JP2020123123A - Gate setting learning system, information processing apparatus, gate setting learning method, and program - Google Patents

Abstract

To provide a gate setting learning system, an information processing apparatus, a gate setting learning method, and a program that can make the accuracy in learning a setting value for setting the state of each of a plurality of gate devices provided in a passage, equivalent to a level determined by a human.SOLUTION: A gate setting learning method executed in a gate system 100 includes: a step of acquiring variation information for causing a variation in passage setting for each of a plurality of automatic ticket gates 1; a step of, when manager setting information including the details of setting determined by a station staff member is input, creating adjustment data including the variation information acquired at the time of input and the manager setting information; and a step of adjusting a learning model for a learning unit 442 based on the adjustment data.SELECTED DRAWING: Figure 9

Description

The present invention relates to a gate setting learning system capable of learning an appropriate state in each of a plurality of gate devices capable of changing states to any one of a plurality of states.

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 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, if the surrounding environment around the place where the gate is installed suddenly changes in a short period of time, learning may not follow the change, which may lead to a decrease in determination accuracy.In some cases, the learning model itself becomes obsolete. There is also a risk that the update will be forced.

An object of the present invention is to provide a gate setting learning system capable of making learning accuracy of set values for setting the states of a plurality of gate devices provided in a passage equal to a level judged by a human being, information processing. An object is to provide an apparatus, a gate setting learning method, and a program.

(1) A gate setting learning system according to one aspect of the present invention acquires fluctuation information that causes fluctuations in the states of a plurality of gate devices that can be set in a plurality of states based on a preset setting value. Based on the variation information acquisition unit and the variation information acquired by the variation information acquisition unit, a setting value for learning a first setting value for setting each of the plurality of gate devices in a state corresponding to the variation information. When the learning unit and the second set value for setting each of the plurality of gate devices determined by the administrator of the plurality of gate devices are input, the second set value is input at the timing when the second set value is input. An adjustment data supply unit that supplies adjustment data including the change information acquired by the change information acquisition unit and the second setting value to the setting value learning unit.
The set value learning unit adjusts its own learning model based on the adjustment data supplied by the adjustment data supply unit.

In this way, the learning model of the set value learning unit is adjusted and updated by the adjustment data including the judgment of the administrator. Therefore, it is possible to prevent the learning model from becoming obsolete due to a sudden change in the surrounding environment of the gate device. Further, since the learning model is adjusted by the adjustment data including the administrator's judgment, the learning result by the adjusted learning model approaches the judgment level of the administrator every time the adjustment is made, and the adjustment is repeated. As a result, the learning result can be expected to be equivalent to the judgment level of the administrator. Further, by using the learning model equivalent to the judgment level of the manager, the frequency of the setting change of the state of the gate device by the manager is reduced, and the workload of the manager is reduced.

(2) The adjustment data supply unit determines whether or not to apply the adjustment data based on the judgment level of the administrator, and supplies the adjustment data to the setting value learning unit when it is determined to apply. ..

When the learning model of the set value learning unit is adjusted by the adjustment data including the judgment made by the administrator having a low judgment level, the learning accuracy of the learning model may be deteriorated. However, as described above, by determining whether to apply the adjustment data based on the determination level of the administrator, by supplying the adjustment data to the setting value learning unit when it is determined to apply, The accuracy of the learning result due to the learning model is prevented from decreasing.

(3) The gate setting learning system, when the second setting value is input, sets a state of each of the plurality of gate devices based on the input second setting value; A congestion determination unit that determines whether or not a traffic state in the plurality of gate devices exceeds a predetermined congestion degree based on peripheral images of the plurality of gate devices captured after the setting by the first setting unit, Is further provided.
The adjustment data supply unit includes the adjustment including the second setting value used for the setting by the first setting unit only when the congestion determination unit determines that the traffic state is less than the congestion degree. The data is supplied to the set value learning unit.

If the traffic condition around the gate device deteriorates after the setting of the state of the gate device is changed by the first setting unit, the contents of the setting change are not suitable for the current fluctuation information, and There is a high possibility of misjudgment. Therefore, in this case, as described above, only when the congestion determination unit determines that the traffic state is less than the congestion degree, the second set value used for the setting by the first setting unit. It is preferable to supply the adjustment data including the above to the setting value learning unit. As a result, it is possible to avoid the adjustment that reduces the accuracy of the learning result by the learning model.

(4) The gate setting learning system further includes a second setting unit that sets the state of each of the plurality of gate devices based on the learning result by the setting value learning unit.

This reduces the setting work by the administrator and reduces the work load on the administrator.

(5) The plurality of states include 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 another direction is permitted, and It is preferable that there are two or more of the third states that allow passage from both directions to the passage of the gate device.

(6) The gate device is an automatic ticket gate installed at a ticket gate of a railway station and set to any one of the plurality of states based on the set value.

The present invention is suitable for a plurality of automatic ticket gates installed in railway stations.

(7) An information processing device according to another aspect of the present invention is a fluctuation that acquires fluctuation information that causes fluctuations in the states of a plurality of gate devices that can be set in a plurality of states based on a preset setting value. A setting value learning for learning a first setting value for setting each of the plurality of gate devices in a state corresponding to the fluctuation information based on the information acquisition unit and the fluctuation information acquired by the fluctuation information acquisition unit. Section and a second set value for setting each of the plurality of gate devices determined by an administrator of the plurality of gate devices, the fluctuation is performed at a timing when the second set value is input. An adjustment data supply unit that supplies adjustment data including the variation information acquired by the information acquisition unit and the second setting value to the setting value learning unit.
The set value learning unit adjusts its own learning model based on the adjustment data supplied by the adjustment data supply unit.

(8) A gate setting learning method according to another aspect of the present invention acquires fluctuation information that causes fluctuations in the states of a plurality of gate devices that can be set in a plurality of states based on a preset setting value. Timing when the second setting value is input when the variation information acquisition step and the second setting value for setting each of the plurality of gate devices determined by the administrator of the plurality of gate devices are input In the adjustment data generation step of generating adjustment data including the variation information acquired in the variation information acquisition step and the second setting value, the variation is based on the adjustment data generated in the adjustment data generation step. A learning model adjusting step of adjusting a learning model of a setting value learning unit that learns a first setting value for setting each of the plurality of gate devices to a state corresponding to information.

(9) The present invention is to be understood as an invention of a program for causing a computer to execute each step of the gate setting learning method, or an invention of a computer-readable recording medium in which such a program is recorded non-temporarily. Can also

According to the present invention, the learning accuracy of the set value for setting the state of each of the plurality of gate devices provided in the passage can be made equal to the level judged by humans.

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 configuration of the passage setting learning unit included in the station server. FIG. 7 is a block diagram showing the configuration of a station staff terminal device to which the gate system according to the embodiment of the present invention is applied. FIG. 8 is a diagram showing passage setting history data stored in a storage unit included in the station server. FIG. 9 is a flowchart showing a first example of passage setting change processing executed by the control unit included in the station server. FIG. 10 is a flowchart showing a second example of the passage setting change processing executed by the control unit included in the station server. FIG. 11 is a flowchart showing a third example of the passage setting change processing executed by the control unit included in the station server. FIG. 12 is a flowchart showing a fourth example of passage setting changing processing executed by the control unit included in the station server. FIG. 13 is a flowchart showing a fifth example of passage setting change processing executed by the control unit included in the station server.

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. As shown, the automatic ticket gate 1, the station employee terminal device 2, the station server 4 (an example of the information processing device of the present invention), and the center device 5 are configured. 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. Hereinafter, the aisle setting value determined to be appropriate by a station clerk who manages a plurality of automatic ticket gates 1 (an example of the administrator of the present invention) is referred to as an administrator setting value, and the setting value including the administrator setting value The information is called administrator setting information. The administrator setting value or the administrator setting information is an example of the second setting value of the present invention.

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 of the automatic ticket gate 1 (passage regulation state) in which the passage regulation is set to be used for both entrance and exit so that the flap door 15 operates as described above is an example of a plurality of states of the present invention. Yes, and 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 of the automatic ticket gate 1 (passage regulation state) in which the passage regulation is set only for the entrance so that the flap door 15 operates as described above is an example of a plurality of states of the present invention. It corresponds to the first state of the 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 of the automatic ticket gate 1 (passage regulation state) in which the passage regulation is set only for the participation so that the flap door 15 operates is an example of a plurality of states of the present invention. It corresponds to the second state of the 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 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 a reading processing unit 111, a recording processing unit 112, a passage setting unit 113 (an example of the first setting unit and the second setting unit of the present invention), a traffic control unit 114, a flap door. It includes various processing units such as the drive control unit 116 and the notification processing unit 117.

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 this embodiment, the case where the administrator setting information (setting value information) is input to the automatic ticket gate 1 from the station staff terminal device 2 and the case where the setting value information is input to the automatic ticket gate 1 from the station server 4 There is. 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.

As described above, the manager setting information is information including the manager setting value (passage setting value) indicating the passage regulation for each automatic ticket gate 1 determined by the judgment of the station staff, and the station staff terminal device 2 Is transmitted to each automatic ticket gate 1.

The setting value information input from the station server 4 to each automatic ticket gate 1 includes a learning result by the passage setting learning unit 44 (one example of the setting value learning unit of the present invention) of the station server 4. As will be described later, the passage setting learning unit 44 learns the passage setting value for setting the passage regulation of each of the automatic ticket gates 1. When the aisle setting unit 113 receives the setting value information including the aisle setting value (learning result) learned by the aisle setting learning unit 44, the automatic ticket gate 1 based on the aisle setting value included in the setting value information. Change or maintain the passage settings in. Hereinafter, in order to distinguish it from the administrator setting information, the setting value information including the passage setting value learned by the passage setting learning unit 44 is referred to as learning setting information. The learning setting information is transmitted from the station server 4 to each automatic ticket gate 1 when the automatic passage setting mode in the station server 4 is set to be valid. The passage setting learning unit 44 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 control unit 41, a storage unit 42, a communication unit 43, and a passage setting learning unit 44 (an example of the set value learning unit of the present invention).

The communication unit 43 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 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 42 is a non-volatile storage medium including an HDD or SSD that stores various types of information. In the storage unit 42, a control program for causing the control unit 41 to execute various arithmetic processes, a control program used for passage setting change processing (see FIGS. 8 to 13) to be described later executed by the station server 4, and Data used for each process is stored. In addition, the storage unit 42 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 42 is provided in the station server 4 is illustrated. However, for example, a part or all of various information in the storage unit 42 is stored in the station server 4 via the networks N1 and N2. 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. Further, a station staff management data storage unit 421 and a passage setting history storage unit 422, which will be described later, may be provided in the external device.

Further, the storage unit 42 is provided with storage areas such as a station staff management data storage unit 421 and a passage setting history storage unit 422.

The station clerk management data storage unit 421 stores station clerk management data including the ID numbers, names, and positions of the plurality of station clerk belonging to the station 8. The station clerk management data is used for passage setting change processing described later. Further, in the station staff management data, a predetermined accuracy is registered for each station staff. The accuracy is predetermined for each station staff. The accuracy indicates the accuracy of a judgment made by a station clerk that the contents of the traffic regulation are changed for the automatic ticket gate 1, and is an example of the judgment level of the present invention. The accuracy is determined based on, for example, an experience period (years of experience) in which a station clerk has been involved in station affairs, a service period (years of service) at the station 8, an evaluation of past judgment, and the like. It is represented by a numerical value of 1 to 10 points. The higher the number, the higher the accuracy, and the lower the number, the lower the accuracy. In the station staff management data, the accuracy is managed so that the ID number can be searched.

The passage setting history storage unit 422 stores passage setting history data. The aisle setting history data includes the manager setting information sent from the station staff terminal device 2 to the automatic ticket gate 1. The passage setting history data is used in passage setting changing processing 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. FIG. 8 is a diagram showing an example of the passage setting history data. As shown in FIG. 8, in the passage setting history data, the manager setting information used for changing the setting, the date and time of the setting change, the ID number of the station clerk who changed the setting, the accuracy of the station clerk ( Point value) etc. are included. Further, in the passage setting changing process described later, when it is determined that the traffic situation at the ticket gate 7 after the passage setting is changed is deteriorated, the determination result (corresponding to the manager setting information and indicating that the passage condition is changed ( For example, a "x" mark) is added to the passage setting history data.

The control unit 41 controls the operation of each unit of the station server 4. The control unit 41 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 41 controls the station server 4 by causing the CPU to execute various control programs stored in advance in the ROM or the storage unit 42.

As shown in FIG. 5, the control unit 41 includes an input person determination unit 411, a variation information acquisition unit 412 (an example of the variation information acquisition unit of the present invention), an adjustment data supply unit 413 (an adjustment data supply unit of the present invention), A congestion determination unit 414 (an example of the congestion determination unit of the present invention), a learning result transmission unit 415, and other various processing units are included. The control unit 41 functions as the various processing units when the CPU executes various arithmetic processes according to the control program. Further, some or all of the processing units included in the control unit 41 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.

When the ID number of the station staff member is transmitted from the station staff terminal device 2, the input person determination unit 411 compares the ID number with the station staff management data stored in the station staff management data storage unit 421. , Information about the station staff member corresponding to the ID number is specified.

The fluctuation information acquisition unit 412 acquires fluctuation information for generating adjustment data input to the passage setting learning unit 44 described below. This variation information is also used for machine learning in the passage setting learning unit 44. The fluctuation information is information regarding elements (fluctuation elements) that cause fluctuations in the passage regulation content of each of the plurality of automatic ticket gates 1.

The fluctuation information includes, for example, the number of installed automatic ticket gates 1 installed at the ticket gate 7A of the station 8, the identification number of each automatic ticket gate 1 and position information. The variation information can be obtained from the storage unit 42 in which the information is stored in advance. In addition, the change information includes the concourse inside or outside the ticket gate 7A of the station 8 (see FIG. 2), the vicinity of the ticket gate 7A, the vicinity of the settlement terminal device 3 and the ticket vending machine 6 (see FIG. 2), the ticket gate. 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), Information such as the speed and direction of travel of the user, the age group of the user, the presence or absence of group users, and the like. When the user includes a non-healthy person, the variation information includes 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. Information such as whether or not it is used. These pieces of variation information 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 fluctuation information includes temperature, humidity, atmospheric pressure, altitude, and weather at the location of the station 8. Further, the fluctuation information includes the current season, calendar (year, month, day), and time. Further, the fluctuation information includes event information held around the station 8, presence/absence of a large facility around the station 8, operation status (operation schedule) at the station 8, train delay information, and the like. When the variation information is the temperature, humidity, atmospheric pressure, and altitude at the location of the station 8, the variation information acquisition unit 412 includes a temperature sensor, a humidity sensor, an atmospheric pressure sensor, and an altitude sensor provided inside or outside the station 8. The sensor output value output from is received, and the real-time temperature, humidity, atmospheric pressure, and altitude indicated by the sensor output value are acquired. If the change information is the weather around the station 8, the change information acquisition unit 412 downloads the weather information from the weather information database connected to the station server 4 to the Internet, and the change information acquisition unit 412 downloads the change information. 412 receives the weather information from the control unit 41. Further, the fluctuation information acquisition unit 412 can acquire information such as the operation status and the delay information from the center device 5.

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

Since such variation information affects the traffic situation of the user who passes through the ticket gate 7A, it can be said that the variation information affects the passage regulation contents 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, an automatic ticket gate with passage restrictions set for exclusive use It becomes necessary to increase the number of ones.

In the present embodiment, the passage setting learning unit 44, which will be described later, learns the passage setting value that is an appropriate passage regulation content for each automatic ticket gate 1 based on the plurality of pieces of variation information described above.

The adjustment data supply unit 413 generates the adjustment data provided to the passage setting learning unit 44. The adjustment data is a variation information acquisition unit at a reception timing (date and time of reception) when the control unit 41 receives the administrator setting information (second setting value) corresponding to the passage regulation desired by the station staff from the station staff terminal device 2. 412, and includes the change information and the administrator setting information. The adjustment data is for adjusting various parameters (weight, bias, etc.) of the learning model in the passage setting learning unit 44, and corresponds to teacher data in so-called supervised learning. In the present embodiment, the administrator setting information including the administrator setting value determined by the judgment of the station staff is the optimum solution for the variation information acquired at the timing when the administrator setting information is received (reception timing). By observing, the variation information is used as an input value, and the administrator setting value of the administrator setting information is used as an optimum solution of the input value.

Further, in the present embodiment, the adjustment data supply unit 413 extracts the characteristic amount of the variation information by analyzing the variation information acquired at the reception timing, and the characteristic amount and the administrator setting information are combined. The associated adjustment data is generated. Then, the adjustment data supply unit 413 transmits the generated adjustment data to the passage setting learning unit 44.

The adjustment data supply unit 413 determines whether to apply the adjustment data based on the accuracy (judgment level) of the station clerk who has transmitted the manager setting information to the automatic ticket gate 1, and determines to apply the adjustment data. Only in such a case, the adjustment data may be transmitted to the passage setting learning unit 44. For example, the adjustment data supply unit 413 determines to apply the adjustment data when the accuracy is equal to or higher than a predetermined threshold value (reference level), and transmits the adjustment data to the passage setting learning unit 44.

When the aisle setting unit 113 of the automatic ticket gate 1 changes the aisle setting based on the administrator setting information, the congestion determination unit 414 is based on the image around the automatic ticket gate 1 captured after the change. It is determined whether or not the traffic condition at the ticket gate 7 exceeds a predetermined congestion level. The image around the automatic ticket gate 1 can be obtained from a plurality of cameras installed around the ticket gate 7 or in the concourse of the station 8. Based on these images, the congestion determination unit 414 compares the image before the setting change with the image after the setting change to determine whether the traffic condition of the ticket gate 7 exceeds the congestion degree. The image after the setting change is, for example, an image after a predetermined set time has elapsed since the setting was changed. The congestion degree and the set time are arbitrarily determined depending on the usage status of the station 8 and the surrounding environment.

In the present embodiment, the adjustment data supply unit 413 may transmit the adjustment data to the passage setting learning unit 44 only when it is determined that the traffic state of the ticket gate 7 is less than the congestion degree. ..

The learning result transmitting unit 415 transmits the learning setting information including the learning result (passage setting value) by the passage setting learning unit 44 to the automatic ticket gate 1 when the automatic setting mode is set to be valid. Here, the automatic setting mode is a passage setting control mode in which the passage setting of the automatic ticket gate 1 is automatically changed based on the learning result by the passage setting learning unit 44. The setting value of the automatic setting mode is stored in, for example, the storage unit 42 of the station server 4, and the validity or invalidity of the setting value can be changed by a request from the station staff terminal device 2. If the automatic setting mode is disabled, the learning setting information is not transmitted to the automatic ticket gate 1, and even if the learning result is output from the passage setting learning unit 44, the learning result is It is stored in the storage unit 42 as learning history data.

The passage setting learning unit 44 will be described below with reference to FIG. Here, FIG. 6 is a block diagram showing a configuration of the passage setting learning unit 44 included in the station server 4.

The passage setting learning unit 44 is a learning device configured to specify the passage setting value, which is the setting content of the passage regulation of the automatic ticket gate 1 to be set, by machine learning, and is the learning for specifying the passage setting value. I have a model. In the present embodiment, the aisle setting learning unit 44 sets the aisle settings of the plurality of automatic ticket gates 1, the distribution of the above-mentioned three types of traffic regulation, and each traffic regulation so as to be suitable for the input variation information. The passage setting value indicating the position of the automatic ticket gate 1 is output as a learning result. Here, the passage setting value output as the learning result or the learning result is an example of the first setting value of the present invention.

As shown in FIG. 6, the passage setting learning unit 44 includes an adjustment data acquisition unit 441, a learning unit 442, and a learning model adjustment unit 443. The passage setting learning unit 44 can use a general-purpose CPU, but in order to enable faster arithmetic processing, for example, GPGPU (General-Purpose computing on Graphics Processing Units) or a large-scale PC cluster is used. It is desirable to use.

The adjustment data acquisition unit 441 acquires the adjustment data transmitted from the adjustment data supply unit 413. The acquired adjustment data is information used for learning by the learning unit 442, is stored in a storage unit (not shown) in the passage setting learning unit 44, and is input to the learning unit 442. Further, the plurality of pieces of variation information acquired by the variation information acquisition unit 412 are input to the learning unit 442, and the variation information is used for machine learning in the learning unit 442. In addition, in this embodiment, the configuration in which the variation information acquisition unit 412 is provided in the control unit 41 is illustrated, but the variation information acquisition unit 412 may be provided in the passage setting learning unit 44.

The learning unit 442 learns the passage setting value based on the input variation information. In the present embodiment, the learning unit 442 uses not only the acquired variation information but also the adjustment data acquired by the adjustment data acquisition unit 441 to determine the appropriate passage setting value corresponding to the variation information. Machine learning.

The learning unit 442 extracts feature quantities such as useful rules and rules, knowledge expressions, and judgment criteria from the set of the input variation information by analysis, outputs the judgment result, and outputs the judgment result. It has a learning function. 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 unit 442 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. By giving a large amount of such data to the learning unit 442, the learning unit 442 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.

Unsupervised learning is an algorithm that learns features such as data structure, characteristics, and new knowledge from a large amount of input data, without being given correct 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.

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.

In addition, in reinforcement learning, the result caused by the action is unknown. Therefore, when adopting the reinforcement learning as the machine learning of the learning unit 442, the learning starts from a state in which the passage setting value to be learned is not known at all, and in the initial stage, the passage setting value obtained by the learning is obtained. Is not suitable for the variation information. Therefore, generally, pre-learning is performed by supervised learning, and the relationship of pre-learned input and output is set as an initial state, and then reinforcement learning is applied.

The learning model adjustment unit 443 adjusts the parameters of the learning model of the learning unit 442 based on the adjustment data input from the adjustment data acquisition unit 441.

By the way, even if the passage setting of the plurality of automatic ticket gates 1 is entrusted to the learning result by the learning unit 442, an appropriate solution is not always output according to the variation information including the situation around the ticket gate 7. , In some cases, a significantly inappropriate solution may be output. In this case, the passage setting of the automatic ticket gate 1 is changed to an inappropriate content that does not match the variation information, and a user passing through the ticket gate 7 is 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. In addition, when the surrounding environment changes rapidly due to the construction of schools or large shopping facilities around the station 8, learning by the learning model may not follow such changes, which may lead to a decrease in learning accuracy. The learning model itself may become obsolete and forced to be updated.

On the other hand, in the present embodiment, the learning model adjustment unit 443 adjusts the parameters of the learning model of the learning unit 442 based on the adjustment data, and updates the parameters so as to be able to respond to the sudden change information. It is possible to prevent the learning model from becoming obsolete and to make the learning accuracy equal to the level judged by humans.

[Station staff terminal device 2]
FIG. 7 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 employee terminal device 2 includes a control unit 21, an input unit 22, a storage unit 23, a display unit 24, a communication unit 25, and an ID card reading unit 26.

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 ID card reading unit 26 reads the ID number of the station employee included in the ID card from the ID card distributed to the station employee without contact. The information read by the ID card reading unit 26 is transmitted to the station server 4 by the control unit 21 and used for authentication of the station staff.

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 set value generation unit 211 includes the management including the administrator set value corresponding to the instruction information. User setting information is generated. Then, when a setting change instruction is input by an operation by a station clerk, the control unit 21 transmits the manager setting 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). The control unit 21 also transmits the manager setting information to the station server 4 and causes the station server 4 to generate the adjustment data.

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.

[Aisle setting change processing]
Hereinafter, with reference to FIGS. 9 to 13, aisle setting change processing (including learning model adjustment processing) executed by the control unit 41 of the station server 4 of the gate system 100 to change aisle settings of the automatic ticket gates 1. ) First to fifth examples, and the gate setting learning method of the present invention will be described. In each figure, S11, S12,... Denote processing procedure numbers (step numbers).

[First example of passage setting change processing]
First, the passage setting changing process (first example) will be described with reference to FIG. 9.

As shown in FIG. 9, in step S11, the control unit 41 determines whether the ID number of the station staff member is received. When the station staff member causes the ID card reading unit 26 to read his/her own ID card to sign in to the station staff terminal device 2, the control unit 21 of the station staff terminal device 2 causes the station server 4 to read the ID number read from the ID card. Send. The control unit 41 determines that the ID number is received when the ID number information is input to the communication unit 43 of the station server 4.

In step S12, the control unit 41 compares the ID number acquired in step S11 with the station clerk management data, and determines the input person (station clerk) who has input the ID number from the station clerk terminal device 2. If the collation matches in step S12, a permission signal for permitting sign-in is transmitted to the station staff terminal device 2. In the station employee terminal device 2 that has received this permission signal, the passage setting of the automatic ticket gate 1 can be changed manually by the station staff. Note that if the collation matches, the accuracy corresponding to the received ID number is extracted from the station staff management data.

In the next step S13, the control unit 41 determines whether or not the manager setting information for changing the passage setting of each automatic ticket gate 1 has been received. In order to change the passage settings of each of the automatic ticket gates 1, the station staff operates the station staff terminal device 2, determines the contents of the setting change, and inputs a change instruction. The administrator setting information (second setting value) including the corresponding administrator setting value is transmitted to each automatic ticket gate 1 and also to the station server 4. Upon receipt of the manager setting information, each automatic ticket gate 1 changes the passage setting relating to the traffic regulation based on the manager setting value included in the manager setting information. On the other hand, in the station server 4, the control unit 41 determines that the administrator setting information has been received when the administrator setting information is input to the communication unit 43 of the station server 4.

When the administrator setting information is received in step S13, the control unit 41 stores the received administrator setting information in the passage setting history data stored in the passage setting history storage unit 422 (S14). In this case, the control unit 41 writes the reception date and time of the administrator setting information, the ID number of the station clerk who changed the setting, and the accuracy of the station clerk in the passage setting history data together with the administrator setting information. ..

In the next step S15, the control unit 41 acquires the fluctuation information at the timing when the manager setting information is received. In this case, the control unit 41 extracts the characteristic amount of the fluctuation information by analyzing the acquired fluctuation information. Note that step S15 is an example of the variation information acquisition step of the present invention.

When the manager setting information is received in step S13 and the feature amount of the variation information is extracted in step S15, the control unit 41 causes the passage setting learning unit 44 to extract the feature setting from the manager setting information and the feature amount. The adjustment data provided is generated (S16). Note that step S16 is an example of the adjustment data generation step of the present invention.

After that, the control unit 41 inputs the adjustment data generated in step S16 to the passage setting learning unit 44 (S17). Then, when the adjustment data is input to the passage setting learning unit 44, the adjustment data is transferred to the learning model adjusting unit 443, and the learning model adjusting unit 443 adjusts the learning model of the learning unit 442 (S18). Specifically, the parameters (weight and bias) of the learning model are adjusted. Note that step S18 is an example of the learning model adjusting step of the present invention.

As described above, in the present embodiment, the learning model of the learning unit 442 is adjusted and updated by the adjustment data including the judgment of the station staff. Therefore, the learning model becomes obsolete due to a sudden change in the surrounding environment of the station 8. Can be prevented. Further, since the learning model is adjusted by the adjustment data including the judgment of the station staff, the learning result by the adjusted learning model approaches the human judgment level every time it is adjusted, and the adjustment is repeated, It can be expected that the learning result will be equivalent to the human judgment level. In addition, by using a learning model equivalent to a human judgment level, the frequency of setting changes by station staff is reduced, and the work load on station staff is reduced.

[Second example of passage setting change processing]
Next, the passage setting changing process (second example) will be described with reference to FIG.

As shown in FIG. 10, in the passage setting changing process, the processes of steps S11 to S16 described above are performed, and then the determination process of step S31 is performed.

In step S31, the control unit 41 of each automatic ticket gate 1 after the passage setting of each automatic ticket gate 1 is changed based on the manager setting information transmitted from the station staff terminal device 2 to the automatic ticket gate 1. It is determined whether or not the traffic condition exceeds the predetermined congestion level. That is, the control unit 41 determines whether or not the traffic state of the ticket gate 7 after the passage setting is changed is worse than that before the change. Such a determination can be made by comparing moving images or still images taken before and after the setting change with a plurality of cameras installed around the ticket gate 7 or the concourse at the station 8.

When it is determined in step S31 that the traffic state after the setting change is equal to or less than the congestion degree (No in S31), the control unit 41 performs the processing of step S17 and subsequent steps. That is, the control unit 41 inputs the adjustment data to the passage setting learning unit 44 (S17). After that, the learning model adjusting unit 443 adjusts the learning model of the learning unit 442 based on the adjustment data (S18).

On the other hand, when it is determined in step S31 that the traffic condition after the setting change exceeds the congestion degree (Yes in S31), the control unit 41 determines the setting used for the setting change in the next step S32. Corresponding to the value information, a judgment result "x" mark indicating that the traffic condition has deteriorated is written in the passage setting history data.

In the next step S33, the control unit 41 transmits a request signal for requesting the setting change to the station staff terminal device 2. Upon receiving the request signal, the station staff operates the station staff terminal device 2, and within a predetermined set time T1, the new manager setting information is transmitted to each automatic ticket gate 1 and the station server 4 to change the setting. When is performed (Yes in S34), the processes in and after step S14 are repeated.

Even though the request signal is transmitted, if the setting is not changed before the set time T1 elapses (No in S34) and the automatic setting mode is set to be invalid (S35). No), the control unit 41 sends the setting value information including the passage setting value before the setting change to each automatic ticket gate 1 to return the passage setting of each automatic ticket gate 1 to the state before the change. ..

On the other hand, if the setting is not changed before the set time T1 elapses (No in S34) and the automatic setting mode is set to be valid (Yes in S35), the control unit 41 sets the passage setting. The learning unit 44 is caused to perform learning based on the current variation information (S37), and then the learning setting information including the learning result (passage setting value) by the passage setting learning unit 44 is transmitted to each automatic ticket gate 1. Then, the passage setting of each automatic ticket gate 1 is changed based on the learning result (S38).

When the traffic condition around the automatic ticket gate 1 after the setting is changed is deteriorated, the changed passage setting is not suitable for the current change information, and there is a high possibility that the station clerk makes a mistake in the judgment. Therefore, in this case, as described above, the passage setting is returned to the original setting before the change, or when the automatic setting mode is enabled, the passage setting is changed based on the learning result by the passage setting learning unit 44. Preferably.

[Third example of passage setting change processing]
Next, the passage setting changing process (third example) will be described with reference to FIG.

As shown in FIG. 11, in the passage setting change process, the processes of steps S11 to S16 described above are performed, and then the determination process of step S41 is performed.

In step S41, the control unit 41 determines whether or not the accuracy of the station clerk who has instructed the automatic ticket gate 1 to change the passage setting is less than a reference value. The control unit 41 extracts the accuracy corresponding to the ID number acquired at the time of signing in the station staff from the station staff management data stored in the station staff management data storage unit 421, and the extracted accuracy is It is determined whether it is less than the reference value. Here, if the accuracy is less than the reference value (Yes in S41), it is unlikely that the adjustment data is appropriate for the current variation information. The series of processing is terminated without inputting to the setting learning unit 44.

On the other hand, if the accuracy exceeds the reference value (No in S41), it is highly likely that the adjustment data is appropriate for the current fluctuation information. In this case, the control unit 41 therefore determines in step S17. Perform the following processing. That is, the control unit 41 inputs the adjustment data to the passage setting learning unit 44 (S17). After that, the learning model adjusting unit 443 adjusts the learning model of the learning unit 442 based on the adjustment data (S18).

If the learning model of the learning unit 442 is adjusted by the adjustment data including the determination by the station staff having low accuracy, the learning accuracy of the learning model may be deteriorated. Therefore, in this case, it is preferable to adjust the learning model based on the adjustment data only when the accuracy exceeds the reference value. This prevents the learning model from lowering the accuracy of the learning result.

[Fourth example of passage setting change processing]
Next, the passage setting changing process (fourth example) will be described with reference to FIG.

As shown in FIG. 12, in the passage setting changing process, the processes of steps S11 to S16 described above are performed, and thereafter, the determination process of step S31 described above is performed. Then, when it is determined in step S31 that the traffic state after the setting change exceeds the congestion degree (Yes in S31), the control unit 41 performs the determination process of step S41 described above. Then, in step S41, when it is determined that the accuracy is less than the reference value, a series of processes is ended, and when it is determined that the accuracy exceeds the reference value, the processes of step S17 and thereafter are performed. If it is determined in step S31 that the traffic condition exceeds the congestion degree, the processing from step S32 (see FIG. 10) is performed.

In this way, even when it is determined that the traffic condition has not deteriorated, learning is performed by adjusting the learning model based on the adjustment data only when the accuracy exceeds the reference value. The accuracy of the learning result due to the model is prevented from decreasing.

[Fifth example of passage setting change processing]
Next, the passage setting changing process (fifth example) will be described with reference to FIG.

As shown in FIG. 13, in the passage setting change process, the processes of steps S11 to S16 described above are performed, and then the determination process of step S31 described above is performed. Then, when it is determined in step S31 that the traffic state after the setting change exceeds the congestion degree (Yes in S31), the control unit 41 performs the determination process of step S41 described above. After that, when it is determined in step S41 that the accuracy exceeds the reference value, the processes of step S17 and thereafter are performed.

On the other hand, if it is determined in step S41 that the accuracy is less than the reference value, then in step S42, the control unit 41 determines whether the accuracy is greater than a lower limit value that is less than the reference value. To be judged. Here, when it is determined that the accuracy is smaller than the lower limit value, the series of processes ends without adjusting the learning model with the adjustment data.

If the accuracy is smaller than the lower limit, and if the learning model of the learning unit 442 is adjusted by the adjustment data including the judgment made by the station staff, the learning accuracy of the learning model is likely to be significantly reduced. Therefore, in this case, it is preferable to prevent the accuracy of the learning result from decreasing by terminating the processing without adjusting the learning model.

In step S42, when it is determined that the accuracy is equal to or higher than the lower limit value, that is, when the accuracy is determined between the lower limit value and the reference value, the control unit 41 The determination process of the next step S43 is performed. Specifically, in step S43, the control unit 41 refers to the aisle setting history data (see FIG. 8) stored in the aisle setting history storage unit 422 and refers to the station staff member who has instructed to change the aisle setting. It is determined whether or not the past change history includes a history in which the traffic situation deteriorates after the passage setting is changed (traffic deterioration history). Specifically, when there is no "x" mark in the item "Status after change of passage setting" in the passage setting history of the station staff, the control unit 41 has no history of deterioration of the passage, and It is determined that the change record is good, and when the “x” mark is attached, it is determined that there is the passage deterioration history.

When it is determined in step S43 that there is the traffic deterioration history, the learning accuracy of the learning model is likely to be significantly reduced when the learning model of the learning unit 442 is adjusted by the adjustment data. Therefore, in this case, the process ends without adjusting the learning model.

On the other hand, in step S43, when it is determined that the traffic deterioration history does not exist, the reliability of the determination by the station clerk is high, and even if the learning model of the learning unit 442 is adjusted by the adjustment data, the learning model Learning accuracy is unlikely to decrease. Therefore, in this case, the processing from step S17 is performed to adjust the learning model based on the adjustment data.

In the above-described embodiment, an example in which the passage setting process shown in FIGS. 9 to 13 is executed by the control unit 41 of the station server 4 has been described, but the process in each step is the station server 4, the automatic ticket gate 1, It may be executed by the control unit of either the station staff terminal device 2 or the center device 5, or may be distributed and executed by the control units of the respective devices.

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 staff terminal device 3: Settlement terminal device 4: Station server 5: Center device 6: Ticket vending machine 7: Ticket gate 7A: Ticket gate 8: Station 9: Ticket gate 9A: Gate 9B: Gate 10: case 11: control unit 12: storage unit 13: upper display unit 14: communication unit 15: flap door 15A: flap door 15B: flap door 16: IC card reading unit 17: side display unit 18: imaging unit 19: Human sensor 21: control unit 22: input unit 23: storage unit 24: display unit 25: communication unit 26: ID card reading unit 32: storage unit 41: control unit 42: storage unit 43: communication unit 44: passage setting learning Part 90: Station office 100: Gate system 111: Read 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: Input person determination unit 412: Variation information acquisition unit 413: Adjustment data supply unit 414: Congestion determination unit 415: Learning result transmission unit 421: Station staff management data storage unit 422: Passage setting history storage unit 441: Adjustment Data acquisition unit 442: Learning unit 443: Learning model adjustment unit

Claims (9)

A fluctuation information acquisition unit that acquires fluctuation information that causes fluctuations in each of a plurality of gate devices that can be set in a plurality of states based on a preset setting value,
A set value learning unit that learns a first set value for setting each of the plurality of gate devices in a state corresponding to the change information based on the change information acquired by the change information acquisition unit;
When a second setting value for setting each of the plurality of gate devices, which is determined by the administrator of the plurality of gate devices, is input, the variation information acquisition unit is at the timing when the second setting value is input. An adjustment data supply unit that supplies adjustment data including the variation information acquired by the above and the second setting value to the setting value learning unit,
The set value learning unit,
A gate setting learning system that adjusts its own learning model based on the adjustment data supplied by the adjustment data supply unit. The adjustment data supply unit,
The gate setting learning according to claim 1, wherein it is determined whether or not to apply the adjustment data based on a determination level of the administrator, and the adjustment data is supplied to the setting value learning unit when it is determined to be applied. system. A first setting unit configured to set a state of each of the plurality of gate devices based on the input second setting value when the second setting value is input;
A congestion determination unit that determines whether or not a traffic state in the plurality of gate devices exceeds a predetermined congestion degree based on peripheral images of the plurality of gate devices captured after the setting by the first setting unit, Further equipped with,
The adjustment data supply unit,
Only when the congestion determination unit determines that the traffic state is less than the congestion degree, the adjustment data including the second setting value used for the setting by the first setting unit is used as the setting value learning unit. The gate setting learning system according to claim 1 or 2, which is supplied to. The gate setting learning system according to claim 1, further comprising a second setting unit that sets a state of each of the plurality of gate devices based on a learning result by the set value learning unit. The plurality of states include 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 another direction is permitted, and the gate device. The gate setting learning system according to any one of claims 1 to 4, wherein the gate setting learning system has two or more of any of the third states in which passage is permitted from both directions. The said gate apparatus is an automatic ticket gate installed in the ticket gate of the railway station, and is set to any one of the said some states based on the said setting value, The automatic ticket gate in any one of Claim 1 to 5. Gate setting learning system. A fluctuation information acquisition unit that acquires fluctuation information that causes fluctuations in each of a plurality of gate devices that can be set in a plurality of states based on a preset setting value,
A set value learning unit that learns a first set value for setting each of the plurality of gate devices in a state corresponding to the change information based on the change information acquired by the change information acquisition unit;
When a second setting value for setting each of the plurality of gate devices, which is determined by the administrator of the plurality of gate devices, is input, the variation information acquisition unit is at the timing when the second setting value is input. An adjustment data supply unit that supplies adjustment data including the variation information acquired by the above and the second setting value to the setting value learning unit,
The set value learning unit,
An information processing apparatus that adjusts its own learning model based on the adjustment data supplied by the adjustment data supply unit. A fluctuation information acquisition step of acquiring fluctuation information that causes fluctuations in each of a plurality of gate devices that can be set in a plurality of states based on a preset setting value,
When the second set value for setting each of the plurality of gate devices, which is determined by the administrator of the plurality of gate devices, is input, the fluctuation information acquisition step at the timing when the second set value is input. An adjustment data generating step of generating adjustment data including the variation information acquired by the above and the second setting value;
A learning model adjusting step of adjusting a learning model for learning a first set value for setting each of the plurality of gate devices to a state corresponding to the variation information based on the adjustment data generated by the adjustment data generating step. And a gate setting learning method provided. A program for causing a computer to execute each step of the gate setting learning method according to claim 8.

Images