Congestion prediction system, congestion prediction method, and congestion prediction program

Abstract

To provide a congestion prediction system, a congestion prediction method, and a congestion prediction program capable of predicting congestion on a target device.SOLUTION: A congestion prediction system 10 includes: an acquisition processing part 112 which acquires first transaction data of a first user who used a target device (ticket machine 2, automatic ticket gate 3) and second transaction data of a second user who used the target device after the first user; and a calculation processing part 114 which calculates congestion level of the use target device according to time difference between transaction end time of the use target device included in the first transaction data and transaction start time of the use target device included in the second transaction data.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a technique for predicting congestion at target equipment such as station service equipment. [Background technology]

[0002] Congestion in railway stations or on trains can have a significant impact on train operations, such as increasing the time it takes passengers to board and disembark, causing delays in train arrivals and departures, etc. Therefore, in order to deal with congestion at railway stations, technology has been proposed that predicts congestion at stations based on information such as data acquired from automatic ticket gates and train schedule data (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-103924 Summary of the Invention [Problem to be solved by the invention]

[0004] Congestion at stations is thought to fluctuate depending on the number and functionality of station equipment (devices to be used), such as automatic ticket gates and ticket vending machines, installed at stations. The number of station equipment varies depending on factors such as the size of the station and the number of users. For example, if there is not enough station equipment compared to the number of users, queues will form at the station equipment, causing congestion at the station. Installing the optimal number of station equipment at each station would help alleviate congestion at stations, but until now it has been difficult to predict congestion at station equipment.

[0005] An object of the present invention is to provide a congestion prediction system, a congestion prediction method, and a congestion prediction program that are capable of predicting congestion at a target device. [Means for solving the problem]

[0006] The congestion prediction system according to the present invention predicts congestion at a target device based on usage history data of users who have used the device, and includes an acquisition processing unit and a calculation processing unit. The acquisition processing unit acquires first usage history data of a first user who used the target device and second usage history data of a second user who used the target device after the first user. The calculation processing unit calculates the congestion level of the target device based on the time difference between the end time of use of the target device included in the first usage history data and the start time of use of the target device included in the second usage history data.

[0007] The congestion prediction method of the present invention is a congestion prediction method that predicts congestion at a target device based on usage history data of users who have used the device, and is executed by one or more processors to obtain first usage history data of a first user who used the target device and second usage history data of a second user who used the target device after the first user, and calculate the degree of congestion at the target device based on the time difference between the end time of usage of the target device included in the first usage history data and the start time of usage of the target device included in the second usage history data.

[0008] The congestion prediction program of the present invention is a congestion prediction program that predicts congestion at a target device based on usage history data of users who have used the device, and causes one or more processors to execute the following steps: obtain first usage history data of a first user who used the target device and second usage history data of a second user who used the target device after the first user; and calculate the degree of congestion at the target device based on the time difference between the end time of usage of the target device included in the first usage history data and the start time of usage of the target device included in the second usage history data. [Effects of the Invention]

[0009] According to the present invention, a congestion prediction system, a congestion prediction method, and a congestion prediction program are provided that are capable of predicting congestion at a target device. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram showing the overall configuration of a congestion prediction system according to an embodiment of the present invention. [Figure 2] FIG. 2 is an external view showing an example of a ticket vending machine according to an embodiment of the present invention. [Figure 3] FIG. 3 is an external view showing an example of an automatic ticket gate according to an embodiment of the present invention. [Figure 4] FIG. 4 is a functional block diagram showing the configuration of the management server according to the embodiment of the present invention. [Figure 5] FIG. 5 is a diagram showing an example of transaction data information used in the congestion prediction system according to the embodiment of the present invention. [Figure 6] FIG. 6 is a diagram showing an example of estimated date and time information used in the congestion prediction system according to the embodiment of the present invention. [Figure 7] FIG. 7 is a diagram showing an example of congestion prediction information used in the congestion prediction system according to the embodiment of the present invention. [Figure 8] FIG. 8 is a diagram showing a typical usage situation of a user in a ticket vending machine according to an embodiment of the present invention. [Figure 9] FIG. 9 is a graph showing the relationship between the interval between the arrival times of users and the cumulative number of arrivals at a ticket vending machine according to an embodiment of the present invention. [Figure 10] FIG. 10 is a flowchart showing an example of a procedure for a congestion prediction process executed by the congestion prediction system according to the embodiment of the present invention. [Figure 11] FIG. 11 is a flowchart showing an example of a procedure for a congestion prediction process executed by the congestion prediction system according to the embodiment of the present invention. [Figure 12A] FIG. 12A is a diagram for explaining a specific example (specific example 2-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 12B] FIG. 12B is a diagram showing a transaction status corresponding to a specific example (specific example 2-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 13A] FIG. 13A is a diagram for explaining a specific example (specific example 2-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 13B] FIG. 13B is a diagram showing a transaction status corresponding to a specific example (specific example 2-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 14A] FIG. 14A is a diagram for explaining a specific example (specific example 2-2) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 14B] FIG. 14B is a diagram showing a transaction status corresponding to a specific example (specific example 2-2) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 15A] FIG. 15A is a diagram for explaining a specific example (specific example 2-2) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 15B] FIG. 15B is a diagram showing a transaction status corresponding to a specific example (specific example 2-2) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 16A] FIG. 16A is a diagram for explaining a specific example (specific example 2-3) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 16B] FIG. 16B is a diagram showing a transaction status corresponding to a specific example (specific example 2-3) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 17A] FIG. 17A is a diagram for explaining a specific example (specific example 2-3) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 17B] FIG. 17B is a diagram showing a transaction status corresponding to a specific example (specific example 2-3) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 18]FIG. 18 is a flowchart showing an example of the procedure of a ticket vending machine simulation process executed by the congestion prediction system according to the embodiment of the present invention. [Figure 19A] FIG. 19A is a diagram for explaining a specific example (specific example 3-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 19B] FIG. 19B is a diagram showing a transaction status corresponding to a specific example (specific example 3-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 20A] FIG. 20A is a diagram for explaining a specific example (specific example 3-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 20B] FIG. 20B is a diagram showing a transaction status corresponding to a specific example (specific example 3-1) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 21] FIG. 21 is a diagram for explaining a specific example (specific example 3-3) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 22] FIG. 22 is a diagram for explaining a specific example (specific example 3-4) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 23] FIG. 23 is a diagram for explaining a specific example (specific example 3-5) of a simulation in the congestion prediction system according to the embodiment of the present invention. [Figure 24] FIG. 24 is a flowchart showing an example of the procedure of an automatic ticket gate simulation process executed by the congestion prediction system according to the embodiment of the present invention. [Figure 25] FIG. 25 is a diagram for explaining a specific example of a simulation in the congestion prediction system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings to help understand the present invention. Note that the following embodiments are examples that embody the present invention and do not limit the technical scope of the present invention.

[0012] [Congestion Prediction System 10] A congestion prediction system 10 according to an embodiment of the present invention is a system for predicting congestion at target equipment that can be used by multiple users, and is applicable to systems for predicting congestion at target equipment in a variety of fields, such as station service equipment such as ticket vending machines, automatic ticket gates, and fare adjustment machines installed at railway stations, check-in machines installed at airports, ticket vending machines installed at bus stops, check-in machines installed at accommodation facilities, and vending machines (for example, vending machines installed at highway service areas, tourist spots, etc. and used by group travelers and tourists). In this embodiment, an example will be described in which the congestion prediction system 10 is applied to a system for predicting congestion at station service equipment installed at railway stations.

[0013] As shown in Fig. 1, the congestion prediction system 10 includes a management server 1, a ticket vending machine 2, an automatic ticket gate 3, and a station server 4. The management server 1, the ticket vending machine 2, the automatic ticket gate 3, and the station server 4 can communicate with each other via a network N2 such as the Internet, a LAN, a WAN, or a public telephone line. The ticket vending machine 2 and the automatic ticket gate 3 are examples of station equipment, and are examples of equipment that can be used in the present invention. The station equipment may also include a fare adjustment machine.

[0014] As shown in FIG. 1, each station is equipped with a station server 4, multiple ticket vending machines 2, and multiple automatic ticket gates 3. The station equipment is communicatively connected to one another via a network N1 such as a LAN. The station server 4 is also communicatively connected to a management server 1, which is a server device managed by a railway operator (railway company), via a network N2 such as a dedicated line or public line. The management server 1 is a central monitoring device managed by the railway operator that operates railway operations including stations, and manages station equipment such as the station server 4, ticket vending machines 2, and automatic ticket gates 3 at all stations operated by the railway operator. As shown in FIG. 1, the management server 1 is wirelessly connected to the network N2 and performs data communication between the station server 4 and each piece of station equipment via the network N2 in accordance with a predetermined communication protocol.

[0015] Here, a brief description will be given of the configurations of the ticket vending machine 2 and the automatic ticket gate 3. Fig. 2 shows an example of the ticket vending machine 2, and Fig. 3 shows an example of the automatic ticket gate 3.

[0016] [Ticket machine 2] The ticket vending machine 2 is installed at a station ticket counter and performs processes such as issuing tickets and charging to users. A plurality of ticket vending machines 2 are arranged side by side. Each ticket vending machine 2 includes an operation and display unit 23, a ticket issuing unit 24, a currency processing unit 25, and a card processing unit 26. The plurality of ticket vending machines 2 may have the same functions or different functions. The ticket vending machine 2 performs data communication with station service equipment such as automatic ticket gates 3 and station server 4 via network N1.

[0017] The operation display unit 23 is a user interface that includes a display unit such as a liquid crystal display or organic EL display that displays various information, and an operation unit such as a touch panel that accepts operations. The operation display unit 23 is provided on the front of the main body of the ticket vending machine 2, and displays operation screens that allow users to purchase tickets and charge money to IC cards. In addition, below the operation display unit 23, an input device such as a key operation unit 23a with a numeric keypad is provided.

[0018] The ticket issuing unit 24 issues tickets and the like. The ticket issuing unit 24 is provided on the front side of the main body of the ticket vending machine 2 and dispenses tickets purchased by users to the outside. The currency processing unit 25 processes coins and banknotes. Specifically, the currency processing unit 25 is equipped with a coin processing unit that accepts coins used to settle the transaction amount for issuing tickets and the like and dispenses change coins to users, and a banknote processing unit that accepts banknotes used to settle the transaction amount for issuing tickets and the like and dispenses change banknotes to users. The currency processing unit 25 is equipped with a banknote insertion slot 25a, a coin insertion slot 25b, a banknote ejection slot 25c, a change coin tray 25d, etc. The currency processing unit 25 also has a currency identification unit that identifies the denomination and authenticity of coins and banknotes inserted by users and change coins and change banknotes dispensed as change.

[0019] The card processing unit 26 processes payment cards such as contactless IC cards that can be used as train tickets and credit cards. The card processing unit 26 is provided on the front of the main body of the ticket vending machine 2. The card processing unit 26 has the function of reading and writing card data from the IC of a contactless IC card inserted into the card insertion slot. The card processing unit 26 also has the function of reading and writing card data from the magnetic stripe of a magnetic card inserted into the card insertion slot. The configuration that realizes these functions is publicly known, so a detailed description will be omitted here.

[0020] The station server 4 acquires user transaction data (usage history data) from each ticket vending machine 2 installed in the station. The transaction data includes the transaction start date and time (date and time when use began), the transaction end date and time (date and time when use ended), the ticket vending machine 2 identification information (machine name, etc.), and operation details (transaction details). The transaction start date and time is, for example, the date and time when the ticket vending machine 2 accepts the user's start operation (for example, the operation to start purchasing a ticket, or the operation to start charging the amount). The transaction end date and time is, for example, the date and time when the ticket vending machine 2 accepts the user's end operation (for example, the operation to remove the issued ticket), the date and time when the ticket vending machine 2 issues a ticket, commuter pass, etc., and the date and time when charging is completed. The operation details include information such as the ticket's entry station, exit station, fare, adult / child type, boarding date, reserved / unreserved seat type, and charge amount. Each ticket vending machine 2 transmits transaction data to the station server 4, and the station server 4 transmits the transaction data of each ticket vending machine 2 associated with the station identification information (station code) to the management server 1.

[0021] [Automatic ticket gate 3] As shown in Figure 3, the automatic ticket gate 3 may be used as a dual-use automatic ticket gate that performs both entry and exit processing, with an entry automatic ticket gate 3A and an exit automatic ticket gate 3B facing each other to form a ticket gate passage R1 between them. One of the automatic ticket gates, 3A, serves as an entry automatic ticket gate that performs ticket processing (entrance ticket gate processing) for users entering the ticket gate from the ticket gate along the direction of travel at the time of entry (the direction of arrow D10). The other automatic ticket gate 3B serves as an exit automatic ticket gate that performs ticket processing (exit ticket gate processing) for users exiting from the ticket gate to the outside of the ticket gate along the direction of travel at the time of exit (the direction of arrow D11).

[0022] The automatic ticket gate 3 may be either the automatic ticket gate 3A or the automatic ticket gate 3B, which may be used alone to perform ticket gate processing for users passing in one direction. In this case, the automatic ticket gate 3A is used as an entrance automatic ticket gate, and the automatic ticket gate 3B is used as an exit automatic ticket gate.

[0023] The automatic ticket gate 3 includes a display unit 33, a gate 35, an IC reader 36, and a magnetic ticket inserter 37, all of which are provided in a housing 30 of the automatic ticket gate 3.

[0024] The display unit 33 displays a message to a user passing through the ticket gate passage R1. The display unit 33 has, for example, a liquid crystal panel. The display unit 33 is arranged on the top surface of the housing 30 of the automatic ticket gate 3. When the user is permitted to pass, the display unit 33 displays a message indicating that the user is permitted to pass. When the user is not permitted to pass, the display unit 33 displays a message indicating that the user is not permitted to pass (prohibited). When the automatic ticket gate 3 is used for exiting, the display unit 33 may display, for example, a message indicating that the fare is insufficient.

[0025] The automatic ticket gate 3 performs data communication with the station server 4 via the network N1 in accordance with a predetermined communication protocol. The automatic ticket gate 3 also performs data communication with the management server 1 via the network N2 in accordance with a predetermined communication protocol.

[0026] Gate 35 is installed near the exit on the front side in the travel direction in ticket gate passage R1 of automatic ticket gate 3. Gate 35 is, for example, a door that can be opened and closed. When gate 35 is opened, the user can pass through ticket gate passage R1 of automatic ticket gate 3, and when gate 35 is closed, the user cannot pass through ticket gate passage R1 of automatic ticket gate 3. Note that gate 35 is not limited to a physical door, and may be, for example, a door represented by a three-dimensional image using a hologram. Furthermore, gate 35 may be an audio gate that allows or prohibits the user from passing by audio.

[0027] The IC reader 36 reads ticket information (entrance station, exit station, etc.) from an IC ticket (IC medium) such as an IC card or a mobile terminal. The IC reader 36 also reads the amount of money charged to the IC ticket. The automatic ticket gate 3 performs ticket gate processing based on the read information.

[0028] A magnetic ticket is inserted into the magnetic ticket insertion unit 37. The automatic ticket gate 3 is equipped with a transport mechanism that transports and ejects the magnetic ticket, a reading mechanism that reads the ticket information on the magnetic ticket, and the like, and performs ticket gate processing based on the read information.

[0029] In the ticket gate processing, the station server 4 determines the entry station, exit station, fare (charge balance, fare, etc.) based on the ticket information obtained from the automatic ticket gate 3, and sends the determination result (whether the ticket is valid or invalid) to the automatic ticket gate 3, which then allows or prohibits passage through the ticket gate passage R1 based on the determination result.

[0030] 3 is an automatic ticket gate that can read both IC tickets and magnetic tickets (combined IC / magnetic automatic ticket gate), but the automatic ticket gate of the present invention may also include an automatic ticket gate that can read IC tickets but not magnetic tickets (IC-only automatic ticket gate), and an automatic ticket gate that can read magnetic tickets but not IC tickets (magnetic-only automatic ticket gate). The type of automatic ticket gate to be installed at a station (entrance, exit, entrance / exit, combined IC / magnetic, IC only, magnetic only, etc.) is determined depending on the size of the station and the number of users.

[0031] The station server 4 acquires user transaction data (usage history data) from each automated ticket gate 3 installed in a station. The transaction data includes the transaction start date and time (use start date and time), transaction end date and time (use end date and time), automated ticket gate 3 identification information (machine name, etc.), ticket type (IC ticket or magnetic ticket), and entry / exit type (entry or exit). The transaction start date and time may be, for example, the date and time when the automated ticket gate 3 reads the user's ticket, or the date and time when the sensor of the automated ticket gate 3 detects the user entering ticket gate passage R1. The transaction end date and time may be, for example, the date and time when the user removes the ticket ejected from the automated ticket gate 3, or the date and time when the sensor of the automated ticket gate 3 detects the user exiting ticket gate passage R1. Each automated ticket gate 3 transmits the transaction data to the station server 4, and the station server 4 transmits the transaction data of each automated ticket gate 3 associated with the station identification information (station code) to the management server 1.

[0032] When a large number of users gather at station service equipment such as the ticket vending machine 2 and the automatic ticket gate 3, queues may form. For example, when a user uses a train, the user purchases a ticket at the ticket vending machine 2 or charges an IC card. Because it takes a certain amount of time for a user to complete a transaction with the ticket vending machine 2, a queue may form in front of the ticket vending machine 2 as the number of users increases. Furthermore, for example, users pass through the automatic ticket gate 3 when entering the ticket gate to board a train and when exiting the ticket gate after disembarking. For example, when a train arrives at a station, many users who have disembarked gather at the automatic ticket gate 3 to exit the ticket gate, forming a queue at the automatic ticket gate 3. When queues form at station service equipment, the number of people remaining inside the station increases, reducing convenience for users, causing delays in train arrivals and departures, and increasing the workload of station staff, thereby adversely affecting train operations.

[0033] Therefore, the congestion prediction system 10 according to this embodiment has a configuration that can predict congestion on station equipment. The configuration of the congestion prediction system 10 makes it possible to reduce the number of people remaining in the station and alleviate congestion at the station by implementing measures to alleviate congestion on station equipment based on the results of congestion prediction on station equipment. The specific configuration of the congestion prediction system 10 will be described below.

[0034] [Administration Server 1] FIG. 4 is a functional block diagram showing the configuration of a congestion prediction system 10. As shown in FIG. 4, the management server 1 is an information processing device (server device) including a control unit 11, a memory unit 12, an operation / display unit 13, and a communication unit 14. The management server 1 is not limited to a single computer, but may be a computer system in which multiple computers operate in cooperation with each other. The various processes executed by the management server 1 may be distributed and executed by one or multiple processors. The management server 1 also has a management function for managing station service equipment such as the station server 4, ticket vending machines 2, and automatic ticket gates 3 at each station, and a congestion prediction function for predicting congestion at the station service equipment. In another embodiment, the management server 1 may be a congestion prediction device that only has a congestion prediction function.

[0035] The communication unit 14 is a communication interface that connects the management server 1 to the network N2 via a wired or wireless connection and performs data communication in accordance with a predetermined communication protocol with external devices such as the station server 4, ticket vending machine 2, and automatic ticket gate 3 via the network N2.

[0036] The operation display unit 13 is a user interface that includes a display unit such as a liquid crystal display or an organic EL display that displays various information, and an operation unit such as a mouse, keyboard, or touch panel that accepts operations.

[0037] The storage unit 12 is a non-volatile storage unit such as an HDD (Hard Disk Drive), SSD (Solid State Drive), or flash memory that stores various types of information. Specifically, the storage unit 12 stores data such as transaction data information D1 including transaction data acquired from the station server 4, estimated date and time information D2 estimated based on the transaction data, and congestion prediction information D3 indicating the results of congestion prediction processing. FIG. 5 is a diagram showing an example of the transaction data information D1, FIG. 6 is a diagram showing an example of the estimated date and time information D2, and FIG. 7 is a diagram showing an example of the congestion prediction information D3. Note that FIGS. 5 to 7 each show information corresponding to a ticket vending machine 2 at a certain station (hereinafter referred to as "α station"). A specific example of the process of predicting congestion at the ticket vending machine 2 at α station will be described below.

[0038] As shown in FIG. 5, the transaction data information D1 includes information such as the corresponding "transaction start date and time," "transaction end date and time," and "machine name" for each transaction data. The transaction data information D1 also includes past transaction data (usage history data) corresponding to the operations performed on the ticket vending machine 2 by each user. The transaction start date and time is the date and time when the ticket vending machine 2 accepts the user's start operation, for example, the date and time when the user begins purchasing a ticket, i.e., the date and time when the user begins using the ticket vending machine 2. The transaction end date and time is the date and time when the ticket vending machine 2 accepts the user's end operation, for example, the date and time when the user removes the ticket issued by the ticket vending machine 2, i.e., the date and time when the user finishes using the ticket vending machine 2. In another embodiment, the transaction start date and time and the transaction end date and time may be determined by detecting the user using a sensor or camera on the ticket vending machine 2. The machine name is identification information for the ticket vending machine 2.

[0039] FIG. 5 shows transaction data (No. 1 to 6) for the first through sixth users at ticket vending machine 2 No. 3 at station α. ​​Transaction data information D1 may register transaction data for one device, or may register transaction data for all devices. When transaction data for one device is registered in transaction data information D1, multiple pieces of transaction data D1 for each device are stored in memory unit 12. FIG. 5 shows transaction data information D1 extracted from transaction data for ticket vending machine 2 No. 3 at station α. ​​Upon acquiring each piece of transaction data output from station server 4, control unit 11 registers it in transaction data information D1. Note that control unit 11 may acquire transaction data from station server 4 each time a transaction is made by one user at ticket vending machine 2 and register it in transaction data information D1, or may acquire multiple pieces of transaction data from station server 4 at predetermined intervals and register them in transaction data information D1.

[0040] As shown in FIG. 6, the estimated date and time information D2 includes information such as the corresponding "transaction start date and time," "transaction end date and time," "machine name," and "estimated arrival date and time" for each transaction data. The transaction start date and time, transaction end date and time, and machine name are the same as those in the transaction data information D1. The estimated arrival date and time is the estimated arrival time of the user arriving at the location where the ticket vending machine 2 will be used (in front of the ticket vending machine 2, such as the location where the ticket vending machine 2 is installed or operated). The estimated arrival date and time is estimated by the "arrival time estimation process" described below. FIG. 6 shows the estimated date and time information D2 for ticket vending machine No. 3 at station α.

[0041] As shown in FIG. 7, congestion prediction information D3 includes, for each transaction data, information such as the corresponding "transaction start date and time," "transaction end date and time," "machine name," "estimated arrival date and time," "number of people waiting," and "waiting time." The transaction start date and time, transaction end date and time, and machine name are the same as those in transaction data information D1, respectively, and the estimated arrival date and time is the same as that in estimated date and time information D2. The number of people waiting and the wait time are examples of the congestion degree of the present invention and are calculated by the "congestion degree calculation process" described below. FIG. 7 shows congestion prediction information D3 for ticket vending machine No. 3 2 at station α.

[0042] In another embodiment, some or all of the information such as the transaction data information D1, the estimated date and time information D2, and the congestion prediction information D3 may be stored in another server accessible from the management server 1 via the network N2. For example, the transaction data information D1 may be stored in the station server 4. In this case, the control unit 11 of the management server 1 may acquire the transaction data information D1 from the station server 4 and execute various processes such as the arrival time estimation process and the congestion degree calculation process described below.

[0043] The storage unit 12 also stores control programs such as a congestion prediction program for causing the control unit 11 to execute a congestion prediction process (see FIGS. 10 and 11) described below, and a station service equipment simulation program for causing the control unit 11 to execute a station service equipment simulation process (see FIGS. 18 and 24). For example, the control program is non-temporarily recorded on a computer-readable recording medium such as a CD or DVD, and is read by a reading device (not shown) such as a CD drive or DVD drive provided in the management server 1 and stored in the storage unit 12.

[0044] 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 unit in which control programs such as an OS that cause the CPU to execute various types of arithmetic processing are pre-stored. The RAM is a volatile or non-volatile storage unit that stores various types of information and is used as a temporary storage memory (work area) for the various types of processing executed by the CPU. The control unit 11 controls the management server 1 by having the CPU execute various control programs pre-stored in the ROM or the storage unit 12.

[0045] Specifically, as shown in Fig. 4, the control unit 11 includes various processing units such as a registration processing unit 111, an acquisition processing unit 112, an estimation processing unit 113, a calculation processing unit 114, a presentation processing unit 115, and an allocation processing unit 116. The control unit 11 functions as the various processing units by executing various processes in accordance with the control program using the CPU. Some or all of the processing units may be configured with electronic circuits. The control program may be a program for causing multiple processors to function as the processing units.

[0046] The control unit 11 mainly executes congestion prediction processing (arrival time estimation processing, congestion degree calculation processing) and station service equipment simulation processing. Each processing will be explained below separately.

[0047] [1. Congestion prediction processing] [1-1. Arrival time estimation process] The control unit 11 executes a process (arrival time estimation process) to estimate the arrival time at which the user arrives at the location where the user uses station service equipment (here, ticket vending machine 2) based on the transaction data information D1 (see FIG. 5).

[0048] Specifically, the registration processing unit 111 registers each transaction data of a user at the ticket vending machine 2 in the transaction data information D1 (see FIG. 5). For example, when the station server 4 acquires transaction data from the ticket vending machine 2, it transmits the transaction data to the management server 1. When the registration processing unit 111 acquires transaction data from the station server 4, it registers information contained in the transaction data, such as the transaction start date and time, the transaction end date and time, and the machine name, in the transaction data information D1. The registration processing unit 111 registers the transaction data at each ticket vending machine 2 at each station in the transaction data information D1, associating it with the station identification information (station code) and the machine name. The registration processing unit 111 stores each transaction data at the ticket vending machine 2 in the memory unit 12 so that it can be searched and extracted by station and machine name.

[0049] The acquisition processing unit 112 acquires transaction data for which estimated arrival times are to be estimated from the transaction data information D1 (see FIG. 5). For example, the acquisition processing unit 112 acquires transaction data in order of earliest transaction start date and time (oldest date and time).

[0050] The estimation processing unit 113 estimates the estimated arrival time (estimated arrival time) of the user at the usage location where the user uses the ticket vending machine 2, based on the transaction data acquired by the acquisition processing unit 112. Specifically, the estimation processing unit 113 estimates the estimated arrival time of the user to be estimated based on the time difference t0 between the transaction end date and time (transaction end time) included in the transaction data of the user immediately preceding the user to be estimated and the transaction start date and time (transaction start time) included in the transaction data of the user to be estimated.

[0051] FIG. 8 shows a schematic diagram of how users use the ticket vending machine 2. For example, user A starts a transaction (e.g., purchasing a train ticket) as soon as he arrives at an unused ticket vending machine No. 3 2 at time t1. In this case, the transaction start time t1 can be considered the estimated arrival time. After that, user A's transaction ends at time t2, and user B starts a transaction at time t3, t0 hours after time t2.

[0052] Here, if the t0 time is long, that is, if the time between when user A finishes using the ticket vending machine 2 and when user B starts using it is long, it is unlikely that user B arrived at the location of the ticket vending machine 2 while user A was using it and was waiting for user A to finish using it, and it is more likely that user B arrived at the location after user A had finished using the ticket vending machine 2 and left the location. On the other hand, if the t0 time is short, that is, if the time between when user A finished using the ticket vending machine 2 and when user B started using it is short, it is more likely that user B arrived at the location of the ticket vending machine 2 while user A was using it and was waiting for user A to finish using it.

[0053] Therefore, if the time difference t0 between user A's transaction end time t2 and user B's transaction start time t3 is equal to or greater than threshold value Tth, the estimation processing unit 113 estimates user B's transaction start time t3 as the estimated arrival time. On the other hand, if the time difference t0 between user A's transaction end time t2 and user B's transaction start time t3 is less than threshold value Tth, the estimation processing unit 113 estimates a time before user A's transaction end time t2 as the estimated arrival time. The threshold value Tth is set in advance based on the time required to use station service equipment, and is set to, for example, 10 seconds for the ticket vending machine 2 and 2 seconds for the automatic ticket gate 3. The control unit 11 may automatically set threshold value Tth depending on the service equipment, or the administrator of the management server 1 may set or change threshold value Tth.

[0054] In the example shown in FIG. 8 , the time difference t0 between user A's transaction end time t2 and user B's transaction start time t3 is equal to or greater than the threshold value Tth, so the estimation processor 113 estimates user B's transaction start time t3 as the estimated arrival time of user B. Furthermore, the time difference t0 between user B's transaction end time t4 and the next user C's transaction start time t5 is also equal to or greater than the threshold value Tth, so the estimation processor 113 estimates user C's transaction start time t5 as the estimated arrival time of user C. In contrast, the time difference t0 between user C's transaction end time t6 and the next user D's transaction start time t7 is less than the threshold value Tth, so the estimation processor 113 estimates a time before user C's transaction end time t6 as the estimated arrival time of user D. Similarly, users E, F, G, and H have a time difference t0 less than the threshold value Tth, indicating that they are lining up to use the ticket vending machine 2.

[0055] Furthermore, when the time difference t0 is less than the threshold value Tth, the estimation processing unit 113 estimates the estimated arrival time of each user (users D to H in FIG. 8) using random numbers that follow an exponential distribution (see FIG. 9) with the time period when the queue is formed and the number of people in the queue as parameters.

[0056] FIG. 6 shows the estimated arrival time (estimated arrival date and time) of each transaction data item estimated by the estimation processing unit 113. For example, since there is no previous user for the first user (No. 1), the estimation processing unit 113 registers the transaction start date and time as the estimated arrival date and time. Since more than 10 seconds (threshold Tth) (t0 = 28 seconds) passed between the time the first user finished their transaction and the time the second user (No. 2) started their transaction, it is considered that the second user was not waiting in line. Therefore, the estimation processing unit 113 registers the transaction start date and time as the estimated arrival date and time of the second user.

[0057] Since less than 10 seconds elapsed between the time the second user finished their transaction and the time the third user (No. 3) started their transaction, it is believed that the third user arrived at the location of the ticket vending machine 2 before the second user finished their transaction. Therefore, the estimation processing unit 113 estimates the estimated arrival date and time of the third user using random numbers based on an exponential distribution. For example, the estimation processing unit 113 sets the number of people in line and the time it takes for the line to clear from the time it forms to the time it clears as parameters. In the example shown in FIG. 6, the fourth user (No. 4) and the fifth user (No. 5) are also in the queue because the time difference t0 is less than 10 seconds. The queue ends at the sixth user (No. 6) (the time difference t0 is 24 seconds, which is more than 10 seconds). Therefore, the number of people in the queue is three, and the queue time span is 1 minute 27 seconds, from the transaction start date and time of the third user (2024-04-01 07:26:13) to the transaction start date and time of the fifth user (2024-04-01 07:27:40). The estimation processing unit 113 calculates the arrival interval per user when three users arrive in 1 minute 27 seconds. Note that if the estimated arrival time is later than the transaction start time, the estimation processing unit 113 corrects the arrival time to the transaction start time.

[0058] In the case of the sixth user, it is considered that there is no queue, so the estimation processing unit 113 registers the transaction start date and time as the estimated arrival date and time of the sixth user.

[0059] In this way, the estimation processing unit 113 estimates the time (estimated arrival time) at which each user arrives at the location where the ticket vending machine 2 is used, based on the transaction data (usage history data) of each user at the ticket vending machine 2 (see FIG. 6). That is, the estimation processing unit 113 estimates the estimated arrival time corresponding to each user in the queue, based on the number of people in the queue represented by the number of consecutive transaction data where the time difference t0 is less than the threshold value Tth, and the period (time period) from the transaction start time of the first user in the queue to the transaction end time of the last user in the queue.

[0060] The estimation processing unit 113 estimates the estimated arrival time of each user for each of the multiple ticket vending machines 2 (machine 1, machine 2, machine 3, ...). Figure 6 shows the estimated arrival date and time of each user who used ticket vending machine 2 No. 3 at station α.

[0061] The estimation processing unit 113 can similarly estimate the estimated arrival time for the automatic ticket gate 3. In the case of the automatic ticket gate 3, since the transaction time (usage time) per person is short, the threshold value Tth is set to a time (for example, 2 to 3 seconds) shorter than that for the ticket vending machine 2.

[0062] Furthermore, in the case of ticket vending machines 2, users use the machine of their choice, so the degree of congestion varies for each machine. For this reason, it is desirable for the estimation processing unit 113 to estimate the estimated arrival time for each machine. In contrast, in the case of automatic ticket gates 3, users' purpose is to enter and exit, so the degree of congestion does not vary significantly for each automatic ticket gate 3. For this reason, it is desirable for the estimation processing unit 113 to estimate the estimated arrival time for each entry and exit for multiple automatic ticket gates 3 together. For example, for multiple automatic ticket gates 3 installed at α station, the control unit 11 estimates the estimated arrival time of each entering user based on the transaction data of entering users (entrance gate data), and estimates the estimated arrival time of each exiting user based on the transaction data of exiting users (exit gate data).

[0063] [1-2. Congestion degree calculation process] The calculation processing unit 114 calculates the congestion degree of the station service equipment. Specifically, the calculation processing unit 114 calculates the congestion degree of the station service equipment based on the time difference t0 between the transaction end date and time (transaction end time) included in the transaction data of the user immediately before the user to be estimated and the transaction start date and time (transaction start time) included in the transaction data of the user to be estimated. In addition, the calculation processing unit 114 calculates the congestion degree based on the estimated arrival time estimated by the estimation processing unit 113.

[0064] Here, the calculation processing unit 114 calculates, as an index representing the degree of congestion, for example, the number of users waiting to use station equipment (waiting number of users) and the time they have been waiting to use station equipment (waiting time). Specifically, the calculation processing unit 114 calculates the number of users waiting by counting the number of users who have already arrived at the location where the station equipment is being used at the end of each transaction. That is, the calculation processing unit 114 calculates the number of transaction data in which the time difference t0 is less than the threshold value Tth as the number of users waiting for the station equipment. For example, in the example shown in FIG. 6, at the third ticket vending machine 2, at the time of the second user's transaction completion date and time "April 1, 2024, 7:26:06," the third user (estimated arrival date and time "April 1, 2024, 7:25:59") has already arrived, and the fourth user (estimated arrival date and time "April 1, 2024, 7:26:35") has not arrived since then. Therefore, the calculation processing unit 114 calculates the number of people waiting at the time of the second user's transaction completion at the third ticket vending machine 2 as "1 person" (see FIG. 7). Also, for example, at the time of the third user's transaction completion at the third ticket vending machine 2, the fourth and fifth users have arrived, so the calculation processing unit 114 calculates the number of people waiting at the time of the third user's transaction completion as "2 people" (see FIG. 7). The calculation processing unit 114 similarly calculates the number of people waiting for each transaction data.

[0065] Furthermore, the calculation processing unit 114 calculates the time difference between the estimated arrival time and the transaction start time for each transaction data as the waiting time (see FIG. 7).

[0066] The calculation processing unit 114 calculates the congestion degree based on the number of people waiting and the waiting time (see FIG. 7) calculated for each transaction data. For example, the calculation processing unit 114 calculates the congestion degree as the maximum and average values ​​of the number of people waiting per hour and the maximum and average values ​​of the waiting time per hour.

[0067] The presentation processing unit 115 presents the degree of congestion calculated by the calculation processing unit 114. For example, the presentation processing unit 115 causes the operation display unit 13 to display the maximum and average number of people waiting per hour and the maximum and average waiting time per hour. For example, the presentation processing unit 115 may display a graph or a heat map showing the degree of congestion per hour.

[0068] The method of calculating and presenting the degree of congestion is the same regardless of the station equipment (ticket vending machine 2, automatic ticket gate 3, etc.).

[0069] [1-3. Congestion prediction process flow] 10 and 11, the congestion prediction process executed in the congestion prediction system 10 will be described. Specifically, in this embodiment, the congestion prediction process is executed by the control unit 11 of the management server 1. The control unit 11 may execute the congestion prediction process at predetermined intervals, or may execute the congestion prediction process in response to an instruction from a user (for example, a railway operator, an administrator of the management server 1, etc.).

[0070] The present invention can be understood as an invention of a congestion prediction method that executes one or more steps included in the congestion prediction process. Furthermore, one or more steps included in the congestion prediction process described herein may be omitted as appropriate. The steps in the congestion prediction process may be executed in a different order as long as the same effects are achieved. Furthermore, while the example described here is one in which the control unit 11 executes each step in the congestion prediction process, one or more processors may execute each step in the congestion prediction process in a distributed manner. The congestion prediction method is one example of the congestion prediction method of the present invention.

[0071] <Step S1> First, in step S1, the control unit 11 acquires transaction data, which is a usage history of a user using station equipment. Specifically, the control unit 11 acquires multiple pieces of transaction data in order of earliest transaction start date and time (oldest date and time) within a predetermined period. Here, it is assumed that the control unit 11 has acquired transaction data "No. 1" to "No. 6" (transaction data information D1 in FIG. 5) corresponding to ticket vending machine No. 3 2 at α station.

[0072] <Step S2> In step S2, the control unit 11 executes an arrival time estimation process for each acquired transaction data to estimate the time of arrival at the usage location of the ticket vending machine 2. Fig. 11 shows an example of the arrival time estimation process.

[0073] <Step S211> In step S211 of FIG. 11, the control unit 11 acquires the Nth transaction data from among the acquired transaction data in chronological order.

[0074] <Step S212> In step S212, the control unit 11 determines whether the time difference t0 between the transaction end date and time (transaction end time) included in the transaction data of the user immediately preceding the user to be estimated (the (N-1)th transaction data) and the transaction start date and time (transaction start time) included in the transaction data of the user to be estimated (the Nth transaction data) is greater than or equal to a threshold value Tth (10 seconds in this example). If the control unit 11 determines that the time difference t0 is greater than or equal to the threshold value Tth (S212: Yes), it proceeds to step S213, and if it determines that the time difference t0 is less than the threshold value Tth (S212: No), it proceeds to step S214.

[0075] In the case of the first transaction data, since there is no previous transaction data, the control unit 11 shifts the process to step S213. In the case of the second transaction data, the control unit 11 calculates the difference (time difference t0) between the transaction end time of the first transaction data and the transaction start time of the second transaction data, and determines whether the time difference t0 is 10 seconds or more.

[0076] <Step S213> In step S213, the control unit 11 estimates the transaction start time of the transaction data of the user to be estimated as the estimated arrival time. For example, in the case of the second transaction data shown in Figure 6, since the time difference t0 is 28 seconds, the control unit 11 estimates the transaction start time of the second transaction data as the estimated arrival time. The control unit 11 registers the transaction start time as the estimated arrival time (estimated arrival date and time) in the estimated date and time information D2 (see Figure 6).

[0077] <Step S214> In step S214, control unit 11 stores the transaction data of the user to be estimated as data to be estimated based on parameters. Control unit 11 estimates the arrival time for the stored transaction data to be estimated in step S216, which will be described later.

[0078] <Step S215> In step S215, the control unit 11 determines whether the above-mentioned determination process has been completed for all transaction data. If the control unit 11 has completed the above-mentioned determination process for all transaction data (S215: Yes), the control unit 11 proceeds to step S216. The control unit 11 repeatedly executes steps S211 to S214 until the above-mentioned determination process has been completed for all transaction data (S215: No). In this way, for the Nth transaction data, if the time difference t0 is 10 seconds or more, the control unit 11 estimates and registers the transaction start time as the estimated arrival time, and if the time difference t0 is less than 10 seconds, the control unit 11 suspends the estimation process at this point. In the example shown in FIG. 6, the control unit 11 suspends the transaction data of the third to fifth users (No. 3 to 5).

[0079] <Step S216> In step S216, control unit 11 performs parameter-based estimation processing on the transaction data stored in step S214. Specifically, control unit 11 estimates the estimated arrival time of each transaction data using random numbers that follow an exponential distribution, with the time period when a queue is formed and the number of people in the queue as parameters.

[0080] For example, the control unit 11 estimates the estimated arrival time of the third user using random numbers based on an exponential distribution as follows. In the example shown in FIG. 6, the third to fifth users (No. 3 to No. 5) are each waiting in line, and the line ends at the sixth user (No. 6). Therefore, the number of users in line is three, and the time period of the line is 1 minute 27 seconds from the transaction start date and time of the third user (2024-04-01 07:26:13) to the transaction start date and time of the fifth user (2024-04-01 07:27:40). Note that the number of users in line does not mean the total number of users waiting at one time, but rather the number of users who are waiting because there is at least one user ahead of them (a user currently making a transaction or a user waiting). The control unit 11 calculates the arrival interval per user when three users arrive in 1 minute 27 seconds. The control unit 11 estimates the estimated arrival time of the third user using a random number that follows an exponential distribution, with the time period "1 minute 27 seconds" and the number of people in line "3" as parameters. In this way, the control unit 11 estimates the estimated arrival time for each of the transaction data of the third to fifth users (No. 3 to 5) saved (reserved) in step S214. The control unit 11 registers each estimated estimated arrival time in estimated date and time information D2 (see FIG. 6).

[0081] When the control unit 11 finishes the arrival time estimation process, it shifts the process to step S3 (see FIG. 10).

[0082] <Step S3> In step S3, the control unit 11 calculates the congestion level at the station equipment. Specifically, the control unit 11 calculates the congestion level based on the estimated arrival time of each transaction data item estimated by the arrival time estimation process. For example, for each transaction data item, the control unit 11 counts the number of users who have already arrived at the location where the station equipment is used by the time the transaction ends, i.e., the number of users whose estimated arrival time is before the transaction end time, to calculate the number of people waiting. For example, in the example shown in FIG. 7, focusing on the transaction data of the third user, the estimated arrival times of the fourth and fifth users are before the transaction end time of the third user, and the estimated arrival time of the sixth user is after the transaction end time of the third user. In this case, the control unit 11 calculates the number of people waiting for the transaction data of the third user as two.

[0083] Furthermore, the control unit 11 calculates the time difference between the estimated arrival time and the transaction start time for each transaction data as the waiting time (see FIG. 7). Focusing on the transaction data of the third user, the control unit 11 calculates the time difference between the estimated arrival time "2024-04-01 07:25:59" and the transaction start time "2024-04-01 07:26:13" as "14 seconds".

[0084] In this way, the control unit 11 calculates the number of people waiting and the waiting time (degree of congestion) for each transaction data (see FIG. 7).

[0085] <Step S4> In step S4, the control unit 11 presents the calculated congestion level to the manager. For example, the control unit 11 causes the operation display unit 13 to display the maximum and average number of people waiting per hour and the maximum and average waiting time per hour. Note that the control unit 11 may present only either the number of people waiting or the waiting time as the congestion level.

[0086] In this way, the control unit 11 executes the congestion prediction process at predetermined intervals and presents the degree of congestion at the station service equipment.

[0087] [2.Station equipment simulation processing] The administrator of the management server 1 (railway operator) considers measures to alleviate congestion at station equipment, referring to the congestion level presented by the congestion prediction process. For example, the administrator determines the optimal number of station equipment by simulating changes in the congestion level by increasing or decreasing the number of station equipment units installed.

[0088] The management server 1 executes a simulation process based on an increase or decrease in the number of station equipment. Specifically, the allocation processing unit 116 of the control unit 11 allocates users to one of the station equipment in accordance with the increase or decrease in the number of station equipment. A specific example of the simulation process based on an increase or decrease in the number of ticket vending machines 2 will be described below.

[0089] <Example 2-1> Figure 12A shows the transaction data of three users who used ticket vending machines 2 No. 1, No. 2, and No. 3 in specific example 2-1. Figure 12B shows the transaction status (usage status) at the time when the third user arrived at ticket vending machine 2 No. 3 ("April 1, 2024, 7:24:30 AM"). At this time, the first user (ticket vending machine 2 No. 1) had completed their transaction, and the second user (ticket vending machine 2 No. 2) was in the middle of a transaction.

[0090] In the above example, a simulation will be performed in which, for example, ticket vending machine 2 No. 2 is removed. As shown in Figures 13A and 13B, allocation processing unit 116 allocates the second user to ticket vending machine 2 No. 3, which is available at the estimated arrival time. Also, allocation processing unit 116 allocates the third user to ticket vending machine 2 No. 1, which has completed a transaction at the estimated arrival time.

[0091] In the above example, since no new waiting numbers will occur after the allocation (distribution) of users due to the elimination of the second ticket vending machine 2, the allocation processing unit 116 maintains the transaction start date and time unchanged before and after the elimination of the ticket vending machine 2 (see Figure 13A).

[0092] <Example 2-2> Figure 14A shows the transaction data of three users who used ticket vending machines 2 No. 1, No. 2, and No. 3 in specific example 2-2. Figure 14B shows the transaction status at the time when the third user arrived at ticket vending machine 2 No. 3 ("April 1, 2024, 7:24:25 AM"). At this time, both the first user (ticket vending machine 2 No. 1) and the second user (ticket vending machine 2 No. 2) are in the middle of a transaction.

[0093] In the above example, a simulation will be performed in which, for example, ticket vending machine 2 No. 2 is removed. As shown in Figures 15A and 15B, allocation processing unit 116 allocates the second user to ticket vending machine 2 No. 3, which is available at the estimated arrival time. Also, allocation processing unit 116 allocates the third user to ticket vending machine 2 No. 1 or No. 3. Here, it is assumed that allocation processing unit 116 allocates the third user to ticket vending machine 2 No. 1.

[0094] Here, the transaction start date and time of the third user before the second ticket vending machine 2 is removed, "April 1, 2024, 7:24:25" (see FIG. 14A), is earlier than the transaction end date and time of the first user, "April 1, 2024, 7:24:30." Therefore, assuming that the third user uses the first ticket vending machine 2, the transaction start date and time of the third user must be changed to a time later than the transaction end date and time of the first user. Therefore, the allocation processing unit 116 changes the transaction start date and time of the third user to the transaction end date and time of the first user plus two seconds. In addition, the allocation processing unit 116 also changes the transaction end date and time in accordance with the change in the transaction start date and time. Here, the allocation processing unit 116 changes the transaction start date and time of the third user before the reduction of the second ticket vending machine 2 from "April 1, 2024, 7:24:25" to "April 1, 2024, 7:24:32", and accordingly changes the transaction end date and time from "April 1, 2024, 7:25:01" to "April 1, 2024, 7:25:08".

[0095] In this way, in specific example 2-2, the transaction start date and time is updated in accordance with the reduction in the number of ticket vending machines 2. When the transaction start date and time is changed, for example, the calculation processing unit 114 updates the time difference (waiting time) between the estimated arrival time and the transaction start time. As a result, the presentation processing unit 115 presents the updated congestion level as a simulation result. From the simulation result, the manager can understand how much the congestion level will change if the number of ticket vending machines 2 is increased or decreased.

[0096] Incidentally, there are three types of ticket vending machines 2: multi-function ticket vending machines that have a ticket purchasing function for purchasing tickets and a charging function for charging an amount onto an IC card; charging-type ticket vending machines that have no ticket purchasing function but have a charging function; and ticket purchasing-type ticket vending machines that have no charging function but have a ticket purchasing function.

[0097] Here, for example, in a simulation of reducing the number of ticket-purchase ticket vending machines 2, a user who has used a ticket-purchase ticket vending machine 2 cannot be assigned to a charge-type ticket vending machine 2. In this way, when ticket vending machines 2 with different functions are included, the assignment processing unit 116 needs to take into account the functions of the ticket vending machine 2 to which the ticket vending machine 2 is to be assigned. An example of this is explained in Specific Example 2-3 below.

[0098] <Example 2-3> Figure 16A shows the transaction data of four users who used ticket vending machines 2 No. 1, No. 2, and No. 3 in specific example 2-3. Here, No. 1 and No. 3 are multi-function ticket vending machines 2, and No. 2 is a charge-type ticket vending machine 2. Figure 16B shows the transaction status at the time when the fourth user arrived at ticket vending machine 2 No. 1 (April 1, 2024, 7:24:35). At this time, the first user (user of ticket vending machine 2 No. 2) had completed their transaction, and the second and third users (user of multi-function ticket vending machine 2 No. 1) were both in the middle of transactions.

[0099] In the above example, a simulation will be performed in which, for example, ticket vending machine No. 3 2 is removed. As shown in Figures 17A and 17B, the allocation processing unit 116 allocates the third user to multi-function ticket vending machine No. 1 2 because the third user is a ticket purchaser and cannot be allocated to charge-type ticket vending machine No. 2. Similarly, the allocation processing unit 116 allocates the fourth user to multi-function ticket vending machine No. 1 2 because the fourth user is also a ticket purchaser.

[0100] Also, similar to specific example 2-2, the allocation processing unit 116 adds 2 seconds to the transaction end date and time of the previous user, and changes the transaction start date and time and transaction end date and time of the third user and the transaction start date and time and transaction end date and time of the fourth user (see Figure 17A).

[0101] If there is another ticket vending machine 2 with fewer people waiting and from which tickets can be purchased, the allocation processing unit 116 may allocate users to that ticket vending machine 2 with priority.

[0102] [Ticket vending machine simulation process flow] The ticket vending machine simulation process executed in the congestion prediction system 10 will be described below with reference to FIG. 18. Specifically, in this embodiment, the ticket vending machine simulation process is executed by the control unit 11 of the management server 1. The control unit 11 may also execute the ticket vending machine simulation process in response to an execution instruction from a user. For example, the administrator selects a ticket vending machine 2 to be eliminated and inputs an instruction to execute the ticket vending machine simulation.

[0103] The present invention can be understood as an invention of a ticket vending machine simulation method that executes one or more steps included in the ticket vending machine simulation process. Furthermore, one or more steps included in the ticket vending machine simulation process described here may be omitted as appropriate. The steps in the ticket vending machine simulation process may be executed in a different order as long as the same operational effect is achieved. Furthermore, while the explanation here takes as an example a case where the control unit 11 executes each step in the ticket vending machine simulation process, one or more processors may execute each step in the ticket vending machine simulation process in a distributed manner. The ticket vending machine simulation method is an example of a congestion prediction method of the present invention.

[0104] <Step S11> First, in step S11, the control unit 11 acquires transaction data, which is a usage history of a user using station equipment. Specifically, the control unit 11 acquires the Nth transaction data in chronological order from transaction data information D1 (see FIG. 5), which stores usage histories of multiple ticket vending machines 2 installed at α station.

[0105] <Step S12> In step S12, the control unit 11 selects the ticket vending machine 2 with the smallest number of people waiting as the ticket vending machine 2 to be reduced. The control unit 11 also selects a ticket vending machine 2 that has the same functions as the ticket vending machine 2 to be reduced.

[0106] <Step S13> In step S13, the control unit 11 determines whether there is a queue at the assigned ticket vending machine 2 to which users of the ticket vending machine 2 to be reduced are to be assigned. If there is a queue at the assigned ticket vending machine 2 (specific examples 2-2 and 2-3 above) (S13: Yes), the control unit 11 shifts the process to step S14. On the other hand, if there is no queue at the assigned ticket vending machine 2 (specific example 2-1 above) (S13: No), the control unit 11 shifts the process to step S15.

[0107] <Step S14> In step S14, the control unit 11 changes the transaction time (transaction start date and time and transaction end date and time) of the transaction data. For example, the control unit 11 changes the transaction start date and time of the Nth transaction data to the transaction end date and time of the (N-1)th transaction data plus 2 seconds (see FIGS. 15A and 17A).

[0108] <Step S15> In step S15, the control unit 11 maintains the transaction times (transaction start date and time and transaction end date and time) of the transaction data at the times before the reduction of ticket vending machine 2 (before simulation) (see FIG. 13A).

[0109] <Step S16> In step S16, control unit 11 determines whether the above-mentioned determination process has been completed for all transaction data. When control unit 11 has completed the above-mentioned determination process for all transaction data (S16: Yes), control unit 11 ends the ticket vending machine simulation process. Control unit 11 repeatedly executes steps S11 to S15 until the above-mentioned determination process has been completed for all transaction data (S16: No).

[0110] In this way, the control unit 11 updates the transaction date and time of each transaction data when a ticket vending machine 2 is removed, and simulates the degree of congestion after the update. In other words, the control unit 11 (allocation processing unit 116) allocates target users to ticket vending machines 2 selected based on the functions of each ticket vending machine 2, its positional relationship with the ticket vending machine 2 to be removed, and the number of people queuing at each ticket vending machine 2.

[0111] In the above example, a simulation was shown for the case where the number of ticket vending machines 2 was reduced, but if an additional ticket vending machine 2 was added, the transaction date and time of each transaction data can be updated to simulate the degree of congestion after the update.

[0112] Next, a specific example of simulation processing based on an increase or decrease in the number of automatic ticket gates 3 will be described. As described above, there are multiple types of automatic ticket gates 3 according to their functions, such as entry, exit, dual entry / exit, combined IC / magnetic, IC only, and magnetic only. The allocation processing unit 116 allocates a user to an automatic ticket gate 3 having the same function based on information about the type of ticket (IC ticket or magnetic ticket) held by the user when the user passed through the automatic ticket gate 3. For example, a magnetic ticket cannot pass through an IC-only automatic ticket gate 3, so the allocation processing unit 116 allocates the user to an IC / magnetic combined automatic ticket gate 3. The allocation processing unit 116 also refers to entry or exit information and allocates the user to an automatic ticket gate 3 that is passable. For example, a user exiting a ticket gate cannot pass through an entry-only automatic ticket gate 3, so the allocation processing unit 116 allocates the user to an entry / exit or exit-only automatic ticket gate 3.

[0113] Furthermore, the automatic ticket gate 3 for both entrance and exit has three states: an exit state, an entry state, and a neutral state where both exit and entry are possible. After a user passes through, the state in the direction in which the user passed is maintained for a few seconds (for example, two seconds), and if no other users pass through during that time, the gate returns to the neutral state. If a user exits within a few seconds, the gate enters the exit state for the next two seconds, prohibiting entry, and then returns to the neutral state where both exit and entry are possible after another two seconds.

[0114] <Example 3-1> Figure 19A shows transaction data for 11 users in Example 3-1. Figure 19B shows the transaction status at the time when the 11th user arrived at the IC-only, entrance / exit, No. 1 automatic ticket gate 3 ("April 1, 2024, 7:24:15 AM"). At this time, the first and sixth users (at No. 1 automatic ticket gate) had completed their transactions (exit), the tenth user (at No. 1 automatic ticket gate) had completed their transaction (entry), the second user (at No. 2 automatic ticket gate) had completed their transaction (entry), the third and ninth users (at No. 3 automatic ticket gate) had completed their transactions (exit), the fourth user (at No. 4 automatic ticket gate) had completed their transaction (entry), and the fifth user (at No. 5 automatic ticket gate) had completed their transaction (exit). Also, at the above time, the seventh user (automatic ticket gate No. 4) has not completed the transaction (entry), and the eighth user (automatic ticket gate No. 5) has not completed the transaction (exit).

[0115] In the above example, a simulation will be performed in which, for example, the first automatic ticket gate 3 is removed. As shown in FIGS. 20A and 20B, the allocation processing unit 116 allocates the first user to the second automatic ticket gate 3. In this case, the first user enters through the second automatic ticket gate 3, so the second user is unable to immediately exit and must wait. The allocation processing unit 116 changes the transaction start date and time of the second user to "April 1, 2024, 7:24:11" (the transaction end date and time of the first user), plus the time (2 seconds) until the state switches to a neutral state, to "April 1, 2024, 7:24:13." Accordingly, the allocation processing unit 116 changes the transaction end date and time to "April 1, 2024, 7:24:15."

[0116] Furthermore, with the removal of the first automatic ticket gate, the allocation processing unit 116 allocates the sixth user to the adjacent second automatic ticket gate 3. At this time, the second user was originally scheduled to pass through after the first user, but because the sixth user entered after the first user, the second user is now able to exit after the sixth user. Therefore, the allocation processing unit 116 changes the transaction start date and time of the second user to "April 1, 2024, 7:24:15," which is the transaction end date and time of the sixth user, "April 1, 2024, 7:24:13," plus the time required to switch to a neutral state (2 seconds) (see FIG. 20A). Accordingly, the allocation processing unit 116 changes the transaction end date and time to "April 1, 2024, 7:24:17."

[0117] Furthermore, for the tenth user, the allocation processing unit 116 assumes that because machine No. 2 is in an entry state at the time the tenth user arrives (2024-04-01 07:24:14), the tenth user cannot exit, and checks another machine. The third automatic ticket gate 3 is an entry-only machine, so the tenth user cannot exit. The fourth automatic ticket gate 3 is in an exit state immediately after the fourth user exits, so the allocation processing unit 116 allocates the tenth user to the fourth automatic ticket gate 3. Because the tenth user exits after the seventh user, the allocation processing unit 116 changes the transaction start date and time of the tenth user to the transaction end date and time of the seventh user (2024-04-01 07:24:16). Accordingly, the allocation processing unit 116 changes the transaction end date and time to (2024-04-01 07:24:17).

[0118] The 11th user is deemed able to exit at the arrival time of "2024 / 04 / 01 07:24:15" because the second machine has returned to a neutral state, and the allocation processing unit 116 allocates the 11th user to the second automatic ticket gate 3. At this time, since the 11th user will exit after the second user, the allocation processing unit 116 changes the transaction start date and time of the 11th user to "2024 / 04 / 01 07:24:17" and the transaction end date and time to "2024 / 04 / 01 07:24:18".

[0119] Note that for users who use an automatic ticket gate 3 other than the automatic ticket gate 3 to be reduced, the allocation processing unit 116 does not perform allocation (change) processing of the used machine, but maintains the machine that was used and performs simulation. This is because people generally tend to select a machine that is closest to the direction of travel after passing through the automatic ticket gate 3, regardless of the number of people in line, and if optimization (simulation) is performed based on the premise of, for example, "using a machine with a smaller queue," it will be too optimized, resulting in an unrealistic degree of congestion (such as being lower than before the reduction). However, the allocation processing unit 116 is not limited to adjacent machines, and may check up to several neighboring machines and perform processing to preferentially allocate to machines with smaller queues from among them.

[0120] <Example 3-2> Furthermore, when allocating a user who has used the automated ticket gate 3 to be eliminated to another automated ticket gate 3, the allocation processing unit 116 may preferentially allocate the user to a locationally closer automated ticket gate 3. For example, when eliminating the second automated ticket gate 3, the allocation processing unit 116 checks whether allocation can be prioritized in the order of the first, third, and fourth automated ticket gates, and allocates the user to them. This is because it is considered that a user who has used the first automated ticket gate 3 would have had an advantage in terms of location in using the first automated ticket gate 3 (for example, it is close to the direction the user wants to go after passing through the ticket gate), and allocating the user to a locationally distant automated ticket gate 3 would result in simulation results that are unrealistic.

[0121] <Example 3-3> Furthermore, when IC-only automatic ticket gates 3 are eliminated, users who have used IC tickets are the allocation targets, but because IC tickets can be used at any type of automatic ticket gate 3, the allocation processing unit 116 can allocate to various types of automatic ticket gates 3 regardless of the type of gate. In contrast, when automatic ticket gates 3 that support magnetic tickets are eliminated, if users who have used magnetic tickets are the allocation targets, they cannot be allocated to IC-only automatic ticket gates 3. For this reason, for example, as shown in Figure 21, when eliminating gate 2, where a user exited using a magnetic ticket, the allocation processing unit 116 allocates the user to automatic ticket gate 3 4, which is close to gate 2 and from which a user can exit using a magnetic ticket.

[0122] <Example 3-4> Furthermore, as shown in FIG. 22, as the number of automatic ticket gates 3 is reduced, users may be assigned to both the entrance and exit sides of an automatic ticket gate 3 (machine 2) that can be used for both entrance and exit. FIG. 22 shows a state in which user X, who wants to exit, is assigned to machine 2, which is currently in an entrance state, because there are no other automatic ticket gates 3 available for exit. Since automatic ticket gate 3 2 is currently in an entrance state, user X cannot exit, but will be able to pass (exit) once the entrance queue (users A, B, and C) ends and the ticket gate returns to a neutral state. In this case, the allocation processing unit 116 changes the transaction start time of user X to the transaction end time of user C, who is at the end of the entrance queue, plus the time it takes for the automatic ticket gate 3 to return to a neutral state.

[0123] <Example 3-5> 23 shows a waiting queue at the second automatic ticket gate 3, where users A, B, and C on the exit side are waiting for the automatic ticket gate 3 to switch from an entry state to a neutral state. When the second automatic ticket gate 3 is in an entry state and, for example, user X who wants to enter is assigned to the second automatic ticket gate 3, the allocation processing unit 116 changes the transaction start time of user X to the transaction end time of user E who precedes user X. In addition, the allocation processing unit 116 changes the transaction start time of user A, who is at the head of the waiting queue, to the transaction end time of user X plus the time it takes for the automatic ticket gate 3 to return to the neutral state.

[0124] [Automatic ticket gate simulation processing flow] Hereinafter, the automatic ticket gate simulation process executed in the congestion prediction system 10 will be described with reference to FIG. 24. Specifically, in this embodiment, the automatic ticket gate simulation process is executed by the control unit 11 of the management server 1. The control unit 11 may also execute the automatic ticket gate simulation process in response to an execution instruction from a user. For example, the administrator selects an automatic ticket gate 3 to be eliminated and inputs an instruction to execute the automatic ticket gate simulation.

[0125] The present invention can be understood as an invention of an automatic ticket gate simulation method that executes one or more steps included in the automatic ticket gate simulation process. Furthermore, one or more steps included in the automatic ticket gate simulation process described herein may be omitted as appropriate. The steps in the automatic ticket gate simulation process may be executed in a different order as long as the same effects are achieved. Furthermore, while the description here uses an example in which the control unit 11 executes each step in the automatic ticket gate simulation process, one or more processors may execute each step in the automatic ticket gate simulation process in a distributed manner. The automatic ticket gate simulation method is an example of a congestion prediction method of the present invention.

[0126] <Step S21> First, in step S21, the control unit 11 acquires transaction data, which is a usage history of a user using station equipment. Specifically, the control unit 11 acquires the Nth transaction data in chronological order from transaction data information D1 (see FIG. 5) which stores usage histories of multiple automatic ticket gates 3 installed at α station.

[0127] <Step S22> In step S22, the control unit 11 determines whether the automatic ticket gate 3 that is the transaction target (target of use) corresponding to the acquired transaction data is a reduction target automatic ticket gate 3. If the transaction data is transaction data of the reduction target automatic ticket gate 3 (S22: Yes), the control unit 11 shifts the processing to step S23, and if the transaction data is not transaction data of the reduction target automatic ticket gate 3 (S22: No), the control unit 11 shifts the processing to step S221.

[0128] <Step S23> In step S23, the control unit 11 checks the state (entry state, exit state, neutral state) of each automatic ticket gate 3 at the time of arrival (estimated arrival date and time) corresponding to the acquired transaction data.

[0129] <Step S24> In step S24, the control unit 11 determines whether the automatic ticket gate 3 adjacent to the target automatic ticket gate 3 for reduction is in a passable state. If the adjacent automatic ticket gate 3 is in a passable state (S24: Yes), the control unit 11 shifts the processing to step S25, and if the adjacent automatic ticket gate 3 is not in a passable state (S24: No), the control unit 11 shifts the processing to step S241.

[0130] <Step S25> In step S25, the control unit 11 determines whether the automatic ticket gate 3 adjacent to the target automatic ticket gate 3 satisfies the functional conditions corresponding to the ticket type (IC ticket, magnetic ticket) corresponding to the transaction data. If the adjacent automatic ticket gate 3 satisfies the functional conditions (S25: Yes), the control unit 11 shifts the processing to step S26, and if the adjacent automatic ticket gate 3 does not satisfy the functional conditions (S25: No), the control unit 11 shifts the processing to step S241.

[0131] <Step S26> In step S26, the control unit 11 changes the machine number used by the user corresponding to the transaction data to the adjacent automatic ticket gate 3. In other words, the control unit 11 assigns the user corresponding to the transaction data to the adjacent automatic ticket gate 3.

[0132] <Step S241> In step S241, the control unit 11 determines whether all the automatic ticket gates are passable and whether they satisfy the functional conditions corresponding to the ticket type. The control unit 11 executes the determination process in order of proximity to the automatic ticket gate 3 to be reduced, and if there is a automatic ticket gate 3 that is passable and satisfies the functional conditions, assigns the user to that automatic ticket gate 3 (S26).

[0133] On the other hand, when the determination process is performed in order of proximity to the automatic ticket gate 3 to be reduced and there is no gate that is passable or satisfies the functional conditions (S241: Yes), the control unit 11 assigns the user to an automatic ticket gate 3 that is close to the automatic ticket gate 3 to be reduced, is for both entrance and exit, and is currently passable. After step S242, the control unit 11 shifts the process to step S221.

[0134] <Step S27> In step S27, the control unit 11 determines whether the automatic ticket gate 3 to which the user has been assigned is a dual-use automatic ticket gate and whether there are users waiting (queue) on the opposite side of the automatic ticket gate 3. If the automatic ticket gate 3 to which the user has been assigned is a dual-use automatic ticket gate and there are users waiting on the opposite side of the automatic ticket gate 3 (S27: Yes), the control unit 11 shifts the process to step S28. On the other hand, if the automatic ticket gate 3 to which the user has been assigned is not a dual-use automatic ticket gate, or if there are no users waiting on the opposite side of the automatic ticket gate 3 (S27: No), the control unit 11 shifts the process to step S21 without changing the transaction date and time.

[0135] <Step S28> In step S28, the control unit 11 changes the transaction date and time (transaction start date and time and transaction end date and time) of the user (waiting person) waiting on the opposite side of the automatic ticket gate 3.

[0136] <Step S221> If the transaction data is not transaction data for the automatic ticket gate 3 to be reduced (S22: No), in step S221, the control unit 11 determines whether there is a user (waiting person) waiting in line ahead. If there is a user waiting in line ahead (S221: Yes), the control unit 11 shifts the process to step S222. On the other hand, if there is no user waiting in line ahead (S221: No), the control unit 11 shifts the process to step S21.

[0137] <Step S222> In step S222, the control unit 11 changes the transaction date and time (transaction start date and time and transaction end date and time) of the user corresponding to the transaction data. Specifically, the control unit 11 changes the transaction start date and time of the user corresponding to the transaction data to the transaction end date and time of the user in front of the user, and changes the transaction end date and time accordingly.

[0138] <Step S29> In step S29, the control unit 11 determines whether the above-mentioned determination process has been completed for all transaction data. When the control unit 11 has completed the above-mentioned determination process for all transaction data (S29: Yes), the control unit 11 terminates the automatic ticket gate simulation process. The control unit 11 repeatedly executes the processes of steps S21 to S28 until the above-mentioned determination process has been completed for all transaction data (S29: No).

[0139] In this way, the control unit 11 updates the transaction date and time of each transaction data when the number of automatic ticket gates 3 is reduced, and simulates the degree of congestion after the update. That is, the control unit 11 (allocation processing unit 116) allocates target users to automatic ticket gates 3 selected based on the functions of each automatic ticket gate 3, its positional relationship with the reduced automatic ticket gate 3, and the number of people queuing at each automatic ticket gate 3.

[0140] In the above example, a simulation was shown for the case where the number of automatic ticket gates 3 was reduced, but if an additional number of automatic ticket gates 3 were added, the transaction date and time of each transaction data could be updated to simulate the degree of congestion after the update.

[0141] In the simulation of adding an automatic ticket gate 3, the allocation processing unit 116 does not use the original gate as is, but allocates each user to a nearby gate. This is because, when an automatic ticket gate 3 is removed, it is necessary to distribute the users who used the removed gate to another automatic ticket gate 3, but when an automatic ticket gate 3 is added, if the original gate is used as is, there will be no one to use the added gate.

[0142] For example, as shown in Figure 25, the allocation processing unit 116 checks which machine is available for user M (using an IC card), who was using machine No. 2 in the original transaction data, and allocates it to the newly installed machine No. 4 (combined IC / magnetic, dual entry / exit) which can be used by user M.

[0143] As explained above, the management server 1 calculates the congestion degree at the station equipment based on the arrival time estimated based on the transaction start date and time and the transaction end date and time included in the usage history (transaction data) of the station equipment, and updates the congestion degree by simulating an increase or decrease in the number of station equipment. This makes it possible to accurately predict congestion at the station equipment.

[0144] In the simulation process, for example, in a simulation in which a first station service device is eliminated from among a plurality of station service devices, the management server 1 assigns user a who used the first station service device to a second station service device from among the plurality of station service devices. The management server 1 also assigns user a to the second station service device selected based on the functions of the station service device, its positional relationship with the first station service device, and the number of people in line for the station service device.

[0145] The simulation process can also be applied in a similar manner when changing the model of station service equipment. For example, when changing a multifunction ticket vending machine to a charge-type ticket vending machine, users who have purchased tickets from the multifunction ticket vending machine will not be able to use the changed charge-type ticket vending machine. In this case, as in the simulation of reducing multifunction ticket vending machines, the management server 1 assigns users to a ticket vending machine (multifunction ticket vending machine) selected based on the functions of each ticket vending machine, the relative positions of other ticket vending machines in relation to the multifunction ticket vending machine to be changed, and the number of people in line at each ticket vending machine.

[0146] In addition, if the transaction end time of user b's transaction data using the second station service equipment assigned to user a is later than the transaction start time of user a's transaction data, the management server 1 changes the transaction start time of user a at the second station service equipment based on the transaction end time of user b.

[0147] Furthermore, the management server 1 changes the transaction end time of the user A in the second station service equipment according to the change in the transaction start time of the user A. Then, the management server 1 updates the congestion degree of the second station service equipment based on the changed transaction start time.

[0148] This makes it possible to simulate the degree of congestion of station equipment when the number of station equipment is increased or decreased, thereby determining the optimal number of station equipment and the type of function.

[0149] In this embodiment, the management server 1 alone corresponds to the congestion prediction system according to the present invention. However, the congestion prediction system according to the present invention may also include one or more of the components of the management server 1, the station server 4, and station service equipment (ticket vending machine 2, automatic ticket gate 3). For example, if the components of the management server 1 and the station server 4 cooperate to share and execute the congestion prediction process, a system including the multiple components that execute the process may constitute the congestion prediction system according to the present invention. For example, the station server 4 alone may constitute the congestion prediction system according to the present invention. In this case, the station server 4 may be configured to include each of the processing units 111 to 116 shown in FIG. 4. Alternatively, the management server 1, the ticket vending machine 2, and the automatic ticket gate 3 may constitute the congestion prediction system according to the present invention.

[0150] [Notes on the Invention] The following will provide an outline 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.

[0151] <Appendix 1> an acquisition processing unit that acquires first usage history data of a first user who has used the target device and second usage history data of a second user who has used the target device after the first user; a calculation processing unit that calculates a congestion degree of the target device based on a time difference between a usage end time of the target device included in the first usage history data and a usage start time of the target device included in the second usage history data; A congestion prediction system equipped with

[0152] <Appendix 2> an estimation processing unit that estimates an arrival time of the second user at a usage location where the second user uses the target device based on the time difference; the calculation processing unit calculates the congestion degree based on the estimated arrival time estimated by the estimation processing unit. 1. A congestion prediction system as described in Appendix 1.

[0153] <Appendix 3> The estimation processing unit If the time difference is equal to or greater than a threshold, the use start time of the second user is estimated as the estimated arrival time; If the time difference is less than the threshold, a time before the use end time of the first user is estimated as the estimated arrival time. Attachment 2: A congestion prediction system.

[0154] <Appendix 4> the estimation processing unit estimates the estimated arrival time corresponding to each of the users in the queue based on the number of users in the queue represented by the number of consecutive usage history data in which the time difference is less than the threshold value and the period from the usage start time of the first user in the queue to the usage end time of the last user in the queue; Attachment 3: A congestion prediction system.

[0155] <Appendix 5> the estimation processing unit estimates the estimated arrival time for each of the plurality of pieces of usage history data; the calculation processing unit calculates the number of the usage history data in which the time difference from the usage end time of the first user to the estimated arrival time is less than the threshold as the number of users waiting to use the target device; 5. The congestion prediction system according to claim 3 or 4.

[0156] <Appendix 6> When the time difference is less than the threshold value, the calculation processing unit calculates the time difference between the estimated arrival time of the second user and the usage start time as the usage waiting time of the usage target device. 6. A congestion prediction system according to any one of Supplementary notes 3 to 5.

[0157] <Appendix 7> a presentation processing unit that presents the congestion degree corresponding to each of the plurality of usage history data for a predetermined period; 7. A congestion prediction system according to any one of appendices 1 to 6.

[0158] <Appendix 8> Further, an allocation processing unit is provided that allocates a third user who has used the first target device to a second target device among the plurality of target devices in a simulation of reducing a first target device among the plurality of target devices. A congestion prediction system according to any one of Supplementary notes 1 to 7.

[0159] <Appendix 9> the allocation processing unit allocates the third user to the second target device selected based on the functions of the target device, its position relative to the first target device, and the number of people in line for the target device; 10. The congestion prediction system according to claim 8.

[0160] <Appendix 10> When the usage end time of the usage history data of a fourth user who has used the second target device to which the third user is assigned is later than the usage start time of the usage history data of the third user, the allocation processing unit changes the usage start time of the third user on the second target device based on the usage end time of the fourth user. 10. The congestion prediction system according to claim 9.

[0161] <Appendix 11> Furthermore, the allocation processing unit changes the use end time of the third user on the second target device according to the change time of the use start time of the third user. 11. The congestion prediction system of claim 10.

[0162] <Appendix 12> the calculation processing unit updates the congestion degree of the second target device of use based on the changed use start time. 12. The congestion prediction system according to claim 10 or 11.

[0163] <Appendix 13> The target device is an automatic ticket gate or a ticket vending machine at a railway station. 13. A congestion prediction system according to any one of appendices 1 to 12. [Explanation of symbols]

[0164] 10: Congestion prediction system 1: Management server 2: Ticket machine 3: Automatic ticket gate 4: Station server 11: Control section 12: Storage section 13: Operation display section 14: Communications Department 111: Registration processing unit 112: Acquisition processing unit 113: Estimation processing unit 114: Calculation processing unit 115: Presentation processing unit 116: Allocation processing unit D1: Transaction data information D2: Estimated date and time information D3: Congestion forecast information

Claims

1. A congestion prediction system that predicts congestion of a target device based on usage history data of a user who uses the target device, an acquisition processing unit that acquires first usage history data of a first user who used the target device and second usage history data of a second user who used the target device after the first user; a calculation processing unit that calculates a congestion degree of the target device based on a time difference between a usage end time of the target device included in the first usage history data and a usage start time of the target device included in the second usage history data; A congestion prediction system equipped with

2. an estimation processing unit that estimates an arrival time of the second user at a usage location where the second user uses the target device based on the time difference; the calculation processing unit calculates the congestion degree based on the estimated arrival time estimated by the estimation processing unit. The congestion prediction system according to claim 1 .

3. The estimation processing unit If the time difference is equal to or greater than a threshold, the use start time of the second user is estimated as the estimated arrival time; If the time difference is less than the threshold, a time before the end time of use of the first user is estimated as the estimated arrival time. The congestion prediction system according to claim 2 .

4. the estimation processing unit estimates the estimated arrival time corresponding to each of the users in the queue based on the number of users in the queue represented by the number of consecutive usage history data in which the time difference is less than the threshold value and the period from the usage start time of the first user in the queue to the usage end time of the last user in the queue; The congestion prediction system according to claim 3 .

5. the estimation processing unit estimates the estimated arrival time for each of the plurality of pieces of usage history data; the calculation processing unit calculates the number of the usage history data in which the time difference from the usage end time of the first user to the estimated arrival time is less than the threshold value as the number of users waiting to use the target device; The congestion prediction system according to claim 3 .

6. When the time difference is less than the threshold value, the calculation processing unit calculates the time difference between the estimated arrival time of the second user and the usage start time as the usage waiting time of the usage target device. The congestion prediction system according to claim 3 .

7. a presentation processing unit that presents the congestion degree corresponding to each of the plurality of usage history data for a predetermined period; The congestion prediction system according to claim 1 .

8. In a simulation of deleting a first target device from among the plurality of target devices for use, or in a simulation of changing the first target device to a target device for use having a function different from that of the first target device for use, an allocation processing unit is further provided which allocates a third user who has used the first target device to a second target device from among the plurality of target devices for use. The congestion prediction system according to claim 1 .

9. the allocation processing unit allocates the third user to the second target device selected based on the functions of the target device, its position relative to the first target device, and the number of people in line for the target device; The congestion prediction system according to claim 8 .

10. When the usage end time of the usage history data of a fourth user who has used the second target device to which the third user is assigned is later than the usage start time of the usage history data of the third user, the allocation processing unit changes the usage start time of the third user on the second target device based on the usage end time of the fourth user. The congestion prediction system according to claim 9 .

11. Furthermore, the allocation processing unit changes the use end time of the third user on the second target device according to the change time of the use start time of the third user. The congestion prediction system according to claim 10.

12. the calculation processing unit updates the congestion degree of the second target device of use based on the changed use start time. The congestion prediction system according to claim 10.

13. The target device is an automatic ticket gate or a ticket vending machine at a railway station. The congestion prediction system according to any one of claims 1 to 12.

14. A congestion prediction method for predicting congestion of a target device based on usage history data of a user who has used the target device, comprising: Acquiring first usage history data of a first user who used the target device and second usage history data of a second user who used the target device after the first user; Calculating a congestion level of the target device based on a time difference between a usage end time of the target device included in the first usage history data and a usage start time of the target device included in the second usage history data; A congestion prediction method executed by one or more processors.

15. A congestion prediction program for predicting congestion of a target device based on usage history data of a user who has used the target device, Acquiring first usage history data of a first user who used the target device and second usage history data of a second user who used the target device after the first user; Calculating a congestion level of the target device based on a time difference between a usage end time of the target device included in the first usage history data and a usage start time of the target device included in the second usage history data; A congestion prediction program for executing the above on one or more processors.

Images