JP2020123122A - Teacher data generation device, gate setting learning system, teacher data generation method, and teacher data generation program - Google Patents

Abstract

To provide a teacher data generation device, a gate setting learning system, a teacher data generation method, and a teacher data generation program that can efficiently generate teacher data used for machine learning for setting a passage regulating state of each of a plurality of gate devices.SOLUTION: A teacher data generation device 41 comprises: a passage state acquisition unit 411 acquiring a passage regulation state of each of a plurality of automatic ticket gates 1; a congestion degree detection unit 412 detecting congestion degree of users around the plurality of automatic ticket gates 1 in the passage regulation state; a congestion determination unit 413 determining whether the congestion degree exceeds a threshold value; a congestion time calculation unit 414 calculating congestion total time indicating a sum of time when the congestion degree exceeds the threshold value during a predetermined period; and a teacher data generation unit 415 generating teacher data in which the passage regulation state and the congestion total time are associated with each other.SELECTED DRAWING: Figure 6

Description

The present invention relates to a teacher data generating device, a gate setting learning system, a teacher data generating method, and a teacher data generating device for generating teacher data used for machine learning for making passage control states of a plurality of gate devices proper. Regarding the program.

2. Description of the Related Art Conventionally, there is known an automatic ticket gate that reads a pass ticket such as an admission ticket or a ticket, and acquires information included in the pass ticket. Such an automatic ticket gate is installed at a traffic security gate in a facility or a ticket gate in a railway. The automatic ticket gate is equipped with a door (gate) for opening and closing a passage. The automatic ticket gate operates the door to the open position to open the passage so that the passage can be passed when the pass ticket is legally processed, and closes the door when the pass ticket is not read or a reading failure occurs. Keep in position and prohibit passage.

Generally, a plurality of passages are defined in a ticket gate of a railway, and a plurality of automatic ticket gates are provided at the ticket gates corresponding to the passages. Conventionally, the station staff who manages each automatic ticket gate predicts the congestion situation near the ticket gate and changes the passage setting of each automatic ticket gate in advance in order to allow the visitors and the participants to pass through smoothly, or , The passage settings of each automatic ticket gate are changed according to the current congestion situation near the ticket gate. Specifically, the station staff set the passage settings of each automatic ticket gate to be exclusive for entrance, exclusive for entrance, and combined for entrance and exit.

On the other hand, there is known a device that determines a passage setting by a calculation process by a computer, not by human judgment. For example, there is disclosed a lane operation estimation device that determines the number of operating lanes at a plurality of gates of a tollgate on a toll road based on past operation records and current environmental information (see Patent Document 1). Further, there is disclosed a gate control device that determines a state to be set for each of a plurality of gates based on a position and a traveling direction of a passerby estimated from a captured image around the gate (see Patent Document 2). ..

JP 2001-143109 A JP, 2005-70850, A

However, the conventional method of determining the passage setting by the arithmetic processing does not always output an appropriate setting value according to the situation around the gate (gate, etc.), and outputs an extremely inappropriate setting value. It may be done. In this case, if the passage setting of each gate is automatically changed based on an inappropriate setting value, a passerby or a vehicle driver passing through the gate will be annoyed. In addition, the station staff who notices the deterioration of the congestion situation after the change rushes to change the passage setting, which increases the work load on the station staff.

Further, in recent years, it may be considered to determine the passage setting of each of the plurality of gates by machine learning. However, in the machine learning, a large amount of teacher data is required to improve the determination accuracy, but it is difficult to generate a large amount of teacher data corresponding to a plurality of gates capable of setting a plurality of patterns of paths.

An object of the present invention is to provide a teacher data generation device, a gate setting learning system, and teacher data generation capable of efficiently generating teacher data used for machine learning for setting passage control states of a plurality of gate devices. A method and a teacher data generation program are provided.

A teacher data generation device according to one aspect of the present invention is a teacher data generation device that generates teacher data used for machine learning, and a passage state acquisition unit that obtains a passage regulation state of each of a plurality of gate devices, A congestion degree detection unit that detects a congestion degree of users around the plurality of gate devices in the passage regulation state acquired by the passage state acquisition unit, and the congestion degree detected by the congestion degree detection unit is a threshold value. A congestion determination unit that determines whether or not the time exceeds, a congestion time calculation unit that calculates a total congestion time that indicates the total time when the congestion degree exceeds the threshold value within a predetermined period, and the passage state acquisition unit acquires the congestion time. And a teacher data generation unit that generates the teacher data that associates the passage restriction state with the congestion total time calculated by the congestion time calculation unit.

According to the above configuration, the teacher data generation device does not calculate the total congestion time for all the patterns of the passage restriction state configured by a plurality of gate devices, but the congestion total time for the predetermined number of patterns of the passage restriction states. To calculate. Further, the total congestion time, which is the total time when the congestion degree exceeds the threshold value, is generated as teacher data, and the teacher data is not generated for the time when the congestion degree is equal to or less than the threshold value. Therefore, it is possible to generate specific teacher data that appropriately reflects the congestion situation. Therefore, it is possible to efficiently generate teacher data used for machine learning for setting the passage restriction state of each of the plurality of gate devices.

In the teacher data generation device, the congestion degree detection unit detects the number or density of users around the plurality of gate devices, and the congestion determination unit, the number of people or the density detected by the congestion degree detection unit It is determined whether the density exceeds the threshold value. As a result, it is possible to appropriately determine the congestion situation around the plurality of gate devices.

In the teacher data generation device, the congestion time calculation unit is required until the congestion degree becomes equal to or less than the threshold value when the congestion determination unit determines that the congestion degree exceeds the threshold value in the predetermined period. The total time is calculated as the total congestion time.

In the teacher data generation device, the predetermined time period includes a first predetermined time period and a second predetermined time period, and the passage state acquisition unit includes a first passage control state corresponding to the first predetermined time period and the second predetermined period. The second passage restriction state corresponding to the period is acquired, and the congestion degree detection unit detects the first congestion degree corresponding to the first predetermined period and the second congestion degree corresponding to the second predetermined period. However, the congestion determination unit determines whether the first congestion degree detected by the congestion degree detection unit exceeds a first threshold value, and the second congestion degree detected by the congestion degree detection unit is The congestion time calculating unit determines whether or not the second congestion threshold is exceeded, and the first congestion total time indicating a total time when the first congestion degree exceeds the first threshold, and the second congestion degree are the same. A second congestion total time indicating a total time exceeding a second threshold is calculated, and the teacher data generation unit uses the first passage restriction state acquired by the passage state acquisition unit and the congestion time calculation unit. First teacher data associated with the calculated first congestion total time, the second passage restriction state acquired by the passage state acquisition unit, and the second congestion total calculated by the congestion time calculation unit Second teacher data associated with time is generated.

Further, the first predetermined period may be a period including morning in the day, and the second predetermined period may be a period including afternoon in the day. As a result, it is possible to generate the teacher data according to the congestion situation in the morning and the teacher data according to the congestion situation in the afternoon. The first threshold and the second threshold may be set to different values. For example, the first threshold and the second threshold are set to different values depending on the congestion situation.

In the teacher data generation device, the passage state acquisition unit acquires a predetermined plurality of patterns of the passage regulation state, and the congestion degree detection unit calculates the congestion degree corresponding to the passage regulation states of each of the plurality of patterns. The congestion time calculation unit calculates the total congestion time corresponding to the passage restriction state of each of the plurality of patterns, and the teacher data generation unit detects the congestion control time of each of the plurality of patterns. Generate teacher data. As a result, the teacher data can be generated with a plurality of predetermined patterns, and it is not necessary to prepare a large number of patterns.

In the teacher data generation device, the passage restriction state is a first state in which passage in only one direction is permitted for a passage in the gate device, and a passage state in which passage in only another direction is permitted for a passage in the gate device. It may be in one of two states and a third state in which passage in both directions is permitted for the passage of the gate device. In the teacher data generation device, the gate device is an automatic ticket gate installed at a ticket gate of a railway station and set to any one of the first state, the second state, and the third state. It may be.

A gate setting learning system according to another aspect of the present invention is a learning device that generates a learned model by performing machine learning using the teacher data generation device and the teacher data generated by the teacher data generation device. And Further, in the gate setting learning system, the learning device generates the learned model that estimates the total congestion time corresponding to the arbitrary passage restriction state. Thereby, it is possible to generate a learned model capable of estimating the total congestion time corresponding to an arbitrary passage regulation state by using the teacher data corresponding to the predetermined number (predetermined pattern) of the passage regulation state. ..

In the gate setting learning system, the passage regulation state corresponding to the shortest congestion total time of the plurality of congestion total times estimated by using the learned model generated by the learning device is set to the optimum passage regulation state. It further comprises a passage setting device for determining. As a result, the plurality of gate devices can be set to the optimum passage restriction.

In the gate setting learning system, the teacher data generation device further generates optimum teacher data corresponding to the optimum passage regulation state determined by the passage setting device, and the learning device uses the teacher data generation device. Machine learning is performed using the generated teacher data and the optimum teacher data to generate a modified learned model in which the learned model is modified. In the gate setting learning system, the passage setting device corresponds to the shortest congestion total time of the plurality of congestion total times estimated by using the modified learned model generated by the learning device. The passage regulation state is determined to be the new optimal passage regulation state, whereby the passage regulation of each of the plurality of gate devices can be set to the optimum state according to the congestion situation around the ticket gate.

A teacher data generation method according to another aspect of the present invention is a teacher data generation method for generating teacher data used for machine learning, and a passage state acquisition step of obtaining a passage restriction state of each of a plurality of gate devices, A congestion degree detection step of detecting a congestion degree of a user around the plurality of gate devices in the passage regulation state acquired by the passage state acquisition step, and the congestion degree detected by the congestion degree detection step is a threshold value. Congestion determination step to determine whether or not, the congestion time calculation step of calculating a total congestion time indicating the total time of the congestion degree exceeds the threshold value within a predetermined period, and the passage state acquisition step A teacher data generation method for executing, by one or a plurality of processors, the teacher data generation step of generating the teacher data in which the passage restriction state and the congestion total time calculated in the congestion time calculation step are associated with each other. is there.

A teacher data generation program according to another aspect of the present invention is a teacher data generation program that generates teacher data used for machine learning, and includes a passage state acquisition step of obtaining a passage restriction state of each of a plurality of gate devices, A congestion degree detection step of detecting a congestion degree of a user around the plurality of gate devices in the passage regulation state acquired by the passage state acquisition step, and the congestion degree detected by the congestion degree detection step is a threshold value. Congestion determination step to determine whether or not, the congestion time calculation step of calculating a total congestion time indicating the total time of the congestion degree exceeds the threshold value within a predetermined period, and the passage state acquisition step Teacher data generation for causing one or a plurality of processors to execute the teacher data generation step of generating the teacher data in which the passage restriction state and the congestion total time calculated in the congestion time calculation step are associated with each other. It is a program.

According to the present invention, it is possible to efficiently generate teacher data used for machine learning for setting the passage restriction state of each of a plurality of gate devices.

FIG. 1 is a diagram showing a network configuration of a gate system according to an embodiment of the present invention. FIG. 2 is a sketch showing a plurality of automatic ticket gates to which the gate system according to the embodiment of the present invention is applied and a situation around the ticket gate. FIG. 3 is a perspective view showing an automatic ticket gate to which the gate system according to the embodiment of the present invention is applied. FIG. 4 is a block diagram showing a configuration of an automatic ticket gate to which the gate system according to the embodiment of the present invention is applied. FIG. 5 is a block diagram showing a configuration of a station server to which the gate system according to the embodiment of the present invention is applied. FIG. 6 is a block diagram showing the configurations of the teacher data generation device, the learning device, and the passage setting device included in the station server. FIG. 7 is a graph showing an example of a change in the number of users, which represents the congestion situation around the ticket gates during a day at a station. FIG. 8 is a diagram showing an example of teacher data generated in the teacher data generating device according to the embodiment of the present invention. FIG. 9 is a block diagram showing a configuration of a station staff terminal device to which the gate system according to the embodiment of the present invention is applied. FIG. 10 is a flowchart showing an example of the teacher data generation process executed by the teacher data generation device according to the embodiment of the present invention. FIG. 11 is a flowchart showing an example of a passage setting process executed in the teacher data generation device, the learning device, and the passage setting device according to the embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings as appropriate. The embodiments described below are merely examples embodying the present invention and do not limit the technical scope of the present invention.

[Gate system 100]
FIG. 1 is a network diagram showing a gate system 100 (an example of a gate setting learning system of the present invention) according to an embodiment of the present invention. The gate system 100 is applied to a plurality of automatic ticket gates 1 (an example of the gate device of the present invention) provided at a ticket gate 7 of a railway station 8 operated and managed by a railway company, and is shown in FIG. As shown, an automatic ticket gate 1, a station employee terminal device 2, a station server 4 (each example of a teacher data generating device, a learning device, and a passage setting device of the present invention), a center device 5, and the like are configured. There is. Although FIG. 1 illustrates a configuration in which a plurality of automatic ticket gates 1 are installed at two ticket gates 7 provided at a railway station 8, the gate system 100 has at least two or more ticket gates at one ticket gate. It is applicable to a configuration in which a plurality of automatic ticket gates 1 are installed in the passage.

The gate system 100 is not limited to being applied to the plurality of automatic ticket gates 1 at the station 8. For example, a plurality of automatic entrances provided at a traffic security gate such as an airport boarding gate or facility entrance. The present invention is also applicable to a device (an example of the gate device of the present invention) and a plurality of automatic gate devices (an example of the gate device of the present invention) provided at a plurality of ETC gates defined at a toll gate on a toll road.

A plurality of station service devices belong to the station 8. Specifically, a plurality of automatic ticket gates 1, station staff terminal devices 2 used by station staff, settlement terminal devices 3 (see FIG. 2), station server 4, ticket sales. Station service equipment such as the machine 6 (see FIG. 2) is installed around the ticket gate 7 of the station 8. These station service devices are communicably connected to each other via a network N1 such as a LAN. Further, the station server 4 of the station 8 is communicatively connected to a center device 5 which is a server device managed by a railway company (railroad company) via a network N2 such as a private line or a public line.

The automatic ticket gate 1 is installed at the ticket gate 7 of the station 8. A plurality of automatic ticket gates 1 are installed in each of the ticket gates 7. FIG. 2 is a sketch diagram (layout diagram) showing a situation around the ticket gate 7A. As shown in FIG. 2, a plurality of ticket gate passages 9 are defined in the ticket gate 7A, and specifically, six ticket gate passages 9 are partitioned.

As shown in FIG. 3, the automatic ticket gate 1 has an automatic ticket gate 1A for entrance (hereinafter referred to as an entrance ticket gate 1A) and an automatic ticket gate 1B for entrance (hereinafter referred to as an entrance ticket gate 1B). ) And is a configuration that is opposed to each other. The entrance ticket gate 1A and the exit ticket gate 1B are arranged to face each other. The ticket gate passage 9 is a space formed between the entrance ticket gate 1A and the exit ticket gate 1B, and connects the inside and outside of the ticket gate 7A. In addition, one of the entrance ticket gates 1A is a ticket processing (an entrance ticket processing) for a user (an attendee) who enters from the outside of the ticket gate 7A to the inside along the traveling direction (direction of arrow D10) at the time of entrance. ) Is responsible for doing. On the other hand, the ticket gate 1B for entrance performs a ticket processing (entrance ticket processing) for a user (entrant) who enters from the inside of the ticket gate 7A to the outside along the traveling direction (direction of arrow D11) at the time of exit. Play a role. In the following, unless otherwise specified, the automatic ticket gate 1 will be described as including the entrance ticket gate 1A and the exit ticket gate 1B, which have both entrance and exit ticket functions.

In the present embodiment, the gate system 100 can set the passage for each of the plurality of automatic ticket gates 1 so as to have a predetermined passage regulation. As passage restrictions that the automatic ticket gate 1 can take, three passage restrictions are set. That is, the gate system 100 can set the passage of the automatic ticket gate 1 so as to be a specific passage regulation selected from the three passage regulations.

There are three types of passage restrictions that the automatic ticket gate 1 can take: "only for entry", "only for entry", and "combined entry and exit" described below. Specifically, the entrance-only is a passage regulation that allows only a user (entrance) who attempts to enter by stopping the ticket gate function of the exit ticket gate 1B of the automatic ticket gate 1. .. The exclusive use of the entrance is a passage restriction that allows only the user (exiter) who is going to enter by stopping the ticket inspection function of the entrance ticket inspection machine 1A of the automatic ticket inspection machine 1. The combined use of entrance and exit is a passage regulation that enables both the entrance and exit ticket gates 1A and 1B to enable both ticket gates to pass through. The passage setting of the plurality of automatic ticket gates 1 is set to one of the above-mentioned three types of traffic regulation.

In the automatic ticket gate 1 set for exclusive use of the entrance, when the entrance ticket processing is performed, passage through the ticket passage 9 only in the advancing direction D10 is permitted, and passage in the opposite direction is prohibited. Further, in the automatic ticket gate 1 set for exclusive use for the participation, when the exit ticket processing is performed, the ticket gate passage 9 is allowed to pass only in the traveling direction D11 at the time of entry, and the opposite direction is prohibited. It Further, in the automatic ticket gate 1 set for both entrance and exit, it is possible to allow the ticket gate passage 9 to pass from both the advancing direction D10 when entering and the advancing direction D11 when entering. Permit passage of users who have undergone the ticket gate processing.

For the passage setting of each automatic ticket gate 1, the station staff themselves set the passage setting value corresponding to the passage regulation desired by the station staff, and the setting value information including the passage setting value is set through the station staff terminal device 2 to each automatic ticket gate. It is possible to change by sending to 1. Here, the passage setting value is a setting value indicating the contents (passage restriction type) of the passage setting of each of the plurality of automatic ticket gates 1. Further, the set value information is information for performing passage setting for each of the automatic ticket gates 1.

The configurations of the automatic ticket gate 1, the station server 4, the station staff terminal device 2, and the center device 5 to which the gate system 100 is applied will be described below.

[Automatic ticket gate 1]
FIG. 3 is a perspective view showing the appearance of the automatic ticket gate 1, and FIG. 4 is a block diagram showing the configuration of the automatic ticket gate 1.

The automatic ticket gate 1 is installed at the ticket gate 7 of the station 8 and performs a ticket processing for a user who passes through the ticket gate 7. As shown in FIG. 3, the automatic ticket gate 1 includes an entrance ticket gate 1A and an exit ticket gate 1B which are installed so as to face each other. In this embodiment, the automatic ticket gate 1 acquires ticket information included in the ticket from tickets such as IC cards and tickets (magnetic tickets) owned by a user who is going through the ticket passage 9. , Performs the ticket gate processing based on the ticket information. Specifically, the automatic ticket gate 1 determines whether or not the acquired ticket information is valid. If the ticket information is determined to be valid, the ticket is permitted, and if it is determined to be invalid, the ticket information is acquired. If it does not exist, users are prohibited from passing. When passage is permitted, the automatic ticket gate 1 opens the flap door 15 and opens the ticket passage 9 so that the user can pass the ticket. On the other hand, when the passage is prohibited, the automatic ticket gate 1 closes the flap door 15 and the ticket gate passage 9 so that the user cannot pass.

An information code such as a barcode or a QR code (registered trademark) in which the ticket information is recorded may be used as the ticket. In this case, a paper medium on which the information code is printed or a display screen of a terminal device such as a smartphone on which the information code is displayed is used as the ticket.

As shown in FIGS. 3 and 4, the automatic ticket gate 1 includes a control unit 11, a storage unit 12, an upper display unit 13, a communication unit 14, a flap door 15 (15A, 15B), and an IC card reading unit. A section 16, a side display section 17, an image pickup section 18, and a motion sensor 19 are provided, and these are provided in the housing 10 (see FIG. 3) of the automatic ticket gate 1.

The storage unit 12 is a non-volatile storage medium including an HDD or SSD that stores various types of information. The storage unit 12 stores a control program for causing the control unit 11 to execute various arithmetic processes executed by the automatic ticket gate 1, various data used for the various arithmetic processes, and the like. The storage unit 12 also stores various kinds of information such as aisle setting values related to aisle regulation transmitted from the station server 4 and the center device 5 to the automatic ticket gate 1.

The upper display unit 13 displays a message to the user who passes through the ticket gate passage 9 according to an instruction from the control unit 11. The upper display unit 13 has, for example, a liquid crystal panel. As shown in FIG. 3, the upper display unit 13 is provided on the upper surface of the housing 10 of the automatic ticket gate 1. Specifically, the upper display unit 13 is arranged on the upper surface of the housing 10 in the front side of the ticket gate passage 9 (see FIG. 3) in the traveling direction of the user (direction of the arrow D10 or the arrow D11). When the passage of the user is permitted, the upper display unit 13 displays a message indicating that the passage is possible. If the user is not allowed to pass, a message indicating that the passage is not possible (prohibited) is displayed on the upper display section 13. In addition, when the automatic ticket gate 1 is used for participation, for example, a message indicating that the fare is insufficient, or prompting the user to make a payment at the payment terminal device 3 (see FIG. 2) are displayed on the upper display unit 13. A message may be displayed.

The communication unit 14 connects the automatic ticket gate 1 to the network N1 by wire or wirelessly, and communicates with station equipment such as the station server 4 and the station staff terminal device 2 via the network N1 in accordance with a predetermined communication protocol. It is a communication interface for executing communication.

As shown in FIG. 3, the motion sensor 19 is provided in the housing 10, and more specifically, is provided on the side surface of the housing 10 on the side of the ticket gate 9 side. The human sensor 19 is a sensor that detects a user who has entered the ticket gate passage 9, and is, for example, an optical proximity sensor that detects a user without contact. In the present embodiment, the human presence sensors 19 are provided on the front side (entrance side) of the advancing direction D10 when entering the ticket gate passage 9 and on the front side (exit side) of the advancing direction. In other words, the human sensor 19 is provided on the side surface of the housing 10 at a position inside the ticket gate 7 and at a position outside the ticket gate 7. For example, when the user in the ticket gate passage 9 is detected by the human sensor 19 on the front side in the traveling direction before the ticket is read, it is determined that the user has entered the ticket gate passage 9 without performing the ticket gate processing. When the user is detected by the human sensor 19 on the front side in the traveling direction, it is determined that the user has passed through the ticket gate passage 9 without performing the ticket gate processing.

The flap doors 15 are provided in the ticket gate passage 9 of the automatic ticket gate 1 near the respective passage openings 9A and 9B on both sides. In other words, the flap doors 15 are installed in the ticket passage 9 at a passageway 9A inside the ticket gate 7 and at a passageway 9B outside the ticket gate 7. The former passage 9A is a front exit (passage) in the traveling direction D10 at the time of entry, and the latter passage 9B is a front exit (passage) in the traveling direction D11 at the time of entry.

The flap doors 15 are a pair of doors that can be opened and closed, and each door is rotatably provided on the side surface of each of the entrance ticket gate 1A and the exit ticket gate 1B. The flap door 15 opens and closes by receiving a driving force from a driving unit (not shown) such as a motor. The flap door 15 is displaced between the open position and the closed position by being driven and controlled by the flap door drive controller 116 of the controller 11. The flap door 15 is opened when the entrance ticket processing or exit ticket processing is performed and the passage of the user is permitted. As a result, the user can pass through the ticket gate 9 of the automatic ticket gate 1. On the other hand, when the passage of the user is not permitted, the flap door 15 is closed or the closed position is maintained.

In the present embodiment, in the automatic ticket gate 1 in which the passage regulation in the ticket gate passage 9 is set to be used for both entrance and exit, each of the flap doors 15A and 15B of the ticket gate passage 9 is arranged in the open position. In this state, when the user enters the ticket gate passage 9 before the entrance ticket processing or exit ticket processing is performed and the user is detected by the human sensor 19 (see FIG. 3 ), the flap door 15 is closed. Displaces from the open position to the closed position.

For example, when a user enters the ticket gate passage 9 from the entrance 9B while the entrance ticket is not being processed at the time of entry, the human presence sensor 19 of the entrance 9B detects the user, and the flap door on the entrance 9A side is detected. 15A is displaced from the open position to the closed position. Then, when the entrance ticket gate processing is performed thereafter, the flap door 15A is displaced from the closed position to the open position, and the ticket gate passage 9 is opened. On the other hand, when the entrance ticket processing is not performed, the flap door 15A is maintained in the closed position.

Further, when a user enters the ticket gate passage 9 from the entrance 9A while the exit ticket processing is not being performed at the time of exit, it is detected by the human sensor 19 of the entrance 9A, and the flap door on the entrance 9B side is detected. 15B is displaced from the open position to the closed position. Then, when the exit ticket processing is performed thereafter, the flap door 15B is displaced from the closed position to the open position, and the ticket passage 9 is opened. On the other hand, when the exit ticket processing is not performed, the flap door 15B is maintained in the closed position.

The state (passage regulation state) of the automatic ticket gate 1 in which the passage regulation is set so that the entrance and exit are combined so that the flap door 15 operates as described above corresponds to the third state of the present invention.

Further, in the automatic ticket gate 1 in which the passage regulation in the ticket gate passage 9 is set only for the entrance, the flap door 15A of the passage 9A of the ticket gate passage 9 is arranged at the closed position, and the flap door 15B of the passage 9B. Are located in the open position. In this state, the flap door 15A is opened and the ticket gate 9 is opened when the entrance ticket processing is performed and the passage of the user is permitted. When the entrance ticket gate process is not performed, the flap door 15A maintains the closed position and the ticket gate passage 9 maintains the closed state.

The state (passage regulation state) of the automatic ticket gate 1 in which the passage regulation is set only for the entrance so that the flap door 15 operates as described above corresponds to the first state of the present invention. In addition, when the passage regulation is set only for the entrance, the exit ticket gate function is stopped, so that the user is prohibited from exiting through the ticket entrance passage 9.

Further, in the automatic ticket gate 1 in which the passage restriction in the ticket gate passage 9 is set only for the participation, the flap door 15B of the passage 9B of the ticket gate passage 9 is arranged at the closed position, and the flap door 15A of the passage 9A. Are located in the open position. In this state, when the exit ticket processing is performed and the passage of the user is permitted, the flap door 15B is opened and the ticket passage 9 is opened. Further, when the exit ticket processing is not performed, the flap door 15B maintains the closed position, and the ticket passage 9 maintains the closed state.

As described above, the state (passage regulation state) of the automatic ticket gate 1 in which the passage regulation is set for the participation only so that the flap door 15 operates, corresponds to the second state of the present invention. If the passage restriction is set only for the entrance, the user is prohibited from entering from the ticket passage 9 because the entrance ticket function is stopped.

The flap door 15 is not limited to a physical door, and may be a door represented by a stereoscopic image using a hologram, for example. Further, instead of the flap door 15, a voice gate that permits or prohibits passage of the user by voice may be used.

The side display unit 17 displays a message to a user who intends to pass through the ticket gate passage 9 according to an instruction from the control unit 11. The side display unit 17 has, for example, a liquid crystal panel. As shown in FIG. 3, the side display unit 17 is provided on the front surface (side surface on the front side in the traveling direction) of the housing 10 of the automatic ticket gate 1. The side display portion 17 displays information indicating the contents of the passage setting set in the automatic ticket gate 1, that is, the information indicating the contents of the passage regulation. For example, in the case of a ticket gate dedicated to an IC card, the letters “IC” are displayed on the side display unit 17. Further, when the ticket gate processing is possible, a “◯” mark is displayed on the side display portion 17, and when the ticket gate processing is not possible, a “x” mark is displayed on the side display portion 17.

The IC card reading unit 16 is provided on the upper surface of the housing 10 on the front side in the traveling direction. The IC card reading unit 16 reads information (ticket information) recorded on an IC card type ticket (hereinafter referred to as “IC card”) in a non-contact manner. The IC card reading unit 16 is, for example, a reader/writer device that reads information in the IC card in a non-contact manner and performs writing in a non-contact manner by short-distance communication. The information read by the IC card reading unit 16 is transmitted to the control unit 11, and the control unit 11 executes the ticket gate processing based on the information. A user who uses an IC card holds the IC card over the IC card reading unit 16 and causes the IC card reading unit 16 to read the ticket information.

Even when a ticket is inserted into the ticket insertion slot (not shown), the control unit 11 executes the ticket gate processing based on the information read from the ticket.

The imaging unit 18 is provided on the upper surface of the housing 10. The image capturing unit 18 captures an image of a user who intends to use the automatic ticket gate 1, and specifically captures the face of the user. The imaging unit 18 is specifically a camera. The imaging unit 18 is installed so that the lens faces the upstream side in the traveling direction. The image capturing unit 18 captures an image of the face of the user when the ticket gate processing at the time of entry and exit is performed. The captured face image is used for face image matching processing. If it is determined by the face image matching process that the captured face image matches the registered face image of the user himself/herself registered in advance, the ticket gate processing at the time of entry and exit is performed, and the ticket gate passage 9 passes are allowed. The image capturing unit 18 may be omitted.

The control unit 11 controls the operation of each unit of the automatic ticket gate 1. The control unit 11 has control devices such as a CPU, a ROM, and a RAM. The ROM is a non-volatile storage medium in which control programs such as a BIOS and an OS for causing the CPU to execute various arithmetic processes are stored in advance. The RAM is a volatile or non-volatile storage medium that stores various kinds of information, and is used as a temporary storage memory (work area) for various arithmetic processes executed by the CPU. Then, the control unit 11 controls the automatic ticket gate 1 by causing the CPU to execute various control programs stored in advance in the ROM or the storage unit 12.

As shown in FIG. 4, the control unit 11 includes various processing units such as a reading processing unit 111, a recording processing unit 112, a passage setting unit 113, a passage control unit 114, a flap door drive control unit 116, and a notification processing unit 117. including.

The control unit 11 functions as the various processing units when the CPU executes various arithmetic processes according to the control program. In other words, the CPU executes the control program to cause the reading processing unit 111, the recording processing unit 112, the passage setting unit 113, the passage control unit 114, the flap door drive control unit 116, the notification processing unit 117, and the like. Functions as a processing unit. Further, some or all of the processing units included in the control unit 11 may be configured by electronic circuits. Further, the control program may be a program for causing a plurality of processors to function as the various processing units. The control unit 11 or the CPU is an example of a computer that executes the control program.

The reading processing unit 111 acquires the ticket information of the IC card read by the IC card reading unit 16 or the ticket information of the ticket read by the magnetic reading unit (not shown).

When the reading processing unit 111 acquires the ticket information from the ticket, the recording processing unit 112 updates the IC card reading unit 16 and the magnetic reading unit (not shown) with the information in the ticket. For example, the recording processing unit 112 writes the station name of the entrance station on the ticket. Further, the recording processing unit 112 reduces a predetermined amount (freight) from the amount charged in the IC card at the time of participation, and writes the reduced amount remaining in the information holding unit of the IC card. Further, the recording processing unit 112 writes the station name of the participating station in the IC card.

When the set value information is input to the automatic ticket gate 1, the aisle setting unit 113 sets the aisle in the automatic ticket gate 1 based on the aisle set value included in the input set value information (for passage restriction). Change the content). In the present embodiment, the aisle setting unit 113 changes the aisle setting of the automatic ticket gate 1 based on the aisle setting value so as to be the aisle restriction indicated by the aisle setting value, or maintains the current condition. As described above, there are three types of passage restrictions that the automatic ticket gate 1 can take: the entrance only, the exit exclusive, and the entrance/exit combined, and the passage setting unit 113 sets the passage setting of the automatic ticket gate 1. Modify or maintain any of the three passage restrictions.

The setting value information includes identification information of each of the plurality of automatic ticket gates 1 and the passage setting value indicating the setting content of each automatic ticket gate 1. When the aisle setting unit 113 receives the setting value information, the aisle setting unit 113 extracts the aisle setting value corresponding to the automatic ticket gate 1 of the aisle, and the aisle of the automatic ticket gate 1 is controlled so that the passage restriction is indicated by the aisle setting value. Change or maintain settings.

In the present embodiment, there are a case where the set value information is input to the automatic ticket gate 1 from the station staff terminal device 2 and a case where the set value information is input to the automatic ticket gate 1 from the station server 4. In either case, when the passage setting unit 113 receives the setting value information, the passage setting unit 113 changes or maintains the passage setting of the automatic ticket gate 1.

The setting value information input from the station staff terminal device 2 to each automatic ticket gate 1 is information indicating passage restrictions for each automatic ticket gate 1 determined by the judgment of the station staff. The setting value information input from the station server 4 to each automatic ticket gate 1 includes information determined by the passage setting device 43 of the station server 4 (an example of the passage setting device of the present invention). The passage setting device 43 uses the learned model generated by the learning device 42 to determine the optimum passage regulation state (optimum passage regulation state) and automatically sets the set value information corresponding to the optimum passage regulation state. Send to ticket gate 1. When the passage setting unit 113 receives the setting value information (optimum passage regulation state) including the passage setting value determined by the passage setting device 43, the automatic ticket gate based on the passage setting value included in the setting value information. Change or maintain the passage setting of 1. The passage setting device 43 will be described later.

The passage control unit 114 permits or prohibits a user from passing through the ticket gate passage 9 when a predetermined condition is satisfied. For example, when the passage control unit 114 determines that the ticket information read from the ticket such as an IC card or a ticket is valid, it allows the user to pass through the ticket gate 9. On the other hand, when the passage control unit 114 determines that the ticket information is invalid, the passage control unit 114 prohibits the user from passing through the ticket gate passage 9. When passage is permitted, the flap door drive control unit 116, which will be described later, displaces the flap door 15 to the open position, and the ticket gate 9 is opened. On the other hand, if the passage is not permitted, the flap door drive control unit 116 displaces the flap door 15 to the closed position, and the ticket gate 9 is closed.

The flap door drive control unit 116 controls the operation (opening/closing operation) of the flap door 15. For example, when passage of the user through the ticket gate passage 9 is permitted, the flap door drive control unit 116 controls a drive unit (not shown) such as a motor to displace the flap door 15 to the open position. This opens the ticket gate passage 9. On the other hand, when the passage of the user through the ticket gate passage 9 is prohibited, the flap door drive control unit 116 controls the drive unit to displace the flap door 15 to the closed position or maintain the closed state. As a result, the ticket gate passage 9 is closed.

The notification processing unit 117 outputs and displays predetermined information on the upper display unit 13 and the side display unit 17. In the present embodiment, the notification processing unit 117 displays a message indicating that the vehicle can pass through on the upper display unit 13. If the user is not allowed to pass, a message indicating that the user cannot pass (prohibit) is displayed on the upper display unit 13. Further, the notification processing unit 117 displays on the side display unit 17 a “◯” mark or a “x” mark for identifying whether or not the ticket inspection process is possible. The notification processing unit 117 may display on the side display unit 17 information indicating the contents of the passage setting set in the automatic ticket gate 1, that is, the information indicating the passage regulation.

[Station server 4]
FIG. 5 is a block diagram showing the configuration of the station server 4. The station server 4 is a server device installed in a server room or the like in the station 8 and is installed in each station 8. The station server 4 manages a plurality of station service devices such as the automatic ticket gate 1 connected to the network N1 which is an in-station network of the station 8. The station server 4 is not limited to a single computer, and may be a computer system in which a plurality of computers work together. Further, various processes executed by the station server 4 may be distributed and executed by a plurality of processors.

The station server 4 includes a teacher data generation device 41, a learning device 42, a passage setting device 43, a storage unit 44, and a communication unit 45. The teacher data generation device 41 is an example of the teacher data generation device of the present invention, the learning device 42 is an example of the learning device of the present invention, and the passage setting device 43 is an example of the passage setting device. At least one of the teacher data generation device 41, the learning device 42, and the passage setting device 43 may be an information processing device installed outside the station server 4. In this case, the information processing device is connected to the network N1.

The communication unit 45 connects the station server 4 to the networks N1 and N2 by wire or wirelessly, and communicates with station affairs equipment such as the automatic ticket gate 1 and the station staff terminal device 2 via the network N1 according to a predetermined communication protocol. It is a communication interface for executing data communication and performing data communication with the center device 5 via the network N2.

The storage unit 44 is a non-volatile storage medium including an HDD or SSD that stores various types of information. The storage unit 44 includes a control program for causing the control unit of the station server 4 to execute various arithmetic processes, a teacher data generation process (see FIG. 10) and an optimal passage determination process (see FIG. 10), which will be described later, executed by the station server 4. 11), a control program such as a teacher data generation program and data used for each process are stored. In addition, the storage unit 44 stores the number of installed automatic ticket gates 1, the identification number of each automatic ticket gate 1 and position information, and the like.

In addition, in the present embodiment, the configuration in which the storage unit 44 is provided in the station server 4 is illustrated, but for example, a part or all of various information in the storage unit 44 is stored in the station server 4 via the networks N1, N2, and the like. It may be stored in an external device such as another server device capable of data communication or a storage device connectable to a network. Also, a passage setting history storage unit 441 and a teacher data storage unit 442, which will be described later, may be provided in the external device.

In addition, the storage unit 44 is provided with storage areas such as a passage setting history storage unit 441 and a teacher data storage unit 442.

The aisle setting history storage unit 441 stores aisle setting history data. The passage setting history data includes the setting value information sent from the station staff terminal device 2 to the automatic ticket gate 1. The passage setting history data is used in a teacher data generation process and an optimum passage determination process, which will be described later. The aisle setting history data is log data in which, when the aisle settings of a plurality of automatic ticket gates 1 are changed according to the judgment of the station staff, the history of the changed contents is recorded. The passage setting history data includes the setting value information used for changing the setting, the date and time when the setting is changed, and the like.

The teacher data storage unit 442 stores teacher data (see FIG. 8) generated by the teacher data generation device 41. As shown in FIG. 8, the teacher data is information in which set value information that defines passage settings of each of the plurality of automatic ticket gates 1 and total congestion time described later are associated with each other. The teacher data may be configured by one set value information and the total congestion time, or may be configured by a plurality of set value information and the total congestion time. In the example shown in FIG. 8, teacher data corresponding to each morning from the first day to the tenth day (an example of the first teacher data of the present invention) and each of the first to tenth days. The teacher data corresponding to the afternoon (an example of the second teacher data of the present invention) is shown.

The control unit controls the operation of each unit of the station server 4. The control unit has control devices such as a CPU, a ROM, and a RAM. The ROM is a non-volatile storage medium in which control programs such as a BIOS and an OS for causing the CPU to execute various arithmetic processes are stored in advance. The RAM is a volatile or non-volatile storage medium that stores various kinds of information, and is used as a temporary storage memory (work area) for various arithmetic processes executed by the CPU. Then, the control unit controls the station server 4 by causing the CPU to execute various control programs stored in advance in the ROM or the storage unit 44.

[Teaching data generator 41]
As shown in FIG. 6, the teacher data generation device 41 includes various processing units such as a passage state acquisition unit 411, a congestion degree detection unit 412, a congestion determination unit 413, a congestion time calculation unit 414, and a teacher data generation unit 415. .. The control unit of the teacher data generation device 41 functions as the various processing units by the CPU executing various arithmetic processes according to the control program (including the teacher data generation program). Further, some or all of the processing units included in the control unit may be configured by electronic circuits. The control program may be a program for causing a plurality of processors to function as the various processing units.

The passage status acquisition unit 411 acquires the passage restriction status of each of the automatic ticket gates 1. Specifically, the aisle state acquisition unit 411 acquires the aisle regulation (only for entrance, only for exit, both for entrance and exit) states (passage restriction state) set for each of the plurality of automatic ticket gates 1. For example, the passage state acquisition unit 411 acquires the passage regulation state based on the passage setting history data stored in the passage setting history storage unit 441. In addition, the passage state acquisition unit 411 acquires a plurality of the set value information corresponding to each of the plurality of passage regulation states.

In addition, the passage state acquisition unit 411 acquires a plurality of the passage regulation states based on a predetermined condition.

Here, the passage regulation state changes according to an element (fluctuation element) that causes a change in the passage regulation content of each of the plurality of automatic ticket gates 1.

The variable elements include, for example, the number of installed automatic ticket gates 1 installed at the ticket gate 7A of the station 8 and the position of each automatic ticket gate 1. These variable elements can be obtained from the storage unit 44 in which these pieces of information are stored in advance.

Further, the variable elements are the concourse inside or outside the ticket gate 7A of the station 8 (see FIG. 2), near the ticket gate 7A, around the settlement terminal device 3 and the ticket vending machine 6 (see FIG. 2) A flow index that indicates the liquidity and congestion of users at various places such as stairs and escalators that connect the exit 7A to the station platform (see FIG. 2), elevators that connect the concourse floor and the home floor (see FIG. 2), The progress speed and direction of the user, the age group of the user, the presence or absence of group users, and the like. Further, when the user includes an unhealthy person, the variable factors include the speed of movement, the direction of travel, the position, the age group, whether or not a cane is used, whether or not a wheelchair is used, and the white cane Whether it is used or not. These variable elements can be obtained by analyzing a moving image or a still image captured by a plurality of cameras (see FIG. 2) provided inside and outside the station 8.

Further, the variable elements include temperature, humidity, atmospheric pressure, altitude, and weather at the location of the station 8. The variable elements include the current season, calendar (year, month, day), and time. Further, the variable elements include events held around the station 8, the presence/absence of large facilities around the station 8, the operation status (operation schedule) at the station 8, train delay, and the like. When the variable elements are the temperature, the humidity, the atmospheric pressure, and the altitude at the location of the station 8, the variable elements of the teacher data generation device 41 are the temperature sensor and the humidity sensor provided inside or outside the station 8. The sensor output values output from the atmospheric pressure sensor and the altitude sensor are received, and the real-time temperature, humidity, atmospheric pressure, and altitude indicated by the sensor output values are acquired. When the variable element is the weather around the station 8, the control unit downloads the weather information from the weather information database connected to the station server 4 via the internet, and the teacher data generation device 41 uses the control unit to download the weather information. Receive the weather information. Further, the teacher data generation device 41 can acquire information such as the operation status and the delay information from the center device 5.

Further, the variable element may include statistical information (user history information) indicating the number of users for each past month or each day of the week.

Such a variable element affects the traffic situation of the user who passes through the ticket gate 7A, and thus can be said to be information that causes a change in the passage restriction content of each of the automatic ticket gates 1. For example, if the space outside the ticket gate 7 or the degree of congestion in the concourse increases, it can be estimated that the number of visitors from the ticket gate 7 will rapidly increase. In this case, the automatic ticket gate with passage restrictions set for entrance only It is necessary to increase the number of machines 1. In addition, at the time of work and commuting to school, the number of attending users at stations near business districts and schools will rapidly increase, and the number of entering users at stations near residential areas will also increase rapidly. Therefore, in the former station, it becomes necessary to increase the number of automatic ticket gates 1 whose passage restrictions are set only for entry, and in the latter station, the number of automatic ticket gates 1 whose passage restrictions are set for entry only is increased. The need arises. In addition, if the operation status (operation schedule) is disturbed or delayed, it can be inferred that the number of participating users at station 8 will increase rapidly. In this case, the automatic ticket gate with passage restrictions set only for participation It is necessary to increase the number of machines 1.

Therefore, it is preferable that the passage state acquisition unit 411 obtains the passage regulation states of various patterns set in the past based on the variable element.

For example, since the commuting/commuting element of the variable elements has a large influence on the passage regulation content, the passage state acquisition unit 411 determines that the passage regulation state in the commuting/commuting time zone and the time zone excluding the time zone. And the passage regulation status of. In addition, generally, there are hours during the day when people are commuting to work or school in the morning and in the afternoon, but the contents of passage restrictions are different. For example, in the case of a station where the number of automatic ticket gates 1 set for entrance only in the morning is large, the number of automatic ticket gates 1 set for entrance only increases in the afternoon. Similarly, in the case of a station with a large number of automatic ticket gates 1 set for entrance only in the morning, the number of automatic ticket gates 1 set for entrance only increases in the afternoon. As described above, the passage regulation states of the plurality of automatic ticket gates 1 tend to be different during the day.

Therefore, the aisle state acquisition unit 411 is based on the aisle setting history data stored in the aisle setting history storage unit 441. In the morning (one example of a predetermined period of the present invention) in the morning (the first predetermined period of the present invention). A plurality of the passage regulation states (an example of the first passage regulation state of the present invention) set to a period (an example of a period), and a plurality of days set to the afternoon (an example of a second predetermined period of the present invention) in the day. The passage regulation state (an example of the second passage regulation state of the present invention) is acquired.

Here, as an example, the aisle state acquisition unit 411 has ten (10 patterns) first passage regulation states set in the morning and ten (10 patterns) second passage regulation states set in the afternoon. Shall be obtained. Therefore, the passage state acquisition unit 411 corresponds to the ten first set value information corresponding to the ten first passage regulation states set in the morning and the ten second passage regulation states set in the afternoon. 10 pieces of second setting value information to be acquired. Each of the plurality of passage regulation states acquired by the passage state acquisition unit 411 is sequentially set in the plurality of automatic ticket gates 1, and the processing of each processing unit described below is executed. For example, 10 pieces of the first setting value information are changed to the morning passage setting by transmitting one piece of the first setting value information to a plurality of automatic ticket gates 1 every day. Similarly, 10 pieces of the second setting value information are changed to the afternoon passage setting by transmitting one piece of the second setting value information to the plurality of automatic ticket gates 1 every day.

The congestion degree detection unit 412 detects the congestion degree of users around the plurality of automatic ticket gates 1 in the passage regulation state acquired by the passage state acquisition unit 411. For example, when a plurality of automatic ticket gates 1 are set and operated in the passage regulation state of the passage regulation state acquired by the passage state acquisition unit 411, the congestion degree of users around the plurality of automatic ticket gates 1 is To detect. For example, the congestion degree detection unit 412 may determine the number of users around the plurality of automatic ticket gates 1 or the number of users around the plurality of automatic ticket gates 1 based on images captured by a plurality of cameras installed in the vicinity of the ticket gate 7 or the concourse of the station 8. Detect the density. The density is represented by the number of users per unit area around the plurality of automatic ticket gates 1.

Further, the congestion degree detection unit 412 detects the congestion degree for a predetermined period (predetermined time period). For example, when the day (predetermined period) is divided into the morning (first predetermined period) time period and the afternoon (second predetermined period) time period as described above, the congestion degree detection unit 412 determines that the morning period Of the congestion degree (one example of the first congestion degree of the present invention) and the congestion degree of the afternoon period (an example of the second congestion degree of the present invention). For example, the congestion degree detection unit 412 sets the first congestion degree in the morning from the start time when the use of the station 8 starts to noon and the second congestion degree in the afternoon from the noon to the end time when the use of the station 8 ends. To detect. For example, the congestion degree detection unit 412 detects a change in the number of users in the morning as the first congestion degree and a change in the number of users in the afternoon as the second congestion degree.

The congestion determination unit 413 determines whether the congestion degree detected by the congestion degree detection unit 412 exceeds a threshold value. Specifically, the congestion determination unit 413 determines whether the number or density of users around the plurality of automatic ticket gates 1 detected by the congestion degree detection unit 412 exceeds the threshold value. The threshold value is set to a value corresponding to a state in which a plurality of users are staying (in a matrix) around the plurality of automatic ticket gates 1. For example, the threshold value is set to a value obtained by multiplying the number of ticket gate passages 9 divided into ticket gates by 10 (persons). That is, the threshold value corresponds to a situation where 10 users are waiting for use (waiting for entrance or waiting for exit) per ticket gate 9.

In the example of FIG. 2, since the ticket gates 7A are divided into 6 passages, for example, the congestion determination unit 413 indicates that the number of users around the ticket gate 7A detected by the congestion degree detection unit 412 is 60. Determine if it exceeds. The congestion determination unit 413 executes the determination process each time the congestion degree detection unit 412 detects the congestion degree.

When the day is divided into the morning time zone and the afternoon time zone as described above, the congestion determination unit 413 determines that the first congestion degree detected by the congestion degree detection unit 412 is the threshold value (the present invention. It is determined whether the second congestion degree detected by the congestion degree detection unit 412 exceeds the threshold value (an example of the second threshold value of the present invention). To do. The first threshold value and the second threshold value may be set to the same value or different values.

The congestion time calculation unit 414 calculates a congestion total time indicating a total time during which the congestion degree exceeds the threshold value within a predetermined period. Specifically, when the congestion determination unit 413 determines that the congestion degree exceeds the threshold during the predetermined period, the congestion time calculation unit 414 determines the time required until the congestion degree becomes equal to or less than the threshold. The total is calculated as the total congestion time. The required time is the time from the state where the congestion degree exceeds the threshold value (congestion state) to the state where the congestion degree is equal to or lower than the threshold value (non-congestion state) (the congestion state is resolved) Is.

Here, a specific example of the congestion total time will be described. For the sake of convenience of explanation, the following example does not consider the variable elements, and focuses only on the relationship between the number of users and the passage setting of the automatic ticket gate 1.

In the first example, in the case where a plurality of automatic ticket gates 1 capable of processing ticket gates for 100 people per minute are installed at the ticket gates to divide 10 ticket gate passages, morning commuting/commuting When 1000 users try to participate in the time zone, the congestion time calculation unit 414 calculates the total congestion time as described below. For example, if the 9 ticket gates are set exclusively for participation, the number of users waiting for participation will be 100 or less in 1 minute and the congestion state will be resolved, so the total congestion time will be "1 minute". Further, for example, when eight ticket gates are set exclusively for participation, the congestion state is resolved in 1.125 minutes, so the total congestion time is "1.125 minutes". Further, for example, when one ticket gate passage is set to be exclusively used for participation, the congestion state is resolved in 9 minutes, so the total congestion time is "9 minutes". Therefore, in this example, the total congestion time is the shortest when the nine ticket gates are set exclusively for participation.

In the second example, when the plurality of automatic ticket gates 1 are installed at the ticket gates to divide 10 passageways into the ticket gate, 1,000 users will participate during the morning commuting/commuting period. If 325 users try to enter, the congestion time calculation unit 414 calculates the congestion total time as described below. The crowded state here is a state in which 100 or more users are waiting for entry or entry. For example, if 9 ticket gates are set for entry only and one ticket gate is set for entry only, the number of users waiting for entry will be 100 or less in 1 minute, and congestion will be resolved. At the entrance side, the number of users waiting to enter becomes 100 or less in 2.25 minutes, and the congestion state is resolved, so that the total congestion time is “2.25 minutes”. Also, for example, if 8 ticket gates are set for entry only and 2 ticket gates are set for entry only, the congestion will be resolved in 1.125 minutes on the entry side and 1.125 minutes on the entry side. Since the congestion state is resolved, the total congestion time is “1.125 minutes”. Also, for example, if 7 ticket gates are set for entry only and 3 ticket gates are set for entrance only, congestion will be resolved in 1.286 minutes on the entry side and 0.75 minutes on the entry side. Since the congestion state is resolved, the total congestion time is “1.286 minutes”. Also, for example, if one ticket gate passage is set for entry only and nine ticket passages are set for entry only, the crowded state is resolved in 9 minutes on the entry side and 0.25 minutes on the entry side. Therefore, the total congestion time becomes “9 minutes”. Therefore, in this example, the total congestion time is the shortest when eight ticket gates are set for entry only and two ticket gates are set for entry only.

In the example described above, the calculation results are based on the condition that a plurality of users are evenly distributed to the plurality of automatic ticket gates 1 and the ticket gate processing is executed at a predetermined speed. However, in practice, it is difficult to calculate the total congestion time by a predetermined calculation formula because the variable element is added. Therefore, in the present embodiment, the congestion time calculation unit 414 calculates the total congestion time while the plurality of automatic ticket gates 1 are set in the passage regulation state and operated.

In addition, when the day is divided into the morning time zone and the afternoon time zone as described above, the congestion time calculation unit 414 causes the congestion indicating the total time when the first congestion degree exceeds the first threshold value. Total time (an example of the first total congestion time of the present invention), and the total congestion time (an example of the second total congestion time of the present invention) indicating the total time when the second congestion degree exceeds the second threshold value, To calculate.

FIG. 7 shows a change in the number of users representing the congestion situation around the ticket gate in the period from the use start time to the use end time of the station 8 on a certain day. For example, in the morning, when there are two time zones in which the number of users exceeds the threshold value, the congestion time calculation unit 414 calculates “t1+t2” as the morning total congestion time (first congestion total time T1). To do. In the morning, when there are three time zones in which the number of users exceeds the threshold, the congestion time calculation unit 414 calculates “t3+t4+t5” as the congestion total time (second congestion total time T2) in the afternoon. To do. In this way, the congestion time calculation unit 414 measures the time each time the congestion degree exceeds the threshold value and calculates the congestion total time for a predetermined period.

The teacher data generation unit 415 generates teacher data that associates the passage restriction state acquired by the passage condition acquisition unit 411 with the congestion total time calculated by the congestion time calculation unit 414.

When the day (predetermined period) is divided into the morning (first predetermined period) time period and the afternoon (second predetermined period) time period as described above, the teacher data generation unit 415 determines that the passage state is acquired. First teacher data that associates the first passage restriction state acquired by the unit 411 with the first total congestion time calculated by the congestion time calculation unit 414, and the first teacher data acquired by the passage condition acquisition unit 411. The second teacher data that associates the two-passage restriction state with the second total congestion time calculated by the congestion time calculation unit 414 is generated. That is, the teacher data generation unit 415 generates teacher data every predetermined period.

The teacher data generation device 41 of the present embodiment generates the teacher data corresponding to the passage regulation states of a plurality of patterns. For example, the passage state acquisition unit 411 acquires a predetermined plurality of patterns of the passage regulation state. In the above-mentioned example, the passage condition acquisition unit 411 acquires 10 patterns of the first passage restriction state in the morning and 10 patterns of the second passage restriction state in the afternoon. The congestion degree detection unit 412 detects the congestion degree corresponding to the passage restriction state of each of the plurality of patterns. Also, the congestion time calculation unit 414 calculates the total congestion time corresponding to the passage restriction states of each of the plurality of patterns. Then, the teacher data generation unit 415 generates the teacher data corresponding to the passage restriction state of each of the plurality of patterns. FIG. 8 is a diagram showing an example of the teacher data generated by the teacher data generation device 41. As shown in FIG. 8, the setting information “D101 to D110” and the congestion total time “T101 to T110” corresponding to the passage restriction states of 10 patterns in the morning are registered in association with each other, and the 10 patterns in the afternoon. The setting information “D201 to D210” and the total congestion time “T201 to T210” corresponding to each of the passage restriction states of are registered in association with each other. The teacher data generated by the teacher data generation unit 415 is stored in the teacher data storage unit 442. The teacher data generation device 41 also transmits the teacher data to the learning device 42.

As described above, the teacher data generation device 41 does not calculate the total congestion time for all the patterns of the passage regulation state configured by the plurality of automatic ticket gates 1, but the congestion total time for the passage regulation states of the predetermined number of patterns. To calculate. Further, the total congestion time, which is the total time when the congestion degree exceeds the threshold value, is generated as teacher data, and the teacher data is not generated for the time when the congestion degree is equal to or less than the threshold value. Further, the total congestion time is the time actually measured in the situation (environment) in which the variable element is included. Therefore, it is possible to generate specific teacher data that appropriately reflects the congestion situation without preparing a large number of passage restriction state patterns. Therefore, according to the teacher data generation device 41 of the present embodiment, it is possible to efficiently generate the teacher data used for machine learning for setting the passage restriction state of each of the automatic ticket gates 1.

[Learning device 42]
The learning device 42 generates a learned model by performing machine learning using the teacher data generated by the teacher data generation device 41. Specifically, the learning device 42 performs the machine learning using the teacher data to generate the learned model that estimates the total congestion time corresponding to the arbitrary passage restriction state.

The learning device 42 may perform machine learning using not only the teacher data but also information about the passage restriction state. Although the learning device 42 can use a general-purpose CPU, in order to enable higher-speed arithmetic processing, for example, GPGPU (General-Purpose computing on Graphics Processing Units) or a large-scale PC cluster is used. Is desirable.

Machine learning has algorithms such as supervised learning, unsupervised learning, and reinforcement learning. Furthermore, in order to realize these methods, extraction of the feature quantity itself is performed. A method called “deep learning” for learning is used. In the present embodiment, the learning device 42 has a learning model based on the various algorithms described above.

Here, the supervised learning is an algorithm for learning the "relationship between input and output" from the data input in advance. The correct value of the data is given to the input data together with the input value, and by inputting such data to the learning device 42, the learning device 42 learns the characteristics of those data, Estimate output (result) from input. In supervised learning, an error function (such as a cross-entry function) for digitizing an error between an input and an output is used. In supervised learning, the relationship between given input and output data is learned by adjusting the parameters (weights and biases) of the learning model so that the error becomes small. If this learning is possible, output can be predicted by applying the relationship to unknown data. The learning device 42 of the present embodiment performs supervised learning using the teacher data.

Unsupervised learning is an algorithm that learns features such as data structure, characteristics, and new knowledge from input input data without being given correct answer output data. It should be noted that this differs from supervised learning in that the correct answer is not given to the data to be learned. The learning device 42 of the present embodiment may perform unsupervised learning using the information on the passage restriction state.

Reinforcement learning is not a learning based on fixed and clear data such as supervised learning and unsupervised learning, but the program itself observes a given environment (current state) and a continuous series of actions Is an algorithm that self-learns appropriate behaviors, that is, behaviors that maximize the rewards that will be obtained in the future, based on the interaction of behaviors with the environment. TD learning and Q learning are known as typical methods. The learning device 42 of the present embodiment performs pre-learning by supervised learning, sets the pre-learned input/output relationship as an initial state, and then applies reinforcement learning.

The learning device 42 of the present embodiment generates a learned model by performing supervised learning particularly using the teacher data.

In addition, the learning device 42 of the present embodiment generates a first learned model corresponding to the first predetermined period by performing machine learning using the first teacher data corresponding to the first predetermined period (am), for example. Then, machine learning is performed using the second teacher data corresponding to the second predetermined period (pm) to generate the second learned model corresponding to the second predetermined period.

For example, when the information (setting value information) of an arbitrary passage restriction state is input to the learned model, the congestion total time corresponding to the passage restriction state is estimated. For example, when the information (setting value information) of an arbitrary passage restriction state is input to the first learned model, the first congestion total time corresponding to the morning characteristic corresponding to the passage restriction state is estimated. Similarly, when the information (setting value information) of an arbitrary passage restriction state is input to the second learned model, the second congestion total time corresponding to the afternoon feature corresponding to the passage restriction state is estimated. .. As a result, it is possible to obtain the total congestion time corresponding to an arbitrary path regulation state.

As described above, the learning device 42 can estimate the total congestion time corresponding to an arbitrary passage restriction state by using the teacher data corresponding to the predetermined number (predetermined pattern) of the passage restriction states. To generate. Further, the teacher data corresponds to the total congestion time obtained by totaling the times when the congestion degree exceeds the threshold value. Therefore, it is possible to highly accurately estimate the congestion total time corresponding to an arbitrary passage restriction state.

The learning device 42 outputs the generated learned model to the passage setting device 43. As a result, the learned model is applied to the passage setting device 43.

[Passage setting device 43]
The passage setting device 43 sets the passage regulation state corresponding to the shortest congestion total time among the plurality of congestion total times estimated using the learned model generated by the learning device 42 to the optimum passage regulation state. decide. The passage setting device 43 inputs an arbitrary passage regulation state (setting value information) to the learned model and estimates the total congestion time corresponding to the passage regulation state. Thereby, the congestion total time corresponding to a large amount of passage restriction states (setting value information) can be acquired in advance. The passage setting device 43 stores the acquired setting value information and the data of the congestion total time in its own storage unit or the storage unit 44. Then, the passage setting device 43 determines the passage restriction state corresponding to the shortest congestion total time from the acquired plurality of congestion total times to be the optimum passage restriction state. The passage restriction state in which the total congestion time is the shortest can be said to be a state in which a plurality of users around the ticket gate can smoothly pass through the ticket gate.

For example, the passage setting device 43 sets the passage regulation state corresponding to the shortest congestion total time of the plurality of congestion total times estimated by using the first learned model as a first predetermined period (morning). The optimum passage regulation state corresponding to is determined. Similarly, the passage setting device 43 sets the passage regulation state corresponding to the shortest congestion total time of the plurality of congestion total times estimated by using the second learned model as a second predetermined period (afternoon). ) Is determined as the optimum passage restriction state.

In this way, by determining the optimum passage regulation state for each predetermined period, it is possible to perform appropriate passage regulation even when the congestion status of the ticket gate is different for each predetermined period.

The aisle setting device 43 transmits information on the determined optimal aisle restriction state (setting value information) to the automatic ticket gate 1. When the setting value information is input, each automatic ticket gate 1 changes or maintains the passage setting (contents of passage regulation) based on the passage setting value included in the setting value information.

The gate system 100 of the present embodiment changes the passage setting of each of the plurality of automatic ticket gates 1 every predetermined period. When the predetermined period is divided into a time zone of morning (first predetermined period) and a time zone of afternoon (second predetermined period), the gate system 100 determines that each of the automatic ticket gates 1 at the start time of the morning. Of the automatic ticket gates 1 is changed at the start time of the afternoon.

[Station staff terminal device 2]
FIG. 9 is a block diagram showing the configuration of the station staff terminal device 2. The station clerk terminal device 2 is a terminal device used by a station clerk who performs station affairs on a railroad. Is a mobile terminal such as a smartphone, a mobile phone, or a tablet terminal that can be carried and carried. The station staff terminal device 2 is connected to the network N1 by wire or wirelessly, and performs data communication according to a predetermined communication protocol with other station service devices such as the station server 4 and the automatic ticket gate 1 via the network N1. To do. By operating the station staff terminal device 2, the station staff can browse and confirm various information received by the station staff terminal device 2, and can also change the passage settings of the plurality of automatic ticket gates 1.

As shown in FIG. 7, the station staff terminal device 2 includes a control unit 21, an input unit 22, a storage unit 23, a display unit 24, and a communication unit 25.

The input unit 22 is a user interface such as a keyboard, a mouse, and a touch panel. The station staff operates the station staff terminal device 2 using the input unit 22.

The storage unit 23 is a non-volatile storage medium including an HDD or SSD that stores various types of information. The storage unit 23 stores a control program for causing the control unit 21 to execute various arithmetic processes executed by the station employee terminal device 2, various data used for the various arithmetic processes, and the like. In addition, the storage unit 23 may temporarily store various information transmitted from the station server 4, the center device 5, and the like.

The display unit 24 is, for example, a liquid crystal panel. A GUI screen for changing the passage setting of the automatic ticket gate 1 and a message to a station clerk are displayed on the display unit 24 according to an instruction from the control unit 21.

The communication unit 25 connects the station staff terminal device 2 to the network N1 by wire or wirelessly, and follows a predetermined communication protocol with other station service devices such as the station server 4 and the automatic ticket gate 1 via the network N1. Is a communication interface for executing data communication.

The control unit 21 controls the operation of each unit of the station staff terminal device 2. The control unit 21 has control devices such as a CPU, a ROM, and a RAM. The ROM is a non-volatile storage medium in which control programs such as a BIOS and an OS for causing the CPU to execute various arithmetic processes are stored in advance. The RAM is a volatile or non-volatile storage medium that stores various kinds of information, and is used as a temporary storage memory (work area) for various arithmetic processes executed by the CPU. Then, the control unit 21 controls the station staff terminal device 2 by executing various control programs stored in the ROM or the storage unit 32 in advance by the CPU.

The control unit 21 includes a setting value generation unit 211 and a notification processing unit 212.

The control unit 21 functions as the various processing units when the CPU executes various arithmetic processes according to the control program. In other words, the CPU functions as the set value generation unit 211 and the notification processing unit 212 by executing the control program. Further, the various processing units included in the control unit 21 may be configured by electronic circuits. Further, the control program may be a program for causing a plurality of processors to function as the various processing units. The control unit 21 or the CPU is an example of a computer that executes the control program.

When the instruction information for changing the passage setting of the plurality of automatic ticket gates 1 is input by the operation by the station staff, the setting value generation unit 211 includes the setting value including the passage setting value corresponding to the instruction information. Generate information. Then, when the setting change instruction is input by the operation by the station staff, the control unit 21 transmits the setting value information to the plurality of automatic ticket gates 1 to set the passage setting of each automatic ticket gate 1 to the passage setting unit 113. (See FIG. 4). Further, the control unit 21 also transmits the setting value information to the station server 4 and stores the setting value information in the passage setting history storage unit 441 of the station server 4.

The notification processing unit 212 outputs various messages to notify the station staff and displays them on the display unit 24.

[Center device 5]
The center device 5 is a central monitoring device managed by a railway operator who operates a railway business including the station 8, and station service equipment such as the station server 4 and the automatic ticket gate 1 of all stations 8 operated by the railway operator. Manage. As shown in FIG. 1, the center device 5 wirelessly connects to the network N2 and executes data communication with the station server 4 and other station service devices via the network N2 according to a predetermined communication protocol.

[Teaching data generation process]
Hereinafter, with reference to FIG. 10, an example of the teacher data generation process for generating the teacher data, which is executed by the control unit of the teacher data generation device 41 of the gate system 100, will be described. In each figure, S11, S12,... Denote processing procedure numbers (step numbers). The present invention can be understood as an invention of a teacher data generation method that executes one or a plurality of steps included in the teacher data generation processing.

As shown in FIG. 10, in step S11, the control unit acquires the passage restriction state. For example, the control unit acquires, from the passage setting history data, the passage restriction states of 10 patterns in the morning of 10 days. Then, the control unit sets the passage regulation corresponding to the passage regulation state of one of the 10 patterns in the morning of the first day in the plurality of automatic ticket gates 1. Step S11 is an example of the passage state acquisition step of the present invention.

Next, in step S12, the control unit of the teacher data generation device 41 determines whether or not the predetermined period has started. For example, the control unit determines whether or not the current time is the start time when the use of the station 8 starts, the start time in the morning, or the start time in the afternoon.

Next, in step S13, the control unit starts detection of the degree of congestion of users around the plurality of automatic ticket gates 1 in the passage restricted state. For example, the control unit performs the congestion degree detection process for a predetermined period (morning period) in the passage restriction state. Step S13 is an example of the congestion degree detecting step of the present invention.

Next, in step S14, the control unit determines whether the congestion level exceeds the threshold value. The control unit executes a determination process each time the congestion degree is detected. When the congestion degree exceeds the threshold value (S14: YES), the process proceeds to step S15. When the congestion degree is equal to or less than the threshold value (S14: NO), the process proceeds to step S18. Step S14 is an example of the congestion determination step of the present invention.

In step S15, the control unit starts measuring time. In step S16, the control unit determines whether the congestion degree is equal to or less than the threshold value. When the congestion degree is equal to or less than the threshold value (S16: YES), the process proceeds to step S17. In step S17, the control unit ends time measurement. That is, the control unit measures the time until the congestion degree becomes equal to or less than the threshold value.

In step S18, the control unit determines whether the predetermined period has ended. For example, the control unit determines whether or not the morning is over. When the predetermined period ends (S18: YES), the process proceeds to step S19, and when the predetermined period does not end (S18: NO), the process returns to step S14.

In step S19, the control unit ends the detection of the congestion degree. Next, in step S20, the control unit calculates the congestion total time. For example, the control unit calculates, as the congestion total time, a total time (see “T1” in FIG. 7) in which the congestion degree exceeds the threshold value in the morning. Step S20 is an example of the congestion time calculation step of the present invention.

Finally, in step S21, the control unit generates the teacher data that associates the one passage restriction state acquired in step S12 with the congestion total time. The teacher data generated here is, for example, data including set value information “D101” and total congestion time “T101” shown in FIG. Step S21 is an example of the teacher data generation step of the present invention.

The control unit sets each pattern of the remaining nine passage restriction states acquired in step S11 in each automatic ticket gate 1 on each morning from the second day to the tenth day, and The processing of steps S12 to S21 is repeated. The same processing is performed for each afternoon from the first day to the tenth day. As a result, the teacher data shown in FIG. 8 is generated.

[Optimum passage determination process]
Next, the optimum path setting process will be described with reference to FIG.

As shown in FIG. 11, in the optimum path setting process, the processes of steps S11 to S21 described above are performed, and then the processes of steps S22 to S2 are performed. The teacher data generation device 41 outputs the teacher data generated by the teacher data generation processing to the learning device 42.

The control unit of the learning device 42 performs machine learning using the teacher data generated by the teacher data generation processing (step S22) and generates a learned model (step S23). For example, the control unit uses the teacher data shown in FIG. 8 to generate a first learned model corresponding to a first predetermined period (am) and a second learning corresponding to a second predetermined period (pm). A completed model. The control unit outputs the generated learned model to the passage setting device 43.
In step S24, the control unit of the passage setting device 43 applies the learned model to estimate the congestion total time corresponding to an arbitrary passage restriction state.

In step S25, the control unit of the passage setting device 43 sets the passage regulation state corresponding to the shortest congestion total time of the plurality of congestion total times estimated using the learned model to the optimal passage regulation state. decide.

The control unit of the passage setting device 43 transmits the information (set value information) on the determined optimum passage regulation state to the automatic ticket gate 1. When the setting value information is input, each automatic ticket gate 1 changes or maintains the passage setting (contents of passage regulation) based on the passage setting value included in the setting value information.

In the optimum path determination process, the process may proceed to step S12 when the process of step S25 ends. In this case, in the teacher data generation processing, the control unit of the teacher data generation device 41 detects the congestion degree and calculates the congestion total time in the optimum passage regulation state set in the plurality of automatic ticket gates 1. That is, the control unit generates teacher data (an example of optimum teacher data of the present invention) corresponding to the optimum passage restriction state (S21).

Then, in step S22, the learning device 42 corrects the learned model by performing machine learning (step S22) using the teacher data and the optimum teacher data generated by the teacher data generation processing. A completed model is generated (step S23).

Next, in step S24, the controller of the passage setting device 43 applies the modified learned model to estimate the congestion total time corresponding to an arbitrary passage restriction state.

Then, in step S25, the control unit of the passage setting device 43 newly sets the passage restriction state corresponding to the shortest congestion total time of the plurality of congestion total times estimated by using the modified learned model. Determine the optimum passage regulation state.

The control unit of the passage setting device 43 transmits the information (set value information) on the determined optimum passage regulation state to the automatic ticket gate 1. When the setting value information is input, each automatic ticket gate 1 changes the passage setting based on the passage setting value included in the setting value information or maintains the current setting.

In this way, the teacher data generation process and the optimum path determination process are repeated. Thereby, the passage regulation of each of the plurality of automatic ticket gates 1 can be set to the optimum state according to the congestion situation around the ticket gate.

In the above-described embodiment, an example in which the teacher data generation process and the optimal passage determination process shown in FIGS. 10 and 11 are executed by the station server 4 has been described, but the process in each step is the station server 4, the automatic ticket gate 1, the station staff terminal device 2, and the center device 5 may be executed by any of the control units, or may be distributed and executed by the control units of the respective devices.

Further, each of the teacher data generation device 41, the learning device 42, and the passage setting device 43 may be configured by an individual information processing device. Further, the teacher data generation device 41 and the learning device 42 may be configured by one information processing device installed outside the station server 4, and the passage setting device 43 may be configured by the station server 4. The gate setting learning system of the present invention may be configured by the teacher data generation device 41 and the learning device 42, and may further include the passage setting device 43. Further, the gate setting learning system of the present invention may be the gate system 100.

Further, in the above-described embodiment, the passage setting of the traffic regulation of each automatic ticket gate 1 has been described as a configuration in which it can be set to any of entrance only, exit only, and both entrance and exit, but the present invention has this configuration. Not limited. For example, the automatic ticket gate 1 can be set either for entry only or for entry only, or can be set for either entry only or both entry and exit, or either only entry and entry The present invention is also applicable to a configuration that can be set to.

1: Automatic ticket gate 2: Station employee terminal device 3: Settlement terminal device 4: Station server 5: Center device 6: Ticket vending machine 7: Ticket gate 8: Station 9: Ticket passage 41: Teacher data generation device 42: Learning device 43: Passage setting device 44: Storage unit 45: Communication unit 90: Station office 100: Gate system 111: Reading processing unit 112: Recording processing unit 113: Passage setting unit 114: Passage control unit 116: Flap door drive control unit 117: Notification Processing unit 211: Setting value generation unit 212: Notification processing unit 411: Passage state acquisition unit 412: Congestion degree detection unit 413: Congestion determination unit 414: Congestion time calculation unit 415: Teacher data generation unit 441: Passage setting history storage unit 442 : Teacher data storage

Claims (16)

A teacher data generation device for generating teacher data used for machine learning,
A passage state acquisition unit that acquires the passage regulation state of each of the plurality of gate devices;
A congestion degree detection unit that detects a congestion degree of a user around the plurality of gate devices in the passage restriction state acquired by the passage condition acquisition unit,
A congestion determination unit that determines whether the congestion degree detected by the congestion degree detection unit exceeds a threshold value,
A congestion time calculation unit that calculates a congestion total time indicating a total time when the congestion degree exceeds the threshold value in a predetermined period,
A teacher data generation unit that generates the teacher data that associates the passage restriction state acquired by the passage condition acquisition unit and the congestion total time calculated by the congestion time calculation unit,
A teacher data generation device comprising: The congestion degree detection unit detects the number or density of users around the plurality of gate devices,
The congestion determination unit determines whether the number of people or the density detected by the congestion degree detection unit exceeds the threshold value,
The teacher data generation device according to claim 1. The congestion time calculation unit, in the predetermined period, when the congestion determination unit determines that the congestion degree exceeds the threshold, the total time required until the congestion degree is equal to or less than the threshold, the congestion Calculate as total time,
The teacher data generation device according to claim 1. The predetermined period includes a first predetermined period and a second predetermined period,
The passage state acquisition unit acquires a first passage regulation state corresponding to the first predetermined period and a second passage regulation state corresponding to the second predetermined period,
The congestion degree detection unit detects a first congestion degree corresponding to the first predetermined period and a second congestion degree corresponding to the second predetermined period,
The congestion determination unit determines whether the first congestion degree detected by the congestion degree detection unit exceeds a first threshold value, and the second congestion degree detected by the congestion degree detection unit is second. Determine whether the threshold is exceeded,
The congestion time calculation unit includes a first total congestion time that indicates a total time when the first congestion degree exceeds the first threshold value, and a second congestion time that indicates a total time time when the second congestion degree exceeds the second threshold value. Calculate the total congestion time,
The teacher data generation unit associates the first passage restriction state acquired by the passage condition acquisition unit with the first congestion total time calculated by the congestion time calculation unit; Second teacher data that associates the second passage restriction state acquired by the passage state acquisition unit with the second total congestion time calculated by the congestion time calculation unit is generated.
The teacher data generation device according to claim 1. The first predetermined period is a period including morning in the day, and the second predetermined period is a period including afternoon in the day,
The teacher data generation device according to claim 4. The first threshold and the second threshold are set to different values,
The teacher data generation device according to claim 4 or 5. The passage state acquisition unit acquires a predetermined plurality of patterns of the passage regulation state,
The congestion degree detection unit detects the congestion degree corresponding to the passage restriction state of each of the plurality of patterns,
The congestion time calculation unit calculates the congestion total time corresponding to the passage restriction state of each of the plurality of patterns,
The teacher data generation unit generates the teacher data corresponding to the passage restriction states of each of the plurality of patterns,
The teacher data generation device according to claim 1. The passage restriction state is a first state in which passage of the gate device in only one direction is permitted, a second state in which passage of the gate device in only the other direction is permitted, and the gate One of a third state that permits passage in both directions to the passageway of the device,
The teacher data generation device according to claim 1. The gate device is an automatic ticket gate installed at a ticket gate of a railway station and set to any one of the first state, the second state, and the third state,
The teacher data generation device according to claim 8. A teacher data generation device according to any one of claims 1 to 9,
A learning device that generates a learned model by performing machine learning using the teacher data generated by the teacher data generation device,
A gate setting learning system. The learning device generates the learned model for estimating the congestion total time corresponding to any of the passage restriction states,
The gate setting learning system according to claim 10. A path setting device that determines the path restriction state corresponding to the shortest congestion total time of the plurality of congestion total times estimated using the learned model generated by the learning device to be an optimum path restriction state. Prepare further,
The gate setting learning system according to claim 11. The teacher data generation device further generates optimum teacher data corresponding to the optimum passage restriction state determined by the passage setting device,
The learning device generates a modified learned model by modifying the learned model by performing machine learning using the teacher data and the optimum teacher data generated by the teacher data generation device,
The gate setting learning system according to claim 12. The passage setting device newly optimizes the passage regulation state corresponding to the shortest congestion total time of the plurality of congestion total times estimated using the modified learned model generated by the learning device. Determine the passage restriction status,
The gate setting learning system according to claim 13. A teacher data generation method for generating teacher data used for machine learning, comprising:
A passage state acquisition step for obtaining the passage regulation state of each of the plurality of gate devices;
A congestion degree detecting step of detecting a congestion degree of a user around the plurality of gate devices in the passage regulation state acquired by the passage state acquisition step;
A congestion determination step of determining whether the congestion degree detected by the congestion degree detection step exceeds a threshold value;
A congestion time calculation step of calculating a congestion total time indicating a total time when the congestion degree exceeds the threshold value in a predetermined period,
A teacher data generation step of generating the teacher data in which the passage restriction state acquired in the passage state acquisition step and the congestion total time calculated in the congestion time calculation step are associated with each other;
A method for generating teacher data, which is executed by one or more processors. A teacher data generation program for generating teacher data used for machine learning,
A passage state acquisition step for obtaining the passage regulation state of each of the plurality of gate devices;
A congestion degree detecting step of detecting a congestion degree of a user around the plurality of gate devices in the passage regulation state acquired by the passage state acquisition step;
A congestion determination step of determining whether the congestion degree detected by the congestion degree detection step exceeds a threshold value;
A congestion time calculation step of calculating a congestion total time indicating a total time when the congestion degree exceeds the threshold value in a predetermined period,
A teacher data generation step of generating the teacher data in which the passage restriction state acquired in the passage state acquisition step and the congestion total time calculated in the congestion time calculation step are associated with each other;
Data generation program for causing one or more processors to execute.

Images