Demand prediction method, demand prediction device, and program

Abstract

The present invention makes it possible to accurately predict, when a customer arrives at a certain point using a first transportation facility, the demand for a second transportation facility available to the customer from that point. This demand prediction device comprises: a people arrival count acquisition unit that acquires a people arrival count, which is the number of people who arrive at a prescribed point using a first transportation means, from reservation information of the first transportation means; an attribute information acquisition unit that acquires attribute information of the people who arrive at the prescribed point; and a prediction unit that predicts, at the prescribed point, the demand for one or more second transportation means available to the people who arrive at the prescribed point, on the basis of the people arrival count and the attribute information.

Description

Demand forecasting method, demand forecasting device, and program

[0001] The present disclosure relates to a demand forecasting method, a demand forecasting device, and a program.

[0002] As a related technique, Patent Document 1 discloses an operation support device that supports the operation of mobile objects such as buses. In Patent Document 1, the operation support device supports the operation of buses departing from bus stops located near stations where trains stop. The operation support device acquires information about the number of train passengers and predicts the number of bus users using the acquired information. The operation support device creates an operation plan by revising a pre-operation plan for bus operation using the predicted number of bus users. The operation support device transmits the created operation plan to a vehicle dispatching device that manages bus operations.

[0003] For example, the operations support device acquires information regarding the number of passengers on a train traveling from Station B to Station A. From the number of train passengers, the operations support device predicts the number of passengers on a bus departing from the bus stop in front of Station A. The operations support device stores the ratio of passengers on a bus departing from the bus stop in front of Station A to the number of train passengers, and predicts the number of bus passengers from the number of passengers and the ratio. Using the predicted number of passengers and the advance bus operation plan, the operations support device creates an operation plan for a bus departing from the front of Station A.

[0004] If the train is one that can be reserved or requires reservations, the operations support device uses the train reservation information to obtain the number of people planning to disembark at the station. The operations support device receives reservation information indicating the details of the train reservations from a management system that manages train reservations, and uses the received reservation information to estimate the number of people who will disembark from the train at the station during the time period to be predicted. The operations support device stores the ratio between the number of people disembarking at the station and the number of bus users, and predicts the number of bus users based on the estimated number and the ratio.

[0005] Japanese Patent Application Laid-Open No. 2022-102927

[0006] In Patent Document 1, a certain percentage of train passengers or people disembarking at a station are predicted to use the bus. However, the number of bus users, i.e., the number of people transferring from trains to buses at a station, is not necessarily constant relative to the number of people the train carries to the station. For example, if a train is carrying many elderly people and many elderly people disembark at a station, the proportion of people transferring from trains to buses relative to the number of people disembarking at that station may be higher than if the train were carrying many non-elderly people. The operations support device described in Patent Document 1 only considers the number of people on the train or the number of people disembarking at a station when predicting the number of bus passengers, so the accuracy of the bus passenger prediction results is considered to be low.

[0007] One of the objectives of the present disclosure is to provide a demand forecasting device, a demand forecasting method, and a program that can accurately predict, when a customer arrives at a certain location using a first means of transportation, the demand for a second means of transportation that is available to the customer from that location.

[0008] A demand forecasting method according to a first aspect of the present disclosure includes obtaining, from reservation information for a first means of transportation, a number of arrivals, which is the number of people arriving at a specified location using the first means of transportation; obtaining attribute information of the people arriving at the specified location; and predicting, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location, based on the number of arrivals and the attribute information.

[0009] A program according to a second aspect of the present disclosure causes a computer to perform processing including obtaining, from reservation information for a first means of transportation, a number of arrivals, which is the number of people arriving at a specified location using the first means of transportation; obtaining attribute information of the people arriving at the specified location; and predicting, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location based on the number of arrivals and the attribute information.

[0010] A demand prediction device according to a third aspect of the present disclosure includes an arrival number acquisition unit that acquires, from reservation information for a first means of transportation, an arrival number, which is the number of people arriving at a specified location using the first means of transportation; an attribute information acquisition unit that acquires attribute information of the people arriving at the specified location; and a prediction unit that predicts, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location based on the arrival number and the attribute information.

[0011] The demand forecasting method, demand forecasting device, and program disclosed herein can accurately predict, when a customer arrives at a certain location using a first means of transportation, the demand for a second means of transportation that the customer can use from that location.

[0012] Fig. 1 is a block diagram showing an example configuration of a demand prediction device according to the present disclosure. Fig. 2 is a schematic diagram showing the relationship between a first means of transportation and a second means of transportation. Fig. 3 is a diagram showing a specific example of a table used to calculate a score indicating the probability of using each of a plurality of second means of transportation. Fig. 4 is a diagram showing a specific example of a table used to calculate a score indicating the probability of people heading to each of a plurality of destinations. Fig. 5 is a flowchart showing the operation procedure of the demand prediction device 10. Fig. 6 is a block diagram showing an example configuration of a computer device.

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that the following description and drawings have been omitted and simplified as appropriate for clarity of explanation. In addition, in the following drawings, the same or similar elements are designated by the same reference numerals, and duplicate explanations are omitted as necessary.

[0014] FIG. 1 is a block diagram showing an example configuration of a demand prediction device according to the present disclosure. One embodiment of the present disclosure will be described using FIG. 1. The demand prediction device 10 shown in FIG. 1 includes an arrival number acquisition unit 11, an attribute information acquisition unit 12, and a prediction unit 13. The demand prediction device 10 may be physically configured as a computer device having one or more memories and one or more processors. At least some of the functions of each unit in the demand prediction device 10 may be realized by the processor executing processing in accordance with instructions read from the memory.

[0015] The arrival number acquisition unit 11 acquires the number of people arriving at a predetermined location, i.e., the number of people arriving at a predetermined location using the first transportation means, from the reservation information for the first transportation means. The first transportation means is, for example, a mass transportation means that carries many passengers. Specifically, the first transportation means may be a train, an airplane, or a ship. In the following description, the first transportation means is also referred to as trunk transportation. The arrival number acquisition unit 11 may acquire the reservation information from, for example, a server that manages reservations for the first transportation means at a mass transportation provider. Alternatively, the arrival number acquisition unit 11 may acquire the reservation information for the first transportation means from a server managed by a provider other than the mass transportation provider, such as a travel agency.

[0016] The reservation information includes, for example, information regarding the section of the first transportation means to be used. For example, if the first transportation means is a train, the reservation information includes information regarding the departure station and arrival station of the ticket or express ticket. If the first transportation means is an airplane, the reservation information includes information regarding the departure airport and arrival airport. The reservation information may include information regarding the departure time or arrival time. The reservation information may include basic information such as the name, age, and address of the person making the reservation. If the reservation information is not anonymized, the demand prediction device 10 may anonymize the reservation information.

[0017] The arrival number obtaining unit 11, for example, obtains reservation information for the first transportation means for each flight and obtains the number of people arriving at a location such as a station or an airport for each flight from the obtained reservation information. When the number of flights of the first transportation means is large, the arrival number obtaining unit 11 may, for example, add up the numbers of people arriving on multiple flights that arrive at a location within a predetermined time from a certain time and obtain the number of people arriving at a location within a predetermined time from a certain time. The arrival number obtaining unit 11 may obtain not only the number of arriving people, but also the number of groups and the number of people in each group.

[0018] The attribute information acquisition unit 12 acquires attribute information of people arriving at a predetermined location using the first transportation means. In this embodiment, the attribute information means, for example, information related to the travel characteristics or behavioral characteristics of people arriving at a predetermined location. The attribute information includes one or more attribute values. For example, at the time of reservation, the attribute information of a person who has reserved the first transportation means through a corporate reservation has an attribute value of "corporate reservation." The attribute information of a person who checks baggage on an airplane has an attribute value of "checked baggage." The attribute information of a person under the age of 18 has an attribute value of "age 18 or under." The attribute information may be included in the reservation information. In this case, the attribute information acquisition unit 12 may acquire the attribute information from, for example, a server that manages reservations for the first transportation means at a mass transit operator, or a server managed by an operator such as a travel agency.

[0019] The prediction unit 13 predicts demand for one or more second transportation modes available to people arriving at the specified location based on the predicted number of arrivals and attribute information of people arriving at the specified location. In this embodiment, the second transportation mode is a transportation mode with a lower transport capacity than the first transportation mode. The first transportation mode is called trunk transportation, while the second transportation mode is also called local transportation. The second transportation mode includes, for example, at least one of a local bus, a taxi, or a rental car.

[0020] FIG. 2 is a schematic diagram showing the relationship between a first transportation means and a second transportation means. In this example, the first transportation means includes a train 201 and an airplane 202. The predetermined location is a station where the train stops or an airport where the airplane arrives. Passengers of the train 201 or the airplane 202 board the train 201 or the airplane 202 and arrive at the predetermined location, which is the station or the airport. The arrival number acquisition unit 11 acquires the number of people arriving at the predetermined location from the reservation status of the train 201, such as a Shinkansen, or the airplane 202. For example, the arrival number acquisition unit 11 acquires the number of people who have purchased reserved seat tickets to travel from the starting station or an intermediate station to the predetermined location using a Shinkansen or a limited express train as the number of people arriving at the predetermined location.

[0021] It is assumed that some percentage of passengers who have arrived at the predetermined point will continue their travels by transferring to a second means of transportation, such as a route bus 211 or a taxi 212, at the station or airport. Passengers who have arrived at the predetermined point can travel to a tourist spot, accommodation facility, or other location by using the route bus 211 or the taxi 212. In this embodiment, the prediction unit 13 predicts how many people will use the route bus 211 and the taxi 212 at the station or airport after the train 201 or the airplane 202 arrives at the station or airport.

[0022] The prediction unit 13 calculates, for example, a score indicating the probability that a person arriving at a predetermined location will use each of multiple second transportation modes, depending on an attribute value included in the attribute information of the person arriving at the predetermined location. The prediction unit 13 calculates the scores by, for example, changing the probability that a person arriving at the predetermined location will use each transportation mode, or the score indicating the probability, from their initial values, depending on the attribute value. The initial values ​​of the probabilities or scores may be set in advance depending on characteristics of the predetermined location, such as whether the predetermined location is a commercial area or a tourist destination. The initial values ​​of the probabilities or scores may be set depending on at least a portion of the time of day, day of the week, season, and weather when the first transportation mode arrives at the predetermined location. The prediction unit 13 predicts demand for each of the multiple second transportation modes based on the score. For example, the prediction unit 13 predicts the number of people who will use each transportation mode based on the number of people arriving at the predetermined location and the probability that a person arriving at the predetermined location will use each transportation mode.

[0023] FIG. 3 is a diagram showing a specific example of a table used to calculate a score indicating the probability of using each of a plurality of second transportation modes. In this example, the second transportation modes include rental cars, taxis, and buses. The table shown in FIG. 3 defines in which direction the probability of using each transportation mode changes for each attribute value. In FIG. 3, an up arrow indicates that the probability of a person arriving at a predetermined location using the corresponding transportation mode at the predetermined location increases. A down arrow indicates that the probability of a person arriving at a predetermined location using the corresponding transportation mode at the predetermined location decreases.

[0024] For example, passengers with corporate reservations are likely to be business travelers and therefore likely to use taxis at stations or airports. Passengers with checked baggage on airplanes are likely to be traveling with heavy luggage, such as strollers, and therefore likely to use rental cars or taxis at stations or airports. Furthermore, passengers with high frequent flyer status and passengers who have used lounges are likely to be more likely to use taxis. By calculating the probability of using each means of transportation according to these characteristics, the prediction unit 13 can predict how often a person arriving at a specified location will use each means of transportation according to the attribute information of the person arriving at the specified location.

[0025] Alternatively, the prediction unit 13 may score the destinations to which a person arriving at a predetermined location will travel, according to attribute values ​​included in the attribute information. For example, the prediction unit 13 calculates a score indicating the probability that a person arriving at a predetermined location will travel to each of multiple destinations, according to attribute values ​​included in the attribute information of the person arriving at the predetermined location. For example, the prediction unit 13 calculates the scores by changing the probability that a person arriving at a predetermined location will travel to each destination, or the score indicating the probability, from their initial values, according to the attribute values. The initial values ​​of the probabilities or scores may be set in advance according to characteristics of the predetermined location, such as whether the predetermined location is a commercial area or a tourist destination. The initial values ​​of the probabilities or scores may be set according to at least a portion of the time of day, day of the week, season, and weather when the first transportation mode arrives at the predetermined location.

[0026] The prediction unit 13 may predict the demand for each of the multiple second transportation modes based on the calculated scores of people who arrive at the predetermined point heading to each destination. The prediction unit 13, for example, stores information indicating, for each destination, the probability or percentage of people using each transportation mode to travel to that destination. For example, for the destination "tourist destination," the prediction unit 13 stores information indicating that the percentage of people who travel from the predetermined point to the tourist destination by bus is 10%, the percentage of people who travel by rental car is 50%, and the percentage of people who travel by taxi is 40%. Furthermore, for the destination "XX Company," the prediction unit 13 stores information indicating that the percentage of people who travel from the predetermined point to XX Company by bus is 5%, the percentage of people who travel by rental car is 10%, and the percentage of people who travel by taxi is 85%. The prediction unit 13 predicts the number of people who will use each transportation mode based on the number of people who arrive at the predetermined point, the probability that people who arrive at the predetermined point will head to each destination, and the probability that people will use each transportation mode for each destination.

[0027] FIG. 4 shows a specific example of a table used to calculate a score indicating the probability that a person will head to each of multiple destinations. In this example, potential destinations for a person arriving at a specified location include tourist attractions, businesses, and hotels. The table shown in FIG. 4 defines in which direction the probability of heading to each destination changes for each attribute value. In FIG. 4, an up arrow indicates an increase in the probability that a person arriving at a specified location will head to the corresponding destination. A down arrow indicates a decrease in the probability that a person arriving at a specified location will head to the corresponding destination.

[0028] For example, passengers with corporate reservations are likely to be business travelers and head to a well-known local company for business purposes such as a business meeting from the station or airport. Passengers with children are unlikely to head to a company from the station or airport, and are more likely to head to a tourist spot or hotel. The prediction unit 13 calculates the probability of heading to each of the possible destinations based on these characteristics. In this case, too, it is possible to predict the destination of a person arriving at a predetermined location based on the attribute information of the person, and from the prediction result, it is possible to predict which means of transportation the person arriving at the predetermined location will use.

[0029] The above-described two predictions of demand for the second transportation means may be used in combination. For example, the prediction unit 13 calculates a first score indicating the probability of using each of the plurality of second transportation means according to an attribute value included in the attribute information of a person arriving at a predetermined location. The prediction unit 13 predicts the demand for each of the plurality of second transportation means according to the first score. Furthermore, the prediction unit 13 calculates a second score indicating the probability that a person arriving at the predetermined location will head to each of the plurality of destinations according to the attribute value included in the attribute information of the person arriving at the predetermined location. The prediction unit 13 predicts the demand for each of the plurality of second transportation means according to the second score. The prediction unit 13 may integrate the demand for the second transportation means predicted according to the first score and the demand for the second transportation means predicted according to the second score. For example, the prediction unit 13 may average the two demand prediction results as the prediction result for the demand for the second transportation means. Alternatively, the prediction unit 13 may weight and add the prediction results of the two demands, for example, and use the weighted addition demand as the prediction result of the demand for the second transportation means.

[0030] Next, the operation procedure will be explained. Fig. 5 is a flowchart showing the operation procedure of the demand prediction device 10. The operation procedure of the demand prediction device 10 corresponds to a demand prediction method. In the demand prediction device 10, the arrival number acquisition unit 11 acquires reservation information for a first means of transportation (step S1). The arrival number acquisition unit 11 acquires the number of people arriving at a predetermined location using the first means of transportation from the acquired reservation information (step S2).

[0031] The attribute information acquisition unit 12 acquires attribute information of people arriving at the predetermined location (step S3). The prediction unit 13 predicts demand for the second transportation mode based on the number of people arriving at the predetermined location and the acquired attribute information (step S4). In step S4, the prediction unit 13 may acquire information such as the time of day, day of the week, season, and weather when the first transportation mode arrives at the predetermined location as additional information, and predict demand for the second transportation mode based on the attribute information and the additional information.

[0032] In step S4, the prediction unit 13 predicts, for example, how many people will use taxis, route buses, and rental cars. The prediction unit 13 provides the demand prediction results to the operator of the second transportation means. For example, the prediction unit 13 provides a taxi company with prediction results indicating how many people who arrive at a specific location at a certain time using the first transportation means are predicted to use taxis. An operator of the second transportation means, such as a regional transportation operator, can dispatch vehicles based on the demand prediction results. This allows the operator of the second transportation means to efficiently utilize vehicle resources and maximize business opportunities.

[0033] In this embodiment, the attribute information acquisition unit 12 acquires attribute information of people arriving at a predetermined location using the first transportation means. The prediction unit 13 predicts demand for the second transportation means based on the number of people arriving at the predetermined location using the first transportation means and the acquired attribute information. In this embodiment, demand for the second transportation means can be predicted based on the attributes of people arriving at the predetermined location. This improves the accuracy of demand prediction compared to predicting demand for the second transportation means simply based on the number of people.

[0034] In the present disclosure, the demand prediction device 10 may be configured using a computer device or a server device. Fig. 6 is a block diagram showing an example configuration of a computer device that may be used as the demand prediction device 10. The computer device 500 includes a processor 510 such as a CPU (Central Processing Unit), a storage unit 520, a ROM (Read Only Memory) 530, a RAM (Random Access Memory) 540, a communication interface (IF) 550, and a user interface 560.

[0035] The communication interface 550 is an interface for connecting the computer device 500 to a communication network via wired communication means, wireless communication means, etc. The user interface 560 includes a display unit such as a display, and an input unit such as a keyboard, a mouse, and a touch panel.

[0036] The storage unit 520 is an auxiliary storage device that can store various types of data. The storage unit 520 does not necessarily have to be a part of the computer device 500, but may be an external storage device or cloud storage connected to the computer device 500 via a network.

[0037] The ROM 530 is a non-volatile storage device. For example, a semiconductor storage device with a relatively small capacity, such as a flash memory, is used as the ROM 530. The programs executed by the CPU 510 can be stored in the storage unit 520 or the ROM 530. The storage unit 520 or the ROM 530 stores, for example, various programs for realizing the functions of each unit of the demand prediction device 10.

[0038] The program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include RAM, ROM, flash memory, solid-state drives (SSDs) or other memory technologies, compact discs (CDs), digital versatile discs (DVDs), Blu-ray discs or other optical disc storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices. The program may also be transmitted on a transitory computer-readable medium or a communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0039] The RAM 540 is a volatile storage device. Various semiconductor memory devices such as a dynamic random access memory (DRAM) or a static random access memory (SRAM) are used for the RAM 540. The RAM 540 can be used as an internal buffer for temporarily storing data and the like. The CPU 510 loads a program stored in the storage unit 520 or the ROM 530 into the RAM 540 and executes the program. The CPU 510 executes the program, thereby realizing the functions of each unit in the demand prediction device 10. The CPU 510 may have an internal buffer for temporarily storing data and the like.

[0040] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

[0041] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0042] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0043] [Supplementary Note 1] A demand forecasting method comprising: obtaining, from reservation information for a first means of transportation, a number of arrivals, which is the number of people who will arrive at a specified location using the first means of transportation; obtaining attribute information of the people who will arrive at the specified location; and predicting, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location, based on the number of arrivals and the attribute information.

[0044] [Supplementary Note 2] The demand forecasting method according to Supplementary Note 1, wherein the reservation information includes a route of the first transportation means and attribute information of a person making a reservation, and the attribute information is acquired from the reservation information.

[0045] [Supplementary Note 3] The demand forecasting method according to Supplementary Note 1 or 2, wherein the first transportation means includes at least one of a railway, an airplane, or a ship.

[0046] [Supplementary Note 4] The demand forecasting method according to any one of Supplementary Notes 1 to 3, wherein the second transportation means has a lower transport capacity than the first transportation means.

[0047] [Supplementary Note 5] The demand forecasting method according to any one of Supplementary Notes 1 to 4, wherein the second means of transportation includes at least one of a local bus, a taxi, or a rental car.

[0048] [Supplementary Note 6] The demand forecasting method according to any one of Supplementary Notes 1 to 5, wherein the attribute information includes one or more attribute values, and forecasting the demand for the second means of transportation includes calculating a score indicating a probability of using each of the plurality of second means of transportation according to the attribute values ​​included in the attribute information of people arriving at the specified location, and forecasting the demand for each of the plurality of second means of transportation according to the score.

[0049] [Supplementary Note 7] The demand forecasting method according to any one of Supplementary Notes 1 to 5, wherein the attribute information includes one or more attribute values, and forecasting the demand for the second means of transportation includes calculating a score indicating a probability that a person arriving at the specified location will head to each of a plurality of destinations according to the attribute values ​​included in the attribute information of the person arriving at the specified location, and forecasting the demand for each of the plurality of second means of transportation according to the score.

[0050] [Supplementary Note 8] The demand forecasting method according to any one of Supplementary Notes 1 to 5, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes: calculating a first score indicating a probability that each of the plurality of second means of transportation will be used according to the attribute values ​​included in the attribute information of people arriving at the specified location; predicting the demand for each of the plurality of second means of transportation according to the first score; calculating a second score indicating a probability that a person arriving at the specified location will head to each of a plurality of destinations according to the attribute values ​​included in the attribute information of people arriving at the specified location; predicting the demand for each of the plurality of second means of transportation according to the second score; and integrating the demand for each of the plurality of second means of transportation predicted according to the first score and the demand for each of the plurality of second means of transportation predicted according to the second score.

[0051] [Supplementary Note 9] A program that causes a computer to execute a process including: obtaining, from reservation information for a first means of transportation, a number of arrivals, which is the number of people who will arrive at a specified location using the first means of transportation; obtaining attribute information of the people who will arrive at the specified location; and predicting, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location, based on the number of arrivals and the attribute information.

[0052] [Supplementary Note 10] The program according to Supplementary Note 9, wherein the reservation information includes a section of the first transportation means to be used and attribute information of a person who made a reservation, and the attribute information is acquired from the reservation information.

[0053] [Supplementary Note 11] The program according to Supplementary Note 9 or 10, wherein the first means of transportation includes at least one of a railway, an airplane, or a ship.

[0054] [Supplementary Note 12] The program according to any one of Supplementary Notes 9 to 11, wherein the second transportation means is a transportation means having a lower transportation capacity than the first transportation means.

[0055] [Supplementary Note 13] The program according to any one of Supplementary Notes 9 to 12, wherein the second means of transportation includes at least one of a local bus, a taxi, or a rental car.

[0056] [Supplementary Note 14] The program described in any one of Supplementary Notes 9 to 13, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes calculating a score indicating the probability of using each of the plurality of second means of transportation according to the attribute values ​​included in the attribute information of people arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation according to the score.

[0057] [Supplementary Note 15] The program described in any one of Supplementary Notes 9 to 13, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes calculating a score indicating a probability that a person arriving at the specified location will head to each of a plurality of destinations according to the attribute values ​​included in the attribute information of the person arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation according to the score.

[0058] [Supplementary Note 16] The program according to any one of Supplementary Notes 9 to 13, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes: calculating a first score indicating a probability that each of the plurality of second means of transportation will be used according to the attribute value included in the attribute information of a person arriving at the specified location; predicting the demand for each of the plurality of second means of transportation according to the first score; calculating a second score indicating a probability that a person arriving at the specified location will head to each of a plurality of destinations according to the attribute value included in the attribute information of the person arriving at the specified location; predicting the demand for each of the plurality of second means of transportation according to the second score; and integrating the demand for each of the plurality of second means of transportation predicted according to the first score and the demand for each of the plurality of second means of transportation predicted according to the second score.

[0059] [Supplementary Note 17] A demand prediction device comprising: an arrival number acquisition unit that acquires, from reservation information for a first means of transportation, an arrival number, which is the number of people who will arrive at a predetermined point using the first means of transportation; an attribute information acquisition unit that acquires attribute information of the people who will arrive at the predetermined point; and a prediction unit that predicts, at the predetermined point, demand for one or more second means of transportation that can be used by people arriving at the predetermined point, based on the arrival number and the attribute information.

[0060] [Supplementary Note 18] The demand prediction device according to Supplementary Note 17, wherein the reservation information includes a route of the first transportation means and attribute information of a person making a reservation, and the attribute information acquisition unit acquires the attribute information from the reservation information.

[0061] [Supplementary Note 19] The demand prediction device according to Supplementary Note 17 or 18, wherein the first transportation means includes at least one of a railway, an airplane, or a ship.

[0062] [Supplementary Note 20] The demand prediction device according to any one of Supplementary Notes 17 to 19, wherein the second transportation means is a transportation means having a lower transport capacity than the first transportation means.

[0063] [Supplementary Note 21] The demand prediction device according to any one of Supplementary Notes 17 to 20, wherein the second means of transportation includes at least one of a local bus, a taxi, or a rental car.

[0064] [Supplementary Note 22] The demand prediction device described in any one of Supplementary Notes 17 to 21, wherein the attribute information includes one or more attribute values, and the prediction unit calculates a score indicating a probability of using each of the plurality of second transportation means according to the attribute values ​​included in the attribute information of people arriving at the specified location, and predicts demand for each of the plurality of second transportation means according to the score.

[0065] [Supplementary Note 23] The demand prediction device described in any one of Supplementary Notes 17 to 21, wherein the attribute information includes one or more attribute values, and the prediction unit calculates a score indicating a probability that a person arriving at the specified location will head to each of a plurality of destinations according to the attribute values ​​included in the attribute information of the person arriving at the specified location, and predicts demand for each of the plurality of second transportation modes according to the score.

[0066] [Supplementary Note 24] The demand prediction device according to any one of Supplementary Notes 17 to 21, wherein the attribute information includes one or more attribute values, and the prediction unit: calculates a first score indicating a probability that each of the plurality of second transportation means will be used according to the attribute value included in the attribute information of the person arriving at the specified location, and predicts demand for each of the plurality of second transportation means according to the first score, calculates a second score indicating a probability that the person arriving at the specified location will head to each of a plurality of destinations according to the attribute value included in the attribute information of the person arriving at the specified location, and predicts demand for each of the plurality of second transportation means according to the second score, and integrates the demand for each of the plurality of second transportation means predicted according to the first score and the demand for each of the plurality of second transportation means predicted according to the second score.

[0067] Some or all of the elements described in any appendix may be applied to a variety of hardware, software, recording means for recording software, systems, and methods.

[0068] 10: Demand forecasting device 11: Arrival number acquisition unit 12: Attribute information acquisition unit 13: Prediction unit 201: Train 202: Airplane 211: Route bus 212: Taxi 500: Computer device 510: Processor 520: Storage unit 530: ROM 540: RAM 550: Communication interface 560: User interface

Claims

1. A demand forecasting method comprising: obtaining, from reservation information for a first means of transportation, a number of arrivals, which is the number of people arriving at a specified location using the first means of transportation; obtaining attribute information of the people arriving at the specified location; and predicting, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location, based on the number of arrivals and the attribute information.

2. The demand forecasting method according to claim 1, wherein the reservation information includes the section of the first means of transportation used and attribute information of the person making the reservation, and the attribute information is obtained from the reservation information.

3. A demand forecasting method according to claim 1 or 2, wherein the first means of transportation includes at least one of a railway, an airplane, or a ship.

4. A demand forecasting method according to any one of claims 1 to 3, wherein the second transportation means has a lower transport capacity than the first transportation means.

5. A demand forecasting method according to any one of claims 1 to 4, wherein the second means of transportation includes at least one of a local bus, a taxi, or a rental car.

6. A demand forecasting method according to any one of claims 1 to 5, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes calculating a score indicating the probability of using each of the plurality of second means of transportation according to the attribute values ​​included in the attribute information of people arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation according to the score.

7. A demand forecasting method according to any one of claims 1 to 5, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes calculating a score indicating the probability that a person arriving at the specified location will head to each of a plurality of destinations, depending on the attribute value included in the attribute information of the person arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation depending on the score.

8. A demand forecasting method according to any one of claims 1 to 5, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes: calculating a first score indicating a probability that each of the plurality of second means of transportation will be used according to the attribute value included in the attribute information of people arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation according to the first score; calculating a second score indicating a probability that a person arriving at the specified location will head to each of a plurality of destinations according to the attribute value included in the attribute information of people arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation according to the second score; and integrating the demand for each of the plurality of second means of transportation predicted according to the first score and the demand for each of the plurality of second means of transportation predicted according to the second score.

9. A program that causes a computer to execute a process including: obtaining, from reservation information for a first means of transportation, a number of arrivals, which is the number of people arriving at a specified location using the first means of transportation; obtaining attribute information of the people arriving at the specified location; and predicting, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location based on the number of arrivals and the attribute information.

10. The program according to claim 9, wherein the reservation information includes the section of the first means of transportation to be used and attribute information of the person making the reservation, and the attribute information is obtained from the reservation information.

11. The program according to claim 9 or 10, wherein the first means of transportation includes at least one of a railway, an airplane, or a ship.

12. The program according to any one of claims 9 to 11, wherein the second transportation means is a transportation means having a lower transportation capacity than the first transportation means.

13. The program according to any one of claims 9 to 12, wherein the second means of transportation includes at least one of a local bus, a taxi, or a rental car.

14. A program described in any one of claims 9 to 13, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes calculating a score indicating the probability of using each of the plurality of second means of transportation depending on the attribute values ​​included in the attribute information of people arriving at the specified location, and predicting the demand for each of the plurality of second means of transportation depending on the score.

15. A program described in any one of claims 9 to 13, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes calculating a score indicating the probability that a person arriving at the specified location will head to each of multiple destinations depending on the attribute value included in the attribute information of the person arriving at the specified location, and predicting the demand for each of the multiple second means of transportation depending on the score.

16. The program described in any one of claims 9 to 13, wherein the attribute information includes one or more attribute values, and predicting the demand for the second means of transportation includes: calculating a first score indicating the probability that each of the plurality of second means of transportation will be used according to the attribute value included in the attribute information of people arriving at the specified location; predicting the demand for each of the plurality of second means of transportation according to the first score; calculating a second score indicating the probability that people arriving at the specified location will head to each of a plurality of destinations according to the attribute value included in the attribute information of people arriving at the specified location; predicting the demand for each of the plurality of second means of transportation according to the second score; and integrating the demand for each of the plurality of second means of transportation predicted according to the first score and the demand for each of the plurality of second means of transportation predicted according to the second score.

17. A demand prediction device comprising: an arrival number acquisition unit that acquires, from reservation information for a first means of transportation, an arrival number, which is the number of people arriving at a specified location using the first means of transportation; an attribute information acquisition unit that acquires attribute information of people arriving at the specified location; and a prediction unit that predicts, at the specified location, demand for one or more second means of transportation that can be used by people arriving at the specified location based on the arrival number and the attribute information.

18. The demand forecasting device described in claim 17, wherein the reservation information includes the section of the first means of transportation used and attribute information of the person making the reservation, and the attribute information acquisition unit acquires the attribute information from the reservation information.

19. The demand prediction device according to claim 17 or 18, wherein the first means of transportation includes at least one of a railway, an airplane, or a ship.

20. A demand prediction device according to any one of claims 17 to 19, wherein the second transportation means has a lower transport capacity than the first transportation means.

Images