Automated trading equipment and programs

Abstract

This will prevent fraudulent transactions by third parties using automated trading systems. [Solution] The ATM 100, which performs transactions in response to user operations, includes a transaction detection unit 220 that detects transaction operations for the user to perform a transaction, an image acquisition unit 230 that acquires an image of the user when a transaction operation is detected, an estimation unit 240 that analyzes the user's image and estimates the user's attribute information, a storage unit 210 that stores pre-registered user attribute information, a determination unit 250 that compares the estimated user attribute information with the pre-registered user attribute information and determines whether or not to perform a transaction in response to the user's operation based on the comparison result, and an output unit 260 that outputs the determination result.

Description

Technical Field

[0001] The present invention relates to an automatic transaction device and a program.

Background Art

[0002] ATMs (Automatic Teller Machines) are widely installed not only in financial institutions such as banks and post offices but also in retail stores such as convenience stores and public facilities. ATMs have evolved to handle transactions other than ordinary deposits and various cashless transactions (services) and are also called automatic transaction devices in recent years (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] As described above, although ATMs have become increasingly convenient in recent years, on the other hand, taking advantage of being unmanned, when elderly users or the like use them, third parties may illegally obtain card information or PIN numbers by secretly photographing them, or illegally obtain the card itself, resulting in fraud such as the user's deposit being illegally withdrawn (so-called illegal transactions), which has become a social problem.

[0005] The present invention has been made in view of the above-described circumstances, and an object thereof is to provide a mechanism capable of preventing illegal transactions using an automatic transaction device by a third party.

Means for Solving the Problems

[0006] An automated trading system according to one embodiment of the present disclosure is an automated trading system that performs transactions in response to user operations, and is characterized by comprising: an image acquisition unit that acquires an image of the user; an estimation unit that analyzes the image of the user and estimates the user's attribute information; a user storage unit that stores pre-registered user attribute information; and a determination unit that compares the estimated user attribute information with the pre-registered user attribute information and determines whether or not to perform a transaction in response to user operations based on the comparison result. [Effects of the Invention]

[0007] According to the present invention, it is possible to prevent fraudulent transactions by third parties using automated trading devices. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows the appearance of an ATM according to one embodiment of the present invention. [Figure 2] This diagram shows the main hardware configuration of the information processing unit installed in an ATM. [Figure 3] This block diagram shows the functional configuration realized by ATMs. [Figure 4] This diagram illustrates the contents of the user management database. [Figure 5] This is an explanatory diagram illustrating the judgment operation performed by the judgment unit. [Figure 6] This is a flowchart illustrating the process for preventing fraudulent transactions. [Figure 7] This is a flowchart illustrating the decision-making process. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described in detail below with reference to the drawings. The same elements are denoted by the same reference numerals, and redundant descriptions are omitted.

[0010] A. Embodiment Figure 1 shows the external appearance of ATM 100 as an automated transaction device according to one embodiment of the present invention. ATM 100 can be installed in various locations such as banks, post offices, convenience stores, retail stores, airports, and train stations.

[0011] The ATM 100 includes a main display unit 101, a card reader unit 102, a banknote deposit / withdrawal unit 103 for depositing and withdrawing banknotes, an operation unit 104 for user operation, a code reader unit 105, an optical scan unit 106, a stand 107, a sub-display unit 108, a contactless IC communication unit 109, and a camera 110.

[0012] The ATM 100 according to this embodiment estimates the user's attribute information, such as age and gender, by analyzing the user's image acquired by the camera 110. Then, it compares the estimated attribute information with the attribute information of already registered users (hereinafter also referred to as "legitimate users"), and if a predetermined difference is found between the two, it is determined that the user is not a legitimate user but is highly likely to be a third party with the intention of conducting fraudulent transactions (hereinafter also referred to as "impersonating users"). In such cases, the ATM 100 reserves the transaction that the user desires (for example, withdrawal of deposits) and then prevents fraudulent transactions by impersonating users by performing new identity verification, etc. (details will be described later).

[0013] The main display unit 101 includes, for example, a display means such as a liquid crystal display and an input means such as a touch panel for receiving user input. The display means displays a screen or input keys that guide the user's operation, and the user can input information corresponding to the input keys by pressing these input keys on the touch panel. The user can also input the same information by operating the input means (such as a numeric keypad) of the operation unit 104 instead of the input means displayed on the main display unit 101.

[0014] The card reader 102 can read card information recorded on a cash card (including a debit card), etc. The cash card may be either an IC card type or a magnetic stripe card type. The code reading unit 105 is, for example, a code reader, and can read a two-dimensional code or the like displayed on a user terminal held directly below the code reading unit 105. The card information and code information include an identification ID for identifying the user and account identification information (described later) for identifying the transaction account.

[0015] The optical scanning unit 106 is, for example, an image scanner, and can scan a photo or characters attached to the face of a cash card, IC card, etc. placed on the pedestal 107 as an image. The pedestal 107 has a surface substantially horizontal with respect to the ground, and the optical scanning unit 106 can obtain an image of a certain quality without being affected by hand tremors or the like.

[0016] The sub-display unit 108 has display means such as a liquid crystal display, for example, and is installed on the surface of the pedestal 107. The sub-display unit 108 may have only the display means, or may have input means in addition to the display means, similar to the main display unit 101. The sub-display unit 108 may display, for example, a screen for guiding the position where a cash card, IC card, etc. read by the optical scanning unit 106 is placed. Thereby, even a user who is not familiar with the operations on the ATM 100 can perform the operations smoothly without getting lost.

[0017] The non-contact IC communication unit 109 is, for example, a non-contact IC reader / writer, and is installed inside the pedestal 107. The non-contact IC communication unit 109 can perform non-contact communication with a non-contact IC chip mounted on an IC card or the like, and can read and write information stored in the non-contact IC chip. The non-contact IC communication unit 109 can communicate with the non-contact IC chip when an IC card or the like is placed on the pedestal 107.

[0018] The camera 110 is a high-definition camera device capable of shooting videos or still images. The camera 110 is installed so that images such as the face and actions of the user operating the ATM 100 (hereinafter collectively referred to as "user images") can be captured. The installation location and number of the camera 110 can be arbitrarily set. The camera 110 starts shooting upon a predetermined operation on the ATM 100 by the user.

[0019] As an example, the shooting by the camera 110 may be started upon the insertion operation of the cash card into the card reader 102, or the shooting by the camera 110 may be started upon the reading of the two-dimensional code by the code reader 105. Also, when the ATM 100 is equipped with a human presence sensor (not shown), the shooting by the camera 110 may be started upon the detection of the user by the human presence sensor, and the conditions for starting the shooting can be arbitrarily set and changed.

[0020] FIG. 2 is a diagram showing the main hardware configuration of the information processing device (computer) 200 mounted on the ATM 100, and FIG. 3 is a block diagram showing the functional configuration realized by the ATM 100. As shown in FIG. 2, the information processing device 200 includes a control device 201 having a CPU etc., a storage device 202 having a semiconductor memory etc., an input device 203 consisting of a touch panel etc., a communication device 204 having various communication interfaces, etc., similar to the hardware of a general computer.

[0021] The information processing device 200 realizes functions such as the storage unit 210, transaction detection unit 220, image acquisition unit 230, estimation unit 240, determination unit 250, output unit 260, etc. shown in FIG. 3 by cooperating with various software in which hardware resources such as the control device 201 are stored in the storage device 202.

[0022] The storage unit 210 stores user images acquired by the camera 110, various application programs, databases, etc.

[0023] Figure 4 is an example of the contents of the user management database DB1 stored in the storage unit 210. Various types of information registered in the user management database DB1 may be obtained from, for example, a management server (not shown) that maintains and manages the ATM 100.

[0024] The user management database (user storage unit) DB1 stores account identification information and personal information for each user, linked together. Account identification information includes, for example, some or all of the following: financial institution name, branch name, deposit type, account number, account holder name, PIN, etc. Personal information includes, for example, attribute information such as the user's age, gender, and date of birth, as well as basic information such as name, address, telephone number, email address, and SNS account name, and also some or all of the history information showing the user's past use of ATM 100 (for example, the name of the store where ATM 100 is installed, location information, time information, transaction details, etc.). Personal information may also include user images for each user (for example, a front view or side view of the user). The control device 201 of the information processing device 200 performs new registration and updates (including modification and deletion) of personal information in the user management database DB1.

[0025] The transaction detection unit 220 detects the start of a transaction by the user when the cash card is inserted into the card reader 102 or when the two-dimensional code is read by the code reader 105. When the transaction detection unit 220 detects the start of a transaction by the user, it outputs a detection signal to the image acquisition unit 230. When the card reader 102 or code reader 105 reads the account identification information contained in the card information of the cash card or the account identification information contained in the two-dimensional code, it outputs the personal information (see Figure 4) registered in association with the account identification information to the determination unit 250.

[0026] The image acquisition unit 230, triggered by a detection signal sent from the transaction detection unit 220, starts taking pictures of the user with the camera 110 and acquires the user's image.

[0027] The estimation unit 240 estimates the attribute information of the user who initiated the transaction by analyzing the user image using the built-in artificial intelligence (AI). For example, the estimation unit 240 is equipped with an attribute estimation algorithm that analyzes the user image and estimates attribute information such as the user's gender and age. The estimation unit 240 may also estimate other attribute information, such as physical characteristics (height and build) or nationality. Furthermore, the estimation unit 240 may estimate the user's attribute information not only based on the user image but also on the user's voice.

[0028] The determination unit 250 compares the estimated user attribute information with the user's personal information registered in the user management database DB1, and determines whether or not to permit the transaction in accordance with the user's actions based on the comparison result. As already explained, the user's personal information includes attribute information, basic information, history information, etc.

[0029] Figure 5 is an explanatory diagram illustrating the determination operation performed by the determination unit 250. In the example shown in Figure 5A, the user attribute information estimated by the estimation unit 240 is "70s, female," while the user attribute information included in the personal information (pre-registered attribute information) is "73 years old, female." The determination unit 250 determines that the user is a "regular user" (determination OK in Figure 5) because no predetermined differences are found between the attribute information.

[0030] On the other hand, in the example shown in Figure 5B, the user attribute information estimated by the estimation unit 240 is "20s, male," while the user attribute information included in the personal information (pre-registered attribute information) is "73 years old, female." The determination unit 250 determines that there is a predetermined difference between the attribute information and therefore estimates that the user is a "fake user" (determination NG in Figure 5).

[0031] The conditions for determining whether or not a "predetermined difference" exists (judgment criteria) can be set in advance by the administrator or operator managing and operating the ATM100. For example, one possible condition is that if the age difference is less than or equal to N (N: a natural number) and the genders match, then it is determined that no predetermined difference exists, or if the genders do not match, then it is determined that a predetermined difference exists unconditionally, regardless of the age difference. However, how the judgment criteria are set is at the discretion of the administrator.

[0032] The determination unit 250 estimates whether the user who initiated the transaction is a legitimate user or a fraudulent user, and based on the estimation result, it determines whether or not to permit the transaction by that user. As shown in Figure 5A, if the determination unit 250 estimates that the user is a "legitimate user," it determines that the transaction by that user (in this case, a deposit withdrawal) should be permitted. On the other hand, as shown in Figure 5B, if the determination unit 250 estimates that the user is a "fraudulent user," it determines that the transaction by that user should be withheld. The determination unit 250 notifies the output unit 260 of these determination results.

[0033] When the output unit 260 receives a judgment result from the judgment unit 250, it displays (outputs) a message on the main display unit 101 based on the received judgment result. For example, as shown in Figure 5A, if the determination unit 250 receives a notification that the transaction should be permitted, the output unit 260 displays the message necessary for the user's transaction (for example, "Please enter the withdrawal amount.") on the main display unit 101.

[0034] On the other hand, as shown in Figure 5B, if the output unit 260 receives a notification from the determination unit 250 that the transaction should be suspended, it displays a message on the main display unit 101 indicating that the user's transaction has been suspended (for example, "The transaction has been temporarily suspended for security reasons.") along with a confirmation message requesting the user to provide information necessary for identity verification (for example, "Please use the ATM intercom to complete the identity verification procedure."). Instead of (or in addition to) displaying the confirmation message, the output unit 260 may have the operator managing and operating the ATM 100 contact the user at their contact information (for example, their home or mobile phone number) to verify their identity.

[0035] Furthermore, the output unit 260 may not only display a message based on the judgment result on the main display unit 101, but may also display it on the sub-display unit 108 or the like. It may also output an audio message from a speaker (not shown) or the like.

[0036] As explained above, according to the ATM 100 of this embodiment, attribute information such as the user's age and gender is estimated by analyzing the user's image acquired by the camera 110. Then, the estimated attribute information is compared with the attribute information of a legitimate user that has already been registered, and if a predetermined difference is found between the two, the transaction desired by the user (for example, withdrawal of deposits) is withheld, and a new identity verification is performed. As a result, even if a fraudulent user illegally obtains a legitimate user's cash card or account identification information, the transaction using the ATM 100 will be rejected, making it possible to prevent fraudulent transactions by fraudulent users.

[0037] The following describes the fraud prevention process performed by ATM100, with reference to the diagrams. As a prerequisite, it is assumed that the user management database DB1 contains the account identification information and personal information of each legitimate user, linked together.

[0038] Figure 6 is a flowchart illustrating the process for preventing fraudulent transactions. A user who wishes to withdraw funds from their account (a specified transaction) inserts their cash card into the ATM 100 and enters their PIN and other information. The transaction detection unit 220 detects the start of a transaction by the user when the cash card is inserted into the card reader 102 (step S1). When the transaction detection unit 220 detects the start of a transaction by the user, it outputs a detection signal to the image acquisition unit 230. Meanwhile, when the card reader 102 reads the account identification information from the cash card inserted by the user, it accesses the user management database DB1 and identifies the personal information (i.e., the personal information of a legitimate user) that is registered in association with the account identification information. The card reader 102 outputs the identified personal information to the determination unit 250.

[0039] Based on the detection signal sent from the transaction detection unit 220, the image acquisition unit 230 starts taking pictures of the user with the camera 110 and acquires the user's image (step S2).

[0040] The estimation unit 240 uses its built-in AI to analyze user images and estimate attribute information such as the gender and age of the user who initiated the transaction (step S3).

[0041] The determination unit 250 compares the estimated user attribute information with the personal information of a legitimate user registered in the user management database DB1, and performs a determination process to determine whether or not to permit a transaction corresponding to the user's operation based on the comparison result (step S4). As already explained, the personal information of a legitimate user includes attribute information, basic information, and history information (see Figure 4), and this personal information, including these, is identified and supplied by the card reader unit 102.

[0042] Figure 7 is a flowchart illustrating the determination process performed by the determination unit 250. The determination unit 250 compares the user attribute information estimated by the estimation unit 240 with the attribute information included in the personal information of a regular user to determine whether a predetermined difference exists between each piece of attribute information (step S101). The determination conditions for determining whether a "predetermined difference" exists include, but are not limited to, age difference and gender match / mismatch.

[0043] If the determination unit 250 determines that there are no predetermined differences between the attribute information (step S101; NO), it presumes that the user is a "legitimate user" (step S102). If the determination unit 250 has presumed that the user is a legitimate user, it determines that the transaction by the user (in this case, withdrawal of deposit) should be permitted (step S103), and notifies the output unit 260 of the determination result (step S106).

[0044] On the other hand, if the determination unit 250 determines that there is a predetermined difference between the attribute information (step S101; YES), it presumes that the user is a "fake user" (step S104). If the determination unit 250 presumes that the user is a fake user, it determines that the transaction by the user should be suspended (step S105) and notifies the output unit 260 of the determination result (step S106).

[0045] Returning to Figure 6, when the output unit 260 receives a determination result from the determination unit 250, it displays a message based on the received determination result on the main display unit 101 (step S5). Specifically, if the output unit 260 receives a notification from the determination unit 250 that the transaction should be permitted (see A in Figure 5), it displays the message necessary for the user's transaction on the main display unit 101. The user withdraws funds from the account by following the message displayed on the main display unit 101 and performing operations such as entering the withdrawal amount.

[0046] On the other hand, if the output unit 260 receives notification from the determination unit 250 that the transaction should be suspended (see B in Figure 5), it displays a message on the main display unit 101 indicating that the user's transaction is suspended, along with a confirmation message requesting the user to provide information necessary for identity verification. The user understands that the transaction is suspended and that identity verification is required. If identity verification cannot be performed, the user's transaction is suspended, thereby preventing fraudulent transactions such as withdrawals of deposits from a legitimate user's account by an impersonating user. Furthermore, if a transaction with a user whose identity cannot be verified (an impersonating user) is suspended as described above, the ATM 100 may activate a function (so-called capture function) that takes in the card (such as a cash card) inserted by the impersonating user for the transaction and does not return it to the impersonating user. This makes it possible to prevent further fraudulent transactions by the impersonating user.

[0047] B. Variations In this embodiment, the decision to permit a user's transaction was made based on a comparison between the user's attribute information estimated from the user image and the attribute information of a legitimate user pre-registered in the user management database DB1; however, this is not the only possible approach.

[0048] The determination unit 250 may use not only attribute information but also other information, such as the history information of a legitimate user, to determine whether or not to permit the user's transaction. For example, if a "predetermined difference" is found between the estimated user's attribute information and the attribute information of a legitimate user, and the history information of a legitimate user reveals that the ATM 100 is being used during a time period that has never been used before (for example, around midnight), the determination unit 250 may decide to withhold the user's transaction.

[0049] The conditions (predetermined conditions) regarding transaction history information include not only the time of the transaction, but also, for example, the location information of the ATM 100 being used (e.g., whether it is located in the regular user's residential area) and the frequency of use of the ATM 100 (e.g., whether the regular user has used it multiple times in the past), but are not limited to these. In this way, a combination of conditions regarding attribute information and conditions regarding transaction history information may be used to determine whether or not to permit a user's transaction.

[0050] It should be noted that the present invention is not limited to the embodiments described above, and can be implemented in various other forms without departing from the spirit of the invention. For this reason, the above embodiments are merely illustrative in all respects and should not be interpreted restrictively. For example, the order of each processing step described above can be arbitrarily changed or executed in parallel, as long as there is no inconsistency in the processing content. [Explanation of Symbols]

[0051] 100...ATM, 200...Information Processing Device, 201...Control Device, 202...Storage Device, 203...Input Device, 204...Communication Device, 210...Storage Unit, 220...Transaction Detection Unit, 230...Image Acquisition Unit, 240...Estimation Unit, 250...Determination Unit, 260...Output Unit, DB1...User Management Database

Claims

1. An automated trading system that performs transactions in response to user operations, An image acquisition unit that acquires the user's image, An estimation unit that analyzes the user's image and estimates the user's attribute information, A user storage unit that stores attribute information of the user who has been pre-registered, A determination unit compares the estimated user attribute information with the pre-registered user attribute information and determines whether or not to perform a transaction in accordance with the user's actions based on the comparison result. An automated trading device equipped with the following features.

2. The system further comprises a transaction detection unit that detects transaction operations for the user to perform automated transactions, The automated trading device according to claim 1, wherein the image acquisition unit starts acquiring an image of the user when the trading operation is detected.

3. The automated trading device according to claim 1 or 2, wherein the determination unit compares the estimated user attribute information with the pre-registered user attribute information and determines that a transaction corresponding to the user's operation should be reserved if a predetermined difference is found between the two.

4. The user storage unit further stores transaction history information related to the user, The automated trading device according to claim 3, wherein the determination unit determines that a predetermined difference is found between the two and the historical information satisfies predetermined conditions, and that the transaction corresponding to the user's operation should be reserved.

5. The system further comprises an output unit that outputs the result of the determination, The automated trading device according to claim 3, wherein the output unit requests the user to provide information necessary for identity verification when the determination unit determines that the transaction corresponding to the user's operation should be reserved.

6. A computer that performs transactions in response to user input, The image acquisition step involves acquiring an image of the user, An estimation step of analyzing the user's image and estimating the user's attribute information, A program for executing a determination step of comparing estimated user attribute information with user attribute information pre-registered in the user storage unit, and determining whether or not to perform a transaction in accordance with the user's operation based on the comparison result.

Images