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

Abstract

To provide a passenger flow congestion prediction device, a passenger flow congestion prediction method, and a passenger flow congestion prediction program capable of improving accuracy of congestion prediction with a simple configuration even when a train delay occurs.SOLUTION: A train flow congestion prediction device 10 includes a timetable correction unit 21 that determines whether or not a current train is delayed based on an exit time included in ticket gate pass date D1 including an entrance time to a railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate 5 and corrects timetable data of the current train when the current train is delayed, a route search unit 13 that extracts a route candidate based on at least one of the entrance time and the exit time in the ticket gate pass date D1 and the corrected timetable data corrected by the timetable correction unit 21, and a train allocation unit 14 that allocates the passenger to the route candidate based on the ticket gate pass date D1 and the corrected timetable data.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] However, for example, if trains operate according to a congested train schedule during the morning and evening rush hours when many passengers board and disembark, train departures may be delayed. If a delay of about 1 to 2 minutes occurs during rush hour, a discrepancy occurs between the predetermined train schedule and the actual departure and arrival times, which may reduce the accuracy of congestion predictions.

[0006] Furthermore, if actual arrival and departure information, including the actual arrival and departure times of trains, could be obtained, the timetable information used to estimate the congestion level of delayed trains could be corrected to improve the accuracy of the estimated congestion level for those delayed trains. However, this would result in problems such as the time required to transfer actual arrival and departure information and the cost involved in introducing the system.

[0007] 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 are capable of improving the accuracy of congestion prediction with a simple configuration even when train delays occur. [Means for solving the problem]

[0008] According to one aspect of the present invention, a passenger flow congestion prediction device is a device for predicting passenger flow in rail transport. The passenger flow congestion prediction device includes: a timetable correction unit that determines whether a current train is delayed based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger, the exit time being acquired from an automatic ticket gate installed at the railway station, and corrects timetable data for the current train if a delay occurs; a route search unit that extracts route candidates based on at least one of the entry time and the exit time included in the ticket gate passage data and the corrected timetable data corrected by the timetable correction unit; and a train assignment unit that assigns the passengers to the route candidates based on the ticket gate passage data and the corrected timetable data.

[0009] 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 includes one or more processors that execute the following steps: a timetable correction unit that determines whether a current train is delayed based on an exit time included in ticket gate passage data, the exit time including an entry time into the railway station and an exit time from the railway station for each passenger, the timetable correction unit corrects timetable data for the current train if a delay occurs; extracting route candidates based on at least one of the entry time and the exit time included in the ticket gate passage data and the corrected timetable data corrected by the timetable correction unit; and assigning the passengers to the route candidates based on the ticket gate passage data and the corrected timetable data.

[0010] A passenger flow congestion prediction program according to another aspect of the present invention is a program for predicting passenger flow in rail transport. The passenger flow congestion prediction program causes one or more processors to execute the following: a timetable correction unit that determines whether a current train is delayed based on an exit time included in ticket gate passage data, the timetable including an entry time into the railway station and an exit time from the railway station for each passenger, obtained from an automatic ticket gate installed at the railway station, and corrects timetable data for the current train if a delay occurs; extracts route candidates based on at least one of the entry time and the exit time included in the ticket gate passage data and the corrected timetable data corrected by the timetable correction unit; and assigns the passengers to the route candidates based on the ticket gate passage data and the corrected timetable data. [Effects of the Invention]

[0011] 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 are capable of improving the accuracy of congestion prediction with a simple configuration even when train delays occur. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing the configuration of a passenger flow congestion prediction device according to an 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 embodiment of the present invention. [Figure 3] FIG. 3 is a diagram showing an example of route candidates that have the minimum number of transfers when the time sequence is appropriate, as extracted by a route search unit included in a passenger flow congestion prediction device according to an 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 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 a passenger flow congestion prediction device according to an 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 a plurality of route candidates based on an assignment index calculated by a train assignment unit included in the passenger flow congestion prediction device according to the embodiment of the present invention. [Figure 7] FIG. 7 is a diagram showing an example of the numerical relationship of allocation indices calculated by a train allocation unit included in the passenger flow congestion prediction device according to the 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 embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing an example of the number of people remaining in 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 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 embodiment of the present invention. [Figure 12] FIG. 12 is a flowchart showing the flow of a process of allocating one passenger to a plurality of route candidates, which is executed by the passenger flow congestion prediction device according to the embodiment of the present invention. [Figure 13] FIG. 13 is a diagram showing an example of the operation status including the arrival time and departure time when there is no train delay. [Figure 14] FIG. 14 is a diagram showing an example of the operation status including the arrival time and departure time when a train is delayed. [Figure 15] FIG. 15 is a diagram showing an example of a reference time difference calculated in a timetable correction unit included in the passenger flow congestion prediction device according to the embodiment of the present invention. [Figure 16] FIG. 16 is a diagram showing an example of a delay time calculated by a timetable correction unit included in the passenger flow congestion prediction device according to the embodiment of the present invention. [Figure 17] FIG. 17 is a diagram showing an example of an operation status including arrival times corrected by a timetable correction unit included in the passenger flow congestion prediction device according to the embodiment of the present invention. [Figure 18] FIG. 18 is a flowchart showing the flow of a timetable correction process executed by the passenger flow congestion prediction device according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] 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.

[0014] 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.

[0015] 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.

[0016] 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.

[0017] The passenger flow congestion prediction device 10 according to this embodiment predicts passenger flow based on the passenger entry time at the entry station and the departure time at the exit station, which are included in the ticket gate passage data D1, and the train departure time at the entry station and the arrival time at the exit station, which are included in the timetable data D2 for the current train. For example, the passenger flow congestion prediction device 10 predicts passenger flow by allocating one passenger to multiple candidate routes using an allocation index calculated based on the ticket gate passage data D1 and the timetable data D2. Furthermore, in the event of a train delay, the passenger flow congestion prediction device 10 predicts passenger flow taking into account the delay time calculated based on the number of passengers exiting the exit station.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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 timetable correction unit 21, 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. The various processes executed by the passenger flow congestion prediction device 10 may be executed in a distributed manner by one or multiple processors.

[0035] The data acquisition unit 12, the timetable correction unit 21, 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 operations. 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 operations. 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 processes 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.

[0036] 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 FIGS. 12 and 18). 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] The data acquisition unit 12 acquires the ticket gate passage data D1 transmitted to the data acquisition unit 12 from the data server 4.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] This allows the train allocation unit 14 to allocate one passenger to multiple route candidates based on the entry time and the allocation index.

[0060] 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.

[0061] 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.

[0062] This allows the train allocation unit 14 to allocate one passenger to multiple route candidates based on the allocation index.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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).

[0074] diff = (departure time - entry time) + (exit time - arrival time)...(1) Here, the allocation index is represented as "diff."

[0075] 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.

[0076] 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.

[0077] Therefore, for the first route candidate, diff=2.

[0078] 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.

[0079] Therefore, for the second route candidate, diff=3.

[0080] 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.

[0081]

number

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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).

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] This allows the first congestion level estimating unit 15 to accurately predict passenger flow for each train on each of the multiple route candidates.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] Furthermore, although the stations to be counted are expressed as AAA Station to ZZZ Station, the number of stations is not particularly limited.

[0122] 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.

[0123] The output unit 17 outputs the result of the allocation calculated by the train allocation unit 14 based on the allocation index.

[0124] 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.

[0125] <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.

[0126] 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.

[0127] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0128] [Passenger flow congestion prediction method] 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.

[0129] Hereinafter, the passenger flow congestion prediction process executed in the passenger flow congestion prediction device 10 will be described with reference to Fig. 12. Specifically, the passenger flow congestion prediction process is executed by the control unit 20 of the passenger flow congestion prediction device 10.

[0130] The present invention can be understood as an invention of a passenger flow congestion prediction method that executes one or more steps included in the passenger flow congestion prediction process. Furthermore, one or more steps included in the passenger flow congestion prediction process described herein may be omitted as appropriate. The steps in the passenger flow congestion prediction process may be executed in a different order as long as the same effects are achieved. Furthermore, while an example is described here in which the control unit 20 executes each step in the passenger flow congestion prediction process, one or more processors may execute each step in the passenger flow congestion prediction process in a distributed manner. The passenger flow congestion prediction method is one example of the passenger flow congestion prediction method of the present invention.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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: entry time ≦ departure time < arrival time ≦ exit time). Note that if a train is delayed, the arrival time indicated above indicates the arrival time after correction by the timetable correction described below. The same applies to subsequent arrival times.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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 station is “T exit " is expressed as ".

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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 / diffi / sum) assign people.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] [Timetable adjustments due to train delays] Here, if a train delay occurs, the following problem may occur. FIG. 13 illustrates an example of the operation status of two consecutive trains. As shown in FIG. 13, in timetable data D2, train 101 departs from station A at 08:00 and arrives at station B at 08:10. train 102 departs from station A at 08:02 and arrives at station B at 08:12. For example, assume that 26 passengers enter station A at 07:56 and 10 passengers depart station B at 08:11. In this case, since train 102 arrives at station B after 08:11, it can be determined that the 10 passengers who departed can board train 101. It can also be determined that the remaining 16 passengers who departed station B at 08:13 can board train 102.

[0152] On the other hand, suppose that train 101 is delayed and arrives at station B (for example, arrives between 08:011 and 08:13), as shown in FIG. 14. In this case, if 26 passengers depart station B at 08:13, both trains 101 and 102 are extracted as route candidates. Therefore, according to the above relational expression (1), the route candidate for train 101 is diff = (departure time 08:00 - entry time 07:56) + (departure time 08:13 - arrival time 08:10) = 7. Note that here, since the delay time and the actual arrival time at station B are unknown, the arrival time in the timetable data D2 is used as the "arrival time" in the above relational expression (1).

[0153] In addition, in the route candidate for train 102, diff=(departure time 08:02-entrance time 07:56)+(exit time 08:13-arrival time 08:12)=7.

[0154] Therefore, according to the above relational expression (2), 13 passengers are assigned to each of train 101 and train 102.

[0155] As described above, when a train is delayed, the route candidates change and the number of passengers assigned to multiple route candidates also change. In particular, in an environment where train delay times and actual arrival times are not available, the assigned number of passengers is calculated using the arrival times in the timetable data D2, which deviates from the actual number of passengers for each train, resulting in a problem of reduced congestion prediction accuracy.

[0156] Therefore, the passenger flow congestion prediction device 10 according to this embodiment performs congestion prediction taking delay time into consideration. Specifically, the timetable correction unit 21 determines whether a train delay has occurred, and calculates the delay time if it determines that a delay has occurred. Then, the timetable correction unit 21 corrects the timetable (departure time, arrival time) registered in the timetable data D2 based on the calculated delay time. When the timetable correction unit 21 corrects the timetable, it stores the corrected timetable data. Then, the passenger flow congestion prediction device 10 calculates the number of people to be allocated based on the corrected timetable and performs congestion prediction.

[0157] Specifically, the timetable correction unit 21 calculates a reference time difference t0 that serves as a criterion for determining whether a delay has occurred, based on ticket gate passage data D1 during normal times when trains are not delayed. FIG. 15 shows the change in the number of passengers exiting the train when the train 101 arrives at station B during normal times. "t1" represents the arrival time of the train 101 at station B, which is registered in the timetable data D2. The timetable correction unit 21 can grasp the change characteristics of the number of passengers exiting the train (see the graph in FIG. 15) by analyzing the ticket gate passage data D1.

[0158] As shown in Figure 15, after arrival time t1, the number of passengers leaving station B gradually increases, peaks at time t2, and then gradually decreases. In this way, under normal circumstances, passengers of train 101 pass through the automatic ticket gate 5 and leave station B within a predetermined period after arrival time t1. Also, under normal circumstances, the number of passengers leaving station B peaks after time t0 has passed since arrival time t1. In other words, when train 101 arrives at station B, the number of passengers leaving station B peaks when time t0 has passed since arrival time t1.

[0159] The timetable correction unit 21 sets the time t0 from the arrival time t1 of the timetable to the time t2 when the number of passengers peaks as the "reference time difference" based on the actual results of the ticket gate passage data D1 under normal circumstances. The timetable correction unit 21 registers the reference time difference t0 in association with the arrival time t1 of the train 101 at station B.

[0160] After setting the reference time difference t0, the timetable correction unit 21 uses the reference time difference t0 to determine whether a delay has occurred for the train that is the target of congestion prediction. FIG. 16 shows changes in the number of passengers entering the station corresponding to the arrival time t1 of the train 101 at station B on a certain date and time that is the target of congestion prediction. The timetable correction unit 21 calculates the time (referred to as "t3") at which the number of passengers will peak based on the ticket gate passage data D1 for that date and time. After calculating the peak time t3, the timetable correction unit 21 calculates the time difference Δt between the arrival time t1 and the peak time t3 on the timetable and compares the time difference Δt with the reference time difference t0. If the time difference Δt is longer than the reference time difference t0, the timetable correction unit 21 determines that the train 101 has arrived at station B late, i.e., that a delay has occurred. The timetable correction unit 21 also calculates the time difference ta between the time difference Δt and the reference time difference t0 as the delay time. Furthermore, the timetable correction unit 21 determines that no delay has occurred when the time difference Δt and the reference time difference t0 are substantially the same.

[0161] In this way, the timetable correction unit 21 determines whether or not a train is delayed based on the arrival time t1 of the timetable, the reference time difference t0, and the change characteristics of the number of participants, and calculates the delay time ta if a delay has occurred.

[0162] After calculating the delay time ta, the timetable correction unit 21 corrects the timetable of the timetable data D2. Specifically, the timetable correction unit 21 corrects the arrival time by adding the delay time ta to the arrival time in the timetable. In the above example, the timetable correction unit 21 adds the delay time ta to the arrival time t1 in the timetable, changing the arrival time from "t1" to "t1+ta". As a result, the arrival time at station B in the timetable of the train 101 is switched to "t1+ta".

[0163] 17, when the timetable correction unit 21 calculates that the delay time ta of the train 101 at station B is 1 minute, it corrects the arrival time of the train from 08:10 to 08:11. As a result, the timetable of the train 101 is changed to one in which the train departs from station A at 08:00 and arrives at station B at 08:11.

[0164] The route search unit 13 extracts route candidates based on the corrected timetable, and the train allocation unit 14 allocates passengers to the route candidates based on the corrected timetable. For example, in the example shown in FIG. 17, according to the above relational expression (1), for the route candidate of train 101, diff = (departure time 08:00 - entry time 07:56) + (departure time 08:13 - arrival time 08:11) = 6. For the route candidate of train 102, diff = (departure time 08:02 - entry time 07:56) + (departure time 08:13 - arrival time 08:12) = 7.

[0165] Therefore, according to the above relational expression (2), 14 people (= 26 × 7 / 13) are assigned to the route candidates for train 101, and 12 people (= 26 × 6 / 13) are assigned to the route candidates for train 102. In this way, when train delay times are taken into consideration, the number of people assigned to the route candidates for each train is corrected.

[0166] As described above, when a train is delayed, by correcting the timetable to times (departure time, arrival time) corresponding to the delay time, it is possible to extract route candidates and calculate the number of people to be allocated taking the delay time into consideration. This makes it possible to predict congestion according to the actual train operation status. Furthermore, in this embodiment, since the departure and arrival times can be estimated based on the delay time calculated from the ticket gate passage data D1 and the timetable data D2 without obtaining data on the actual train departure and arrival times, there is no need to introduce a system for obtaining data on the actual departure and arrival times from a server.

[0167] [Schedule correction processing] 18 shows an example of the procedure of the timetable correction process executed in the passenger flow congestion prediction device 10 of this embodiment. For example, the timetable correction unit 21 executes the timetable correction process for the arrival time of each train. In the following, it is assumed that the departure time of a certain train at station A in the timetable is ts and the arrival time at station B in the timetable is t1.

[0168] In step S21, the timetable correction unit 21 acquires ticket gate passage data D1 of station B around arrival time t1 under normal circumstances. For example, the timetable correction unit 21 acquires ticket gate passage data D1 during non-rush hours when delays are unlikely to occur.

[0169] Next, in step S22, the timetable correction unit 21 sets a reference time difference t0 for station B during normal times. Specifically, the timetable correction unit 21 analyzes the characteristics of the number of people exiting immediately after arrival time t1 at station B based on ticket gate passage data D1 during normal times (see FIG. 15). Based on the analysis results, the timetable correction unit 21 calculates the time t2 at which the number of people exiting reaches its peak. Then, the timetable correction unit 21 sets the time difference between arrival time t1 and peak time t2 as the reference time difference t0. The timetable correction unit 21 registers the reference time difference t0 in association with the arrival time t1 of the train at station B.

[0170] Next, in step S23, the timetable correction unit 21 acquires ticket gate passage data D1 for the congestion prediction target. Here, the timetable correction unit 21 acquires ticket gate passage data D1 for Station B around arrival time t1 on the target day for congestion prediction.

[0171] Next, in step S24, the timetable correction unit 21 determines whether a delay has occurred in the train arriving at station B at arrival time t1. For example, in the example shown in Fig. 16, the timetable correction unit 21 analyzes the characteristics of the number of passengers immediately after arrival time t1 at station B based on the ticket gate passage data D1 acquired in step S23, and calculates the time t3 at which the number of passengers will peak based on the analysis results. After calculating the peak time t3, the timetable correction unit 21 then calculates the time difference Δt between the arrival time t1 and the peak time t3 on the timetable, and determines that a delay has occurred in the train if the time difference Δt is longer than the reference time difference t0 (Δt>t0) (S24: Yes). On the other hand, if the time difference Δt is approximately the same as the reference time difference t0, the timetable correction unit 21 determines that no delay has occurred (the train arrived on time) (S24: No). If the timetable correction unit 21 determines that the train is delayed (S24: Yes), it proceeds to step S25, and if it determines that the train is not delayed (S24: No), it ends the timetable correction process.

[0172] Next, in step S25, the timetable correction unit 21 corrects the arrival time t1. Specifically, the timetable correction unit 21 sets the time difference ta between the time difference Δt and the reference time difference t0 as the delay time, and corrects the arrival time by adding the delay time ta to the arrival time t1 in the timetable. In the example shown in FIG. 16, the timetable correction unit 21 adds the delay time ta to the arrival time t1 in the timetable, correcting the arrival time from "t1" to "t1+ta".

[0173] Next, in step S26, the timetable correction unit 21 registers the corrected timetable in the timetable data D2. In the example shown in Fig. 17, the timetable correction unit 21 changes the timetable in which the departure time of the train 101 from station A is 08:00 and the arrival time at station B is 08:10 in the timetable data D2 to a timetable in which the departure time from station A is 08:00 and the arrival time at station B is 08:11.

[0174] As described above, the timetable correction unit 21 determines whether a delay has occurred for each timetable, and executes a process to correct the timetable if a train delay occurs. If a train delay occurs, the route search unit 13 and the train allocation unit 14 extract route candidates and calculate the number of people to be allocated based on the corrected timetable. That is, if a train delay occurs, the control unit 20 of the passenger flow congestion prediction device 10 executes the passenger flow congestion prediction process shown in Fig. 12 based on the corrected timetable.

[0175] In the above embodiment, the timetable correction unit 21 performs the process of correcting the arrival time, but it may also perform the process of correcting the departure time. The timetable correction unit 21 may also calculate the delay time of the train departure time by analyzing passenger behavior using, for example, camera images inside the station.

[0176] Furthermore, in the above-described embodiment, the train allocation unit 14 is configured to allocate one passenger to multiple route candidates using an allocation index, but the present invention is not limited to this. In another embodiment, the train allocation unit 14 may allocate one passenger to any one of the extracted route candidates. For example, the train allocation unit 14 may allocate one passenger to the route candidate that minimizes the diff in the relational expression (1) among the multiple route candidates. The train allocation unit 14 may also allocate multiple passengers evenly to each of the extracted multiple route candidates. In other words, the present invention is characterized in that, when a train delay is extracted, the train schedule is corrected and congestion prediction is performed using the corrected schedule, and the congestion prediction method using the schedule may use well-known technology.

[0177] [Features of the present invention] As described above, the passenger flow congestion prediction device 10 according to this embodiment is a device for predicting passenger flow in rail transport. The passenger flow congestion prediction device 10 also includes: a route search unit 13 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, which is included in ticket gate passage data D1 including the entrance time and exit time of each passenger acquired from an automatic ticket gate installed at the railway station; current train schedule data D2 including the departure time and arrival time of the current train; a train allocation unit that allocates passengers to the route candidates based on the ticket gate passage data D1 and the current train schedule data D2; and a schedule correction unit 21 that determines whether the current train is delayed based on the exit time included in the ticket gate passage data D1 and corrects the schedule data of the current train if the current train is delayed.

[0178] According to the above configuration, when a train is delayed, the arrival time of the delayed train can be estimated based on the exit time and number of passengers exiting the ticket gate passage data D1, without obtaining information on the actual timetable (e.g., arrival time) (actual departure and arrival time data). This allows passengers to be assigned to route candidates using timetable data according to the actual operating conditions, making it possible to make an accurate congestion prediction that reflects the actual operating conditions. Therefore, even when a train is delayed, the accuracy of the congestion prediction can be improved with a simple configuration.

[0179] In the passenger flow congestion prediction device 10, the timetable correction unit 21 may determine whether a delay has occurred in the current train by comparing a reference distribution (see Figure 15) that shows the change in the number of passengers exiting at each exit time at the exit station included in the ticket gate passage data D1 when there is no delay in the current train with a target distribution (see Figure 16) that shows the change in the number of passengers exiting at each exit time at the exit station included in the ticket gate passage data D1 that is the target of congestion prediction.

[0180] For example, the timetable correction unit 21 may calculate the deviation (time difference) between the reference distribution (graph shown in Figure 15) and the target distribution (graph shown in Figure 16), and determine that a delay has occurred to the current train if the target distribution deviates from the reference distribution by more than a predetermined time.

[0181] Furthermore, in the passenger flow congestion prediction device 10, the timetable correction unit 21 may determine whether a delay has occurred in the current train based on the time difference between a reference time set based on the reference distribution and a target time set based on the target distribution. For example, the timetable correction unit 21 may set the reference time to the time t2 (peak time) at which the number of passengers reaches a peak in the reference distribution (see FIG. 15), and set the target time to the time t3 (peak time) at which the number of passengers reaches a peak in the target distribution (see FIG. 16). Then, the timetable correction unit 21 determines that a delay has occurred in the current train if the target time t3 is later than the reference time t2 by a predetermined time or more. The predetermined time may be set according to the time zone, day of the week, season, event information, station, etc.

[0182] In addition, in the passenger flow congestion prediction device 10, the timetable correction unit 21 may determine whether a delay has occurred in the current train based on the reference time difference t0 (first time difference) from the arrival time t1 to the reference time t2 included in the timetable data of the current train and the time difference Δt (second time difference) from the arrival time t1 to the target time t3 included in the timetable data D2 of the current train.

[0183] For example, the timetable correction unit 21 may determine that a delay has occurred in the current train when the time difference Δt is longer than the reference time difference t0 (Δt>t0). Also, the timetable correction unit 21 may set the difference between the time difference Δt and the reference time difference t0 as the delay time of the current train.

[0184] Furthermore, the timetable correction unit 21 may correct the arrival time included in the timetable data D2 of the current train based on the delay time.

[0185] Furthermore, the timetable correction unit 21 may change the arrival time included in the timetable data D2 of the current train to a time obtained by adding a delay time to the arrival time.

[0186] Furthermore, in the passenger flow congestion prediction device 10, the route search unit 13 may extract route candidates based on at least one of the entry time and the exit time in the ticket gate passage data D1 and the corrected timetable data D2 of the current train, and the train allocation unit 14 may allocate passengers to multiple route candidates based on the ticket gate passage data D1 and the corrected timetable data D2 of the current train. For example, the train allocation unit 14 may calculate an allocation index based on the ticket gate passage data D1 and the corrected timetable data D2 of the current train, and allocate one passenger to multiple route candidates according to the allocation index.

[0187] This allows for accurate congestion predictions that reflect actual operating conditions, thereby improving the accuracy of congestion predictions.

[0188] [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.

[0189] In the above-described embodiment, the timetable correction unit 21 sets the reference time difference t0 based on the time t2 (see FIG. 15) when the number of exiting passengers at the exit station reaches its peak. The time t2 (hereinafter referred to as the "determination time") for calculating the reference time difference t0 is not limited to the time of the peak number of passengers, and may be the following time. For example, the timetable correction unit 21 may set the determination time t2 according to the time period. For example, during rush hour, passengers tend to exit the train earlier after arriving at the station, and during non-rush hour, passengers tend to exit the train later after arriving at the station. Therefore, the timetable correction unit 21 may set the determination time t2 during rush hour to be earlier than the determination time t2 during non-rush hour.

[0190] In addition, for example, on weekdays, passengers tend to exit the train earlier after the train arrives at the station, and on holidays, passengers tend to exit the train later after the train arrives at the station. Therefore, the timetable correction unit 21 may set the determination time t2 on weekdays to be earlier than the determination time t2 on holidays.

[0191] Furthermore, for example, the time required for a train to exit after arriving at a station may differ from station to station. For example, if the platform where the train arrives is far from the automatic ticket gate 5, the time will be longer, and if the platform where the train arrives is close to the automatic ticket gate 5, the time will be shorter. Therefore, the timetable correction unit 21 may set the reference time difference t0 based on the structure of the station, etc.

[0192] In another embodiment, the timetable correction unit 21 may analyze the past behavior history (entrance and exit history) of each passenger and set the reference time difference t0. For example, for a specific train, the timetable correction unit 21 may calculate the time required for each passenger from the arrival time on the timetable to exit the automatic ticket gate 5 based on the past entrance and exit history of each of multiple passengers using IC cards, and set the reference time difference t0 to the average of the respective required times.

[0193] In another embodiment, the timetable correction unit 21 may set the reference time difference t0 in response to an input operation by a user (such as a railway company administrator). For example, when a user inputs a desired time on an operation screen, the timetable correction unit 21 may set the input time as the reference time difference t0.

[0194] The timetable correction unit 21 also determines whether a train delay has occurred based on the judgment time t2 (reference time) shown in each of the above-mentioned embodiments. For example, during rush hour periods, the timetable correction unit 21 determines whether a train delay has occurred based on the reference time difference t0 between the arrival time t1 of the timetable and the judgment time t2 corresponding to the rush hour, and the time difference Δt between the arrival time t1 of the timetable and the peak time t3. During non-rush hour periods, the timetable correction unit 21 also determines whether a train delay has occurred based on the reference time difference t0 between the arrival time t1 of the timetable and the judgment time t2 corresponding to the non-rush hour, and the time difference Δt between the arrival time t1 of the timetable and the peak time t3.

[0195] Furthermore, for example, on weekdays, the timetable correction unit 21 determines whether a train delay has occurred based on the reference time difference t0 between the arrival time t1 in the timetable and the judgment time t2 corresponding to the weekday, and the time difference Δt between the arrival time t1 in the timetable and the peak time t3. On holidays, the timetable correction unit 21 determines whether a train delay has occurred based on the reference time difference t0 between the arrival time t1 in the timetable and the judgment time t2 corresponding to the holiday, and the time difference Δt between the arrival time t1 in the timetable and the peak time t3. As described above, the timetable correction unit 21 may determine whether a train delay has occurred by setting the time when the number of passengers is at its peak as the reference time, or may determine whether a train delay has occurred by setting the reference time based on the time period, day of the week, entry / exit history, input operation, etc.

[0196] [Notes on the Invention] The following is a summary of the invention extracted from this embodiment. Note that the configurations and processing functions described in the following supplementary notes can be selected and combined as desired.

[0197] <Appendix 1> A passenger flow congestion prediction device that predicts passenger flow in rail transport, a timetable correction unit that determines whether a delay has occurred in a current train based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and corrects timetable data of the current train when a delay has occurred in the current train; a route search unit that extracts route candidates based on at least one of the entry time and the exit time among the ticket gate passage data and the timetable data corrected by the timetable correction unit; a train allocation unit that allocates the passengers to the route candidates based on the ticket gate passage data and the corrected timetable data; A passenger flow congestion prediction device equipped with:

[0198] <Appendix 2> The timetable correction unit compares a reference distribution indicating a change in the number of exiting passengers at each exit time at an exit station included in the ticket gate passage data when no delay occurs in the current train with a target distribution indicating a change in the number of exiting passengers at each exit time at an exit station included in the ticket gate passage data that is the target of congestion prediction, to determine whether a delay has occurred in the current train. 2. A passenger flow congestion prediction device according to claim 1.

[0199] <Appendix 3> the timetable correction unit determines whether a delay has occurred in the current train based on a time difference between a reference time set based on the reference distribution and a target time set based on the target distribution; 3. A passenger flow congestion prediction device according to claim 2.

[0200] <Appendix 4> the timetable correction unit determines whether a delay has occurred in the current train based on a first time difference between an arrival time included in the timetable data of the current train and the reference time, and a second time difference between the arrival time included in the timetable data of the current train and the target time; 4. A passenger flow congestion prediction device according to claim 3.

[0201] <Appendix 5> The timetable correction unit determines that a delay has occurred in the current train when the second time difference is longer than the first time difference. 5. A passenger flow congestion prediction device according to claim 4.

[0202] <Appendix 6> The timetable correction unit sets the difference between the second time difference and the first time difference as the delay time of the current train. 6. A passenger flow congestion prediction device according to claim 5.

[0203] <Appendix 7> The timetable correction unit corrects the arrival time included in the timetable data of the current train based on the delay time. 7. A passenger flow congestion prediction device according to claim 6.

[0204] <Appendix 8> The timetable correction unit changes the arrival time included in the timetable data of the current train to a time obtained by adding the delay time to the arrival time. 8. A passenger flow congestion prediction device according to claim 7.

[0205] <Appendix 9> The route search unit extracts route candidates based on at least one of the entry time and the exit time of the ticket gate passage data and the corrected timetable data, the train allocation unit allocates the passengers to the plurality of route candidates based on the ticket gate passage data and the corrected timetable data. 9. A passenger flow congestion prediction device according to claim 8.

[0206] <Appendix 10> the train allocation unit calculates an allocation index based on the ticket gate passage data and the corrected timetable data, and allocates one passenger to a plurality of the route candidates according to the allocation index; 10. A passenger flow congestion prediction device according to claim 8 or 9.

[0207] <Appendix 11> A passenger flow congestion prediction method for predicting passenger flow in rail transport, a timetable correction unit that determines whether a delay has occurred in a current train based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and corrects timetable data of the current train when a delay has occurred in the current train; Extracting route candidates based on at least one of the entry time and the exit time among the ticket gate passage data and the timetable data corrected by the timetable correction unit; Allocating the passenger to the route candidates based on the ticket gate passage data and the corrected timetable data; A passenger flow congestion prediction method executed by one or more processors.

[0208] <Appendix 12> A passenger flow congestion prediction program that predicts passenger flow in rail transport, a timetable correction unit that determines whether a delay has occurred in a current train based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and corrects timetable data of the current train when a delay has occurred in the current train; Extracting route candidates based on at least one of the entry time and the exit time among the ticket gate passage data and the timetable data corrected by the timetable correction unit; Allocating the passenger to the route candidates based on the ticket gate passage data and the corrected timetable data; A passenger flow congestion prediction program for executing the above on one or more processors.

[0209] [Reference form] (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.

[0210] 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.

[0211] 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.

[0212] The present invention may also be realized as a recording medium storing a passenger flow congestion prediction program.

[0213] (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 vehicle is provided in the passenger flow congestion prediction device 10. However, the present invention is not limited to this.

[0214] 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.

[0215] (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.

[0216] 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.

[0217] (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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] Furthermore, the train allocation unit 14 may remove or multiply each term in the relational expressions (1) and (3) to (9) by a constant.

[0222] (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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] Furthermore, the train allocation unit 14 may remove or multiply each term in the relational expressions (10) to (14) by a constant.

[0227] (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.

[0228] 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.

[0229] 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.

[0230] (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.

[0231] 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.

[0232] In other words, the passenger flow congestion prediction device of the present invention may not be provided with an output unit.

[0233] [Reference invention] (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.

[0234] 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.

[0235] 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.

[0236] In addition, the "allocation index" is a quantitative parameter used to calculate the proportion of a single rail passenger who selects multiple route options.

[0237] 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.

[0238] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0239] (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.

[0240] 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.

[0241] 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.

[0242] This allows the train allocation unit described below to determine an appropriate allocation index.

[0243] (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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] This allows the train allocation unit to allocate one passenger to a plurality of appropriate route candidates based on the allocation index.

[0249] (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.

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] (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.

[0255] 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.

[0256] 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.

[0257] (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.

[0258] 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.

[0259] This allows the first congestion level estimation unit to accurately predict passenger flow for each train on each of the multiple route candidates.

[0260] (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.

[0261] 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.

[0262] 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.

[0263] (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.

[0264] 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.

[0265] This allows the train allocation unit to allocate one passenger to multiple route candidates based on the entry time and the allocation index.

[0266] (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.

[0267] 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.

[0268] This allows the train allocation unit to allocate one passenger to multiple route candidates based on the allocation index.

[0269] (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.

[0270] 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.

[0271] 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.

[0272] This allows the train allocation unit to allocate one passenger to multiple routes in units of decimal points less than 1 according to the calculated allocation index.

[0273] (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.

[0274] 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.

[0275] 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.

[0276] 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.

[0277] (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.

[0278] 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.

[0279] (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.

[0280] 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.

[0281] (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.

[0282] 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.

[0283] 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.

[0284] In addition, the "allocation index" is a quantitative parameter used to calculate the proportion of a single rail passenger who selects multiple route options.

[0285] 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.

[0286] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past.

[0287] (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.

[0288] 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.

[0289] 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.

[0290] In addition, the "allocation index" is a quantitative parameter used to calculate the proportion of a single rail passenger who selects multiple route options.

[0291] 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.

[0292] As a result, the accuracy of predictions of passenger flow in rail transport can be improved compared to the past. [Explanation of symbols]

[0293] 2: Input device 3:Display device 4: Data Server 5: Automatic ticket gate 10: Passenger flow congestion prediction device 11: Storage section 21: Diameter correction 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

Claims

1. A passenger flow congestion prediction device that predicts passenger flow in rail transport, a timetable correction unit that determines whether a delay has occurred in a current train based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and corrects timetable data of the current train when a delay has occurred in the current train; a route search unit that extracts route candidates based on at least one of the entry time and the exit time among the ticket gate passage data and the timetable data corrected by the timetable correction unit; a train allocation unit that allocates the passengers to the route candidates based on the ticket gate passage data and the corrected timetable data; A passenger flow congestion prediction device equipped with:

2. The timetable correction unit compares a reference distribution indicating a change in the number of passengers exiting at each exit time at an exit station included in the ticket gate passage data when no delay occurs in the current train with a target distribution indicating a change in the number of passengers exiting at each exit time at an exit station included in the ticket gate passage data that is the target of congestion prediction, to determine whether or not a delay has occurred in the current train. The passenger flow congestion prediction device according to claim 1.

3. the timetable correction unit determines whether a delay has occurred in the current train based on a time difference between a reference time set based on the reference distribution and a target time set based on the target distribution; The passenger flow congestion prediction device according to claim 2.

4. the timetable correction unit determines whether a delay has occurred in the current train based on a first time difference between an arrival time included in the timetable data of the current train and the reference time, and a second time difference between the arrival time included in the timetable data of the current train and the target time; The passenger flow congestion prediction device according to claim 3.

5. The timetable correction unit determines that a delay has occurred in the current train when the second time difference is longer than the first time difference. The passenger flow congestion prediction device according to claim 4.

6. The timetable correction unit sets the difference between the second time difference and the first time difference as the delay time of the current train. The passenger flow congestion prediction device according to claim 5.

7. The timetable correction unit corrects the arrival time included in the timetable data of the current train based on the delay time. The passenger flow congestion prediction device according to claim 6.

8. The timetable correction unit changes the arrival time included in the timetable data of the current train to a time obtained by adding the delay time to the arrival time. The passenger flow congestion prediction device according to claim 7.

9. The route search unit extracts route candidates based on at least one of the entry time and the exit time of the ticket gate passage data and the corrected timetable data, the train allocation unit allocates the passengers to the plurality of route candidates based on the ticket gate passage data and the corrected timetable data. The passenger flow congestion prediction device according to claim 8.

10. the train allocation unit calculates an allocation index based on the ticket gate passage data and the corrected timetable data, and allocates one passenger to a plurality of the route candidates according to the allocation index; The passenger flow congestion prediction device according to claim 8.

11. A passenger flow congestion prediction method for predicting passenger flow in rail transport, a timetable correction unit that determines whether a delay has occurred in a current train based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and corrects timetable data of the current train when a delay has occurred in the current train; Extracting route candidates based on at least one of the entry time and the exit time among the ticket gate passage data and the timetable data corrected by the timetable correction unit; Allocating the passenger to the route candidates based on the ticket gate passage data and the corrected timetable data; 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, a timetable correction unit that determines whether a delay has occurred in a current train based on an exit time included in ticket gate passage data including an entry time into the railway station and an exit time from the railway station for each passenger acquired from an automatic ticket gate installed at the railway station, and corrects timetable data of the current train when a delay has occurred in the current train; Extracting route candidates based on at least one of the entry time and the exit time among the ticket gate passage data and the timetable data corrected by the timetable correction unit; Allocating the passenger to the route candidates based on the ticket gate passage data and the corrected timetable data; A passenger flow congestion prediction program for executing the above on one or more processors.

Images