ATM withdrawal method and device, electronic equipment, storage medium and product

Abstract

The embodiment of the invention provides an ATM withdrawal method and device, electronic equipment, a storage medium and a product, and relates to the field of financial science and technology. The method comprises the steps of obtaining current transaction information corresponding to a bank card, and determining whether a current transaction is an abnormal transaction according to the current transaction information; if the current transaction is the abnormal transaction, determining whether a user of the bank card is a holder of the bank card; if the user of the bank card is the owner of the bank card, micro-expression analysis is carried out on the user, an analysis result is obtained, and if the analysis result indicates that the user is in an abnormal state, micro-expression analysis is carried out on the user again after a first preset duration; the latest analysis result indicates that the user is in an abnormal state or the number of times of micro-expression analysis exceeds the preset number of times; and if the latest analysis result indicates that the user is in the normal state, the current transaction is carried out according to the current transaction information, so that the security of the transaction is greatly improved, and the possibility of misjudgment and false alarm is reduced.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to an ATM withdrawal method, device, electronic device, storage medium and product. Background Art

[0002] At an ATM (Automated Teller Machine), withdrawing money using a bank card and a password is a common operation mode, but this operation method still has multiple security risks.

[0003] For example, users queuing at an ATM or nearby people may steal their PINs through direct observation or reflective mirrors. Especially in crowded public places (such as shopping malls and train stations), it is difficult to completely shield the user's PIN when entering, resulting in lower security. Once the PIN is stolen, the thief may directly obtain the user's bank card through pickpocketing or robbery, or use "cloning" devices (such as card readers) to copy the user's bank card information and create counterfeit cards.

[0004] After the thief obtains the password, bank card or counterfeit card, he withdraws funds directly from the ATM, resulting in the theft of bank account funds. Summary of the Invention

[0005] The present application provides an ATM withdrawal method, device, electronic device, storage medium and product for improving the security of transactions using bank cards at ATMs and reducing the risk of bank account funds being stolen.

[0006] In a first aspect, the present application provides an ATM withdrawal method, which is applied to an ATM, and the method comprises:

[0007] Obtaining current transaction information corresponding to the bank card, and determining whether the current transaction is an abnormal transaction based on the current transaction information;

[0008] If the current transaction is an abnormal transaction, determining whether the user of the bank card is the holder of the bank card;

[0009] If the user of the bank card is the holder of the bank card, micro-expression analysis is performed on the user and an analysis result is obtained. If the analysis result indicates that the user is in an abnormal state, micro-expression analysis is performed on the user again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number;

[0010] If the latest analysis result indicates that the user is in a normal state, the current transaction is performed according to the current transaction information.

[0011] In a second aspect, the present application provides an ATM cash withdrawal device, which is applied to the ATM, and the device includes:

[0012] An acquisition module is used to obtain current transaction information corresponding to a bank card and determine whether the current transaction is an abnormal transaction based on the current transaction information;

[0013] a determination module, configured to determine whether the user of the bank card is the holder of the bank card if the current transaction is an abnormal transaction;

[0014] an analysis module configured to, if the user of the bank card is the holder of the bank card, perform micro-expression analysis on the user and obtain an analysis result; if the analysis result indicates that the user is in an abnormal state, perform micro-expression analysis on the user again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number;

[0015] The transaction module is configured to perform a current transaction according to current transaction information if the latest analysis result indicates that the user is in a normal state.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0017] at least one processor; and

[0018] a memory communicatively coupled to the at least one processor;

[0019] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the electronic device to execute the method described in any one of the above aspects.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the method described in any one of the above aspects is implemented.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which implements the method described in any of the above aspects when executed by a processor.

[0022] The ATM withdrawal method, device, electronic device, storage medium and product provided by the present application obtain the current transaction information corresponding to the bank card, and determine whether the current transaction is an abnormal transaction based on the current transaction information; if the current transaction is an abnormal transaction, determine whether the user of the bank card is the holder of the bank card; if the user of the bank card is the holder of the bank card, perform micro-expression analysis on the user and obtain an analysis result; if the analysis result indicates that the user is in an abnormal state, perform micro-expression analysis on the user again after a first preset time period until the latest analysis result indicates that the user is in an abnormal state. The user is in a normal state or the number of micro-expression analyses performed exceeds a preset number; if the latest analysis result indicates that the user is in a normal state, the current transaction is performed according to the current transaction information. In this way, after identifying an abnormal transaction, the ATM first confirms whether the user is the holder. If the user is the holder, the holder's emotional state is evaluated through micro-expression analysis technology, and it can be identified whether the holder is in a state of tension, anxiety, coercion or other abnormal state. In short, this application combines abnormal transaction detection, identity authentication and micro-expression analysis, provides a multi-level verification mechanism, greatly improves the security of transactions, and reduces the possibility of misjudgment and false alarm. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0024] Figure 1 An application scenario diagram provided for an embodiment of the present application;

[0025] Figure 2 A flowchart of an ATM withdrawal method provided in an embodiment of the present application;

[0026] Figure 3 A flowchart of another ATM withdrawal method provided in an embodiment of the present application;

[0027] Figure 4 A schematic diagram of the structure of an ATM cash withdrawal device provided in an embodiment of the present application;

[0028] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application.

[0029] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0030] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0031] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] In addition, this application involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and the use of artificial intelligence technology for automated decision-making, and a technical solution for making decisions that have a significant impact on personal rights and interests based on the results of automated decision-making. The application provides users with corresponding operation entrances for users to choose to agree or reject the results of automated decision-making; if the user chooses to reject, the expert decision-making process will be entered.

[0033] It should be noted that the ATM withdrawal method, device, electronic device, storage medium and product provided in this application can be used in the field of financial technology, and can also be used in any field other than financial technology. The application field of the ATM withdrawal method, device, electronic device, storage medium and product in this application is not limited.

[0034] Withdrawing money from an ATM using a bank card and password is a common operation mode, but this method does have multiple security risks, especially in public places.

[0035] In front of the ATM, users waiting in line or people around can steal the password by directly observing the user entering the password. In addition, reflective surfaces near the ATM, such as glass, metal plates, mobile phone screens, etc., may reflect the user's password input action, allowing thieves to peek at the password from different angles. Some criminals may also install miniature cameras near the ATM to secretly record the process of users entering the password, and these devices are difficult for users to detect.

[0036] After the password is stolen, the thief may directly obtain the user's bank card through pickpocketing, robbery, etc., or may use a "cloning" device (such as a card reader) to copy the user's bank card information to make a counterfeit card.

[0037] After the thief obtains the password, bank card or counterfeit card, he withdraws funds directly from the ATM, resulting in the theft of bank account funds.

[0038] In view of this, the present application provides an ATM withdrawal method. First, the current transaction information corresponding to a bank card is obtained, and based on the current transaction information, whether the current transaction is an abnormal transaction is determined. If the current transaction is an abnormal transaction, the bank card user is determined to be the bank card holder. If the bank card user is the bank card holder, the user's micro-expression analysis is performed and an analysis result is obtained. If the analysis result indicates that the user is in an abnormal state, the user's micro-expression analysis is performed again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number. If the latest analysis result indicates that the user is in a normal state, the current transaction is performed based on the current transaction information. In this way, after identifying an abnormal transaction, the ATM first confirms whether the user is the holder. If the user is the holder, the micro-expression analysis technology is used to assess the holder's emotional state, and can identify whether the holder is in a state of tension, anxiety, coercion, or other abnormal state. In summary, the present application combines abnormal transaction detection, identity verification, and micro-expression analysis to provide a multi-level verification mechanism, greatly improving transaction security and reducing the possibility of misjudgment and false alarms.

[0039] Figure 1 The application scenario diagram provided in the embodiment of this application is as follows: Figure 1 As shown, after the user inserts the bank card into the ATM, he enters the bank card password on the user interface to enter the transaction interface, enters the current transaction information and clicks the confirmation button. The ATM obtains the current transaction information and determines whether the current transaction is an abnormal transaction based on the current transaction information. If it is not an abnormal transaction, the subsequent transaction steps, such as deduction steps, are performed based on the current transaction information. If it is an abnormal transaction, it is determined whether the user of the bank card is the holder of the bank card. If the user is the holder, micro-expression analysis is continued until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds the preset number. If the latest analysis result indicates that the user is in a normal state, the subsequent transaction steps are performed according to the current transaction information. If the number of micro-expression analyses exceeds the preset number, it is switched to manual review, and whether to terminate the transaction is determined based on the result of the manual review.

[0040] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0041] Figure 2 This is a flowchart of an ATM withdrawal method provided in an embodiment of the present application. The execution subject of this embodiment can be any device with data processing function. This application is specifically described with the execution subject being an ATM. Figure 2 As shown, the specific steps of this method are as follows:

[0042] Step 201: Obtain current transaction information corresponding to a bank card, and determine whether the current transaction is an abnormal transaction based on the current transaction information.

[0043] Among them, the current transaction information includes: transaction time, transaction amount, transaction object, transaction location and transaction notes, etc.

[0044] Transaction time refers to the specific moment when the transaction occurs; transaction amount refers to the specific amount of the transaction; transaction object refers to the other party who conducts the transaction with the bank card, and the transaction object can be a merchant, a company or an individual; transaction location: the geographical location where the transaction occurs, that is, the location of the ATM; some transactions will have transaction notes, which usually explain the purpose of the transaction.

[0045] Specifically, the user of the bank card inserts the bank card into the ATM, enters the password corresponding to the bank card in the password input box on the ATM user interface, enters the transaction interface, enters the current transaction information, and clicks the confirmation button after entering. The ATM obtains the current transaction information corresponding to the bank card and determines whether the current transaction is an abnormal transaction based on the current transaction information.

[0046] Optionally, determining whether the current transaction is an abnormal transaction based on the current transaction information includes:

[0047] According to the current transaction information and the historical transaction information of the bank card, whether the current transaction is an abnormal transaction is determined by using a trained abnormal transaction recognition model.

[0048] The historical transaction information is the transaction information generated by transactions involving bank cards through any ATM within a preset time period in the past.

[0049] The abnormal transaction identification model can be any model that can be obtained through training and can determine whether the current transaction is an abnormal transaction based on current transaction information and historical transaction information. Exemplarily, the abnormal transaction identification model can be a large language model (LLM), a neural network model, etc.

[0050] Specifically, the ATM obtains the historical transaction information corresponding to the bank card, inputs the current transaction information and the historical transaction information into a trained abnormal transaction identification model, and the abnormal transaction identification model determines whether the current transaction is an abnormal transaction. This application does not limit the form of the output result of the abnormal transaction identification model.

[0051] In an optional implementation, a simple Boolean value may be directly output, for example, when the current transaction is judged to be an abnormal transaction, true is output; when it is judged to be a normal transaction, false is output.

[0052] In another optional implementation, a numerical value is output to reflect the degree of abnormality, for example, a numerical value between 0 and 1 is output. When the numerical value exceeds a set threshold (such as 0.5), it is determined to be an abnormal transaction, and when the numerical value is lower than the threshold, it is a normal transaction.

[0053] In this way, the trained abnormal transaction recognition model determines whether the current transaction is an abnormal transaction based on the current transaction information and the historical transaction information of the bank card, which can improve the accuracy of the determination.

[0054] Step 202: If the current transaction is an abnormal transaction, determine whether the user of the bank card is the holder of the bank card.

[0055] Among them, the user refers to the person who currently uses the bank card for transactions, and the holder refers to the individual or organization who applies for a bank card from a bank or other financial institution through legal procedures, and after review and approval, opens a bank card account with his or her own identity information and holds the bank card.

[0056] Specifically, if the ATM determines that the current transaction is an abnormal transaction, it determines whether the user of the bank card is the holder of the bank card by verifying the identity of the user.

[0057] This application does not limit the specific method of verifying the user's identity.

[0058] In one example, the user's identity can be verified through facial recognition.

[0059] In another example, the user's identity may be verified by fingerprint recognition.

[0060] In yet another example, the user's identity may be verified by answering private questions.

[0061] Optionally, if the current transaction is an abnormal transaction, determining whether the user of the bank card is the holder of the bank card includes:

[0062] If the current transaction is an abnormal transaction, obtaining the user's iris information;

[0063] Determine whether the user of the bank card is the holder of the bank card based on the iris information.

[0064] Specifically, if the ATM determines that the current transaction is an abnormal transaction, it uses the camera on the ATM to collect the user's iris image, and can process the collected iris image, including iris positioning (determining the position of the inner circle, outer circle and quadratic curve in the image), iris image normalization (adjusting the size of the iris in the image to a fixed size) and image enhancement (improving the recognition rate of iris information in the image), etc.

[0065] After the preprocessing is completed, a preprocessed iris image is obtained. The server then extracts distinctive feature points from the preprocessed iris image, such as spots, filaments, crowns, stripes and other detailed features, and then encodes each feature point separately to obtain the feature information corresponding to each feature point. The iris information includes the feature information corresponding to each feature point.

[0066] The acquired iris information is compared with the pre-stored iris information of the cardholder to obtain a comparison result. Based on the comparison result, it is determined whether the bank card user is the cardholder. Common comparison algorithms include feature matching algorithms, cosine similarity, cross entropy, etc. The feature matching algorithm can be SIFT (Scale-Invariant Feature Transform) or SURF (Speeded-Up Robust Features). This application does not limit the specific form of the comparison algorithm.

[0067] The pre-stored iris information of the holder is obtained in the following way: the holder can collect the iris image when entering information at the bank for the first time, or the holder can collect the iris image while handling business at the counter through supplementary collection. After the collection is completed, the initial iris image is subjected to the same preprocessing, feature point extraction and feature point encoding operations as mentioned above to obtain the holder's iris information and store it.

[0068] By using iris information to verify the identity of bank card holders, transaction security can be significantly improved. Iris recognition is a highly accurate biometric technology whose uniqueness and stability make it difficult to forge or tamper with, effectively preventing fraud and identity theft. Furthermore, by accurately identifying the user's identity in unusual transactions, potential fraud can be prevented in a timely manner, reducing financial losses for banks and cardholders.

[0069] Step 203: If the user of the bank card is the holder of the bank card, a micro-expression analysis is performed on the user to obtain an analysis result. If the analysis result indicates that the user is in an abnormal state, the micro-expression analysis is performed on the user again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number.

[0070] Micro-expressions refer to changes in facial expressions that occur within a short period of time (usually 1 / 25 to 1 / 15 of a second) and often reflect a person's true emotional state. By analyzing these micro-expressions, it's possible to determine whether the user is in an abnormal state.

[0071] Abnormal states can refer to emotions such as tension, anxiety, or fear, which may indicate that the user is conducting transactions under unusual circumstances or facing some kind of pressure or threat. Abnormal states can also refer to painful emotions, which may indicate that the user has a sudden illness.

[0072] Specifically, when the ATM determines that the bank card user is the bank card holder, it performs a micro-expression analysis on the user and obtains an analysis result. If the analysis result indicates that the user is in an abnormal state, the user's micro-expression analysis is performed again after a first preset period of time after the analysis result is obtained. If the analysis result still indicates that the user is in an abnormal state, the user's micro-expression analysis is performed again after a first preset period of time after the analysis result is obtained again. This continues until the latest analysis result indicates that the user is in a normal state, or the number of micro-expression analyses performed exceeds a preset number, at which point the micro-expression analysis of the user is stopped. If the latest analysis result indicates that the user is in a normal state, it indicates that the user's emotional state has returned to normal; if the number of micro-expression analyses performed exceeds the preset number, it indicates that the user's emotional state remains abnormal, and the micro-expression analysis of the user is stopped to prevent an infinite loop.

[0073] Optionally, this application does not limit the analysis method of micro-expressions.

[0074] In an optional implementation, a machine learning algorithm (such as a support vector machine, a convolutional neural network, etc.) can be used to automatically identify and classify micro-expressions by training a model.

[0075] In another optional implementation, a deep learning model, such as a convolutional neural network (CNN), can be trained with a large amount of labeled data to automatically identify and classify micro-expressions.

[0076] In another optional implementation, since micro-expressions usually occur in a very short period of time, time series analysis methods can help capture and analyze these rapid changes. For example, recursive neural networks such as long short-term memory networks (LSTM) can be used to understand the relationship between facial expressions and time, and then classify micro-expressions.

[0077] Optionally, the ATM withdrawal method provided by this application also includes:

[0078] If the number of micro-expression analyses exceeds a preset number, a video call is initiated between the reviewer and the user, so that the reviewer can determine whether the user is in an abnormal state and the type of abnormality corresponding to the abnormal state;

[0079] If the reviewer determines that the user is in an abnormal state, the user performs a preset operation corresponding to the abnormality type according to the abnormality type;

[0080] If the auditor determines that the user is in a normal state, the current transaction is carried out according to the current transaction information.

[0081] The exception type is a specific classification of the user's abnormal status, which may include but is not limited to the following:

[0082] Nervous / Anxious: The user appears uneasy or nervous.

[0083] Suspected fraud: The user's behavior or answers are inconsistent with normal circumstances and may indicate fraudulent intent.

[0084] Duress: Users may be forced to conduct transactions.

[0085] Specifically, if the number of micro-expression analyses exceeds a preset number, the ATM initiates a video call between the user and the auditor. The user can use the camera built into the ATM to video chat with the auditor. After the call starts, the auditor directly observes the user's behavior, facial expressions, movements, etc. to determine whether the user is in an abnormal state. When the user is in an abnormal state, it is also necessary to determine the abnormal type corresponding to the abnormal state. If the auditor determines that the user is in a normal state, he clicks the button corresponding to the normal state on the interactive interface of the auditor's corresponding client. The auditor's corresponding client sends the information that the auditor determines that the user is in a normal state to the ATM. After receiving the information, the ATM completes the subsequent steps of the transaction, such as deduction, confirmation, etc., based on the current transaction information.

[0086] If the auditor determines that the user is in an abnormal state, the auditor enters or filters the abnormal type corresponding to the abnormal state on the interactive interface of the client corresponding to the auditor, and clicks the button corresponding to the abnormal state on the interactive interface. The client corresponding to the auditor sends the information that the auditor determines that the user is in an abnormal state and the abnormal type corresponding to the abnormal state to the ATM. After receiving the information, the ATM performs the preset operation corresponding to the abnormal type according to the received abnormal type.

[0087] In this way, micro-expression analysis may be affected by factors such as the environment and light. Manual review can reduce the probability of false alarms and improve the accuracy of anomaly detection. Manual review can also more accurately identify the specific type of anomaly, thereby taking more targeted measures.

[0088] Optionally, the abnormality types include: being coerced, sudden illness; the preset operations corresponding to coercion are: silent alarm, and conducting the current transaction based on the current transaction information; the preset operations corresponding to sudden illness are: notifying the staff of the bank branch closest to the ATM, and calling the emergency number, and playing pre-recorded voice content after the call is connected, and the pre-recorded voice content includes: the address of the ATM.

[0089] Among them, silent alarm is a security measure used to sound an alarm without attracting attention or alerting potential threats. Silent alarm is usually used in emergency situations where it is necessary to request help secretly or covertly. The purpose of silent alarm is to notify security personnel or law enforcement agencies to take action without exposing the alarm or escalating the tension.

[0090] Specifically, when the abnormality type is duress, the corresponding preset operation is: the ATM silently alarms, and then completes the subsequent steps of the transaction according to the current transaction information, such as deduction, confirmation, etc.

[0091] When the abnormality type is a sudden illness, the corresponding preset operation is: the ATM notifies the staff of the bank branch closest to the ATM, and the ATM dials the emergency number, such as 120. After the emergency call is connected, a pre-recorded voice content is played. The pre-recorded voice content includes the address of the ATM, the name and age of the bank card user (in this case, the user is the holder), etc.

[0092] Optionally, when the abnormality type is a sudden illness, the auditor can also directly call the emergency number and notify the staff of the bank branch closest to the ATM.

[0093] Optionally, the ATM may also notify the staff of the bank branch closest to the ATM to call an emergency number.

[0094] This way, in the event of duress, the ATM can not only sound the alarm but also continue the current transaction, avoiding the duressor's suspicion and ensuring that security personnel are aware of the situation and are taking action. In the event of an illness, the ATM can automatically dial emergency services and play a pre-recorded voice message, ensuring that emergency personnel can quickly obtain necessary information (such as the ATM's address), thereby speeding up rescue efforts.

[0095] Step 204: If the latest analysis result indicates that the user is in a normal state, the current transaction is performed according to the current transaction information.

[0096] Specifically, if the latest analysis result indicates that the user is in a normal state, the subsequent steps of the transaction, such as deduction and confirmation, are completed according to the current transaction information.

[0097] The ATM withdrawal method provided by the present application obtains current transaction information corresponding to a bank card and determines whether the current transaction is an abnormal transaction based on the current transaction information. If the current transaction is an abnormal transaction, it determines whether the user of the bank card is the holder of the bank card. If the user of the bank card is the holder of the bank card, a micro-expression analysis is performed on the user to obtain an analysis result. If the analysis result indicates that the user is in an abnormal state, the micro-expression analysis is performed on the user again after a first preset time period until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number. If the latest analysis result indicates that the user is in a normal state, the current transaction is performed based on the current transaction information. In this way, after identifying an abnormal transaction, the ATM first confirms whether the user is the holder. If so, the micro-expression analysis technology is used to assess the holder's emotional state, and can identify whether the holder is in a state of tension, anxiety, coercion, or other abnormal state. In short, the present application combines abnormal transaction detection, identity verification, and micro-expression analysis to provide a multi-level verification mechanism, greatly improving transaction security and reducing the possibility of misjudgment and false alarms.

[0098] Optionally, if the latest analysis result indicates that the user is in a normal state, performing the current transaction according to the current transaction information includes:

[0099] If the latest analysis result indicates that the user is in a normal state, a risk prompt box will pop up on the user interface;

[0100] Acquiring eye movement data of the user, and determining the user's gaze point and gaze time based on the eye movement data;

[0101] When the user gazes at the risk prompt box for a period exceeding a second preset period, the confirmation button becomes available; in response to clicking the confirmation button, the current transaction is performed according to the current transaction information;

[0102] Timing starts from the acquisition of the eye movement data. If it exceeds a third preset time, a prompt box pops up at a preset position of the user interface, and the prompt box is used to instruct the user to read the risk prompt box, wherein the prompt box does not cover the risk prompt box.

[0103] For example, the content in the risk warning box may be: This transaction is inconsistent with your usual trading habits. We have detected that there may be an abnormality in this transaction. Please confirm whether to continue the transaction.

[0104] The confirmation button can be located in the risk warning box or outside the risk warning box, and this application does not limit this.

[0105] Specifically, if the latest analysis results indicate that the user is in a normal state, a risk warning box will pop up on the ATM user interface, the user's eye movement data will be collected through the camera on the ATM, and the user's gaze point and gaze time will be determined based on the user's eye movement data.

[0106] If the user gazes at the area within the risk warning box for a period exceeding a second preset time, the confirmation button remains in an unavailable state. When the confirmation button is in the unavailable state, the ATM does not perform any action when the user clicks the confirmation button. If the user gazes at the area within the risk warning box for a period exceeding the second preset time, the confirmation button becomes available. When the confirmation button is available, the ATM completes subsequent transaction steps, such as debiting and confirming, based on the current transaction information in response to the user clicking the confirmation button. A timer can be started by acquiring the user's eye movement data from the ATM. If the timer exceeds a third preset time, a prompt box can be popped up at a preset location on the user interface. The prompt box can be used to instruct the user to read the risk warning box. The prompt box can be located in a non-overlapping position with the risk warning box, i.e., the prompt box does not cover the risk warning box; or the prompt box partially covers the risk warning box but does not cover the content of the risk warning box. During the prompt box pop-up process, the ATM continues to acquire the user's eye movement data and determines the user's gaze point and gaze duration based on the eye movement data. The third preset time period is greater than the second preset time period.

[0107] Exemplarily, the content of the prompt box may be: Please carefully read the risk warning information on the screen.

[0108] This combination of eye tracking and confirmation button design provides a double-confirmation mechanism, ensuring users fully understand the risks before conducting transactions, effectively mitigating security risks caused by negligence or misoperation. If the user fails to read the warning box within a third preset time, the ATM will pop up an additional warning box at a preset location on the user interface, reminding the user to read the risk warning, further ensuring that users do not overlook important security information.

[0109] Optionally, the ATM withdrawal method provided by this application also includes:

[0110] If the user of the bank card is not the holder of the bank card, a verification code is sent to the holder's mobile phone and an operation prompt box pops up, wherein the operation prompt box is used to instruct the user to contact the holder by phone to obtain the verification code and enter the verification code into a preset location;

[0111] Obtain the verification code entered by the user, and if the verification code is correct, perform the current transaction according to the current transaction information.

[0112] Specifically, if the user of the bank card is not the holder of the bank card, the ATM obtains the mobile phone number reserved by the holder at the bank, sends the verification code to the holder's mobile phone and pops up an operation prompt box on the user interface. The operation prompt box can instruct the user to contact the holder by phone, obtain the verification code from the holder, and enter the verification code into a preset position on the user interface, or prompt the user to directly enter the verification code and press # to confirm.

[0113] After seeing the content in the operation prompt box, the user calls the holder to ask for the verification code and enters the verification code into the ATM. The ATM receives the verification code entered by the user. If the verification code is correct, it completes the subsequent steps of the transaction based on the current transaction information, such as deduction and confirmation. If the verification code is incorrect, the transaction is terminated.

[0114] For example, the content of the operation prompt box may be: The holder of this card needs to authorize this transaction. The verification code has been sent to the holder's registered mobile phone number. Please contact the holder to obtain the verification code and enter the verification code into the specified location below to continue the transaction.

[0115] In this way, by sending the verification code to the holder's mobile phone, it ensures that only the holder or someone authorized by the holder can complete the transaction. The two-factor authentication mechanism effectively prevents unauthorized transactions and reduces transaction risks.

[0116] Optionally, if the verification code is correct, proceed with the current transaction based on the current transaction information, including:

[0117] If the verification code is correct, the image data of the user is collected and stored; wherein the image data includes the front face image data of the user;

[0118] After the collection is completed, the current transaction is carried out according to the current transaction information.

[0119] Among them, image data may include photos, videos, etc.

[0120] Specifically, if the ATM determines that the verification code is correct, it uses the camera on the ATM to collect and store the user's image data. After the collection is completed, the subsequent steps of the transaction, such as deduction and confirmation, are completed according to the current transaction information.

[0121] In this way, image data, as part of transaction records, can provide strong evidence in subsequent investigations and help identify and track suspicious activities.

[0122] Figure 3A flowchart of another ATM withdrawal method provided in an embodiment of the present application, wherein the ATM obtains current transaction information and historical transaction information, and determines whether the current transaction is an abnormal transaction based on the current transaction information and the historical transaction information of the bank card using a trained abnormal transaction recognition model. If the current transaction is not an abnormal transaction, subsequent transaction steps are continued based on the current transaction information. If the current transaction is an abnormal transaction, the user's iris information is obtained; based on the iris information, it is determined whether the bank card user is the bank card holder. If the user of the bank card is the holder of the bank card, a micro-expression analysis is performed on the user and an analysis result is obtained. If the analysis result indicates that the user is in an abnormal state, the micro-expression analysis is performed on the user again after a first preset time period until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number; if the latest analysis result indicates that the user is in a normal state, the current transaction is performed according to the current transaction information. If the number of micro-expression analyses exceeds a preset number, it is switched to manual review. If the user of the bank card is not the holder of the bank card, a verification code is sent to the holder's mobile phone and an operation prompt box pops up, wherein the operation prompt box is used to instruct the user to contact the holder by phone to obtain the verification code and enter the verification code into a preset location; the verification code entered by the user is obtained. If the verification code is correct, the current transaction is performed according to the current transaction information. If the verification code is incorrect, the current transaction is terminated.

[0123] Corresponding to the above-mentioned ATM withdrawal method, the present application embodiment also provides an ATM withdrawal device, Figure 4 This is a schematic diagram of the structure of an ATM cash withdrawal device provided in an embodiment of the present application. Figure 4 As shown, the cash withdrawal device of the ATM includes:

[0124] The acquisition module 401 is used to obtain the current transaction information corresponding to the bank card and determine whether the current transaction is an abnormal transaction based on the current transaction information;

[0125] Determination module 402, for determining whether the user of the bank card is the holder of the bank card if the current transaction is an abnormal transaction;

[0126] Analysis module 403, configured to, if the user of the bank card is the holder of the bank card, perform micro-expression analysis on the user and obtain an analysis result; if the analysis result indicates that the user is in an abnormal state, perform micro-expression analysis on the user again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number;

[0127] The transaction module 404 is configured to perform a current transaction based on the current transaction information if the latest analysis result indicates that the user is in a normal state.

[0128] Optionally, when determining whether the current transaction is an abnormal transaction based on the current transaction information, the acquisition module 401 is specifically configured to:

[0129] According to the current transaction information and the historical transaction information of the bank card, whether the current transaction is an abnormal transaction is determined by using a trained abnormal transaction recognition model.

[0130] Optionally, the determination module 402 is specifically configured to:

[0131] If the current transaction is an abnormal transaction, obtaining the user's iris information;

[0132] Determine whether the user of the bank card is the holder of the bank card based on the iris information.

[0133] Optionally, the analysis module 403 is further configured to:

[0134] If the number of micro-expression analyses exceeds a preset number, a video call is initiated between the reviewer and the user, so that the reviewer can determine whether the user is in an abnormal state and the type of abnormality corresponding to the abnormal state;

[0135] If the reviewer determines that the user is in an abnormal state, the user performs a preset operation corresponding to the abnormality type according to the abnormality type;

[0136] If the auditor determines that the user is in a normal state, the current transaction is carried out according to the current transaction information.

[0137] Optionally, the abnormality types include: being coerced, sudden illness; the preset operations corresponding to coercion are: silent alarm, and conducting the current transaction based on the current transaction information; the preset operations corresponding to sudden illness are: notifying the staff of the bank branch closest to the ATM, and calling the emergency number, and playing pre-recorded voice content after the call is connected, and the pre-recorded voice content includes: the address of the ATM.

[0138] Optionally, the transaction module 404 is specifically configured to:

[0139] If the latest analysis result indicates that the user is in a normal state, a risk prompt box will pop up on the user interface;

[0140] Acquiring eye movement data of the user, and determining the user's gaze point and gaze time based on the eye movement data;

[0141] When the user gazes at the risk prompt box for a period exceeding a second preset period, the confirmation button becomes available; in response to clicking the confirmation button, the current transaction is performed according to the current transaction information;

[0142] Timing starts from the acquisition of the eye movement data. If it exceeds a third preset time, a prompt box pops up at a preset position of the user interface, and the prompt box is used to instruct the user to read the risk prompt box, wherein the prompt box does not cover the risk prompt box.

[0143] Optionally, the analysis module 403 is further configured to:

[0144] If the user of the bank card is not the holder of the bank card, a verification code is sent to the holder's mobile phone and an operation prompt box pops up, wherein the operation prompt box is used to instruct the user to contact the holder by phone to obtain the verification code and enter the verification code into a preset location;

[0145] Obtain the verification code entered by the user, and if the verification code is correct, perform the current transaction according to the current transaction information.

[0146] Optionally, when the verification code is correct and the current transaction is performed according to the current transaction information, the analysis module 403 is specifically configured to:

[0147] If the verification code is correct, the image data of the user is collected and stored; wherein the image data includes the front face image data of the user;

[0148] After the collection is completed, the current transaction is carried out according to the current transaction information.

[0149] The specific implementation principles and effects of the ATM withdrawal device provided in the embodiment of the present application can be found in the aforementioned embodiment and will not be repeated here.

[0150] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.

[0151] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that the at least one processor 501 performs the above method.

[0152] The specific implementation process of the processor 501 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0153] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0154] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0155] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0156] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0157] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0158] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0159] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0160] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0161] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0162] It should be understood that the above-described device embodiments are merely illustrative, and the device of the present application may also be implemented in other ways. For example, the division of units / modules in the above-described embodiments is merely a logical functional division, and actual implementations may employ other division methods. For example, multiple units, modules, or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0163] In addition, unless otherwise specified, the functional units / modules in the various embodiments of the present application may be integrated into a single unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The aforementioned integrated units / modules may be implemented in the form of hardware or software program modules.

[0164] If the integrated unit / module is implemented in hardware, the hardware may be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor may be any appropriate hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0165] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0166] In the above embodiments, the description of each embodiment has its own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined in any way. To keep the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0168] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A cash withdrawal method for an ATM, applied to an ATM, characterized in that: The method comprises: Obtaining current transaction information corresponding to the bank card, and determining whether the current transaction is an abnormal transaction based on the current transaction information; If the current transaction is an abnormal transaction, determining whether the user of the bank card is the holder of the bank card; If the user of the bank card is the holder of the bank card, micro-expression analysis is performed on the user and an analysis result is obtained. If the analysis result indicates that the user is in an abnormal state, micro-expression analysis is performed on the user again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number; If the latest analysis result indicates that the user is in a normal state, the current transaction is performed according to the current transaction information.

2. The method according to claim 1, characterized in that Determining whether the current transaction is an abnormal transaction based on the current transaction information includes: According to the current transaction information and the historical transaction information of the bank card, whether the current transaction is an abnormal transaction is determined by using a trained abnormal transaction recognition model.

3. The method according to claim 1, characterized in that If the current transaction is an abnormal transaction, determining whether the user of the bank card is the holder of the bank card includes: If the current transaction is an abnormal transaction, obtaining the user's iris information; Determine whether the user of the bank card is the holder of the bank card based on the iris information.

4. The method according to claim 1, wherein The method further comprises: If the number of micro-expression analyses exceeds a preset number, a video call is initiated between the reviewer and the user, so that the reviewer can determine whether the user is in an abnormal state and the type of abnormality corresponding to the abnormal state; If the reviewer determines that the user is in an abnormal state, the user performs a preset operation corresponding to the abnormality type according to the abnormality type; If the auditor determines that the user is in a normal state, the current transaction is carried out according to the current transaction information.

5. The method according to claim 4, characterized in that The abnormality types include: being coerced and sudden illness; the preset operations corresponding to coercion are: silent alarm and conducting the current transaction based on the current transaction information; the preset operations corresponding to sudden illness are: notifying the staff of the bank branch closest to the ATM, calling the emergency number, and playing pre-recorded voice content after the call is connected, and the pre-recorded voice content includes: the address of the ATM.

6. The method according to claim 1, characterized in that If the latest analysis result indicates that the user is in a normal state, the current transaction is performed according to the current transaction information, including: If the latest analysis result indicates that the user is in a normal state, a risk prompt box will pop up on the user interface; Acquiring eye movement data of the user, and determining the user's gaze point and gaze time based on the eye movement data; When the user gazes at the risk prompt box for a period exceeding a second preset period, the confirmation button becomes available; in response to clicking the confirmation button, the current transaction is performed according to the current transaction information; Timing starts from the acquisition of the eye movement data. If it exceeds a third preset time, a prompt box pops up at a preset position of the user interface, and the prompt box is used to instruct the user to read the risk prompt box, wherein the prompt box does not cover the risk prompt box.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: If the user of the bank card is not the holder of the bank card, a verification code is sent to the holder's mobile phone and an operation prompt box pops up, wherein the operation prompt box is used to instruct the user to contact the holder by phone to obtain the verification code and enter the verification code into a preset location; Obtain the verification code entered by the user, and if the verification code is correct, perform the current transaction according to the current transaction information.

8. The method according to claim 7, characterized in that If the verification code is correct, the current transaction will be carried out according to the current transaction information, including: If the verification code is correct, the image data of the user is collected and stored; wherein the image data includes the front face image data of the user; After the collection is completed, the current transaction is carried out according to the current transaction information.

9. An ATM cash withdrawal device, used in an ATM, characterized in that: The device comprises: An acquisition module is used to obtain current transaction information corresponding to a bank card and determine whether the current transaction is an abnormal transaction based on the current transaction information; a determination module, configured to determine whether the user of the bank card is the holder of the bank card if the current transaction is an abnormal transaction; an analysis module configured to, if the user of the bank card is the holder of the bank card, perform micro-expression analysis on the user and obtain an analysis result; if the analysis result indicates that the user is in an abnormal state, perform micro-expression analysis on the user again after a first preset time period, until the latest analysis result indicates that the user is in a normal state or the number of micro-expression analyses exceeds a preset number; The transaction module is configured to perform a current transaction according to current transaction information if the latest analysis result indicates that the user is in a normal state.

10. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 8 when executed by a processor.

12. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 8 when the computer program is executed by a processor.

Images