Traffic demand forecasting device

Abstract

A traffic demand prediction device (10) comprises: a depot headcount prediction unit (10A) for predicting the number of persons per depot in an area from the predicted number of persons having been preliminarily obtained for each area including at least one of the departure area and the arrival area of visitors to the event of interest, on the basis of a numeric value that pertains to the preliminarily obtained use scale of each depot in each area; a route headcount prediction unit (13) for predicting the number of persons per route between each of depots in the area obtained by a route search algorithm and a nearest depot to the event, from the number of persons per depot in the area having been obtained by prediction; and a use headcount prediction unit (14) for predicting the number of use persons per nearest depot to the event or per nearest line, on the basis of the number of persons per route having been obtained by prediction.

Description

[Technical Field]

[0001] The present disclosure relates to a transportation demand prediction device that predicts transportation demand associated with holding various events, occasions, performances, etc. (hereinafter collectively referred to as "events").

[0002] In the following, the "return area" of a visitor to an event refers to the area where the visitor first stays after moving from the event venue immediately after the event. For example, if the visitor goes straight home immediately after the event, the return area will be the area around the home, and if the visitor stops by a commercial facility immediately after the event, the return area will be the area around the commercial facility. Similarly, the "departure area" of a visitor to an event refers to the area where the visitor stays immediately before moving to the event venue immediately before the event. For example, if the visitor goes straight from home to the event venue, the departure area will be the area around the home, and if the visitor stops by a commercial facility immediately before the event, the departure area will be the area around the commercial facility. Furthermore, an area that includes at least one of the "return area" and "departure area" of a visitor to an event will be collectively referred to as "area." [Background technology]

[0003] When planning various events, it is important to predict the transportation demand associated with the event in advance, for purposes such as considering measures to improve transportation to the event venue and marketing merchandise sales. For events with a long history of being held, information such as the approximate number of people heading to each nearest station to the event venue immediately after the event has ended has been accumulated as know-how, making it possible to roughly plan measures such as traffic guidance. For example, Patent Document 1 discloses a technology that calculates the increase rate of passengers disembarking at the nearest station before the event on the day of the event compared to the number of passengers disembarking at the same station on a day when the event is not held, and uses the obtained rate to predict the number of passengers at the nearest station immediately after the event has ended. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-219673 Summary of the Invention [Problem to be solved by the invention]

[0005] However, for events held at newly opened event venues, it was difficult to consider measures such as traffic guidance, because it was unclear how many people would head to the nearest stations immediately after the event ended.Furthermore, even for events with a long track record, there was a limit to how accurately traffic demand could be predicted simply by using know-how accumulated in the past.

[0006] The present disclosure has been made to solve the above-mentioned problem, and aims to accurately predict transportation demand associated with the holding of various events. [Means for solving the problem]

[0007] The transportation demand prediction device according to the present disclosure includes a stop number of passengers prediction unit that predicts the number of passengers at each stop in an area based at least on numerical values ​​relating to the scale of use of each stop in each area obtained in advance from predicted number of passengers obtained in advance for each area including at least one of the departure area and return area of ​​visitors to a target event; a route number of passengers prediction unit that predicts the number of passengers for each route between each stop in the area obtained by a route search algorithm and the nearest stop to the event from the number of passengers for each route obtained by the route number of passengers prediction unit; and a user number prediction unit that predicts the number of passengers for each stop nearest to the event or for each nearest route based on the number of passengers for each route obtained by the prediction by the route number of passengers prediction unit.

[0008] In the above-described transportation demand prediction device, the stop occupancy prediction unit predicts the number of visitors to a target event at each stop in the area based on at least a numerical value related to the scale of use of each stop in each area (for example, the average daily passenger count at each station), using the predicted number of visitors for each area. The route occupancy prediction unit predicts the number of visitors for each route between each stop in the area, obtained by a route search algorithm, and the stop nearest to the event, using the predicted number of visitors for each stop in the area. The user occupancy prediction unit then predicts the number of visitors for each stop nearest to the event or for each nearest line, based on the predicted number of visitors for each route. For example, the number of visitors for a given stop nearest to the event can be predicted by calculating the sum of the number of visitors for each route for all routes leading to the stop nearest to the event. By performing this prediction for all the stops nearest to the event, the number of visitors for each stop nearest to the event can be predicted.

[0009] As described above, without using know-how such as how many people will head to each of the nearest stations to the event venue immediately after the event ends, it is possible to predict the number of users for each nearest bus stop or nearest line to the event from the predicted number of visitors for each area of ​​the target event, which has been obtained in advance. This makes it possible to accurately predict the number of users for each nearest bus stop or nearest line to the event, even for events at event venues that have just opened or new events. Furthermore, even for events that have been held many times before, it is possible to accurately predict the number of users for each nearest bus stop or nearest line to the event, based on the predicted number of visitors for each area of ​​the target event. In other words, it is possible to accurately predict the transportation demand associated with the holding of various events. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to accurately predict the demand for transportation associated with the holding of various events. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a functional block diagram of a transportation demand forecasting device and related devices according to an embodiment of the present invention. [Figure 2] FIG. 2 is a flowchart showing processing executed in the transportation demand prediction device. [Figure 3] FIG. 10 is a diagram for explaining processing by a number-of-people apportionment unit. [Figure 4] FIG. 10 is a diagram illustrating an example of output data from a route number of passengers prediction unit. [Figure 5] 10A is a diagram showing an example of output data of the number of users for each station closest to the event, and FIG. 10B is a diagram showing an example of output data of the number of users for each nearest line. [Figure 6] FIG. 10 is a diagram showing various examples of numerical values ​​relating to the scale of use of each stop within each area. [Figure 7] FIG. 2 is a diagram illustrating an example of a hardware configuration of a transportation demand prediction device. DETAILED DESCRIPTION OF THE INVENTION

[0012] An embodiment of a transportation demand prediction device according to the present disclosure will be described below with reference to the drawings. As shown in FIG. 1, a transportation demand prediction device 10 includes a stop number of passengers prediction unit 10A, a route number of passengers prediction unit 13, and a user number of passengers prediction unit 14. The functions of each unit will be outlined below. Note that routes related to transportation demand include all routes that operate along predetermined routes and stop at predetermined stops (train stations or bus stops), such as railway lines and bus routes. However, in the following embodiment, railway lines are assumed as routes related to transportation demand, and stations are assumed as stops.

[0013] The station occupancy prediction unit 10A is a functional unit that predicts the number of people at each station in an area based on at least previously obtained numerical values ​​(for example, the average daily number of passengers at each station) related to the scale of use of each station in each area from the previously obtained predicted number of people for each area of ​​visitors to the target event (an area including at least one of the departure area and the return area). To perform the above functions, the station occupancy prediction unit 10A includes a candidate station selection unit 11 and a number of people allocation unit 12.

[0014] Of these, the candidate station selection unit 11 acquires a predicted number of users for each area obtained in advance from the terminal 20, and extracts candidate stations within each area by referring to a station information database (DB) 30. Note that while FIG. 1 shows an example in which the station information DB 30 is provided outside the transportation demand prediction device 10, the station information DB 30 may also be provided inside the transportation demand prediction device 10.

[0015] Furthermore, the number of passengers apportionment unit 12 predicts the number of passengers at each station in the area by apportioning the predicted number of passengers for each area to the number of passengers at each station in the area based solely on the previously obtained numerical values ​​relating to the scale of use of each station in each area (for example, the average number of passengers per day at each station), or based on the numerical values ​​relating to the scale of use of each station in each area as well as population data for each station at the time of past events that can be obtained from the location information database (DB) 40. Details will be described later. Note that, as the numerical values ​​relating to the scale of use of each station in each area, in addition to the average number of passengers per day at each station, many patterns of passenger numbers as shown in FIG. 6 may be used. That is, the "method of taking the average value" shown vertically in the table of Figure 6 has variations such as the daily average, weekday average, ..., and average by holiday time slot, while the "target number of passengers" shown vertically in the table of Figure 6 has variations in the number of passengers boarding, alighting, and boarding and alighting passengers (total of passengers boarding and alighting), and each of these has sub-variations such as "commuter" who uses a commuter pass, "non-commuter" who does not use a commuter pass, and "total" which is the sum of commuter and non-commuter. Therefore, it is possible to employ as many patterns of passengers as there are combinations of vertical and horizontal variations in the table of Figure 6.

[0016] Returning to Figure 1, the route passenger count prediction unit 13 included in the transportation demand prediction device 10 is a functional unit that predicts the number of passengers along each route between each station in the area obtained by the route search algorithm and the station closest to the event, based on the number of passengers at each station in the area predicted by the passenger count apportionment unit 12. The route search algorithm uses not only geographical route map information, but also an algorithm that searches for a route based on operation information along a time axis and priorities for route search. Details of this will be described later.

[0017] The number of users prediction unit 14 is a functional unit that predicts the number of users for each nearest station to the event or for each nearest line based on the number of users for each route predicted by the route number prediction unit 13, and details of this will be described later.

[0018] Next, the processing executed by the transportation demand prediction device 10 will be described with reference to the flow diagram of FIG. 2. For example, the processing of FIG. 2 is started when the transportation demand prediction device 10 receives from the terminal 20 an execution start command along with the previously obtained predicted number of users for each area. First, the candidate station selection unit 11 acquires the predicted number of users for each area from the terminal 20 (step S1), and extracts candidate stations within each area by referring to the station information DB 30 (step S2). Note that the processing order of steps S1 and S2 does not have to be the order shown in FIG. 2, and may be reversed, or may be executed simultaneously in parallel. Furthermore, if candidate stations within each area have been extracted in the past and information on the candidate stations for each area is stored in the transportation demand prediction device 10, the processing of step S2 does not need to be executed every time.

[0019] Next, the number of people apportionment unit 12 determines whether to use population data for each station from a past event (step S3). This determination may be made based on a parameter regarding "whether to use past population data" specified by the user in an execution start command from the terminal 20, for example. If past population data is not used in step S3, the number of people apportionment unit 12 apportions the predicted number of users for each area to the predicted number of users for each station within the area based on a numerical value regarding the scale of use of each station (e.g., the average daily passenger numbers at each station) (step S6). For example, if the expected number of visitors to the target event in the departure area X shown in FIG. 3 is 400, and the average daily passenger numbers at candidate stations X1 to X3 within the departure area X are 12,000, 100, and 900, respectively, the estimated number of visitors (400) is apportioned in a ratio of (120:1:9) to obtain the estimated numbers of users of candidate stations X1 to X3 as 369, 3, and 28, respectively. Similarly, by apportioning the expected number of visitors to the target event in departure area Y (100 people) to candidate stations Y1 and Y2 in the ratio of the average daily passenger numbers (2:1) for each of the candidate stations within departure area Y, we obtain the estimated number of users for candidate stations Y1 and Y2, respectively, as 67 and 33 people. Furthermore, by apportioning the expected number of visitors to the target event in departure area Z (200 people) to candidate stations Z1 and Z2 in the ratio of the average daily passenger numbers (30:8) for each of the candidate stations within departure area Z, we obtain the estimated number of users for candidate stations Z1 and Z2, respectively, as 158 and 42 people. Note that while this example focuses on the "departure area" of the "return area" and "departure area" of visitors to a certain event, it is also possible to focus on the "return area" or both the "return area" and the "departure area."

[0020] The above-described allocation in step S6 is expressed, for example, by the following formula: If n candidate stations are included in an arbitrary area and the average number of passengers per day at each station is s m 1, s m 2, …, s m n If the predicted number of visitors in the area is N, the estimated number of visitors to each station at the event is s e 1, s e 2, …, s e nis calculated using the following formula (1).

number

[0021] On the other hand, when past population data is used in step S3, the number of passengers apportionment unit 12 acquires population data of each station at the time of the past event from the location information DB 40 (step S4), and allocates the predicted number of passengers for each area to the predicted number of passengers for each station within the area based on the numerical values ​​related to the scale of use of each station and the population data of each station at the time of the past event (step S5). The allocation here is expressed, for example, by the following formula using an arithmetic mean. An example using a weighted mean will be described later. If an arbitrary area includes n candidate stations and the average daily passenger numbers at each station are calculated as s m 1, s m 2, …, s m n The predicted number of visitors in the area is N, and the number of visitors at each station in past event k is s p 1k , s p 2k , …, s p nk If this is obtained, the estimated number of people using each station for the event will be e 1, s e 2, …, s e n is calculated using the following formula (2).

number

[0022] Next, the route number prediction unit 13 proportionally allocates the estimated number of passengers for each station in the area to the estimated number of passengers for each route between each station and the station nearest to the event (step S7). More specifically, the route number prediction unit 13 uses an existing predetermined route search method (e.g., Dijkstra algorithm, etc.) to set routes between each station and the station nearest to the event based on geographical route map information, operation information along the time axis, and route search priorities (e.g., priority on number of transfers, priority on required time, priority on cost), and allocates the number of passengers at each station estimated by the number of passengers allocation unit 12 proportionally to each of the multiple routes set. Therefore, as shown in FIG. 4, different routes are set depending on which of the number of transfers, required time, and cost is prioritized, and the estimated number of passengers for each set route (information at the right end of the table in FIG. 4) is obtained. In this way, the estimated number of passengers for each route between each station and the station nearest to the event is calculated and transferred to the user number prediction unit 14. Here, we have described an example in which three priorities for route search are used: the number of transfers, the travel time, and the cost. However, the priorities for route search are not limited to these, and the route search method is not limited to a specific method.

[0023] Furthermore, the user number prediction unit 14 predicts and outputs the number of users for each nearest station to the event or for each nearest line based on the predicted number of users for each route (step S8). For example, FIG. 5(a) shows an example of output data of the number of users for each nearest station to the event, and FIG. 5(b) shows an example of output data of the number of users for each nearest line. Note that "output" here includes various forms of output, such as display output on a display, print output on a printer, and data transmission to an external device.

[0024] The effects of the above embodiment will be described below.

[0025] According to the above embodiment, the number of visitors to each nearest station or each nearest train line to the event can be predicted based on the predicted number of visitors to each area of ​​the target event, obtained in advance, without using know-how such as how many people will head to each nearest train station to the event venue immediately after the event ends. This makes it possible to accurately predict the number of visitors to each nearest station or each nearest train line to the event, even for events at event venues that have just opened or new events. Furthermore, even for events with a long history of being held, it is possible to accurately predict the number of visitors to each nearest station or each nearest train line to the event, based on the predicted number of visitors to each area of ​​the target event. In other words, it is possible to accurately predict the transportation demand associated with the holding of various events.

[0026] Furthermore, when the number of people apportionment unit 12 predicts the number of people at each station in an area based on not only the numerical values ​​related to the scale of use of each station in each area, but also the population data of each station at the time of past events, the accuracy of the number of people prediction can be further improved by predicting the number of people based on the population data of each station at the time of past events.

[0027] Furthermore, when the number of people apportionment unit 12 predicts the number of people at each station in an area based on the numbers relating to the scale of use of each station in each area, as well as the population data of each station at the time of past events, the number of people can be predicted using a relatively simple method using arithmetic averages, as described above.

[0028] Furthermore, the route search algorithm uses an algorithm that searches for routes based on geographical route map information, operation information along the time axis, and route search priorities. This makes it possible to predict the "estimated number of people for each route between each station and the station nearest to the event" that matches not only geographical route map information but also actual train operation information such as operation information along the time axis and route search priorities (e.g., number of transfers, required time, fare) and user priorities, further improving the accuracy of number of people predictions.

[0029] (Modification of the allocation in step S5 of FIG. 2) In the apportionment in step S5 of FIG. 2, instead of using the arithmetic mean, a weighted average as follows may be used. Suppose there are n candidate stations in an arbitrary area, and the average daily ridership of each station is s m 1, s m 2, …, s m n Let the predicted number of visitors in that area be N people, and the number of visitors at each station in the past event j be s p 1j , s p 2j , …, s p nj When obtained as such, the estimated number of users at each station of event visitors s e 1, s e 2, …, s e n is obtained by the following formula (3). [Number] In the above method of setting weights, for events with a larger overall area usage, larger weights are set, and for events with a smaller usage, smaller weights are set. For example, in a certain area, if "the number of users in Event 1 is A people" and "the number of users in Event 2 is B people", when the weight w0 regarding the average daily ridership is set to x (where x satisfies 0 < x ≤ 1, and in many cases, x = 0.5 is adopted), the weights regarding Events 1 and 2 are set by the following formula (4). [Number] Based on the prediction using the weighted average with larger weights set for events with a larger overall area usage as in the above modification example, an appropriate weighted average matching the overall area usage and the number prediction for each station within the area can be performed, and the accuracy of the number prediction can be further improved.

[0030] (Explanation of terms, explanation of hardware configuration (FIG. 7), etc.) The block diagrams used to explain the above embodiments and modifications show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0031] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocation, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0032] For example, a transportation demand prediction device according to an embodiment of the present disclosure may function as a computer that performs the processing according to this embodiment. Fig. 7 is a diagram illustrating an example of the hardware configuration of a transportation demand prediction device 10 according to an embodiment of the present disclosure. The transportation demand prediction device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0033] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the transportation demand prediction apparatus 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0034] Each function of the traffic demand forecasting device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0035] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0036] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. While the above-described various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0037] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0038] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray disc), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database including at least one of memory 1002 and storage 1003, or any other suitable medium.

[0039] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0040] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated into one device (for example, a touch panel). Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses for each device.

[0041] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched depending on the implementation. Furthermore, notification of predetermined information (e.g., notification that "X is true") is not limited to being done explicitly, but may be done implicitly (e.g., by not notifying the predetermined information).

[0042] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0043] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0044] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0045] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0046] When used in this disclosure, the terms "include," "including," and variations thereof are intended to be inclusive, similar to the term "comprising." Furthermore, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0047] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0048] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0049] 10...traffic demand prediction device, 10A...stop occupancy prediction unit, 11...candidate station selection unit, 12...occupancy allocation unit, 13...route occupancy prediction unit, 14...user occupancy prediction unit, 20...terminal, 30...station information database, 40...location information database, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. a stop number of people prediction unit that predicts the number of people at each stop in an area based on at least a numerical value relating to the scale of use of each stop in each area obtained in advance from a predicted number of people obtained in advance for each area including at least one of the departure area and return area of ​​visitors to the target event; a route occupancy prediction unit that sets routes between each stop in the area and the stop closest to the event based on geographical route map information, operation information along a time axis, and a route search algorithm that searches for routes based on priorities in route search, and predicts the number of people for each route by allocating the number of people for each stop in the area obtained by the prediction by the stop occupancy prediction unit to each of the routes between each stop in the area and the stop closest to the event; a user number prediction unit that predicts the number of users for each nearest stop to the event or for each nearest line based on the number of users for each route obtained by the prediction by the route user number prediction unit; A traffic demand forecasting device comprising:

2. The station occupancy prediction unit predicting the number of passengers at each stop in each area based on the numerical values ​​relating to the scale of use of each stop in each area, as well as population data at each stop during past events; The traffic demand forecasting device according to claim 1.

3. The station occupancy prediction unit predicting the number of people at each stop within the area based on a numerical value relating to the scale of use of each stop within each area and an arithmetic average of the population data at each stop at the time of the past event; The traffic demand forecasting device according to claim 2.

4. The station occupancy prediction unit predicting the number of people at each stop in each area based on a weighted average, with a weight set to be larger for events with a larger number of users across the entire area, from values ​​related to the scale of use of each stop in each area and population data for each stop at the time of the past event; The traffic demand forecasting device according to claim 2.

Images