CN112562378B - Bus scheduling method and device, computer equipment and medium - Google Patents

Bus scheduling method and device, computer equipment and medium Download PDF

Info

Publication number
CN112562378B
CN112562378B CN202011389837.1A CN202011389837A CN112562378B CN 112562378 B CN112562378 B CN 112562378B CN 202011389837 A CN202011389837 A CN 202011389837A CN 112562378 B CN112562378 B CN 112562378B
Authority
CN
China
Prior art keywords
bus
information
station
passenger
subway
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011389837.1A
Other languages
Chinese (zh)
Other versions
CN112562378A (en
Inventor
王健宗
李泽远
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN202011389837.1A priority Critical patent/CN112562378B/en
Publication of CN112562378A publication Critical patent/CN112562378A/en
Priority to PCT/CN2021/084302 priority patent/WO2022116447A1/en
Application granted granted Critical
Publication of CN112562378B publication Critical patent/CN112562378B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to artificial intelligence, and particularly discloses a bus dispatching method, a bus dispatching device, computer equipment and a readable storage medium. The method comprises the steps that bus station information and subway station information are obtained, wherein the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations; determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station; acquiring bus passenger information of a bus station and subway passenger information of a target subway station; based on the trained passenger flow prediction model, determining passenger flow information of a bus station according to the bus passenger information and the subway passenger information; and determining the number of target vehicles at the bus station according to the passenger flow information of the bus station. The problem that the capacity of the public transport is insufficient in the peak period and the idle load rate of the public transport is too high in the off-peak period is solved. The application also relates to a block chain technology, and the trained passenger flow prediction model can be stored in the block chain.

Description

Bus scheduling method and device, computer equipment and medium
Technical Field
The application relates to the technical field of intelligent transportation, in particular to a bus scheduling method, a bus scheduling device, computer equipment and a readable storage medium.
Background
Public transport is an important component of urban infrastructure, and has increased influence no matter in social life, urban construction or economic development, ensures the unblocked of public transport, and is significant to guaranteeing the civilian life, promotes regional development, and most areas can't schedule public transport according to the mass flow very rationally at present, leads to the insufficient capacity of public transport in the peak period, and is crowded in the car, and even a lot of passengers can't get on the bus, and the public transport idle rate is too high in the idle period, the problem of resource waste appears.
Disclosure of Invention
The application provides a bus scheduling method, a bus scheduling device, computer equipment and a readable storage medium, which can better predict the passenger flow of a bus station to schedule the bus so as to solve the problems of insufficient capacity in a peak period and overhigh idle rate in an idle period.
In a first aspect, the present application provides a bus scheduling method, including:
acquiring bus station information and subway station information, wherein the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations;
determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station;
acquiring bus passenger information of the bus station and subway passenger information of the target subway station;
based on a trained passenger flow prediction model, determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information;
and determining the number of target vehicles of the bus station according to the passenger flow information of the bus station.
In a second aspect, an apparatus for bus scheduling, the apparatus comprising:
the system comprises a station information acquisition module, a data processing module and a data processing module, wherein the station information acquisition module is used for acquiring bus station information and subway station information, the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations;
the station determining module is used for determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station;
the passenger information acquisition module is used for acquiring the bus passenger information of the bus station and the subway passenger information of the target subway station;
the passenger flow determining module is used for determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on a trained passenger flow prediction model;
and the dispatching module is used for determining the number of the buses driving to the bus station according to the passenger flow information of the bus station.
In a third aspect, the present application provides a computer device comprising a memory and a processor; the memory is used for storing a computer program; the processor is used for executing the computer program and realizing the bus dispatching method when the computer program is executed.
In a fourth aspect, the present application provides a computer-readable storage medium, where a computer program is stored, and if the computer program is executed by a processor, the bus scheduling method is implemented.
The application discloses a bus scheduling method, a passenger flow prediction model training method, a device, computer equipment and a readable storage medium, wherein bus station information and subway station information are obtained, the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations; determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station; acquiring bus passenger information of the bus station and subway passenger information of the target subway station; determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on a trained passenger flow prediction model; and determining the number of target vehicles at the bus station according to the passenger flow information of the bus station, so that the bus dispatching center can dispatch buses according to the predicted passenger flow information, and the problems of insufficient capacity of the buses in a peak period and overhigh idle rate of the buses in a peak leveling period are solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a bus dispatching method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a passenger traffic prediction model training method according to an embodiment of the present disclosure;
FIG. 3 is a schematic view of a usage scenario of a passenger traffic prediction model training method according to an embodiment of the present application;
fig. 4 is a schematic block diagram of a structure of a bus dispatching device according to an embodiment of the present application;
fig. 5 is a schematic block diagram of a passenger flow prediction model training apparatus according to an embodiment of the present application;
fig. 6 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
The flow diagrams depicted in the figures are merely illustrative and do not necessarily include all of the elements and operations/steps, nor do they necessarily have to be performed in the order depicted. For example, some operations/steps may be decomposed, combined or partially combined, so that the actual execution sequence may be changed according to the actual situation. In addition, although the division of the functional blocks is made in the device diagram, it may be divided in different blocks from that in the device diagram in some cases.
The embodiment of the application also provides a bus scheduling method, a bus scheduling device, computer equipment and a computer readable storage medium. The method is used for predicting the passenger flow of the bus based on the passenger flow prediction model so as to determine the target vehicle of the bus, reduce the problems of the idle load rate and/or the overload rate of the bus and improve the transport capacity of urban public transport.
The bus scheduling method can be used for a server, and certainly can also be used for a terminal, wherein the terminal can be an electronic device such as a tablet computer, a notebook computer and a desktop computer; the servers may be, for example, individual servers or clusters of servers. However, for the sake of understanding, the following embodiments will be described in detail with reference to a bus scheduling method applied to the server.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments and features of the embodiments described below can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a schematic flow chart of a bus dispatching method according to an embodiment of the present application.
As shown in fig. 1, the bus dispatching method may include the following steps S110 to S150.
Step S110, bus station information and subway station information are obtained, wherein the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations.
Illustratively, the bus station information and the subway station information can be acquired from a city construction system, a bus operation system, a subway operation system and other systems.
Exemplarily, can also acquire bus station information and subway station information through the thing networking in wisdom city.
Illustratively, the bus station information further includes position information of the bus station, a name of the bus station, a longitude and a latitude of the bus station, and it is understood that the subway station information includes position information of the subway station, a name of the subway station, and a longitude and a latitude of the subway station.
For example, the bus station information includes aa major track, bb park main gate station, and longitude and latitude are 112 degrees of east longitude and 26 degrees of north latitude, and the subway station information includes aa major track, bb park station, and longitude and latitude are 112 degrees of east longitude and 26 degrees of north latitude.
And step S120, determining target subway stations associated with the bus station according to the position information of the bus station and the position information of the subway stations, wherein the number of the target subway stations can be one or more.
Illustratively, a target subway station is determined according to the position information of the bus station and the position information of the subway station, wherein the subway station is associated with the bus station, namely, passengers can take buses at the associated bus station with a certain probability after coming out of the subway station.
For example, the target subway station associated with the bus station can be determined according to the station name information of the bus station and the station name information of the subway station.
For example, if the station name information of the bus station is the bb park main station and the station name information of the subway station is the bb park station, the subway station can be determined as the target subway station associated with the bus station.
In some embodiments, the determining a target subway station associated with the bus station according to the location information of the bus station and the location information of the subway station comprises: and determining the subway station located in the preset range of the geographical position of the bus station as a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station.
For example, it can be determined that the subway stations within 1 km are all the target subway stations according to the position information of the bus station, for example, at the front door of the bb park.
For example, it may also be determined that, for example, 5 subway stations closest to the bus station are target subway stations according to the position information of the bus station.
And S130, acquiring the bus passenger information of the bus station and the subway passenger information of the target subway station.
Illustratively, the passenger information may include a passenger number, a passenger traffic card number, a passenger's habitual boarding time, a boarding station name, and the like.
The boarding time, boarding station and the like of the passengers can be determined according to the numbers of the traffic cards swiped by the passengers when the passengers take a car.
For example, the passenger information may be determined according to a monitoring camera device in the station.
Passenger information may also be obtained, for example, at a public transportation operation center and/or a subway operation center.
And step S140, determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on the trained passenger flow prediction model.
In some embodiments, the trained traffic prediction model may be stored in the blockchain node. The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism and an encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Illustratively, the passenger flow information of the bus station is predicted according to a trained passenger flow prediction model.
Illustratively, the passenger flow information of the bus station is predicted according to the historical passenger flow information of the bus station and the subway station.
In some embodiments, the trained passenger flow prediction model comprises: the system comprises a forgetting gate, an input gate and an output gate; the method for determining the passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on the trained passenger flow prediction model comprises the following steps:
based on a forgetting door, screening the bus passenger information and the subway passenger information to obtain the passenger flow of a first bus station and the passenger flow of a first subway station; based on an input door, activating and updating the bus passenger information and the subway passenger information, and determining the passenger flow of a second bus station and the passenger flow of the second subway station according to the activated and updated bus passenger information and subway passenger information; and determining passenger flow information of the bus station according to the passenger flow of the first bus station and the second bus station and the passenger flow of the first subway station and the second subway station based on an output door.
Illustratively, after the bus passenger information and the subway passenger information are input into the model, the bus passenger information and the subway passenger information are screened based on the forgetting gate, and the passenger flow of the first bus station and the passenger flow of the first subway station are determined.
Illustratively, according to the information of a plurality of bus passengers and the information of subway passengers, the information of the passengers comprises boarding time and boarding places, the passenger flow of a bus station and the passenger flow of a subway station at corresponding time are determined, and the passenger flow is screened based on a forgetting door to obtain the passenger flow of a first bus station and the passenger flow of a first subway station.
For example, it is desirable that the predicted traffic information of the bus station is the traffic of a cc residential area at the off-duty peak time, and the left-behind door deletes the on-duty peak time and the on-boarding point not located in the cc residential area from the passenger information of the bus station and the subway station, and retains only the off-duty peak time and the passenger information of getting on/off the bus in the cc residential area.
Illustratively, let bus passenger information be x k The subway passenger information is p k ，x k The system comprises a series of historical time records { f (i, t), f (i, t-1), … }, wherein t is a time-related parameter, and the estimated passenger flow is set to be f (i, t + 1), x k And p k Inputting a forgetting gate, performing a screening operation in the forgetting gate, and outputting a value between 0 and 1 to determine whether to retain x k And p k Wherein the screening operation formula is f t ＝σ(W f [h t-1 ,x t ]+b f ) Wherein h is t-1 Output representing previous time, x t Is the input of the current time, namely, the information needing to be screened is determined according to the historical output record and the current input.
Illustratively, after the screening operation, a value between 0 and 1 is output to determine how much information is retained, and 1 is used to indicate all the reservations. The information retained after the operation is the passenger flow volume of the first bus station and the passenger flow volume of the first subway station.
Illustratively, based on the input door, the activation updating operation is performed according to the passenger information to obtain the passenger flow of the second bus station and the passenger flow of the second subway station.
Illustratively, based on the input gate, the passenger information is subjected to activation and update operation, and the activation operation is i t ＝σ(W i [h t-1 ,x t ]+b i ) (ii) a The update operation is
Figure BDA0002811943060000061
The activation operation is to determine information in the passenger information to update, the update operation is to generate new information to be selected according to the historical time information of the passenger, and the passenger flow of the second bus station and the passenger flow of the second subway station are determined according to the information in the passenger information and the information to be selected.
Illustratively, based on the forgetting gate and the input gate, useless information in the passenger information and the candidate information to be added can be determined, which is determined by using a Hadamard product.
Illustratively, the hadamard product:
Figure BDA0002811943060000062
wherein, f t ⊙C t-1 Represents forgotten information, and>
Figure BDA0002811943060000063
indicating the added candidate information.
Illustratively, the state of the current computing unit is updated according to the forgotten information and the added information to be selected.
Illustratively, the passenger flow information of the bus station is predicted according to the updated unit state for the passenger flow of the first and second bus stations and the passenger flow of the first and second subway stations.
Illustratively, the passenger flow volume of the first and second bus stations and the passenger flow volume of the first and second subway stations are calculated according to the tanh function, and the passenger flow volume information of the bus stations is determined.
Illustratively, according to o t ＝σ(W o [h t-1 ,x t ]+b o ) And h and t ＝o t ⊙tanh(C t ) Performing an operation to obtain h t Namely the predicted passenger flow information of the bus station.
Illustratively, tanh is an activation function given by:
Figure BDA0002811943060000071
illustratively, the predicted passenger flow information of the bus station is determined according to the passenger flow of the first bus station and the passenger flow of the second bus station output by the input gate and the passenger flow of the second subway station output by the output gate.
And S150, determining the number of the target vehicles of the bus station according to the passenger flow information of the bus station.
For example, the bus dispatching center may predict the passenger flow of the bus station according to the predicted passenger flow information of the bus station, so as to determine the target vehicle number of the bus station.
For example, the passenger flow during off-duty peak of friday on the bus station is significantly higher than the passenger flow during off-duty peak of wednesday, and the number of target vehicles on friday is determined to be greater than the number of target vehicles on wednesday.
Illustratively, the utilization efficiency of the bus can be improved by determining the number of the target vehicles of the bus station according to the passenger flow of the bus station, and the problems that passengers are too many and can not get on the bus and the idle rate of the bus is too high in a flat peak period are avoided.
In some embodiments, the bus dispatching method further comprises: and training according to training data to obtain the passenger flow prediction model.
Referring to fig. 2 in conjunction with the foregoing embodiments, fig. 2 is a schematic flowchart illustrating a method for training a passenger traffic prediction model according to an embodiment of the present application. The training method is used for obtaining the passenger flow prediction model through training according to training data.
The method for training the passenger flow prediction model further comprises the step of training the passenger flow prediction model before the bus station information and the subway station information are obtained, and the step S210-the step S250 are included in the method for training the passenger flow prediction model.
Step S210, training data are obtained, wherein the training data comprise bus passenger information of a bus station and subway passenger information of a subway station related to the geographical position of the bus station.
Illustratively, training data for training the passenger flow prediction model is obtained, wherein the training data comprises information of bus passengers and information of subway passengers of a subway station associated with the geographical position of the bus station.
Illustratively, the training data may be passenger information of a bus station and passenger information of a subway station within 2 km of the bus station.
Illustratively, the passenger information includes a boarding station and a time, from which the passenger volume of the corresponding station over a period of time can be determined.
Illustratively, the training data may be represented as D i ＝{(x 1 ,y 1 ),(x 2 ,y 2 ),…,(x k ,y k )}，x k ∈X i ，y k ∈Y i 。
Exemplary, x k Input features representing training data, i.e. passenger information, x, for bus stations and/or subway stations k Historical information of passengers, such as historical bus taking stations and corresponding time, is included.
And S220, based on the first passenger flow prediction model, carrying out screening, activation updating and scaling processing on the bus passenger information to determine a first weight matrix and a first deviation.
Illustratively, the first passenger flow prediction model is used for screening, activating, updating and scaling passenger information of a bus stop, and the first passenger flow prediction model is constructed based on a standard LSTM network.
Illustratively, according to the bus passenger information, the bus passenger information is calculated based on a first passenger flow prediction model, and a first weight matrix and a first deviation are determined.
In some embodiments, the first passenger flow prediction model comprises a forgetting gate, an input gate, and an output gate; the method for determining the first weight matrix and the first deviation by screening, activating, updating and scaling the bus passenger information based on the first passenger flow prediction model comprises the following steps: substep S221-step S224.
And step S221, screening the bus passenger information based on the forgotten door, determining the passenger flow of the first bus station, and obtaining a first forgotten door weight matrix and a first forgotten door deviation.
Illustratively, the first weight matrix and the first deviation are determined from passenger information of the bus stop based on a forgetting gate.
For example, the history information and the station related to the screening information from the passenger information of the bus stop according to the forgetting gate may be retained, for example, the passenger information of the bus stop includes bb park main station and cc residential area station, the boarding time is 9 am and 6 pm respectively, and if the expected predicted passenger flow information of the bus is the passenger flow of the cc residential area in the next peak, the cc residential area station and the information of 6 pm may be retained.
Exemplarily, according to the formula f t ＝σ(W f [h t-1 ,x t ]+b f ) And determining the first forgetting gate weight matrix and a first forgetting gate deviation.
Illustratively, in the calculation process, W f Determining as a first forgetting gate weight matrix, b f The first forgotten door deviation is determined.
Step S222, based on the input door, activating and updating the bus passenger information, determining the passenger flow of the second bus station, and obtaining a first input door weight matrix and a first input door deviation.
Illustratively, the bus passenger information is scaled according to the output gates to determine a first output gate weight matrix and a first output gate bias.
Illustratively, the bus passenger information is subjected to scaling processing according to the tanh activation function, and the scaling processing is performed according to the tanh activation function t ＝σ(W o [h t-1 ,x t ]+b o ) Determining, according to W in scaling process calculation o Determined as a first output gate weight matrix, and b o A first output gate offset is determined.
And S223, based on the output door, carrying out scaling processing on the bus passenger information, and determining a first output door weight matrix and a first output door deviation.
Illustratively, based on the input gates, the bus passenger information is subjected to an activation update process, the passenger flow volume of the second bus stop is determined, and a first input gate weight matrix and a first input gate bias are obtained.
Illustratively, the passenger flow volume of the second bus stop is determined according to the output of the forgotten gate, that is, the history information extracted from the bus information and the bus passenger information after the update processing of the input gate, and the first input gate weight matrix and the first input gate deviation can be obtained in the calculation process.
Illustratively, the activation process is i t ＝σ(W i [h t-1 ,x t ]+b i ) And updating
Figure BDA0002811943060000091
Illustratively, the information to be retained for activation may be determined by a sigmoid function, and the output value is 0 to 1,1 to indicate that all information is retained, where the sigmoid function is
Figure BDA0002811943060000092
Illustratively, tanh is an activation function, given by:
Figure BDA0002811943060000093
illustratively, in the calculation process, the first input gate weight matrix is determined to be W according to the activation process and the update process i And W c First input gate offset is b i And b 0 。
Step S224, determining the first weight matrix according to the first forgetting gate weight matrix, the first input gate weight matrix, and the first output gate weight matrix, and determining the first deviation according to the first forgetting gate deviation, the first input gate deviation, and the first output gate deviation.
Illustratively, the first weight matrix and the first offset are determined from the weight matrix and the offset of each operational gate.
For example, a weight matrix and a weight value corresponding to the deviation may be assigned to each operation gate, so as to determine the first weight matrix and the first deviation according to the weight values.
For example, after a plurality of learning operations, the influence of the weight matrix of the forgetting gate and the offset of the input gate on the operation result is the largest, the weight value of the weight matrix of the forgetting gate is higher than the weight values of the weight matrices of the input gate and the output gate, and the weight value of the offset of the input gate is higher than the weight values of the offsets of the forgetting gate and the output gate.
For example, determining the weight matrix and the bias train the model to make the model prediction result closer to the actual situation.
And step S230, based on the second passenger flow prediction model, carrying out screening, activation updating and scaling processing on the subway passenger information of the subway station to determine a second weight matrix and a second deviation.
Illustratively, the second passenger flow prediction model is used for screening, activating, updating and scaling the passenger information of the subway station, and the second passenger flow prediction model is constructed based on a standard LSTM network.
Illustratively, each subway station has a respective second passenger flow prediction model, and according to the respective second passenger flow prediction model, the passenger information in the respective subway station is subjected to screening, activation updating and scaling processing to determine a second weight matrix and a second deviation.
In some embodiments, the determining, based on the second passenger flow prediction model, the second weight matrix and the second deviation according to the subway passenger information screening, activation updating and scaling process of the subway station includes: substep S231-step S234.
And S231, screening the subway passenger information based on the forgetting gate, determining the passenger flow of the first subway station, and obtaining a second forgetting gate weight matrix and a second forgetting gate deviation.
Step S232, based on the input gate, activating and updating the subway passenger information, determining the passenger flow of the second subway station, and obtaining a second input gate weight matrix and a second input gate deviation.
And step S233, based on the output gate, carrying out scaling processing on the subway passenger information, and determining a second output gate weight matrix and a second output gate deviation.
Step S234, determining the second weight matrix according to the second forgetting gate weight matrix, the second input gate weight matrix, and the second output gate weight matrix, and determining the second deviation according to the second forgetting gate deviation, the second input gate deviation, and the second output gate deviation.
For example, the steps S231 to S234 may refer to the steps S221 to S224, which are not described herein.
Step S240, determining an update parameter according to the first weight matrix, the second weight matrix, the first deviation, and the second deviation.
Illustratively, the first and second weight matrices and the first and second biases are determined based on the number of times of training.
For example, the first weight matrix and the second weight matrix determined by a plurality of times of training are iteratively calculated, and the first deviation and the second deviation determined by a plurality of times of training are iteratively calculated, and updating parameters are determined according to the results of iterative calculation.
For example, the weight matrix and/or the deviation may be determined according to the training data with higher correlation with the factors, such as time, location, etc., which need to predict the passenger flow, and higher weight may be given to the training data with higher correlation when iterative computation is performed.
Illustratively, the more training times, the more accurate the first and second weight matrices and the first and second deviations are determined, so that the determined update parameters are more accurate.
For example, the update parameters may be further determined according to the first and second weight matrices and the first and second deviations, and the distance between the target subway station and the bus station.
For example, if the distance between the target subway station and the bus station is far, the probability that the passenger does not go to the bus station and is changed into a bus is high. And determining an updating parameter according to the distance.
As shown in fig. 3, fig. 3 is a schematic view of a usage scenario of a passenger traffic prediction model training method according to an embodiment of the present application.
In some embodiments, said determining an update parameter based on said first and second weight matrices and said first and second deviations comprises: acquiring a second weight matrix and a second deviation determined by each subway station based on a second passenger flow prediction model; performing aggregation processing on the second weight matrix and the second deviation of each subway station to obtain subway aggregation parameters; and determining an updating parameter according to the first weight matrix, the first deviation and the subway aggregation parameter.
For example, the second weight matrix and the second deviation determined by each subway station are obtained, and it can be understood that passenger information between each subway station is not publicly exchanged, so that the second weight matrix and the second deviation of the subway station need to be calculated by the server.
For example, the second weight matrix and the second deviation may be aggregated according to a distance between a subway station and the bus station, and if the subway station is far away from the bus station, the second weight matrix and the second deviation of the subway station are smaller during the aggregation.
Illustratively, the second weight matrix and the second deviation may be aggregated according to whether a building such as a mall or an office building exists between the subway station and the bus station.
Illustratively, the subway aggregation parameters are formulated by
Figure BDA0002811943060000121
Determining, wherein>
Figure BDA0002811943060000122
Further comprising the first weight matrix and the first bias.
Illustratively, the determining, according to the first weight matrix, the first deviation, and the subway aggregation parameter, an update parameter of a bus station i is:
Figure BDA0002811943060000123
and step S250, adjusting parameters of the first passenger flow volume prediction model according to the updated parameters, and determining the adjusted first passenger flow volume prediction model as the passenger flow volume prediction model.
Illustratively, the parameters of the first passenger flow prediction model are adjusted according to the updated parameters determined in step S240, and the adjusted first passenger flow prediction model is determined as the passenger flow prediction model.
In some embodiments, different updated parameters may be returned to perform parameter adjustments on the first passenger flow prediction model and the second passenger flow prediction model.
The parameter returned to the second passenger flow prediction model may be, for example
Figure BDA0002811943060000124
The second passenger flow prediction model is adjusted to make the second weight matrix and the second deviation determined from the second passenger flow prediction model more accurate.
Illustratively, by obtaining training data including bus passenger information for a bus stop and subway passenger information for a subway station associated with a geographic location of the bus stop; based on a first passenger flow prediction model, carrying out screening, activation updating and scaling processing on the bus passenger information to determine a first weight matrix and a first deviation; based on a second passenger flow prediction model, carrying out screening, activation updating and scaling processing on subway passenger information of a subway station to determine a second weight matrix and a second deviation; determining an updating parameter according to the first and second weight matrixes and the first and second deviations; and adjusting parameters of the first passenger flow prediction model according to the updated parameters, and determining the adjusted first passenger flow prediction model as the passenger flow prediction model. The first passenger flow prediction model can be trained according to different passenger information, and the trained first passenger flow prediction model is used as the passenger flow prediction model to more accurately predict the passenger flow of the bus station, so that the bus dispatching center can dispatch according to the predicted passenger flow, and the problems of bus overload and/or no load and the like are reduced.
Referring to fig. 4, fig. 4 is a schematic diagram of a bus dispatching device according to an embodiment of the present application, where the bus dispatching device may be configured in a server or a terminal for executing the bus dispatching method.
As shown in fig. 4, the bus dispatching device includes: the system comprises a station information acquisition module 110, a station determination module 120, a passenger information acquisition module 130, a passenger flow volume determination module 140 and a scheduling module 150.
The station information acquiring module 110 is configured to acquire bus station information and subway station information, where the bus station information includes location information of multiple bus stations, and the subway station information includes location information of multiple subway stations.
And a station determining module 120, configured to determine the subway station as a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station.
A passenger information obtaining module 130, configured to obtain bus passenger information of the bus station and subway passenger information of the target subway station.
And the passenger flow determining module 140 is configured to determine passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on the trained passenger flow prediction model.
And the scheduling module 150 is used for determining the number of the buses driving to the bus station according to the passenger flow information of the bus station.
Illustratively, the site determination module 120 includes an associated site determination sub-module.
And the associated station determining submodule is used for determining the subway station located in the preset range of the geographical position of the bus station as the target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station.
Illustratively, the passenger flow determination module 140 includes a forgetting gate sub-module, an input gate sub-module, and an output gate sub-module.
And the forgetting door sub-module is used for screening the bus passenger information and the subway passenger information to obtain the passenger flow of a first bus station and the passenger flow of a first subway station.
And the input door module is used for activating and updating the bus passenger information and the subway passenger information, and determining the passenger flow of a second bus station and the passenger flow of the second subway station according to the activated and updated bus passenger information and subway passenger information.
And the output door submodule is used for determining the passenger flow information of the bus station according to the passenger flow of the first bus station, the passenger flow of the second bus station, the passenger flow of the first subway station and the passenger flow of the second subway station.
In some embodiments, the bus dispatching device further comprises: and the passenger flow prediction model training device is used for obtaining the passenger flow prediction model according to training data.
Please refer to fig. 5 in conjunction with the foregoing embodiment, fig. 5 is a schematic diagram of a passenger traffic prediction model training device according to an embodiment of the present application, where the passenger traffic prediction model training device may be configured in a server or a terminal, and is configured to execute the passenger traffic prediction model training method, so as to obtain the passenger traffic prediction model according to training data.
As shown in fig. 5, the passenger flow prediction model training device includes: a data acquisition module 210, a first weight matrix and deviation determination module 220, a second weight matrix and deviation determination module 230, a parameter determination module 240, and a parameter adjustment module 250.
The data acquisition module 210 is configured to acquire training data, where the training data includes bus passenger information of a bus station and subway passenger information of a subway station associated with a geographical location of the bus station.
And a first weight matrix and deviation determining module 220, configured to perform, based on the first passenger flow prediction model, screening, activation updating, and scaling processing on the bus passenger information to determine a first weight matrix and a first deviation.
And a second weight matrix and deviation determining module 230, configured to determine a second weight matrix and a second deviation by performing screening, activation updating, and scaling processing on the subway passenger information of the subway station based on the second passenger flow prediction model.
A parameter determining module 240, configured to determine an update parameter according to the first weight matrix, the second weight matrix, and the first deviation and the second deviation.
And a parameter adjusting module 250, configured to adjust a parameter of the first passenger flow volume prediction model according to the updated parameter, and determine the adjusted first passenger flow volume prediction model as the passenger flow volume prediction model.
Illustratively, the first weight matrix and deviation determination module 220 includes a forgetting gate sub-module, an input gate sub-module, an output gate sub-module, and a synchronization determination module.
And the forgotten door sub-module is used for screening the bus passenger information, determining the passenger flow of the first bus station and obtaining a first forgotten door weight matrix and a first forgotten door deviation.
And the input door submodule is used for carrying out activation updating processing on the bus passenger information, determining the passenger flow of a second bus station and obtaining a first input door weight matrix and a first input door deviation.
And the output door submodule is used for carrying out scaling processing on the bus passenger information and determining a first output door weight matrix and a first output door deviation.
And the synchronous determination module is used for determining the first weight matrix according to the first forgetting gate weight matrix, the first input gate weight matrix and the first output gate weight matrix, and determining the first deviation according to the first forgetting gate deviation, the first input gate deviation and the first output gate deviation.
Illustratively, the second weight matrix and deviation determination module 230 also includes a forgetting gate sub-module, an input gate sub-module, an output gate sub-module, and a synchronization determination module.
And the door forgetting module is used for screening the bus passenger information and the subway passenger information to obtain the passenger flow of a first bus station and the passenger flow of a first subway station.
And the input gate submodule is used for activating and updating the subway passenger information, determining the passenger flow of the second subway station and obtaining a second input gate weight matrix and a second input gate deviation.
And the output gate submodule is used for carrying out scaling processing on the subway passenger information and determining a second output gate weight matrix and a second output gate deviation.
And the synchronous determining module is used for determining the second weight matrix according to the second forgetting gate weight matrix, the second input gate weight matrix and the second output gate weight matrix, and determining the second deviation according to the second forgetting gate deviation, the second input gate deviation and the second output gate deviation.
Illustratively, the parameter determination module 240 includes an aggregation parameter determination sub-module.
The aggregation parameter determining submodule is used for performing aggregation processing on the second weight matrix and the second deviation of each subway station to obtain subway aggregation parameters; and determining an updating parameter according to the first weight matrix, the first deviation and the subway aggregation parameter.
It should be noted that, as will be clear to those skilled in the art, for convenience and brevity of description, the specific working processes of the apparatus, the modules and the units described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The methods, apparatus, and computer program products of the present application are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
The above-described methods and apparatuses may be implemented, for example, in the form of a computer program that can be run on a computer device as shown in fig. 6.
Referring to fig. 6, fig. 6 is a schematic diagram of a computer device according to an embodiment of the present disclosure. The computer device may be a server or a terminal.
As shown in fig. 6, the computer device includes a processor, a memory, and a network interface connected by a system bus, wherein the memory may include a nonvolatile storage medium and an internal memory.
The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause a processor to perform any one of a bus dispatching method and/or any one of a passenger traffic prediction model training method.
The processor is used to provide computing and control capabilities to support the operation of the entire computer device.
The internal memory provides an environment for the execution of a computer program on a non-volatile storage medium, which when executed by the processor, causes the processor to perform any one of a bus dispatching method and/or any one of a passenger flow prediction model training method.
The network interface is used for network communication, such as sending assigned tasks and the like. Those skilled in the art will appreciate that the configuration of the computer apparatus is merely a block diagram of a portion of the configuration associated with aspects of the present application and is not intended to limit the computer apparatus to which aspects of the present application may be applied, and that a particular computer apparatus may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
It should be understood that the Processor may be a Central Processing Unit (CPU), and the Processor may be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, etc. Wherein a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Wherein, in some embodiments, the processor is configured to execute a computer program stored in the memory to implement the steps of: acquiring bus station information and subway station information, wherein the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations; determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station; acquiring bus passenger information of the bus station and subway passenger information of the target subway station; determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on a trained passenger flow prediction model; and determining the number of target vehicles of the bus station according to the passenger flow information of the bus station.
Illustratively, the processor is configured to, when determining a target subway station associated with the bus station based on the location information of the bus station and the location information of the subway station, implement: and determining the subway station located in the preset range of the geographical position of the bus station as a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station.
Illustratively, the processor is configured to implement, when determining the passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on the trained passenger flow prediction model, implementing: based on a forgetting door, screening the bus passenger information and the subway passenger information to obtain the passenger flow of a first bus station and the passenger flow of a first subway station; based on an input door, activating and updating the bus passenger information and the subway passenger information, and determining the passenger flow of a second bus station and the passenger flow of the second subway station according to the activated and updated bus passenger information and subway passenger information; and determining passenger flow information of the bus station according to the passenger flow of the first bus station and the second bus station and the passenger flow of the first subway station and the second subway station based on an output door.
Illustratively, the processor is further configured to implement a passenger flow model training method, and in some embodiments, the processor is configured to run a computer program stored in the memory to perform the steps of:
acquiring training data, wherein the training data comprises bus passenger information of a bus station and subway passenger information of a subway station associated with the geographical position of the bus station; based on a first passenger flow prediction model, carrying out screening, activation updating and scaling processing on the bus passenger information to determine a first weight matrix and a first deviation; based on a second passenger flow prediction model, carrying out screening, activation updating and scaling processing on subway passenger information of a subway station to determine a second weight matrix and a second deviation; determining an updating parameter according to the first and second weight matrixes and the first and second deviations; and adjusting parameters of the first passenger flow prediction model according to the updated parameters, and determining the adjusted first passenger flow prediction model as the passenger flow prediction model.
Illustratively, the processor is configured to perform, when the bus passenger information is screened, activated, updated, and scaled based on the first passenger flow prediction model to determine the first weight matrix and the first deviation, performing: based on a forgetting door, screening the bus passenger information, determining the passenger flow of a first bus station and obtaining a first forgetting door weight matrix and a first forgetting door deviation; based on an input door, carrying out activation updating processing on the bus passenger information, determining the passenger flow of a second bus station and obtaining a first input door weight matrix and a first input door deviation; based on an output door, carrying out scaling processing on the bus passenger information, and determining a first output door weight matrix and a first output door deviation; determining the first weight matrix according to the first forgetting gate weight matrix, the first input gate weight matrix and the first output gate weight matrix, and determining the first deviation according to the first forgetting gate deviation, the first input gate deviation and the first output gate deviation.
Illustratively, the processor is configured to implement, when determining the second weight matrix and the second deviation according to the subway passenger information screening, activation updating, and scaling process of the subway station based on the second passenger flow prediction model, the following: based on a forgetting gate, screening the subway passenger information, determining the passenger flow of a first subway station, and obtaining a second forgetting gate weight matrix and a second forgetting gate deviation; based on an input door, activating and updating the subway passenger information, determining the passenger flow of a second subway station and obtaining a second input door weight matrix and a second input door deviation; based on an output gate, carrying out scaling processing on the subway passenger information, and determining a second output gate weight matrix and a second output gate deviation; determining the second weight matrix according to the second forgetting gate weight matrix, the second input gate weight matrix and the second output gate weight matrix, and determining the second deviation according to the second forgetting gate deviation, the second input gate deviation and the second output gate deviation.
Illustratively, the processor is configured to, when determining the update parameter based on the first and second weight matrices and the first and second deviations, implement: acquiring a second weight matrix and a second deviation determined by each subway station based on a second passenger flow prediction model; performing aggregation processing on the second weight matrix and the second deviation of each subway station to obtain subway aggregation parameters; and determining an updating parameter according to the first weight matrix, the first deviation and the subway aggregation parameter.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application, such as:
a computer-readable storage medium, where a computer program is stored, where the computer program includes program instructions, and a processor executes the program instructions to implement any one of the bus scheduling methods and/or any one of the passenger flow prediction model training methods provided in the embodiments of the present application.
The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the computer device.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (9)

1. A bus dispatching method is characterized by comprising the following steps:
acquiring bus station information and subway station information, wherein the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations;
determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station;
acquiring bus passenger information of the bus station and subway passenger information of the target subway station;
based on a trained passenger flow prediction model, determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information;
determining the number of target vehicles of the bus station according to the passenger flow information of the bus station;
wherein, the trained passenger flow volume prediction model comprises: the system comprises a forgetting gate, an input gate and an output gate;
the method for determining the passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on the trained passenger flow prediction model comprises the following steps:
based on the forgetting door, screening the bus passenger information and the subway passenger information to obtain the passenger flow of a first bus station and the passenger flow of a first subway station;
based on the input door, activating and updating the bus passenger information and the subway passenger information, and determining the passenger flow of a second bus station and the passenger flow of a second subway station according to the activated and updated bus passenger information and subway passenger information;
and determining passenger flow information of the bus station according to the passenger flow of the first bus station, the passenger flow of the second bus station, the passenger flow of the first subway station and the passenger flow of the second subway station based on the output door.
2. The bus dispatching method according to claim 1, wherein the determining a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station comprises:
and determining the subway station located in the preset range of the geographical position of the bus station as a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station.
3. The bus dispatching method according to claim 1, wherein before the obtaining of the bus station information and the subway station information, the bus dispatching method further comprises:
acquiring training data, wherein the training data comprises bus passenger information of a bus station and subway passenger information of a subway station associated with the geographical position of the bus station;
based on a first passenger flow prediction model, carrying out screening, activation updating and scaling processing on the bus passenger information to determine a first weight matrix and a first deviation;
based on a second passenger flow prediction model, carrying out screening, activation updating and scaling processing on subway passenger information of the subway station to determine a second weight matrix and a second deviation;
determining an updating parameter according to the first weight matrix, the second weight matrix, the first deviation and the second deviation;
and adjusting the parameters of the first passenger flow prediction model according to the updated parameters, and determining the adjusted first passenger flow prediction model as the passenger flow prediction model.
4. The bus dispatching method according to claim 3, wherein the first passenger flow prediction model and the second passenger flow prediction model each comprise: the forgetting gate, the input gate and the output gate;
the method for determining the first weight matrix and the first deviation by screening, activating, updating and scaling the bus passenger information based on the first passenger flow prediction model comprises the following steps:
based on the forgetting door, screening the bus passenger information, determining the passenger flow of a first bus station, and obtaining a first forgetting door weight matrix and a first forgetting door deviation;
based on the input door, activating and updating the bus passenger information, determining the passenger flow of a second bus station and obtaining a first input door weight matrix and a first input door deviation;
based on the output door, carrying out scaling processing on the bus passenger information, and determining a first output door weight matrix and a first output door deviation;
determining the first weight matrix according to the first forgetting gate weight matrix, the first input gate weight matrix and the first output gate weight matrix, and determining the first deviation according to the first forgetting gate deviation, the first input gate deviation and the first output gate deviation;
the determining of the second weight matrix and the second deviation according to the subway passenger information screening, activation updating and scaling processing of the subway station based on the second passenger flow prediction model comprises the following steps:
based on the forgetting gate, screening the subway passenger information, determining the passenger flow of a first subway station and obtaining a second forgetting gate weight matrix and a second forgetting gate deviation;
based on the input gate, activating and updating the subway passenger information, determining the passenger flow of a second subway station and obtaining a second input gate weight matrix and a second input gate deviation;
based on the output gate, carrying out scaling processing on the subway passenger information, and determining a second output gate weight matrix and a second output gate deviation;
and determining the second weight matrix according to the second forgetting gate weight matrix, the second input gate weight matrix and the second output gate weight matrix, and determining the second deviation according to the second forgetting gate deviation, the second input gate deviation and the second output gate deviation.
5. The bus dispatching method according to claim 3, wherein the determining an update parameter according to the first weight matrix, the second weight matrix and the first deviation and the second deviation comprises:
performing aggregation processing on the second weight matrix and the second deviation of each subway station to obtain subway aggregation parameters;
and determining an updating parameter according to the first weight matrix, the first deviation and the subway aggregation parameter.
6. An apparatus for bus dispatching, the apparatus comprising:
the system comprises a station information acquisition module, a data processing module and a data processing module, wherein the station information acquisition module is used for acquiring bus station information and subway station information, the bus station information comprises position information of a plurality of bus stations, and the subway station information comprises position information of a plurality of subway stations;
the station determining module is used for determining the subway station as a target subway station associated with the bus station according to the position information of the bus station and the position information of the subway station;
the passenger information acquisition module is used for acquiring the bus passenger information of the bus station and the subway passenger information of the target subway station;
the passenger flow determining module is used for determining passenger flow information of the bus station according to the bus passenger information and the subway passenger information based on a trained passenger flow prediction model;
the dispatching module is used for determining the number of buses driving to the bus station according to the passenger flow information of the bus station;
wherein the passenger flow volume determination module comprises:
the first passenger flow determining submodule is used for screening the bus passenger information and the subway passenger information based on a forgetting door of a trained passenger flow prediction model to obtain the passenger flow of a first bus station and the passenger flow of the first subway station;
the second passenger flow volume determining submodule is used for activating and updating the bus passenger information and the subway passenger information based on an input door of a trained passenger flow volume prediction model, and determining the passenger flow volume of a second bus station and the passenger flow volume of the second subway station according to the activated and updated bus passenger information and subway passenger information;
and the third passenger flow volume determining submodule is used for determining the passenger flow volume information of the bus station according to the passenger flow volume of the first bus station, the passenger flow volume of the second bus station, the passenger flow volume of the first subway station and the passenger flow volume of the second subway station based on the output door of the trained passenger flow volume prediction model.
7. The apparatus for bus dispatching of claim 6, further comprising:
the data acquisition module is used for acquiring training data, wherein the training data comprises bus passenger information of a bus station and subway passenger information of a subway station associated with the geographical position of the bus station;
the first weight matrix and deviation determining module is used for screening, activating, updating and scaling the bus passenger information based on a first passenger flow prediction model to determine a first weight matrix and a first deviation;
the second weight matrix and deviation determining module is used for screening, activating, updating and scaling the subway passenger information of the subway station to determine a second weight matrix and a second deviation based on a second passenger flow prediction model;
a parameter determining module, configured to determine an update parameter according to the first weight matrix, the second weight matrix, the first deviation, and the second deviation;
and the parameter adjusting module is used for adjusting the parameters of the first passenger flow volume prediction model according to the updated parameters and determining the adjusted first passenger flow volume prediction model as the passenger flow volume prediction model.
8. A computer device, wherein the computer device comprises a memory and a processor;
the memory for storing a computer program;
the processor is used for executing the computer program and realizing the following when the computer program is executed:
the bus dispatching method as recited in any of claims 1-5.
9. A computer-readable storage medium, the computer-readable storage medium storing a computer program, wherein execution of the computer program by a processor results in:
the bus dispatching method as recited in any of claims 1-5.
CN202011389837.1A 2020-12-01 2020-12-01 Bus scheduling method and device, computer equipment and medium Active CN112562378B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202011389837.1A CN112562378B (en) 2020-12-01 2020-12-01 Bus scheduling method and device, computer equipment and medium
PCT/CN2021/084302 WO2022116447A1 (en) 2020-12-01 2021-03-31 Bus dispatching method and apparatus, and computer device and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011389837.1A CN112562378B (en) 2020-12-01 2020-12-01 Bus scheduling method and device, computer equipment and medium

Publications (2)

Publication Number Publication Date
CN112562378A CN112562378A (en) 2021-03-26
CN112562378B true CN112562378B (en) 2023-04-18

Family

ID=75047666

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011389837.1A Active CN112562378B (en) 2020-12-01 2020-12-01 Bus scheduling method and device, computer equipment and medium

Country Status (2)

Country Link
CN (1) CN112562378B (en)
WO (1) WO2022116447A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112562378B (en) * 2020-12-01 2023-04-18 平安科技（深圳）有限公司 Bus scheduling method and device, computer equipment and medium
CN113284362A (en) * 2021-05-19 2021-08-20 中国联合网络通信集团有限公司 Bus scheduling method, device, equipment and storage medium
CN114693495B (en) * 2022-05-24 2022-08-23 成都秦川物联网科技股份有限公司 Smart city public traffic management method, Internet of things system, device and medium
CN115409295B (en) * 2022-11-01 2023-02-14 深圳市城市交通规划设计研究中心股份有限公司 Bus scheduling method based on bottleneck analysis, electronic equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107273999A (en) * 2017-04-27 2017-10-20 北京交通大学 A kind of Flow Prediction in Urban Mass Transit method under accident
CN107545320A (en) * 2017-07-03 2018-01-05 北京交通大学 A kind of urban track traffic passenger paths planning method and system based on graph theory
CN110956328A (en) * 2019-11-30 2020-04-03 天津市市政工程设计研究院 Large passenger flow influence rail transit station bus connection scale prediction method
CN111079875A (en) * 2019-12-17 2020-04-28 广州交通信息化建设投资营运有限公司 Public transport passenger flow monitoring method and device based on multi-source data and storage medium
CN111640294A (en) * 2020-04-27 2020-09-08 河海大学 Method for predicting passenger flow change of urban bus line under influence of newly-built subway line
CN111785017A (en) * 2020-05-28 2020-10-16 上海博泰悦臻电子设备制造有限公司 Bus scheduling method and device and computer storage medium
CN111932925A (en) * 2020-07-09 2020-11-13 中咨数据有限公司 Method, device and system for determining travel passenger flow of public transport station

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090207049A1 (en) * 2008-02-15 2009-08-20 Chunghwa United Television Co., Ltd. Method for smart announcing of bus stop
US20130041941A1 (en) * 2010-04-09 2013-02-14 Carnegie Mellon University Crowd-Sourcing of Information for Shared Transportation Vehicles
US8306848B1 (en) * 2011-06-06 2012-11-06 International Business Machines Corporation Estimation of transit demand models for enhancing ridership
CN105224992A (en) * 2014-05-28 2016-01-06 国际商业机器公司 To waiting for the method and system predicted of ridership and evaluation method and system
CN104318113A (en) * 2014-10-29 2015-01-28 中国科学院深圳先进技术研究院 Passenger transfer spatial-temporal characteristics based method and system for calculating passengers' boarding stations
CN105469602B (en) * 2015-12-31 2017-08-11 北京航空航天大学 A kind of Forecasting Methodology of the bus passenger waiting time scope based on IC-card data
CN106652434B (en) * 2016-12-02 2019-04-30 东南大学 A kind of bus dispatching method coordinated based on rail traffic
CN107358045A (en) * 2017-07-12 2017-11-17 东南大学 A kind of flow and method for evaluating subway and regular public traffic interchange efficiency
CN107529651B (en) * 2017-08-18 2020-10-16 北京航空航天大学 Urban traffic passenger flow prediction method and equipment based on deep learning
KR101974109B1 (en) * 2017-12-21 2019-04-30 그제고스 말레비치 A method and a computer system for providing a route or a route duration for a journey from a source location to a target location
CN109887267B (en) * 2019-03-21 2021-04-30 华侨大学 Conventional public transportation adjusting method for common line segment of rail transit
CN110991794B (en) * 2019-10-28 2024-01-19 上海城市交通设计院有限公司 Urban rail and public transport two-network fusion level evaluation method
CN111985710B (en) * 2020-08-18 2023-08-25 深圳诺地思维数字科技有限公司 Bus passenger travel station prediction method, storage medium and server
CN112562378B (en) * 2020-12-01 2023-04-18 平安科技（深圳）有限公司 Bus scheduling method and device, computer equipment and medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107273999A (en) * 2017-04-27 2017-10-20 北京交通大学 A kind of Flow Prediction in Urban Mass Transit method under accident
CN107545320A (en) * 2017-07-03 2018-01-05 北京交通大学 A kind of urban track traffic passenger paths planning method and system based on graph theory
CN110956328A (en) * 2019-11-30 2020-04-03 天津市市政工程设计研究院 Large passenger flow influence rail transit station bus connection scale prediction method
CN111079875A (en) * 2019-12-17 2020-04-28 广州交通信息化建设投资营运有限公司 Public transport passenger flow monitoring method and device based on multi-source data and storage medium
CN111640294A (en) * 2020-04-27 2020-09-08 河海大学 Method for predicting passenger flow change of urban bus line under influence of newly-built subway line
CN111785017A (en) * 2020-05-28 2020-10-16 上海博泰悦臻电子设备制造有限公司 Bus scheduling method and device and computer storage medium
CN111932925A (en) * 2020-07-09 2020-11-13 中咨数据有限公司 Method, device and system for determining travel passenger flow of public transport station

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
马飞虎等.基于EMD优化NAR动态神经网络的地铁客流量短时预测模型.《应用科学学报》.2020,第38卷(第6期),第936-943页. *

Also Published As

Publication number Publication date
WO2022116447A1 (en) 2022-06-09
CN112562378A (en) 2021-03-26

Similar Documents

Publication Publication Date Title
CN112562378B (en) Bus scheduling method and device, computer equipment and medium
CN109872535B (en) Intelligent traffic passage prediction method, device and server
Hoang et al. FCCF: Forecasting citywide crowd flows based on big data
Liu et al. Context-aware taxi dispatching at city-scale using deep reinforcement learning
CN113326126B (en) Task processing method, task scheduling method, device and computer equipment
US20200050938A1 (en) Systems and methods for improvement of index prediction and model building
CN110570678B (en) Method and device for predicting total travel time of bus from starting point to end point
CN105593769A (en) Context aware command and control system
CN112862546B (en) User loss prediction method and device, computer equipment and storage medium
Nejadettehad et al. Short-term demand forecasting for online car-hailing services using recurrent neural networks
US11507896B2 (en) Method and system for spatial-temporal carpool dual-pricing in ridesharing
CN116346863A (en) Vehicle-mounted network data processing method, device, equipment and medium based on federal learning
Brahimi et al. Modelling on Car‐Sharing Serial Prediction Based on Machine Learning and Deep Learning
Zhang et al. Graph-based traffic forecasting via communication-efficient federated learning
CN111845768A (en) Vehicle running parameter prediction method and device
CN113159408B (en) Rail transit station passenger flow prediction method and device
CN112230663B (en) Method and device for monitoring vehicle positioning data
CN111327473B (en) Network regulation and control method, device, network regulation and control system and electronic equipment
CN115907136B (en) Electric automobile dispatching method, device, equipment and computer readable medium
Xu et al. An LSTM approach for predicting the short-time passenger flow of urban bus
CN115936379A (en) Shared vehicle scheduling method, device, equipment and storage medium
CN111260912B (en) Method and device for processing vehicle formation
CN110782063B (en) Regional congestion degree prediction method and device
CN113837397A (en) Model training method and device based on federal learning and related equipment
CN116311951B (en) Traffic volume data processing method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant