JP6935919B2 - Automatic teller machines, terminal devices, control methods, control programs - Google Patents

Description

The present invention relates to an automated teller machine, a terminal device, a control method, and a program.

The techniques shown in Patent Document 1 and Patent Document 2 are known as automatic teller machines.
In the automatic trading machine shown in Patent Document 1, the card insertion / ejection port, the bill insertion slot, the ticketing slot, the bill ejection port, the coin ejection port, and the coin ejection receiver are all photographed from above by a handheld camera, whereby the card is photographed. , The structure is shown to suppress various fraudulent acts related to deposit banknotes, change, and tickets.

The automated teller machine shown in Patent Document 2 has a surveillance camera that captures a predetermined range and a surveillance computer that stores images captured by the surveillance camera and monitors the installation of suspicious objects. The captured image includes a card mechanism section, a passbook mechanism section, a coin deposit / withdrawal section, and a banknote deposit / withdrawal section of an automated teller machine. In this automated teller machine, the image taken by the surveillance camera is compared with the basic image in the state where no suspicious object is installed, so that the card mechanism, passbook mechanism, coin deposit / withdrawal section, and banknote deposit / withdrawal section are suspicious. Determine if there is an object.

Japanese Unexamined Patent Publication No. 2014-16946 Japanese Unexamined Patent Publication No. 2010-61196

By the way, the automatic teller machine shown in Patent Documents 1 and 2 is shown to be provided with a photographing device for photographing the vicinity of a card insertion slot and a bill insertion slot, and monitoring of fraudulent acts or suspicious objects based on the photographing device. I try to do.
Such automated teller machines are required to prevent troubles caused by breakdowns and frauds related to automated teller machines with higher accuracy.

The present invention provides an automated teller machine, a terminal device, a control method, and a program capable of solving the above-mentioned problems.

According to the first aspect of the present invention, the automated teller machine has a photographing device that photographs a range in which the card insertion slot and the bill insertion slot are included in the angle of view, an image acquired from the photographing device, and the like. Based on the information of the learning model showing the relationship between the image and whether or not the abnormality is shown, which is obtained by the machine learning process in the past, the input to be inserted into the card insertion slot or the bill insertion slot can be accepted. or a process of identifying, in the processing-on product is introduced into the card insertion port to identify whether an acceptable card acceptable to monitor whether the inserted things is abnormal ones performs a process of identifying whether a card, accepted in the processing-on product is introduced into the bill slot to identify whether the bill acceptable monitors whether the inserted things is abnormal ones notes and monitoring device that performs a process of identifying whether a possible, comprising: a.

According to the second aspect of the present invention, the terminal device includes a photographing device that photographs a range in which the card insertion slot and the bill insertion slot are included in the angle of view, an image acquired from the photographing device, and in the past. Based on the information of the learning model showing the relationship between the image and whether or not the abnormality is shown, which is obtained by the machine learning process, whether or not the input to be inserted into the card insertion slot or the bill insertion slot is acceptable. a process for identifying, in the processing-on product is introduced into the card insertion port to identify whether an acceptable card is capable card receiving monitors whether the inserted things is abnormal ones performs a process of identifying whether, in the processing-on product is introduced into the bill slot to identify whether the bill can be accepted acceptable monitors whether the inserted things is abnormal ones characterized in that it comprises a monitoring device that performs a process of identifying whether a banknote, a.

According to the third aspect of the present invention, the control method is that an automated teller machine equipped with a photographing device for photographing a range in which the card insertion slot and the bill insertion slot are included in the angle of view is obtained from the photographing device. It is inserted into the card insertion slot or the bill insertion slot based on the acquired image and the information of the learning model indicating the relationship between the image and whether or not an abnormality is shown, which was obtained by machine learning processing in the past. a process for inserted things to identify whether acceptable, monitors whether the process inserted things to be put into the card insertion port to identify whether an acceptable card is the closing thereof is abnormal ones or to perform a process of identifying whether the acceptable card, is abnormal things the closing thereof is in the process of inserted things to be put into the bill slot to identify whether the bill acceptable and performing processing to identify whether the bill acceptable monitors.

According to a fourth aspect of the present invention, the control program captures the computer of an automated teller machine equipped with a photographing device that photographs a range in which the card insertion slot and the bill insertion slot are included in the angle of view. Based on the image acquired from the device and the information of the learning model showing the relationship between the image and whether or not it shows an abnormality, which was obtained by the machine learning process in the past, it is inserted into the card insertion slot or the bill insertion slot. a process for inserted things to be to identify whether acceptable or in a process-on product is introduced into the card insertion port to identify whether an acceptable card is the closing thereof is abnormal ones in a performs a process for identifying whether a card acceptable watching, the inserted things unusual thing in the process of inserted things to be put into the bill slot to identify whether the bill acceptable it is made to function there as a monitoring unit, which performs a process of identifying whether a possible bill acceptor watching characterized.

According to the present invention, troubles due to breakdowns and frauds related to automated teller machines can be prevented with higher accuracy.

It is a figure which shows the schematic structure of the automatic teller machine according to one Embodiment of this invention. It is a figure which shows the whole view and the enlarged view of the operation part of the automatic teller machine according to one Embodiment of this invention. It is a hardware block diagram of the monitoring apparatus by one Embodiment of this invention. It is a functional block diagram of the monitoring apparatus according to one Embodiment of this invention. It is a figure which shows the example of the input which was put in the bill insertion slot by one Embodiment of this invention. It is a figure which shows the processing flow executed by the monitoring apparatus by one Embodiment of this invention.

The automatic teller machine 100 of the present invention will be described with reference to FIG.
As shown in FIG. 1, an automated teller machine 100, which is an example of a terminal device, includes a photographing device 19. The photographing device 19 photographs a range in which the card insertion slot 15 into which the card is inserted and the bill insertion slot 18 into which the bill is inserted are included in the angle of view R.
The image data captured by the photographing device 19 is supplied to the monitoring device 21.

Based on the image data acquired from the photographing device 19, the monitoring device 21 detects an abnormality in the card insertion slot 15, the input M1 inserted into the card insertion slot 15, the input M2 inserted inside the bill insertion slot 18, and the like. Monitor.

Based on the image data from the photographing device 19, the monitoring device 21 detects fraudulent foreign matter in the card insertion slot 15 and monitors whether or not the input M1 inserted into the card insertion slot 15 is an acceptable card. can do. Specifically, the monitoring device 21 monitors whether or not the input M1 is an abnormal object (for example, a dirty / damaged card, a fake card, a card analog, etc.) that is not an acceptable card. By doing so, it is possible to identify an acceptable card. The monitoring device 21 can also detect a skimming device illegally attached to the card insertion slot 15.
The monitoring device 21 can monitor whether or not the input M2 inserted into the bill insertion slot 18 is an acceptable bill based on the image data captured by the photographing device 19. Specifically, in this monitoring device 21, in addition to abnormal banknotes such as folded banknotes, damaged banknotes, and dirty banknotes, coins and foreign banknotes, which are not acceptable banknotes for the input M2, are used. , Counterfeit bills, paper scraps, clips, seals, non-banknotes such as rubber rings), it is possible to identify acceptable banknotes.

According to the automatic teller machine 100 configured as described above, one photographing device 19 photographs both the card insertion slot 15 and the bill insertion slot 18. After that, the monitoring device 21 monitors the abnormality of the card insertion slot 15, the input M1 inserted into the card insertion slot 15, and the input M2 inserted into the bill insertion slot 18 based on the image acquired from the photographing device 19. can do.
That is, according to the automatic teller machine of the present invention, an object to be inserted into the card insertion slot 15 or the bill insertion slot 18 together with fraudulent acts such as skimming based on an image taken by one photographing device 19. Since the abnormalities of M1 and M2 can be monitored together, it is possible to perform various abnormality monitoring at low cost.

(Embodiment)
The automated teller machine 100 according to the embodiment of the present invention will be described with reference to FIGS. 2 to 6.

FIG. 2 (A) is a diagram showing the entire automatic teller machine 100, and FIG. 2 (B) is an enlarged view of the operation unit of FIG. 2 (A).
An automated teller machine 100, which is an example of a terminal device, includes a main body 10 that performs cash deposit and withdrawal processing, an operation unit 11 that is provided on the front side of the main body 10 and can operate cash deposit and payment. have.

The operation unit 11 includes a first panel 12 and a second panel 13 provided at an upper position of the main body 10, a numeric keypad 14 provided at an intermediate position between the main body 10, a card insertion slot 15, a receipt port 16, and an IC card reader. It has a unit 17, a bill slot 18, a camera 19, a motion sensor 20, and the like.

The first panel 12 is a touch-type operation panel operated by the user.
The second panel 13 is located above the first panel 12 and is a display display indicating that the machine is an automated teller machine and that card information and the like can be used.

The card insertion slot 15 is an opening for inserting a card used for depositing and withdrawing banknotes.
The bill slot 18 is a bill slot for inserting and withdrawing bills, and the user inserts and removes bills when a shutter (not shown) is opened.
In FIG. 2, the input material inserted into the card insertion slot 15 is indicated by reference numeral M1, and the input material inserted into the bill insertion slot 18 is indicated by reference numeral M2.

The camera 19 is a photographing device provided for monitoring fraudulent activities in the vicinity of the card insertion slot 15 and the bill insertion slot 18.
The camera 19 is arranged at an obliquely upper position of the card insertion slot 15 and the bill insertion slot 18, and captures a range in which the card insertion slot 15 and the bill insertion slot 18 are included in the angle of view R. The position is set to.
The motion sensor 20 is a detector for detecting whether or not there is a user in front of the operation unit 11.

Inside the main body 10, a first panel 12, a ten-key 14, a card insertion slot 15, a data processing device that processes information input by the IC card reading section 17, and a bill insertion slot 18 based on signals from the data processing device. A deposit / withdrawal device for depositing and withdrawing banknotes and a printing device for printing receipts to be taken out from the receipt opening 16 are installed, but they are omitted in the drawings.

Next, with reference to FIGS. 3 to 6, a monitoring device 21 for monitoring abnormalities occurring in the card insertion slot 15 and the bill insertion slot 18 based on the image data taken by the camera 19 serving as the photographing device will be described.

FIG. 3 is a hardware configuration diagram of the monitoring device 21.
As shown in this figure, the image processing device 22 includes a CPU (Central Processing Unit) 23, a ROM (Read Only Memory) 24, a RAM (Random Access Memory) 25, an SSD (Solid State Drive) 26, and the like.

FIG. 4 is a functional block diagram of the monitoring device 21 shown in FIG. 3, and the monitoring device 21 executes a monitoring program stored in advance .
The monitoring device 21 shown in FIG. 4 includes an image acquisition unit 30, a reference image storage unit 31, an image data determination unit 32, an abnormality result output unit 33, a control stop unit 34, a countermeasure instruction unit 35, and the like.

The image capturing unit 30 is generated at the card insertion slot 15 and the bill insertion slot 18 on condition that the banknote deposit operation by the operation unit 11 is started after detecting the presence of the user by the motion sensor 20. Image data taken by the camera 19 is captured for abnormality monitoring.
The reference image storage unit 31 stores a plurality of reference image data of the regular card inserted into the card insertion slot 15 and image data of the regular bill inserted into the bill insertion slot 18 as reference image data.

The image data determination unit 32 compares the image data from the camera 19 captured by the image capture unit 30 with the image data stored in the reference image storage unit 31 with the reference image data, whereby the card insertion slot 15 and the billboard Detects an abnormality that occurs at the slot 18. The image data determination unit 32 detects foreign matter attached to the card insertion slot 15 reflected in the image data obtained from the camera 19 based on the information obtained by the machine learning process in the past, and abnormalities of the inputs M1 and M2. May be good.
That is, the image data determination unit 32 monitors whether or not the input M1 inserted into the card insertion slot 15 is an acceptable card by comparing the image data from the camera 19 with the reference image data. .. Specifically, in the image data determination unit 32, whether or not the input M1 is an abnormal object (for example, a dirty / damaged card, a fake card, a card analog, etc.) that is not an acceptable card. Identify acceptable cards by monitoring. Alternatively, the image data determination unit 32 determines whether the shape of the card insertion slot 15 is different from the predetermined shape, and identifies that the skimming device is attached.

Further, the image data determination unit 32 monitors whether or not the input M2 inserted into the bill insertion slot 18 is an acceptable bill based on the image data taken by the camera 19. Specifically, in the image data determination unit 32, in addition to abnormal banknotes such as folded banknotes, damaged banknotes, and dirty banknotes, coins, which are not acceptable banknotes for the input M2, Identify acceptable banknotes by monitoring for foreign banknotes, counterfeit notes, paper scraps, clips, stickers, non-banknotes such as rubber rings).

Note that FIG. 5 (A) shows an example in which a normal bill is inserted into the bill insertion slot 18 as an input M2, and FIG. 5 (B) shows a paper waste as an input M2 inside the bill insertion slot 18. FIG. 5C is a diagram showing an example in which a dirty bill is inserted as an input M2 inside the bill insertion slot 18. FIG.

In the abnormality result output unit 33, the image data determination unit 32 has an abnormality in the card insertion slot 15, an abnormal input M1 has been inserted in the card insertion slot 15, and an abnormal input M2 has been inserted in the bill insertion slot 18. When it is identified that it has been done, an abnormality detection signal is output.
The control stop unit 34 performs a process of stopping acceptance at the card insertion slot 15 or the bill insertion slot 18 based on the abnormality detection signal output from the abnormality result output unit 33.
The countermeasure instruction unit 35 takes various countermeasures after the acceptance process is stopped by the control stop unit 34. For example, the countermeasure instruction unit 35 performs a process of displaying an image or character message indicating that the inputs M1 and M2 cannot be accepted on the first panel 12, and a process of outputting a voice message from a speaker (not shown).

At the same time, the countermeasure instruction unit 35 notifies the management center 40 of the automated teller machine 100 that an abnormality has occurred, and provides the management center 40 with various measures (for example, remote support, remote device control, etc.). Make transactions suspended, deposit / withdrawal suspension, maintenance staff dispatch arrangements, etc.).
In addition, the countermeasure instruction unit 35 performs a process of leaving a log of the operating status, transaction status, etc. of the automated teller machine 100 so that it can be analyzed after the fact, and an alarm is displayed on the image of the automated teller machine 100 and the surveillance camera on the ceiling. Record the information of the contents and the transaction status in association with each other.
At this time, the countermeasure instruction unit 35 adds the camera image to a high-definition mode, specifically, a still image recording to a moving image mode, a mode to increase the frame rate, resolution, image quality, and the like. It is good to perform similar processing.

Next, the processing of the monitoring device 21 will be described with reference to the flowchart of FIG.

<< Step S1 >>
The monitoring device 21 determines whether or not the deposit operation in the operation unit 11 has been started, and if YES, proceeds to the next step S2.

<< Step S2 >>
The image capture unit 30 of the monitoring device 21 starts capturing image data taken by the camera 19 for abnormality monitoring that occurs in the card insertion slot 15 and the bill insertion slot 18.

<< Step S2 >>
The image data determination unit 32 stores the image data of the camera 19 captured in step S1 in the reference image storage unit 31, the reference image of the card insertion slot 15, and the reference image of the regular card inserted in the card insertion slot 15. The data and the image data of the regular bill inserted into the bill slot 18 are compared with the corresponding reference image data.

<< Step S3 >>
The image data determination unit 32 determines whether or not the image data of the camera 19 matches the reference image data stored in the reference image storage unit 31 based on the comparison result in step S2, and if they match, it is considered normal. The determination is made, the process returns to the previous step S1, and if there is a discrepancy, it is determined that there is an abnormality, and the process proceeds to the next step S4.
Specifically, the image data determination unit 32 compares the image data from the camera 19 with the reference image data in step S3, so that the input M1 inserted into the card insertion slot 15 can accept the card. Monitor whether or not it is. Specifically, in step S3, it is monitored whether the card insertion slot 15 has an abnormal shape. Further, in step S3, by monitoring whether or not the input M1 is an abnormal object (for example, a dirty / damaged card, a fake card, a card analog, etc.) that is not an acceptable card, the input M1 is monitored. Identify acceptable cards.

Further, in step S3, the image data determination unit 32 monitors whether or not the input M2 inserted into the bill insertion slot 18 is an acceptable bill based on the image data taken by the camera 19. Specifically, in step S3, the image data determination unit 32 includes abnormal banknotes (for example, bent banknotes, damaged banknotes, dirty banknotes, and the like) that are not acceptable banknotes for the input M2. , Coins, foreign banknotes, counterfeit bills, paper scraps, clips, stickers, non-banknotes such as ring rubber) to identify acceptable banknotes.

In step S3, the image data determination unit 32 detects foreign matter attached to the card insertion slot 15 reflected in the image data obtained from the camera 19 based on the information obtained by the machine learning process in the past, and abnormalities of the inputs M1 and M2. It may be detected.

<< Step S4 >>
In step S3, the abnormality result output unit 33 outputs an abnormality detection signal when it is identified that the abnormal inputs M1 and M2 have been inserted at the card insertion slot 15 or the bill insertion slot 18.

<< Step S5 >>
The control stop unit 34 performs a process of stopping acceptance at the card insertion slot 15 or the bill insertion slot 18 based on the abnormality detection signal output in step S4.

<< Step S6 >>
After stopping the acceptance at the card insertion slot 15 or the bill insertion slot 18, the countermeasure instruction unit 35 outputs a message to the user that the inputs M1 and M2 cannot be accepted, and ends this flowchart. ..

According to the automatic teller machine 100 configured as described above, the camera 19 photographs both the card insertion slot 15 and the bill insertion slot 18. After that, the monitoring device 21 monitors the abnormality of the card insertion slot 15, the input M1 inserted into the card insertion slot 15, and the input M2 inserted into the bill insertion slot 18 based on the image acquired from the camera 19. be able to.
That is, according to the automatic teller machine 100 shown in the present embodiment, the cash machine 100 is inserted into the card insertion slot 15 or the bill insertion slot 18 together with fraudulent acts such as skimming based on the image taken by one camera 19. Since the abnormalities of the inputs M1 and M2 can be monitored together, it is possible to perform various abnormality monitoring at low cost. And it is possible to prevent troubles caused by breakdowns and frauds related to automated teller machines with higher accuracy.

(Modification example 1)
In the above embodiment, the camera 19 is used as a photographing device for photographing both the card insertion slot 15 and the bill insertion slot 18, but the card insertion slot 15 and the card insertion slot 15 and the card insertion slot 18 are provided by a dedicated photographing device different from the camera 19. The abnormalities of the inputs M1 and M2 inserted into the bill insertion slot 18 may be monitored together.

(Modification 2)
Further, in the above embodiment, the photographing device monitors the bill insertion slot 18 for depositing and withdrawing bills, but the present invention is not limited to this, and the bill insertion slot 18 dedicated to depositing is monitored together with the card insertion slot 15. You may.

(Modification example 3)
Further, in the above embodiment, by comparing the image data from the camera 19 with the reference image data, the data is inserted into the card insertion slot 15, the input m1 to be inserted into the card insertion slot 15, and the bill insertion slot 18. The abnormality of the input material M2 was monitored. At this time, the image data of the detected abnormal material may also be stored in the reference image storage unit 31 as the reference image data. Then, by accumulating such reference image data, the monitoring function of the monitoring device 21 may be enhanced.

Although the above description uses the automated teller machine 1, the automated teller machine 1 is an example of a terminal device, and the terminal device other than the automated teller machine 1 is the automated teller machine 1 described above. The same processing may be performed with the same configuration as the above. In this case, the terminal device includes the above-mentioned control device 10.

Although the embodiments of the present invention have been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like within a range not deviating from the gist of the present invention are also included.

The monitoring device 21 has a computer system. The process of each process described above is stored in a computer-readable recording medium in the form of a program, and the process is performed by the computer reading and executing this program. Here, the computer-readable recording medium refers to a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, or the like. Further, this computer program may be distributed to a computer via a communication line, and the computer receiving the distribution may execute the program.

Further, the above program may be for realizing a part of the above-mentioned functions. Further, a so-called difference file (difference program) may be used, which can realize the above-mentioned functions in combination with a program already recorded in the computer system.

Some or all of the above embodiments may also be described, but not limited to:

(Appendix 1) A photographing device that photographs the range in which the card insertion slot and the bill insertion slot are included in the angle of view, and
An automated teller machine comprising: a monitoring device for monitoring an abnormality of an input to be inserted into the card insertion slot or a bill insertion slot based on an image acquired from the photographing device.

(Appendix 2) Based on the image acquired from the photographing device, the monitoring device has an abnormality in the card insertion slot or an abnormality in the card inserted into the card insertion slot, and an input object inserted into the bill insertion slot. The automatic teller machine according to Appendix 1, which is characterized by monitoring anomalies.

(Supplementary Note 3) The automatic teller machine according to Appendix 1 or Appendix 2, wherein the monitoring device detects non-banknotes as an abnormality of the input to be inserted into the bill insertion slot.

(Appendix 4) Based on the image acquired from the photographing device, the monitoring device inserts the card into the card insertion slot in an abnormal state or the card inserted into the card insertion slot in an abnormal state and the bill insertion slot in an abnormal state. The automatic teller machine according to Appendix 1 or Appendix 2, wherein the banknotes are monitored.

(Appendix 5) The monitoring device is characterized in that it detects abnormal banknotes including at least bent banknotes, damaged banknotes, and dirty banknotes as banknotes to be inserted into the banknote slot in an abnormal state. The automatic teller machine described in 4.

(Appendix 6) It has a reference image storage unit that stores a plurality of image data of a regular card and a regular bill inserted into the bill slot as reference image data.
By comparing the image acquired from the photographing device with a plurality of reference image data stored in advance in the reference image storage unit, the monitoring device has an abnormal input in the card insertion slot or the bill insertion slot. Or, the automatic teller machine according to any one of Appendix 1 to Appendix 5, which detects whether or not a banknote has been inserted into the banknote slot in an abnormal state.

(Supplementary Note 7) The automatic teller machine according to any one of Supplementary note 1 to Supplementary note 6, further comprising an output unit for outputting the occurrence of the abnormality.

(Supplementary Note 8) The automatic teller machine according to any one of Supplementary note 1 to Supplementary note 7, further comprising a stop section for stopping a predetermined control when the abnormality occurs.

(Appendix 9) A photographing device that photographs the range in which the card insertion slot and the bill insertion slot are included in the angle of view, and
A terminal device including a monitoring device for monitoring an abnormality of an input object inserted into the card insertion slot or a bill insertion slot based on an image acquired from the photographing device.

(Appendix 10) An automated teller machine equipped with a photographing device that photographs the area where the card insertion slot and the bill insertion slot are included in the angle of view.
A control method characterized in that an abnormality of an input object inserted into the card insertion slot or a bill insertion slot is monitored based on an image acquired from the photographing device.

(Appendix 11) A computer of an automated teller machine equipped with a photographing device that photographs the range in which the card insertion slot and the bill insertion slot are included in the angle of view.
A control program characterized by functioning as a monitoring means for monitoring an abnormality of an input object inserted into the card insertion slot or a bill insertion slot based on an image acquired from the photographing device.

1 Imaging device 21 Monitoring device 15 Card insertion slot 18 Banknote slot 19 Camera (photographing device)
100 ATM automatic teller machine M1 input M2 input

Claims (7)

A photographing device that photographs the range in which the card insertion slot and the bill insertion slot are included in the angle of view,
Based on the image acquired from the photographing device and the information of the learning model indicating the relationship between the image and whether or not an abnormality is shown, which was obtained by machine learning processing in the past, the card insertion slot or the bill insertion slot In the process of identifying whether the input to be inserted into the card is acceptable, and in the process of identifying whether the input to be inserted into the card insertion slot is an acceptable card, the input is abnormal. In the process of monitoring the presence of a card and identifying whether it is an acceptable card, and identifying whether the input inserted into the bill slot is an acceptable bill, the input is abnormal. A monitoring device that monitors whether it is a thing and identifies whether it is an acceptable banknote,
An automated teller machine characterized by being equipped with. The automatic teller machine according to claim 1, wherein the monitoring device cancels acceptance of the input when the input is unacceptable. The automatic teller machine according to claim 1 or 2, wherein the monitoring device controls the image captured by the photographing device to have high definition when the input is acceptable. The automatic teller machine according to any one of claims 1 to 3 , further comprising an output unit that outputs that the abnormality has occurred. A photographing device that photographs the range in which the card insertion slot and the bill insertion slot are included in the angle of view,
Based on the image acquired from the photographing device and the information of the learning model indicating the relationship between the image and whether or not an abnormality is shown, which was obtained by machine learning processing in the past, the card insertion slot or the bill insertion slot In the process of identifying whether the input to be inserted into the card is acceptable, and in the process of identifying whether the input to be inserted into the card insertion slot is an acceptable card, the input is abnormal. In the process of monitoring the presence of a card and identifying whether it is an acceptable card, and identifying whether the input inserted into the bill slot is an acceptable bill, the input is abnormal. A monitoring device that monitors whether it is a thing and identifies whether it is an acceptable banknote,
A terminal device comprising. An automated teller machine equipped with a shooting device that captures the area where the card insertion slot and the bill slot are included in the angle of view.
Based on the image acquired from the photographing device and the information of the learning model showing the relationship between the image and whether or not an abnormality is shown, which was obtained by machine learning processing in the past, the card insertion slot or the bill insertion slot In the process of identifying whether the input to be inserted into the card is acceptable, and in the process of identifying whether the input to be inserted into the card insertion slot is an acceptable card, the input is abnormal. In the process of monitoring the presence of a card and identifying whether it is an acceptable card, and identifying whether the input inserted into the bill slot is an acceptable bill, the input is abnormal. A control method characterized in that it monitors whether it is a thing and identifies whether it is an acceptable banknote. A computer of an automated teller machine equipped with a shooting device that captures the area where the card insertion slot and the bill slot are included in the angle of view.
Based on the image acquired from the photographing device and the information of the learning model indicating the relationship between the image and whether or not an abnormality is shown, which was obtained by machine learning processing in the past, the card insertion slot or the bill insertion slot In the process of identifying whether the input to be inserted into the card is acceptable, and in the process of identifying whether the input to be inserted into the card insertion slot is an acceptable card, the input is abnormal. In the process of monitoring the presence of a card and identifying whether it is an acceptable card, and identifying whether the input inserted into the bill slot is an acceptable bill, the input is abnormal. A monitoring means that monitors whether it is a thing and identifies whether it is an acceptable banknote.
A control program characterized by functioning as.

Images