Railroad use management system, use probability estimation device, use probability estimation method, and program

Abstract

To provide a railroad use management system, a use probability estimation device, a use probability estimation method, and a program capable of improving both of operation efficiency of trains having an excellent vehicle and user's usability using the excellent vehicle by accurately acquiring in advance user's use probability of the excellent vehicle requiring extra fee other than fare.SOLUTION: A railroad use management system 100 comprises the steps of: determining a use section used by a user on a railroad route by a control unit 11 (S12); and estimating use probability of estimated users using a specific vehicle operated in the use section on the basis of a reserve seat purchase history and the use section (S23). Further, the number of estimated persons using the excellent vehicle with fare is estimated on the basis of each of the use probabilities of a plurality of estimated persons.SELECTED DRAWING: Figure 12

Description

[Technical Field]

[0001] The present invention relates to a railway usage management system, a usage probability estimation device, a usage probability estimation method, and a program. [Background technology]

[0002] Railway vehicles operating on railway lines include general carriages, which require passengers to pay a standard fare to ride, and express carriages, which require a separate fee in addition to the standard fare. In Japan, local trains, semi-express trains, express trains, and other trains (hereinafter referred to as general trains), which passengers can ride for just the fare, are generally made up of the general carriages. Also, express trains, such as limited express trains, which require an additional fee such as a limited express fare, are made up of the express carriages. In recent years, in order to meet the demand for seated commuting, trains made up of a mixture of the general carriages and the express carriages have been operating during rush hour.

[0003] For example, if a regular train and an express train are running on the same line, a user can choose to board either the regular train or the express train. To board the express train, the user must either purchase a ticket (e.g., a reserved seat express ticket) for the express train in advance at a station ticket counter or ticket machine, or log in to a website operated by the railway company using their registered ID, make a reservation for the express train on the website, and link the reservation information to the identification code on the user's IC card.

[0004] In recent years, with the widespread use of IC cards and mobile devices such as smartphones, passengers can access the website and reserve a reserved seat on an available express train even while they are waiting on the platform for the arrival of the local train.

[0005] Conventionally, a transportation planning system is known that creates a transportation plan to increase the number of reserved seats on a train when the ratio of the reserved seat demand forecast value to the reserved seat capacity exceeds a threshold value (see Patent Document 1). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-100485 Summary of the Invention [Problem to be solved by the invention]

[0007] However, for example, if the number of reserved seats purchased for the express train is less than the reserved seat capacity, the express train must operate with empty seats, resulting in poor operational efficiency. Furthermore, if the reserved seat capacity is met despite demand for seats, passenger demand cannot be met, resulting in poor passenger convenience. Conventionally, before operating the express train, railway operators determine the expected number of passengers for the express train on the operating day based on empirical rules, taking into account the number of reserved seat purchases (reservations), and then determine the number of express train cars for the express train based on the expected number of passengers. However, the expected number of passengers based on empirical rules may differ significantly from the actual number of passengers. In this case, the operational efficiency of the express train and the convenience of the passengers cannot be improved.

[0008] The object of the present invention is to provide a railway usage management system, usage probability estimation device, usage probability estimation method, and program that can improve both the operating efficiency of trains that have first-class cars and the convenience of users who use first-class cars by accurately determining in advance the usage probability of users using first-class cars, which require a usage fee in addition to the train fare. [Means for solving the problem]

[0009] According to one aspect of the present invention, a railway utilization management system includes a utilization section determination unit and a utilization probability estimation unit. The utilization section determination unit determines a utilization section of a railway line that a user will utilize, the utilization section being a section from a predetermined departure station to a destination station. The utilization probability estimation unit estimates, based on the utilization section, a utilization probability that the user will utilize a specific express train that travels to the destination station for at least a portion of the utilization section, among express trains that require a utilization fee in addition to the fare required for riding a regular train.

[0010] According to another aspect of the present invention, a utilization probability estimation device includes a utilization section determination unit and a utilization probability estimation unit. The utilization section determination unit determines a utilization section of a railway line that a user will use, the utilization section being a section from a predetermined departure station to a destination station. The utilization probability estimation unit estimates, based on the utilization section, a utilization probability that the user will use a specific express train that travels to the destination station for at least a portion of the utilization section, among express trains that require a utilization fee in addition to the fare required for riding a regular train.

[0011] A utilization probability estimation method according to another aspect of the present invention is a method in which one or more processors execute a utilization section determination step and a utilization probability estimation step. The utilization section determination step determines a utilization section on a railway line that a user will use, which is a section from a predetermined departure station to a destination station. The utilization probability estimation step estimates, based on the utilization section, a utilization probability that the user will use a specific express car that travels to the destination station for at least a portion of the utilization section, among express cars that require a utilization fee in addition to the fare required for riding in a regular car.

[0012] A program according to another aspect of the present invention is a program for causing one or more processors to execute the utilization interval determination step and the utilization probability estimation step of the utilization probability estimation method.

[0013] The present invention can also be understood as an invention of a non-transitory computer-readable storage medium on which the program is stored. [Effects of the Invention]

[0014] According to the present invention, by accurately determining in advance the probability that a passenger will use a first-class carriage, which requires a usage fee in addition to the fare, it is possible to improve both the operating efficiency of trains that have such first-class carriages and the convenience of passengers who use such first-class carriages. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a diagram showing the configuration of a railway utilization management system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing the configuration of a management device of a railway utilization management system according to an embodiment of the present invention. [Figure 3] FIG. 3 is a diagram showing an example of user registration data used in the railway utilization management system according to the embodiment of the present invention. [Figure 4] FIG. 4 is a diagram showing an example of a railway line. [Figure 5] FIG. 5 is a diagram showing an example of table data of the accuracy variable U used in the railway utilization management system according to the embodiment of the present invention. [Figure 6] FIG. 6 is a diagram showing an example of table data of the accuracy variable V used in the railway utilization management system according to the embodiment of the present invention. [Figure 7] FIG. 7 is a diagram showing an example of table data of the probability variable W used in the railway utilization management system according to the embodiment of the present invention. [Figure 8] FIG. 8 is a diagram showing an example of table data showing the set values ​​of the accuracy variable X used in the railway utilization management system according to the embodiment of the present invention. [Figure 9] FIG. 9 is a diagram showing an example of table data of the accuracy variable Y used in the railway utilization management system according to the embodiment of the present invention. [Figure 10] FIG. 10 is a diagram showing an example of table data of the accuracy variable Z used in the railway utilization management system according to the embodiment of the present invention. [Figure 11] FIG. 11 is a diagram showing a list of potential users determined by the railway usage management system according to the embodiment of the present invention. [Figure 12] FIG. 12 is a diagram showing a usage probability table including the numerical values ​​of each accuracy variable of users whose usage probabilities are to be estimated and their usage probabilities. [Figure 13] FIG. 13 is a flowchart showing an example (first processing example) of a utilization probability estimation process executed by the control unit of the management device. [Figure 14] FIG. 14 is a flowchart showing an example (second processing example) of a utilization probability estimation process executed by the control unit of the management device. [Figure 15] FIG. 15 is a flowchart showing an example (second processing example) of a utilization probability estimation process executed by the control unit of the management device. [Figure 16] FIG. 16 is a flowchart illustrating an example (third processing example) of a utilization probability estimation process executed by the control unit of the management device. [Figure 17] FIG. 17 is a flowchart illustrating an example of the probability variable correction process executed by the control unit of the management device. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. Note that the embodiments described below are merely examples of the present invention and do not limit the technical scope of the present invention.

[0017] [Railway Usage Management System 100] 1 is a network diagram showing the configuration of a railway usage management system 100 (hereinafter simply referred to as the "management system") according to an embodiment of the present invention. The management system 100 is a system that performs an estimation process to estimate the probability that railway users will use so-called first-class cars operated by a railway operator, and a prediction process to predict in advance the number of users who will use the first-class cars.

[0018] The express cars are different from ordinary cars that can be boarded with just the regular fare, and require a separate fee in addition to the regular fare, and are also called paid cars. The ordinary cars are cars that are part of ordinary trains such as local trains, semi-express trains, and express trains that can be boarded with just the regular fare. The paid cars are cars that are part of express trains that require a separate express fee, for example.

[0019] In this embodiment, the general trains are defined as local trains, semi-express trains, express trains, etc. made up of the general cars, and the express trains are defined as premium trains, etc. made up of the paid cars. In addition, it is assumed that the general trains and the premium trains share at least a portion of the same route. In other words, the general cars and the premium cars operate on a route that is partially shared.

[0020] 1, the management system 100 includes a management device 10 and a database 30. The management system 100 is an example of a railway usage management system of the present invention. The management device 10 is also an example of a usage probability estimation device of the present invention.

[0021] Hereinafter, the management system 100 will be described as being independent from other existing systems, such as a seat reservation system 200 (one example of a reservation system of the present invention) that manages reservations for express trains and reserved seats on express trains, a boarding / alighting management system 300 that manages the entry and exit of railway users, or a point management system 400 that manages points awarded to registered users. Note that the management system 100 may be incorporated into an existing system, such as the seat reservation system 200, the boarding / alighting management system 300, or the point management system 400. Furthermore, the management system 100 may include the seat reservation system 200, the boarding / alighting management system 300, or the point management system 400.

[0022] 1, in the management system 100, the management device 10 is communicably connected to the database 30 via a network N1, which is a wireless communication network or a wired communication network. The network N1 is, for example, a dedicated line or a public line.

[0023] The management device 10 is, for example, an information processing device managed by a railway operator or its related business operator, such as a server device or a cloud server. The management device 10 is installed, for example, in the railway operator's central control room. The management device 10 is not limited to being configured with a single computer, but may be a computer system in which multiple computers operate in cooperation, or a cloud computing system. For example, the management device 10 may be configured as a system in which multiple station server devices (hereinafter sometimes referred to as station servers) installed at each railway station operate in cooperation. Furthermore, various processes executed by the management device 10 may be executed by a single processor, or may be executed in a distributed manner by multiple processors. Computer software for operating the management system 100 of this embodiment is installed in the management device 10.

[0024] The management device 10 is further connected to a user terminal 40, an existing seat reservation system 200, an existing boarding and alighting management system 300, an existing point management system 400, and the like via a network N2 so as to be able to communicate with each other.

[0025] The user terminal 40 is an information processing device or terminal device used by a user riding on the regular train, the express train, etc. The user terminal 40 is, for example, a portable terminal such as a smartphone or tablet terminal that can be carried by the user. An application (software) is installed on the user terminal 40 to work in conjunction with the management system 100, output various requests to the management device 10, and display information output from the management device 10.

[0026] The seat reservation system 200 is a conventionally well-known system that, based on a purchase request from a user, reserves a ride on an express train that departs at a time desired by the user from a section desired by the user, reserves a reserved seat in a carriage (express carriage) of the express train, and issues the reserved ticket. The seat reservation system 200 manages reservation information for express trains and reserved seats that users have reserved in advance at station counters or ticket vending machines, and reservation information for express trains and reserved seats that users have reserved in advance via a website operated by a railway company. The seat reservation system 200 also manages reservation history information related to past reservations for express trains that have already operated and past reservations for reserved seats in the express carriages.

[0027] The seat reservation system 200 also manages purchase history data 201, which includes express car usage history such as the express train riding history for each user ID of the express trains that have already operated and the reserved seat ticket purchase history for each user ID who purchased a reserved seat ticket for the express car. The purchase history data 201 is stored in a storage device provided in the seat reservation system 200. The express car usage history includes, for example, the riding history of an express car with unreserved seats, whether or not a reserved seat ticket was purchased (whether or not an express train was used), the number of times a reserved seat ticket was purchased (the number of times an express train was used), the time and period of use of the reserved seat, operation information of the express train used (departure date, departure time from departure station, arrival date, arrival time at stop stations, etc.), the valid section of the purchased reserved seat, and the fare for the purchased reserved seat (reserved seat fare). The purchase history data 201 may be stored in a database 30, which will be described later.

[0028] When the seat reservation system 200 receives a transmission request from the management device 10, it extracts the express car usage history corresponding to the user ID included in the transmission request from the purchase history data 201, and transmits the express train riding history, reserved ticket purchase history, reservation information, reservation history information, etc. of the user ID to the management device 10.

[0029] The boarding and alighting management system 300 is a conventionally well-known system that acquires and manages boarding and alighting information such as a user's entry station, entry time (ticket gate entry time), exit station, exit time (ticket gate exit time), and boarding date (date of use) by reading information from a contactless IC card using an automatic ticket gate installed at the ticket gate of a railway station. The boarding and alighting management system 300 manages the boarding and alighting information transferred from the station server installed at each station for each user ID.

[0030] The point management system 400 is a conventionally well-known system that grants points and benefits (such as coupons) to registered users (hereinafter referred to as point members) of the point service realized by the point management system 400 in accordance with the usage history of railway vehicles operated by the railway operator and the usage history of related facilities operated by the railway operator, and manages the granted points and benefits. The point service may be provided by the railway operator or its related business, or may be provided by a different business that is affiliated with the railway operator. Note that the point service is not limited to a service that grants points, but may also be a service that grants benefits such as discount tickets, coupons, and exchange tickets.

[0031] In the point management system 400, the user ID commonly used in the management system 100, the seat reservation system 200, and the boarding and disembarking management system 300 is used as the identification information of the point member. The point management system 400 registers a user who has applied to register to use the point service provided by the point management system 400 as the point member, and manages the user ID that identifies the point member, the number of points and benefits issued to the point member, the number of years the point member has been registered (number of years of continued registration), and the like, using point member data 401. The point member data 401 is stored in a storage device provided in the point management system 400. The point member data 401 may also be stored in the database 30, which will be described later.

[0032] When the point management system 400 receives a transmission request from the management device 10, it refers to the point member data 401 and performs a process of searching for the member points corresponding to the user ID included in the transmission request. If the member points corresponding to the user ID are found, it sends point member registration information to the management device 10 indicating that the user has already registered as a point member, and if not found, it sends point member unregistration information to the management device 10 indicating that the user is not yet registered as a point member. When the management device 10 acquires this information, it registers whether the point member is registered, the number of years the point member has been registered, and so forth in user registration data 31, which will be described later, and updates the user registration data 31.

[0033] The database 30 is a storage device such as an HDD or SSD. The database 30 is configured as an external device such as another server device or another storage device that can communicate data with the management device 10 via the network N1. The database 30 may be a storage device provided in the management device 10, or may be a storage device connected to the management device 10 via a local network.

[0034] [Database 30] 2, database 30 stores user registration data 31, boarding and alighting history data 32, occupancy rate data 33, route data 34, and bus schedule data 35. Database 30 is allocated a plurality of storage areas for storing each data, and each data is stored in each storage area. Note that each data 31 to 35 may be stored separately in a plurality of storage devices communicably connected to management device 10.

[0035] The user registration data 31 includes various types of registration information (user registration information) related to multiple users who use railways. The user registration information included in the user registration data 31 is, for example, information registered when purchasing an IC passenger card that can be used on railway lines operated by a railway operator. The IC passenger card stores at least information such as the user ID of the IC passenger, the type of the IC passenger card, the expiration date of the IC passenger card, and, if the IC passenger card has a commuter pass function (hereinafter abbreviated as a commuter pass), the commuter pass section.

[0036] Fig. 3 is an example of user registration data 31 used in management system 100. As shown in Fig. 3, the user registration data 31 includes information registered when an IC transportation card that functions as a commuter pass is purchased. Specifically, the user registration data 31 includes information such as the user ID, user name, user attributes (age, gender, student status, etc.), IC transportation card type (commuter commuter pass, student commuter pass), the commuter pass area, and contact information.

[0037] In addition, the user registration data 31 includes attribute information indicating the user's attributes, such as the user's age and gender, as well as whether or not the user is registered as a point member for the point service provided by the point management system 400, and the number of years the point member has been registered.

[0038] The boarding and alighting history data 32 includes past boarding and alighting information (boarding and alighting history information) of users who have used the railway line. The boarding and alighting history data 32 is sometimes referred to as OD (Origin to Destination) data. For example, the boarding and alighting history information includes the entry time when a user enters a departure station when traveling by train, entry station information, exit time when a user exits a destination station, exit station information, entry date (date of use, date of boarding), and user ID.

[0039] When a user passes through an automatic ticket gate installed at a station, the boarding and alighting information is read from the user's IC card by the automatic ticket gate. The boarding and alighting information obtained by the automatic ticket gate is managed by a station server for each user ID, and is transferred from each station server to boarding and alighting management system 300. Boarding and alighting management system 300 compiles the boarding and alighting information transferred from each station server into boarding and alighting history data 32 so that it can be managed for each user ID, and stores the data in database 30. Boarding and alighting management system 300 is a well-known system operated and managed by each railway operator, but it may also be, for example, a mutual use system managed and operated by Japan's IC Card Interoperability Center Co., Ltd., or the National Integrated Transport Analysis System (NITAS) managed and operated by Japan's Ministry of Land, Infrastructure, Transport and Tourism.

[0040] The passenger occupancy rate data 33 includes the passenger occupancy rates of all trains operating on each line. The passenger occupancy rate of the general train is calculated, for example, based on the detected values ​​of weight sensors installed in each car of the general train. The passenger occupancy rate of the express train is the ratio of the actual number of reserved seat purchases to the reserved seat capacity. The passenger occupancy rate of the general train is acquired by a conventionally well-known operation system that comprehensively controls train operations. The operation system acquires the detected values ​​of the weight sensors from the general trains in operation at predetermined intervals and calculates the passenger occupancy rate of the general trains in operation. The operation system also acquires the reservation history information for reserved seats of the express trains in operation from the seat reservation system 200 at predetermined intervals and calculates the passenger occupancy rate of the express trains in operation. After operation or each time the operation system calculates the passenger occupancy rate of a train in operation, it compiles the data into passenger occupancy rate data 33 in chronological order and stores it in the database 30.

[0041] The route data 34 includes information about the railway lines on which each train runs. For example, the route data 34 includes station information for all railway lines, the distance from the starting point to the end point of each line, the distance between stations on each line, etc. In this embodiment, the route data 34 includes route information for multiple railway lines operated by multiple railway operators.

[0042] The train schedule data 35 includes operation schedule information for each train on each railway line. The operation schedule information is timetable information for each train, both current and past, and specifically includes the scheduled time of departure of each train from a starting station on a given railway line, the scheduled time of arrival at intermediate stops, the scheduled time of departure from the stops, the scheduled time of arrival at the terminal station on the railway line, etc.

[0043] [Management device 10] The specific configuration of the management device 10 will be described below with reference to FIG.

[0044] The management device 10 is intended to realize the management system 100 of this embodiment, and as shown in Figure 2, it includes a control unit 11, a memory unit 12, a communication unit 13, a display unit 14, and an operation unit 15.

[0045] The communication unit 13 is a communication interface that connects the management device 10 to the networks N1 and N2 and performs data communication with each device connected to the networks N1 and N2 in accordance with a predetermined communication protocol. Specifically, the communication unit 13 performs data communication with the database 30 via the network N1. The communication unit 13 also performs data communication with the user terminal 40, the seat reservation system 200, and the boarding and alighting management system 300 via the network N2.

[0046] The storage unit 12 is a non-volatile storage medium such as an HDD or SSD that stores various types of information. The storage unit 12 stores control programs for executing various processes by the control unit 11, as well as data, thresholds, reference values, etc. used in the various processes.

[0047] In this embodiment, the storage unit 12 stores probability variable tables 121 to 126 that indicate a plurality of probability variables U, V, W, X, Y, and Z. The probability variables U, V, W, X, Y, and Z will be described later.

[0048] The display unit 14 is a display device such as a liquid crystal display or an organic EL display that displays various information. The operation unit 15 is an input device such as a mouse, keyboard, or touch panel that accepts operations by an operator.

[0049] However, if the actual number of reserved seat purchases on the express train is significantly lower than the reserved seat capacity, the express train will have to operate with many empty seats. In this case, the operation efficiency of the express train will be poor. Also, if the reserved seat capacity is reached despite there being demand for reserved seats, the passengers' desire to sit and travel will not be satisfied, which is inconvenient for passengers.

[0050] In order to prevent the deterioration of the operational efficiency and convenience, conventionally, a railway operator obtains the number of reserved seats purchased in advance from the seat reservation system 200 before the express train starts operation, determines the expected number of passengers of the express train on the operation day based on an empirical rule taking into account the number of reserved seats purchased, and determines the number of express cars in the express train based on the expected number of passengers. However, the expected number of passengers based on an empirical rule may differ greatly from the actual number of passengers, and in this case, the operational efficiency of the express train and the convenience of the passengers cannot be sufficiently improved.

[0051] In contrast, in the management system 100 of this embodiment, the control unit 11 configured as described below executes a utilization probability estimation process (see FIGS. 13 to 16) described below. Therefore, the utilization probability of a user using the express car can be accurately calculated before the sale of reserved seats on the express train ends (before applications for use end). This makes it possible to improve both the operating efficiency of the express train and the convenience for users of the express train.

[0052] The control unit 11 controls the operation of each unit of the management device 10. The control unit 11 has control devices such as a CPU, a ROM, and a RAM. The CPU is a processor that executes various types of arithmetic processing. The ROM is a non-volatile storage medium that pre-stores control programs such as a BIOS and an OS that cause the CPU to execute various types of arithmetic processing. The RAM is a volatile or non-volatile storage medium that stores various types of information and is used as a temporary storage memory (work area) for the various types of arithmetic processing executed by the CPU. The control unit 11 controls the management device 10, the management system 100, etc. by having the CPU execute various control programs pre-stored in the ROM or the storage unit 12.

[0053] In this embodiment, the control unit 11 is configured to perform a usage probability estimation process (see FIGS. 13 to 16) for estimating the usage probability that a user will use a specific express train (hereinafter referred to as a specific express train) traveling from a departure station to a destination station in at least a part of a usage section of a railway line that the user uses. In other words, the control unit 11 estimates the riding probability that the user will ride an express train (hereinafter referred to as a specific train) made up of the specific express cars rather than the general train running in the usage section.

[0054] For example, suppose that a user normally rides a general train (e.g., a local train) on the route from the nearest departure station to his / her home to a destination station near his / her workplace when commuting to work. When the specific train bound for the same destination station is running around the time of departure of the general train that the user normally rides, the control unit 11 estimates the probability (usage probability) that the user will pay a reserved seat fare and ride the specific train.

[0055] In order to execute the utilization probability estimation process, the control unit 11 includes, as shown in FIG. 2 , a data acquisition unit 111, a utilization interval determination unit 112 (an example of a utilization interval determination unit of the present invention), a utilization probability estimation unit 113 (an example of a utilization probability estimation unit of the present invention), a user determination unit 114 (an example of a user determination unit of the present invention), a number-of-users prediction unit 115 (an example of a number-of-users prediction unit of the present invention), It includes various processing units such as a parameter correction unit 116 (an example of a parameter correction unit of the present invention), an output processing unit 117 (an example of an output processing unit of the present invention), and a probability variable changing unit 118 (an example of a probability variable changing unit of the present invention). Note that in this embodiment, not all of these processing units are necessarily required, and they may be omitted in some cases.

[0056] The control unit 11 functions as the various processing units by the CPU executing various arithmetic processes in accordance with the control program. The control unit 11 or the CPU is an example of a computer or processor that executes the control program. Note that some or all of the processing units included in the control unit 11 may be configured with electronic circuits. The control program may also be a program that causes multiple processors to function as the various processing units.

[0057] The data acquisition unit 111 executes a process of acquiring each piece of information used in the utilization probability estimation process (see FIGS. 13 to 16) described below. For example, the data acquisition unit 111 transmits a transmission request to the seat reservation system 200, and receives from the seat reservation system 200 the express train riding history and the reserved seat purchase history, etc., of the express train corresponding to the requested user ID.

[0058] Furthermore, the data acquisition unit 111 refers to the database 30 and performs a process (user registration information acquisition process) of extracting the user registration information corresponding to the user ID of the user (estimation target person) whose usage probability is to be estimated from the user registration data 31. If there are multiple estimation targets, the data acquisition unit 111 extracts multiple pieces of user registration information corresponding to the user IDs of the multiple estimation targets from the user registration data 31.

[0059] The data acquisition unit 111 may also perform a process of extracting the boarding and alighting history information corresponding to the user ID of the person to be estimated from the boarding and alighting history data 32 (boarding and alighting history acquisition process).

[0060] Furthermore, the data acquisition unit 111 refers to the database 30 and performs a process of extracting, from the bus schedule data 35, timetable information for a scheduled operation date of the specific train that is to be estimated in the utilization probability estimation process (see FIG. 13) described below. Furthermore, the data acquisition unit 111 refers to the database 30 and performs a process of extracting, from the bus schedule data 35, timetable information for a past operation date of the specific train that is to be estimated in the utilization probability estimation process (see FIG. 16) described below.

[0061] In addition, the data acquisition unit 111 receives from the seat reservation system 200 the actual number of passengers (actual number of users) who actually used the specific train during the specific time period on the requested past date of use by sending a transmission request to the seat reservation system 200.

[0062] The utilization section determination unit 112 executes a process (utilization section determination process) of determining the utilization section (section from the entrance station to the exit station) that the estimated target person will utilize.

[0063] The utilization section determination unit 112 refers to the boarding and alighting history data 32 stored in the database 30, and determines the utilization section mainly used by the presumed subject based on the boarding and alighting history information of the presumed subject registered in the boarding and alighting history data 32. The utilization section is information on the section from the entrance station (boarding station) to the exit station (disembarking station) on the line mainly used by the presumed subject.

[0064] Furthermore, the utilization section determination unit 112 refers to the boarding and alighting history data 32 stored in the database 30, and determines a utilization section that the presumed person is likely to use on a predetermined predicted day, based on the boarding and alighting history information of the presumed person registered in the boarding and alighting history data 32. The boarding and alighting history information is acquired by the data acquisition unit 111.

[0065] In this embodiment, the utilization section is determined for each of an up line from the end point to the start point on a railway line and a down line from the start point to the end point. In other words, the utilization section determination unit 112 determines an outward journey section (outward utilization section) that the presumed subject will use when traveling from the departure station (entrance station) to the destination station (exit station), and a return journey section (return utilization section) that the presumed subject will use when returning from the destination station to the departure station.

[0066] For example, the utilization section determination unit 112 determines the section with the most frequent use count among one or more determination target sections used by the estimated target person during a determination period from the time of determination to a predetermined period before as the utilization section that the estimated target person will mainly use, or determines the utilization section that the estimated target person is likely to use on the predicted date. The predetermined period may be, for example, several hours, several days, several weeks, or several months. The predetermined period may be set arbitrarily.

[0067] For example, if the predetermined period is several days or more and the predicted date is a weekday, the utilization section determination unit 112 may determine the most frequently used section among the determination target sections used on weekdays during the determination period as the utilization section, thereby improving the accuracy of determining the utilization section.

[0068] Furthermore, if the predetermined period is one week or longer, the utilization interval determination unit 112 may determine that the utilization interval is the interval with the most number of uses among the determination intervals that were used on the same day of the week as the predicted date during the determination period. In this case, the accuracy of determining the utilization interval can also be improved.

[0069] Furthermore, the utilization section determination unit 112 may determine, for example, the commuter pass utilization section of a commuter pass registered in the user registration data 31 as the utilization section to be determined, without referring to the boarding and alighting history data 32. This allows the utilization section determination unit 112 to determine the utilization section even if there is no boarding and alighting history data 32.

[0070] The utilization probability estimation unit 113 executes a process (utilization probability estimation process) to estimate the utilization probability that the estimated subject will utilize the specific train traveling to the destination station of the utilization section through at least a portion of the common section of the utilization section, based on the utilization section determined by the utilization section determination unit 112.

[0071] Preferably, the utilization probability estimation unit 113 executes a process (utilization probability estimation process) to estimate the utilization probability that the estimated subject will utilize the specific train traveling through the common section to the destination station, based on the express train utilization history indicating that the express train has been utilized in the past and the utilization section determined by the utilization section determination unit 112.

[0072] The utilization probability estimation unit 113 estimates the utilization probability of the estimation target person for each of the utilization sections determined for the inbound line and the utilization sections determined for the outbound line.

[0073] In this embodiment, the utilization probability estimation unit 113 estimates the utilization probability based on a total of six elements: the history of utilization of express trains, such as the history of utilization of express trains and the history of purchase of reserved tickets, the required time for the utilization section, the attributes of the person to be estimated, the degree of congestion of the ordinary trains running in the utilization section, the utilization fare of the specific train, and the departure time difference between the specific train and the ordinary train. Note that the utilization probability estimation unit 113 may further use the distance of the utilization section to estimate the utilization probability.

[0074] The control unit 11 can acquire the priority car usage history of the person to be estimated from the seat reservation system 200.

[0075] The required time is the travel time when the general train travels through the section of use according to a predetermined operation plan. In other words, the required time is the travel time when the estimated subject travels on the general train traveling through the section of use according to the operation plan. The control unit 11 can calculate the required time for the section of use by, for example, referring to the train schedule data 35.

[0076] The control unit 11 can acquire the attributes of the person to be estimated from the user registration data 31.

[0077] Furthermore, the control unit 11 can calculate the congestion degree based on the occupancy rate included in the occupancy rate data 33. For example, when the occupancy rate of the general train exceeds 100%, the occupancy rate can be used as an index showing the congestion degree. Generally, when the occupancy rate is 100% or less, it is considered that the train is not crowded, so in that case, the utilization probability estimation unit 113 estimates the utilization probability without using the congestion degree.

[0078] Here, the control unit 11 can acquire the passenger occupancy rate of the general train and the type of the general train from the passenger occupancy rate data 33.

[0079] Furthermore, the control unit 11 can acquire from the seat reservation system 200 the fare required when the presumed subject person boards the specific train that runs through the utilization section.

[0080] Furthermore, the control unit 11 can obtain the distance of the section of use by referring to the route data 34, for example.

[0081] Furthermore, the control unit 11 can obtain the timetable information of the specific train by referring to the timetable data 35.

[0082] The utilization probability estimation unit 113 does not necessarily need to estimate the utilization probability based on the six factors described above, and may estimate the utilization probability based only on the utilization section, or may estimate the utilization probability based only on the priority vehicle utilization history, or may estimate the utilization probability based on both the utilization section and the priority vehicle utilization history. Furthermore, the utilization probability estimation unit 113 may estimate the utilization probability by further taking into account, in addition to the priority vehicle utilization history, any one or more of the required time for the utilization section, attributes of the person to be estimated, the congestion level, the utilization fare, the departure time difference, or the distance of the utilization section.

[0083] The user determination unit 114 performs a process of determining the plurality of presumed target users who will use the departure station in the utilization section during a specific time period on a predetermined prediction date (presumed target user determination process). Specifically, the user determination unit 114 refers to the boarding and alighting history data 32 stored in the database 30, and extracts, from the boarding and alighting history data 32, user IDs who have used the departure station during the specific time period in the past, based on the boarding and alighting history information in the boarding and alighting history data 32.

[0084] The user determination unit 114 may determine a plurality of the estimated subjects who are likely to use the general train that satisfies a predetermined specific condition. Here, the general train that satisfies the specific condition is a train that departs from the departure station in the utilization section toward the destination station during the specific time period on the prediction date.

[0085] For example, if the section to be used is a section determined for the inbound line, the departure station is the station closest to the end of the section to be used, and if the section to be used is a section determined for the outbound line, the departure station is the station closest to the start of the section to be used.

[0086] Here, the predicted date is a scheduled operation date of the specific train for which the utilization probability is to be estimated, and the specific time period is a specific time period determined on the scheduled operation date.

[0087] For example, as shown in FIG. 4, on a railway line starting from station ST1 located in the center of the metropolitan area and ending at station ST2, the utilization section is assumed to be the section from station A as the departure station to a predetermined destination station (any station between station A and terminal station ST2). The specific train runs from the starting station ST1 to terminal station ST2, and the stations along the way (specific train stops) are station A, station B10, station B21, and station B33. The forecasted day is assumed to be a Friday (weekday) on the weekend. The specific time period is assumed to be a first set time (e.g., 18:00 to 18:10) during rush hour (e.g., 17:00 to 20:00) when many people, such as workers in the metropolitan area, board trains.

[0088] In this case, the user determination unit 114 refers to the boarding and alighting history information and extracts from the boarding and alighting history data 32 users who have entered the station A a number of times equal to or greater than a predetermined threshold during four weekday days (determination period) from Thursday of the same week as the predicted date (the day before the predicted date) to Monday of the same week (four days before the predicted date).Then, from among the extracted users, the unit 114 further extracts users who entered the station A during a second set time period from a time a predetermined time before the start time (18:00) of the first set time to the end time (18:10) of the first set time, and determines these users as the presumed target users who are likely to use the station A in the utilization section during the specific time period on the next predicted date.

[0089] The threshold value is an arbitrarily set value, and is set within a range from 1 to the maximum number of times, for example, the same number of times as the number of days in the determination period (4 times). The predetermined time is a time that takes into consideration the margin of time that a user can board a train car departing from Station A, which is the departure station, in the travel direction D1, and is, for example, the time required from entering Station A to arriving at the platform and boarding the train (e.g., 5 minutes). In this case, the user determination unit 114 extracts, as the presumed target users, users who entered Station A during the second set time, which is from 17:55, 5 minutes before the start time of the first set time, to 18:10, the end time of the first set time.

[0090] FIG. 11 shows a list of suspected persons, which is generated by the user determination unit 114 and lists the attribute information of each of the n suspected persons Mk (k=1, 2, . . . , k, . . . , n) who entered Station A, the departure station, during the second set time (17:55 to 18:10), information on the entry and exit stations, information on the general trains that the person usually rides, the operation status of the specific train to be suspected, the fare for the specific train, the usage history of the specific train, and the departure time difference between the specific train and the general train. The list of suspected persons may be generated each time the user determination unit 114 determines a suspected person. In the list of suspected persons, the departure time difference between the preceding specific train and the specific train is indicated by a negative sign, and the departure time difference between the specific train that departs after the general train is indicated by a positive sign. Note that the list of suspected persons in Figure 11 does not show attributes such as whether the suspected person Mk is registered as a point member or the number of years he or she has been registered as a point member (number of years of continued registration), but this attribute information may be included in the list of suspected persons.

[0091] The user determination unit 114 is not limited to determining the presumed target person who entered the departure station in the utilization section at the second set time. For example, the user determination unit 114 sets the specific time period at predetermined time intervals (for example, 10-minute intervals) during the rush hour on the predicted date, and determines the presumed target person corresponding to each specific time period. Of course, the specific time period is not limited to the rush hour, and the presumed target person may be determined by setting the specific time period at the time interval set for all operating hours on the predicted date.

[0092] In this case, the train to be estimated by the utilization probability estimation unit 113 is the specific train that departs from the departure station at a time close to the specific time period, for example, the specific train that departs from the departure station at a time closest to the departure time of the general train that departs during the specific time period. In other words, the utilization probability estimation unit 113 estimates the utilization probability that the target person will use the specific train that departs from the departure station at a time close to the specific time period.

[0093] For example, the utilization probability estimation unit 113 refers to the timetable information of the specific train included in the timetable data 35, extracts the specific train that departs from the departure station at a time closest to the departure time of the general train that departs during the specific time period, and estimates the utilization probability that the target person will board the extracted specific train. Note that the utilization probability estimation unit 113 may also extract the specific train that departs from the departure station within a predetermined time range from the specific time period. In this case, the predetermined time range may be, for example, a range from 10 minutes before the start time of the specific time period (first set time) to 10 minutes after the end time of the specific time period. Note that the predetermined time range may be set arbitrarily.

[0094] In addition, if the departure station is a station where the specific train does not stop (a station where the specific train passes), the train to be estimated by the utilization probability estimation unit 113 is the specific train departing in the traveling direction D1 from the next stop (specific train stop station) on the traveling direction D1 side of the departure station of the specific train. For example, in FIG. 4, if the departure station of the utilization section is Station B1, Station B1 is a station where the general train stops but the specific train does not stop. Therefore, when the target person to be estimated boards the specific train, they must first board the general train that arrives at Station B1 before the specific train, and then transfer to the specific train at Station B10 (a transfer station), which is the next stop. Therefore, in this case, the train to be estimated by the utilization probability estimation unit 113 is the specific train departing in the traveling direction D1 from Station B10, which is the next stop on the traveling direction D1 side of Station B1. In this case, the specific train departs from the station B10 at a time within the specific time period, or at a time slightly later than the end time of the specific time period.

[0095] Furthermore, if the departure station is a station where the specific train does not stop (a station where the specific train passes), the train to be estimated by the utilization probability estimation unit 113 may be a specific train that departs in the traveling direction D1 from a specific train stop station on the opposite side of the departure station in the traveling direction D1 of the train. For example, if the departure station of the utilization section is Station B1, the person to be estimated travels from Station B1 to Station A (a transfer station) on the opposite side by the general train, transfers to the specific train departing in the traveling direction D1 at Station A, and travels to a predetermined destination station on the traveling direction D1 side of Station B1 by the specific train. In this case, the specific train departs from Station A in the traveling direction D1 at a time within the specific time slot, or departs from Station A in the traveling direction D1 at a time slightly later than the end time of the specific time slot.

[0096] In this embodiment, the utilization probability estimation unit 113 estimates the utilization probability based on a preset first reliability variable U (an example of the first reliability parameter of the present invention), a second reliability variable V (an example of the second reliability parameter of the present invention), a third reliability variable W (an example of the third reliability parameter of the present invention), a fourth reliability variable X (an example of the fourth reliability parameter of the present invention), a fifth reliability variable Y (an example of the fifth reliability parameter of the present invention), and a sixth reliability variable Z (an example of the sixth reliability parameter of the present invention).

[0097] The first accuracy variable U is a variable set according to both or either one of the actual usage history (whether or not the train has been used) and the number of times the train has been used during a predetermined period, and its unit is "%." The actual usage history corresponds to the actual purchase history (whether or not the train has been purchased) of a reserved seat on the specific train, and the number of times the reserved seat has been purchased. FIG. 5 shows an accuracy variable table 121 showing the first accuracy variable U. The accuracy variable table 121 defines a value of the first accuracy variable U corresponding to the actual usage history (whether or not the train has been used) and a value of the first accuracy variable U corresponding to the number of times the train has been used when the train has been used. In general, the more the number of times the train has been used, the less the person to be predicted will be reluctant to board the specific train. Therefore, as shown in FIG. 5, the accuracy variable table 121 defines the first accuracy variable U so that the value increases as the number of times the train has been used increases. The predetermined period can be set arbitrarily, for example, one month before the prediction date.

[0098] The utilization probability estimation unit 113 sets the first accuracy variable U based on the reserved seat purchase history. Specifically, the utilization probability estimation unit 113 acquires the utilization record (reserved seat purchase record) and the number of utilizations (number of reserved seat purchases) of the estimation target person from the purchase history data 201, and extracts and sets the first accuracy variable U corresponding to these from accuracy variable table 121 (see FIG. 5).

[0099] The second accuracy variable V is a variable set according to the ride time (travel time) of the target person when riding the general train running through the section of use, and is expressed in percentage. FIG. 6 shows an accuracy variable table 122 showing the second accuracy variable V. In the accuracy variable table 122, the value of the second accuracy variable V is set corresponding to the ride time (travel time) when the general train runs through the section of use. In general, the longer the ride time, the more likely the target person is to ride the specific train. Therefore, as shown in FIG. 6, the accuracy variable table 122 sets the second accuracy variable V so that the longer the ride time, the larger the value. Furthermore, if the destination station in the section of use is a station on which the specific train passes, the target person will need to transfer to the general train at an earlier stop if they board the specific train. Therefore, even if the ride time is long, if a transfer is required, the second accuracy variable V is subtracted by a predetermined amount or a predetermined ratio. If the distance between the departure station and the destination station is shorter than a predetermined distance (e.g., 10 km) or the travel time therebetween is shorter than a predetermined time (e.g., 10 minutes), there is no motivation to ride the specific train, and the specific train does not operate in the short distance. In this case, the second accuracy variable V is set to a numerical value that reduces the estimated value of the utilization probability. Specifically, the second accuracy variable V is set to a specified value "-15" that significantly reduces the estimated value of the utilization probability.

[0100] The usage probability estimation unit 113 sets the second accuracy variable V based on the boarding and alighting history information of the person to be estimated. Specifically, the usage probability estimation unit 113 calculates the riding time (travel time) when the person to be estimated travels in the section to be used by the general train, and extracts and sets the second accuracy variable V corresponding to the riding time from accuracy variable table 122 (see FIG. 6).

[0101] The third accuracy variable W is a variable set according to the attributes of the person to be estimated, and is expressed in units of "%". FIG. 7 shows an accuracy variable table 123 showing the third accuracy variable W. In the accuracy variable table 123, the value of the third accuracy variable W is determined according to the attributes of the person to be estimated. In general, it is considered that the older the person to be estimated is, the less reluctant the person to be estimated is to board the specific train than the younger the person. It is also considered that the reluctance is lower for workers (non-students) than for students. In this embodiment, it is assumed that the reluctance is lower for men than for women. Therefore, as shown in FIG. 7, in the accuracy variable table 123, the third accuracy variable W is determined so that the value is larger for older people, for workers than for students, and for men than for women.

[0102] The usage probability estimation unit 113 sets the third accuracy variable W based on the attributes of the person to be estimated. Specifically, the usage probability estimation unit 113 acquires the attributes of the person to be estimated (age, sex, whether or not the person is a student, etc.) from the user registration data 31, and extracts and sets the third accuracy variable W corresponding to these from accuracy variable table 123 (see FIG. 7).

[0103] Furthermore, if the user registration data 31 includes the attributes of the person to be estimated, such as whether or not the person is registered as a point member and the number of years the person has been registered as a point member, the usage probability estimation unit 113 may obtain attributes of the person to be estimated, such as whether or not the person is registered as a point member or the number of years the person has been registered as a point member, from the user registration data 31, and set the third probability variable W to a setting value corresponding to this attribute information.

[0104] Here, the point member is a person who has registered to use the point service provided by the point management system 400 (see FIG. 1), as described above. The registration information that the point member registers in the point service includes, for example, the user ID that identifies the user, personal information such as name, address, age, and gender, and information such as the date of registration. Of course, information such as the stations that the member usually uses (entrance station, exit station) and contact information (telephone number and email address) may also be registered.

[0105] In this embodiment, the points or benefits granted to the point members who are registered with the point service include points or benefits granted to the point members who purchase tickets for the specific trains by paying the usage fee. In this case, it is considered that railway users who are registered as point members have a higher probability of riding the specific trains than non-registered users.

[0106] Therefore, for example, when the presence or absence of the point membership is registered in the user registration data 31, a value obtained by adding a predetermined additional value to the numerical value of the third accuracy variable W shown in the accuracy variable table 123 is set to the third accuracy variable W so that the value of the third accuracy variable W of the registered estimated target person is larger than that of an unregistered person. As a result, the numerical value of the usage probability of the estimated target person who is the point membership boarding the specific train becomes larger than that of the estimated target person who is not registered to use the point service.

[0107] The additional value may be a value that varies in proportion to the number of years of registration. For example, the additional value may be a value obtained by multiplying a predetermined reference value by a coefficient greater than "1" that is proportional to the number of years of registration. Of course, the additional value may be an arbitrarily determined value.

[0108] The fourth accuracy variable X is a variable set according to the congestion level of the general train when the target person travels on the general train through the use section, and its unit is "%." FIG. 8 shows an accuracy variable table 124 indicating a set value α of the fourth accuracy variable X. In the accuracy variable table 124, the value of the fourth accuracy variable X is set according to the congestion level of the general train. Generally, the higher the congestion level of the general train the target person is about to board, the less resistance the target person will have to board the specific train. Therefore, as shown in FIG. 8, in the accuracy variable table 124, the fourth accuracy variable X is set to a larger value as the congestion level of the general train increases. Furthermore, generally, the resistance is less when the general train is an express type. Therefore, as shown in FIG. 8, in the accuracy variable table 124, the fourth accuracy variable X is set to a larger value as the express level of the general train increases. In detail, the fourth probability variable X is set to have a larger value for semi-express trains than for local trains, and is set to have a larger value for express trains than for semi-express trains.

[0109] The utilization probability estimation unit 113 sets the fourth accuracy variable X based on the congestion degree and the type of the ordinary train. Specifically, the utilization probability estimation unit 113 acquires the occupancy rate of the ordinary train corresponding to the estimation target person from the occupancy rate data 33, acquires the type of the ordinary train running in the utilization section from the train schedule data 35, extracts a setting value α of the fourth accuracy variable X corresponding to these from an accuracy variable table 124 (see FIG. 8), and sets the extracted setting value α to the fourth accuracy variable X.

[0110] Furthermore, the utilization probability estimation unit 113 may set the value (=p·α) calculated by multiplying the set value α extracted from the reliability variable table 124 as described above by a weighting coefficient p determined according to the occupancy rate as the fourth reliability variable X. In general, it is considered that the higher the degree of congestion of the train that the person to be estimated intends to board, the higher the utilization probability that the person to be estimated will board the specific train. Therefore, the weighting coefficient p is set to a value larger than the reference value "1", and further, the higher the degree of congestion, the larger the value is set.

[0111] For example, the weighting coefficient p is determined for each predetermined range of the passenger load factor. Specifically, as shown in Fig. 8, the weighting coefficient p is determined in advance in a probability variable table 124. For example, when the type of the general train is a local train, the weighting coefficient p1 is set to 1.2 when the passenger load factor is 100-125%, 1.4 when the passenger load factor is 125-150%, 1.6 when the passenger load factor is 150-175%, and 1.8 when the passenger load factor exceeds 175%.

[0112] These weighting coefficients p are predetermined for each type of general train, and as shown in the probability variable table 124 of Figure 8, the weighting coefficient p is set to increase as the level of express increases, from local trains to semi-express trains and express trains.

[0113] The fourth accuracy variable X can be expressed as a linear function such as X=p·α+q, where α is a variable. Here, the coefficient q is, for example, an adjustment value determined for each type of ordinary train. The fourth accuracy variable X may be a numerical value given by, for example, a quadratic function or logarithmic function of the set value α.

[0114] The fifth accuracy variable Y is a variable set according to the fare of the specific train, and its unit is "%." FIG. 9 shows an accuracy variable table 125 showing the fifth accuracy variable Y. In the accuracy variable table 125, the value of the fifth accuracy variable Y is set according to the fare of the specific train for which the usage probability of the estimated user is to be calculated. In general, the higher the fare, the greater the resistance of the estimated user to board the specific train. Therefore, as shown in FIG. 9, in the accuracy variable table 125, the fifth accuracy variable Y is set to a smaller value as the fare increases. Furthermore, the fifth accuracy variable Y is set to a value that reduces the estimated value of the usage probability. Note that if the specific train does not operate in the usage section, the usage probability is zero. Therefore, in this case, the fifth accuracy variable Y is set to a predetermined value of "-100" to significantly reduce the estimated value of the usage probability to below 0.

[0115] The utilization probability estimation unit 113 sets the fifth accuracy variable Y based on the fare of the specific train corresponding to the estimation target person. Specifically, the utilization probability estimation unit 113 acquires the fare from the seat reservation system 200, and extracts and sets the fifth accuracy variable Y corresponding to the acquired fare from the accuracy variable table 125 (see FIG. 9).

[0116] The sixth accuracy variable Z is a variable set according to the difference (departure time difference) between the departure time of the general train that the target person usually rides and the departure time of the specific train, the target vehicle for which the target person's usage probability is estimated, in the usage section, and is expressed in percentage. FIG. 10 shows an accuracy variable table 126 indicating the sixth accuracy variable Z. The accuracy variable table 126 indicates an accuracy variable Z according to the departure time difference between the general train that the target person usually rides and the specific train that departs earlier. The accuracy variable table 126 also indicates an accuracy variable Z according to the departure time difference between the general train that the target person usually rides and the specific train that departs later. The larger the departure time difference, the less likely the target person is to ride the specific train. Therefore, as shown in FIG. 10, the accuracy variable table 126 determines the sixth accuracy variable Z so that the smaller the departure time difference, the larger the value. The sixth accuracy variable Z is set to a smaller value as the departure time difference increases. Note that when the departure time difference between the preceding or following specific train is 30 minutes or more, the probability of use is considered to be extremely low. In this case, the sixth accuracy variable Z is set to a specified value of "-50" in order to significantly reduce the estimated value of the probability of use. In addition, since the person to be estimated is generally more likely to board the following specific train than the preceding specific train, the sixth accuracy variable Z of the departure time difference between the following specific train is set to be larger than the departure time difference between the following specific train.

[0117] The usage probability estimation unit 113 sets the sixth accuracy variable Z based on the departure time difference corresponding to the estimation target person. Specifically, for example, as described above, when the specific train that departs from the departure station at a time closest to the departure time of the general train departing in the specific time period is determined to be the specific train to be estimated, the usage probability estimation unit 113 refers to the estimation target person list shown in Fig. 11 to extract the departure time difference corresponding to the estimation target person, and extracts and sets the sixth accuracy variable Z corresponding to the departure time difference from accuracy variable table 126 (see Fig. 10).

[0118] In addition, if the specific train to be estimated has not been determined, the utilization probability estimation unit 113 may refer to the train schedule data 35 to determine whether the specific train is running, and if the specific train is running, determine the specific train with the smallest departure time difference from among the specific trains that depart before or after the departure time of the general train that the person to be estimated normally takes as the specific train to be estimated (the specific train that the person to be estimated is likely to take), calculate the time difference between the departure time of the determined specific train and the departure time of the general train that the person to be estimated normally takes, and extract and set the sixth probability variable Z corresponding to the calculated departure time difference from the probability variable table 126 (see Figure 10).

[0119] After setting the six accuracy variables U, V, W, X, Y, and Z described above, the usage probability estimation unit 113 performs a process of calculating the usage probability of the estimated person based on the calculation formula (1) below. In formula (1), n ​​indicates the number of estimated people, Mk (k=1, 2, . . ., k, . . ., n) indicates a specific estimated person, and Tk (k=1, 2, . . ., k, . . ., n) indicates the usage probability of estimated person Mk. However, the usage probability Tk indicates a probability. Therefore, if the usage probability Tk<0, the usage probability estimation unit 113 estimates the usage probability Tk=0.

[0120] Tk=Uk+Vk+Wk+Xk+Yk+Zk(Tk≧0)[%] ···(1)

[0121] 12 shows a usage probability table including the numerical values ​​of the accuracy variables U, V, W, X, Y, and Z for each estimated target person Mk and the usage probability Tk. As shown in FIG. 12, the calculated values ​​of the usage probabilities T1 and T5 for users M1 and M5 were less than 0, so the usage probability Tk=0 is entered.

[0122] Furthermore, when a predetermined weighting coefficient is h, the utilization probability estimation unit 113 can also calculate the utilization probability Tk based on the following calculation formula (2).

[0123] Tk=h(Uk+Vk+Wk+Xk+Yk+Zk)(Tk≧0)[%] ···(2)

[0124] Here, the coefficient h in equation (2) is a weighting coefficient determined based on the weather conditions on the predicted date when the usage probability is estimated, whether or not an event is being held at any station in the usage section, the scale of the event, etc.

[0125] Generally, if the weather forecast for the predicted day indicates bad weather, the estimated subject will tend to want to sit in a spacious vehicle and travel to their destination station. Therefore, the coefficient h is preferably set based on weather forecast information. For example, if the weather forecast for the predicted day indicates bad weather, the coefficient h is set to a value greater than a predetermined reference value of "1" for the coefficient h. As a result, the utilization probability Tk on a day when bad weather is forecast is higher than the utilization probability Tk on a day when good weather is forecast. Furthermore, the coefficient h on a bad weather day may be set to a value corresponding to the severity of the weather. For example, the coefficient h is set to a higher value the higher the probability of precipitation, the amount of precipitation, and the level of warnings and alerts on the predicted day obtained from the weather forecast. Furthermore, the coefficient h may be set to a value greater than the reference value of "1" if the temperature on the predicted day obtained from the weather forecast is higher than a predetermined abnormally high temperature (e.g., 35°C) or lower than a predetermined abnormally low temperature (e.g., -5°C).

[0126] The control unit 11 of the management device 10 can acquire the weather forecast information via an internet line using a so-called weather forecast API or the like.

[0127] Furthermore, if an event accommodating a large number of guests is held at a venue along the route of the use section on the predicted date, trains along the use section are likely to be significantly crowded. Examples of such events include professional baseball or soccer games, concerts by famous singers, and so on. In this case, the estimated target person's feelings are likely to be inclined to avoid crowds and travel to their destination station in a spacious car. Therefore, in this case, the coefficient h is preferably set based on event information. For example, if the event is held on the predicted date, the coefficient h is set to a value greater than the reference value "1" if the specific time period or the estimated target person's boarding time is close to the scheduled start or end time of the event. As a result, the usage probability Tk on days when the event is held at a venue along the route of the use section is higher than the usage probability Tk on days when the event is not held.

[0128] The control unit 11 of the management device 10 can acquire the event information from a website that handles event information related to the event via an internet line.

[0129] Furthermore, if evaluation information regarding the specific train to be estimated is available, the coefficient h may be set based on the evaluation information. Here, the evaluation information includes, for example, comment information from users who have ridden the specific train, service information regarding the content of services provided by railway operators to users of the specific train, station evaluation information regarding evaluations of the specific train's stop stations or final destination stations, or the number of posts of the comment information or the station evaluation information. The comment information includes, for example, information on comments such as impressions of riding the specific train, information on comments regarding impressions of using the stop stations or the final destination station, and the number of such comments. The station evaluation information includes, for example, information on services provided at the station, the content of the station's facilities, and information on tourist spots near the station. For example, possible examples of the comment information include comments regarding the crowdedness of the specific train's carriage, comments regarding the comfort of the carriage, comments regarding the quality of the service, comments regarding evaluations of facilities at the stop stations or the final destination station, and comments regarding evaluations of tourist spots near the stop stations or the final destination station.

[0130] Generally, when the person to be estimated views the evaluation information on a specific website via the Internet from a mobile terminal such as a smartphone, if the content of the evaluation information is good (highly rated), the person to be estimated will tend to want to travel by boarding the specific train. Therefore, if the content of the evaluation information is good, the coefficient h is set to a value greater than the reference value "1." On the other hand, if the content of the evaluation information is not good (lowly rated), the person to be estimated will be less likely to want to travel by boarding the specific train. Therefore, in this case, the coefficient h is either maintained at the reference value "1" or set to a value smaller than the reference value "1."

[0131] The control unit 11 of the management device 10 can acquire one or more pieces of evaluation information from websites that handle the evaluation information via an Internet connection. For example, the management device 10 acquires the evaluation information from websites that provide social networking services (SNS), websites that provide electronic bulletin boards where route information and the like is posted, websites for recording and publishing personal experiences (e.g., blogs), etc. The acquired evaluation information is preferably information about the specific train that is the target of estimation. Note that the acquired evaluation information may also include information about past specific trains that operate on the same schedule as the specific train that is the target of estimation.

[0132] When the control unit 11 of the management device 10 acquires the evaluation information, it determines whether the evaluation information is the high evaluation or the low evaluation based on the evaluation information.

[0133] For example, if the evaluation information is the number of posts of the comment information or the station evaluation information (e.g., the number of posts on the SNS, etc.), it can be determined that the greater the number of posts, the higher the attention and the higher the evaluation. Also, it can be determined that the fewer the number of posts, the lower the attention and the lower the evaluation. Therefore, for example, when the number of posts is equal to or greater than a predetermined threshold, the control unit 11 of the management device 10 sets the coefficient h to a value greater than the reference value "1", and when the number of posts is less than the predetermined threshold, the control unit 11 either maintains the coefficient h at the reference value "1" or sets the coefficient h to a value smaller than the reference value "1".

[0134] Furthermore, for example, if the evaluation information is the comment information or the station evaluation information, the control unit 11 of the management device 10 may analyze the text of the comments posted on the website using a well-known text mining process, extract positive and negative words related to the specific train to be estimated, calculate the occurrence rates of these words, and compare the occurrence rates to determine whether the evaluation information is the high evaluation or the low evaluation. In this case, if the occurrence rate of the positive words is higher than the occurrence rate of the negative words, the control unit 11 of the management device 10 sets the coefficient h to a value greater than the reference value "1." On the other hand, if the occurrence rate of the positive words is lower than the occurrence rate of the negative words, the control unit 11 either maintains the coefficient h at the reference value "1" or sets it to a value smaller than the reference value "1."

[0135] Furthermore, the use probability estimation unit 113 may calculate the use probability Tk of the estimation target person based on the following calculation formula (3).

[0136] Tk=t1Uk+t2Vk+t3Wk+t4Xk+t5Yk+t6Zk (Tk≧0) [%] (3)

[0137] The coefficient t (t1, t2, t3, ...) in equation (3) is a weighting coefficient assigned to each probability variable. Each coefficient t is determined depending on which of the probability variables is given more importance. For example, if the second probability variable V has a greater influence than the first probability variable U on the calculated estimated value of the utilization probability, coefficient t2 is set to a value greater than coefficient t1.

[0138] The number of users prediction unit 115 executes a process (paying user number prediction process) to predict the number of paying users who will use the specific train based on the usage probability of each of the multiple estimated subjects estimated by the usage probability estimation unit 113.

[0139] For example, if the predicted number of paying users is S, the number-of-users prediction unit 115 can calculate the number of paying users by the following formula (4) using the usage probability Tk of the predicted target users Mk.

[0140]

number

[0141] The parameter correction unit 116 generates correction values ​​for correcting the accuracy variables U, V, W, X, Y, and Z based on the difference between the predicted number of passengers predicted by the passenger number prediction unit 115 and the actual number of passengers (actual number of passengers) who actually boarded the specific train that was the subject of usage prediction, and executes a process of correcting the accuracy variables U, V, W, X, Y, and Z using the correction values. Here, the actual number of passengers is the number of passengers who actually purchased tickets or reserved tickets for the specific train and boarded the specific train. The parameter correction unit 116 can obtain the actual number of passengers for the specific train that was the subject of usage prediction from the purchase history data 201 managed by the seat reservation system 200.

[0142] If the prediction accuracy by the number-of-passengers prediction unit 115 is sufficiently high, the predicted number of passengers should be approximately the same as the actual number of passengers, and for example, the difference should be less than the allowable limit value. However, if the difference is equal to or greater than the allowable limit value, this indicates that the prediction accuracy is poor. Therefore, in this embodiment, the accuracy variables U, V, W, X, Y, and Z are corrected by the parameter correction unit 116 so that the difference is less than the allowable limit value, that is, so that the predicted number of passengers approximates the actual number of passengers.

[0143] For example, if the difference is equal to or greater than the allowable limit value and the predicted number of passengers is less than the actual number of passengers, the parameter correction unit 116 generates an increase correction factor (an example of a correction value) according to the difference and performs a process of multiplying only the positive probabilities among the probability variables U, V, W, X, Y, and Z by the increase correction factor.

[0144] Furthermore, for example, if the difference is equal to or greater than the allowable limit value and the predicted number of passengers is greater than the actual number of passengers, the parameter correction unit 116 generates a reduction correction rate (an example of a correction value) according to the difference and performs a process of multiplying only the positive probabilities among the probability variables U, V, W, X, Y, and Z by the reduction correction rate.

[0145] The parameter correction unit 116 does not need to correct all of the probability variables U, V, W, X, Y, and Z, but only needs to correct one or more of the probability variables U, V, W, X, Y, and Z.

[0146] The output processing unit 117 outputs the use probability of the estimation target person estimated by the use probability estimation unit 113 to an external information processing device or the like.

[0147] Furthermore, when the predicted number of passengers predicted by the passenger-number prediction unit 115 is less than a predetermined first threshold based on the reserved seat capacity of the specific train (an example of an allowable capacity), the output processing unit 117 performs a process of distributing usage promotion information to the estimated target persons to promote usage of the specific train. When the prediction process by the passenger-number prediction unit 115 is completed, the control unit 11 compares the predicted number of passengers with the first threshold and performs a process of determining whether the predicted number of passengers is less than the first threshold. The first threshold may be, for example, the reserved seat capacity, or may be a value obtained by multiplying the reserved seat capacity by an allowable error rate (for example, 90%).

[0148] Furthermore, the output processing unit 117 transmits the usage promotion information to the user terminal 40 of the presumed target person before the sales of reserved seats on the specific train end in order to promote the sale of vacant reserved seats on the specific train. For example, the output processing unit 117 may transmit the usage promotion information only to the user terminal 40 of one of the presumed target people whose usage probability is equal to or greater than a predetermined reference rate, among the plurality of presumed target people. The usage promotion information may be, for example, a discount benefit (such as a discount code) that discounts the fare for the specific train. Furthermore, the output processing unit 117 may transmit the discount benefit, the discount amount of which is proportional to the usage probability, to the user terminal 40 of the presumed target person as the usage promotion information. Note that the discount benefit may apply to the fare for the specific train that can be boarded immediately, or may be a discount benefit that can be used on subsequent occasions after purchasing a reserved seat on the specific train.

[0149] Furthermore, the output processing unit 117 may output information indicating that the train is over capacity (over-capacity information) to an external device when the predicted number of passengers predicted by the passenger-number prediction unit 115 is equal to or greater than a predetermined second threshold based on the reserved seat capacity of the specific train (an example of an allowable capacity). The second threshold may be, for example, the reserved seat capacity, or a value obtained by multiplying the reserved seat capacity by an allowable error rate (e.g., 110%). The over-capacity information is output to, for example, the seat reservation system 200. Upon receiving the over-capacity information, the seat reservation system 200 can sell all reserved seats while maintaining a balance between supply and demand for the reserved seats by raising the prices of the remaining reserved seats, thereby further increasing sales.

[0150] Furthermore, when the predicted number of people is equal to or greater than the second threshold, the output processing unit 117 may transmit surcharge information to the user terminal 40 of the estimated target person indicating that the reserved seats will soon be charged a surcharge because the seats will soon be over capacity. This increases the likelihood of the estimated target person rushing to purchase the reserved seats before the surcharge is imposed, which leads to the promotion of sales of vacant reserved seats.

[0151] Furthermore, when the occupancy rate of the occupancy rate data 33 is updated, the output processing unit 117 transmits the updated occupancy rate to the user terminal 40 of the person to be estimated before the sale of reserved seats on the specific train ends. This allows the person to know in advance the degree of congestion of the general train that he or she is likely to board next.

[0152] The accuracy variable change unit 118 executes a process of changing the set values ​​of various accuracy variables set by the utilization probability estimation unit 113 in order to execute a utilization probability estimation process described below. The accuracy variables to be changed are, for example, accuracy variables corresponding to one or more of the required time for the utilization section, the congestion level (occupancy rate) of the general vehicles traveling in the utilization section, the utilization fare for the designated express vehicle, or the departure time difference. Specifically, the accuracy variables to be changed are the second accuracy variable V, the fourth accuracy variable X, the fifth accuracy variable Y, and the sixth accuracy variable Z.

[0153] When a setting change request is input from outside through the operation unit 15, the probability variable change unit 118 displays an input screen, which is a user interface, on the display unit 14, and when a change value for any one or more of the above-mentioned probability variables is input from the input screen, the probability variable change unit 118 accepts the change value and changes (updates) the setting value of the corresponding probability variable.

[0154] In this case, the use probability estimation unit 113 estimates the use probability based on each of the changed probability variables.

[0155] [First example of usage probability estimation processing] Hereinafter, an example of the procedure of the use probability estimation process (first process example) executed in the management system 100 will be described with reference to Fig. 13. In the figure, S11, S12, ... indicate the numbers (step numbers) of the processing procedures.

[0156] Note that one or more steps included in the use probability estimation process described below may be omitted as appropriate. Furthermore, the steps in the use probability estimation process may be executed in a different order as long as the same operational effect is achieved. Furthermore, the following description will be given using an example in which one processor corresponding to the control unit 11 executes the processing of each step in the use probability estimation process, but the steps in the use probability estimation process may be executed in a distributed manner by multiple processors.

[0157] In addition, in the use probability estimation process described below, an example of a process for estimating the use probability of the predetermined estimation target person will be described.

[0158] As shown in Figure 13, in step S11, the control unit 11 refers to the boarding and alighting history information of multiple users included in the boarding and alighting history data 32 and obtains the boarding and alighting history information corresponding to the user ID of the predetermined estimated person.

[0159] Next, in step S12, the control unit 11 determines the section of use that the person mainly used in the past based on the acquired boarding and alighting history information. Specifically, the control unit 11 determines that the section that has been used most frequently among one or more determination target sections that the person to be estimated used during the determination period from the time of determination to the predetermined period before is the section of use that the person mainly used. Note that step S12 is an example of a use section determination step of the present invention.

[0160] If the usage section is determined in step S12 (Yes in S13), the control unit 11 determines whether the commuter pass usage section of the commuter pass registered in the user registration data 31 matches the determination section obtained in step S12 (S14). If it is determined that the determination section matches the commuter pass usage section, the control unit 11 determines the determination section as the usage section of the estimated target person (S15). On the other hand, if it is determined that the determination section does not match the commuter pass usage section, the control unit 11 does not determine the usage section, and outputs a usage section determination error (S16), after which the series of processes ends.

[0161] If the judgment in step S12 is negative (No in S13), the control unit 11 determines the commuter pass usage section registered in the user registration data 31 as the usage section to be judged (17).

[0162] Once the usage section is determined, the control unit 11 obtains the usage history (reserved seat purchase history) and the number of uses (number of reserved seat purchases) of the estimated target person from the purchase history data 201, and extracts the first probability variable U corresponding to these from the probability variable table 121 (S18).

[0163] In addition, the control unit 11 acquires the boarding and alighting history information of the person to be estimated from the boarding and alighting history data 32, calculates the boarding time based on the boarding and alighting history information, and extracts the second probability variable V corresponding to the boarding time from the probability variable table 122 (S19).

[0164] In addition, the control unit 11 acquires the attributes (age, gender, whether or not the person is a student, etc.) of the person to be estimated from the user registration data 31, and extracts the third probability variable W corresponding to these from the probability variable table 123 (S20).

[0165] Furthermore, the control unit 11 acquires the congestion degree of the general train and the type of the general train from the occupancy rate data 33, and extracts the fourth probability variable X corresponding thereto from the probability variable table 124 (S21).

[0166] Furthermore, the control unit 11 acquires the usage fee from the seat reservation system 200, and extracts the fifth accuracy variable Y corresponding to the acquired usage fee from the accuracy variable table 125 (S22).

[0167] In addition, the control unit 11 refers to the train schedule data 35, extracts from the train schedule data 35 the schedule information of the specific train that departs from the departure station at the time closest to the departure time of the general train that departs during the specific time period, and extracts from the probability variable table 126 the sixth probability variable Z that corresponds to the departure time difference between the extracted specific train and the general train (S23).

[0168] Then, in step S24, the control unit 11 calculates the usage probability that the person to be estimated will use the specific train using the probability variables U, V, W, X, Y, and Z and the above-mentioned calculation formulas (1) to (3). Then, the control unit 11 outputs the calculated usage probability to an external information processing device or the like (S25), and the series of processes ends. Note that step S24 is an example of a usage probability estimation step of the present invention.

[0169] [Second example of usage probability estimation processing] 14 and 15, another processing example (second processing example) of the procedure of the utilization probability estimation processing executed in the management system 100 will be described. Note that the same step numbers are assigned to the procedures having the same processing content as those in the first processing example described above, and detailed descriptions thereof will be omitted.

[0170] In the use probability estimation process described below, an example of a process for estimating the use probabilities of a plurality of the estimation subjects who use the predetermined departure station will be described.

[0171] 14, in step S31, the control unit 11 determines the presumed target person who will use the departure station during the specific time period on the predicted date. For example, the control unit 11 refers to the boarding and alighting history information of a plurality of users included in the boarding and alighting history data 32, and extracts users who have entered the departure station a predetermined number of times during a predetermined determination period that is equal to or greater than a predetermined threshold, and then further extracts users who have entered the departure station within the second set time from the extracted users, and determines these users as the presumed target person who is likely to use the departure station during the specific time period on the predicted date.

[0172] Then, in the next step S11, the control unit 11 acquires the boarding and alighting history information corresponding to the user IDs of all of the multiple presumed persons determined in step S31, and determines the usage section of each of the multiple presumed persons (S12). Then, the control unit 11 executes the processes from step S13 to step S23 for each of the multiple presumed persons.

[0173] When the sixth probability variable Z is extracted in step S23, in the next step S231, the control unit 11 determines whether a setting change value for changing a specific probability variable has been input along with the setting change request for changing the probability variable. If the setting change value is input in step S231, the control unit 11 updates the setting value of the corresponding probability variable to the setting change value (S232). On the other hand, if the setting change value is not input in step S231, the control unit 11 proceeds to step S24.

[0174] Then, in step S24, the control unit 11 calculates the usage probability of each person to be estimated based on each accuracy variable, and outputs the calculated usage probability to an external information processing device or the like (S25).

[0175] 15, in the next step S32, the control unit 11 predicts the number of paying passengers who will use the specific train based on the usage probability of each of the multiple estimated passengers calculated in step S24. Then, the control unit 11 outputs the calculated usage probability and the predicted number of paying passengers to an external information processing device or the like (S33).

[0176] In the next step S34, the control unit 11 determines whether the predicted number of passengers is less than a predetermined threshold based on the reserved seat capacity of the specific train (an example of the allowable seating capacity). For example, if it is determined in step S34 that the predicted number of passengers is less than the reserved seat capacity, the control unit 11 transmits the promotion information for promoting the sale of vacant reserved seats on the specific train to the user terminal 40 of the estimated target passenger before the sale of reserved seats on the specific train ends (S35). On the other hand, if it is determined in step S34 that the predicted number of passengers is equal to or greater than the reserved seat capacity, the promotion information is not transmitted, and the over-capacity information is transmitted to the seat reservation system 200 (S36). Then, the series of processes ends.

[0177] The processing in steps S231 to S232 in FIG. 14 may be applied to the first processing example described above.

[0178] [Third example of usage probability estimation processing] 16, another processing example (third processing example) of the procedure of the utilization probability estimation processing executed in the management system 100 will be described. Note that the same step numbers are assigned to the procedures having the same processing content as the first and second processing examples described above, and detailed descriptions thereof will be omitted.

[0179] In the above-mentioned first and second processing examples, a processing example is described in which the utilization probability indicating the possibility that the estimated person will board the first-class car that the estimated person is likely to board is estimated. In contrast, in the following third processing example, a processing example is described in which the utilization probability indicating the possibility that the predetermined estimated person will use the specific train on a specific usage date in the past (hereinafter referred to as a past usage date) is estimated.

[0180] 16, in step S51, the control unit 11 acquires the boarding and alighting history information corresponding to the predetermined user ID of the person to be estimated, by referring to the boarding and alighting history data 32. At this time, the control unit 11 extracts the boarding and alighting information of the person to be estimated during the specific time period on the past usage date for which the usage probability is to be estimated, from the boarding and alighting history data 32.

[0181] Next, in step S52, the control unit 11 determines the section of use that the person to be estimated actually used during the specific time period on the past use date, based on the boarding and alighting information extracted in step S51.

[0182] In the next step S53, the control unit 11 estimates the type of general train that the target person actually rode during the specific time period on the past use date. For example, the control unit 11 identifies a general train that stops at the entrance station during the specific time period from the entrance station, entrance time (ticket gate entry time), exit station, and exit time (ticket gate exit time) included in the boarding and alighting information on the past use date and the operation schedule for the specific time period.

[0183] Next, in steps S18 to S23, the control unit 11 extracts the probability variables U, V, W, X, Y, and Z, and then in step S24, the control unit 11 calculates the use probability of each estimation target person based on each probability variable.Then, the control unit 11 outputs the calculated use probability to an external information processing device or the like (S25).

[0184] In the next step S231, the control unit 11 determines whether a setting change value for changing a specific probability variable has been input along with the setting change request for changing the probability variable. If the setting change value has been input in step S231, the control unit 11 updates the setting value of the corresponding probability variable to the setting change value (S232) and executes the processes from step S24 onwards. On the other hand, if the setting change value has not been input in step S231, the control unit 11 executes the processes from step S32 (see FIG. 15) onwards.

[0185] [Accuracy variable correction processing] An example of the procedure of the accuracy variable correction process executed in the management system 100 will be described below with reference to Fig. 17. In each figure, S11, S12, ... indicate the numbers (step numbers) of the processing procedures.

[0186] 17, in step S41, the control unit 11 determines whether the predicted number of passengers is equal to the actual number of passengers who actually boarded the reserved seats on the specific train. If the difference between the predicted number of passengers and the actual number of passengers is small and within an acceptable range, it is determined that the predicted number of passengers is equal to the actual number of passengers. In this case, the accuracy variables U, V, W, X, Y, and Z can be evaluated as appropriate values, so the accuracy variables U, V, W, X, Y, and Z are not corrected, and the series of processes ends.

[0187] On the other hand, if it is determined that the predicted number of passengers is not equal to the actual number of passengers, in the next step S42, the control unit 11 determines whether the predicted number of passengers is greater than the actual number of passengers. If it is determined that the predicted number of passengers is greater than the actual number of passengers, it can be said that the prediction accuracy by the number of passengers prediction unit 115 is poor. In this case, the control unit 11 generates the decrease correction rate (correction value) based on the difference between the predicted number of passengers and the actual number of passengers (S43), and performs downward corrections to reduce the numerical values ​​of the accuracy variables U, V, W, X, Y, and Z by multiplying only the positive accuracy among the accuracy variables U, V, W, X, Y, and Z by the decrease correction rate (S44).

[0188] Furthermore, if it is determined in step S42 that the predicted number of passengers is smaller than the actual number of passengers, it can also be said that the prediction accuracy by the number of passengers prediction unit 115 is poor. In this case, the control unit 11 generates the increase correction factor (correction value) based on the difference between the predicted number of passengers and the actual number of passengers (S45), and multiplies only the positive accuracy of the accuracy variables U, V, W, X, Y, and Z by the increase correction factor to upwardly correct the numerical values ​​of the accuracy variables U, V, W, X, Y, and Z (S46). Thereafter, the determination process of step S41 is performed again, and the accuracy variable correction process is repeated until it is determined in step S41 that the predicted number of passengers and the actual number of passengers are equal.

[0189] As described above, in the management system 100 of this embodiment, the control unit 11 determines the section of the railway line used by the user, and estimates the probability that the estimated target person will use the specific train operating on the section of the railway based on the reserved seat purchase history and the section of the railway. Furthermore, the number of paying passengers who will use the first-class cars is predicted based on the usage probability for each of the estimated multiple estimated target people. This allows the railway operator to accurately determine the predicted number of passengers before the specific train starts operating, and therefore the railway operator can, for example, adjust the number of reserved seats on the specific train or increase or decrease the number of first-class cars on the specific train based on the predicted number of passengers before the specific train starts operating.

[0190] Furthermore, if the predicted number of passengers is less than a predetermined threshold based on the reserved seat capacity of the specific train, the promotion information is delivered to the potential passengers before the sales of reserved seats on the specific train end, and therefore the potential passengers can easily determine whether or not to purchase reserved seats on the specific train by understanding the promotion information they received. As a result, the purchase of reserved seats is promoted, which improves the operating efficiency of the specific train and also improves convenience for the potential passengers. Furthermore, if the promotion information includes the discount benefit, the potential passengers can purchase reserved seats on the specific train at a price lower than the regular fare, thereby promoting the purchase of reserved seats.

[0191] Furthermore, if the predicted number of passengers does not match the actual number of passengers on the specific train, the accuracy variable is corrected, thereby improving the prediction accuracy by the passenger number prediction unit 115 of the control unit 11.

[0192] According to the present embodiment, since the usage probability of the target person during the specific time period on the past usage date is estimated, the railway operator can understand the accuracy of the predicted number of users by comparing the predicted number of users with the actual number of users. Furthermore, by arbitrarily changing the setting value of the probability variation, the predicted number of users can be adjusted to approach the actual number of users.

[0193] In the above-described embodiment, an example was described in which the general train and the special train run on the utilization section, but the present invention can also be suitably applied to a case in which a mixed train consisting of the general train and the special train that runs on the utilization section during the commuting hours of workers or the commuting hours of students runs on the utilization section.

[0194] Furthermore, for example, if the section of use is part of a Shinkansen line, the general carriages of the general train are regarded as Shinkansen standard seat carriages, and the first-class carriages of the specific train are regarded as Shinkansen green seat carriages, so that the present invention can be suitably applied to cases where the Shinkansen operates over the section of use on a Shinkansen line. In this case, the additional charge for using green seats corresponds to the fare for the specific train.

[0195] Furthermore, in the above embodiment, the management system 100 has been described as an example of one embodiment of the present invention, but the present invention is not limited to the management system 100. For example, the management device 10 constituting the management system 100 can be regarded as a utilization probability estimation device of the present invention.

[0196] [Notes on the Invention] The following is a summary of the invention extracted from the above-described 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 utilization section determination unit that determines a utilization section of a railway line that is used by a user, the utilization section being from a predetermined departure station to a destination station; a utilization probability estimation unit that estimates, based on the utilization section, a utilization probability of the user using a specific express vehicle that travels to the destination station for at least a portion of the utilization section, among express vehicles that require a utilization fee in addition to the fare required for riding a general vehicle; and A railway usage management system equipped with:

[0198] <Appendix 2> the utilization probability estimation unit estimates the utilization probability further based on a priority vehicle utilization history indicating that the specific priority vehicle traveling in the utilization section has been utilized in the past; The railway utilization management system described in Appendix 1.

[0199] <Appendix 3> The utilization probability estimation unit estimates the utilization probability further based on any one or more of the required time for the utilization section, attributes of the user, the congestion level of the general vehicles traveling in the utilization section, the utilization fee for the special express vehicle, the departure time difference between the general vehicle and the special express vehicle, or the distance of the utilization section. 2. A railway utilization management system as set forth in appendix 1 or 2.

[0200] <Appendix 4> The required time is the travel time when the general vehicle travels through the utilization section according to a predetermined operation plan. The railway user management system described in Appendix 3.

[0201] <Appendix 5> The user attributes are attribute information included in user registration data in which user registration information about the user is registered. The railway user management system described in Appendix 3.

[0202] Appendix 6 a user determination unit that determines a plurality of users who will use the departure station during a specific time period on a predetermined prediction date based on the boarding and alighting history of the users; The utilization probability estimation unit estimates the utilization probability that each of the plurality of users determined by the user determination unit will utilize the specific express car departing from the departure station or a transfer station before or after the departure station toward the destination station at a time close to the specific time period. 6. A railway utilization management system according to any one of appendices 1 to 5.

[0203] Appendix 7 a user number prediction unit that predicts the number of paying users who will use the special express vehicle based on the usage probability of each of the plurality of users estimated by the usage probability estimation unit; The railway user management system described in Appendix 6.

[0204] Appendix 8 and an output processing unit configured to transmit, at a predetermined timing before the end of applications for the special express vehicle, if the predicted number of users predicted by the user number prediction unit is less than a predetermined first threshold based on the allowable number of users of the special express vehicle, to the user determined by the user determination unit, usage promotion information that promotes the use of the special express vehicle. The railway user management system described in Appendix 7.

[0205] Appendix 9 and an output processing unit configured to output information indicating that the number of passengers exceeds the allowable capacity of the special express vehicle to a predetermined reservation system that manages reservations for the special express vehicle, when the predicted number of passengers predicted by the user number prediction unit is equal to or greater than a predetermined second threshold based on the allowable capacity of the special express vehicle at a predetermined timing before the end of applications for use of the special express vehicle. The railway user management system described in Appendix 7.

[0206] Appendix 10 The utilization probability estimation unit setting a first accuracy parameter according to both or either one of whether or not the specified premium vehicle has been used and the number of times it has been used during a predetermined period based on the premium vehicle usage history; calculating a ride time when the user rides in the general vehicle traveling in the usage section based on the boarding and alighting history of the user, and setting a second accuracy parameter according to the ride time; estimating the utilization probability based on the first certainty parameter and the second certainty parameter; The railway usage management system described in Appendix 2.

[0207] Appendix 11 The utilization probability estimation unit Further setting one or more of a third accuracy parameter according to the attributes of the user, a fourth accuracy parameter according to the congestion level of the general vehicles traveling in the used section, a fifth accuracy parameter according to the usage fee of the special express vehicle, or a sixth accuracy parameter according to the departure time difference between the special express vehicle and the general vehicle, estimating the utilization probability further based on any one or more of the third certainty parameter, the fourth certainty parameter, the fifth certainty parameter, or the sixth certainty parameter; 10. A railway utilization management system as set forth in Appendix 10.

[0208] Appendix 12 a user determination unit that determines a plurality of users who will use the departure station during a specific time period on a predetermined prediction date based on the boarding and alighting history of the users; the utilization probability estimation unit estimates the utilization probability that each of the plurality of users determined by the user determination unit will utilize the specific express car departing from the departure station or a transfer station before or after the departure station toward the destination station at a time close to the specific time period; a user number prediction unit that predicts the number of paying users who will use the special express vehicle based on the usage probability of each of the plurality of users estimated by the usage probability estimation unit, The utilization probability estimation unit setting a first accuracy parameter according to both or either one of whether or not the specified premium vehicle has been used and the number of times it has been used during a predetermined period based on the premium vehicle usage history; calculating a ride time when the user rides in the general vehicle traveling in the usage section based on the boarding and alighting history of the user, and setting a second accuracy parameter according to the ride time; estimating the utilization probability based on the first certainty parameter and the second certainty parameter; a parameter correction unit that corrects both or either one of the first accuracy parameter and the second accuracy parameter using a correction value calculated based on a difference between the predicted number of users predicted by the user number prediction unit and the actual number of users of the specific express vehicle; The railway usage management system described in Appendix 2.

[0209] Appendix 13 the parameter correction unit corrects both or either one of the first accuracy parameter and the second accuracy parameter so that the predicted number of users approximates the actual number of users; 12. A railway utilization management system as set forth in Appendix 12.

[0210] Appendix 14 a probability variable change unit that changes a set value of a probability parameter according to one or more of the required time for the section of use, the congestion level of the general vehicles traveling in the section of use, the use fee for the special express vehicle, or the departure time difference; The railway usage management system described in Appendix 11, wherein the usage probability estimation unit estimates the usage probability of using the specific express vehicle based on the probability parameter changed by the probability variable change unit.

[0211] Appendix 15 a utilization section determination unit that determines a utilization section of a railway line that is used by a user, the utilization section being from a predetermined departure station to a destination station; a utilization probability estimation unit that estimates, based on the utilization section, a utilization probability of the user using a specific express vehicle that travels to the destination station for at least a portion of the utilization section, among express vehicles that require a utilization fee in addition to the fare required for riding a general vehicle; and A utilization probability estimation device comprising:

[0212] Appendix 16 a utilization section determination step of determining a utilization section of a railway line from a predetermined departure station to a destination station to be utilized by the user; A usage probability estimation method executed by one or more processors, comprising: a usage probability estimation step of estimating, based on the usage section, the usage probability that the user will use a specific express train that travels to the destination station for at least a portion of the usage section, among express trains that require a usage fee in addition to the fare required to ride a regular train;

[0213] Appendix 17 a utilization section determination step of determining a utilization section of a railway line from a predetermined departure station to a destination station to be utilized by the user; A program for causing one or more processors to execute the following steps: a usage probability estimation step for estimating, based on the usage section, the usage probability of the user using a specific express train that travels to the destination station for at least a portion of the usage section, among express trains that require a usage fee in addition to the fare required to travel in a regular train; [Explanation of symbols]

[0214] 10: Management device 11: Control section 12: Storage section 13: Communications Department 14: Display section 15:Operation unit 30: Database 40: User terminal 100: Railway usage management system 111: Data acquisition unit 112: Usage section determination unit 113: Usage probability estimation unit 114: User determination section 115: User Prediction Department 116: Parameter correction unit 117: Output processing section 118: Accuracy variable change section 121-126: Accuracy variable table 200: Seat reservation system 201: Purchase history data 300: Boarding and alighting management system 400: Point System

Claims

1. a utilization section determination unit that determines a utilization section of a railway line that is used by a user, the utilization section being from a predetermined departure station to a destination station; a utilization probability estimation unit that estimates, based on the utilization section, a utilization probability that the user will utilize a specific priority vehicle that travels to the destination station for at least a portion of the utilization section, among priority vehicles that require a utilization fee in addition to the fare required for riding a general vehicle; and A railway usage management system equipped with:

2. the utilization probability estimation unit estimates the utilization probability further based on a priority vehicle utilization history indicating that the specific priority vehicle traveling in the utilization section has been utilized in the past; The railway utilization management system according to claim 1 .

3. The utilization probability estimation unit estimates the utilization probability further based on any one or more of the required time for the utilization section, attributes of the user, the congestion level of the general vehicles traveling in the utilization section, the utilization fee for the special express vehicle, the departure time difference between the general vehicle and the special express vehicle, or the distance of the utilization section. The railway utilization management system according to claim 1 or 2.

4. The required time is the travel time when the general vehicle travels through the utilization section according to a predetermined operation plan. The railway utilization management system according to claim 3 .

5. The user attributes are attribute information included in user registration data in which user registration information about the user is registered. The railway utilization management system according to claim 3 .

6. a user determination unit that determines a plurality of users who will use the departure station during a specific time period on a predetermined prediction date based on the boarding and alighting history of the users; The utilization probability estimation unit estimates the utilization probability that each of the plurality of users determined by the user determination unit will utilize the specific express car departing from the departure station or a transfer station before or after the departure station toward the destination station at a time close to the specific time period. The railway utilization management system according to claim 1 or 2.

7. a user number prediction unit that predicts the number of paying users who will use the special express vehicle based on the usage probability of each of the plurality of users estimated by the usage probability estimation unit; The railway utilization management system according to claim 6.

8. and an output processing unit that transmits, at a predetermined timing before the end of applications for the special express vehicle, if the predicted number of users predicted by the user number prediction unit is less than a predetermined first threshold based on the allowable number of users of the special express vehicle, to the user determined by the user determination unit, usage promotion information that promotes the use of the special express vehicle. The railway utilization management system according to claim 7.

9. and an output processing unit that outputs information indicating that the number of passengers will exceed the allowable capacity of the special express vehicle to a predetermined reservation system that manages reservations for the special express vehicle, when the predicted number of passengers predicted by the user number prediction unit is equal to or greater than a predetermined second threshold based on the allowable capacity of the special express vehicle at a predetermined timing before the end of applications for use of the special express vehicle. The railway utilization management system according to claim 7.

10. The utilization probability estimation unit setting a first accuracy parameter according to both or either one of whether or not the specified premium vehicle has been used and the number of times the specified premium vehicle has been used during a predetermined period based on the premium vehicle usage history; calculating a ride time when the user rides in the general vehicle traveling in the use section based on the boarding and alighting history of the user, and setting a second accuracy parameter according to the ride time; estimating the utilization probability based on the first certainty parameter and the second certainty parameter; The railway utilization management system according to claim 2 .

11. The utilization probability estimation unit Further setting one or more of a third accuracy parameter according to the attributes of the user, a fourth accuracy parameter according to the congestion level of the general vehicles traveling in the use section, a fifth accuracy parameter according to the use fare of the special express vehicle, or a sixth accuracy parameter according to the departure time difference between the special express vehicle and the general vehicle, estimating the utilization probability further based on any one or more of the third certainty parameter, the fourth certainty parameter, the fifth certainty parameter, or the sixth certainty parameter; The railway utilization management system according to claim 10.

12. a user determination unit that determines a plurality of users who will use the departure station during a specific time period on a predetermined prediction date based on the boarding and alighting history of the users; the utilization probability estimation unit estimates the utilization probability that each of the plurality of users determined by the user determination unit will utilize the specific express car departing from the departure station or a transfer station before or after the departure station toward the destination station at a time close to the specific time period; a user number prediction unit that predicts the number of paying users who will use the special express vehicle based on the usage probability of each of the plurality of users estimated by the usage probability estimation unit, The utilization probability estimation unit setting a first accuracy parameter according to both or either one of whether or not the specified premium vehicle has been used and the number of times the specified premium vehicle has been used during a predetermined period based on the premium vehicle usage history; calculating a ride time when the user rides in the general vehicle traveling in the use section based on the boarding and alighting history of the user, and setting a second accuracy parameter according to the ride time; estimating the utilization probability based on the first certainty parameter and the second certainty parameter; a parameter correction unit that corrects both or either one of the first accuracy parameter and the second accuracy parameter using a correction value calculated based on a difference between the predicted number of users predicted by the user number prediction unit and the actual number of users of the specific priority vehicle; The railway utilization management system according to claim 2 .

13. the parameter correction unit corrects both or either one of the first accuracy parameter and the second accuracy parameter so that the predicted number of users approximates the actual number of users; The railway utilization management system according to claim 12.

14. a probability variable change unit that changes a set value of a probability parameter according to one or more of the required time for the section of use, the congestion level of the general vehicles traveling in the section of use, the use fee for the special express vehicle, or the departure time difference; The railway utilization management system according to claim 11 , wherein the utilization probability estimation unit estimates the utilization probability of utilizing the specific priority vehicle based on the accuracy parameter changed by the accuracy variable change unit.

15. a utilization section determination unit that determines a utilization section of a railway line that is used by a user, the utilization section being from a predetermined departure station to a destination station; a utilization probability estimation unit that estimates, based on the utilization section, a utilization probability that the user will utilize a specific priority vehicle that travels to the destination station for at least a portion of the utilization section, among priority vehicles that require a utilization fee in addition to the fare required for riding a general vehicle; and A utilization probability estimation device comprising:

16. a utilization section determination step of determining a utilization section of a railway line from a predetermined departure station to a destination station to be utilized by the user; A usage probability estimation method executed by one or more processors, comprising: a usage probability estimation step of estimating, based on the usage section, the usage probability that the user will use a specific express train that travels to the destination station for at least a portion of the usage section, among express trains that require a usage fee in addition to the fare required to ride a regular train;

17. a utilization section determination step of determining a utilization section of a railway line from a predetermined departure station to a destination station to be utilized by the user; A program for causing one or more processors to execute the following steps: a usage probability estimation step for estimating, based on the usage section, the usage probability of the user using a specific express train that travels to the destination station for at least a portion of the usage section, among express trains that require a usage fee in addition to the fare required to travel in a regular train;

Images