Passenger stream congestion prediction device, passenger stream congestion prediction method, and passenger stream congestion prediction program

Abstract

To provide a passenger stream congestion prediction device, a passenger stream congestion prediction method, and a passenger stream congestion prediction program capable of improving the accuracy of the prediction result of a passenger stream in railroad transportation.SOLUTION: A path search unit 13 extracts a path candidate on the basis of at least one of entrance time at an entrance station through which passengers enter and exit time at an exit station through which the passengers exit in ticket gate passage data D1 acquired from an automatic ticket gate 5 and diagram data D2 of a current train. A train allocation unit 14 calculates an allocation index on the basis of the ticket gate passage data D1 and the diagram data D2 of the current train, and allocates one passenger to a plurality of path candidates in accordance with the allocation index. The train allocation unit 14 allocates, when a plurality of path candidates include a plurality of transfer path candidates via transfer stations, one passenger to one or more transfer path candidates extracted from among the transfer path candidates in accordance with a prescribed condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a passenger flow congestion prediction device, a passenger flow congestion prediction method, and a passenger flow congestion prediction program for predicting passenger flow in rail transport. [Background technology]

[0002] Congestion in railway stations and on trains can have a significant impact on train operations, such as increasing boarding and alighting times and causing delays to train arrivals and departures. Therefore, in order to avoid congestion in railway transportation, several methods have been proposed for predicting passenger flow using statistical methods based on information such as data obtained from automatic ticket gates and train schedule data.

[0003] For example, Patent Document 1 discloses a passenger flow simulation device that, in a route search network used to search for passenger train transfer routes, distinguishes arrival / departure nodes into whether passengers are seated or standing, changes the cost of the seating arc according to the corresponding seating probability, and changes the inter-station arc according to the congestion rate between stations corresponding to each seated / standing passenger; in train boarding and alighting control, first seats standing passengers in vacant seats created by seated passengers alighting, classifies stranded passengers into priority / general stranded passengers according to the waiting time (stay time) at the station, and allows stranded passengers to board so that priority stranded passengers become seated passengers first. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-229459 Summary of the Invention [Problem to be solved by the invention]

[0005] Here, for example, if there are multiple transfer stations between the entrance station and the exit station, one possible method is to assign passengers to one route candidate that passes through the transfer station with the shortest transfer time. However, a method that uniformly determines transfer stations can deviate from the actual usage of transfer stations by passengers, resulting in a problem of reduced accuracy in congestion prediction.

[0006] An object of the present invention is to provide a passenger flow congestion prediction device, a passenger flow congestion prediction method, and a passenger flow congestion prediction program that can improve the accuracy of prediction results of passenger flow in rail transport. [Means for solving the problem]

[0007] A passenger flow congestion prediction device according to one aspect of the present invention is a passenger flow congestion prediction device that predicts passenger flow in rail transport. The passenger flow congestion prediction device includes a route search unit and a train allocation unit. The route search unit extracts route candidates based on at least one of the entry time at the entry station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entry time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and current train schedule data including the departure time and arrival time of a current train. The train allocation unit calculates an allocation index based on the ticket gate passage data and the current train schedule data, and allocates one passenger to multiple route candidates according to the allocation index. In addition, when the multiple route candidates include multiple transfer route candidates that pass through a transfer station, the train allocation unit allocates one passenger to one or more transfer route candidates extracted from the multiple transfer route candidates according to specified conditions.

[0008] According to another aspect of the present invention, there is provided a passenger flow congestion prediction method for predicting passenger flow in rail transport, the passenger flow congestion prediction method being executed by one or more processors to: extract route candidates based on ticket gate passage data, the ticket gate passage data including the entry time at the entry station where the passenger entered and the exit time at the exit station where the passenger exited, for each passenger, acquired from an automatic ticket gate installed at the railway station; and current train timetable data including the departure time and arrival time of the current train; calculate an allocation index based on the ticket gate passage data and the current train timetable data, and assign each passenger to multiple route candidates according to the allocation index; and, when the multiple route candidates include multiple transfer route candidates that pass through transfer stations, assign each passenger to one or more of the multiple transfer route candidates extracted according to predetermined conditions from the multiple transfer route candidates.

[0009] According to another aspect of the present invention, there is provided a passenger flow congestion prediction program for predicting passenger flow in rail transport. The passenger flow congestion prediction program causes one or more processors to execute the following steps: extracting route candidates based on at least one of the entry time at the entry station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entry time at the railway station and the exit time for each passenger acquired from an automatic ticket gate installed at the railway station, and current train timetable data including the departure time and arrival time of the current train; calculating an allocation index based on the ticket gate passage data and the current train timetable data, and allocating each passenger to multiple route candidates according to the allocation index; and, when the multiple route candidates include multiple transfer route candidates that pass through a transfer station, allocating each passenger to one or more of the multiple transfer route candidates extracted according to a predetermined condition from the multiple transfer route candidates. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide a passenger flow congestion prediction device, a passenger flow congestion prediction method, and a passenger flow congestion prediction program that can improve the accuracy of prediction results of passenger flow in rail transport. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing the configuration of a passenger flow congestion prediction device according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a diagram showing an example of a route candidate taken by one passenger assigned by a train assignment unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 3] FIG. 3 is a diagram showing an example of route candidates that have an appropriate time sequence and minimize the number of transfers, extracted by a route search unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 4] Figure 4 (a) to (d) are diagrams showing an example of the congestion level, number of people on the train, number of people entering and exiting, and number of people transferring for each train estimated by the first congestion level estimation unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 5] FIG. 5 is a diagram showing an example of route candidates extracted by a route search unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention when the time sequence is inappropriate. [Figure 6] FIG. 6 is a diagram showing an example in which one passenger is assigned to multiple route candidates based on an assignment index calculated by a train assignment unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 7] FIG. 7 is a diagram showing an example of the numerical relationship of allocation indices calculated by the train allocation unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 8] FIG. 8 is a schematic diagram showing how one passenger gets on and off along the route candidates in FIG. [Figure 9]FIG. 9 is a diagram showing an example of the number of people remaining for each train estimated by the first congestion degree estimation unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing an example of the number of people remaining within each railway station by time period estimated by the second congestion degree estimation unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 11] FIG. 11 is a diagram showing an example of aggregated data of the number of people remaining within each railway station by time period, estimated by the second congestion degree estimation unit included in the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 12] FIG. 12 is a flowchart showing the flow of processing for allocating one passenger to a plurality of route candidates, which is performed by the passenger flow congestion prediction device according to the first embodiment of the present invention. [Figure 13] FIG. 13 is a block diagram showing the configuration of a passenger flow congestion prediction device according to the second embodiment of the present invention. [Figure 14] FIG. 14 is a diagram showing an example of route candidates extracted by a route search unit included in the passenger flow congestion prediction device according to the second embodiment of the present invention. [Figure 15] FIG. 15 is a flowchart showing the flow of processing for allocating one passenger to a plurality of route candidates, which is performed by the passenger flow congestion prediction device according to the second embodiment of the present invention. [Figure 16] FIG. 16 is a block diagram showing the configuration of a passenger flow congestion prediction device according to the third embodiment of the present invention. [Figure 17] FIG. 17 is a flowchart showing the flow of the linking process performed by the passenger flow congestion prediction device according to the third embodiment of the present invention. [Figure 18] FIG. 18 is a diagram showing a specific example of the linking process performed by the passenger flow congestion prediction device according to the third embodiment of the present invention. [Figure 19] FIG. 19 is a diagram showing a specific example of the linking process performed by the passenger flow congestion prediction device according to the third embodiment of the present invention. [Figure 20]FIG. 20 is a diagram showing a specific example of route candidates according to the fourth embodiment of the present invention. [Figure 21] FIG. 21 is a diagram showing a specific example of route candidates according to the fourth embodiment of the present invention. [Figure 22] FIG. 22 is a diagram showing an example of setting weights according to a specific example 1 of the fourth embodiment of the present invention. [Figure 23] FIG. 23 is a diagram showing an example of setting weights according to specific example 2 of the fourth embodiment of the present invention. [Figure 24] FIG. 24 is a diagram showing an example of setting weights according to a specific example 3 of the fourth embodiment of the present invention. [Figure 25] FIG. 25 is a diagram showing an example of setting weights according to a specific example 4 of the fourth embodiment of the present invention. [Figure 26] FIG. 26 is a diagram showing a specific example of the allocation process according to the fourth embodiment of the present invention. [Figure 27] FIG. 27 is a diagram showing a specific example of the allocation process according to the fourth embodiment of the present invention. [Figure 28] FIG. 28 is a diagram showing a specific example of the allocation process according to the fourth embodiment of the present invention. [Figure 29] FIG. 29 is a diagram showing a specific example of the allocation process according to the fourth embodiment of the present invention. [Figure 30] FIG. 30 is a flowchart showing the flow of a process of allocating one passenger to a plurality of transfer route candidates, which is performed by the passenger flow congestion prediction device according to the fourth embodiment of the present invention. [Figure 31] FIG. 31 is a diagram showing a specific example of the allocation process according to the fourth embodiment of the present invention. [Figure 32] FIG. 32 is a diagram showing a specific example of the allocation process according to the fourth embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings to help understand the present invention. Note that the following embodiments are examples that embody the present invention and do not limit the technical scope of the present invention.

[0013] A passenger flow congestion prediction device and a passenger flow congestion prediction method according to one embodiment of the present invention will be described below with reference to FIGS.

[0014] In the present embodiment, more detailed explanation than necessary may be omitted. For example, detailed explanation of well-known matters or redundant explanation of substantially the same configuration may be omitted. This is to avoid unnecessary redundancy in the following explanation and to facilitate understanding by those skilled in the art.

[0015] Furthermore, the applicant provides the accompanying drawings and the following description to enable those skilled in the art to fully understand the present invention, and they are not intended to limit the subject matter described in the claims.

[0016] [First embodiment] The passenger flow congestion prediction device 10 of this embodiment predicts passenger flow by allocating one passenger to multiple candidate routes using an allocation index calculated based on the passenger's entry time at the entry station and the exit time at the exit station contained in the ticket gate passage data D1, and the train's departure time at the entry station and the arrival time at the exit station contained in the current train timetable data D2.

[0017] 1, the passenger flow congestion prediction device 10 is connected to an input device 2, a display device 3, and a data server 4. The passenger flow congestion prediction device 10 may be an information processing device such as a server (such as a cloud server) or a personal computer. The passenger flow congestion prediction device 10 may also be configured to include the input device 2, the display device 3, and the data server 4.

[0018] The ticket gate passage data D1 is passenger boarding and alighting data obtained from an automatic ticket gate 5 installed at a railway station, and is recorded, for example, when a passenger passes through the automatic ticket gate 5 shown in Fig. 1. As shown in Fig. 2, the ticket gate passage data D1 records the passenger's medium type (e.g., IC card, magnetic ticket, etc.), entrance station, entrance time at the entrance station, exit station, exit time at the exit station, etc.

[0019] Here, the ticket gate passage data D1 is a collection of multiple trip data. Each trip data is a set of data including an entry record and a corresponding exit record. The entry record includes the entry station and the time when the train passed through the automatic ticket gate 5 installed at the entry station. The exit record includes the exit station and the time when the train passed through the automatic ticket gate 5 installed at the exit station.

[0020] The entry record and exit record are acquired by the automatic ticket gate 5 at different locations and at different times. When acquired by the automatic ticket gate 5, the entry record and exit record include ticket ID information assigned to each ticket used to pass through (enter or exit) the automatic ticket gate 5. The collected entry records and exit records are stored on the data server 4 in a state where they are linked to each other via the ticket ID information to form trip data.

[0021] Trip data identifies a single rail trip, from entry to exit, by showing what type of ticket a single passenger used, when and at which station they entered, and when and from which station they exited. A single trip corresponds one-to-one with a single "passenger" as the subject of that trip.

[0022] The timetable data D2 is data that represents the operating status of trains on tracks managed by a railway company. For example, as shown in Fig. 3, the timetable data D2 represents each departure time T1 of a train at a departure station and each arrival time T2 of the train at an arrival station, as well as four route candidates, consisting of solid lines and dotted lines, between the departure times T1 and the arrival times T2.

[0023] The input device 2 is, for example, a keyboard, mouse, touch panel, etc., and receives various instruction inputs as well as inputs of timetable data D2, OD data D3, station data D4, and route data D5 to be stored in the passenger flow congestion prediction device 10.

[0024] The OD data D3 is data that represents the number of passengers for each combination of the departure station of the train where passengers using the railway board and the arrival station of the train where the passengers disembark. For example, as shown in Figures 4(a) to 4(d), the number of passengers for a certain train when combined with XXX station and YYY station is 560.

[0025] Here, Figure 4(a) shows the degree of congestion for each train (six levels from 1 to 6), Figure 4(b) shows the number of passengers on board the train, Figure 4(c) shows the number of passengers entering and exiting the train at the entry and exit stations, and Figure 4(d) shows the number of passengers transferring at transfer stations.

[0026] The congestion degree for each train shown in FIG. 4(a) will be explained in detail later in the first congestion degree estimation unit 15.

[0027] The station data D4 is information about all stations included in the lines managed by the railway company, such as data representing the names of departure and arrival stations. The station data D4 may also include information such as the time required for transfers at transfer stations.

[0028] The route data D5 is data on all routes managed by a railway company, and is data representing, for example, the name of the railway company, a route map, and the name of the route.

[0029] In addition, various data such as timetable data D2, OD data D3, station data D4, route data D5, etc. input from the input device 2 may be transmitted to the data acquisition unit 12 without being stored in the memory unit 11 of the passenger flow congestion prediction device 10.

[0030] The display device 3 is, for example, a PC (Personal Computer) owned by a railway company, and displays the results (prediction results) of assigning one passenger using a railway assigned by the passenger flow congestion prediction device 10 to multiple route candidates, as well as the congestion status for each train and each station estimated based on the assignment results.

[0031] The data server 4 stores ticket gate passage data D1 acquired from magnetic tickets, electronic tickets, etc. held by passengers who pass through automatic ticket gates at railway stations.

[0032] One or more automatic ticket gates 5 are installed at train stations, and when a passenger passes through, the gates write information to an IC (integrated circuit) card or the like carried by the passenger, or read the information to process the fare.

[0033] As shown in FIG. 1 , the passenger flow congestion prediction device 10 of this embodiment includes a memory unit 11, a data acquisition unit 12, a route search unit 13, a train allocation unit 14, a first congestion level estimation unit 15, a second congestion level estimation unit 16, and an output unit 17. The passenger flow congestion prediction device 10 is not limited to a single computer, but may be a computer system in which multiple computers operate in cooperation, or may be configured as a cloud server. Various processes executed by the passenger flow congestion prediction device 10 may be executed in a distributed manner by one or multiple processors.

[0034] The data acquisition unit 12, the route search unit 13, the train allocation unit 14, the first congestion level estimation unit 15, the second congestion level estimation unit 16, and the output unit 17 constitute a control unit 20, which has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that executes various types of arithmetic processing. The ROM is a non-volatile storage unit that pre-stores control programs such as a BIOS and an OS for causing the CPU to execute various types of arithmetic processing. The RAM is a volatile or non-volatile storage unit that stores various types of information and is used as a temporary storage memory (work area) for various types of processing executed by the CPU. The control unit 20 controls the passenger flow congestion prediction device 10 by having the CPU execute various control programs pre-stored in the ROM or the storage unit 11.

[0035] The storage unit 11 is a non-volatile storage unit such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory that stores various types of information. The storage unit 11 also stores a control program for causing the control unit 20 to execute various processes (see FIG. 12 ). For example, the control program is non-temporarily recorded on a computer-readable recording medium such as a CD or a DVD, and is read by a reading device (not shown) such as a CD drive or a DVD drive provided in the passenger flow congestion prediction device 10 and stored in the storage unit 11.

[0036] For example, the storage unit 11 stores various data input from the input device 2, such as timetable data D2, OD data D3, station data D4, and route data D5.

[0037] As a result, for example, by using various data stored in the memory unit 11 provided within the passenger flow congestion prediction device 10, the accuracy of the prediction results for passenger flow in rail transport can be improved compared to the conventional case.

[0038] In addition, if, for example, a train schedule is changed and the departure and arrival times included in the schedule data D2 are changed, the user of the passenger flow congestion prediction device 10 may add or change new schedule data including the changed departure and arrival times to the memory unit 11 via the input device 2.

[0039] As a result, for example, the route search unit 13 extracts multiple route candidates after the change in the timetable data D2 in response to a change, and the train allocation unit 14 can allocate one passenger using the train to multiple appropriate route candidates.

[0040] Furthermore, for example, when a new station is installed and a new combination of stations included in the OD data D3, station data D4, and route data D5 occurs, the user of the passenger flow congestion prediction device 10 may add or change the list of the new station combination in the memory unit 11 via the input device 2.

[0041] As a result, for example, the route search unit 13 extracts multiple new route candidates using the OD data D3, station data D4, and line data D5 that have been newly added in response to changes in the surrounding environment, such as the establishment of a new station, and the train allocation unit 14 can allocate one passenger to multiple appropriate route candidates.

[0042] The data acquisition unit 12 acquires the ticket gate passage data D1 transmitted to the data acquisition unit 12 from the data server 4.

[0043] Furthermore, the data acquiring unit 12 acquires the timetable data D2, the OD data D3, the station data D4, and the line data D5 stored in the memory unit 11. Alternatively, the data acquiring unit 12 may directly acquire the timetable data D2, the OD data D3, the station data D4, and the line data D5 that are input from the input device 2 and transmitted to the data acquiring unit 12 without being stored in the memory unit 11.

[0044] As a result, the route search unit 13 extracts a plurality of route candidates acquired by the data acquisition unit 12, and the train allocation unit 14 can allocate one passenger to a plurality of appropriate route candidates.

[0045] The route search unit 13 extracts multiple route candidates with appropriate time sequence based on the entry and exit times of passengers using the railway contained in the ticket gate passage data D1 acquired by the data acquisition unit 12 and the departure and arrival times of trains contained in the timetable data D2 of current trains.

[0046] Here, a route candidate with an appropriate time sequence is one in which the departure time at the entrance station is the same as or later than the entrance time at the entrance station, the arrival time at the exit station is later than the departure time, and the exit time is the same as or later than the arrival time at the exit station.

[0047] In this embodiment, four route candidates are illustrated as shown in Fig. 3. For example, the first route candidate is a route candidate in which a passenger enters the entrance station at an entrance time of 09:10, departs from the entrance station at a departure time T1 of 09:10, changes trains at a transfer station, arrives at the exit station at an arrival time T2 of 09:12, and departs from the exit station at an exit time of 09:16.

[0048] The second route candidate is a route candidate in which a passenger enters the entry station at 09:10, departs from the entry station at departure time T1 of 09:10, changes trains at the transfer station, arrives at the exit station at arrival time T2 of 09:13, and departs from the exit station at departure time of 09:16.

[0049] The third route candidate is a route candidate in which a passenger does not need to change trains, with the entry time at the entry station being 09:10, the departure time T1 from the entry station being 09:11, the arrival time T2 at the exit station being 09:15, and the departure time from the exit station being 09:16.

[0050] The fourth route candidate is a route candidate in which a passenger does not change trains, entering the entry station at 09:10, departing from the entry station at departure time T1 at 09:13, arriving at the exit station at arrival time T2 at 09:16, and leaving the exit station at departure time 09:16.

[0051] As a result, the route search unit 13 extracts a plurality of route candidates that have an appropriate time sequence, and the train allocation unit 14 can determine an appropriate allocation index.

[0052] The route search unit 13 extracts, from among a plurality of route candidates with appropriate time sequences, for example, a route candidate that minimizes the number of train changes required by a passenger between the entrance station and the exit station.

[0053] Here, the number of route candidates is considered to be small when the passenger is moving quickly from the entrance station to the exit station, and large when the passenger is moving slowly. Therefore, in order to extract appropriate route candidates, the route search unit 13 extracts route candidates with the minimum number of transfers.

[0054] Of the multiple route candidates shown in Figure 3, the third and fourth route candidates mentioned above have appropriate time sequences and are route candidates with the fewest number of transfers.

[0055] This allows the train allocation unit 14 to calculate an appropriate allocation index. Furthermore, the train allocation unit 14 can allocate one passenger to a plurality of appropriate route candidates based on the appropriate allocation index.

[0056] The route search unit 13 determines the departure times of a predetermined number of trains after the passenger's entry time as candidates for the departure time.

[0057] For example, as shown in Figure 3, when a passenger's entry time is 09:10, the possible departure times at the departure station are 09:10, which is the same time as the entry time, and the four trains immediately following it, 09:11, 09:12, 09:13, and 09:18.

[0058] This allows the train allocation unit 14 to allocate one passenger to multiple route candidates based on the entry time and the allocation index.

[0059] The route search unit 13 determines the arrival times of a predetermined number of trains before the departure time of the train as candidates for the arrival time.

[0060] For example, as shown in Figure 3, when a passenger's departure time is 09:16, the possible arrival times at the arrival station are 09:16, which is the same time as the departure time, and the four trains immediately preceding it, 09:15, 09:13, 09:12, and 09:08.

[0061] This allows the train allocation unit 14 to allocate one passenger to multiple route candidates based on the allocation index.

[0062] In addition, the route search unit 13 extracts multiple route candidates with inappropriate time relationships based on the entry and exit times of passengers using the railway contained in the ticket gate passage data D1 acquired by the data acquisition unit 12 and the departure and arrival times of trains contained in the timetable data D2 of current trains.

[0063] Here, route candidates with inappropriate time sequence are those that do not satisfy the conditions of a route candidate where the departure time at the entrance station is the same as or later than the entrance time at the entrance station, the arrival time at the exit station is later than the departure time, and the departure time is the same as or later than the arrival time at the exit station, and if the departure time is the same as or later than the entrance time, then a predetermined number of route candidates are extracted in order of the earliest train arrival time after the entrance time.

[0064] Five route candidates are illustrated in Figure 5. For example, the first route candidate is a route candidate in which a passenger enters the entrance station at 09:10, departs from the entrance station at 09:10 at departure time T1, changes trains at a transfer station, arrives at the exit station at 09:12 at arrival time T4, and departs from the exit station at 09:10.

[0065] The second route candidate is a route candidate in which the passenger enters the entry station at 09:10, departs from the entry station at departure time T1 of 09:10, changes trains at the transfer station, arrives at the exit station at arrival time T4 of 09:13, and departs from the exit station at departure time of 09:10.

[0066] The third route candidate is a route candidate in which the passenger enters the entry station at 09:10, departs from the entry station at departure time T1 at 09:11, changes trains at the transfer station, arrives at the exit station at arrival time T4 at 09:13, and departs from the exit station at departure time 09:10.

[0067] The fourth route candidate is a route candidate in which the passenger does not need to change trains, with the entry time at the entry station being 09:10, the departure time T1 at the entry station being 09:13, the arrival time T4 at the exit station being 09:15, and the departure time at the exit station being 09:10.

[0068] The fifth route candidate is a route candidate in which the passenger does not need to change trains, with the entry time at the entry station being 09:10, the departure time T1 at the entry station being 09:18, the arrival time T4 at the exit station being 09:16, and the departure time at the exit station being 09:10.

[0069] Note that the arrival time T3 at which the passenger arrives at the exit station is clearly earlier than the departure time T1 at which the passenger departs from the entrance station, and therefore may be excluded from the route candidates in this embodiment.

[0070] In this case, when one passenger is assigned to three route candidates, the first, second, and third route candidates mentioned above have an inappropriate time sequence, and are route candidates whose arrival time is earlier than the departure time.

[0071] As a result, even if the time is inappropriate due to a schedule disruption or the like, the route search unit 13 can extract route candidates, and the train allocation unit 14 can perform a predetermined calculation and allocate one passenger to multiple route candidates.

[0072] The train allocation unit 14 calculates an allocation index based on the sum of the time difference between the entry time and departure time and the time difference between the exit time and arrival time for the route candidates extracted by the route search unit 13. That is, the train allocation unit 14 allocates routes using a ratio according to the value of the following relational expression (1).

[0073] diff = (departure time - entry time) + (exit time - arrival time)...(1) Here, the allocation index is represented as "diff."

[0074] FIG. 6 shows two possible routes that a passenger can take from entering station X, which is the entrance station, to leaving station Y, which is the exit station.

[0075] The first route candidate is a route candidate in which one passenger enters the entry station, X station, at 9:10, boards a train departing from the entry station, X station, at 09:11, disembarks a train arriving at the exit station, Y station, at 09:15, and leaves the exit station, Y station, at 9:16.

[0076] Therefore, for the first route candidate, diff=2.

[0077] The second route candidate is one in which one passenger enters the entry station, X station, at 9:10, boards a train departing from the entry station, X station, at 09:13, disembarks a train arriving at the exit station, Y station, at 09:16, and exits the exit station, Y station, at 9:16.

[0078] Therefore, for the second route candidate, diff=3.

[0079] For example, when there are route candidates from route candidate i to route candidate N, the train allocation unit 14 adds up the reciprocals of diff from i to N using the following relational expression (2). In addition, for example, the train allocation unit 14 uses the calculated sum value to calculate (1 / diff i / sum) assign people.

[0080]

number

[0081] Therefore, in Figure 6, the first route candidate has diff=2, so 0.6 of one passenger is allocated. Furthermore, the second route candidate has diff=3, so 0.4 of one passenger is allocated.

[0082] The relational expression for calculating the allocation index is not limited to relational expression (1), and the train allocation unit 14 may reduce the allocation index by subtracting an arbitrary constant. Furthermore, since the calculation result may become a negative integer when an arbitrary constant is used for subtraction, the train allocation unit 14 may use a power in the relational expression to make the calculation result positive. Furthermore, the train allocation unit 14 may set the value of the allocation index to be greater than 0 using a MAX function that selects the largest value from multiple calculation results.

[0083] Furthermore, as shown in Figure 7, the number of people assigned to the route candidate with diff=2 is 1.5 times the number of people assigned to the route candidate with diff=3, as shown in the allocation results above. In other words, the probability that the passenger will select the route candidate with diff=2 is 1.5 times higher than the probability that the passenger will select the route candidate with diff=3. At the same time, if the passenger selects the route candidate with diff=3, the passenger will lose 1.5 times the time compared to when the passenger selects the route candidate with diff=2.

[0084] As a result, the train allocation unit 14 can allocate one passenger to multiple route candidates in units of decimal points less than 1 according to the calculated allocation index. Also, a user of the passenger flow congestion prediction device 10 can determine which of the multiple route candidates allocated based on the allocation index is more likely to be selected. Furthermore, a user of the passenger flow congestion prediction device 10 can determine how much time can be saved by comparing the multiple route candidates allocated based on the allocation index.

[0085] The first congestion degree estimation unit 15 estimates the congestion degree for each train based on the number of passengers using the railway inside the train on the route candidates assigned by the train assignment unit 14, the number of passengers entering at the entry station and the number of passengers exiting at the exit station, and the number of passengers who transferred.

[0086] 4(a) to 4(d) show an example of a method for calculating the congestion level for each train on a route candidate assigned based on an assignment index. Here, express train 000, which has a capacity of 800 people, arrives at XXX station, undergoes passenger transfers and other processes at XXX station, and then departs from XXX station. The number of passengers on train 000 arriving at XXX station is 512, the number of passengers departing from XXX station is 10, the number of passengers transferring from train 000 arriving at XXX station to another train is 21, the number of passengers entering XXX station is 39, and the number of passengers transferring from another train to train 000 departing from XXX station is 40.

[0087] Therefore, the first congestion level estimation unit 15 estimates, using the above numerical values, that the number of passengers on board train 000 departing from XXX station is 512-10-21+39+40=560 (people).

[0088] Furthermore, if the number of passengers on board train 000 arriving at XXX station is 512 and the number of passengers on board train 000 departing from XXX station is 560, the first congestion degree estimation unit 15 will estimate, for example, that the congestion degree of train 000 arriving at XXX station is 3 and the congestion degree of train 000 departing from XXX station is 4.

[0089] The congestion level for each train may be expressed using any numerical value, since it is an index showing the flow of passengers using the train during the period from when the train enters the station of entry to when the train exits the station of exit, which is difficult to predict from the ticket gate passage data D1 or the timetable data D2. For example, the congestion level is expressed as a scale of 1 to 6.

[0090] Figure 8 also shows the boarding and alighting process of one passenger traveling along the route candidates in Figure 2. Here, one passenger enters the entry station, XXX station, using an IC card at 10:23, boards train 000 departing from the entry station, XXX station, at 10:25, disembarks from train 000 at the transfer station, YYY station, at 10:32, and transfers to train 123 departing from the transfer station, YYY station, at 10:35. Furthermore, one passenger disembarks from train 123, which he boarded at the transfer station, YYY station, at 10:55, at the exit station, ZZZ station, and exits from the exit station at 10:58 using an IC card.

[0091] FIG. 9 also shows the allocation method for one passenger and the number of passengers remaining on each train when one passenger transfers between a rapid train and a local train in FIG. 8. Here, rapid train 000, which has a capacity of 800 passengers, and local train 123, which has a capacity of 800 passengers, arrive at XXX station, undergo passenger transfers and other passenger flows at XXX station, and then depart from XXX station. After that, each of the above trains arrives at YYY station, undergoes passenger transfers and other passenger flows at YYY station, and then departs from YYY station. Similarly, at the subsequent Z station, each of the above trains arrives at ZZZ station, undergoes passenger transfers and other passenger flows at ZZZ station, and then departs from ZZZ station.

[0092] For example, when one passenger boards express train 000 departing from XXX station, the entry station, at 10:25, the number of passengers on express train 000 departing XXX station at 10:25 is added together as 560 + 1, and the number of passengers entering XXX station is added together as 39 + 1.

[0093] When one passenger gets off rapid train 000, which arrives at YYY station, a transfer station, at 10:32, and transfers to another train, the number of passengers on rapid train 000, which departs YYY station at a specified time, is 700 - 1, and the number of passengers transferring from rapid train 000 to another train at YYY station is 7 + 1.

[0094] When one passenger boards local train 123 departing from YYY station, which is a transfer station, at 10:35, the number of passengers on local train 123 departing from YYY station at 10:35 is added together as 430 + 1, and the number of passengers who transferred from other trains to local train 123 departing at 10:35 is added together as 7 + 1.

[0095] When one passenger gets off local train 123, which arrives at its exit station, ZZZ station, at 10:55, the number of passengers on local train 123, which arrives at ZZZ station at 10:55, is calculated as 720 - 1, and the number of passengers departing from ZZZ station is calculated as 5 + 1.

[0096] The congestion degree for each train estimated by the first congestion degree estimating unit 15 may be expressed using any numerical value. For example, the congestion degree is expressed as 1 to 6.

[0097] Here, the first congestion level estimation unit 15 has calculated one passenger in integer units in calculating the number of people remaining on each train and the congestion level, but considering that the route candidates are assigned based on the allocation index, the one passenger may also be assigned in decimal units.

[0098] This allows the first congestion level estimation unit 15 to accurately predict passenger flow within a railway station by time period using the allocation result in which one passenger is allocated to multiple route candidates in decimal units.

[0099] Furthermore, the first congestion degree estimation unit 15 adds up the number of passengers between the entry time and the departure time at the entry station, between the departure time at the entry station and the arrival time at the exit station, and between the entry time and the arrival time at the exit station, for each train on each of the multiple route candidates, using the allocation result in which one passenger is allocated to multiple route candidates in decimal units, for each time.

[0100] For example, the first congestion level estimation unit 15 may add up the number of passengers remaining on each train at each time to the nearest decimal point, such as at 10:30, the number of passengers on board the train departing from XXX station at 10:25 is 560.6, and at 10:40, the number of passengers on board the train departing from YYY station at 10:35 is 700.4.

[0101] Furthermore, the first congestion level estimating unit 15 may represent the congestion levels of the trains at the respective times as 3, 5, and so on.

[0102] This allows the first congestion level estimating unit 15 to accurately predict passenger flow for each train on each of the multiple route candidates.

[0103] The second congestion level estimation unit 16 estimates the congestion level of the railway station by time period based on the number of passengers using the railway who are within the premises of the entry station, the number of passengers who are within the premises of each transfer station, and the number of passengers who are within the premises of the exit station for the route candidates assigned by the train assignment unit 14.

[0104] Here, the second congestion level estimation unit 16 estimates the number of passengers present within XXX station after the departure time of train 999 and before the departure time of train 000, for example, by excluding the number of passengers who boarded train 999, which departs earlier from XXX station, from the total number of passengers present within XXX station, the entrance station. In this case, the number of passengers within XXX station after the departure time of train 000, which departs later, is 0. Furthermore, if train 000 transfers at YYY station, a transfer station, on its way to ZZZ station, the arrival station, and train 999 does not transfer until it reaches ZZZ station, the number of passengers present within YYY station is the number of passengers who disembarked from train 000 at YYY station. Furthermore, if train 000 arrives at ZZZ station before train 999, the number of passengers who disembarked from train 000 at that arrival time will be the number of passengers present within ZZZ station, and if train 999 arrives at ZZZ station after that, the number of passengers present within ZZZ station will be estimated to be the sum of the number of passengers already present within ZZZ station and the number of passengers who disembarked from train 999 at ZZZ station.

[0105] Here, FIG. 10 shows two route candidates, one for 0.2 passengers and the other for 0.8 passengers, which are allocated by the train allocation unit 14 based on the allocation index.

[0106] A 0.2 minute passenger enters the entry station, XXX station, at 10:23 and boards train 000, which departs from the entry station, XXX station, at 10:25. The passenger also gets off train 000, which arrives at the transfer station, YYY station, at 10:32, and boards train 123, which departs from the transfer station, YYY station, at 10:35. The passenger also gets off train 123, which arrives at the exit station, ZZZ station, at 10:56, and departs from the exit station, ZZZ station, using an IC card at 10:58.

[0107] A 0.8 minute passenger enters the entry station, XXX station, at 10:23 and boards train 999, which departs from the entry station, XXX station, at 10:24. After that, the passenger gets off train 999, which arrives at the exit station, ZZZ station, at 10:58 without changing trains, and leaves the exit station, ZZZ station, at 10:58 using an IC card.

[0108] In the above situation, the number of people remaining within the station premises at each time of day at XXX station is 1.0 people at 10:23, 0.2 people at 10:24, and 0.0 people at 10:25.

[0109] In the above situation, the number of people remaining within the station premises at YYY station at each time is 0.2 people between 10:32 and 10:34.

[0110] In the above situation, the number of people remaining within the station premises at ZZZ station at each time is 0.2 people between 10:56 and 10:57, and 1.0 people at 10:58.

[0111] Furthermore, for example, if the number of passengers staying at XXX station is 0.2 at 10:24, the second congestion level estimation unit 16 may use an arbitrary numerical value to represent the congestion level of each station as 2 or the like.

[0112] This allows the second congestion level estimation unit 16 to accurately predict passenger flow within a railway station by time period using the allocation result in which one passenger is allocated to multiple route candidates in decimal units.

[0113] Furthermore, the second congestion degree estimation unit 16 adds up the number of passengers between the entry time and the departure time at the entry station, between the departure time at the entry station and the arrival time at the exit station, and between the entry time and the arrival time at the exit station, for each station on each of the multiple route candidates and for each time period, using the allocation result in which one passenger is allocated to multiple route candidates in decimal units.

[0114] For example, the second congestion level estimation unit 16 may determine that at 10:58, the number of passengers remaining within ZZZ station is 0.2 if the first route candidate is taken, and 0.8 if the second route candidate is taken, and add these together to arrive at 1.0.

[0115] In this case, the second congestion level estimation unit 16 may represent the congestion level for each station at 10:58 as 1 for XXX station, 1 for YYY station, 6 for ZZZ station, and so on.

[0116] FIG. 11 also shows the results of the second congestion level estimating unit 16 adding up the number of people staying for each station and each time.

[0117] For example, at 07:30, the number of people staying at AAA station is 1253.5, and the number of people staying at BBB station is 1082.1.

[0118] At this time, the second congestion level estimation unit 16 may compare the results expressed in decimal points to estimate the congestion level for each station at each time. For example, the second congestion level estimation unit 16 may express the congestion level at 07:30 using arbitrary numerical values, such as 4 for AAA station and 3 for BBB station.

[0119] The time period covered is from 03:00 to 02:59 the following day, and the results are displayed for 24 hours. The time period can be in units of one minute or one second, and is not particularly limited.

[0120] Furthermore, although the stations to be counted are expressed as AAA Station to ZZZ Station, the number of stations is not particularly limited.

[0121] This allows the second congestion level estimating unit 16 to accurately predict passenger flow for each station and for each time on each of the multiple route candidates.

[0122] The output unit 17 outputs the result of the allocation calculated by the train allocation unit 14 based on the allocation index.

[0123] As a result, the output unit 17 outputs the output data, for example, the result of allocation of one passenger to multiple route candidates, to a railway company, etc., so that the railway company can understand the flow status of passengers using the railway.

[0124] <Main features> As described above, the passenger flow congestion prediction device 10 is a device that predicts passenger flow in rail transport and includes a data acquisition unit 12, a route search unit 13, and a train allocation unit 14. The data acquisition unit 12 acquires ticket gate passage data D1 including the entry time and exit time of each passenger at the railway station, acquired from automatic ticket gates installed at the railway station, and current train schedule data D2 including the departure time and arrival time of the current train. The route search unit 13 extracts route candidates based on the entry time at the entry station where the passenger entered, the exit time at the exit station where the passenger exited, and the departure time and arrival time of the current train, all acquired by the data acquisition unit 12. The train allocation unit 14 calculates an allocation index based on the ticket gate passage data D1 and the current train schedule data D2, and allocates each passenger to multiple route candidates according to the allocation index.

[0125] This allows one passenger to be assigned to multiple route candidates using an assignment index calculated based on the entry and exit times of passengers using the railway and the departure and arrival times of trains, thereby reducing the bias in route candidates compared to assigning one passenger to one specific route.

[0126] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0127] <Passenger flow congestion prediction method according to the first embodiment> The passenger flow congestion prediction device 10 of this embodiment executes the passenger flow congestion prediction method in accordance with the flowchart shown in FIG.

[0128] That is, in the passenger flow congestion prediction method of this embodiment, as shown in Figure 12, in step S1, the data acquisition unit 12 reads the nth ticket gate passage data D1 of one passenger using a railway who passed through an automatic ticket gate 5 recorded in the data server 4.

[0129] Next, in step S2, the route search unit 13 determines that the n-th ticket gate passage data D1 acquired by the data acquisition unit 12 in step S1 is the first ticket gate passage data D1 by substituting 1 for the number n.

[0130] Next, in step S3, the route search unit 13 selects a route candidate R with an appropriate time sequence based on the timetable data D2, OD data D3, station data D4, and route data D5 input to the input device 2 and stored in the storage unit 11, and the first ticket gate passage data D1 acquired by the data acquisition unit 12. i Extract.

[0131] Here, a route candidate with an appropriate time sequence is one in which the departure time at the entrance station is the same as or later than the entrance time at the entrance station, the arrival time at the exit station is later than the departure time, and the exit time is the same as or later than the arrival time at the exit station (a route candidate that satisfies the condition that entry time ≦ departure time < arrival time ≦ exit time).

[0132] Next, in step S4, the route search unit 13 selects a route candidate R that has an appropriate time sequence extracted in step S3. i Determine whether there is one or more.

[0133] Here, the route candidate R i If the number is one or more, the process proceeds to step S5, and if the number is less than one, the process proceeds to step S6.

[0134] Next, in step S5, the train allocation unit 14 selects a route candidate R that has an appropriate time sequence in step S4. i Since it is determined that there is one or more, the allocation index is calculated using the following relational expression (3).

[0135] diff i =(dep i -T enter )+(T exit -arr i )…(3) Here, the allocation index is "diff" and the time when one passenger enters the entrance station is "T enter ", and the time the train departs from the entrance station is "dep i ” and the number of times passengers transfer at a transfer station is “trans i ", and the time of arrival of the train at the exit station is "arr i ”, and the time when the passenger leaves the exit station is “T exit " is expressed as ".

[0136] Next, in step S6, the route search unit 13 selects a route candidate R that has an appropriate time sequence in step S4. i Since it is determined that there is less than one, among the route candidates that have the earliest arrival time of the train that arrives at the exit station after the time when one passenger enters the entrance station, M route candidates R m Extract.

[0137] Next, in step S7, the train allocation unit 14 selects a route candidate R that has an appropriate time sequence in step S4. i is determined to be less than one, and in step S6, M route candidates R are selected from the earliest arriving candidates among the route candidates for which the arrival time of a train that arrives at the exit station after the time when one passenger enters the entrance station is the earliest. m Since the above has been extracted, the allocation index is calculated using the following relational expression (4).

[0138] diff=1 / M…(4) Next, in step S8, the train allocation unit 14 selects a route candidate R that has an appropriate time sequence in step S4.i When one or more of the above are extracted and the calculation result of the allocation exponent calculated in step S5 is diff=0, the allocation exponent is calculated as diff=1.

[0139] In addition, the train allocation unit 14 selects a route candidate R with an appropriate time sequence in step S4. i is determined to be less than one, and in step S6, M route candidates R are selected from the earliest arriving candidates among the route candidates for which the arrival time of a train that arrives at the exit station after the time when one passenger enters the entrance station is the earliest. m is extracted, and when the calculation result of the allocation exponent calculated in step S7 is diff=0, the allocation exponent is calculated as diff=1.

[0140] Next, in step S9, the train allocation unit 14 selects a route candidate R for the n-th passenger. i Using the sum calculated from equation (2), (1 / diff i / sum) assign people.

[0141] At this time, when the number of ticket gate passage data D1 acquired by the data acquisition unit 12 is 1, the route candidate R for the first passenger is i The allocation is performed as described above.

[0142] Next, in step S10, the train allocation unit 14 determines whether or not the allocation process in step S9 based on the n-th ticket gate passage data D1 has been completed.

[0143] At this time, if the number of pieces of ticket gate passage data D1 acquired by the data acquisition unit 12 is one, it is determined whether or not the allocation process of step S9 based on the first piece of ticket gate passage data D1 has been completed.

[0144] If the allocation process in step S9 based on all ticket gate passage data D1 has been completed, the process proceeds to step S12, and if the process has not been completed, the process proceeds to step S11.

[0145] Next, in step S11, the route search unit 13 assigns n+1 to the number n of ticket gate passage data D1 because it was determined in step S10 that the allocation process in step S9 based on all of the ticket gate passage data D1 has not been completed. Then, the process returns to step S3, and the processes from step S3 onwards are repeatedly executed based on the read result of the (n+1)th ticket gate passage data D1.

[0146] Next, in step S12, the output unit 17 outputs the allocation result in which the train allocation unit 14 allocates one passenger to multiple route candidates.

[0147] This allows one passenger to be assigned to multiple route candidates using an assignment index calculated based on the entry and exit times of passengers using the railway and the departure and arrival times of trains, thereby reducing the bias in route candidates compared to assigning one passenger to one specific route.

[0148] [Other embodiments] Although one embodiment of the present invention has been described above, the present invention is not limited to the above embodiment, and various modifications are possible without departing from the gist of the invention.

[0149] (A) In the above embodiment, an example has been described in which the present invention is realized as a passenger flow congestion prediction device and a passenger flow congestion prediction method, but the present invention is not limited to this.

[0150] For example, the present invention may be realized as a passenger flow congestion prediction program that causes a computer to execute the above-described passenger flow congestion prediction method.

[0151] This passenger flow congestion prediction program is stored in a memory (storage unit) installed in the passenger flow congestion prediction device, and a CPU reads the passenger flow congestion prediction program stored in the memory and causes the hardware to execute each step. More specifically, the CPU reads the passenger flow congestion prediction program and executes the above-mentioned data acquisition step, route search step, and train allocation step, thereby achieving the same effects as those described above.

[0152] The present invention may also be realized as a recording medium storing a passenger flow congestion prediction program.

[0153] (B) In the above embodiment, an example has been described in which the first congestion level estimation unit 15 that estimates the congestion level for each train is provided in the passenger flow congestion prediction device 10. However, the present invention is not limited to this.

[0154] For example, a user of the passenger flow congestion prediction device can understand the approximate congestion level for each train at each time by referring to the allocation result in which the train allocation unit allocates one passenger to multiple route candidates in decimal units. Therefore, the passenger flow congestion prediction device of the present invention may be configured without including the first congestion level estimation unit.

[0155] (C) In the above embodiment, an example has been described in which the second congestion level estimation unit 16 that estimates the congestion level by time period within a railway station is provided in the passenger flow congestion prediction device 10. However, the present invention is not limited to this.

[0156] For example, a user of the passenger flow congestion prediction device can understand the approximate congestion level at each train station at each time by referring to the allocation result in which the train allocation unit allocates one passenger to multiple route candidates in decimal units. Therefore, the passenger flow congestion prediction device of the present invention may be configured without including the second congestion level estimation unit.

[0157] (D) In the above embodiment, the train allocation unit 14 allocates routes using a ratio according to the value of the relational expression (1) when the time sequence is appropriate. However, the present invention is not limited to this.

[0158] For example, the train allocation unit can change the calculation method of the allocation index depending on the situation, thereby more accurately allocating one passenger to multiple route candidates, and therefore may calculate the allocation index using the following relational expressions (5) to (9).

[0159] diff=(departure time - entrance time) k +max(0, departure time-arrival time-const b ) l …(5) diff=max(departure time-entrance time-const a ) k +(Departure time - Arrival time - const b ) l …(6) diff=max(departure time-entrance time-const a ) k +max(0,(Departure time-Arrival time-const b )) l …(7) diff=(departure time - entrance time) k + (Departure time - Arrival time) l …(8) diff=1 / N…(9) Here, the train allocation unit 14 is configured to a " and "const b ", " are arbitrary constants, and "k" and "l" are arbitrary real numbers, so these values ​​can be set freely. Also, "N" represents the number of route candidates.

[0160] Furthermore, the train allocation unit 14 may add a term of an arbitrary real number p that represents the waiting time when transferring to the relational expressions (5) to (9), or may raise the power of the arbitrary real number p that represents the waiting time when transferring.

[0161] Furthermore, the train allocation unit 14 may remove or multiply each term in the relational expressions (1) and (3) to (9) by a constant.

[0162] (E) In the above embodiment, an example has been described in which the train allocation unit 14 allocates routes using a ratio according to the value of relational expression (4) when the time sequence is inappropriate. However, the present invention is not limited to this.

[0163] For example, the train allocation unit 14 can more accurately allocate one passenger to multiple route candidates by changing the calculation method of the allocation index depending on the situation, so the allocation index may be calculated using the following relational expressions (10) to (14).

[0164] diff=(departure time - entrance time) k …(10) diff=(departure time - entrance time) k +max(|Departure time-Arrival time|-const b ) l …(11) diff=max(departure time-entrance time-const a ,0)…(12) diff=max(departure time-entrance time-const a ,0) k +max(|Departure time-Arrival time|-const b ,0) l …(13) diff=(departure time - entrance time) k +|Departure time-Arrival time| l …(14) Here, the train allocation unit 14 is configured to a " and "const b ", " are arbitrary constants, and "k" and "l" are arbitrary real numbers, so these values ​​can be set freely. Also, "N" represents the number of route candidates.

[0165] Furthermore, the train allocation unit 14 may add a term of an arbitrary real number p representing the waiting time when transferring to the relational expressions (10) to (14), or may raise the power of the arbitrary real number p representing the waiting time when transferring.

[0166] Furthermore, the train allocation unit 14 may remove or multiply each term in the relational expressions (10) to (14) by a constant.

[0167] (F) In the above embodiment, an example has been described in which the memory unit 11 that stores various data such as the timetable data D2, OD data D3, station data D4, and route data D5 input from the input device 2 is provided within the passenger flow congestion prediction device 10. However, the present invention is not limited to this.

[0168] For example, the storage unit that stores the timetable data, OD data, station data, route data, etc. may be provided in a server or the like that is provided outside the passenger flow congestion prediction device. In other words, the passenger flow congestion prediction device of the present invention may not be provided with a storage unit as long as it is configured to be able to acquire necessary data from an external storage device, etc.

[0169] Even in this case, by having the data acquisition unit acquire the above-mentioned various data from a server located outside the travel purpose determination device, the passenger flow congestion prediction device can improve the accuracy of the predicted results of passenger flow in rail transportation more than before.

[0170] (G) In the above embodiment, an example has been described in which the output unit 17 that outputs the result of allocation calculated based on the allocation index in the train allocation unit 14 is provided in the passenger flow congestion prediction device 10. However, the present invention is not limited to this.

[0171] For example, in order to utilize the results of allocation calculated based on the allocation index, in addition to outputting them to the outside from the output unit and utilizing them, it is also possible to simply store them as data in the passenger flow congestion prediction device.

[0172] In other words, the passenger flow congestion prediction device of the present invention may not be provided with an output unit.

[0173] [Appendix 1 of the invention] The following is a summary of the invention extracted from the first embodiment. Note that the configurations and processing functions described in the following supplementary notes can be selected and combined as desired.

[0174] <Appendix 1> A passenger flow congestion prediction device according to a first aspect of the present invention is a passenger flow congestion prediction device that predicts passenger flow in rail transport, and includes a data acquisition unit, a route search unit, and a train allocation unit. The data acquisition unit acquires ticket gate passage data including the entry time and exit time of each passenger acquired from automatic ticket gates installed at rail stations, and current train schedule data including the departure time and arrival time of the current train. The route search unit extracts route candidates based on the entry time at the entry station where the passenger entered, the exit time at the exit station where the passenger exited, and the departure time and arrival time of the current train, all acquired by the data acquisition unit. The train allocation unit calculates an allocation index based on the ticket gate passage data and the current train schedule data, and allocates each passenger to multiple route candidates according to the allocation index.

[0175] Here, passenger flow is predicted by allocating one passenger to multiple candidate routes using an allocation index calculated based on the passenger entry and exit times contained in the ticket gate passage data and the train departure and arrival times contained in the current train timetable data.

[0176] Here, "ticket gate passage data" refers to, for example, data acquired when a passenger using a railway passes through a ticket gate, including the entry station, entry time, exit station and exit time for each passenger. "Timetable data" refers to, for example, data indicating the starting station, terminal station and intermediate stops for each train in operation, as well as information indicating the departure time from the starting station, arrival time and departure time at intermediate stops and arrival time at the terminal station.

[0177] In addition, the "allocation index" is a quantitative parameter used to calculate the proportion of a single rail passenger who selects multiple route options.

[0178] This allows one passenger to be assigned to multiple route candidates using an assignment index calculated based on the entry and exit times of passengers using the railway and the departure and arrival times of trains, thereby reducing the bias in route candidates compared to assigning one passenger to one specific route.

[0179] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0180] <Appendix 2> A passenger flow congestion prediction device according to a second aspect of the present invention is the passenger flow congestion prediction device according to the first aspect of the present invention, wherein the route search unit extracts route candidates in which the departure time at the entrance station is the same as or later than the entrance time at the entrance station, the arrival time at the exit station is later than the departure time, and the exit time is the same as or later than the arrival time at the exit station.

[0181] Here, the route search unit extracts route candidates with appropriate sequential relationships between entry time, departure time, arrival time, and exit time from a large amount of acquired ticket gate passage data.

[0182] Here, for example, if the entry time is 9:10, the departure time is 9:11, the arrival time is 9:12, and the exit time is 9:13, the route search unit extracts the route candidate because the above conditions are met and the relationship between the times is appropriate. Also, for example, the route search unit may extract the route candidate even if the entry time is 9:10, the departure time is 9:10, the arrival time is 9:12, and the exit time is 9:12 because the above conditions are met and the relationship between the times is appropriate. However, for example, if the entry time is 9:13, the departure time is 9:12, the arrival time is 9:11, and the exit time is 9:10, the above conditions are not met and the relationship between the times is inappropriate, so the route search unit does not extract the route candidate.

[0183] This allows the train allocation unit described below to determine an appropriate allocation index.

[0184] <Appendix 3> A passenger flow congestion prediction device according to a third aspect of the present invention is a passenger flow congestion prediction device according to the first or second aspect of the present invention, wherein the route search unit extracts route candidates that minimize the number of train changes required by passengers between the entrance station and the exit station.

[0185] Here, the route search unit extracts route candidates with reference to the number of transfers, on the premise that a likely mode of travel used by passengers using trains is selected.

[0186] Here, since passengers using trains are generally more likely to use route candidates with fewer transfers, route candidates with fewer transfers can be the most likely route candidates.

[0187] In this case, there may be multiple route candidates that minimize the number of train changes required by a passenger using a railway between the entrance station and the exit station.

[0188] Furthermore, if a passenger moves quickly between the entrance station and the exit station, there will be fewer route candidates, and if the passenger moves slowly, there will be more route candidates.

[0189] This allows the train allocation unit to allocate one passenger to a plurality of appropriate route candidates based on the allocation index.

[0190] <Appendix 4> The passenger flow congestion prediction device of the fourth invention is the passenger flow congestion prediction device of the first invention, further comprising a first congestion degree estimation unit that estimates the congestion degree for each train operating on the route candidate assigned by the train assignment unit.

[0191] Here, the first congestion degree estimation unit estimates the congestion degree for each train based on the number of passengers using the railway inside the train on the route candidates assigned by the train assignment unit, the number of passengers entering at the entry station and the number of passengers exiting at the exit station, and the number of passengers who transferred.

[0192] At this time, the first congestion degree estimation unit estimates the number of passengers on train B departing from station X by, for example, subtracting the number of passengers exiting station X and the number of passengers transferring from train A arriving at station X to another train from the number of railway passengers on train A arriving at station X, and adding the number of passengers entering station X and the number of passengers transferring from another train to train B departing from station X. The congestion degree for each train is estimated according to these values.

[0193] Here, "congestion level" is an indicator that indicates the flow of passengers using the railway during the period from entering at the entrance station to exiting at the exit station, which is difficult to predict from ticket gate passage data or timetable data.

[0194] This allows the first congestion level estimation unit to accurately predict passenger flow for each train using the allocation result in which one passenger is allocated to a plurality of route candidates in decimal units.

[0195] <Appendix 5> The passenger flow congestion prediction device according to the fifth aspect of the present invention is the passenger flow congestion prediction device according to the first aspect of the present invention, further comprising a second congestion degree estimation unit that estimates the congestion degree by time period within the premises of a railway station.

[0196] Here, the second congestion level estimation unit estimates the congestion level within the railway station by time period based on the number of passengers using the railway within the entry station, the number of passengers within each transfer station, and the number of passengers within the exit station for the route candidates assigned by the train assignment unit.

[0197] This allows us to accurately predict passenger flow within a train station by time period using the allocation results in which one passenger is assigned to multiple route candidates in decimal units.

[0198] <Appendix 6> A passenger flow congestion prediction device according to a sixth aspect of the present invention is a passenger flow congestion prediction device according to the fourth or fifth aspect of the present invention, wherein the first congestion degree estimation unit adds up, for each train, the number of passengers from the time of passenger entry to the time of departure at the entry station, from the time of departure at the entry station to the time of arrival at the exit station, and from the time of departure to the time of arrival at the exit station.

[0199] Here, the first congestion level estimation unit uses the allocation result in which one passenger using a railway is allocated to multiple route candidates in decimal units to add up the number of passengers on each train on each of the multiple route candidates.

[0200] This allows the first congestion level estimation unit to accurately predict passenger flow for each train on each of the multiple route candidates.

[0201] <Appendix 7> A passenger flow congestion prediction device according to a seventh aspect of the present invention is the passenger flow congestion prediction device according to the fourth or fifth aspect of the present invention, wherein the second congestion degree estimation unit adds up, for each station, the number of passengers between the passenger's entry time and departure time at the entry station, between the departure time at the entry station and arrival time at the exit station, and between the departure time and arrival time at the exit station.

[0202] Here, the second congestion level estimation unit uses the allocation result in which one passenger is allocated to multiple route candidates in decimal units to add up the number of passengers for each station and time on each of the multiple route candidates.

[0203] This allows the second congestion level estimation unit to accurately predict passenger flow for each station and for each time period on each of the multiple route candidates.

[0204] <Appendix 8> The passenger flow congestion prediction device of the eighth invention is the passenger flow congestion prediction device of the first or second invention, wherein the route search unit selects the departure times of a predetermined number of current trains after the passenger entry time as candidate departure times.

[0205] Here, the route search unit extracts multiple candidates for trains that the passenger will board by referring to the departure time included in the timetable data of the current train immediately after the passenger's entry time.

[0206] This allows the train allocation unit to allocate one passenger to multiple route candidates based on the entry time and the allocation index.

[0207] <Appendix 9> A passenger flow congestion prediction device according to a ninth aspect of the present invention is a passenger flow congestion prediction device according to the first or second aspect of the present invention, wherein the route search unit selects the arrival times of a predetermined number of current trains that occur before the departure time of the current train as candidate arrival times.

[0208] Here, the route search unit extracts multiple candidate trains for the passenger to disembark from, by referring to the arrival time included in the timetable data of the current train immediately prior to the passenger's departure time.

[0209] This allows the train allocation unit to allocate one passenger to multiple route candidates based on the allocation index.

[0210] <Appendix 10> A passenger flow congestion prediction device according to a tenth aspect of the present invention is a passenger flow congestion prediction device according to the first or second aspect of the present invention, wherein the train allocation unit calculates an allocation index based on the sum of the time difference between the entry time and departure time and the time difference between the exit time and arrival time for a route candidate.

[0211] Here, the train allocation unit uses the entry and exit times acquired from the data acquisition unit and the departure and arrival times included in the current train timetable data to calculate an allocation index for allocating one passenger to multiple route candidates at a predetermined ratio.

[0212] In this case, the relational expression for calculating the allocation index is not limited to the above description, and any constant may be incorporated into the relational expression. The relational expression may also use a MAX function that selects the largest value from multiple calculation results. Furthermore, the relational expression may be calculated using the power of the time difference.

[0213] This allows the train allocation unit to allocate one passenger to multiple routes in units of decimal points less than one according to the calculated allocation index.

[0214] <Appendix 11> A passenger flow congestion prediction device according to an eleventh aspect of the present invention is a passenger flow congestion prediction device according to the first or second aspect of the present invention, wherein, in a case where the conditions for a route candidate where the departure time at the entrance station is the same as or later than the entrance time at the entrance station, the arrival time at the exit station is later than the departure time, and the departure time is the same as or later than the arrival time at the exit station are not satisfied, if the departure time is the same as or later than the entrance time, the route search unit extracts a predetermined number of route candidates at times after the entrance time in order of earliest train arrival time.

[0215] Here, the route search unit extracts route candidates in which the arrival time is earlier than the departure time from among route candidates in which the relationship between the entry time, departure time, arrival time, and exit time is inappropriate, from the large amount of ticket gate passage data acquired.

[0216] Here, a route candidate in which the arrival time is earlier than the departure time corresponds to, for example, a case in which the arrival time does not indicate an appropriate time due to a disruption in the schedule or the like.

[0217] This allows the route search unit to extract route candidates even when the time combination is inappropriate, and the train allocation unit can perform a specified calculation and allocate one passenger to multiple route candidates.

[0218] <Appendix 12> The passenger flow congestion prediction device of the twelfth invention is the passenger flow congestion prediction device of the first or second invention, further comprising a memory unit that stores timetable data indicating operation plans for departure stations and arrival stations, OD (Origin Destination) data indicating the number of users for each combination of departure station and arrival station, station data indicating the departure station and arrival station, and route data indicating a route map.

[0219] This makes it possible to improve the accuracy of predictions of passenger flow in rail transport compared to conventional methods by using various data stored in a memory unit installed within the passenger flow congestion prediction device.

[0220] <Appendix 13> A passenger flow congestion prediction device according to a thirteenth aspect of the present invention is the passenger flow congestion prediction device according to the first or second aspect of the present invention, further comprising an output unit that outputs a result of allocation in the train allocation unit.

[0221] As a result, the output unit can output the output data, for example, of the allocation results in which one passenger is allocated to multiple route candidates, to a railway company, etc., so that the railway company can understand the flow status of passengers using the railway.

[0222] <Appendix 14> A passenger flow congestion prediction method according to a fourteenth aspect of the present invention is a passenger flow congestion prediction method for predicting passenger flow in rail transport, and includes a data acquisition step, a route search step, and a train allocation step. The data acquisition step acquires ticket gate passage data including the entry time and exit time of each passenger acquired from an automatic ticket gate installed at a railway station, and current train schedule data including the departure time and arrival time of the current train. The route search step extracts route candidates based on the entry time at the entry station where the passenger entered, the exit time at the exit station where the passenger exited, and the departure time and arrival time of the current train, all acquired in the data acquisition step. The train allocation step calculates an allocation index based on the ticket gate passage data and the current train schedule data, and allocates each passenger to multiple route candidates according to the allocation index.

[0223] Here, passenger flow is predicted by allocating one passenger to multiple candidate routes using an allocation index calculated based on the passenger entry and exit times contained in the ticket gate passage data and the train departure and arrival times contained in the current train timetable data.

[0224] Here, "ticket gate passage data" refers to, for example, data acquired when a passenger using a railway passes through a ticket gate, including the entry station, entry time, exit station and exit time for each passenger. "Timetable data" refers to, for example, data indicating the starting station, terminal station and intermediate stops for each train in operation, as well as information indicating the departure time from the starting station, arrival time and departure time at intermediate stops and arrival time at the terminal station.

[0225] In addition, the "allocation index" is a quantitative parameter used to calculate the proportion of a single rail passenger who selects multiple route options.

[0226] This allows one passenger to be assigned to multiple route candidates using an assignment index calculated based on the entry and exit times of passengers using the railway and the departure and arrival times of trains, thereby reducing the bias in route candidates compared to assigning one passenger to one specific route.

[0227] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0228] <Appendix 15> A passenger flow congestion prediction program according to a fifteenth aspect of the present invention is a passenger flow congestion prediction program for predicting passenger flow in rail transport, and includes a data acquisition step, a route search step, and a train allocation step. The data acquisition step acquires ticket gate passage data including the entry time and exit time of each passenger acquired from an automatic ticket gate installed at a rail station, and current train schedule data including the departure time and arrival time of the current train. The route search step extracts route candidates based on the entry time at the entry station where the passenger entered, the exit time at the exit station where the passenger exited, and the departure time and arrival time of the current train, all acquired in the data acquisition step. The train allocation step calculates an allocation index based on the ticket gate passage data and the current train schedule data, and allocates each passenger to multiple route candidates according to the allocation index.

[0229] Here, passenger flow is predicted by allocating one passenger to multiple candidate routes using an allocation index calculated based on the passenger entry and exit times contained in the ticket gate passage data and the train departure and arrival times contained in the current train timetable data.

[0230] Here, "ticket gate passage data" refers to, for example, data acquired when a passenger using a railway passes through a ticket gate, including the entry station, entry time, exit station and exit time for each passenger. "Timetable data" refers to, for example, data indicating the starting station, terminal station and intermediate stops for each train in operation, as well as information indicating the departure time from the starting station, arrival time and departure time at intermediate stops and arrival time at the terminal station.

[0231] In addition, the "allocation index" is a quantitative parameter used to calculate the proportion of a single rail passenger who selects multiple route options.

[0232] This allows one passenger to be assigned to multiple route candidates using an assignment index calculated based on the entry and exit times of passengers using the railway and the departure and arrival times of trains, thereby reducing the bias in route candidates compared to assigning one passenger to one specific route.

[0233] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0234] [Second embodiment] The configuration of a passenger flow congestion prediction device 10 according to a second embodiment of the present invention will be described. In the following, the description of the same configuration as that shown in the first embodiment will be omitted as appropriate.

[0235] As shown in FIG. 13, the passenger flow congestion prediction device 10 according to the second embodiment further includes, in addition to the configuration shown in the first embodiment, an allocation correction unit 141 that corrects the number of passengers allocated to each of a plurality of route candidates according to the allocation index.

[0236] Specifically, when the train allocation unit 14 calculates the number of people to be allocated to one passenger for each of the multiple route candidates extracted by the route search unit 13 based on the allocation index (diff) calculated using the above relational expression (1), the allocation correction unit 141 executes a correction process to correct the number of people to be allocated calculated by the train allocation unit 14 based on the attributes of the train corresponding to the route candidate.

[0237] A specific example of the correction process will be described with reference to Fig. 14. Fig. 14 shows departure times T1 of trains at a departure station, arrival times T2 of trains at an arrival station, and five routes between the departure times T1 and the arrival times T2.

[0238] For example, the first route is the route of train number "211" on which a passenger enters the entry station at 07:05, departs from the entry station at departure time T1 of 07:10, arrives at the exit station at arrival time T2 of 07:34, and departs from the exit station at departure time of 07:55.

[0239] The second route is the route of train number "212" where a passenger entered the entry station at 07:05, departed from the entry station at departure time T1 at 07:15, arrived at the exit station at arrival time T2 at 07:43, and departed from the exit station at departure time 07:55.

[0240] The third route is the route of train number "213" where a passenger entered the entry station at 07:05, departed from the entry station at departure time T1 at 07:16, arrived at the exit station at arrival time T2 at 07:52, and departed from the exit station at departure time 07:55.

[0241] The fourth route is the route of train number "214" where a passenger entered the entry station at 07:05, departed from the entry station at departure time T1 at 07:20, arrived at the exit station at arrival time T2 at 07:45, and departed from the exit station at departure time 07:55.

[0242] The fifth route is the route of train number "215" on which a passenger entered the entry station at 07:05, departed from the entry station at departure time T1 of 07:24, arrived at the exit station at arrival time T2 of 07:53, and departed from the exit station at departure time of 07:55.

[0243] The route search unit 13 extracts multiple route candidates with appropriate time sequences based on the entrance and exit times of passengers using the train, which are included in the ticket gate passage data D1 acquired by the data acquisition unit 12, and the departure and arrival times of trains, which are included in the current train schedule data D2. For example, the route search unit 13 extracts, as route candidates, routes that arrive at the exit station between a predetermined time before the exit time and the exit time, from the multiple routes shown in FIG. 14. In the first embodiment, the route search unit 13 extracts, as route candidates, routes of a predetermined number of trains departing after the passenger's entrance time, based on the entrance time. However, in the second embodiment, the route search unit 13 does not use the entrance time as a criterion because passengers are allowed to stay at the entrance station (departure station) from the time they enter the entrance station until they board the train. On the other hand, in many cases, passengers arrive at the arrival station and exit without staying there for a long time. Therefore, in the second embodiment, the route search unit 13 may extract route candidates based on the exit time.

[0244] For example, the route search unit 13 extracts routes that arrive at the departure station between six minutes before the departure time and the departure time as route candidates. In the example shown in Fig. 14, the route search unit 13 extracts the route of train number "213" and the route of train number "215" that arrive at the departure station between 7:49, which is six minutes before 07:55, and 07:55 as route candidates. Note that the route search unit 13 may set the predetermined time based on information such as the date and time (time zone), day of the week, and timetable data D2.

[0245] In this way, the route search unit 13 excludes from the route candidates routes in which passengers board immediately after entering the entrance station and stay for a long time at the arrival station. In addition, the route search unit 13 extracts, as route candidates, routes in which passengers stay for a long time at the entrance station or intermediate stations or routes that take longer than usual, because these routes may be selected to wait for the first train or to avoid congestion.

[0246] In another embodiment, the route search unit 13 may extract, as route candidates, a predetermined number of routes that arrive at the departure station earlier than the departure time and whose arrival times are closest to the departure time. For example, when the departure time is 07:55, the route search unit 13 extracts, as route candidates, four routes (in the example shown in FIG. 14 , train numbers “212,” “213,” “214,” and “215”) in order of closest to 07:55.

[0247] In another embodiment, the route search unit 13 may extract, as route candidates, routes that depart from the entrance station later than the entrance time and within a predetermined time from the entrance time. Alternatively, the route search unit 13 may extract, as route candidates, a predetermined number of routes that depart from the entrance station later than the entrance time and whose departure times are closest to the entrance time.

[0248] The train allocation unit 14 calculates the number of passengers to be allocated to each of the multiple route candidates extracted by the route search unit 13 based on the allocation index (diff) calculated by the above relational expression (1). For example, when there are route candidates from route candidate i to route candidate N, the train allocation unit 14 adds up the reciprocals of diff from i to N using the above relational expression (2). Furthermore, the train allocation unit 14 uses the calculated sum value to calculate (1 / diff i / sum) assign people.

[0249] In the example shown in FIG. 14, the train allocation unit 14 calculates diff=14 (=11+3) for the route candidate with train number "213" using the above relational expression (1), and calculates diff=21 (=19+2) for the route candidate with train number "215". Next, the train allocation unit 14 allocates one passenger to each route candidate based on the allocation index. Here, the train allocation unit 14 allocates 0.6 (=1 / 14 / (5 / 42)) of one passenger to the route candidate with train number "213", and allocates 0.4 (=1 / 21 / (5 / 42)) of one passenger to the route candidate with train number "215".

[0250] When the train allocation unit 14 allocates the number of passengers to each route candidate, the allocation correction unit 141 determines whether the trains corresponding to the route candidates include a train with a predetermined attribute. The predetermined attribute includes information about the type of train, such as a first train, a paid train, a limited express train, an express train, a rapid train, or a local train. When the allocation correction unit 141 determines that the trains corresponding to the route candidates include a train with the predetermined attribute, it corrects the allocated number of passengers according to the attribute.

[0251] [Examples of first and non-first trains] For example, if the trains corresponding to the multiple route candidates include a first train that departs from an entrance station or a station between the entrance station and the exit station, passengers staying at the entrance station or transfer station are likely to board the first train of the multiple trains. Therefore, the allocation correction unit 141 executes a correction process to increase the number of people allocated to the route candidate corresponding to the first train and decrease the number of people allocated to the route candidate corresponding to other trains (non-first trains) that are not the first train, with respect to the number of people allocated to each route candidate by the train allocation unit 14 based on the allocation index.

[0252] For example, in the example shown in FIG. 14 , when train number "213" of train numbers "213" and "215" is a train that starts from the departure station and train number "215" is a train that stops at each station between the departure station and the arrival station (a non-starting train), the allocation correction unit 141 multiplies the number of passengers "0.6" calculated by the train allocation unit 14 for the route candidate for train number "213" by a correction coefficient K (where K is a value greater than 1). For example, when the correction coefficient K is set to 1.5, the allocation correction unit 141 corrects the number of passengers "0.6" for the route candidate for train number "213" to "0.9" (=0.6×1.5). Furthermore, the allocation correction unit 141 subtracts the increase from the number of passengers allocated to each route candidate to make the total number of passengers allocated to each route candidate 1.0. Here, the allocation correction unit 141 corrects the assigned number of passengers "0.4" to "0.1" (=0.4-0.3) for the route candidate with train number "215." Note that in this method (first correction method), the allocation correction unit 141 subtracts the increased amount from the other route candidates, but as another method (second correction method), the allocation correction unit 141 may correct each assigned number of passengers by adding up the corrected assigned number of passengers for the route candidate to be corrected and the assigned number of passengers originally assigned to the other route candidates, and dividing each assigned number of passengers by the total number of passengers. For example, in the above example, the allocation correction unit 141 adds up the corrected allocated number of people "0.9" for the route candidate with train number "213" and the original allocated number of people "0.4" for the route candidate with train number "215", divides "0.9" by the total number of people "1.3" to calculate "0.693" as the allocated number of people for train number "213", and divides "0.4" by the total number of people "1.3" to calculate "0.307" as the allocated number of people for train number "215".

[0253] In this way, when the route candidates include a route candidate corresponding to the first train, the allocation correction unit 141 multiplies the number of people allocated to the route candidate corresponding to the first train by the correction coefficient K. After performing the correction process for one passenger, the allocation correction unit 141 allocates the corrected number of people to each route candidate.

[0254] The allocation correction unit 141 may set a correction coefficient K corresponding to the first train based on a predetermined condition. For example, when the departure times T1 of multiple route candidates extracted by the route search unit 13 are close to each other, passengers are more likely to board the first train than when the departure times T1 are far apart. For example, if the first train departs from a departure station five minutes after the departure time of a non-first train, passengers are more likely to wait five minutes before boarding the first train. In contrast, if the first train departs 30 minutes after the departure time of a non-first train, passengers are less likely to board the first train due to the long waiting time. In this way, the train selected by passengers may change depending on the interval between the departure times of multiple trains. Therefore, for example, when the first train departs after the departure time of a non-first train, the allocation correction unit 141 may set the correction coefficient K to a larger value as the interval between the departure times is shorter, and may set the correction coefficient K to a smaller value as the interval between the departure times of multiple route candidates is longer.

[0255] Furthermore, passengers who wait at an entrance station to select the first train often do so in order to avoid crowded trains. Therefore, the more crowded the time period, the more likely they are to board the first train. Therefore, the allocation correction unit 141 may perform the correction process only during crowded time periods (such as commuter hours or school hours), or may set the correction coefficient K to a large value during crowded time periods and a small value during less crowded time periods. Furthermore, when comparing urban areas and suburban areas, passengers who use trains in urban areas tend to select the first train more than passengers who use trains in suburban areas. Therefore, the allocation correction unit 141 sets the correction coefficient K to a large value for stations in urban areas and stations close to the urban area, and sets the correction coefficient K to a small value (e.g., K=1) for suburban stations and stations close to the suburbs.

[0256] In another embodiment, the allocation correction unit 141 may be configured to perform the correction process when the multiple route candidates include a route candidate for the first train and a route candidate for a train (non-first train) that departs from the entrance station before the first train, and not to perform the correction process when the multiple route candidates include a route candidate for the first train and do not include a route candidate for a train (non-first train) that departs from the entrance station before the first train. In other words, when the multiple route candidates include a route candidate for the first train, if the first train departs from the entrance station first, the train allocation unit 14 assigns a higher number of passengers to the route candidate for the first train, so the allocation correction unit 141 may not perform the correction process. In another embodiment, when the first train departs the entrance station first, the allocation correction unit 141 may assign "1.0 passenger" to the route candidate for the first train, assuming that the passenger will definitely board the first train.

[0257] [Examples of paid and free trains] As another example, if the trains corresponding to the multiple route candidates include both toll trains and free trains, passengers staying at an entrance station or a transfer station are less likely to board a toll train among the multiple trains, and more likely to board a free train. Therefore, the allocation correction unit 141 executes a correction process to reduce the number of people allocated to route candidates corresponding to toll trains and increase the number of people allocated to route candidates corresponding to free trains, with respect to the number of people allocated to each route candidate by the train allocation unit 14 based on the allocation index. Note that toll trains are trains that require an additional fee (such as a limited express fee or a reserved seat fee) on top of the normal fare, while free trains are trains that can be boarded for just the normal fare.

[0258] For example, in the example shown in FIG. 14 , when train number "213" is a toll train and train number "215" is a free train among train numbers "213" and "215," the allocation correction unit 141 multiplies the allocated number of passengers "0.6" calculated for the route candidate with train number "213" by a correction coefficient K (where K is a value smaller than 1). For example, when the correction coefficient K is set to 0.5, the allocation correction unit 141 corrects the allocated number of passengers "0.6" for the route candidate with train number "213" to "0.3" (=0.6×0.5). Furthermore, the allocation correction unit 141 adds the reduced number of passengers to the other route candidates so that the total number of passengers allocated to each route candidate becomes 1.0. Here, the allocation correction unit 141 corrects the allocated number of passengers "0.4" for the route candidate with train number "215" to "0.7" (=0.4+0.3). The allocation correction unit 141 may correct the number of people allocated by the second correction method described above. According to the second correction method, the allocation correction unit 141 corrects the number of people allocated to the route candidate with train number "213" to "0.428" (=0.3÷0.7), and corrects the number of people allocated to the route candidate with train number "215" to "0.572" (=0.4÷0.7).

[0259] In this way, when the route candidates include a route candidate corresponding to a toll train, the allocation correction unit 141 multiplies the number of people allocated to the route candidate corresponding to the toll train by the correction coefficient K. After performing the correction process for one passenger, the allocation correction unit 141 allocates the corrected number of people to each route candidate.

[0260] The allocation correction unit 141 may set a correction coefficient K corresponding to a paid train based on a predetermined condition. For example, when comparing the travel time (boarding time) from the departure time to the arrival time of a paid train and a free train, if the travel time of the free train is significantly longer than that of the paid train, passengers are more likely to board the paid train. For example, if a free train departs from a departure station five minutes after the departure time of a paid train, passengers are more likely to board the free train. On the other hand, if a free train departs 30 minutes after the departure time of a paid train, passengers are less likely to board the free train. In this way, it is conceivable that the train selected by passengers will change depending on the interval between the departure times of multiple trains. Therefore, for example, if a free train departs after the departure time of a paid train, the allocation correction unit 141 may set the correction coefficient K to a smaller value as the interval between the respective departure times is shorter, and may set the correction coefficient K to a larger value as the interval between the respective departure times of multiple route candidates is longer. It should be noted that the predetermined condition may be the distance from the departure time to the arrival time instead of the "required time (ride time)".

[0261] Furthermore, when the fare for a toll train is low, passengers are more likely to board the toll train than when the fare for a toll train is high. Therefore, the allocation correction unit 141 may set the correction coefficient K to a larger value as the fare for a toll train is lower, and may set the correction coefficient K to a smaller value as the fare for a toll train is higher.

[0262] In another embodiment, the allocation correction unit 141 may be configured not to perform the correction process when the multiple route candidates include a route candidate for a toll train and a route candidate for a free train that departs from the entrance station before the toll train, and to perform the correction process when the multiple route candidates include a route candidate for a toll train and do not include a route candidate for a free train that departs from the entrance station before the toll train. In other words, when the free train departs from the entrance station first among multiple route candidates including a route candidate for a toll train, the train allocation unit 14 assigns a higher number of passengers to the route candidate for the free train, so the allocation correction unit 141 may not perform the correction process. In another embodiment, when the free train departs the entrance station first, the allocation correction unit 141 may assign "1.0 passenger" to the route candidate for the free train, assuming that the passenger will definitely board the free train.

[0263] [Examples of express and local trains] As another example, if the trains corresponding to the multiple route candidates include express trains and local trains, passengers staying at an entrance station or a transfer station are more likely to board an express train among the multiple trains and less likely to board a local train. In this embodiment, a "express train" refers to a free train, such as a limited express train, an express train, or a rapid train, that does not require an additional fee (such as a limited express fare or a reserved seat fare). A local train is, for example, a train that stops at every station between a departure station and a destination station (a local train that stops at every station), and an express train is, for example, a train that passes through at least one of the stations between a departure station and a destination station (a non-local train). Therefore, the allocation correction unit 141 performs a correction process to increase the number of passengers assigned to route candidates corresponding to non-local trains and decrease the number of passengers assigned to route candidates corresponding to local trains, based on the allocation index assigned by the train allocation unit 14 to each route candidate.

[0264] For example, in the example shown in FIG. 14 , when train number "213" is a local train and train number "215" is an express train, the allocation correction unit 141 multiplies the allocated number of passengers "0.6" calculated for the route candidate with train number "213" by a correction coefficient K (where K is a value greater than 1). For example, when the correction coefficient K is set to 1.2, the allocation correction unit 141 corrects the allocated number of passengers "0.6" for the route candidate with train number "213" to "0.72" (=0.6×1.2). Furthermore, the allocation correction unit 141 subtracts the increase from the other route candidates to make the total allocated number of passengers to each route candidate 1.0. Therefore, the allocation correction unit 141 corrects the allocated number of passengers "0.4" for the route candidate with train number "215" to "0.28" (=0.4−0.12). The allocation correction unit 141 may correct the number of people allocated by the second correction method described above. According to the second correction method, the allocation correction unit 141 corrects the number of people allocated to the route candidate with train number "213" to "0.643" (=0.72÷1.12), and corrects the number of people allocated to the route candidate with train number "215" to "0.357" (=0.4÷1.12).

[0265] In this way, when the route candidates include a route candidate corresponding to an express train, the allocation correction unit 141 multiplies the number of people allocated to the route candidate corresponding to the express train by the correction coefficient K. When the allocation correction unit 141 executes the correction process for one passenger, it allocates the corrected number of people to each route candidate.

[0266] The allocation correction unit 141 may set a correction coefficient K corresponding to an express train based on a predetermined condition. For example, when the departure times T1 of the multiple route candidates extracted by the route search unit 13 are close to each other, passengers are more likely to board a non-local train (express train) than when the departure times T1 are far apart. For example, when an express train departs from a departure station five minutes after the departure time of a local train, passengers are more likely to board the express train. In contrast, when an express train departs 30 minutes after the departure time of a local train, passengers are less likely to board the express train. In this way, the train selected by passengers may change depending on the interval between the departure times of multiple trains. Therefore, for example, when a non-local train departs after the departure time of a local train, the allocation correction unit 141 may set the correction coefficient K to a larger value as the interval between the departure times is shorter, and may set the correction coefficient K to a smaller value as the interval between the departure times of the multiple route candidates is longer.

[0267] Furthermore, the allocation correction unit 141 may set the correction coefficient K based on the number of stations (number of stopping stations) at which a train stops between a departure station and an arrival station. For example, the fewer the number of stopping stations a non-local train has, the earlier it arrives at the arrival station, so passengers are more likely to board a train with fewer stopping stations among multiple types of non-local trains (express trains). Therefore, the allocation correction unit 141 may set the correction coefficient K to a larger value as the number of stopping stations decreases, and may set the correction coefficient K to a smaller value as the number of stopping stations increases.

[0268] Furthermore, some passengers choose to take trains that take longer (local trains) to avoid crowded trains. Therefore, the allocation correction unit 141 may execute the correction process only during crowded times (commuting hours, school commute hours, etc.), or may set the correction coefficient K to a small value during crowded times and a large value during non-congested times. This results in a higher number of passengers being allocated to local trains during crowded times and a lower number of passengers being allocated to local trains during non-congested times.

[0269] If the express train is a toll train, the possibility that passengers will board it is low, so as shown in the above [Example of toll train and free train], the allocation correction unit 141 executes a correction process to decrease the number of passengers allocated to the route candidates corresponding to toll trains and increase the number of passengers allocated to the route candidates corresponding to free trains. Also, the allocation correction unit 141 may set the correction coefficient K based on each piece of information on whether the train is the first train, whether the train is a toll train, and whether the train is a local train.

[0270] [Other conditions] The predetermined attributes are not limited to the examples described above, and may be, for example, vehicle-specific information (number of vehicles, seat type (cross seat, long seat, etc.), age of vehicle, etc.). For example, a train with a large number of vehicles has a lower congestion rate than a train with a small number of vehicles, and therefore is more likely to attract passengers. Therefore, the allocation correction unit 141 corrects the number of allocated passengers for a train of the target route candidate so that the larger the number of vehicles, the higher the allocated passengers, and corrects the number of allocated passengers so that the fewer the number of vehicles, the lower the allocated passengers.

[0271] Furthermore, for example, the longer the riding distance (distance from departure station to arrival station, number of stations, etc.), the higher the possibility of riding on a train with cross seats. Therefore, the allocation correction unit 141 corrects the number of passengers allocated to trains with cross seats so that the longer the riding distance, the more likely it is that passengers will ride on a train with cross seats, and corrects the number of passengers allocated to trains with cross seats so that the shorter the riding distance, the more likely it is that passengers will ride on a train with long seats (the more likely it is that passengers will ride on a train with long seats).

[0272] Furthermore, for example, a train that has been in operation for a short time is more likely to have passengers boarding than a train that has been in operation for a long time. Therefore, the allocation correction unit 141 corrects the number of passengers to be allocated to increase the number of passengers as the number of years that have passed since the train was introduced, and corrects the number of passengers to decrease the number of passengers as the number of years that have passed since the train was introduced.

[0273] [Mutual use by multiple railway companies] In the case where a train of a second railway company (another railway company) can enter a first railway company (the company) and passenger flow congestion of the company is predicted, the allocation correction unit 141 may further include the following configuration.

[0274] For example, if you board a train operated by one of our companies at the departure station and exit at another company's arrival station, you may not be able to obtain the departure time.Also, if you board a train operated by another company at the departure station and exit at your company's arrival station, you may not be able to obtain the entry time.

[0275] In this case, the train allocation unit 14 first allocates 1 / N of the number of people to each of multiple route candidates (e.g., N route candidates) extracted by the route search unit 13 based on the entry time or exit time. Next, the allocation correction unit 141 multiplies the route candidate corresponding to the predetermined condition by a correction coefficient K (K-fold), and adjusts the number of people allocated to the other route candidates so that the total number of people allocated to each route candidate becomes 1.0.

[0276] <Passenger flow congestion prediction method according to the second embodiment> The passenger flow congestion prediction device 10 of this embodiment executes the passenger flow congestion prediction method in accordance with the flowcharts shown in FIGS.

[0277] The flowchart shown in FIG. 15 is executed, for example, between the processing of step S9 and the processing of step S10 shown in FIG. 12. In the second embodiment, for example, when the data acquisition unit 12 acquires the first ticket gate passage data D1, the route search unit 13 extracts route candidates with appropriate time sequences based on the timetable data D2, OD data D3, station data D4, line data D5, and ticket gate passage data D1. For example, the route search unit 13 extracts routes that arrive at the exit station between a predetermined time before the departure time and the departure time as route candidates. Then, the train allocation unit 14 calculates the number of people to allocate to one passenger based on the allocation index (diff) calculated by the above relational expression (1) (S9).

[0278] After step S9, in step S21, the allocation correction unit 141 determines whether the train corresponding to the route candidate satisfies predetermined attributes. The predetermined attributes include information about the train type (such as first train, paid train, limited express train, express train, rapid train, or local train) and unique information about the train cars (such as the number of cars, seat type (cross seat, long seat, or the like), and age of the cars). If the train corresponding to the route candidate satisfies the predetermined attributes (S21: Yes), the allocation correction unit 141 proceeds to step S22. On the other hand, if the train corresponding to the route candidate does not satisfy the predetermined attributes (S21: No), the allocation correction unit 141 proceeds to step S10 (see FIG. 12).

[0279] In step S22, the allocation correction unit 141 sets a correction coefficient K for correcting the number of people allocated calculated in step S9. The allocation correction unit 141 sets the correction coefficient K according to the attribute. For example, if the attribute is "first train," the allocation correction unit 141 sets the correction coefficient K to "1.5," and if the attribute is "paid train," the allocation correction unit 141 sets the correction coefficient K to "0.5." Furthermore, the allocation correction unit 141 may set the correction coefficient K based on the attribute, as well as the time period (commuting time, school commuting time, etc.), date and time (month, day of the week, season, etc.), congestion status, event information, etc. Furthermore, the allocation correction unit 141 may set the correction coefficient K according to a setting operation by the user.

[0280] In step S23, the allocation correction unit 141 corrects the number of people to be allocated calculated in step S9 using the correction coefficient K. For example, if the route candidates include a route for the first train, the allocation correction unit 141 multiplies the number of people to be allocated calculated for that route candidate by the correction coefficient K "1.5" (multiplies by 1.5). In addition, the allocation correction unit 141 subtracts the number of people to be allocated calculated for each route candidate for trains excluding the first train, and corrects the total to 1.0 people.

[0281] Furthermore, for example, if the route candidates include a route for a toll train, the allocation correction unit 141 multiplies the allocated number of passengers calculated for that route candidate by a correction coefficient K of "0.5" (multiplies by 0.5). Also, the allocation correction unit 141 adds up the allocated number of passengers calculated for each route candidate for trains excluding toll trains, and corrects the total to 1.0 passengers.

[0282] After step S23, the process proceeds to step S10 (see FIG. 12). The output unit 17 outputs the allocation results (allocated number of passengers, corrected allocated number of passengers) in which one passenger is allocated to multiple route candidates by the train allocation unit 14 and the allocation correction unit 141.

[0283] This makes it possible to predict passenger flow that reflects the intention of each passenger in selecting the train to board based on the train's attributes, thereby improving the accuracy of passenger flow prediction results for rail transport.

[0284] As described above, the passenger flow congestion prediction device 10 according to the second embodiment includes a data acquisition unit 12, a route search unit 13, a train allocation unit 14, and an allocation correction unit 141. The data acquisition unit 12 acquires ticket gate passage data D1 and timetable data D2 of the current train acquired from the automatic ticket gate 5. The route search unit 13 extracts route candidates based on the entry time of the passenger at the entry station where the passenger entered and the exit time of the passenger at the exit station where the passenger exited, and the departure time and arrival time of the current train. The train allocation unit 14 allocates one passenger to multiple route candidates according to an allocation index calculated based on the ticket gate passage data D1 and the timetable data D2. Furthermore, the allocation correction unit 141 corrects the number of people allocated to each of the multiple route candidates when the multiple route candidates include a route candidate for a train with a predetermined attribute.

[0285] For example, when the candidate routes include the first train, in the conventional configuration, there are cases where the congestion level of the first train is calculated to be low due to the long residence time of passengers at the entrance station or transfer station. However, with the above configuration, the congestion level of the first train can be estimated to be high, taking into account the possibility that passengers will board the first train even if the residence time is long.

[0286] For example, when a toll train is included in the route candidates, in the conventional configuration, the congestion level of the toll train may be calculated as high due to the long residence time of passengers at the entrance station or transfer station.However, with the above configuration, the congestion level of the toll train can be estimated as low, taking into account the possibility of boarding the toll train.

[0287] In this way, the passenger flow congestion prediction device 10 according to the second embodiment can calculate the number of people to be allocated according to the attributes of the trains included in the route candidates and estimate the congestion level, thereby improving the accuracy of the prediction results for passenger flow in rail transport compared to conventional configurations.

[0288] [Appendix 2 of the invention] The following is a summary of the invention extracted from the second embodiment. Note that the configurations and processing functions described in the following supplementary notes can be selected and combined as desired.

[0289] <Appendix 1> A passenger flow congestion prediction device that predicts passenger flow in rail transport, a route search unit that extracts route candidates based on at least one of the entrance time at the entrance station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entrance time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and timetable data of a current train including the departure time and arrival time of the current train; a train allocation unit that calculates an allocation index based on the ticket gate passage data and the timetable data of the current train, and allocates one passenger to a plurality of the route candidates according to the allocation index; an allocation correction unit that corrects the number of people assigned to each of the plurality of route candidates by the train allocation unit when the plurality of route candidates includes a route candidate for a train having a predetermined attribute; A passenger flow congestion prediction device equipped with:

[0290] <Appendix 2> the route search unit extracts, as the route candidate, a route that arrives at the exit station between a predetermined time before the departure time and the departure time; 2. A passenger flow congestion prediction device according to claim 1.

[0291] <Appendix 3> the route search unit extracts, as the route candidates, a predetermined number of routes that arrive at the exit station earlier than the departure time and whose arrival times are closest to the departure time; 3. A passenger flow congestion prediction device according to claim 1 or 2.

[0292] <Appendix 4> the train allocation unit calculates the allocation index based on the sum of the time difference between the entry time and the departure time and the time difference between the exit time and the arrival time in the route candidate. 4. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 3.

[0293] <Appendix 5> When a first train departing from the entrance station or a station between the entrance station and the exit station is included in the plurality of trains corresponding to the plurality of route candidates, the allocation correction unit increases the number of people allocated to the route candidate corresponding to the first train among the number of people allocated to each of the plurality of route candidates, and decreases the number of people allocated to the route candidate corresponding to another train other than the first train. 5. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 4.

[0294] <Appendix 6> The allocation correction unit multiplies the allocated number of passengers allocated to the route candidate corresponding to the first train by a correction coefficient greater than 1, and subtracts an increase in the allocated number of passengers from the allocated number of passengers allocated to the route candidate corresponding to the other train. 6. A passenger flow congestion prediction device according to claim 5.

[0295] <Appendix 7> when a plurality of trains corresponding to the plurality of route candidates include a toll train, the allocation correction unit decreases the number of people allocated to the route candidate corresponding to the toll train among the number of people allocated to each of the plurality of route candidates, and increases the number of people allocated to the route candidate corresponding to the toll train; 5. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 4.

[0296] <Appendix 8> the allocation correction unit multiplies the allocated number of passengers allocated to the route candidate corresponding to the toll train by a correction coefficient smaller than 1, and adds the amount of decrease in the allocated number of passengers to the allocated number of passengers allocated to the route candidate corresponding to the toll-free train. 8. A passenger flow congestion prediction device according to claim 7.

[0297] <Appendix 9> the allocation correction unit sets the correction coefficient based on a time period, a date and time, or a day of the week. 9. A passenger flow congestion prediction device according to claim 6 or 8.

[0298] <Appendix 10> the allocation correction unit sets the correction coefficient based on intervals between the departure times of the plurality of route candidates. 9. A passenger flow congestion prediction device according to claim 6 or 8.

[0299] <Appendix 11> The allocation correction unit When the plurality of route candidates include the route candidate for a train having the predetermined attribute and the route candidate for a train that departs from the entrance station before the train having the predetermined attribute, a process of correcting the assigned number of passengers is performed; When the plurality of route candidates includes the route candidate for the train having the predetermined attribute and does not include the route candidate for the train that departs from the entrance station before the train having the predetermined attribute, the process of correcting the assigned number of passengers is not executed. 11. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 10.

[0300] [Third embodiment] The configuration of a passenger flow congestion prediction device 10 according to a third embodiment of the present invention will be described. In the following, the description of the same configuration as that shown in the first and second embodiments will be omitted as appropriate.

[0301] As shown in FIG. 16 , in addition to the configuration shown in the first embodiment, the passenger flow congestion prediction device 10 according to the third embodiment further includes a data linking unit 142 that links passengers using paid trains to ticket gate passage data D1. Specifically, the data linking unit 142 links paid ticket sales record data D6 with the ticket gate passage data D1. Here, the paid ticket sales record data D6 is data related to passengers' purchases of express tickets, reserved seat tickets, and other tickets for riding paid trains (such as limited express trains), and includes at least information on the train number, boarding station, and disembarking station. For example, passengers may purchase express tickets at ticket vending machines or ticket counters in stations, or by accessing a website via the Internet. Furthermore, passengers may purchase express tickets using their IC cards, or they may purchase express tickets without using an IC card, using cash or a credit card, for example.

[0302] For example, if the trains corresponding to the multiple route candidates include both toll trains and free trains, passengers staying at an entrance station or a transfer station are less likely to board a toll train among the multiple trains and more likely to board a free train. Therefore, in the second embodiment described above, the allocation correction unit 141 reduces the number of people allocated to route candidates corresponding to toll trains and increases the number of people allocated to route candidates corresponding to free trains, based on the allocation index assigned by the train allocation unit 14 to each route candidate. In this way, if there is a toll train that runs at a similar time, speed, and stops to a toll train, the allocated number of people for the toll train will be lower, which may deviate from the number of people actually boarding the toll train, reducing the accuracy of congestion predictions for the toll train. Furthermore, toll trains often have a set capacity and are not permitted to carry more passengers than the capacity. However, the configuration of the second embodiment may result in more passengers than the capacity being allocated to the toll train.

[0303] In view of these circumstances, in the third embodiment, the paid sales performance data D6 is compared with the ticket gate passage data D1, passengers using paid trains are searched for in the ticket gate passage data D1, and one person is assigned to one route of the paid train, thereby improving the accuracy of congestion predictions for paid trains and also improving the accuracy of congestion predictions for surrounding trains.

[0304] A specific example of the process of linking the paid sales record data D6 with the ticket gate passage data D1 will be described.

[0305] Here, since the paid sales record data D6 contains information only on the toll section, for example, if there is a line that runs from Station A to Station B to Station C to Station D, even if the actual travel (ticket gate passage data D1) was from Station A to Station D, the paid sales record data D6 may only contain information on the travel from Station B to Station C. Also, depending on how a passenger purchases a limited express ticket, etc., the IC card ID (IC card number) may be known (e.g., when purchasing with an IC card) or may not be known (e.g., when purchasing with cash). Also, a single passenger may purchase two or more limited express tickets, etc. Furthermore, there may be cases where the IC card used to purchase a limited express ticket, etc. is not actually used to board the train on the day, or where the passenger did not use the train on the day at all. The IC card ID (IC card number) is an example of sales identification information (purchase identification information) in the present invention.

[0306] In this way, the paid sales result data D6 may include data in which the IC card ID is known and data in which the ID is unknown. Therefore, the data linking unit 142 performs a linking process for each of the data in which the IC card ID is known and the data in which the ID is unknown.

[0307] <Passenger flow congestion prediction method according to the third embodiment> 17 is a flowchart showing an example of the linking process executed by the data linking unit 142. The data linking unit 142 executes the following linking process for each piece of paid sales result data D6.

[0308] In step S31, the data linking unit 142 determines whether it is possible to acquire an IC card ID for each piece of paid sales performance data D6. If the paid sales performance data D6 is data purchased using an IC card, for example, the data linking unit 142 is able to acquire an ID corresponding to the paid sales performance data D6. On the other hand, if the paid sales performance data D6 is data purchased with cash at a ticket machine, for example, the data linking unit 142 is unable to acquire an ID corresponding to the paid sales performance data D6. If the data linking unit 142 is able to acquire an IC card ID corresponding to the paid sales performance data D6 (S31: Yes), the data linking unit 142 proceeds to step S32. On the other hand, if the data linking unit 142 is unable to acquire an IC card ID corresponding to the paid sales performance data D6 (S31: No), the data linking unit 142 proceeds to step S35.

[0309] In step S32, the data linking unit 142 determines whether or not there is any ticket gate passage data D1 that corresponds to the ID acquired in step S31 and that allows boarding a toll train. If there is any ticket gate passage data D1 that satisfies the above conditions, i.e., ticket gate passage data D1 that satisfies the entry time, exit time, and travel section (entry station → exit station) that allows boarding a toll train (S32: Yes), the data linking unit 142 proceeds to step S33, and if there is no ticket gate passage data D1 that satisfies the above conditions (S32: No), the data linking unit 142 proceeds to step S35.

[0310] In step S33, the data linking unit 142 determines whether the multiple pieces of paid sales record data corresponding to one ID include at least one piece of paid sales record data that cannot be linked to the ticket gate passage data D1. For example, when two limited express tickets have been purchased, if one of them can be linked to the ticket gate passage data D1 based on the ID and the other cannot be linked to the ticket gate passage data D1 (S33: Yes), the data linking unit 142 proceeds to step S35. On the other hand, when two limited express tickets have been purchased, if both can be linked to the ticket gate passage data D1 based on the ID (S33: No), the data linking unit 142 proceeds to step S34.

[0311] In step S34, the data linking unit 142 assigns one person to the most likely route candidate among the route candidates in the ticket gate passage data D1 that can board a toll train. Specifically, when the assigned number of people is calculated by the assignment process in embodiment 1 for each of the multiple route candidates that are ticket gate passage data D1 that can board a toll train and that correspond to the ticket gate passage data D1 that corresponds to the ID acquired in step S31, the data linking unit 142 determines the route candidate with the highest assigned number of people and assigns 1.0 person to that route candidate. The data linking unit 142 assigns one piece of paid sales performance data D6 to one piece of ticket gate passage data D1 based on the ID of the IC card.

[0312] In this way, the data linking unit 142 links the paid sales record data D6 to the ticket gate passage data D1 that is associated with the same ID as the ID associated with the paid sales record data D6, among the multiple ticket gate passage data D1. Furthermore, the data linking unit 142 assigns one passenger corresponding to the ticket gate passage data D1 linked with the paid sales record data D6 to a candidate route for the paid train that corresponds to the paid sales record data D6.

[0313] Here, the data linking unit 142 executes the processes of steps S35 to S38 for each of paid sales result data D6 (S31: No) (first target data) for which an IC card ID cannot be obtained, paid sales result data D6 (S32: No) (second target data) for which there is no ticket gate passage data D1 that can be used with the IC card ID corresponding to the paid sales result data D6, and paid sales result data D6 (S33: No) (third target data) for which two or more tickets have been purchased but at least one of them is not linked to the ticket gate passage data D1. Note that the data linking unit 142 aggregates paid sales result data D6 that meets the above conditions for each boarding section and train number of a paid train, and executes the processes of steps S35 to S38.

[0314] Paid sales record data D6 that does not have ticket gate passage data D1 that can be used with the IC card ID corresponding to the paid sales record data D6 includes, for example, data when a limited express ticket is purchased but the ticket is not used on the day, data when a ticket is used on another paid train, etc. Also, paid sales record data D6 for purchases of two or more tickets includes data that could not be linked to the ticket gate passage data D1 because multiple limited express tickets were purchased with one ID.

[0315] First, in step S35, the data linking unit 142 determines whether the number of passengers who can board the paid train is equal to or greater than the total number of the collected paid sales result data D6. If the number of passengers who can board the paid train is equal to or greater than the total number (S35: Yes), the data linking unit 142 proceeds to step S36.

[0316] In response to this, the data linking unit 142 excludes the paid sales result data D6 that exceeds the number of passengers that can board the paid train (S351). Note that the remaining paid sales result data D6 after the exclusion is subject to processing in step S36, which will be described later.

[0317] In step S36, the data linking unit 142 determines whether or not there is allocation information for allocating a route candidate. The allocation information is information that provides a hint as to which passenger (ticket gate passage data D1) the paid sales performance data D6 should be linked to, and is, for example, for the third target data, information on passengers who enter and exit the same station as the station associated with the IC card ID and at similar times (within ±X minutes of the entry time and exit time, respectively). If the allocation information is not present (S36: No), i.e., for the first target data and the second target data, the data linking unit 142 proceeds to step S37. On the other hand, if the allocation information is present (S36: Yes), i.e., for the third target data, the data linking unit 142 proceeds to step S38.

[0318] In step S37, for the first target data and the second target data, the data linking unit 142 assigns 1.0 passenger to each route candidate using the target paid train, starting with the passenger who is assigned with the highest ratio (allocated number of passengers) to the route candidate that uses the target paid train, for passengers who can board the route according to the section in the paid sales performance data D6.

[0319] In step S38, for the third target data, the data linking unit 142 searches for passengers who entered or exited the same station as the station associated with the IC card ID and at similar times (within ±X minutes of the entry time and exit time, respectively). If the number of passengers who can be the target is greater than the number of data in the paid sales performance data D6, the data linking unit 142 assigns 1.0 passengers to the route candidate using the target paid train, starting with the passenger who was assigned with the highest ratio (assigned number of passengers) to that route candidate.

[0320] In this way, when an ID is not associated with the paid sales record data D6, the data linking unit 142 determines one route candidate from among multiple route candidates corresponding to each of multiple ticket gate passage data D1 based on the number of passengers assigned to one passenger among multiple route candidates by the train allocation unit 14, and links the paid sales record data D6 to the ticket gate passage data D1 corresponding to the determined route candidate. For example, when there are multiple route candidates for a paid train, the data linking unit 142 links the paid sales record data D6 to the ticket gate passage data D1 corresponding to the route candidate with the highest number of assigned passengers.

[0321] Furthermore, when there are multiple pieces of paid sales result data D6 that are not associated with an ID, the data linking unit 142 links the paid sales result data D6 to the ticket gate passage data D1 corresponding to the route candidate in descending order of the number of assigned passengers when there are multiple route candidates for toll trains. Furthermore, when the data linking unit 142 links each of the multiple pieces of paid sales result data D6 to the ticket gate passage data D1 and there is ticket gate passage data D1 to which no paid sales result data D6 is associated, the data linking unit 142 assigns one passenger corresponding to the ticket gate passage data D1 to the remaining route candidates, excluding the route candidates for toll trains, from the multiple route candidates corresponding to the ticket gate passage data D1.

[0322] 18 and 19 show a specific example of the linking process. Here, the paid ticket sales record data D6 includes information (limited express ticket information) on the train number "311," the boarding station "Station A," and the disembarking station "Station B." Also, it is assumed that there are two pieces of paid ticket sales record data D6 (for example, sales record data for two limited express tickets) that could not be linked to the ticket gate passage data D1.

[0323] FIG. 18 shows ticket gate passage data D1 for passengers P1, P2, and P3, and the allocated number of passengers assigned to route candidates based on each ticket gate passage data D1. The allocated number of passengers is calculated, for example, by the method described in embodiment 1 (allocation index according to dwell time). Passengers P1, P2, and P3 are passengers who are allowed to board the paid train with train number "311." The train allocation unit 14 allocates allocated number of passengers to multiple route candidates for each of passengers P1, P2, and P3 based on the allocation index calculated based on the ticket gate passage data D1 and the timetable data D2 (see FIG. 18).

[0324] The data linking unit 142 links all paid sales result data D6 corresponding to paid trains to the ticket gate passage data D1. In the example shown in FIG. 18, the data linking unit 142 links the first of two paid sales result data D6 (train number "311," boarding station "Station A," and disembarking station "Station B") to the ticket gate passage data D1 (Station A → Station B) of passenger P1, who is the passenger of the route candidate with the highest number of allocated passengers among the route candidates including paid trains, i.e., passenger P1, who is allocated 0.8 passengers. Furthermore, as shown in FIG. 19, the data linking unit 142 assigns "1.0 passengers" to the route candidate with the train number "311" of the paid train, and assigns "0 passengers" to the route candidate with the train number "312" of another train.

[0325] Furthermore, the data linking unit 142 links the second of the two paid sales performance data D6 (train number "311", boarding station "Station A", disembarking station "Station B") to the ticket gate passage data D1 (Station A → Station C) of passenger P3 with the next highest allocated number of passengers among the route candidates that include paid trains, i.e., the allocated number of passengers "0.6 people". Furthermore, as shown in FIG. 19, the data linking unit 142 assigns "1.0 people" to the route candidates with train numbers "311" and "312" that correspond to paid trains, and assigns "0 people" to the route candidate with train number "315" of another train.

[0326] Furthermore, as a result of the above-described process, the two paid ticket sales record data D6 are linked to the two ticket gate passage data D1, respectively. When there is no paid ticket sales record data D6 that is not linked to the ticket gate passage data D1, passenger P2 will no longer be able to board the train number "311" corresponding to the ticket gate passage data D1. Therefore, as shown in FIG. 19 , the data linking unit 142 assigns "0 passengers" to the route candidates for the paid trains "311" and "312" corresponding to passenger P2, and adjusts the assigned numbers for the other trains, "313" and "314." Specifically, the data linking unit 142 recalculates the assigned numbers for the two route candidates, "311" and "312," based on their respective allocation indices. Here, the assigned number for each of the route candidates for train numbers "311" and "312" is "0.5 passengers."

[0327] As described above, the passenger flow congestion prediction device 10 according to the third embodiment includes a data acquisition unit 12, a route search unit 13, a train allocation unit 14, and an allocation correction unit 141. The data acquisition unit 12 acquires ticket gate passage data D1, timetable data D2 of the current train, and paid fare sales data D6 from the automatic ticket gate 5. The route search unit 13 extracts route candidates based on the entry time of the passenger at the entry station where the passenger entered and the exit time of the passenger at the exit station where the passenger exited, and the departure time and arrival time of the current train. The train allocation unit 14 allocates one passenger to multiple route candidates according to an allocation index calculated based on the ticket gate passage data D1 and the timetable data D2. Furthermore, the data linking unit 142 links the paid fare sales data D6 to the ticket gate passage data D1 when a route candidate for a paid train is included among the multiple route candidates.

[0328] For example, the data linking unit 142 links the paid sales record data D6 to the ticket gate passage data D1 among the multiple ticket gate passage data D1 that is associated with the same ID (user identification information) as the ID of the IC card associated with the paid sales record data D6.

[0329] Furthermore, for example, if an ID is not associated with the paid sales actual data D6, the data linking unit 142 determines one route candidate from among multiple route candidates corresponding to each of multiple ticket gate passage data D1 based on the number of people assigned to multiple route candidates by the train allocation unit 14 for one passenger, and links the paid sales actual data D6 to the ticket gate passage data D1 corresponding to the determined route candidate.

[0330] According to the above configuration, each piece of paid sales record data D6 can be linked to one piece of ticket gate passage data D1. This allows passengers who have purchased, for example, limited express tickets or reserved seat tickets to be reliably assigned to potential paid train routes. In particular, according to the above configuration, even if there is a free train that runs at a similar time, speed, and stops to the paid train, passengers can be appropriately assigned to the paid train, thereby improving the accuracy of congestion predictions for paid trains. Furthermore, improving the accuracy of congestion predictions for paid trains also makes it possible to simultaneously improve the accuracy of congestion predictions for free trains that run at similar time, speed, and stops to the paid train. Therefore, compared to conventional configurations, the accuracy of passenger flow predictions in rail transport can be improved.

[0331] In the third embodiment, a paid train is used as an example of the special train of the present invention, but the special train of the present invention is not limited to a paid train. The special train of the present invention includes, for example, trains that require special tickets, admission tickets, etc. (e.g., tourist trains). In other words, the special train of the present invention includes various trains for which sales performance data including train numbers, boarding stations, and disembarking stations can be obtained.

[0332] [Appendix 3 of the invention] The following is a summary of the invention extracted from the third embodiment. Note that the configurations and processing functions described in the following supplementary notes can be selected and combined as desired.

[0333] <Appendix 1> A passenger flow congestion prediction device that predicts passenger flow in rail transport, a route search unit that extracts route candidates based on at least one of the entrance time at the entrance station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entrance time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and timetable data of a current train including the departure time and arrival time of the current train; a train allocation unit that calculates an allocation index based on the ticket gate passage data and the timetable data of the current train, and allocates one passenger to a plurality of the route candidates according to the allocation index; a data linking unit that links sales performance data including the train number, boarding station, and alighting station of the specific train to the ticket gate passage data when the route candidate of a specific train is included in the plurality of route candidates; A passenger flow congestion prediction device equipped with:

[0334] <Appendix 2> the data linking unit, when the route candidate for the specific train is included in the plurality of route candidates, assigns one passenger corresponding to the ticket gate passage data linked with the sales performance data to the route candidate for the specific train; 2. A passenger flow congestion prediction device according to claim 1.

[0335] <Appendix 3> The data linking unit links the sales performance data to the ticket gate passage data associated with the same sales identification information as the sales identification information associated with the sales performance data, among the plurality of ticket gate passage data. 3. A passenger flow congestion prediction device according to claim 1 or 2.

[0336] <Appendix 4> the data linking unit assigns one passenger corresponding to the ticket gate passage data linked with the sales performance data to the route candidate of the specific train corresponding to the sales performance data. 4. A passenger flow congestion prediction device according to claim 3.

[0337] <Appendix 5> If the sales identification information is not associated with the sales performance data, the data linking unit determines one of the plurality of route candidates corresponding to each of the plurality of ticket gate passage data based on the number of passengers assigned to each of the plurality of route candidates by the train allocation unit, and links the sales performance data to the ticket gate passage data corresponding to the determined route candidate; 5. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 4.

[0338] <Appendix 6> When there are a plurality of route candidates for the specific train, the data linking unit links the sales performance data to the ticket gate passage data corresponding to the route candidate with the highest number of allocated passengers. 6. A passenger flow congestion prediction device according to claim 5.

[0339] <Appendix 7> When there are a plurality of sales performance data to which sales identification information is not associated, When there are a plurality of route candidates for the specific train, the data linking unit links the sales performance data to the ticket gate passage data corresponding to the route candidates in descending order of the number of allocated passengers. 7. A passenger flow congestion prediction device according to claim 5 or 6.

[0340] <Appendix 8> When each of the plurality of sales performance data is linked to the ticket gate passage data, and when there is ticket gate passage data to which the sales performance data is not linked, the data linking unit assigns one passenger corresponding to the ticket gate passage data to the remaining route candidates excluding the route candidate for the specific train from among the plurality of route candidates corresponding to the ticket gate passage data. 8. A passenger flow congestion prediction device according to claim 7.

[0341] <Appendix 9> the route search unit extracts, as the route candidate, a route that arrives at the exit station between a predetermined time before the departure time and the departure time; 9. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 8.

[0342] <Appendix 10> the route search unit extracts, as the route candidates, a predetermined number of routes that arrive at the exit station earlier than the departure time and whose arrival times are closest to the departure time; 10. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 9.

[0343] <Appendix 11> the train allocation unit calculates the allocation index based on the sum of the time difference between the entry time and the departure time and the time difference between the exit time and the arrival time in the route candidate. 11. A passenger flow congestion prediction device according to any one of Supplementary notes 1 to 10.

[0344] [Fourth embodiment] The configuration of a passenger flow congestion prediction device 10 according to a fourth embodiment of the present invention will be described. In the following, descriptions of the same configurations as those shown in the first, second, and third embodiments will be omitted as appropriate.

[0345] The passenger flow congestion prediction device 10 according to the fourth embodiment has, in addition to the configurations shown in the above-described embodiments, a configuration in which the train allocation unit 14 executes a process of allocating one passenger to each of a plurality of route candidates including a plurality of transfer stations.

[0346] Specifically, when there are one or more transfer stations between the entry station where the passenger entered and the exit station where the passenger exited, the train allocation unit 14 extracts multiple route candidates (hereinafter referred to as "transfer route candidates") that pass through the transfer stations based on the entry time at the entry station and the departure time at the exit station, and the departure time and arrival time of the current train.

[0347] Then, for each of the plurality of transfer route candidates extracted, the train allocation unit 14 calculates the number of allocations for allocating one passenger based on the allocation index (diff) calculated by the above relational expression (1), and allocates one passenger to each of the plurality of transfer route candidates.

[0348] Here, when there are a plurality of transfer stations in the route candidate, a method of allocating one passenger to one transfer route candidate via the transfer station with the shortest transfer time can be considered. For example, in the examples shown in FIGS. 20 and 21, consider the case where one passenger enters at Station A and exits at Station E. Also, here, as trains available for moving from Station A to Station E, there are an express train α and a local train β. In this case, the train allocation unit 14 extracts a route candidate R0 (see FIG. 20) that uses the local train β from Station A to Station E, a transfer route candidate R1 (see FIG. 21) that boards the express train α at Station A, transfers to the local train β at Station D, and moves to Station E, a transfer route candidate R2 (see FIG. 21) that boards the express train α at Station A, transfers to the local train β at Station C, and moves to Station E, and a transfer route candidate R3 (see FIG. 21) that boards the express train α at Station A, transfers to the local train β at Station B, and moves to Station E.

[0349] In the above example, since there are 3 transfer stations (Station B, Station C, Station D) where transfer is possible between Station A and Station E, there are 3 transfer route candidates R1, R2, and R3 as transfer route candidates. In this case, the train allocation unit 14 calculates the transfer time (the difference between the arrival time of the train before transfer and the departure time of the train after transfer) at each transfer station. Here, the transfer time for transferring from the express train α to the local train β at Station D is t1 seconds, the transfer time for transferring from the express train α to the local train β at Station C is t2 seconds, and the transfer time for transferring from the express train α to the local train β at Station B is t3 seconds, and it is assumed that the relationship t1 < t2 < t3 is satisfied.

[0350] The train allocation unit 14 determines the transfer route candidate with the shortest transfer time and allocates one passenger to that transfer route candidate. In this case, because the transfer time t1 at Station D is shortest, the train allocation unit 14 determines the transfer route candidate R1, which involves transferring at Station D, from the three transfer route candidates (see FIG. 20). Then, for each of the route candidate R0 without a transfer (a route candidate using local train β from Station A to Station E) and the transfer route candidate R1 with a transfer, the train allocation unit 14 calculates the allocation number of passengers to be allocated to one passenger based on the allocation index (diff), and allocates one passenger to each route candidate. For example, the train allocation unit 14 allocates "0.6 people" to the route candidate R0 and "0.4 people" to the transfer route candidate R1.

[0351] In the above method, passengers are not assigned to the transfer route candidates R2 and R3 (see Figure 21), so it is difficult to reflect actual usage patterns, such as passengers who transfer at a station close to the departure station regardless of transfer time, passengers who transfer at a station close to the arrival station, or passengers who decide on a transfer station based on the station structure (ease of transfer, etc.), and there is a risk that the accuracy of the passenger flow prediction results will decrease.

[0352] Therefore, the train allocation unit 14 in this embodiment performs a process of allocating one passenger to one or more transfer route candidates extracted from the multiple transfer route candidates according to specified conditions when the multiple route candidates include multiple transfer route candidates that pass through a transfer station.

[0353] Specifically, the train allocation unit 14 sets a weight according to a predetermined condition for each of a plurality of transfer route candidates, and allocates one passenger to one or more transfer route candidates extracted based on the set weight. Specific examples (Specific Examples 1 to 4) of weight setting methods will be described below.

[0354] <Example 1> The train allocation unit 14 according to the first specific example sets a weight k1 corresponding to the length of transfer time at a transfer station to each of a plurality of transfer route candidates.

[0355] Figure 22 shows a specific example 1 of the method for setting the weight k1. Here, as shown in Figure 21, it is assumed that there are transfer stations B, C, and D between Station A and Station E as transfer stations. The train allocation unit 14 sets, for example, a weight k1 corresponding to the transfer time for each transfer route candidate. For example, the train allocation unit 14 sets a smaller value of the weight k1 for a shorter transfer time at the transfer station and a larger value of the weight k1 for a longer transfer time. Note that the train allocation unit 14 may set the transfer time itself as the weight k1, or may set a value corresponding to the ratio of the transfer times at each transfer station as the weight k1. The weight k1 is an index (setting parameter) for preferentially allocating passengers to transfer route candidates that allow for transfer in a short time.

[0356] In the examples shown in Figures 21 and 22, the case where the transfer time "t2 seconds" for transferring from the express train α to the local train β at Station C is the shortest, the transfer time "t3 seconds" for transferring from the express train α to the local train β at Station B is the next shortest, and the transfer time "t1 seconds" for transferring from the express train α to the local train β at Station D is the longest (t2 < t3 < t1) is shown. In this case, the train allocation unit 14 sets a weight "40" corresponding to the transfer time "t1 seconds" at Station D for the transfer route candidate R1, sets a weight "20" corresponding to the transfer time "t2 seconds" at Station C for the transfer route candidate R2, and sets a weight "30" corresponding to the transfer time "t3 seconds" at Station B for the transfer route candidate R3.

[0357] <Specific Example 2> The train allocation unit 14 according to Specific Example 2 sets a weight corresponding to the positional relationship of the transfer station with respect to the entry station and the exit station for each of the plurality of transfer route candidates.

[0358] FIG. 23 shows a specific example 2 of a method for setting the weight k2. The train allocation unit 14 sets the weight k2 corresponding to, for example, a transfer location to the transfer route candidate. For example, the closer the train is to the entry station, the smaller the weight k2 is set to, and the closer the train is to the exit station, the larger the weight k2 is set to. Note that the train allocation unit 14 may set the weight k2 to a value corresponding to the distance from the entry station and the exit station, or may set the weight k2 to a value corresponding to the order of stations from the entry station and the exit station. The weight k2 is an index (setting parameter) for preferentially allocating passengers to transfer route candidates that allow early entry and transfer.

[0359] In the example shown in FIG. 23, the train allocation unit 14 assigns a weight of "10" to the transfer route candidate R3 in which a transfer is made at station B, which is closest to the entrance station "station A." The train allocation unit 14 assigns a weight of "20" to the transfer route candidate R2 in which a transfer is made at station C, which is the second closest to the entrance station. The train allocation unit 14 assigns a weight of "40" to the transfer route candidate R1 in which a transfer is made at station D, which is farthest from the entrance station (closest to the exit station). The train allocation unit 14 may also assign the weight k2 based on the transfer time at the transfer station. For example, the train allocation unit 14 may assign the weight k2 by increasing or decreasing the weight k1, which corresponds to the transfer time, based on the weight k1 (see FIG. 22). Specifically, the train allocation unit 14 assigns the weight k2 of "10" to the transfer route candidate R3 by subtracting a predetermined value from the weight k1 of "30."

[0360] <Example 3> FIG. 24 shows a specific example 3 of a method for setting a weight. As in the specific example 2, the train allocation unit 14 sets a weight k3 corresponding to, for example, a transfer location to the transfer route candidate. For example, the closer the train is to the entry station, the greater the weight k3 is set to, and the closer the train is to the exit station, the smaller the weight k3 is set to. Note that the train allocation unit 14 may set the weight k3 to a value corresponding to the distance from the entry station and the exit station, or may set the weight k3 to a value corresponding to the order of stations from the entry station and the exit station. The weight k3 is an index (setting parameter) for preferentially allocating passengers to transfer route candidates that allow passengers to enter and transfer later.

[0361] In the example shown in FIG. 24, the train allocation unit 14 assigns a weight of "10" to the transfer route candidate R1 in which a transfer occurs at station D, which is closest to the exit station "station E," assigns a weight of "20" to the transfer route candidate R2 in which a transfer occurs at station C, which is the second closest to the exit station, and assigns a weight of "30" to the transfer route candidate R3 in which a transfer occurs at station B, which is farthest from the exit station (closest to the entrance station). As with the weight k2, the train allocation unit 14 may set the weight k3 by increasing or decreasing the weight k1 (see FIG. 22) corresponding to the transfer time as a reference. Specifically, for the transfer route candidate R1, the train allocation unit 14 assigns a weight k3 of "10" by subtracting a predetermined value from the weight k1 of "40."

[0362] <Example 4> The train allocation unit 14 according to the fourth specific example sets a weight k4 corresponding to station information relating to transfer stations for each of a plurality of transfer route candidates.

[0363] FIG. 25 shows a fourth specific example of a method for setting the weight k4. The train allocation unit 14 sets the weight k4 corresponding to, for example, the structure of the station to the transfer route candidate. The station structure includes, for example, station-specific information (station information) such as the length and width of the passageway when transferring from express train α to local train β, and the location and structure of elevators, escalators, and stairs. For example, the train allocation unit 14 evaluates the ease of transfer at a transfer station based on the station information, and sets the weight k4 to a smaller value as the transfer is easier (higher evaluation value), and sets the weight k4 to a larger value as the transfer is more difficult (lower evaluation value). Note that the train allocation unit 14 may set the weight k4 to a value corresponding to the length of the passageway, or may set the weight k4 to a value corresponding to the evaluation of each piece of unique information. The weight k4 is an index (setting parameter) for preferentially allocating passengers to transfer route candidates that allow for easy transfers at transfer stations.

[0364] In the example shown in FIG. 25, the train allocation unit 14 assigns a weight of "10" to the transfer route candidate R2 in which a transfer is made at station C, where the transfer is easiest, a weight of "30" to the transfer route candidate R3 in which a transfer is made at station B, where the transfer is next easiest, and a weight of "40" to the transfer route candidate R1 in which a transfer is made at station D, where the transfer is most difficult. The train allocation unit 14 may set the weight k4 by increasing or decreasing the weight k1 based on the weight k1 (see FIG. 22) corresponding to the transfer time. Specifically, for the transfer route candidate R2, the train allocation unit 14 assigns the weight k4 of "10" by subtracting a predetermined value from the weight k1 of "20".

[0365] As described above, the train allocation unit 14 sets weights k1 to k4 corresponding to a plurality of indices for each transfer route candidate. Note that the weights are not limited to the four weights k1 to k4 described above, and may further include weights corresponding to other indices. For example, a weight may be set based on an index as to whether or not trains of other companies share the same line at a transfer station.

[0366] <Allocation process> The train allocation unit 14 sets weights to a plurality of transfer route candidates that pass through transfer stations, extracts transfer route candidates to be allocated based on the set weights, and allocates the number of people to the extracted transfer route candidates.

[0367] 26 and 27 show specific examples of allocation processing using weights k1 and k2. As a transfer route candidate corresponding to weight k1, the train allocation unit 14 extracts transfer route candidate R2 (k1=20) having the smallest weight k1 (shortest transfer time) from among transfer route candidate R1 for transferring at station D, transfer route candidate R2 for transferring at station C, and transfer route candidate R3 for transferring at station B. Furthermore, as a transfer route candidate corresponding to weight k2, the train allocation unit 14 extracts transfer route candidate R3 (k2=10) having the smallest weight k2 (closest to the entrance station) from among transfer route candidate R1, transfer route candidate R2, and transfer route candidate R3.

[0368] The train allocation unit 14 allocates three route candidates, including the extracted transfer route candidates R2 and R3 and the route candidate R0 of the local train β without transfers, to each route candidate, the allocated number of passengers calculated based on the allocation index (diff). For example, based on the allocation index (diff), the train allocation unit 14 allocates "0.6 passengers" to the route candidate R0 of the local train β and "0.4 passengers" to the transfer route candidates R2 and R3. Furthermore, the train allocation unit 14 allocates the "0.4 passengers" allocated to the transfer route candidates R2 and R3 to each of the transfer route candidates R2 and R3. For example, if the congestion prediction concept places importance on routes that allow passengers to enter and transfer early, the train allocation unit 14 allocates a larger number of passengers to the transfer route candidate R3 with a transfer at Station B. For example, as shown in FIG. 27, the train allocation unit 14 allocates "0.3 people" to the transfer route candidate R3, and allocates the remaining "0.1 people" to the transfer route candidate R2.

[0369] Furthermore, when prioritizing routes with short transfer times as a congestion prediction concept, the train allocation unit 14 allocates a larger number of people to transfer route candidate R2 for transfers at Station C. For example, the train allocation unit 14 allocates "0.3 people" to transfer route candidate R2 and the remaining "0.1 people" to transfer route candidate R3.

[0370] The method of allocation to the multiple transfer route candidates is not limited to the above method. For example, the train allocation unit 14 may equally allocate "0.2 people" to each of the transfer route candidates R2 and R3.

[0371] Furthermore, the train allocation unit 14 may allocate numbers of passengers to each of the transfer route candidates R2 and R3 according to the weights k1 and k2. Specifically, the train allocation unit 14 allocates passengers such that the smaller the weight, the greater the number of passengers allocated. For example, since the weight k1 of the transfer route candidate R2 is set to "20" and the weight k2 of the transfer route candidate R3 is set to "10," the train allocation unit 14 allocates passengers such that the number of passengers allocated to the transfer route candidate R3 is greater than the number of passengers allocated to the transfer route candidate R2. That is, the train allocation unit 14 allocates passengers to each of the transfer route candidates R2 and R3 according to the ratio (proportion) of the weights k1 and k2. For example, the train allocation unit 14 may calculate the number of passengers allocated to the transfer route candidate R3 using the formula 0.4 × (k1 / (k1 + k2)) and the number of passengers allocated to the transfer route candidate R2 using the formula 0.4 × (k2 / (k1 + k2)).

[0372] Here, the method of calculating the number of people to be allocated according to the weights can be generalized as follows. FIG. 28 shows a transfer route candidate R1 for transferring at station D, a transfer route candidate R2 for transferring at station C, and a transfer route candidate R3 for transferring at station B, along with weights k1, k2, and k3 set for each transfer route candidate. For example, the train allocation unit 14 extracts the transfer route candidate R2 (k1=k12) as the transfer route candidate corresponding to the weight k1, extracts the transfer route candidate R3 (k2=k23) as the transfer route candidate corresponding to the weight k2, and extracts the transfer route candidate R1 (k3=k31) as the transfer route candidate corresponding to the weight k3. Then, the train allocation unit 14 calculates the number of people to be allocated to each of the transfer route candidates R1, R2, and R3 based on the weights k12, k23, and k31. Specifically, the train allocation unit 14 calculates the number of passengers to be allocated to transfer route candidate R1 using the formula 0.4 × (k31 × p1), calculates the number of passengers to be allocated to transfer route candidate R2 using the formula 0.4 × (k12 × p2), and calculates the number of passengers to be allocated to transfer route candidate R3 using the formula 0.4 × (k23 × p3) (see FIG. 29). p1 to p3 are allocation coefficients, and are set, for example, according to the ratios (proportions) of the weights k12, k23, and k31.

[0373] As described above, in the specific example 1, the train allocation unit 14 may set the weight k1 to a smaller value as the transfer time is shorter, and may allocate one passenger to the transfer route candidate with the smallest weight k1. Furthermore, in the specific example 2, the train allocation unit 14 may set the weight k2 to a smaller value as the transfer station is closer to the entrance station, and may allocate one passenger to the transfer route candidate with the smallest weight k2. Furthermore, in the specific example 3, the train allocation unit 14 may set the weight k3 to a smaller value as the transfer station is closer to the exit station, and may allocate one passenger to the transfer route candidate with the smallest weight k3. Furthermore, in the specific example 4, the train allocation unit 14 may evaluate the ease of transferring at the transfer station based on the station information of the transfer station, and may set the weight k4 to a smaller value as the transfer is easier, and may allocate one passenger to the transfer route candidate with the smallest weight k4.

[0374] The train allocation unit 14 also allocates one passenger to each of the multiple route candidates and the multiple transfer route candidates extracted based on the weights according to the allocation index, and further allocates the number of passengers allocated to the multiple transfer route candidates to each of the multiple transfer route candidates according to the weights.The train allocation unit 14 also extracts transfer route candidates to be allocated based on the multiple weights that have been set, and allocates the allocated number of passengers to the transfer route candidates.The train allocation unit 14 may use all of the weights k1 to k4 described above to extract four transfer route candidates corresponding to each weight, and allocate the allocated number of passengers.The train allocation unit 14 may also allocate the allocated number of passengers using one or more weights selected by the user from the multiple weights according to the congestion prediction philosophy.

[0375] As another example of the allocation process, the train allocation unit 14 may extract multiple transfer route candidates for one weight. For example, in the example shown in FIG. 26, the train allocation unit 14 may extract a transfer route candidate R2 with a weight k1 of "20" and a transfer route candidate R3 with a weight k1 of "30" as transfer route candidates corresponding to the weight k1. In this case, the train allocation unit 14 may calculate the number of people to be allocated to each of the transfer route candidates R2 and R3 according to the weight. For example, the train allocation unit 14 may allocate 0.3 people to the transfer route candidate R2 and 0.1 people to the transfer route candidate R3.

[0376] <Passenger flow congestion prediction method according to the fourth embodiment> The passenger flow congestion prediction device 10 of the fourth embodiment executes the passenger flow congestion prediction method in accordance with the flowcharts shown in FIGS.

[0377] The flowchart shown in FIG. 30 is executed, for example, between the processing of step S9 and the processing of step S10 shown in FIG. 12. In the fourth embodiment, for example, when the data acquisition unit 12 acquires the first ticket gate passage data D1, the route search unit 13 extracts route candidates with appropriate time sequences based on the timetable data D2, OD data D3, station data D4, line data D5, and ticket gate passage data D1. For example, the route search unit 13 extracts routes that arrive at the exit station between a predetermined time before the departure time and the departure time as route candidates. Then, the train allocation unit 14 calculates the number of people to allocate to one passenger based on the allocation index (diff) calculated by the above relational expression (1) (S9).

[0378] After step S9, in step S41, the train allocation unit 14 determines whether the extracted route candidates include multiple transfer route candidates that pass through a transfer station. For example, in the example shown in FIG. 21, there are three transfer stations, "Station B," "Station C," and "Station D," between the entrance station "Station A" and the exit station "Station E," and there are transfer route candidates R1, R2, and R3 that pass through each transfer station. If the train allocation unit 14 determines that the extracted route candidates include multiple transfer route candidates (S41: Yes), it proceeds to step S42. On the other hand, if the train allocation unit 14 determines that the extracted route candidates do not include multiple transfer route candidates (S41: No), it proceeds to step S10 (see FIG. 12).

[0379] In step S42, the train allocation unit 14 extracts transfer route candidates. In the example of Fig. 21, the train allocation unit 14 extracts three transfer route candidates R1, R2, and R3.

[0380] In step S43, the train allocation unit 14 sets a weight to each transfer route candidate. Specifically, the train allocation unit 14 sets a plurality of weights according to a plurality of indicators, for example, at least one of the weights k1 to k4 described above, to each transfer route candidate. Here, the weights k1 and k2 are used as an example.

[0381] For example, in the example shown in FIG. 21, the train allocation unit 14 assigns a weight of "40" (see FIG. 22) to the transfer route candidate R1 for transfers at station D according to the transfer time t1, assigns a weight of "20" (see FIG. 22) to the transfer route candidate R2 for transfers at station C according to the transfer time t2 (see FIG. 21), and assigns a weight of "30" (see FIG. 22) to the transfer route candidate R3 for transfers at station B according to the transfer time t3 (see FIG. 21). That is, the train allocation unit 14 assigns a smaller value to the weight k1 at the transfer station as the transfer time is shorter, and assigns a larger value to the weight k1 as the transfer time is longer. In this case, the train allocation unit 14 extracts the transfer route candidate R2 (k1=20) with the smallest weight k1 (shortest transfer time) as the transfer route candidate corresponding to the weight k1 (see FIG. 26).

[0382] Furthermore, the train allocation unit 14 assigns a weight of "10" (see FIG. 23) to the transfer route candidate R3 for transferring at station B, which is closest to the entrance station "station A," assigns a weight of "20" (see FIG. 23) to the transfer route candidate R2 for transferring at station C, which is the next closest to the entrance station, and assigns a weight of "40" (see FIG. 23) to the transfer route candidate R1 for transferring at station D, which is farthest from the entrance station (closest to the exit station). That is, the train allocation unit 14 assigns a smaller value to the weight k2 the closer the train is to the entrance station, and a larger value to the closer the train is to the exit station. In this case, the train allocation unit 14 extracts the transfer route candidate R3 (k2=10) with the smallest weight k2 (which allows the fastest transfer) as the transfer route candidate corresponding to the weight k2 (see FIG. 26).

[0383] In this way, the train allocation unit 14 extracts transfer route candidates according to each weight. Note that the train allocation unit 14 may extract multiple transfer route candidates for one weight. For example, for weight k1, the train allocation unit 14 may extract transfer route candidate R2 with the smallest weight k1 and transfer route candidate R3 with the second smallest weight k1.

[0384] In step S34, the train allocation unit 14 reallocates the allocated number of passengers calculated in step S9 to multiple transfer route candidates. For example, in the example shown in FIGS. 26 and 27, in step S9, the train allocation unit 14 allocates "0.6 passengers" for one passenger to route candidate R0 of local train β and "0.4 passengers" to the transfer route candidates. In this case, in step S34, the train allocation unit 14 reallocates "0.4 passengers" to each of transfer route candidates R2 and R3. For example, when prioritizing a route that allows passengers to enter and transfer quickly, the train allocation unit 14 allocates "0.3 passengers" to transfer route candidate R3 and "0.1 passengers" to transfer route candidate R2 (see FIG. 27). On the other hand, when prioritizing a route with a short transfer time, the train allocation unit 14 allocates "0.3 passengers" to transfer route candidate R2 and "0.1 passengers" to transfer route candidate R3. In another embodiment, the train allocation unit 14 may equally allocate "0.2 people" to each of the transfer route candidates R2 and R3. Furthermore, the train allocation unit 14 may allocate the number of people to each of the transfer route candidates R2 and R3 according to the ratio of the weights k1 and k2.

[0385] After step S34, the process proceeds to step S10 (see FIG. 12). In this way, the train allocation unit 14 executes the processes of steps S31 to S34 every time it extracts a plurality of transfer route candidates.

[0386] As described above, in the passenger flow congestion prediction device 10 according to the fourth embodiment, the route search unit 13 extracts route candidates based on at least one of the entry time at the entry station where the passenger entered and the exit time at the exit station where the passenger exited, which are included in the ticket gate passage data D1 acquired from the automatic ticket gate 5, and the timetable data D2 of the current train. The train allocation unit 14 calculates an allocation index based on the ticket gate passage data D1 and the timetable data D2 of the current train, and allocates one passenger to multiple route candidates according to the allocation index. When multiple route candidates include multiple transfer route candidates that pass through transfer stations, the train allocation unit 14 allocates one passenger to one or more transfer route candidates extracted from the multiple transfer route candidates according to predetermined conditions.

[0387] According to the above configuration, when there are multiple transfer route candidates, one passenger can be assigned to each of the transfer route candidates, thereby preventing bias in assigning passengers to a specific transfer route candidate. For example, passengers can be assigned to multiple transfer route candidates based on predetermined conditions corresponding to various indicators such as transfer time and transfer location. This makes it possible to improve the accuracy of passenger flow prediction results for rail transport.

[0388] The train allocation unit 14 may also set a weight according to a predetermined condition for each of a plurality of transfer route candidates, and allocate one passenger to one or more transfer route candidates extracted based on the set weight. By setting weights in this way, passengers can be allocated to each of a plurality of transfer route candidates, and the prediction concept can be easily changed by adjusting the weights. For example, it is possible to make a prediction that emphasizes transfer time, a prediction that emphasizes transfer locations, or a prediction that emphasizes ease of transfer.

[0389] Specifically, the train allocation unit 14 may set a weight (weight k1) for each of the multiple transfer route candidates according to the length of transfer time at the transfer station. For example, the train allocation unit 14 may set a smaller value for the weight k1 as the transfer time becomes shorter, and may allocate one passenger to the transfer route candidate with the smallest weight k1.

[0390] Furthermore, the train allocation unit 14 may set a weight (weight k2) for each of the multiple transfer route candidates according to the positional relationship of the transfer station with respect to the entrance station and the exit station. For example, the train allocation unit 14 may set a smaller value for the weight k2 as the transfer station is closer to the entrance station, and allocate one passenger to the transfer route candidate with the smallest weight k2. Furthermore, the train allocation unit 14 may set a smaller value for the transfer station as the transfer station is closer to the exit station, and allocate one passenger to the transfer route candidate with the smallest weight k3.

[0391] Furthermore, the train allocation unit 14 may set a weight k4 for each of a plurality of transfer route candidates according to station information about the transfer stations. For example, the train allocation unit 14 may evaluate the ease of transfer at a transfer station based on the station information about the transfer station, set the weight k4 to a smaller value as the transfer becomes easier, and allocate one passenger to the transfer route candidate with the smallest weight k4.

[0392] In addition, the train allocation unit 14 may allocate one passenger to multiple route candidates and multiple transfer route candidates extracted based on the weights according to the allocation index, and further allocate the number of people allocated to the multiple transfer route candidates to each of the multiple transfer route candidates according to the weights.

[0393] [Other embodiments] As another embodiment of the fourth embodiment, the train allocation unit 14 may include trains of other companies that mutually enter each other's routes as route candidates. For example, FIG. 31 shows the company's express trains α1 and α2 and the other company's mutually through train γ. Station D is a connecting station to the other company's route. For example, a passenger using the express train α2 changes to the mutually through train γ that enters the other company's route at Station D. Also, a passenger using the express train α1 changes to the mutually through train γ at Station C or Station B. In this example, the train allocation unit 14 extracts a route candidate R0 that connects from Station A to Station D and enters the other company's route, a transfer route candidate R1 that changes at Station C, connects to Station D, and enters the other company's route, a transfer route candidate R2 that changes at Station B, connects to Station D, and enters the other company's route, and a transfer route candidate R3 that changes at Station D and enters the other company's route, and allocates one passenger. For example, the train allocation unit 14 allocates "0.6 persons" to the route candidate R0, "0.2 persons" to the transfer route candidate R3, the remaining "0.05 persons" to the transfer route candidate R1, and "0.15 persons" to the transfer route candidate R2 (see FIG. 32). Note that the train allocation unit 14 may allocate to each transfer route candidate according to indicators (weights) such as transfer time, transfer location, and ease of transfer.

[0394] As another embodiment of the fourth embodiment, among a plurality of transfer route candidates, the train allocation unit 14 may extract a transfer route candidate for the allocation target based on the transfer time at the reference station, and allocate the number of allocated persons to the extracted transfer route candidate. For example, in the example shown in FIG. 21, the train allocation unit 14 sets Station C, at which the transfer time (t2 < t3 < t1) is the shortest, as the reference station among the plurality of transfer stations "Station B", "Station C", and "Station D". The train allocation unit 14 sets a determination threshold time Tth (Tth = t2 + Δt) obtained by adding a predetermined time Δt to the transfer time t2 at the reference station "Station C". Then, the train allocation unit 14 extracts, from among the plurality of transfer route candidates, a transfer route candidate whose transfer time at the transfer station is less than the determination threshold time Tth. Note that the predetermined time Δt may be set and changed by the user of the passenger flow congestion prediction device 10.

[0395] For example, the train allocation unit 14 extracts transfer route candidates R2 and R3 when the transfer time of transfer route candidates R2 and R3 among transfer route candidates R1, R2, and R3 is less than the determination threshold time Tth, and excludes transfer route candidate R1 from the transfer route candidates to be allocated when the transfer time of transfer route candidate R1 is equal to or greater than the determination threshold time Tth. As a result, even if a transfer route candidate has a long transfer time, it can be excluded from the allocation candidates because it is unlikely that passengers will actually use it. This makes it possible to further improve the accuracy of passenger flow prediction results.

[0396] In another embodiment, the train allocation unit 14 may extract, from among multiple transfer route candidates, transfer route candidates whose transfer time is less than a predetermined time (determination threshold time), allocate the number of passengers to the extracted transfer route candidates, and exclude transfer route candidates whose transfer time is equal to or greater than the determination threshold time from the transfer route candidates to be allocated. Even in the above configuration, for example, routes with excessively long transfer times can be excluded from the candidates to be allocated because they are unlikely to be used by passengers. Note that the determination threshold time may be set or changed by the user of the passenger flow congestion prediction device 10.

[0397] The passenger flow congestion prediction device according to the present invention may be a combination of at least two of the above-described first, second, third and fourth embodiments.

[0398] [Appendix 4 of the invention] The following is a summary of the invention extracted from the fourth embodiment. Note that the configurations and processing functions described in the following supplementary notes can be selected and combined as desired.

[0399] <Appendix 1> A passenger flow congestion prediction device that predicts passenger flow in rail transport, a route search unit that extracts route candidates based on at least one of the entrance time at the entrance station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entrance time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and timetable data of a current train including the departure time and arrival time of the current train; a train allocation unit that calculates an allocation index based on the ticket gate passage data and the timetable data of the current train, and allocates one passenger to a plurality of the route candidates according to the allocation index; Equipped with The train allocation unit is a passenger flow congestion prediction device that allocates one passenger to one or more candidate transfer routes extracted from the multiple candidate transfer routes according to predetermined conditions when the multiple candidate routes include multiple candidate transfer routes that pass through a transfer station.

[0400] <Appendix 2> the train allocation unit sets a weight according to the predetermined condition for each of the plurality of transfer route candidates, and allocates one of the passengers to one or more transfer route candidates extracted based on the set weight. 2. A passenger flow congestion prediction device according to claim 1.

[0401] <Appendix 3> the train allocation unit sets a weight for each of the plurality of transfer route candidates according to the length of transfer time at the transfer station; 3. A passenger flow congestion prediction device according to claim 2.

[0402] <Appendix 4> the train allocation unit sets the weight to a smaller value as the transfer time is shorter, and allocates one passenger to the transfer route candidate with the smallest weight. 4. A passenger flow congestion prediction device according to claim 3.

[0403] <Appendix 5> the train allocation unit sets a weight for each of the plurality of transfer route candidates according to a positional relationship of the transfer station with respect to the entry station and the exit station; 5. A passenger flow congestion prediction device according to any one of Supplementary notes 2 to 4.

[0404] <Appendix 6> the train allocation unit sets the weight to a smaller value as the transfer station is closer to the entrance station, and allocates one passenger to the transfer route candidate with the smallest weight; 6. A passenger flow congestion prediction device according to claim 5.

[0405] <Appendix 7> the train allocation unit sets the weight to a smaller value as the transfer station is closer to the exit station, and allocates one passenger to the transfer route candidate with the smallest weight; 7. A passenger flow congestion prediction device according to claim 5 or 6.

[0406] <Appendix 8> the train allocation unit sets a weight for each of the plurality of transfer route candidates according to station information related to the transfer station; 8. A passenger flow congestion prediction device according to any one of Supplementary notes 2 to 7.

[0407] <Appendix 9> the train allocation unit evaluates the ease of transfer at the transfer station based on the station information of the transfer station, sets the weight to a smaller value as the transfer becomes easier, and allocates one passenger to the transfer route candidate with the smallest weight; 9. A passenger flow congestion prediction device according to claim 8.

[0408] <Appendix 10> the train allocation unit allocates one passenger to the plurality of route candidates and the plurality of transfer route candidates extracted based on the weights according to the allocation index, and further allocates the number of passengers allocated to the plurality of transfer route candidates to each of the plurality of transfer route candidates according to the weights; 10. A passenger flow congestion prediction device according to any one of Supplementary notes 2 to 9. [Explanation of symbols]

[0409] 2: Input device 3:Display device 4: Data Server 5: Automatic ticket gate 10: Passenger flow congestion prediction device 11: Storage section 12: Data acquisition section 13: Route search section 14: Train Allocation Department 15: First congestion estimation unit 16: Second congestion estimation unit 17: Output section 20: Control section 31: Control unit 141: Allocation correction unit 142: Data linking section 311: Acquisition processing unit 312: Reception processing unit 313: Display processing unit D1: Ticket gate passage data D2: Diameter data D3:OD data D4: Station data D5: Route data D6: Paid sales performance data

Claims

1. A passenger flow congestion prediction device that predicts passenger flow in rail transport, a route search unit that extracts route candidates based on at least one of the entrance time at the entrance station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entrance time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and timetable data of a current train including the departure time and arrival time of the current train; a train allocation unit that calculates an allocation index based on the ticket gate passage data and the timetable data of the current train, and allocates one passenger to a plurality of the route candidates according to the allocation index; Equipped with The train allocation unit is a passenger flow congestion prediction device that allocates one passenger to one or more transfer route candidates extracted from the multiple transfer route candidates according to specified conditions when the multiple route candidates include multiple transfer route candidates that pass through a transfer station.

2. the train allocation unit sets a weight according to the predetermined condition for each of the plurality of transfer route candidates, and allocates one of the passengers to one or more transfer route candidates extracted based on the set weight. The passenger flow congestion prediction device according to claim 1.

3. the train allocation unit sets a weight for each of the plurality of transfer route candidates according to the length of transfer time at the transfer station; The passenger flow congestion prediction device according to claim 2.

4. the train allocation unit sets the weight to a smaller value as the transfer time is shorter, and allocates one passenger to the transfer route candidate with the smallest weight. The passenger flow congestion prediction device according to claim 3.

5. the train allocation unit sets a weight for each of the plurality of transfer route candidates according to a positional relationship of the transfer station with respect to the entry station and the exit station. The passenger flow congestion prediction device according to claim 2.

6. the train allocation unit sets the weight to a smaller value as the transfer station is closer to the entrance station, and allocates one passenger to the transfer route candidate with the smallest weight; The passenger flow congestion prediction device according to claim 5.

7. the train allocation unit sets the weight to a smaller value as the transfer station is closer to the exit station, and allocates one passenger to the transfer route candidate with the smallest weight. The passenger flow congestion prediction device according to claim 5.

8. the train allocation unit sets a weight for each of the plurality of transfer route candidates according to station information related to the transfer station; The passenger flow congestion prediction device according to claim 2.

9. the train allocation unit evaluates the ease of transfer at the transfer station based on the station information of the transfer station, sets the weight to a smaller value as the transfer becomes easier, and allocates one passenger to the transfer route candidate with the smallest weight. The passenger flow congestion prediction device according to claim 8.

10. the train allocation unit allocates one passenger to the plurality of route candidates and the plurality of transfer route candidates extracted based on the weights according to the allocation index, and further allocates the number of passengers allocated to the plurality of transfer route candidates to each of the plurality of transfer route candidates according to the weights. The passenger flow congestion prediction device according to any one of claims 2 to 9.

11. A passenger flow congestion prediction method for predicting passenger flow in rail transport, extracting route candidates based on at least one of the entrance time at the entrance station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entrance time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and current train timetable data including the departure time and arrival time of the current train; Calculating an allocation index based on the ticket gate passage data and the timetable data of the current train, and allocating one passenger to a plurality of the route candidates according to the allocation index; When the plurality of route candidates include a plurality of transfer route candidates that pass through a transfer station, assigning one of the passengers to one or more transfer route candidates extracted from the plurality of transfer route candidates according to a predetermined condition; A passenger flow congestion prediction method executed by one or more processors.

12. A passenger flow congestion prediction program that predicts passenger flow in rail transport, extracting route candidates based on at least one of the entrance time at the entrance station where the passenger entered and the exit time at the exit station where the passenger exited, among ticket gate passage data including the entrance time to the railway station and the exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and current train timetable data including the departure time and arrival time of the current train; Calculating an allocation index based on the ticket gate passage data and the timetable data of the current train, and allocating one passenger to a plurality of the route candidates according to the allocation index; When the plurality of route candidates include a plurality of transfer route candidates that pass through a transfer station, assigning one of the passengers to one or more transfer route candidates extracted from the plurality of transfer route candidates according to a predetermined condition; A passenger flow congestion prediction program for executing the above on one or more processors.

Images