by the operator as the target to calculate a quantile point as the initial emergency diversion threshold , continuously monitor and collect the emergency diversion index corresponding to the full load of the emergency channel when the emergency diversion starts , and The interval of is the value range of

[0075] In the emergency diversion mode, start a token distribution and release operation to relieve the roundabout congestion as soon as possible. First, generate a list of vehicles to be released from the current roundabout queue list in the order of vehicle entry. Then, according to the number of tokens allocated, take out the corresponding number of vehicles from the front of the list in turn, and each vehicle is allocated an emergency release token.

[0076] When the token distribution is completed, the fast lane changes to the emergency lane, and when the barrier is encountered again, the vehicle entry event recognize the license plate, and when it is recognized as a token-holding vehicle, the display screen displays the license plate to inform the turn into the fast lane.

[0077] To avoid frequent switching, when has been less than , continue to maintain the emergency diversion mode until the end of the next monitoring interval time.

[0078] S3, get the position and queuing time of all roundabout queued vehicles, calculate the integral starting threshold and the integral requirement for entering the fast lane.

[0079] Specifically, the position and queuing time of all roundabout queued vehicles are acquired, and the integral starting threshold and integral demand for entering the fast lane are calculated, including periodically collecting the number and waiting time of all vehicles queuing at the roundabout, and dynamically adjusting the integral starting threshold and integral demand for entering the fast lane in the next reservation time interval according to the current congestion ratio and average waiting time coefficient.

[0080] Further, based on the current congestion ratio and average waiting time coefficient in the roundabout, the two dynamic parameters generate the integral starting threshold in the next reservation time interval .

[0081] The integral starting threshold is expressed as:

[0082] ;

[0083] Wherein, is a reference threshold, which can be selected as the average integral starting threshold on non-holidays or set by the operator.

[0084] The dynamic integral starting threshold ensures that when the queue number or average waiting time exceeds the operator's expectation, the threshold will decrease proportionally, making it easier for drivers to get the integral, and reducing the drivers' resistance to queuing. When the queue is empty or the average waiting time is lower than the operator's expectation, the driver's frequency of picking up passengers is higher, and the integral starting threshold is increased.

[0085] Then, the congestion ratio is adjusted to adjust the integral demand for entering the fast lane, which is expressed as:

[0086] ;

[0087] Wherein, is the integral demand for entering the fast lane in the next reservation time interval, is the reference integral demand for entering the fast lane, which is set by the operator, represents the limit is in the range of , , is the minimum exchange integral, is the maximum exchange integral.

[0088] The minimum exchange integral and the maximum exchange integral are determined by the number of scores obtained by the online car-hailing driver, and the integral obtained by completing a short trip with the destination within the secondary fence under the current queuing time state is selected as , and the integral obtained by completing a short trip with the destination within the primary fence under the current queuing time state is selected as . Ensure that the exchange frequency is always within a controllable range under various queuing pressures.

[0089] S4, the passenger gets into the car after the waiting time of the online car-hailing service exceeds the integral threshold, calls the map service to determine the passenger's destination, and calculates the obtained integral.

[0090] Specifically, the passenger gets into the car after the waiting time of the online car-hailing service exceeds the integral threshold, calls the map service to determine the passenger's destination, and calculates the obtained integral, which includes calling the map service to obtain the passenger's destination coordinates and dividing them into a first, second and third fence for the online car-hailing service whose queuing time exceeds the integral threshold threshold, assigning different fence coefficients according to the fence level and calculating the integral increment this time in combination with the time exceeding the integral threshold, and updating the driver's integral account.

[0091] Further, some drivers are short of points or want to accumulate points, and enter the roundabout queue.

[0092] When the passenger gets into the car, the queuing time of the online car-hailing service is completed, and the time stamp of the license plate is collected to the time when the passenger gets into the car as the queuing time, and the queuing time is compared with the integral threshold Only when the queuing time is greater than the integral threshold It is considered that this time the passenger can obtain the integral.

[0093] According to the operation party, three fences are set, divided into a first fence, a second fence and a third fence, and the three fences are set according to the needs of the operation party. The range of the first fence is the smallest, the coefficient of the first fence is The largest, the range of the second fence is between the first fence and the third fence, the coefficient of the second fence is Less than the coefficient of the first fence Greater than the coefficient of the third fence The range of the third fence is the largest, and the coefficient of the third fence is The smallest, when the passenger's destination exceeds the range of the third fence, it is considered as a long-distance passenger, and no integral is obtained.

[0094] The integral rule obtained by the online car-hailing driver after completing a passenger delivery is represented as:

[0095] ;

[0096] Among them, is the integral increment this time, is the fence coefficient, corresponding to 1, 2 and 3, is the threshold gain coefficient, , is the queuing time.

[0097] If However, there is no event of getting into the car, which is considered as a long waiting time, and no integral is calculated for this time regardless of the location of the passenger's destination in any fence.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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. .

[0103] Driver selects the booking time range Submit an appointment request and record the request time. And generate a temporary identifier.

[0104] The booking process analyzes ride-hailing information and rejects the booking if any step fails.

[0105] 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.

[0106] 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.

[0107] Next, check the points balance and read the current points. ,like If the score is insufficient, a message will be displayed.

[0108] 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.

[0109] 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.

[0110] If all checks pass, then deduct. The points.

[0111] After the completion of a day of operation, the daily appointment rate is calculated , is expressed as:

[0112] ;

[0113] wherein, is the total number of appointments for the day, is the total number of seats for the day.

[0114] The daily appointment rate adjusts the baseline credit requirement for entering the fast lane the next day, expressed as:

[0115] ;

[0116] wherein, is the updated baseline credit exchange, is the credit adjustment sensitivity coefficient, the value range is [0, 1].

[0117] S6, classify abnormal operation, and link maintenance personnel for offline processing.

[0118] Specifically, classifying abnormal operation and linking maintenance personnel for offline processing includes considering sensor misidentification, no appointment barrier crossing, excessive waiting time, and failure to cancel as abnormal events, triggering abnormal events, extracting the corresponding license plate number and positioning to the trigger abnormal columnar visual camera and informing the maintenance personnel of the type of abnormal event for offline processing.

[0119] Further, identifying all abnormal operation problems includes sensor misidentification, no appointment barrier crossing, excessive waiting time, and failure to cancel. Extract all abnormal operation of online car hailing license plate numbers, if a car enters the event and the license plate number identified by the vehicle entry event are different, the position of the columnar visual camera is extracted and sent to the maintenance personnel.

[0120] For no appointment barrier crossing behavior, the corresponding vehicle is pulled into the blacklist, and when the barrier crossing vehicle is identified in the future, the position of the columnar visual camera is sent to the maintenance personnel.

[0121] If the cancellation fails to identify whether the gate is opened, if the gate is opened, the uncharged credits are deducted by manual review, and if the gate is not opened, the position of the columnar visual camera that identifies the license plate is retrieved and sent to the maintenance personnel.

[0122] The columnar visual camera identifies the license plate number of the vehicle with excessive waiting time, and when the license plate is identified, the position of the columnar visual camera is sent to the maintenance personnel for warning.

[0123] The embodiment also provides a scheduling system for improving efficiency of a passenger waiting for a train in a station by an operating vehicle, comprising: a license plate recognition module, a shunting decision module, a threshold correction module, an integral calculation module, a reservation verification module, and an abnormality positioning module.

[0124] The license plate recognition module is configured to obtain an entry vehicle license plate number when a network car enters a roundabout queue.

[0125] The shunting decision module is configured to determine a vehicle state and reservation information according to the license plate number, determine whether the vehicle enters a fast lane, record a vehicle queuing time, and determine and generate a shunting decision.

[0126] The threshold correction module is configured to obtain positions and queuing durations of all roundabout queued vehicles, and calculate an integral starting threshold and an integral requirement for entering the fast lane.

[0127] The integral calculation module is configured to obtain an integral when a network car waiting time exceeds the integral starting threshold and a passenger gets on the vehicle, and determine a passenger destination by calling a map service.

[0128] The reservation verification module is configured to perform application verification after a driver submits a fast lane reservation application, and perform parameter optimization for the next day after a day of operation is completed.

[0129] The abnormality positioning module is configured to classify abnormal operation, and link a maintenance personnel for offline processing.

[0130] The embodiment also provides a computer device suitable for a scheduling method for improving efficiency of a passenger waiting for a train in a station by an operating vehicle, comprising: a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the scheduling method for improving efficiency of a passenger waiting for a train in a station by an operating vehicle proposed in the above embodiment.

[0131] The computer device can be a terminal, and the computer device comprises a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, a carrier network, NFC (near field communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball, or touchpad arranged on the computer device shell. The input device can also be an external keyboard, touchpad, or mouse, etc.

[0132] The embodiment also provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the scheduling method for improving the efficiency of the passenger waiting for the train in the station according to the above embodiment; 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 read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0133] To sum up, the application realizes dynamic quantitative adjustment of real-time queuing pressure and waiting time by obtaining the positions and queuing time of all roundabout queued vehicles, calculating the integral starting threshold and integral demand for entering the fast channel, synchronously driving the shunt decision and integral cost, and can automatically float the incentive threshold according to the peak or valley, realizes accurate matching of fast channel resources and driver behavior, improves the overall queuing efficiency. The number of obtained points is adjusted through the fence where the user destination is located, so as to ensure that the online car-hailing driver can quickly get the next passenger based on the points in the case of long queuing and small amount of fare, realize positive scheduling of the vehicle, reduce the dissatisfaction of the driver to the short-distance passenger, fully utilize the fast channel resources, and improve the operation efficiency of the station.

[0134] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A scheduling method for improving the efficiency of operating vehicles waiting for passengers at railway stations, characterized in that: The method comprises the following steps: Obtaining the license plate number of the entry vehicle when the online car-hailing vehicle enters the roundabout queue; Determining the vehicle state and reservation information according to the license plate number, judging whether the vehicle enters the fast lane, recording the vehicle queue time, judging and generating the shunt decision; Obtaining the position and queue time of all vehicles in the roundabout queue, calculating the integral starting threshold and the integral requirement for entering the fast lane; The passenger gets on the vehicle when the waiting time of the online car-hailing vehicle exceeds the integral starting threshold, calls the map service to determine the passenger's destination, and calculates the obtained integral; After the driver submits the fast lane reservation application, the application is verified, and the parameters are optimized the next day after a day of operation; Classify abnormal operation and link maintenance personnel for offline processing; The method comprises the following steps: Periodically collecting the number and waiting time of all vehicles in the roundabout queue, dynamically adjusting the integral starting threshold and the integral requirement for entering the fast lane of the next reservation time interval according to the current congestion ratio and the average waiting time coefficient; 2. The method of claim 1, wherein the method is a method of scheduling a service vehicle to improve efficiency of passenger waiting at a train station. The passenger gets on the vehicle when the waiting time of the online car-hailing vehicle exceeds the integral starting threshold, calls the map service to determine the passenger's destination, and calculates the obtained integral; The method comprises the following steps: Real-time monitoring and identification of vehicle entry events by configuring ground inductive coils and millimeter wave radars; 3. The method of claim 2, wherein the method further comprises: Synchronously capturing the license plate image and point cloud raw data of the vehicle head and tail by the columnar visual camera and the top LiDAR, and processing the data; Input the processed license plate image into the license plate recognition hybrid architecture for character recognition, and record the online car-hailing license plate number and collection timestamp to the local log database after successful recognition.

4. The method of claim 3, wherein the method is characterized by: The method comprises the following steps: Identifying and reading the reservation item corresponding to the license plate, and writing the license plate number and timestamp into the roundabout queue record table as the queue time if there is no reservation record; 5. The method of claim 4, wherein the method further comprises: determining a number of passengers waiting at the train station; and determining a number of vehicles available to transport the passengers to the train platform. If there is a reservation and the timestamp is within the reservation interval and the remaining seats are sufficient, prompt the driver to enter the fast lane on the display screen. The method comprises the following steps: After the driver selects the reservation time interval and submits the application, the black list status, seat availability, integral balance and default behavior are verified in sequence, and the required integral is deducted and the reservation seat is locked after verification; After a day of operation, the benchmark integral requirement for the next day is corrected according to the reservation rate of the day. The method comprises the following steps: Sensor misidentification, no reservation, long waiting time and failed cancellation are regarded as abnormal events, triggering abnormal time, extracting the corresponding license plate number and positioning to the columnar visual camera that triggered the abnormality, and informing the maintenance personnel of the type of abnormal event for offline processing.

6. A scheduling system for improving the efficiency of a passenger waiting for a train at a station, based on the scheduling method for improving the efficiency of a passenger waiting for a train at a station according to any one of claims 1 to 5, characterized in that: It comprises a license plate recognition module, a shunt decision module, a threshold correction module, an integral calculation module, a reservation verification module and an abnormal positioning module. The license plate recognition module is used to obtain the license plate number of the vehicle entering the roundabout when the online car-hailing vehicle enters the roundabout to queue; The shunt decision module is used to determine the vehicle state and reservation information according to the license plate number, judge whether the vehicle enters the fast lane, record the vehicle queuing time, judge and generate the shunt decision; The threshold correction module is used to obtain the position and queuing time of all roundabout queuing vehicles, calculate the integral starting threshold and the integral requirement for entering the fast lane; The integral calculation module is used to calculate the obtained integral when the online car-hailing vehicle waiting time exceeds the integral starting threshold and the passenger gets on the vehicle; The reservation verification module is used to verify the application after the driver submits the fast lane reservation application, and optimize the parameters for the next day after completing the operation of one day; The abnormal positioning module is used to classify the abnormal operation and link the maintenance personnel for offline processing. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the scheduling method for improving the efficiency of the operating vehicle in the train station waiting room according to any one of claims 1-5.

8. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the scheduling method for improving the efficiency of the operating vehicle in the train station waiting room according to any one of claims 1-5.

Images