WO2019003672A1 - 交通需要予測装置、及び交通需要予測方法 - Google Patents

交通需要予測装置、及び交通需要予測方法 Download PDF

Info

Publication number
WO2019003672A1
WO2019003672A1 PCT/JP2018/018595 JP2018018595W WO2019003672A1 WO 2019003672 A1 WO2019003672 A1 WO 2019003672A1 JP 2018018595 W JP2018018595 W JP 2018018595W WO 2019003672 A1 WO2019003672 A1 WO 2019003672A1
Authority
WO
WIPO (PCT)
Prior art keywords
route
traffic
information
demand
movement
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.)
Ceased
Application number
PCT/JP2018/018595
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
友恵 富山
浩仁 矢野
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.)
Hitachi Ltd
Original Assignee
Hitachi 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 Hitachi Ltd filed Critical Hitachi Ltd
Priority to SG11201907852SA priority Critical patent/SG11201907852SA/en
Priority to EP18823362.1A priority patent/EP3572991A4/en
Publication of WO2019003672A1 publication Critical patent/WO2019003672A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles

Definitions

  • the present invention relates to a traffic demand prediction device and a traffic demand prediction method.
  • Patent Document 1 when the present location of the mobile and its destination are zones where public transportation can be used, when switching to the expected cost and public transportation using only road traffic A technology has been proposed that can be used to guide mixed routes used in combination with road traffic and public transportation in comparison with the expected cost of
  • Patent Document 1 Although it is possible to calculate the movement route of each mobile person, congestion of public transportation caused by a situation where a plurality of mobile persons are concentrated on a specific route, congestion of roads is predicted Not considered. For this reason, we can not cope with imbalance of movement demand among plural movement routes between certain two points such as large event holding, operation disorder of public transport by various factors, traffic jam of road by traffic accident etc. There was a problem.
  • the present invention has been made to solve the above and other problems, and one object of the present invention is to timely consider a plurality of moving means constituting a moving path while considering the temporal demand fluctuation of each.
  • a traffic demand forecasting device capable of executing traffic demand forecasting, and a traffic demand forecasting method.
  • Transport service plan information which is information
  • travel demand forecast information which is forecast information on travel demand between points in the forecast target area
  • traffic congestion information which is information on congestion degree of the transit service
  • the first route which is the route from each point to the nearest boarding point of public transportation, is acquired between the two points in the prediction target area by acquiring the traffic congestion information which is information on the traffic congestion state of the road traffic in the area.
  • a second route which is a route for traveling by public transportation between the nearest boarding points, and a square of the public transportation included in the two points or in the second route.
  • a route model is created and acquired including a third route connecting between any one of the two points or between the two points and the transit point of the public transportation included in the second route by the preset road traffic.
  • the route model between the departure point and the destination point of the movement demand included in the movement demand forecast information, the movement from the combination point from the first route to the third route to the destination point
  • the route is extracted, and the congestion degree and congestion condition regarding the traffic and road traffic included in the movement route are calculated from the traffic congestion information and traffic congestion information, and the congestion degree or congestion condition is included.
  • the utility value for each movement route is calculated based on the evaluation index, and movement from the departure point to the destination point obtained from the movement demand forecast information Allocated to each travel route numbers as sharing migrants based on the utility value for the travel route, a traffic demand prediction method aggregate and outputs for each public transportation included in each movement path.
  • FIG. 1 is a diagram showing a configuration example of a traffic system 1 including a traffic demand prediction apparatus 150 according to an embodiment of the present invention.
  • FIG. 2 is a view showing a configuration example of the computer 10.
  • FIG. 3 is a view showing a configuration example of the transportation planning device 110.
  • FIG. 4 is a diagram showing a configuration example of the movement demand prediction apparatus 120.
  • FIG. 5 is a diagram showing a configuration example of the congestion prediction device 130.
  • FIG. FIG. 6 is a diagram showing a configuration example of the traffic jam prediction device 140.
  • FIG. FIG. 7 is a view showing a configuration example of the passenger terminal device 160.
  • FIG. 8 is a diagram showing a configuration example of the traffic demand prediction device 150.
  • FIG. 9 is a view showing a configuration example of the transportation service plan information 1000.
  • FIG. 10 is a diagram showing a configuration example of the movement demand prediction information 2000.
  • FIG. 11 is a view showing a configuration example of the traffic congestion information 3000.
  • FIG. 12 is a diagram showing a configuration example of the traffic congestion information 4000.
  • FIG. 13 is a diagram showing an example of a network model used by the traffic demand prediction apparatus 150.
  • FIG. 14 is a flowchart showing an example of the data processing flow by the traffic demand prediction apparatus 150.
  • FIG. 15 is a diagram showing an output example of the traffic demand prediction information by the traffic demand prediction device 150.
  • FIG. 16 is a diagram showing an output display example of the traffic demand prediction result by the traffic demand prediction device 150.
  • FIG. 17 is a diagram showing a configuration example of a traffic demand prediction apparatus 150 according to another embodiment.
  • FIG. 18 is a flow chart showing an example of the data processing flow by the traffic demand prediction apparatus 150 according to another embodiment.
  • FIG. 19 is a diagram showing an example of a calculation convergence operation screen applied to the data processing flow of FIG.
  • FIG. 1 is a block diagram showing an example of the overall configuration of a traffic information system 100 including a traffic demand prediction apparatus 150 according to a first embodiment of the present invention.
  • the traffic information system 100 provides efficient means of transportation such as a railway company, a transit bus company, etc., providing appropriate means of transportation on demand in response to fluctuations in traffic demand in the traffic service provision area. The purpose is to contribute to
  • the traffic information system 100 of FIG. 1 includes a transportation planning device 110, a movement demand prediction device 120, a congestion prediction device 130, a traffic congestion prediction device 140, a traffic demand prediction device 150, and a passenger terminal device 160, and among these devices
  • a communication network N is communicably connected.
  • the computer 10 includes a main storage device 12 configured of a processor 11 such as a central processing unit (CPU) and storage devices such as a random access memory (RAM) and a read only memory (ROM).
  • a main storage device 12 configured of a processor 11 such as a central processing unit (CPU) and storage devices such as a random access memory (RAM) and a read only memory (ROM).
  • An auxiliary storage device 13 such as a hard disk drive (HDD) or a solid state drive (SSD), an input device 14 comprising a keyboard, a mouse, a touch panel, etc., an output device 15 comprising a display, a printer, a speaker etc., a communication network N
  • a communication device 16 for communicating with another computer via
  • the communication network N can be configured without particular restrictions, including appropriate communication lines such as the Internet, various leased lines, mobile telephone networks, WANs, and LANs.
  • the traffic demand prediction apparatus 150 shown in FIG. 1 is configured to estimate the public transportation operation plan in the prediction target area from the transportation planning device 110, and to the public transportation agency from the travel demand prediction apparatus 120, among various points in the prediction target area.
  • Receive forecasted information on passenger movement demand from congestion forecasting device 130 congestion rate forecasting information on each public transportation in the operation section within the forecasting area, and congestion forecasting information on roads in the forecasting area from congestion forecasting apparatus 140 Then, it predicts the passenger movement between various points in the forecast target area, and provides the forecast result to the public transport organization, the road manager, etc.
  • public transportation uses this prediction result to take timely measures such as operation status information for passengers and operation of temporary trains and temporary bus services for sections where traffic demand is increasing. Do.
  • the traffic demand prediction result calculated by the traffic demand prediction device 150 can also be provided to the passenger terminal device 160.
  • the passenger terminal device 160 is assumed to be a portable terminal such as a smartphone possessed by a person who intends to move using a public transportation facility or the like.
  • the traffic demand prediction device 150 can provide the passenger with the traffic demand prediction result via an appropriate application program or the like installed in the passenger terminal device 160.
  • the passenger who obtained this information can decide the route to his destination accordingly.
  • the traffic demand forecast result may be provided to a service provider who provides a navigation service to a mobile terminal or the like. It is also possible to provide the public with the traffic demand forecast results at facilities of public transportation facilities, stations, bus terminals and the like through digital signage and the like.
  • Each device other than the traffic demand prediction device 150 or a device corresponding thereto provides an organization such as a railway company, a route bus company, a road manager or the like related to the traffic service in the traffic demand prediction target area or prediction information thereof. It is installed in information service companies, data centers, etc. First, the configuration of these devices will be described below.
  • the structural example of the transportation planning apparatus 110 is shown in FIG.
  • the transportation planning device 110 is a transportation planning based on, for example, required transportation amount prediction information for each unit time predicted by the transportation demand prediction device 120 installed in a public transportation organization such as a railway company or a route bus company. It creates and holds transportation plan information such as train diagrams and bus operation tables.
  • the transportation planning unit 110 executes, for example, the transportation planning unit 111 described above, the communication unit 112 for receiving information necessary for transportation planning processing from the external device, and the prepared transportation plan as train diagram information. And the like, and is configured to include an output unit 113 for outputting as, for example.
  • the transportation planning unit 111, the communication unit 112, and the output unit 113 can be configured as a program that operates on the computer 10 illustrated in FIG. The same applies to the other devices included in the traffic information system 100 of FIG.
  • the structural example of the movement demand prediction apparatus 120 is shown in FIG.
  • the movement demand prediction device 120 is installed in a public transportation facility such as a railway company or a route bus company, for example, and statistical information on the amount of passenger movement between various points in the transportation service provision area periodically implemented by the country or local government etc. Based on basic information such as holding events, etc., daily weather forecasts, etc., passenger movement demand forecast information between various points in the target area is calculated and held.
  • the movement demand prediction apparatus 120 includes a movement demand prediction unit 121 that executes passenger movement demand prediction information generation processing based on the basic information, and a communication unit 122 for transmitting the generated movement demand prediction information to an external device. Configured
  • FIG. 5 shows a configuration example of the congestion prediction device 130.
  • the congestion forecasting device 130 is installed in a public transportation facility such as a railway company or a route bus company, for example, according to the operation plan such as trains and buses prepared by the transportation planning device 110 and the passenger movement demand prediction information generated by the movement demand prediction device 120
  • the congestion degree for each time of the operation section such as between stations and between stops is calculated and held as a numerical value such as a boarding rate.
  • the calculation of the congestion degree is repeatedly performed by feeding back the traffic demand prediction result by the traffic demand prediction device 150.
  • the congestion prediction device 130 performs calculation of the congestion degree, and a communication unit 132 for transmitting information on the calculated congestion degree to an external device and receiving a calculation result from the traffic demand prediction device 150. It is configured with.
  • the structural example of the traffic congestion prediction apparatus 140 is shown in FIG.
  • the congestion prediction device 140 is installed, for example, in a business entity that collects and provides road traffic information, and generates congestion prediction information based on traffic condition statistical information for each section, day, and hour for each road in the target area. Generate and hold.
  • the calculation result of the traffic demand prediction device 150 is also fed back and repeatedly executed for the congestion occurrence prediction.
  • the traffic congestion prediction device 140 executes the processing of generating the traffic congestion prediction information, and transmits the generated traffic congestion prediction information external device to the generated traffic congestion prediction information external device, and a communication unit 142 for receiving the calculation result from the traffic demand prediction device 150. It is configured with.
  • the passenger terminal device 160 is, for example, a portable terminal such as a smart phone or a tablet terminal possessed by a passenger using a public transportation facility, and as shown in FIG. , And a communication unit 163 that provides a communication function with a mobile telephone communication network, the Internet, and the like.
  • each device shown in FIG. 3 to FIG. 7 is an example, and it is acceptable to provide another functional unit not shown according to the function required for each device. Also, these devices may be provided as independent elements as shown in FIG. 1, or may be configured to combine and integrate some devices.
  • the traffic demand prediction device 150 in the present embodiment will be described.
  • the structural example of the traffic demand prediction apparatus 150 is shown in FIG.
  • the traffic demand prediction device 150 is typically installed at a business establishment of a service provider who is engaged in providing traffic demand forecast information to a public transportation service provider such as a railway company, for example. It may be configured by a cloud computing system on a network.
  • the traffic demand prediction apparatus 150 of this embodiment includes an input unit 151, an output unit 152, a communication unit 153, a movement distribution calculation unit 154, a prediction device cooperation unit 155, and a storage unit 157. Be done.
  • the input unit 151 has a function of receiving an input from a user through an input device for inputting an instruction to a computer such as a keyboard, a mouse, and a touch panel.
  • the output unit 152 has a function of outputting information to the user such as an execution status of data processing by the traffic demand prediction apparatus 150 and an execution result through an output device such as a display, a printer, and a speaker.
  • the communication unit 153 has a function of exchanging various data and commands with other external devices via the communication network N.
  • the movement allocation calculation unit 154 is a program that executes data processing for calculating traffic demand prediction information, which is a main function of the present apparatus, and is configured to include a plurality of subprograms described later.
  • the storage unit 157 is a storage area in which various data used by the traffic demand prediction apparatus 150 to execute data processing is stored. As shown in FIG. 8, the storage unit 157 stores transportation service plan information 1000, travel demand prediction information 2000, traffic congestion information 3000, and traffic congestion information 4000. Each piece of stored information will be described later.
  • the network model creation unit 1541 reads the transportation service plan information 1000 and the movement demand forecast information 2000 stored in the storage unit 157, and the boarding point of public transportation in the target area of the traffic demand prediction apparatus 150, the departure place of the movement demand. Create a network model that represents the destination, and the transfer between road traffic and public transport.
  • the basic configuration and configuration example of the network model created here will be described later.
  • the movement demand information classification unit 1542 reads the movement demand prediction information 2000 stored in the storage unit 157, and organizes, classifies and stores the passenger movement between points in the prediction target area according to the departure place, the destination, and the departure time zone. doing.
  • the movement route calculation unit 1543 executes, for each movement demand classified by the movement demand information classification unit 1542, a process of extracting a movement route in the network model created by the network model creation unit 1541.
  • the utility value calculation unit 1544 adjusts the traffic congestion information 3000 and the traffic congestion information 4000 stored in the storage unit 157 according to the departure time of each movement demand classified by the movement demand information classification unit 1542. Based on the above, evaluation values such as required time, fare, degree of congestion, degree of congestion, etc. of each transportation system are calculated, and processing of calculating the utility value of the movement route is executed based on the calculated evaluation values. Based on the utility value calculated by the utility value calculation unit 1544, the sharing mobile number calculation unit 1545 executes processing for calculating the distribution of the number of moving persons in the movement route for each movement demand.
  • the prediction device linkage unit 155 calls the congestion prediction device 130 and the traffic congestion prediction device 140, and transmits the number of mobile persons calculated by the shared mobile number calculation unit 1545 for each transport device handled by each prediction device, while each device The function of receiving the prediction result of
  • the calculation convergence determination unit 156 has a function of comparing the result received by the prediction device linkage unit 155 with the traffic demand prediction result up to the previous time, and determining whether the traffic demand prediction calculation has converged.
  • the convergence of the calculation means an event in which the sharing of the number of mobile persons of the moving route converges and becomes stable as a result of executing the prediction calculation.
  • the network model correction unit 1541 corrects the network model
  • the movement route calculation unit 1543 calculates the movement route
  • the sharing movement number calculation unit 1545 calculates the movement number
  • the prediction device of the cooperation unit 155 is called, and the calculation convergence determination unit 156 determines whether the calculation convergence is present or not repeatedly.
  • the transportation service plan information 1000 is information defining transportation capacity planned in advance for transportation services by public transportation such as railways, local buses, taxis, etc., and a point where passengers such as a station, a bus stop and a taxi stand can get on and off. In addition, it is information that records the time when each transit flight set for that point arrives, departs, or passes. On the day of operation, the transportation service plan information 1000 includes the current operation status and the time at which the prediction of the future operation status is reflected. In other words, in the transportation service plan information 1000, information such as disturbance of the operation time due to various causes and a recovery schedule thereof is incorporated. The transportation service plan information 1000 is calculated by the transportation planning unit 111 of the transportation planning device 110, and transmitted to the traffic demand prediction device 150 via the communication unit 112.
  • FIG. 9 shows a configuration example of the transportation service plan information 1000 in the present embodiment.
  • the transportation service plan information 1000 is configured as a data table having a plurality of records. Each record includes items of a name 1001, a transportation facility 1002, a point 1003, an arrival time 1004, and a departure time 1005.
  • the name 1001 stores a name for uniquely identifying the transportation service provided by the transportation service (public transportation organization) which is the processing target of the traffic demand prediction apparatus 150.
  • codes such as a train number, an operation number, and a vehicle symbol can be recorded.
  • the transportation organization 1002 stores the type of transportation organization to which the transportation service identified by the name 1001 belongs.
  • the transportation facility 1002 is used to identify what transportation means the transportation service is, when presenting the transportation service as an output of the device.
  • the transportation facility 1002 can include types such as trains, route buses, taxis, and the like.
  • a point 1003 stores a point at which the transit service identified by the name 1001 stops or passes.
  • the station 1003 sets a station if it is a railway, a stop if it is a route bus, a station where passengers are going to get on and off if it is a reserved taxi, and a main intersection etc. if it is a taxi that has not been reserved be able to.
  • the arrival time 1004 stores the time when the transit flight identified by the name 1001 arrives at the point 1003. When the corresponding transit flight passes the point 1003, the arrival time 1004 is, for example, blank.
  • the departure time 1005 stores the time when the transit flight identified by the name 1001 leaves or passes through the point 1003.
  • the movement demand prediction information 2000 is information indicating a prediction value regarding the number of people who are going to move from one point in the prediction target area to another point.
  • the movement demand prediction information 2000 is calculated by the movement demand prediction unit 121 of the movement demand prediction device 120, and is transmitted to the traffic demand prediction device 150 via the communication unit 122.
  • FIG. 10 shows a configuration example of the movement demand forecast information 2000.
  • the movement demand forecast information 2000 is configured as a data table having a plurality of records. Each record includes items of ID 2001, departure time zone 2002, origin 2003, final destination 2004, and number of people in demand 2005.
  • the ID 2001 stores a code for uniquely identifying each record stored in the movement demand forecast information 2000.
  • the departure time zone 2002 stores the time zone in which the mobile (passenger) who corresponds to the travel demand identified by the ID 2001 starts moving.
  • the departure point 2003 stores a point at which a mobile person corresponding to the movement demand identified by the ID 2001 starts moving.
  • the final destination 2004 stores a point at which the mobile person corresponding to the movement demand identified by the ID 2001 ends the movement.
  • the origin 2003 and the final destination 2004 are represented by the points defined in the transportation service plan information 1000.
  • the number of people in demand 2005 stores the number of mobile persons who correspond to the movement demand identified by the ID 2001. In the example of FIG. 10, the movement demand specified by the ID "1" indicates that it is predicted that 1000 people will go from the point A to the point E between "7:30 to 7:35". .
  • the traffic congestion information 3000 is information defining a predicted congestion rate for each transportation service defined by the transportation service plan information 1000, and as shown in FIG. 11, an identification code 3001 for uniquely identifying the transportation service. It can be configured to include the predicted value of the congestion rate 3002 of the transit flight.
  • the congestion rate of the transportation service may be recorded as the congestion rate between stations in the case of a railway, or the congestion rate between stops in the case of a route bus.
  • the traffic congestion information 3000 is calculated by the congestion prediction unit 131 of the congestion prediction device 130, and transmitted to the traffic demand prediction device 150 via the communication unit 132.
  • the traffic congestion information 4000 is information defining the current congestion status of the road and the predicted value of the traffic congestion status of the future road, and specifies, for example, the start position 4001 and the termination position 4002 of the traffic congestion information as illustrated in FIG. Position information, a predicted value of the traffic jam length 4003 from the start point to the end point, and a predicted value of the required travel time 4004 from the start point to the end point can be configured.
  • the traffic congestion information 4000 is calculated by the traffic congestion prediction unit 141 of the traffic congestion prediction device 140 and is transmitted to the traffic demand prediction device 150 via the communication unit 142.
  • FIG. 13 An example of this network model is illustrated in FIG. This network model models and expresses the movement route from the departure place to the final destination set in the prediction target area and the transportation means to be used. As shown in FIG. 13, the network is represented by connecting nodes representing points in the prediction target area with lines (links) representing transportation means that can be selected between the nodes. The nodes represent either a departure point, an end point, or a passing point included in the movement route.
  • the departure place of the movement demand, the final destination, the departure place of the movement demand and the nearest available transportation and unloading point, the final destination of the movement demand and the nearest transportation flight can be defined as defined in the movement demand forecast information 2000 Links (first and second routes) representing movement by road traffic (cars, taxis, etc.) are created between nodes at each point.
  • FIG. 13 shows the network model created using the record example of the transportation service plan information 1000 shown in FIG. 9, created in consideration of the movement demand shown in the top record of the movement demand forecast information 2000 shown in FIG.
  • the network model is shown.
  • the points shown in the transportation service plan information 1000 of FIG. 9 are represented as nodes 1302 like the stations A to F, and are connected by links 1303 according to the transportation provided between the nodes 1302.
  • the node 1301 corresponding to the starting point and final destination A and E of the movement demand is created, and between the nearest station and starting point (point A) and final destination (point E) of each point. Create a link representing road traffic at.
  • the required time is the shortest by comparing in advance the required times of a plurality of routes of road traffic connecting the respective nodes. I set one route. Thereby, the calculation time of the movement route search can be shortened.
  • FIG. 14 shows an example of a processing flow of traffic demand prediction processing according to the present embodiment.
  • the symbol S in the figure represents a step.
  • the network model creation unit 1541 reads the transportation service plan information 1000 and the movement demand forecast information 2000 stored in the storage unit 157, and each transportation service defined by the transportation service plan information 1000, the departure place and purpose of the movement demand A network model representing the ground is created as described above (S201). In the example of the present embodiment, it is assumed that a network model illustrated in FIG. 13 is created.
  • the processing start timing is triggered by the power on of the traffic demand prediction device 150 or the like, the update timing of travel demand information, and the like.
  • the movement demand information classification unit 1542 reads the movement demand prediction information 2000 stored in the storage unit 157, and classifies the plurality of acquired records based on the departure place and the destination, and the departure time zone (S202) ).
  • the movement route calculation unit 1543 repeatedly executes the processing of S204 to S207 for all of the plurality of movement demands classified by the movement demand information classification unit 1542 (S203).
  • the movement route calculation unit 1543 acquires one unprocessed movement demand among the movement demands classified by the movement demand information classification unit 1542 (S 204), and is included in the route connecting the obtained movement demand departure place and the destination. Nodes and links connected to the nodes are all extracted from the network model created in S201 (S205).
  • the utility value calculation unit 1544 has the traffic congestion information 3000 and the traffic congestion information stored in the storage unit 157 for the link whose transportation means is public transportation. Based on the traffic congestion information 4000, it determines the transportation service on which the passenger constituting the movement demand to be processed gets, and travels the movement section represented by each link using the transportation service plan information 1000 for the determined transportation service. Calculate the required time for The utility value calculation unit 1544 calculates the evaluation index of each link in consideration of the calculated required time, and the comparison factor such as the congestion degree (riding rate) of the transport service and the cost (fare). Among the comparison elements required for calculating the evaluation index, fixed values such as the cost (fare) for transportation convenience and the transfer cost can be stored in advance in the transportation service plan information 1000 of FIG. 9.
  • the utility value calculation unit 1544 defines the traffic congestion information 4000 stored in the storage unit 157 for a link whose transportation means is road traffic among links included in the movement route extracted by the movement route calculation unit 1543.
  • the link evaluation index is calculated based on the required time and the congestion level.
  • the utility value calculation unit 1544 calculates the utility value of the movement route based on the calculated evaluation index of each link (S206).
  • the utility value for each moving route can be calculated as follows, for example, using the required time and moving cost when using the moving route. As apparent from these equations, the utility value Ui calculated for the moving route i becomes smaller as the moving time for the moving route i becomes longer and as the moving cost increases. In other words, the value of the utility value Ui increases as the travel route that the user may want to select in consideration of convenience.
  • the degree of congestion by the congestion prediction device 130 and the degree of congestion by the congestion prediction device 140 can be added to the movement cost and incorporated in the evaluation by using a function that converts each into an expense.
  • the sharing moving number calculation unit 1545 calculates the sharing of the number of moving users using each moving route (S207).
  • the sharing of the number of mobiles can be calculated using, for example, a multinomial logit model in which selection probabilities are calculated based on utility values as follows. That is, the sharing of the number of moving persons for a plurality of moving routes is proportionally distributed according to the utility value Ui.
  • the movement path calculation unit 1543 proceeds to the process of S208.
  • the prediction device cooperation unit 155 aggregates the number of mobile persons on each movement route with respect to each movement demand calculated by the sharing mobile number calculation unit 1545 for each time zone and transportation means (S208).
  • the prediction device linkage unit 155 transmits the number of mobile persons collected in S208 to the congestion prediction device 130 or the traffic congestion prediction device 140 for the corresponding transportation means, and receives the prediction results calculated in each (S209).
  • the calculation convergence calculation unit 156 determines whether the calculation has converged based on the congestion degree and the congestion degree received by the prediction device cooperation unit 155 (S210).
  • the degree of congestion / congestion degree set in advance and the degree of congestion / congestion degree acquired this time are respectively compared as the attribute of the movement route.
  • the degree of congestion and congestion acquired last time are compared with the degree of congestion acquired and degree of congestion acquired this time, respectively.
  • the determination as to whether the calculation has converged can be made, for example, according to the following criteria. Determination method 1: When the difference between the congestion degree and the congestion degree becomes equal to or less than a predetermined threshold value, it is determined that the calculation is convergent.
  • Judgment method 2 When the difference between the number of sharing mobile persons of each moving route or the sharing ratio of the total number of mobile persons becomes equal to or less than a predetermined threshold value, it is determined as calculation convergence.
  • the determination of the calculation convergence is not limited to the above method, and among the plurality of movement routes, the difference, such as the number of sharing movement persons, is less than or equal to a predetermined value for the main movement route having the largest number of sharing movement persons. It is possible to adopt an appropriate determination method such as assuming that the case has converged.
  • the calculation convergence calculation unit 156 returns to S203, and repeatedly executes the processing of S204 to S207 for each movement demand.
  • the calculation convergence calculation unit 156 calculates the number of persons on each movement route for each movement demand calculated by the number of allocated movement persons calculation unit 1545 in S208 as a time zone.
  • Information obtained by aggregating each means of transportation is presented as traffic demand forecast information to the user through the output unit 152, the output unit 162 of the passenger terminal device 160, the output unit 113 of the transportation planning device 110, etc., and the processing is ended.
  • a transportation company such as a railway company, a route bus company, or a taxi company can receive traffic demand forecast information as data from the traffic demand forecasting device 150, and can also use it for transportation plan planning at each company.
  • FIG. 15 shows a display example of traffic demand forecast information.
  • data such as the number of sharing people for each moving route, sharing rate, congestion degree, congestion degree, required time, utility value, etc. may be represented numerically as in the example of FIG. And may be graphically displayed on a network model as shown in FIG.
  • the expression of increasing the width of the link is adopted as the number of shared moving persons increases in the moving route so that the amount of traffic demand can be recognized at a glance.
  • the traffic demand prediction apparatus 150 of the first embodiment described above it is possible to easily provide timely use of traffic demand prediction information for the public transport organization and road traffic in the prediction target area.
  • a business operator such as a public transportation organization can adjust the on-demand transportation capacity using the provided traffic demand forecast information, and can improve the convenience of the user.
  • each passenger can grasp the concentration of the mover in the moving route and the like in a timely manner, it becomes possible to select an appropriate moving route from the viewpoint of arrival time, comfort and the like.
  • a traffic demand prediction apparatus 150 according to a second embodiment of the present invention will be described.
  • a configuration example has been shown in which the number of mobile persons assigned to each transportation means is calculated, and then the device is cooperated with the congestion / congestion prediction device for each transportation means.
  • a configuration example for accelerating the convergence of calculation with respect to the traffic demand prediction process of the first embodiment will be described.
  • the same reference numerals as in the first embodiment denote the same parts in the second embodiment.
  • FIG. 17 is a diagram showing a configuration example of the traffic demand prediction apparatus 150 in the second embodiment. As shown in FIG. 17, in the traffic demand prediction apparatus 150 of the present embodiment, a route fixing unit 1546 and a threshold changing unit 1547 are added in the movement distribution calculating unit 154.
  • the route fixing unit 1546 has a function of fixing the movement routes for which the difference is reduced to some extent in the comparison of the calculation results so that the number of shared movers does not change thereafter.
  • the threshold changing unit 1547 changes the threshold used in the route fixing unit 1546 so that the calculation converges in a situation where the calculation can not be expected to converge within a practical range in terms of the required time for calculation etc. Have the ability to
  • FIG. 18 is a diagram showing an example of a processing flow of traffic demand prediction processing by the traffic demand prediction apparatus 150 of the present embodiment, which corresponds to FIG. 14 of the first embodiment.
  • the processing steps of S201 to S212 are the same as in the first embodiment.
  • the second embodiment is different from the first embodiment in the processing when it is determined in S211 that the calculation has not converged.
  • the calculation convergence determination unit 156 determines whether the number of calculations is less than the specified value at that time (S213), and is less than the specified value. When it is determined, S214 is executed (S213, Yes), and when it is determined that it is the specified value or more, S215 is executed (S213, No).
  • step S214 the route fixing unit 1546 determines that the difference between the calculation convergence determination value calculated by the calculation convergence determination unit 156 and the previous time between the nodes or the difference between the number of shared movers and the previous time is less than the threshold. For the movement demand or both, fix the number of shared movers not to change. The result of fixing the number of sharing mobile persons is presented to the user via the output unit 152 together with the network model created in S201, as described later.
  • the threshold value changing unit 1547 repeats the calculation a fixed number of times (prescribed value) or more, the node between the nodes in which the difference between the calculation convergence determination value calculated by the calculation convergence determination unit 156 and the previous one continues to be a predetermined value or more Alternatively, an operation is performed to increase the threshold value used in the calculation convergence determination unit 156 with respect to the movement demand in which the difference between the number of sharing mobile persons and the previous time continues to be equal to or greater than the threshold value.
  • the threshold used for the determination in this case is presented to the user via the output unit 152 together with the network model created in S201, as described later.
  • FIG. 19 shows an example of a screen displaying inter-node or mobile demand (corresponding to a mobile) fixed by the route fixing unit 1546 and a threshold used for determining between fixed nodes or mobile demand.
  • Reference numeral 901 denotes a screen frame
  • reference numeral 902 denotes a first display area displaying the network model created in S201
  • Reference numeral 903 denotes a second display area for displaying a graph representing the transition of the determination value of calculation convergence for the link selected by the user among the links set in the network model displayed in the first display area 902. is there.
  • a fixed section or movement demand and a non-fixed section or movement demand are displayed so as to be distinguishable.
  • a fixed section or a symbol L indicating that a movement demand is fixed as a dashed-dotted line a section that is not fixed or the movement demand is displayed as a solid line.
  • Reference numeral 904 represents the “current value / fixed target threshold value” for the determination value of calculation convergence of each link, and in the example of FIG. 19, the threshold value for the link connecting point A and point E directly with road traffic It shows that 11 calculations have been performed for 36.
  • the vertical axis 905 represents the determination value used in the convergence determination of the calculation in S 211
  • the horizontal axis 906 represents the number of calculations.
  • Reference numeral 907 is a curve representing the transition of the determination value of the calculation convergence for each number of calculations.
  • Reference numeral 908 represents a threshold value for determining whether to fix the displayed section.
  • the user of the traffic demand prediction apparatus 150 can be configured to be able to change the threshold that is the determination value of the calculation convergence via the screen and the input unit 151 shown in FIG. 19.
  • the threshold that is the determination value of the calculation convergence via the screen and the input unit 151 shown in FIG. 19.
  • the graph concerning the corresponding link in the second display area 903 is clicked by clicking the corresponding link in the first display area 902.
  • other methods may be used, such as displaying an input field where the value of the threshold 908 can be directly specified.
  • the traffic demand forecasting can be made in a timely manner taking into consideration the temporal demand fluctuation of each of the plurality of transportation means constituting the travel route. It can be done.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Automation & Control Theory (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)
PCT/JP2018/018595 2017-06-28 2018-05-14 交通需要予測装置、及び交通需要予測方法 Ceased WO2019003672A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
SG11201907852SA SG11201907852SA (en) 2017-06-28 2018-05-14 Traffic demand prediction device and traffic demand prediction method
EP18823362.1A EP3572991A4 (en) 2017-06-28 2018-05-14 PUBLIC TRANSPORTATION REQUEST DEVICE AND PUBLIC TRANSPORTATION REQUEST METHOD

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017125896A JP6895325B2 (ja) 2017-06-28 2017-06-28 交通需要予測装置、交通需要予測方法、及び交通需要予測プログラム
JP2017-125896 2017-06-28

Publications (1)

Publication Number Publication Date
WO2019003672A1 true WO2019003672A1 (ja) 2019-01-03

Family

ID=64742817

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/018595 Ceased WO2019003672A1 (ja) 2017-06-28 2018-05-14 交通需要予測装置、及び交通需要予測方法

Country Status (4)

Country Link
EP (1) EP3572991A4 (enExample)
JP (1) JP6895325B2 (enExample)
SG (1) SG11201907852SA (enExample)
WO (1) WO2019003672A1 (enExample)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110969299A (zh) * 2019-11-29 2020-04-07 浙江大搜车软件技术有限公司 交通路线生成的方法、装置、计算机设备及存储介质
CN111143769A (zh) * 2019-12-09 2020-05-12 深圳市市政设计研究院有限公司 一种基于大数据的出行方式分担率的预测方法和预测装置
CN111340543A (zh) * 2020-02-25 2020-06-26 上海大学 一种基于注意力机制的细粒度打车需求预测方法
WO2022044375A1 (ja) * 2020-08-25 2022-03-03 株式会社日立製作所 オペレーション連携装置およびオペレーション連携支援方法
JP2023086167A (ja) * 2021-12-10 2023-06-22 株式会社MaaS Tech Japan プログラム及び情報処理装置
JP7732124B1 (ja) * 2025-06-03 2025-09-01 株式会社Ye Digital 情報提供装置および情報提供方法

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111341099B (zh) * 2020-02-27 2022-05-10 阿里巴巴集团控股有限公司 一种数据处理方法、装置及电子设备
CN111859193B (zh) * 2020-07-31 2021-08-31 爱易成技术(天津)有限公司 行车时刻表的生成方法、装置及电子设备
JP7478395B2 (ja) * 2021-02-02 2024-05-07 日本電信電話株式会社 軌道算出装置、軌道算出方法およびプログラム
CN112926806A (zh) * 2021-04-12 2021-06-08 东风小康汽车有限公司重庆分公司 一种目的地的预测方法、装置、存储介质和车机
JP7500504B2 (ja) * 2021-06-10 2024-06-17 株式会社東芝 情報処理装置、情報処理方法およびプログラム
KR102702133B1 (ko) * 2021-12-09 2024-09-04 울산과학기술원 시각화를 통해 버스 수요를 분석하기 위한 방법 및 장치
JP7636632B2 (ja) * 2022-03-17 2025-02-26 株式会社日立製作所 交通サービス連携支援装置、交通サービス連携支援方法、及び交通サービス連携支援システム

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001124569A (ja) 1999-08-17 2001-05-11 Toyota Motor Corp 経路案内装置及び媒体
JP2014115956A (ja) * 2012-12-12 2014-06-26 Toyota Motor Corp 交通計画作成支援装置、交通計画作成支援方法
WO2014121329A1 (en) * 2013-02-06 2014-08-14 University Of Technology, Sydney Computer-implemented crowd influencing system
WO2014199503A1 (ja) * 2013-06-14 2014-12-18 株式会社 日立製作所 交通需要制御装置
JP2016080665A (ja) * 2014-10-22 2016-05-16 株式会社ナビタイムジャパン 情報処理システム、情報処理プログラム、情報処理装置、および情報処理方法
JP2017125896A (ja) 2016-01-12 2017-07-20 株式会社リコー 駆動伝達装置および画像形成装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003168193A (ja) * 2001-11-29 2003-06-13 Canon Inc 物流及び交通システム
JP4385865B2 (ja) * 2004-06-25 2009-12-16 株式会社日立製作所 交通広告運用管理システム
JP5325241B2 (ja) * 2011-01-14 2013-10-23 三菱重工業株式会社 交通流シミュレーション装置、交通流シミュレーションプログラム、及び交通流シミュレーション方法
CN105096584A (zh) * 2014-05-06 2015-11-25 中兴通讯股份有限公司 一种交通决策支持方法、装置及系统
JP6493831B2 (ja) * 2015-02-26 2019-04-03 三菱重工機械システム株式会社 交通流制御装置、端末装置、交通流制御システム、交通流制御方法及びプログラム
JP6632247B2 (ja) * 2015-08-06 2020-01-22 三菱電機株式会社 案内システム及び案内方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001124569A (ja) 1999-08-17 2001-05-11 Toyota Motor Corp 経路案内装置及び媒体
JP2014115956A (ja) * 2012-12-12 2014-06-26 Toyota Motor Corp 交通計画作成支援装置、交通計画作成支援方法
WO2014121329A1 (en) * 2013-02-06 2014-08-14 University Of Technology, Sydney Computer-implemented crowd influencing system
WO2014199503A1 (ja) * 2013-06-14 2014-12-18 株式会社 日立製作所 交通需要制御装置
JP2016080665A (ja) * 2014-10-22 2016-05-16 株式会社ナビタイムジャパン 情報処理システム、情報処理プログラム、情報処理装置、および情報処理方法
JP2017125896A (ja) 2016-01-12 2017-07-20 株式会社リコー 駆動伝達装置および画像形成装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3572991A4

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110969299A (zh) * 2019-11-29 2020-04-07 浙江大搜车软件技术有限公司 交通路线生成的方法、装置、计算机设备及存储介质
CN111143769A (zh) * 2019-12-09 2020-05-12 深圳市市政设计研究院有限公司 一种基于大数据的出行方式分担率的预测方法和预测装置
CN111143769B (zh) * 2019-12-09 2023-05-09 深圳市市政设计研究院有限公司 一种基于大数据的出行方式分担率的预测方法和预测装置
CN111340543A (zh) * 2020-02-25 2020-06-26 上海大学 一种基于注意力机制的细粒度打车需求预测方法
CN111340543B (zh) * 2020-02-25 2024-03-22 上海大学 一种基于注意力机制的细粒度打车需求预测方法
WO2022044375A1 (ja) * 2020-08-25 2022-03-03 株式会社日立製作所 オペレーション連携装置およびオペレーション連携支援方法
JP2022037515A (ja) * 2020-08-25 2022-03-09 株式会社日立製作所 オペレーション連携装置およびオペレーション連携支援方法
JP7404190B2 (ja) 2020-08-25 2023-12-25 株式会社日立製作所 オペレーション連携装置およびオペレーション連携支援方法
JP2023086167A (ja) * 2021-12-10 2023-06-22 株式会社MaaS Tech Japan プログラム及び情報処理装置
JP7374509B2 (ja) 2021-12-10 2023-11-07 株式会社MaaS Tech Japan プログラム及び情報処理装置
JP7732124B1 (ja) * 2025-06-03 2025-09-01 株式会社Ye Digital 情報提供装置および情報提供方法

Also Published As

Publication number Publication date
JP6895325B2 (ja) 2021-06-30
SG11201907852SA (en) 2019-09-27
EP3572991A4 (en) 2020-07-15
EP3572991A1 (en) 2019-11-27
JP2019008689A (ja) 2019-01-17

Similar Documents

Publication Publication Date Title
JP6895325B2 (ja) 交通需要予測装置、交通需要予測方法、及び交通需要予測プログラム
Gurumurthy et al. Analyzing the dynamic ride-sharing potential for shared autonomous vehicle fleets using cellphone data from Orlando, Florida
Gu et al. Plan-based flexible bus bridging operation strategy
Nuzzolo et al. A mesoscopic transit assignment model including real-time predictive information on crowding
Niu et al. Optimizing urban rail timetable under time-dependent demand and oversaturated conditions
JP5902607B2 (ja) 旅行時間情報提供装置、旅行時間情報提供方法
Niu et al. Demand-driven train schedule synchronization for high-speed rail lines
CN109033718A (zh) 一种城市轨道交通线路失效的动态应急疏散方法
KR102696587B1 (ko) 운송 관련 서비스에 대한 요청을 관리하기 위한 통신 서버 장치, 방법, 및 통신 시스템
CN107358309A (zh) 基于微信公众号的轨道交通乘客出行信息服务系统
KR102813022B1 (ko) 수요 응답형 버스의 경로를 생성하기 위한 방법 및 장치
Li et al. Using smart card data trimmed by train schedule to analyze metro passenger route choice with synchronous clustering
US10402755B2 (en) Transportation service information providing apparatus, and transportation service information providing method
Li et al. A smart path recommendation method for metro systems with passenger preferences
JP6999519B2 (ja) 輸送力調整装置、輸送力調整システムおよび輸送力調整方法
Hua et al. Effect of information contagion during train service disruption for an integrated rail-bus transit system
Wu et al. A coordinated bus bridging and metro short turning model in response to urban metro disruptions
Yuan et al. Dynamic integration of heterogeneous transportation modes under disruptive events
Mátrai et al. Route planning based on urban mobility management
Xie et al. Estimating distributions of walking speed, walking distance, and waiting time with automated fare collection data for rail transit
JP2017154536A (ja) 乗務員運用管理システムおよび乗務員運用管理方法
CN116562574A (zh) 城际定制客运的协同优化方法、装置、设备和存储介质
Rakow et al. Mobility as a service enabled by the autonomous driving
JP7449192B2 (ja) ダイヤ情報管理システム、ダイヤ情報管理方法および運行案内システム
Wang et al. Integrated design and optimization of customized bus travel services for urban commuting

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18823362

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2018823362

Country of ref document: EP

Effective date: 20190822

NENP Non-entry into the national phase

Ref country code: DE