CN112150733A

CN112150733A - Bank card misoperation processing method, device and equipment

Info

Publication number: CN112150733A
Application number: CN202011032500.5A
Authority: CN
Inventors: 黄文强; 季蕴青; 胡路苹; 胡玮; 黄雅楠; 胡传杰; 浮晨琪; 李蚌蚌; 徐晨敏
Original assignee: Bank of China Ltd
Current assignee: Bank of China Ltd
Priority date: 2020-09-27
Filing date: 2020-09-27
Publication date: 2020-12-29
Anticipated expiration: 2040-09-27
Also published as: CN112150733B

Abstract

The application provides a bank card misoperation processing method, a device and equipment, when the authentication of the account password value input by the current operator fails, the method can firstly determine the prediction probability of the current operator taking the first bank card by mistake according to the password input information aiming at the first bank card and the second bank card authentication information associated with the identification of the first bank card, if the prediction probability reaches the probability threshold value, the identity information to be authenticated of the current operator is further obtained, and the character relationship between the current operator and the holder of the first bank card is obtained according to the character relationship, so that when the current operator takes the first bank card by mistake, the corresponding reminding information is output, the current operator is reminded to take the first bank card by mistake, the input of the wrong password to the first bank card is stopped, and the wrong locking of the account of the first bank card due to the input password is avoided, various inconveniences and panic for the first bank card holder even cause the bank customer to lose.

Description

Bank card misoperation processing method, device and equipment

Technical Field

The application relates to the field of bank card security application, in particular to a bank card misoperation processing method, device and equipment.

Background

Nowadays, in order to facilitate consumption, business handling or work requirements and the like, people usually handle a plurality of bank cards (such as debit cards, savings cards, credit cards and the like), and some family members can intensively place the handled bank cards so as to be convenient to take and use. However, because the appearance of each bank card is similar, for the bank cards of the family who are easily taken by the members of a family, especially the bank cards of the same type handled by the same bank, if the users do not realize that the users take the bank cards by mistake, the users directly handle the business on the bank self-service equipment, the bank cards are easily locked due to wrong passwords, the business handling requirements of the users are delayed, great inconvenience is brought to the holders who are locked with the bank cards, and the users who receive the short message reminding of the wrong locking of the bank card passwords can cause panic due to the fact that the users do not know the wrong taking condition of the family in time, so that the safety of the banks is questioned, even the bank cards are cancelled, and the customers of bank institutions are lost.

Disclosure of Invention

In view of the above, in order to solve the above technical problems, the present application provides the following technical solutions:

on one hand, the application provides a bank card misoperation processing method, which comprises the following steps:

authenticating the account password value input by the current operator aiming at the first bank card;

if the authentication fails, acquiring password input information aiming at the first bank card and second bank card authentication information associated with the identifier of the first bank card;

determining the prediction probability of the current operator taking the first bank card by mistake according to the password input information and the second bank card authentication information;

if the prediction probability reaches a probability threshold, carrying out identity recognition on the current operator to obtain identity information to be authenticated of the current operator;

acquiring the character relationship between the current operator and the holder of the first bank card according to the identity information to be authenticated;

and determining whether to output the reminding information of the current operator for mistakenly taking the first bank card or not according to the obtained character relationship.

Optionally, the identifying the identity of the current operator to obtain the identity information to be authenticated of the current operator includes:

carrying out face recognition on the current operator to obtain a face recognition result of the current operator;

detecting whether customer identity information matched with the face recognition result exists or not;

if the client identity information exists, determining the client identity information as identity information to be authenticated;

the obtaining of the human relationship between the current operator and the holder of the first bank card according to the identity information to be authenticated includes:

acquiring holder identity information associated with the identification of the first bank card;

sending the identity information to be authenticated and the identity information of the holder to a public security management system, and determining the personal relationship between the current operator and the holder of the first bank card by the public security management system according to the identity information to be authenticated and the identity information of the holder, wherein the personal relationship comprises the relationship and the non-relationship in n generations, and n is an integer greater than 1;

and receiving the character relationship fed back by the public security management system.

Optionally, the determining, according to the obtained relationship between the persons, whether to output a prompt message that the current operator mistakes the first bank card includes:

acquiring a misoperation verification rule preset by a local banking institution;

verifying whether the character relation accords with the misoperation verification rule or not;

and if the first bank card is matched with the current bank card, outputting first reminding information of the current operator for mistakenly taking the first bank card.

Optionally, if the prediction probability does not reach the probability threshold, or the person relationship does not conform to the misoperation verification rule, the method further includes:

outputting second reminding information for reminding the current operator to input the password again; or,

and outputting third reminding information of illegal operation of the current operator on the first bank card, forbidding responding to an input instruction aiming at the first bank card, and sending fourth reminding information of illegal operation of the first bank card to a preset terminal of a holder of the first bank card.

Optionally, if the person relationship conforms to the misoperation verification rule, the method further includes:

and sending fifth reminding information to a preset terminal of a holder of the first bank card, wherein the fifth reminding information comprises the misoperation of the first bank card, the identity information to be authenticated of the current operator and/or the character relationship between the current operator and the holder.

Optionally, the determining, according to the password input information and the second bank card authentication information, a prediction probability that the current operator mistakes the first bank card includes:

extracting the characteristics of the password input information and the second bank card authentication information to obtain corresponding password characteristic vectors;

inputting the password feature vector into a misoperation prediction model for processing, and outputting the prediction probability of the current operator taking the first bank card by mistake;

the misoperation prediction model is obtained by training positive and negative sample data based on a neural network algorithm and a genetic algorithm, the positive sample data comprises a sample password feature vector obtained by inputting a password by a sample user by mistake taking a bank card, and the negative sample data comprises a sample password feature vector obtained by inputting a password by an illegal user to the bank card.

Optionally, the obtaining password input information for the first bank card and second bank card authentication information associated with the identifier of the first bank card includes:

acquiring an account password value input for each time by the first bank card, a first input time interval of each character in the account password value and a second input time interval between different account password values;

and identifying the identifier of the first bank card, and acquiring second bank card authentication information associated with the identifier, wherein the second bank card authentication information comprises the account password value of the second bank card.

In another aspect, the present application further provides a device for processing misoperation of a bank card, where the device includes:

the password authentication module is used for authenticating the account password value input by the current operator aiming at the first bank card;

the information acquisition module is used for acquiring password input information aiming at the first bank card and second bank card authentication information associated with the identifier of the first bank card if authentication fails;

the misoperation prediction module is used for determining the prediction probability of the current operator taking the first bank card by mistake according to the password input information and the second bank card authentication information;

the identity recognition module is used for carrying out identity recognition on the current operator under the condition that the prediction probability reaches a probability threshold value to obtain identity information to be authenticated of the current operator;

the character relation obtaining module is used for obtaining the character relation between the current operator and the holder of the first bank card according to the identity information to be authenticated;

and the misoperation reminding module is used for determining whether to output the reminding information of the current misoperation of the first bank card by the operator according to the obtained character relationship.

In another aspect, the present application further provides a device for processing misoperation of a bank card, where the device includes: at least one communication interface, at least one memory, and at least one processor, wherein:

the memory is used for storing a program for realizing the bank card misoperation processing method;

the processor is used for loading and executing the program stored in the memory so as to realize the steps of the bank card misoperation processing method.

Optionally, the device is a self-service device, and the device further includes:

the input component is used for responding to the account password input operation of the current operator aiming at the first bank card to obtain a corresponding account password value;

the image collector is used for collecting a face image of a current operator;

and the display screen is used for outputting the reminding information that the current operator takes the first bank card by mistake.

Therefore, compared with the prior art, the application provides a bank card misoperation processing method, a device and equipment, when a current operator (user) takes a first bank card to handle business, the account password value input by the current operator is authenticated, if the authentication fails, the application can detect whether the current operator takes the first bank card of a parent by mistake, specifically, the prediction probability of the current operator taking the first bank card by mistake can be determined according to password input information aiming at the first bank card and second bank card authentication information associated with the identifier of the first bank card, if the prediction probability reaches a probability threshold value, the identity of the current operator can be further identified for detecting reliability, and the character relationship between the current operator and the holder of the first bank card can be obtained according to the obtained identity information to be authenticated, therefore, whether reminding information of the current operator for mistakenly taking the first bank card is output or not is determined according to the character relation, the current operator can be reminded of mistakenly taking the first bank card in time, the input of a wrong password to the first bank card is stopped, the phenomenon that the account of the first bank card is locked due to the wrong password input is avoided, the inconvenience and the panic of a holder of the bank card due to the locking of the account of the bank card are solved, the safety of a bank institution is questioned by the holder of the bank card, even the bank card can be cancelled, and the technical problem that a customer of the bank institution runs off is solved, and the customer experience is greatly improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic flow chart illustrating an alternative example of a bank card misoperation processing method proposed in the present application;

fig. 2 is a schematic flow chart illustrating yet another alternative example of the bank card misoperation processing method proposed in the present application;

fig. 3 is a schematic structural diagram showing an alternative example of the bank card misoperation processing device provided by the application;

fig. 4 is a schematic structural diagram showing still another alternative example of the bank card misoperation processing device provided by the application;

fig. 5 is a schematic structural diagram showing still another alternative example of the bank card misoperation processing device provided by the application;

fig. 6 is a schematic structural diagram showing still another alternative example of the bank card misoperation processing device provided by the application;

fig. 7 is a schematic diagram showing a hardware structure of an alternative example of the bank card misoperation processing device provided by the application;

fig. 8 is a schematic diagram illustrating an optional application scenario of the bank card misoperation processing method provided by the present application.

Detailed Description

Aiming at the prior art problems described in the background technology section, the application hopes that when a bank card password input by an operator is detected to be wrong, whether the operator takes a bank card of other people (such as family members) by mistake or not can be detected, and the operator is reminded that the bank card is taken by mistake to cause the password to be incorrect, so that the problem that the password error frequency reaches the preset frequency and the account of the bank card is locked, inconvenience and panic are brought to a holder of the bank card, even the holder of the bank card can question the safety of a bank institution and cancel the bank card to cause the loss of customers of the bank institution can be avoided.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present application may be combined with each other without conflict.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this application and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements. An element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

In the description of the embodiments herein, "/" means "or" unless otherwise specified, for example, a/B may mean a or B; "and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present application, "a plurality" means two or more than two. The terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

Additionally, flow charts are used herein to illustrate operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

Referring to fig. 1, a schematic flow chart of an optional example of the method for processing the misoperation of the bank card provided by the present application is shown, where the method may be applied to a device for processing the misoperation of the bank card, where the device may be a self-service device, such as an ATM (Automatic Teller Machine) or other self-service business handling devices, or a service device in a bank management system, and the present application does not limit the product form and the composition structure of the device for processing the misoperation of the bank card, and may be determined according to the requirements of an actual application scenario. As shown in fig. 1, the method may include:

step S11, authenticating the account password value input by the current operator aiming at the first bank card;

taking a bank card misoperation processing device as an example of a self-service device, after a current operator inserts a first bank card into a bank card slot of the self-service device, the self-service device identifies the first bank card, and before outputting relevant information of the first bank card or responding to input operation aiming at the first bank card, considering security, the self-service device or a bank management system needs to verify an account password of the first bank card, so that the self-service device can output a password input interface for the current operator to input an account password value to be authenticated.

Step S12, under the condition of authentication failure, acquiring password input information aiming at the first bank card and second bank card authentication information associated with the identification of the first bank card;

in practical application, after the authentication of the account password value input by the current operator for the first bank card fails, a corresponding prompt message is usually output to inform the current operator that the password value input this time is incorrect, and the current operator is allowed to input the account password value again for authentication.

In this embodiment, in order to avoid various problems caused by locking the account of the first bank card before the current operator has an incorrect account password value input for the first bank card and the number of times of inputting the incorrect account password value has not reached the preset error number threshold, the present embodiment proposes to detect a character relationship between the current operator and a holder of the first bank card (i.e., a legal holder of the first bank card) to determine whether the current operator has taken the first bank card of a family by mistake or taken the first bank card of an unrelated person illegally.

Based on the analysis of the technical concept of the application, in order to realize the verification of the character relationship, the application can analyze in advance the difference existing in the process that the user wrongly takes the bank card of a family, and the user inputs the account password value of the bank under the two conditions that the user illegally takes the bank card of an unrelated person, and can also refer to other bank card authentication information owned by the holder of the bank card for realization.

Following the above analysis, the present embodiment may obtain the password input information for the first bank card, that is, information obtained in the process of inputting the account password value for the first bank card by the current operator, for example, the account password value input for each time by the first bank card, the first input time interval of each character in the account password value, the second input time interval between different account password values (which refers to the time interval between two adjacent account password values), and the like, and the content included in the password input information is not limited in the present application.

In order to further improve the reliability of the character relationship verification, in the embodiment of the application, an identifier of the first bank, such as a card number or an identifier of the first bank card, may be further identified, and then second bank card authentication information associated with the identifier of the first bank card, such as account password values of other bank cards owned by a holder of the first bank card, is queried, but is not limited to the content and the obtaining manner described in this embodiment.

Step S13, determining the prediction probability of the current operator taking the first bank card by mistake according to the password input information and the second bank card authentication information;

as described above in the technical concept of the present application, in the embodiment of the present application, two situations, namely, the situation that the user has taken the bank card of a family by mistake and the situation that the user illegally takes the bank card of an unrelated person, can be analyzed in advance from the password input information and the second bank card authentication information, and then according to the difference, the actually obtained password input information and the second bank card authentication information are analyzed to determine which situation they belong to, and specifically, a probability prediction mode can be used to indicate which situation they belong to, and a specific implementation method of the present application is not limited.

It should be noted that when the difference between the two cases of the user taking the bank card of the family by mistake and the bank card of an unrelated person illegally taken by the user is analyzed, the two information items obtained in the embodiment are not limited, and other information items may be added according to the needs of the scene or the content of the two information items may be adjusted, which may be determined, and the detailed description is not given herein.

In some embodiments provided by the present application, in order to improve the online analysis efficiency and accuracy, the present application may utilize an artificial intelligence algorithm to train a prediction model in advance, and analyze the actually obtained password input information and the second bank card authentication information to obtain the prediction probability that the current operator mistakenly takes the first bank card, but the present application is not limited to this model prediction processing manner, and the present application does not limit the training method of the prediction model, and may refer to but not limited to the description of the corresponding parts of the following embodiments.

Step S14, under the condition that the prediction probability reaches the probability threshold, carrying out identity recognition on the current operator to obtain the identity information to be authenticated of the current operator;

after the above analysis, in the embodiment of the present application, it may be preliminarily predicted, according to the above manner, whether the current operator mistakenly takes the first bank card, and if the obtained prediction probability reaches the probability threshold, it may be preliminarily determined that the current operator mistakenly takes the first bank card, but further verification is still required, so as to ensure reliability of the detection result. In practical application, because the situation that the family's bank card is taken by mistake is easily caused by factors such as centralized placement of the bank cards or sharing of a plurality of regions where the bank cards are placed among family members, the application can further verify whether the current operator takes the first bank card by mistake (the bank card not owned by the current operator) by verifying the character relationship between the current operator and the holder of the first bank card.

Based on this, the present embodiment may first identify the identity information of the current operator, that is, the identity information to be authenticated, so as to compare the identity information with the identity information of the holder of the first bank card subsequently, to determine the relationship between the current operator and the holder of the first bank card, such as whether the relationship is a relationship, specifically, a relationship in several generations.

The identity recognition of the current operator can be realized by detecting physiological characteristic information of the current operator, such as face recognition, fingerprint recognition, voiceprint recognition, pupil recognition and the like.

Step S15, acquiring the character relationship between the current operator and the holder of the first bank card according to the identity information to be authenticated;

since the identity information of the issuer, that is, the holder of the bank card, is usually recorded when the bank card is opened, the embodiment may obtain the identity information of the holder of the first bank card according to the identifier of the first bank card, so as to determine the relationship between the current operator and the holder of the first bank card according to the identity information to be authenticated of the current operator and the identity information of the holder.

In practical application, the relationship between different citizens can be determined by the information such as the household registration of the citizen, and since the information relates to the privacy of the citizen, the public security organization generally has authority to inquire, so after the identity information to be authenticated of the current operator and the identity information of the holder are obtained, the obtained identity information can be sent to the public security management system, and the public security management system inquires the relationship between the current operator and the holder of the first bank card according to the obtained identity information.

It should be understood that, in order to improve the security of the citizen information, the user may be prompted whether to allow checking the identity information of the user under the condition that the operator transacts the bank card or needs to perform identity verification on the operator of the bank card, and the relationship between the user and other people is determined according to the identity information, and after the user agrees to authorize, the verification may be performed directly according to the above-mentioned manner; if the user does not agree, the banking institution may not obtain the character relationship, so that it is impossible to further verify whether the current operator mistakenly takes the first bank card, and the reliability and accuracy of the result of determining whether the current operator mistakenly takes the first bank card are reduced.

It should be noted that, the above-mentioned manner of obtaining the relationship between people is not limited to the above-mentioned query manner implemented according to the public security organization, and after obtaining the approval and authorization of the holder of the bank card, partial identity information (non-important privacy information) of the holder of the first bank card may be fed back to the self-service device for output, and the current operator may directly determine the relationship between the current operator and the holder of the first bank card based on the approval, or directly determine whether the current operator has mistakenly taken the first bank card of the relative but not the own bank card, and once it is determined that the first bank card is not the own bank card, the subsequent operation may be directly stopped.

Certainly, in order to ensure the security of the personal information of the holder of the bank card and avoid that an illegal user deciphers the account password value of the first bank card according to the account password value, the holder of the first bank card may not agree with others to view the personal information at will, and in such a case, the relationship between the current operator and the holder of the first bank card still needs to be obtained through other ways, and the specific obtaining way is not described in detail in the application.

And step S16, determining whether to output the reminding information of the current operator mistakenly taking the first bank card according to the obtained character relationship.

In combination with the above description of the technical concept of the application, if a bank card is taken by mistake between relatives in a specific range, the bank card is not usually used illegally, and after knowing that the bank card of the relatives is taken by mistake, the user does not try to input the account password value; if an illegal user uses the bank card, even if the password is mistaken, the illegal user continuously tries to input other account password values and tries to steal resources under the account of the bank card, and the illegal user is not a relative of a holder of the bank card.

Based on this, after the above-mentioned character relationship is obtained, the character relationship may be analyzed according to a specific verification rule, that is, a misoperation verification rule, of whether the customer mistakenly takes the parent bank card by a bank organization to which the self-service device belongs, that is, whether the character relationship satisfies the misoperation verification rule, if so, it may be considered that the current operator has mistakenly taken the parent first bank card, and the system may not determine the current operator as an illegal person, and at this time, corresponding reminding information may be output to remind the current operator of the verification result, and it is not necessary to continue to try to input the account password value of the own bank card, so that the account password value of the own bank card is not the account password value of the first bank card, and the account of the first bank card is locked, such as freezing and losing the account of the first bank card.

In some embodiments, after the verification, it is determined that the current operator does not mistakenly take the first bank card of the relative, the current operator may be prompted to re-input the password, and if the re-authentication fails, the account of the first bank card may be locked, so as to ensure the fund security of the holder of the first bank card. Optionally, in this case, the present application may further detect whether the current operator is an escaping suspect or not according to a public security management system, so as to maintain social harmony and stability, and a detailed implementation process of the present application is not described in detail herein.

To sum up, in the embodiment of the present application, when a current operator (user) handles a business with a first bank card, an account password value input by the current operator is authenticated, if the authentication fails, the present application may detect whether the current operator has taken the first bank card of a parent by mistake, specifically, first, according to password input information for the first bank card and second bank card authentication information associated with an identifier of the first bank card, a prediction probability that the current operator has taken the first bank card by mistake is determined, if the prediction probability reaches a probability threshold, for detecting reliability, identity recognition may be further performed on the current operator, and according to the obtained identity information to be authenticated, a relationship between the current operator and a holder of the first bank card is obtained, so as to determine whether to output a reminding information that the current operator has taken the first bank card by mistake according to the relationship, the method can remind the current operator of mistakenly taking the first bank card in time, and stops continuously inputting the wrong password into the first bank card, so that the problem that the account of the first bank card is locked due to the wrong password is avoided, the inconvenience and the panic of a holder of the bank card due to the locking of the account of the bank card are solved, the holder of the bank card is questioned on the safety of a bank institution, and even the bank card can be cancelled, so that the technical problem that the customer of the bank institution runs off is solved, and the customer experience is greatly improved.

Referring to fig. 2, which is a schematic flow chart of another optional example of the method for processing the misoperation of the bank card provided by the present application, the present embodiment may be an optional detailed implementation manner of the method for processing the misoperation of the bank card described in the foregoing embodiment, but is not limited to this detailed implementation manner, and as shown in fig. 2, the method may include:

step S21, authenticating the account password value input by the current operator for the first bank card

Step S22, if the authentication fails, counting the failure times of the authentication failure of the account password value continuously input to the first bank card;

step S23, if the failure times reach the misoperation verification threshold, acquiring password input information aiming at the first bank card and second bank card authentication information associated with the identification of the first bank card;

the misoperation verification threshold value can be determined according to a requirement of a local banking institution (namely, the banking institution to which the first bank card belongs) on misoperation reminding, an error time threshold value for allowing a customer to continuously input a password value of an error account, and the like, for example, the misoperation verification threshold value is equal to the error time threshold value-1, and the numerical value and the determination mode of the misoperation verification threshold value are not limited in the application.

For the specific implementation process of step S21 to step S23, reference may be made to the description of the corresponding parts in the foregoing embodiments, which are not described in detail in this embodiment.

Step S24, extracting the characteristics of the password input information and the second bank card authentication information to obtain corresponding password characteristic vectors;

in the embodiment of the present application, a machine learning algorithm such as a neural network may be used to perform feature extraction (e.g., encoding processing) on each piece of information to obtain a corresponding password feature vector.

Step S25, inputting the password feature vector into the misoperation prediction model for processing, and outputting the prediction probability of the current operator taking the first bank card by mistake;

the misoperation prediction model can be obtained by training positive and negative sample data based on a neural network algorithm and a genetic algorithm, and in combination with the analysis, in order to realize reliable prediction of whether the current operator mistakenly takes the first bank card, the positive sample data used for model training can include but is not limited to: the sample password feature vector is obtained by inputting the password by taking the bank card by the sample user by mistake, namely the password feature vector is obtained by historical relevant information of the bank card taken by mistake collected in the past; the negative sample data may include, but is not limited to, a sample password feature vector obtained by an illegal user (i.e., an illegal person) performing password input on the bank card, and the obtaining process of the sample password feature vector is similar to the above-mentioned obtaining process of the password feature vector, and this embodiment will not be described in detail.

Therefore, in the process of training the misoperation prediction model, the distinguishing characteristics between the positive sample and the negative sample can be analyzed in advance and used as one of the constraint conditions of model training, so that the misoperation prediction model obtained by training can reliably distinguish two situations that a user takes a bank card of a family by mistake and a bank card of an irrelevant person is taken by the user illegally, and the reliability and the accuracy of the prediction result output by the misoperation prediction model are further improved, namely whether the current operator takes the first bank card by mistake or not. The concrete training implementation process of the misoperation prediction model is not detailed.

In a possible implementation manner, the neural network structure can be determined according to the number of data input and output by the model and the like, so that the number of parameters needing to be optimized in the genetic algorithm is determined, and a specific implementation process is not described in detail. Optionally, according to the kolmogorov principle, the network structure of the misoperation prediction model can be obtained through a three-layer BP neural network and a genetic network, wherein the number of nodes of a hidden layer in the network structure can be determined by a trial and error method, and an initial weight and a threshold of the neural network are obtained through a genetic algorithm, so that model training learning is performed on the basis, and the model training efficiency and reliability are improved.

In addition, in order to ensure the reliability and accuracy of the output result of the model, when the sample data (i.e. the training set) is determined, the test data carrying the real condition can be determined at the same time, so that the prediction accuracy of the model obtained by training can be verified by the test data in the model training process, if the verification result is not converged, namely the prediction accuracy does not meet the constraint requirement, the model obtained at this time can be continuously learned and trained until the model is converged, the finally obtained model is determined to be the misoperation prediction model, and at the moment, the prediction accuracy of the misoperation prediction model meets the constraint requirement, so that whether the current operator mistakenly takes the prediction result of the first bank card by the misoperation prediction model is reliable and accurate.

It should be noted that the training method of the misoperation prediction model provided in the present application is not limited to the training method implemented by the neural network and the genetic algorithm described in the above embodiment, and the artificial intelligence algorithm on which the model training is based may be adaptively adjusted according to the requirements of practical applications, which is not described in detail herein.

Step S26, detecting whether the prediction probability reaches a probability threshold value, if so, entering step S27; if not, go to step S215;

step S27, carrying out face recognition on the current operator to obtain the face recognition result of the current operator;

step S28, whether identity information to be authenticated matched with the face recognition result exists is detected, and if the identity information to be authenticated exists, the step S29 is executed; if not, go to step S215;

in combination with the above analysis, the present application preliminarily determines that the current operator may mistakenly take the first bank card, and further verification may be performed in an identity recognition mode, which is only described by taking an identity recognition mode of face recognition as an example, and implementation processes of other identity recognition modes are similar, and detailed description is not given in this embodiment.

Specifically, under the condition that the prediction probability is determined to reach the probability threshold, an image collector of the self-service equipment can be started to collect a face image of a current operator, and then a face recognition system carries out recognition and authentication on the collected face image so as to determine whether the current operator is a customer of a local banking institution, if so, whether customer identity information matched with the face image exists in a corresponding banking management system is detected, and if so, the customer identity information is determined as to-be-authenticated identity information of the current operator; if not, it may be considered that the current operator does not take the bank card of another person by mistake due to the same bank institution, at this time, the subsequent step S215 may be executed, and in consideration of security, preset intervention may also be directly executed on the first bank card, for example, the first bank card account is locked, so as to ensure the fund security of the first bank card holder.

In another possible implementation manner, in the case that the detection result is no, the face image of the current operator may be further sent to a public security management system to inquire whether the current operator is a trespass or the like.

It should be understood that, in the process of identifying the identity of the current operator, for other identity identification modes different from the face identification mode, the self-service device may need to be configured with a corresponding detection component, for example, for the fingerprint identification mode, a fingerprint sensor may be configured on a password input key, so that in the process of inputting an account password value by the current operator, fingerprint information to be authenticated of the current operator may be acquired at the same time; for the voiceprint recognition mode, the self-service equipment is required to be provided with a sound collector for collecting the sound signal of the current operator, and after the noise reduction processing is performed, the identity authentication of the current operator is realized by using the sound signal after the noise reduction processing. Therefore, the detection component required to be configured by the self-service equipment can be determined according to the identification principle of the selected identity identification mode, and detailed description is omitted.

Step S29, acquiring the identity information of the holder associated with the identifier of the first bank card;

step S210, the identity information to be authenticated and the identity information of the holder are sent to a public security management system;

with reference to the description of the corresponding part of the foregoing embodiment, the public security management system may determine, according to the identity information to be authenticated and the identity information of the bearer, a personal relationship between the current operator and the bearer of the first bank card, where the personal relationship includes a relationship in n generations, a non-relationship, and the like, n is an integer greater than 1, and n is 3, where the application does not limit a specific value of n, and does not limit an implementation process of how the public security management system obtains the personal relationship, and a content included in the personal relationship.

Step S211, receiving the character relationship between the current operator and the first bank card holder fed back by the public security management system;

step S212, acquiring a misoperation verification rule preset by a local banking institution;

step S213, verifying whether the character relationship accords with the misoperation verification rule, and if so, entering step S214; if not, go to step S215;

for the bank institutions in different regions, different misoperation verification rules can be set, namely the verification standard for whether the user mistakenly takes the bank card can be different, the setting basis and the requirement of the misoperation verification rules are not limited, and the misoperation verification rules can be determined according to the business requirement, the management requirement and the like of the corresponding bank institutions, and the detailed description is omitted here.

In general, in combination with the above analysis description on whether the user mistakenly takes the bank card, the situation is usually caused between relatives, and therefore, the misoperation can be realized according to the analysis description when the misoperation verification rule is formulated, if the bank card holder and the current operator are not the same person, but the bank card holder and the current operator are relatives within m generations, m is an integer greater than 1, for example, m is 3, it can be considered that the current operator mistakenly takes the bank card holder's bank card, and in order to avoid the misoperation caused by the above, the bank card account is locked, the current operator can be reminded of the verification result; otherwise, it is stated that the operator does not mistakenly take the first bank card at present, the holder of the first bank card may be prompted as needed, or the input of the primary account password value is currently allowed, the re-input may be prompted, and the like.

In some embodiments, the misoperation verification rule may be a rule fed back by a staff of a corresponding banking institution in the bank, and the rule is reported to the bank management system through a corresponding terminal device in a manner of text, voice, and the like, the reported rule information is processed by the bank management system to obtain the misoperation verification rule applicable to the banking institution, and the misoperation verification rule is associated with an identifier (such as a unique identifier of the banking institution) of the banking institution, so as to subsequently query the misoperation verification rule corresponding to the banking institution.

It should be understood that, for the above-mentioned misoperation verification rule, in order to enable the self-service device or the service device to implement verification of human-physical relationship based on this, a verification program characterizing the misoperation verification rule is usually written in advance, and the verification process is implemented by executing the verification program, and the writing implementation manner of the verification program is not described in detail in this application.

Step S214, outputting first reminding information of the current first bank card taken by the operator by mistake;

as described above, when it is determined that the current operator has taken the first bank card by mistake, the first reminding information is output to actively inform the current operator that the current operator has taken the bank card of the parent by mistake, and the input account password value is not the account password value of the first bank card, at this time, the current operator usually does not input the account password value of the bank card held by the current operator with respect to the first bank card any more, so that the situation that the authentication failure times of the account password value reach the error times threshold value, which causes the bank management system to perform an intervention measure on the first bank card, such as locking the first bank card, is avoided.

It should be noted that, the output mode and the output content of the first reminding information are not limited in the present application, and may be directly presented in a display screen of the self-service device in a text manner, may be output in a voice playing manner, and the like, which may be determined according to the circumstances, and the present application is not described in detail herein.

In still other embodiments provided by the present application, in a case that the verification result is yes, the present application may further send fifth prompting information (for example, in a short message manner, in a voice manner, and the like) to a preset terminal of the holder of the first bank card, where the fifth prompting information may include a verification result that the first bank card is operated by mistake, identity information to be authenticated of a current operator, and/or a character relationship between the current operator and the holder, so that the holder of the first bank card can know the situation in time, thereby avoiding urgency caused by the fact that the first bank card cannot be found, and improving customer experience.

Step S215, outputting a second reminding message for prompting the current operator to input the password again.

As described above, in the embodiment of the present application, under the condition that the prediction probability does not reach the probability threshold, the to-be-authenticated identity information matched with the face recognition result is not detected, the person relationship does not conform to the misoperation verification rule, and the like, the second reminding information may be output, at this time, the current operator may continue to input the account password value, and when the authentication failure number of the account password value reaches the error number threshold, the bank management system directly executes an intervention measure on the first bank card, such as locking the first bank card, to ensure the fund security of the holder of the first bank card.

In another possible implementation manner, in a case that the detection result is negative, the self-service device may further output third prompting information that the current operator performs illegal operations on the first bank card, so as to discourage the current operator from stopping the current illegal activities in time, and in this case, the self-service device may prohibit a response to an input instruction for the first bank card, so as to prevent the current operator from stealing funds of the account of the first bank card, and the like, and may further send fourth prompting information that the first bank card is operated illegally to a preset terminal of a holder of the first bank card, and inform the holder of the first bank card that the current person attempts to use the first bank card illegally, so that the holder may take corresponding measures to ensure the fund security and the like of the first bank card.

To sum up, when a current operator (user) handles a business with a first bank card, the account password value input by the current operator is authenticated, if the authentication fails for multiple times but does not reach the threshold of the number of wrong times, the method can detect whether the current operator mistakenly holds the first bank card of a parent, specifically, can extract the characteristics of the password input information aiming at the first bank card and the authentication information of a second bank card associated with the identifier of the first bank card, input the obtained password characteristic vector into a misoperation prediction model obtained by pre-training, output the prediction probability of the current operator mistakenly holding the first bank card, if the prediction probability reaches the probability threshold, further perform face recognition on the current operator, thereby obtaining the character relationship between the current operator and the holder of the first bank card through a public security management system according to the identity information obtained by the face recognition, if the misoperation verification rule of the local banking institution is met, the current operator is reminded of taking the first bank card of the relative by mistake, and the input of the wrong password to the first bank card is stopped, so that the first bank card account is locked due to the wrong input password, the inconvenience and the panic of a holder of the first bank card account due to the locking of the bank card account are avoided, and the customer experience is improved.

Certainly, through the verification, if it is determined that the current operator does not accidentally take the first bank card of the relative, it may be considered that the current operator is currently performing an illegal operation on the first bank card, and when it is determined that the password failure authentication frequency reaches the error frequency threshold value, an intervention operation on the first bank card is performed, such as locking the first bank card, to ensure the fund security of the holder of the first bank card.

Referring to fig. 3, a schematic structural diagram of an alternative example of the bank card misoperation processing device provided by the present application may include:

the password authentication module 31 is used for authenticating the account password value input by the current operator for the first bank card;

an information obtaining module 32, configured to obtain password input information for the first bank card and second bank card authentication information associated with an identifier of the first bank card if authentication fails;

the misoperation predicting module 33 is used for determining the prediction probability that the current operator mistakenly takes the first bank card according to the password input information and the second bank card authentication information;

the identity recognition module 34 is configured to perform identity classification on the current operator to obtain identity information to be authenticated of the current operator when the prediction probability reaches a probability threshold;

a person relationship obtaining module 35, configured to obtain, according to the identity information to be authenticated, a person relationship between the current operator and a holder of the first bank card;

and the misoperation reminding module 36 is configured to determine whether to output a reminding message that the current operator mistakenly takes the first bank card according to the obtained character relationship.

In some embodiments proposed in the present application, as shown in fig. 4, the identity module 34 may include:

a face recognition unit 341, configured to perform face recognition on the current operator to obtain a face recognition result of the current operator;

a first identity detection unit 342, configured to detect whether there is client identity information that matches the face recognition result;

a first identity determining unit 343, configured to determine, if the detection result of the identity detecting unit is yes, the detected client identity information as the identity information to be authenticated.

In still other embodiments, the identification module 34 may also include:

the fingerprint identification unit is used for carrying out fingerprint identification on the current operator to obtain a fingerprint identification result of the current operator;

the second identity detection unit is used for detecting whether the client identity information matched with the fingerprint identification result exists or not;

and the second identity determining unit is used for determining the detected client identity information as the identity information to be authenticated under the condition that the detection result of the identity detecting unit is positive.

Accordingly, for other identification manners, the identification module 34 may include a corresponding unit for implementing the identification, which is not described in detail in this application.

Optionally, as shown in fig. 5, the person relationship obtaining module 35 may include:

a holder identity acquiring unit 351 for acquiring holder identity information associated with the identification of the first bank card;

a personal relationship query unit 352, configured to send the identity information to be authenticated and the identity information of the holder to a public security management system, where the public security management system determines, according to the identity information to be authenticated and the identity information of the holder, a personal relationship between the current operator and the holder of the first bank card, where the personal relationship includes a relationship and a non-relationship in n generations, and n is an integer greater than 1;

the person relation receiving unit 353 is configured to receive the person relation fed back by the public security management system.

In a possible implementation manner, as shown in fig. 5, the misoperation reminding module 36 may include:

the misoperation verification rule obtaining unit 361 is used for obtaining misoperation verification rules preset by a local banking institution;

a person relationship verification unit 362 for verifying whether the person relationship conforms to the misoperation verification rule;

and the first reminding information output unit 363 is configured to output the first reminding information that the current operator mistakenly takes the first bank card, if the verification result of the person relationship verification unit is yes.

Based on the description of the above embodiment, the apparatus may further include:

the second reminding information output device is used for outputting second reminding information for reminding the current operator to input the password again under the condition that the prediction probability does not reach the probability threshold value or the character relationship does not accord with the misoperation verification rule; or,

a third reminding information output device, configured to output third reminding information of illegal operation of the current operator on the first bank card and prohibit a response to an input instruction for the first bank card, when the prediction probability does not reach the probability threshold or the person relationship does not meet the misoperation verification rule;

and the fourth reminding information sending module is used for sending fourth reminding information that the first bank card is illegally operated to a preset terminal of the holder of the first bank card.

Optionally, the apparatus may further include:

and a fifth reminding information output device, configured to send fifth reminding information to a preset terminal of the holder of the first bank card if the verification result of the person relationship verification unit is yes, where the fifth reminding information includes that the first bank card is operated by mistake, the identity information to be authenticated of the current operator, and/or the person relationship between the current operator and the holder.

Based on the device structure described in the foregoing embodiments, referring to fig. 6, the information obtaining module 32 may include:

a first information obtaining unit 321, configured to obtain an account password value input for each time by the first bank card, a first input time interval of each character in the account password value, and a second input time interval between different account password values;

a second information obtaining unit 322, configured to identify an identifier of the first bank card, and obtain second bank card authentication information associated with the identifier, where the second bank card authentication information includes an account password value of the second bank card.

Accordingly, as shown in fig. 6, the misoperation prediction module 33 may include:

a password feature vector obtaining unit 331, configured to perform feature extraction on the password input information and the second bank card authentication information to obtain a corresponding password feature vector;

the prediction processing unit 332 is configured to input the password feature vector into a misoperation prediction model for processing, and output a prediction probability that the current operator mistakenly takes the first bank card;

It should be noted that, various modules, units, and the like in the embodiments of the foregoing apparatuses may be stored in the memory as program modules, and the processor executes the program modules stored in the memory to implement corresponding functions, and for the functions implemented by the program modules and their combinations and the achieved technical effects, reference may be made to the description of corresponding parts in the embodiments of the foregoing methods, which is not described in detail in this embodiment.

The present application further provides a storage medium, where a program is stored, and when the program is executed by a processor, the method implements the steps of the method for processing the misoperation of the bank card, and a specific implementation process may refer to descriptions of corresponding parts in the embodiments of the method, which are not described in detail in this embodiment.

Referring to fig. 7, a schematic structural diagram of an optional example of the device for processing misoperation of the bank card provided by the present application may include: at least one communication interface 71, at least one memory 72, and at least one processor 73, wherein:

the communication interface 71, the memory 72 and the processor 73 can be connected with a communication bus to realize mutual data interaction, and the connection relation of the lines in the misoperation processing equipment of the bank card is not detailed one by one, and can be determined according to the communication requirement of an actual application scene.

The communication interface 71 may include an interface of a communication module, such as a GSM module, a WIFI module, an interface for implementing data communication of a mobile communication network (such as a 5G network or a 6G network), and in practical applications, it may be used to implement data interaction with other devices, such as transmitting image information, fingerprint information, account password value, and the like of a current operator captured by the image collector.

According to actual needs, the communication interface 71 may further include interfaces such as a USB interface, a serial/parallel interface, and the like, for implementing data interaction between internal components of the device, for example, various intermediate data, input parameters, and the like generated or required in the implementation process of the bank card misoperation processing method provided by the present application may be determined according to requirements of an actual application scenario, and details of the present application are not described in detail.

The memory 72 may store a program formed by a plurality of instructions for implementing the bank card misoperation processing method provided by the embodiment of the present application, and the processor 73 calls and loads the program stored in the memory 72, so as to implement the bank card misoperation processing method provided by the embodiment of the present application, and the specific implementation process may refer to, but is not limited to, the following description of the corresponding embodiments.

In the present embodiment, the memory 72 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid state storage device. The processor 73 may be a Central Processing Unit (CPU), an application-specific integrated circuit (ASIC), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic device.

In one possible implementation, the memory 72 may include a program storage area and a data storage area, and the program storage area may store an operating system, and application programs required for at least one function (such as an image processing function and an information display function), programs for implementing the bank card misoperation processing method proposed in the present application, and the like; the data storage area can store data generated in the using process of the equipment, such as account password values input by the current operator, collected identity information of the current operator and the like, as the case may be.

In some embodiments provided by the present application, the bank card misoperation processing device provided by the present application may be a service device (such as a management server in a bank management system) or a self-service device. For the service equipment, the self-service equipment is usually required to cooperate with the bank card misoperation processing method provided by the application, for example, the self-service equipment sends the collected password input information, identity identification information and the like to the service equipment for processing, and the specific implementation process is not detailed in the application.

In the case that the device for processing the misoperation of the bank card is a self-service device, as shown in fig. 8, the device may further include: input assembly 74, image collector 75 and display screen 76, wherein:

the input component 74 may be configured to obtain a corresponding account code value in response to a current operator account code input operation for the first bank card.

Referring to an optional scenario diagram shown in fig. 8, after the current operator inserts the first bank card into the slot of the self-service device, the operator may operate a virtual button or an entity input key output by the display screen to input an account password value, the structure type of the input component 74 is not limited in the present application, and may be a virtual keyboard component, an entity keyboard, a voice recognition component, or the like, for different types of input components 74, the input mode for inputting the account password value may be different, and the detailed description is not given in the present application.

The image collector 75 may be used to collect a face image of the current operator.

In combination with the description of the corresponding part of the above embodiment of the method, the face recognition is used as an identity recognition mode for the current operator, and the image collector 75 may be started to enter the working state and collect the face image of the current operator to implement the face recognition authentication under the condition that the prediction probability reaches the probability threshold, and the specific implementation process may refer to the description of the corresponding part of the above embodiment, which is not repeated in this embodiment.

It should be understood that, for other identification manners, the self-service device needs to be configured with corresponding identification components, such as a fingerprint identification component, a voice identification component, and the like, fig. 8 only shows an application scenario of identification, which is not limited to the composition structure of the self-service device, and the composition structure of the self-service device can be adapted and adjusted according to the change of the application requirement, and details of this embodiment are not described.

In practical application, the image collector can be a camera integrated in self-service equipment or an independent camera, the product type of the image collector is not limited in the application, the image collector can be determined according to the requirements of practical application scenes, but the shooting lens of the image collector is required to face the current operator, and at least the face image of the current operation can be shot, but the image collector is not limited to the above, and can be determined according to the specific implementation mode of identity recognition, and the detailed description is not given in the application.

Display screen 76 may be used to output a reminder that the current operator has taken the first bank by mistake.

As described in the above embodiment, the prompt information indicating that the operator has taken the first bank by mistake is output through the display screen, which is only an optional prompt mode, and other prompt modes such as voice prompt can be also used.

It can be seen that the structure of the self-service device described in the foregoing embodiments of the present application does not limit the bank card misoperation processing device in the embodiments of the present application, and in practical applications, the bank card misoperation processing device may include more or less components than the structure described in the foregoing embodiments, or may combine some components, such as at least one output device, such as a speaker, a vibration mechanism, a lamp, and the like, which are not listed herein.

The present application further provides a bank card misoperation processing system, which refers to but is not limited to the application scenario shown in fig. 8, where the system may include a self-service device, a service device, and a public security management system, and the application does not limit structural composition of the self-service device, the service device, and the public security management system, and refers to but is not limited to the description of the corresponding parts in the above embodiments.

It should be understood that the system structure composition proposed in the present application is not limited to the self-service device and the service device listed above, and may further include, for example, a database, a queuing device, a public security management system, and the like, which may be specifically determined according to a specific application scenario of the bank card misoperation processing method, and the present application is not described in detail herein.

Finally, it should be noted that, in the present specification, the embodiments are described in a progressive or parallel manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. The device, the equipment and the system disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to 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

1. A bank card misoperation processing method is characterized by comprising the following steps:

2. The method according to claim 1, wherein the identifying the current operator to obtain the identity information to be authenticated of the current operator comprises:

3. The method according to claim 2, wherein the determining whether to output the reminding message of the current operator mistaking the first bank card according to the obtained character relationship comprises:

4. The method of claim 3, wherein if the predicted probability does not meet the probability threshold or the human relationship does not meet the faulty operation verification rule, the method further comprises:

5. The method of claim 3, wherein if the person relationship complies with the maloperation verification rule, the method further comprises:

6. The method according to any one of claims 1 to 5, wherein the determining the predicted probability that the current operator mistakenly takes the first bank card according to the password input information and the second bank card authentication information comprises:

7. The method of claim 6, wherein obtaining password input information for the first bank card and second bank card authentication information associated with the identity of the first bank card comprises:

8. A bank card malfunction processing apparatus, characterized in that the apparatus comprises:

9. A bank card malfunction processing apparatus, characterized in that the apparatus comprises: at least one communication interface, at least one memory, and at least one processor, wherein:

the memory is used for storing a program for realizing the bank card misoperation processing method according to any one of claims 1 to 7;

the processor is used for loading and executing the program stored in the memory so as to realize the steps of the bank card misoperation processing method according to any one of claims 1 to 7.

10. The device of claim 9, wherein the device is a self-service device, the device further comprising:

the image collector is used for collecting a face image of a current operator;