CN112053148A - Self-service terminal transfer verification method, device, equipment and storage medium - Google Patents

Self-service terminal transfer verification method, device, equipment and storage medium Download PDF

Info

Publication number
CN112053148A
CN112053148A CN202011048536.2A CN202011048536A CN112053148A CN 112053148 A CN112053148 A CN 112053148A CN 202011048536 A CN202011048536 A CN 202011048536A CN 112053148 A CN112053148 A CN 112053148A
Authority
CN
China
Prior art keywords
user
transfer
payment account
transfer transaction
verification
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011048536.2A
Other languages
Chinese (zh)
Other versions
CN112053148B (en
Inventor
季蕴青
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202011048536.2A priority Critical patent/CN112053148B/en
Publication of CN112053148A publication Critical patent/CN112053148A/en
Application granted granted Critical
Publication of CN112053148B publication Critical patent/CN112053148B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/08—Payment architectures
    • G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
    • G06Q20/108—Remote banking, e.g. home banking
    • G06Q20/1085—Remote banking, e.g. home banking involving automatic teller machines [ATMs]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G06Q20/40145—Biometric identity checks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/409—Device specific authentication in transaction processing
    • G06Q20/4097—Device specific authentication in transaction processing using mutual authentication between devices and transaction partners
    • G06Q20/40975—Device specific authentication in transaction processing using mutual authentication between devices and transaction partners using encryption therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/02—Banking, e.g. interest calculation or account maintenance

Abstract

The method comprises the steps of after a payment account is input, determining the accumulated input duration of the payment account, the input interval duration of adjacent digits of the payment account and the sight line characteristic of a user as a characteristic to be verified; verifying the characteristics to be verified by using a transfer verification model to obtain a verification result; if the verification result indicates that the current transfer transaction is a safe transfer transaction, acquiring a first face image, comparing the first face image with a second face image acquired when an account number is input to determine whether the first face image is matched with the second face image, and if the first face image is matched with the second face image, executing the transfer transaction; and if the verification result indicates that the current transfer transaction is not the safe transfer transaction or the two images are not matched, deleting the payment account number and the password input by the user, and refusing to execute the transfer transaction. According to the scheme, the pre-trained transfer verification model and the pre-trained transfer verification face image are used for verification before transfer, so that serious property loss caused by leakage of account numbers and passwords is avoided.

Description

Self-service terminal transfer verification method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of security verification, in particular to a method, a device, equipment and a storage medium for self-service terminal account transfer verification.
Background
A self-service terminal (such as an ATM (automatic Teller machine) and a self-service cash recycling machine) is a common device of a bank, and after a user logs in the self-service terminal, various operations such as deposit, withdrawal, transfer, inquiry and the like can be executed on the self-service terminal, so that the daily use requirements of the user can be met conveniently and quickly.
The current self-service terminal generally supports card-free transaction, and during transfer, a payment user can complete login only by inputting a bank account number and a password of the payment user at the self-service terminal. The self-service terminal is convenient to use, and potential safety hazards are brought, once the account number and the password are stolen by a third party, the third party can input the account number and the password on the self-service terminal, and properties in a bank account can be transferred. Therefore, an effective transfer verification scheme of the self-service terminal is needed at present to prevent a third party from stealing property in an account in a transfer mode of the self-service terminal.
Disclosure of Invention
Based on the problems in the prior art, the application provides a method, a device, equipment and a storage medium for self-service terminal transfer verification, so that the safety of a user in transferring money by using a self-service terminal is improved.
The application provides a self-service terminal transfer verification method in a first aspect, which comprises the following steps:
and (3) a model training process:
generating sample characteristics corresponding to each historical transfer transaction and a corresponding sample result according to data of multiple historical transfer transactions of the self-service terminal; the sample characteristics comprise accumulated entry duration of a payment account of the corresponding historical account transfer transaction, entry interval duration of every two adjacent digits of the payment account, and sight line characteristics of a user operating the self-service terminal; the sample result is used for indicating whether the corresponding historical transfer transaction is a safe transfer transaction;
training a pre-constructed negative feedback neural network optimized by a genetic algorithm by using the sample characteristics and the sample results to obtain a transfer verification model;
transfer verification process:
after a user enters a payment account, determining the accumulated entry duration of the payment account, the entry interval duration of every two adjacent digits of the payment account and the sight line characteristic of the user as a characteristic to be verified during entry of the payment account;
verifying the to-be-verified feature by using the transfer verification model to obtain a verification result of the to-be-verified feature;
if the verification result of the to-be-verified feature indicates that the current transfer transaction is a safe transfer transaction, acquiring a first face image, and comparing whether the first face image is matched with a second face image; the second facial image is a user facial image acquired when an account is entered;
if the first facial image and the second facial image are matched, executing a transfer transaction based on the payment account number and a password input by a user;
and if the verification result of the to-be-verified feature indicates that the current transfer transaction is not a safe transfer transaction or the first face image and the second face image are not matched, deleting the payment account number and the password input by the user, and refusing to execute the transfer transaction.
Optionally, after deleting the payment account and the password entered by the user and refusing to perform the transfer transaction, the method further includes:
establishing network connection with a mobile banking client of a user;
and after the mobile banking client passes the identity verification of the user, recovering the payment account number through the mobile banking client, and executing the transfer transaction based on the payment account number and the identity verification result of the mobile banking client.
Optionally, the executing of the transfer transaction based on the payment account number and the password entered by the user includes:
after the payment account is verified to be matched with the password input by the user, a collection account and a transfer amount are obtained;
and deducting the transfer amount from the payment account number, and adding the transfer amount to the collection account number.
Optionally, the obtaining the collection account number includes:
shooting to obtain an account image, and identifying to obtain a collection account from the account image by using an image identification technology;
or scanning a chip of a bank card corresponding to the collection account number, and extracting the collection account number from the scanned chip information;
or, establishing network connection with a mobile banking client of the user, and acquiring a collection account number from the mobile banking client.
The second aspect of the application provides a self-service terminal transfer verification device, including:
the generating unit is used for generating sample characteristics and corresponding sample results corresponding to each historical transfer transaction according to data of multiple historical transfer transactions of the self-service terminal; the sample characteristics comprise accumulated entry duration of a payment account of the corresponding historical account transfer transaction, entry interval duration of every two adjacent digits of the payment account, and sight line characteristics of a user operating the self-service terminal; the sample result is used for indicating whether the corresponding historical transfer transaction is a safe transfer transaction;
the training unit is used for training a pre-constructed negative feedback neural network optimized by a genetic algorithm by using the sample characteristics and the sample results to obtain a transfer verification model;
the verification unit is used for determining the accumulated entry duration of the payment account, the entry interval duration of every two adjacent digits of the payment account and the sight line characteristic of the user as a characteristic to be verified when the payment account is entered by the user;
the verification unit is used for verifying the feature to be verified by using the transfer verification model to obtain a verification result of the feature to be verified;
the comparison unit is used for acquiring a first face image and comparing whether the first face image is matched with a second face image or not if the verification result of the feature to be verified indicates that the current transfer transaction is a safe transfer transaction; the second facial image is a user facial image acquired when an account is entered;
the execution unit is used for executing transfer transaction based on the payment account number and a password input by a user if the first face image is matched with the second face image;
and the execution unit is used for deleting the payment account number and the password input by the user and refusing to execute the transfer transaction if the verification result of the to-be-verified feature indicates that the current transfer transaction is not a safe transfer transaction or the first face image and the second face image are not matched.
Optionally, the apparatus further includes a recovery unit, configured to:
establishing network connection with a mobile banking client of a user;
and after the mobile banking client passes the identity verification of the user, recovering the payment account number through the mobile banking client, and executing the transfer transaction based on the payment account number and the identity verification result of the mobile banking client.
Optionally, when the execution unit executes the transfer transaction based on the payment account and the password entered by the user, the execution unit is specifically configured to:
after the payment account is verified to be matched with the password input by the user, a collection account and a transfer amount are obtained;
and deducting the transfer amount from the payment account number, and adding the transfer amount to the collection account number.
Optionally, when the execution unit obtains the collection account, the execution unit is specifically configured to:
shooting to obtain an account image, and identifying to obtain a collection account from the account image by using an image identification technology;
or scanning a chip of a bank card corresponding to the collection account number, and extracting the collection account number from the scanned chip information;
or, establishing network connection with a mobile banking client of the user, and acquiring a collection account number from the mobile banking client.
A third aspect of the present application provides a computer storage medium for storing a computer program which, when executed, is particularly adapted to implement the method of self-service terminal transfer verification as provided in any of the first aspects of the present application.
A fourth aspect of the present application provides an electronic device comprising a memory and a processor;
wherein the memory is for storing a computer program;
the processor is configured to execute the computer program, and in particular, is configured to implement the method for self-service terminal transfer verification provided by any one of the first aspects of the present application.
The method comprises the steps of after a payment account is input, determining the accumulated input duration of the payment account, the input interval duration of adjacent digits of the payment account and the sight line characteristic of a user as a characteristic to be verified; verifying the characteristics to be verified by using a transfer verification model to obtain a verification result; if the verification result indicates that the current transfer transaction is a safe transfer transaction, acquiring a first face image, comparing the first face image with a second face image acquired when an account number is input to determine whether the first face image is matched with the second face image, and if the first face image is matched with the second face image, executing the transfer transaction; and if the verification result indicates that the current transfer transaction is not the safe transfer transaction or the two images are not matched, deleting the payment account number and the password input by the user, and refusing to execute the transfer transaction. According to the scheme, the pre-trained transfer verification model and the pre-trained transfer verification face image are used for verification before transfer, so that serious property loss caused by leakage of account numbers and passwords is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a training method of a transfer verification model provided by an embodiment of the application;
FIG. 2 is a flow chart of a method for self-service terminal transfer verification provided by an embodiment of the application;
FIG. 3 is a schematic structural diagram of a self-service terminal transfer verification device according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides a transfer verification method of a self-service terminal, which specifically comprises a model training process and a transfer verification process, wherein after the model training process is finished, when the transfer verification process is executed each time in the follow-up process, the transfer verification model obtained by training in the model training process can be directly used for verifying the characteristics to be verified, and the model training process does not need to be executed again.
Optionally, when the transfer verification model is actually applied to transfer verification, parameters of the transfer verification model can be adjusted according to the verification result of the transfer verification model and the deviation of the actual result, so that the transfer verification model is dynamically updated, and the accuracy of the detection result of the model is improved.
Referring to fig. 1, the transfer verification model training method provided in the embodiment of the present application may specifically include the following steps:
s101, generating sample characteristics corresponding to each historical transfer transaction and corresponding sample results according to data of multiple historical transfer transactions of the self-service terminal.
The sample characteristics comprise accumulated entry duration of a payment account of the corresponding historical account transfer transaction, entry interval duration of every two adjacent digits of the payment account and sight line characteristics of a user operating the self-service terminal; the sample result is used to indicate whether the corresponding historical transfer transaction is a secure transfer transaction.
And S102, training a pre-constructed negative feedback neural network optimized by a genetic algorithm by using the sample characteristics and the sample results to obtain a transfer verification model.
The genetic algorithm optimized negative feedback neural network (also called GA-BP network) can be a neural network model with three layers of structures (an output layer, a hidden layer and an input layer), and is different from a general neural network.
The training process of the GA-BP network is consistent with that of other neural networks, only a plurality of sample characteristics are required to be input into the neural network to be trained one by one, then a plurality of verification results output by the neural network are compared with real sample results to determine the loss of the neural network, then the initial parameters set in the neural network are updated based on the loss of the current neural network based on the negative feedback regulation theory, then the training process is executed again from the link of inputting the sample characteristics until the loss of the neural network determined at a certain time meets the convergence condition (generally, the loss value can be smaller than a convergence threshold value, or the current loss value is closer to the loss value at the previous time), and then a trained GA-BP network, namely a transfer verification model, is obtained.
The genetic algorithm is an existing algorithm, and in the GA-BP network provided in the embodiment of the present application, a basic principle is that a plurality of parameter individuals are randomly generated, each parameter individual includes a set of completed parameters capable of constructing a neural network, and meanwhile, the fitness of each parameter individual is defined as:
and (4) a neural network constructed by the parameters contained in the parameter individual verifies all sample characteristics in the step (S101), and then determines a loss value according to a verification result and an actual sample result.
Based on the definition of the fitness, executing multiple iterations, in each iteration, randomly executing cross operation and mutation operation on each parameter individual according to a certain probability to obtain a plurality of new parameter individuals, wherein each parameter individual has corresponding fitness decision by executing the cross operation and the mutation operation, and the higher the fitness is, the higher the probability of executing the cross operation and the mutation operation of the parameter individual is, so that after repeated iterations, the optimal parameter individual (with the minimum fitness, namely the minimum corresponding loss value) is selected from all the parameter individuals obtained by the iterations, and the parameter contained by the parameter individual is the initial parameter for constructing the initial GA-BP network.
Referring to fig. 2, an embodiment of the present application provides a method for self-service terminal transfer verification, where a transfer verification model obtained by training in the training method is used to perform a verification result on a to-be-verified feature, and whether to execute a subsequent transfer transaction is determined according to the verification result. The transfer verification model can analyze the accumulated input duration of the payment account in the characteristics to be verified, the input interval duration of every two adjacent digits of the payment account, and the relationship between parameters such as sight characteristics of a user and the safety of the transfer transaction when the payment account is input through the previous data of multiple transfer transactions, so that whether the transfer transaction is safe or not is predicted according to the characteristics to be verified (namely, a corresponding verification result is output).
The self-service terminal verification method provided by the application can comprise the following steps:
s201, after the user enters the payment account, obtaining the features to be verified.
The to-be-verified characteristic comprises the accumulated entry duration of the user input payment account, the entry interval duration of every two adjacent digits of the payment account and the sight line characteristic of the user determined as the to-be-verified characteristic when the payment account is entered.
Generally, if the user is the actual holder (i.e. the user owner) of the currently input payment account, the time for the user to input the complete accumulated payment account will be shorter, that is, the longer the accumulated entry duration is, the more likely the user currently inputting the payment account will steal the payment account of another person, and the more insecure the corresponding current transfer transaction will be.
Similarly, if the user is the actual holder (i.e., the householder) of the currently input payment account, the input interval duration of every two adjacent digits of the payment account is shorter when the user inputs the payment account, and if the input interval duration of every two adjacent digits of the payment account is longer, the security of the current transfer transaction is lower.
The sight line characteristic of the user is mainly used for indicating the amplitude and frequency of deviation of the sight line of the user from the self-service terminal in the account number inputting process, if the sight line of the user is large in amplitude and deviates from the self-service terminal for multiple times, the more likely the user who inputs the payment account number is to steal the payment account number of other people, and the more unsafe the corresponding current transfer transaction is.
The sight line characteristic of the user can be obtained through the following steps:
the method comprises the steps of capturing photos of a customer in real time through a camera of the self-service deposit and withdrawal machine, obtaining a characteristic value of each picture through an image recognition module, and inputting the characteristic values into a pre-constructed sight line characteristic extraction model, so that sight line characteristics of the user during the account number input for payment are extracted and obtained.
S202, verifying the to-be-verified feature by using the transfer verification model to obtain a verification result of the to-be-verified feature.
The verification result is mainly used for indicating whether the current transfer transaction is a safe transfer transaction. Specifically, the output verification result may be a probability that the current transfer transaction is a safe transfer transaction, if the output probability is greater than a set safety threshold, the current transfer transaction is a safe transfer transaction, that is, it may be determined that the user currently inputting the payment account is a legitimate user of the account, and conversely, if the output probability is not greater than the set safety threshold, the current transfer transaction is not a safe transfer transaction, that is, it is considered that the user currently inputting the payment account is probably not a legitimate user of the account.
And if the verification result of the to-be-verified feature indicates that the current transfer transaction is a safe transfer transaction, executing step S203, and if the verification result of the to-be-verified feature indicates that the current transfer transaction is not a safe transfer transaction, executing step S205.
S203, collecting the first face image, and comparing whether the first face image is matched with the second face image.
The first facial image is used for indicating that the current transfer transaction verification result is obtained and indicates that the current transfer transaction is the facial image of the user acquired after the safe transfer transaction, and the second facial image indicates the facial image of the user acquired when the account number is recorded.
Step S203 may be performed by using a pre-trained image recognition network, and the image recognition network may both refer to related prior art, which is not described herein again.
If the first face image and the second face image match, that is, the user in the first face image and the user in the second face image are the same person, step S204 is performed, otherwise, if the first face image and the second face image do not match, that is, the user in the first face image and the user in the second face image are not the same person, step S205 is performed.
And S204, executing the transfer transaction based on the payment account number and the password input by the user.
S205, deleting the payment account number and the password input by the user, and refusing to execute the transfer transaction.
Optionally, after deleting the payment account and the password entered by the user and refusing to perform the transfer transaction, the method further includes:
and the self-service terminal displays prompt information to prompt a user to operate the mobile phone bank client and establish network connection between the mobile phone bank client and the self-service terminal.
Specifically, the self-service terminal can display a two-dimensional code on a display screen, or can output a prompt message to prompt a user to scan a two-dimensional code adhered to one side of the self-service terminal by using a mobile banking client, and after the user scans the two-dimensional code by using the mobile banking client, network connection can be established between the mobile banking client and the self-service terminal.
After the network connection is established, the user can perform identity authentication on the mobile banking client, and the specific authentication mode includes, but is not limited to, short message dynamic password authentication, fingerprint authentication, voiceprint authentication, face identification authentication and the like.
After the mobile banking client passes the identity verification of the user, the self-service terminal can recover the payment account number through the mobile banking client and execute the transfer transaction based on the payment account number and the identity verification result of the mobile banking client.
That is to say, after the mobile banking client passes the authentication of the user, the self-service terminal can determine that the user currently operating is a valid user of the payment account input previously, and at this time, the self-service terminal can directly read the payment account of the user from the mobile banking client which establishes the network connection, so that the user directly logs in the self-service terminal without logging in the account again, and the use experience of the user is improved.
And after the payment account is recovered, the user can continue to operate the self-service terminal to perform transfer transaction.
Optionally, the specific implementation process of executing the transfer transaction based on the payment account number and the password entered by the user in step S204 may include:
after the payment account is verified to be matched with the password input by the user, a collection account and a transfer amount are obtained;
the transfer amount is deducted from the payment account and added to the collection account.
Optionally, the method for obtaining the collection account includes, but is not limited to, the following several methods, and the user may select any one of the methods for entering the collection account according to the actual situation:
firstly, an account image is obtained through shooting, and a collection account is obtained through recognition from the account image through an image recognition technology.
That is, if the customer holds a handwritten collection account, the self-service terminal may capture a carrier (e.g., a note, a notebook, etc.) written with the collection account in the customer's hand to obtain an account image, and then identify the collection account from the account image by using an Optical Character Recognition (OCR) technique.
And secondly, scanning a chip of the bank card corresponding to the collection account number, and extracting the collection account number from the scanned chip information.
If the customer has a bank card of the transfer customer (namely, the bank card corresponding to the collection account number in one transfer transaction), the user can place the bank card corresponding to the collection account number in a designated area, then the self-service terminal can scan a chip of the bank card, read chip information of the bank card and extract a card number of the bank card from the chip information, namely, the collection account number in the transfer transaction.
And thirdly, establishing network connection with a mobile banking client of the user, and acquiring a collection account number from the mobile banking client.
The mobile banking client can establish network connection with the self-service terminal by scanning the two-dimensional code arranged on one side of the self-service terminal.
In the third mode, the self-service terminal can directly obtain a collection account number in a digital form from the mobile banking client, and under the condition, the self-service terminal can display the collection account number on a display screen and prompt the user to confirm.
In addition, the self-service terminal can also acquire an account image with a collection account from the mobile banking client, then recognize the collection account from the account image by using an image recognition technology, and redisplay the acquired collection account on a display screen for the user to confirm.
Of course, the user may also choose to manually enter the collection account number.
Optionally, after the user confirms the collection account number, the self-service terminal may query account number information of the collection account number and account number information of the payment account number through a background system of the bank, and if the two account numbers have previously undergone a transfer transaction through a mobile banking, an internet banking, a counter, or a self-service teller machine of the bank, or if the holders of the two account numbers are in a relationship, may display customer information (such as a real name) of the holder of the collection account number on a display screen of the self-service terminal, otherwise, if the transfer transaction that is currently taking place is the first transfer between the two account numbers and the holders of the two account numbers are not in a relationship, the customer information of the holder of the collection account number is not displayed.
The method for defining the relationship is configured by a bank outlet, and the method for judging the relationship is inquired by an online public security system.
By the method, the safety of the customer to which the collection account belongs is protected, and the customer experience can be improved.
The application provides a self-service terminal transfer verification method, which comprises the steps of after a payment account is input, determining the accumulated input duration of the payment account, the input interval duration of adjacent digits of the payment account and the sight characteristics of a user as characteristics to be verified; verifying the characteristics to be verified by using a transfer verification model to obtain a verification result; if the verification result indicates that the current transfer transaction is a safe transfer transaction, acquiring a first face image, comparing the first face image with a second face image acquired when an account number is input to determine whether the first face image is matched with the second face image, and if the first face image is matched with the second face image, executing the transfer transaction; and if the verification result indicates that the current transfer transaction is not the safe transfer transaction or the two images are not matched, deleting the payment account number and the password input by the user, and refusing to execute the transfer transaction. According to the scheme, the pre-trained transfer verification model and the pre-trained transfer verification face image are used for verification before transfer, so that serious property loss caused by leakage of account numbers and passwords is avoided.
With reference to fig. 3, the device may include the following units:
the generating unit 301 is configured to generate a sample feature and a corresponding sample result corresponding to each historical transfer transaction according to data of multiple historical transfer transactions of the self-service terminal.
The sample characteristics comprise accumulated entry duration of a payment account of the corresponding historical account transfer transaction, entry interval duration of every two adjacent digits of the payment account and sight line characteristics of a user operating the self-service terminal; the sample result is used to indicate whether the corresponding historical transfer transaction is a secure transfer transaction.
And the training unit 302 is used for training a pre-constructed negative feedback neural network optimized by a genetic algorithm by using the sample characteristics and the sample results to obtain a transfer verification model.
The determining unit 303 is configured to determine, after the user enters the payment account, the accumulated entry duration of the payment account, the entry interval duration of every two adjacent digits of the payment account, and the sight line characteristic of the user when the payment account is entered as the to-be-verified characteristic.
And the verification unit 304 is configured to verify the feature to be verified by using the transfer verification model to obtain a verification result of the feature to be verified.
And a comparing unit 305, configured to, if the verification result of the feature to be verified indicates that the current transfer transaction is a safe transfer transaction, acquire the first face image, and compare whether the first face image and the second face image are matched.
And the second facial image is the facial image of the user acquired when the account is entered.
And the execution unit 306 is used for executing the transfer transaction based on the payment account number and the password input by the user if the first face image is matched with the second face image.
And the execution unit 306 is configured to delete the payment account number and the password entered by the user and refuse to execute the transfer transaction if the verification result of the to-be-verified feature indicates that the current transfer transaction is not a secure transfer transaction or the first facial image and the second facial image are not matched.
Optionally, the apparatus further comprises a recovery unit 307, configured to:
establishing network connection with a mobile banking client of a user;
and after the mobile banking client passes the identity verification of the user, recovering the payment account number through the mobile banking client, and executing the transfer transaction based on the payment account number and the identity verification result of the mobile banking client.
Optionally, when the execution unit 306 executes the transfer transaction based on the payment account and the password entered by the user, the execution unit is specifically configured to:
after the payment account is verified to be matched with the password input by the user, a collection account and a transfer amount are obtained;
the transfer amount is deducted from the payment account and added to the collection account.
Optionally, when the execution unit obtains the collection account, the execution unit is specifically configured to:
shooting to obtain an account image, and identifying from the account image by using an image identification technology to obtain a collection account;
or scanning a chip of a bank card corresponding to the collection account number, and extracting the collection account number from the scanned chip information;
or, establishing network connection with a mobile banking client of the user, and acquiring a collection account number from the mobile banking client.
The self-service terminal transfer verification device provided by the embodiment of the application has the specific working principle that reference can be made to the self-service terminal transfer verification method provided by any embodiment of the application, and the detailed description is omitted here.
The application provides a self-service terminal transfer verification device, wherein after a payment account is input by a determination unit 303, the accumulated input duration of the payment account, the input interval duration of adjacent digits of the payment account and the sight line characteristic of a user are determined as the characteristic to be verified; the verification unit 304 verifies the to-be-verified feature by using the transfer verification model to obtain a verification result; if the verification result indicates that the current transfer transaction is a safe transfer transaction, the comparison unit 305 collects a first facial image and compares whether the first facial image is matched with a second facial image collected when an account number is recorded, and if the first facial image is matched with the second facial image, the execution unit 306 executes the transfer transaction; if the verification result indicates that the current transfer transaction is not a secure transfer transaction or the two images are not matched, the execution unit 306 deletes the payment account number and the password input by the user and refuses to execute the transfer transaction. According to the scheme, the pre-trained transfer verification model and the pre-trained transfer verification face image are used for verification before transfer, so that serious property loss caused by leakage of account numbers and passwords is avoided.
A third aspect of the present application provides a computer storage medium for storing a computer program, which when executed, is particularly adapted to implement the method for self-service terminal transfer verification as provided in any of the embodiments of the present application.
A fourth aspect of the present application provides an electronic device, please refer to fig. 4, which may include a memory 401 and a processor 402.
Wherein the memory 401 is used for storing computer programs;
the processor is used for executing a computer program, and is particularly used for realizing the self-service terminal transfer verification method provided by any embodiment of the application.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
It should be noted that the terms "first", "second", and the like in the present invention are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
Those skilled in the art can make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method of self-service terminal transfer verification, comprising:
and (3) a model training process:
generating sample characteristics corresponding to each historical transfer transaction and a corresponding sample result according to data of multiple historical transfer transactions of the self-service terminal; the sample characteristics comprise accumulated entry duration of a payment account of the corresponding historical account transfer transaction, entry interval duration of every two adjacent digits of the payment account, and sight line characteristics of a user operating the self-service terminal; the sample result is used for indicating whether the corresponding historical transfer transaction is a safe transfer transaction;
training a pre-constructed negative feedback neural network optimized by a genetic algorithm by using the sample characteristics and the sample results to obtain a transfer verification model;
transfer verification process:
after a user enters a payment account, determining the accumulated entry duration of the payment account, the entry interval duration of every two adjacent digits of the payment account and the sight line characteristic of the user as a characteristic to be verified during entry of the payment account;
verifying the to-be-verified feature by using the transfer verification model to obtain a verification result of the to-be-verified feature;
if the verification result of the to-be-verified feature indicates that the current transfer transaction is a safe transfer transaction, acquiring a first face image, and comparing whether the first face image is matched with a second face image; the second facial image is a user facial image acquired when an account is entered;
if the first facial image and the second facial image are matched, executing a transfer transaction based on the payment account number and a password input by a user;
and if the verification result of the to-be-verified feature indicates that the current transfer transaction is not a safe transfer transaction or the first face image and the second face image are not matched, deleting the payment account number and the password input by the user, and refusing to execute the transfer transaction.
2. The method of claim 1, wherein after deleting the payment account number and the password entered by the user and denying performance of the transfer transaction, further comprising:
establishing network connection with a mobile banking client of a user;
and after the mobile banking client passes the identity verification of the user, recovering the payment account number through the mobile banking client, and executing the transfer transaction based on the payment account number and the identity verification result of the mobile banking client.
3. The method of claim 1, wherein performing a transfer transaction based on the payment account number and a user-entered password comprises:
after the payment account is verified to be matched with the password input by the user, a collection account and a transfer amount are obtained;
and deducting the transfer amount from the payment account number, and adding the transfer amount to the collection account number.
4. The method of claim 3, wherein obtaining the collection account number comprises:
shooting to obtain an account image, and identifying to obtain a collection account from the account image by using an image identification technology;
or scanning a chip of a bank card corresponding to the collection account number, and extracting the collection account number from the scanned chip information;
or, establishing network connection with a mobile banking client of the user, and acquiring a collection account number from the mobile banking client.
5. A self-service terminal transfer verification apparatus comprising:
the generating unit is used for generating sample characteristics and corresponding sample results corresponding to each historical transfer transaction according to data of multiple historical transfer transactions of the self-service terminal; the sample characteristics comprise accumulated entry duration of a payment account of the corresponding historical account transfer transaction, entry interval duration of every two adjacent digits of the payment account, and sight line characteristics of a user operating the self-service terminal; the sample result is used for indicating whether the corresponding historical transfer transaction is a safe transfer transaction;
the training unit is used for training a pre-constructed negative feedback neural network optimized by a genetic algorithm by using the sample characteristics and the sample results to obtain a transfer verification model;
the verification unit is used for determining the accumulated entry duration of the payment account, the entry interval duration of every two adjacent digits of the payment account and the sight line characteristic of the user as a characteristic to be verified when the payment account is entered by the user;
the verification unit is used for verifying the feature to be verified by using the transfer verification model to obtain a verification result of the feature to be verified;
the comparison unit is used for acquiring a first face image and comparing whether the first face image is matched with a second face image or not if the verification result of the feature to be verified indicates that the current transfer transaction is a safe transfer transaction; the second facial image is a user facial image acquired when an account is entered;
the execution unit is used for executing transfer transaction based on the payment account number and a password input by a user if the first face image is matched with the second face image;
and the execution unit is used for deleting the payment account number and the password input by the user and refusing to execute the transfer transaction if the verification result of the to-be-verified feature indicates that the current transfer transaction is not a safe transfer transaction or the first face image and the second face image are not matched.
6. The apparatus of claim 5, further comprising a recovery unit to:
establishing network connection with a mobile banking client of a user;
and after the mobile banking client passes the identity verification of the user, recovering the payment account number through the mobile banking client, and executing the transfer transaction based on the payment account number and the identity verification result of the mobile banking client.
7. The apparatus according to claim 5, wherein the execution unit, when executing the transfer transaction based on the payment account number and the password entered by the user, is configured to:
after the payment account is verified to be matched with the password input by the user, a collection account and a transfer amount are obtained;
and deducting the transfer amount from the payment account number, and adding the transfer amount to the collection account number.
8. The apparatus of claim 7, wherein the execution unit, when obtaining the collection account number, is specifically configured to:
shooting to obtain an account image, and identifying to obtain a collection account from the account image by using an image identification technology;
or scanning a chip of a bank card corresponding to the collection account number, and extracting the collection account number from the scanned chip information;
or, establishing network connection with a mobile banking client of the user, and acquiring a collection account number from the mobile banking client.
9. A computer storage medium storing a computer program which, when executed, is particularly adapted to implement a method of self-service terminal transfer verification as claimed in any one of claims 1 to 4.
10. An electronic device comprising a memory and a processor;
wherein the memory is for storing a computer program;
the processor is configured to execute the computer program, in particular to implement the method of self-service terminal transfer verification as claimed in any of claims 1 to 4.
CN202011048536.2A 2020-09-29 2020-09-29 Method, device, equipment and storage medium for self-service terminal account transfer verification Active CN112053148B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011048536.2A CN112053148B (en) 2020-09-29 2020-09-29 Method, device, equipment and storage medium for self-service terminal account transfer verification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011048536.2A CN112053148B (en) 2020-09-29 2020-09-29 Method, device, equipment and storage medium for self-service terminal account transfer verification

Publications (2)

Publication Number Publication Date
CN112053148A true CN112053148A (en) 2020-12-08
CN112053148B CN112053148B (en) 2023-10-27

Family

ID=73605254

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011048536.2A Active CN112053148B (en) 2020-09-29 2020-09-29 Method, device, equipment and storage medium for self-service terminal account transfer verification

Country Status (1)

Country Link
CN (1) CN112053148B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012008773A (en) * 2010-06-24 2012-01-12 Hitachi Omron Terminal Solutions Corp Cash automatic transaction device, program and transaction method
KR20170141930A (en) * 2016-06-16 2017-12-27 주식회사 하나은행 System for providing financial service and method for transfer thereof
CN107612922A (en) * 2017-09-30 2018-01-19 北京梆梆安全科技有限公司 User ID authentication method and device based on user operation habits and geographical position
CN109829706A (en) * 2018-12-15 2019-05-31 深圳壹账通智能科技有限公司 Transfer account method, device, computer equipment and storage medium based on recognition of face

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012008773A (en) * 2010-06-24 2012-01-12 Hitachi Omron Terminal Solutions Corp Cash automatic transaction device, program and transaction method
KR20170141930A (en) * 2016-06-16 2017-12-27 주식회사 하나은행 System for providing financial service and method for transfer thereof
CN107612922A (en) * 2017-09-30 2018-01-19 北京梆梆安全科技有限公司 User ID authentication method and device based on user operation habits and geographical position
CN109829706A (en) * 2018-12-15 2019-05-31 深圳壹账通智能科技有限公司 Transfer account method, device, computer equipment and storage medium based on recognition of face

Also Published As

Publication number Publication date
CN112053148B (en) 2023-10-27

Similar Documents

Publication Publication Date Title
Das et al. Designing a biometric strategy (fingerprint) measure for enhancing ATM security in Indian e-banking system
US20130036017A1 (en) Financial card for online fund transfer and method therefor
CN108171137B (en) Face recognition method and system
WO2018174824A1 (en) Systems and methods for user identity authentication
CN110992053B (en) Secure payment system and method based on finger vein recognition and blockchain technology
Ansar et al. Enhancement of two-tier ATM security mechanism: towards providing a real-time solution for network issues
CN107146079B (en) Transaction payment method and system
Oruh Three-factor authentication for automated teller machine system
CN108270789B (en) Internet banking opening method, equipment, system and computer readable storage medium
Hooda ATM security
KR101334744B1 (en) Loaning method using kiosk system
Priya et al. A novel algorithm for secure Internet Banking with finger print recognition
Jaiswal et al. Enhancing ATM security using Fingerprint and GSM technology
CN112053148B (en) Method, device, equipment and storage medium for self-service terminal account transfer verification
CN108053580B (en) Method and system for carrying out deposit and sales by using self-service equipment
CN110910586B (en) Anti-theft card swiping method and system
CN111882425B (en) Service data processing method, device and server
Nawaya et al. Designing a Biometric (Finger) Using Multispectral Imaging Biometric Authentication Measures for Enhancing ATM Security in Nigeria
Singh et al. Secure swipe machine with help of biometric security
Priya et al. An Effective Cardless Atm Transaction Using Computer Vision Techniques
CN111985913A (en) Card-free transaction method and device and server
Lala et al. Towards A secured financial transaction: A multi-factor authentication model
Ahmeduddin et al. The use of fingerprints within the ATM system
Onyesolu et al. Robust Authentication Model for ATM: a Biometric Strategy Measure for Enhancing E-Banking Security in Nigeria.
CN117114629B (en) Intelligent management system and implementation method for bank website business library

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant