CN111652596A - Anti-fraud method, device, terminal equipment and storage medium for credit business - Google Patents

Abstract

The invention relates to the technical field of financial technology, and discloses an anti-fraud method, device, terminal device and computer storage medium for credit business. The anti-fraud method for the credit business includes: when it is determined that the credit business needs identity verification, collecting historical behavior data of the user to be verified; if it is determined according to the historical behavior data that face recognition is required, collecting the Identify the face data of the verified user and obtain the face recognition result; analyze the face recognition result and output the asynchronous audit mode, and receive the verification result of the identity verification of the user to be verified according to the asynchronous verification method ; Perform corresponding processing on the credit business according to the audit result. The invention avoids the problems of serious human resource consumption caused by traditional anti-fraud methods and poor timeliness of identity verification for users, and achieves a good balance between the anti-fraud risk control and the timeliness of verification for users.

Description

Anti-fraud method, device, terminal equipment and storage medium for credit business

technical field

The present invention relates to the technical field of financial technology (Fintech), in particular to an anti-fraud method, device, terminal device and computer storage medium for credit business.

Background technique

With the development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually transforming into financial technology (Fintech). requirements.

Nowadays, for the processing of high-risk financial services such as bank account opening, loan application, investment and wealth management, and sensitive information modification, it is necessary to use face recognition system technologies such as "face collection, portrait comparison, and liveness detection" or artificially conduct asynchronous review. Verify the user's identity to ensure the authenticity of the user's identity and meet the security requirements of remote real-name authentication. However, on the one hand, it is difficult to effectively prevent counterfeiting attacks such as "secondary retakes, snapping pictures, prints, video frame extraction, high imitation molds, and third-person face brushing" based on system technology, and it is difficult to avoid counterfeiting. Fraudulent behaviors such as account opening, counterfeit loans, account takeover, account theft, etc.; on the other hand, if manual asynchronous audits continue to be implemented after system-based technical verification, this will not only consume a large amount of human resources, but also reduce the timeliness of certification. very bad.

To sum up, how to further ensure the timeliness and user experience of the core body under the premise of ensuring the authentication efficiency of the core body for users to achieve effective risk control has always been an urgent problem to be solved in the industry.

SUMMARY OF THE INVENTION

The main purpose of the present invention is to provide an anti-fraud method, device, terminal device and computer storage medium for credit business, aiming at realizing effective risk control under the premise of ensuring the authentication efficiency of verification for users and improving the risk control of users. Carry out the timeliness of nuclear body to achieve a good balance between risk control and timeliness.

In order to achieve the above object, the present invention provides an anti-fraud method for credit business, and the anti-fraud method for credit business includes:

When determining that identity verification is required for the credit business, collect historical behavior data of the user to be verified;

If it is determined according to the historical behavior data that face recognition is required, the face data of the user to be verified is collected for identification and a face recognition result is obtained;

Analyzing the face recognition result and outputting an asynchronous auditing method, and receiving an auditing result of performing identity verification on the user to be verified according to the asynchronous auditing method;

Corresponding processing is performed on the credit business according to the audit result.

Optionally, after the step of analyzing the face recognition result and outputting an asynchronous review mode, and receiving the review result of performing identity verification on the user to be verified according to the asynchronous review mode, the method further includes:

If the audit result is not received for a preset period of time, detecting the overall risk level of the credit business;

If the overall risk level is lower than the preset risk level threshold, the credit business is started by verifying the identity of the user to be authenticated.

Optionally, the step of collecting the historical behavior data of the user to be verified when it is determined that the credit business needs to be verified, includes:

If it is detected that the credit business belongs to a preset high-risk financial business, it is determined that the credit business needs to be authenticated;

A user who initiates a business processing request for the credit business is marked as a user to be verified, and historical behavior data of the user to be verified is collected.

Optionally, after the step of collecting the historical behavior data of the user to be verified, the method further includes:

Determine whether face recognition needs to be performed on the user to be verified according to the historical behavior data;

The step of determining whether it is necessary to perform face recognition on the user to be verified according to the historical behavior data includes:

If it is detected that there is negative behavior data in the historical behavior data, it is determined that face recognition needs to be performed on the user to be verified;

If it is detected that there is no negative behavior data in the historical behavior data, it is determined that face recognition is not required for the user to be verified.

Optionally, the asynchronous review methods include: no need for asynchronous review, first pass and then review, and first review and then pass,

The step of analyzing the face recognition result and outputting the asynchronous review mode includes:

If it is obtained from the analysis that the authentication index value of the face recognition result mapping is high, output the asynchronous auditing not required;

If the value of the authentication index mapped by the face recognition result is found in the analysis, output the first pass and then review;

If the analysis shows that the authentication index value mapped by the face recognition result is low, output the first review and then pass.

Optionally, the step of performing corresponding processing on the credit business according to the audit result includes:

If the verification result indicates that the user to be verified has passed the verification, then start processing the credit business;

If the verification result indicates that the verification of the user to be verified fails, the processing of the credit business that has already been processed will be stopped, or the credit business that has been processed will be dunned in advance.

Optionally, the step of performing corresponding processing on the credit business according to the audit result further includes:

If the audit result identifies that the user to be authenticated has malicious attack intent, the financial account associated with the credit business is detected, and the financial account is managed and controlled.

In addition, in order to achieve the above object, the present invention also provides an anti-fraud device for credit business, and the anti-fraud device for credit business includes:

a data collection module, used to collect historical behavior data of the user to be verified when it is determined that the credit business needs to be verified;

a data processing module, configured to collect the face data of the user to be verified for identification and obtain a face recognition result if it is determined according to the historical behavior data that face recognition is required;

an auditing and deployment module, configured to analyze the face recognition result and output an asynchronous auditing method, and receive an auditing result of performing identity verification on the user to be verified according to the asynchronous auditing method;

A business processing module, configured to perform corresponding processing on the credit business according to the audit result.

In addition, in order to achieve the above object, the present invention also provides a terminal device, the terminal device includes: a memory, a processor, and an anti-fraud program for credit business stored on the memory and running on the processor, The anti-fraud program of the credit business, when executed by the processor, implements the steps of the anti-fraud method of the credit business as described above.

In addition, in order to achieve the above object, the present invention also provides a computer storage medium, on which an anti-fraud program for credit business is stored, and the anti-fraud program for credit business is executed by a processor to achieve the above-mentioned The steps of the anti-fraud method of credit business.

The present invention provides an anti-fraud method, device, terminal device and computer storage medium for credit business, by collecting historical behavior data of users to be verified when it is determined that identity verification is required for the credit business; If the data determines that face recognition is required, then collect the face data of the user to be verified for identification and obtain the face recognition result; analyze the face recognition result and output the asynchronous review mode, and receive the user according to the asynchronous review mode. The verification result of performing identity verification on the user to be verified; and performing corresponding processing on the credit business according to the verification result.

When judging that the credit business applied for by the user needs to be verified for the user, the present invention further combines the historical behavior data of the user to determine whether face recognition needs to be performed for the user, so as to ensure the basic authentication efficiency for the verification of the user. Anti-fraud risk control; and call the face recognition system to collect face data for identification only when it is determined to be necessary, which further improves the intelligence and timeliness of risk control for user identity audit; After analyzing the results and outputting different asynchronous auditing methods to call manual asynchronous auditing, it not only avoids the traditional anti-fraud method to continue to implement manual asynchronous auditing in the application of face recognition system, but also causes serious consumption of human resources and poor timeliness. It achieves a good balance between the anti-fraud risk control of user verification and the timeliness of verification.

Description of drawings

1 is a schematic diagram of a device structure of a hardware operating environment involved in an embodiment of the present invention;

2 is a schematic flowchart of an embodiment of an anti-fraud method for credit business according to the present invention;

3 is a schematic flowchart of another embodiment of the anti-fraud method for credit business according to the present invention;

FIG. 4 is a schematic diagram of a detailed flow of step S30 in an embodiment of the anti-fraud method for credit business according to the present invention;

5 is a schematic diagram of an application flow of an embodiment of an anti-fraud method for credit business according to the present invention;

FIG. 6 is a schematic diagram of functional modules of the first embodiment of the anti-fraud device for credit business according to the present invention.

The realization, functional characteristics and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed ways

It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

Referring to FIG. 1 , FIG. 1 is a schematic diagram of a device structure of a hardware operating environment involved in an embodiment of the present invention.

The terminal device in the embodiment of the present invention may be a smart phone, or may be a terminal device such as a PC (Personal Computer, personal computer), a tablet computer, and a portable computer.

As shown in FIG. 1 , the terminal device may include: a processor 1001 , such as a CPU, a communication bus 1002 , a user interface 1003 , a network interface 1004 , and a memory 1005 . Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (eg, a Wi-Fi interface). The memory 1005 may be high-speed RAM memory, or may be non-volatile memory, such as disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .

Those skilled in the art can understand that the structure of the terminal device shown in FIG. 1 does not constitute a limitation on the terminal device, and may include more or less components than those shown in the figure, or combine some components, or arrange different components.

As shown in FIG. 1 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an anti-fraud program for credit business.

In the terminal shown in FIG. 1 , the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server; the user interface 1003 is mainly used to connect to the client and perform data communication with the client; and the processor 1001 can be used for The anti-fraud program of the credit service stored in the memory 1005 is invoked, and the following operations are performed:

When determining that identity verification is required for the credit business, collect historical behavior data of the user to be verified;

If it is determined according to the historical behavior data that face recognition is required, the face data of the user to be verified is collected for identification and a face recognition result is obtained;

Analyzing the face recognition result and outputting an asynchronous auditing method, and receiving an auditing result of performing identity verification on the user to be verified according to the asynchronous auditing method;

Corresponding processing is performed on the credit business according to the audit result.

Further, the processor 1001 can call the anti-fraud program of the credit business stored in the memory 1005, analyze the face recognition result and output the asynchronous auditing method, and receive the user to be verified according to the asynchronous auditing method. After the audit results for identity verification, the following actions are also performed:

If the audit result is not received for a preset period of time, detecting the overall risk level of the credit business;

If the overall risk level is lower than the preset risk level threshold, the credit business is started by verifying the identity of the user to be authenticated.

Further, the processor 1001 can call the anti-fraud program of the credit business stored in the memory 1005, and also perform the following operations:

If it is detected that the credit business belongs to a preset high-risk financial business, it is determined that the credit business needs to be authenticated;

A user who initiates a business processing request for the credit business is marked as a user to be verified, and historical behavior data of the user to be verified is collected.

Further, the processor 1001 may call the anti-fraud program of the credit business stored in the memory 1005, and after performing the collection of the historical behavior data of the user to be verified, the following operations may also be performed:

Determine whether face recognition needs to be performed on the user to be verified according to the historical behavior data;

The processor 1001 can call the anti-fraud program of the credit business stored in the memory 1005, and also perform the following operations:

If it is detected that there is negative behavior data in the historical behavior data, it is determined that face recognition needs to be performed on the user to be verified;

If it is detected that there is no negative behavior data in the historical behavior data, it is determined that face recognition is not required for the user to be verified.

Further, the asynchronous review methods include: no need for asynchronous review, first pass and then review, and first review and then pass, the preset theme also includes a policy theme, and the processor 1001 can call the anti-fraud program of the credit business stored in the memory 1005. , and also do the following:

If it is obtained from the analysis that the authentication index value of the face recognition result mapping is high, output the asynchronous auditing not required;

If the value of the authentication index mapped by the face recognition result is found in the analysis, output the first pass and then review;

If the analysis shows that the authentication index value mapped by the face recognition result is low, output the first review and then pass.

Further, the processor 1001 can call the anti-fraud program of the credit business stored in the memory 1005, and also perform the following operations:

If the verification result indicates that the user to be verified has passed the verification, then start processing the credit business;

If the verification result indicates that the verification of the user to be verified fails, the processing of the credit business that has already been processed will be stopped, or the credit business that has been processed will be dunned in advance.

Further, the processor 1001 can call the anti-fraud program of the credit business stored in the memory 1005, and also perform the following operations:

If the audit result identifies that the user to be authenticated has malicious attack intent, the financial account associated with the credit business is detected, and the financial account is managed and controlled.

Based on the above hardware structure, various embodiments of the anti-fraud method for credit business of the present invention are proposed.

It should be noted that, for the processing of high-risk financial services such as bank account opening, loan application, investment and wealth management, and sensitive information modification, it is necessary to use face recognition system technology such as "face collection, portrait comparison, and live detection" or manually. Asynchronous auditing is used to verify the user's identity to ensure the authenticity of the user's identity and meet the security requirements of remote real-name authentication. However, on the one hand, it is difficult to effectively prevent the risks of counterfeit attacks such as "secondary remakes, snapshots, prints, video frame extraction, high imitation molds, and third-person face brushing" based on system technology, and it is difficult to avoid counterfeit account opening. , fraudulent behaviors such as fake loans, account takeover, account theft, etc.; on the other hand, if the manual asynchronous audit will continue to be implemented after the verification based on the system technology, it will not only consume a large amount of human resources, but also the timeliness of certification is also very high. Difference.

To sum up, how to further ensure the timeliness and user experience of the core body under the premise of ensuring the authentication efficiency of the core body for users to achieve effective risk control has always been an urgent problem to be solved in the industry. In view of this, the present invention provides an anti-fraud method for credit business, which aims to improve the timeliness of verification for users on the premise of ensuring the authentication efficiency of verification for users to carry out effective risk control, so as to avoid risks Good balance between control and timeliness.

Referring to FIG. 2, FIG. 2 is a schematic flowchart of the first embodiment of the anti-fraud method for credit business of the present invention. In this embodiment, the anti-fraud method of the credit business includes:

Step S10, when it is determined that the credit business needs identity verification, collect historical behavior data of the user to be verified;

It should be noted that, the anti-fraud method for the credit service in this embodiment may be implemented by the above-mentioned terminal device.

The terminal device determines whether the user needs to perform identity verification before handling the credit business by detecting whether the credit business pointed to by the business processing request initiated by the user belongs to the preset high-risk financial business, and determines whether the user needs to conduct the credit business before handling the credit business. When identity verification is required, the historical behavior data of the user for financial credit business processing is collected.

It should be noted that, in this embodiment, the preset high-risk financial services may be one or more types of financial services preset by the staff of the enterprise. Specifically, for example, enterprise staff may pre-set financial services such as bank account opening, loan application, investment and wealth management, and sensitive information modification as high-risk financial services based on actual work needs. It should be understood that, based on different design needs of practical applications, the preset high-risk financial business can of course also be different from the other business of the above-listed financial business in other ways different from those set forth by the staff independently. The type is also set as a preset high-risk financial service, and the anti-fraud method for credit service of the present invention does not specifically limit the type and setting method of the preset high-risk financial service.

Further, in a feasible embodiment, the above step S10 may include:

Step S101, if it is detected that the credit business belongs to a preset high-risk financial business, it is determined that the credit business requires identity verification;

When the terminal device detects that the credit business specified in the business processing request initiated by the user belongs to a preset high-risk financial business, the terminal device immediately determines that the user needs to perform identity verification on the user before handling the credit business.

Specifically, for example, as shown in the application process shown in FIG. 5 , after receiving the service processing request initiated by the user, the terminal device detects that the credit service specified by the service processing request is a loan application, and the terminal device detects that the credit service The business-loan application belongs to one of the above-mentioned high-risk financial services pre-defined by the enterprise staff, and the terminal device determines that the current user needs to scan the user's face before processing the credit business-loan application. Face recognition method for identity verification.

Further, in another embodiment, if the terminal device detects that the credit business specified by the business processing request initiated by the user does not belong to any one of the high-risk financial services predefined by the enterprise staff, the terminal The device will determine that the user does not need to verify the identity of the user before handling the credit business, and directly starts the process of handling the credit business.

Step S102, marking the user who initiates a business processing request for the credit business as a user to be verified, and collects historical behavior data of the user to be verified.

It should be noted that, in this embodiment, the historical behavior data may specifically be all the behavior data of the user in the process of handling the financial business recorded by the terminal device.

After the terminal device determines that the user needs to verify the identity of the user before processing the requested credit business, the terminal device first marks the user as a user to be verified that needs to be verified, and then handles any financial business from the storage of all users. From the database of behavior data generated in the process, extract all behavior data of the user to be verified.

Specifically, for example, when the user handles any financial business developed by the enterprise, the terminal device records all behavior data generated based on user operations, and stores the behavior data in a pre-configured dedicated store for all user transactions. In the database of behavior data generated in the process of any financial business, when the terminal device determines that the current user needs to verify the identity of the user before processing the credit business-loan application requested by him, the terminal device first marks the user. For the user to be verified who needs to be verified, and then based on any characteristic information of the user to be verified (such as name + mobile phone number, etc.) In the process of matching and extracting all the behavior data generated by the user to be verified in the process of handling the financial business developed by the enterprise (such as bank account opening, loan application, investment and wealth management, and sensitive information modification, etc.).

In this embodiment, after it is determined that the user needs to be swiped for identity verification, the face recognition system is not directly called to perform the authentication operation based on the system technology, but priority is given to obtaining the user's previous authentication operation. The historical behavior data handled by financial business is used for subsequent analysis of whether to perform face recognition authentication operations, which improves the intelligence of user identity verification, and avoids the need for face recognition operations in the traditional way. The face recognition system is still called to perform the authentication operation of face recognition on the user, which causes the waste of system resources and reduces the timeliness of authentication, and improves the authentication efficiency of user identity verification.

Further, in a feasible embodiment, after step S10, the anti-fraud method for credit business of the present invention may further include:

Step A: Determine whether face recognition needs to be performed on the user to be verified according to the historical behavior data.

After the terminal device extracts all the behavior data of the user to be verified from the database that stores the behavior data generated by all users in the process of handling any financial business, the terminal device further determines whether to call the face recognition system based on the all behavior data. The system technology performs face recognition on the user to be authenticated to authenticate and verify the identity of the user to be authenticated.

Further, in a feasible embodiment, step A may include:

Step A1, if it is detected that there is negative behavior data in the historical behavior data, it is determined that face recognition needs to be performed on the user to be verified;

Step A2, if it is detected that there is no negative behavior data in the historical behavior data, it is determined that face recognition is not required for the user to be verified.

Specifically, for example, as shown in the application process shown in FIG. 5 , the terminal device detects that the user to be verified is in the process of handling the financial business (such as bank account opening, loan application, investment and wealth management, and sensitive information modification, etc.) previously developed by the enterprise. In all the generated behavior data, whether there are negative behaviors such as arrears in repayment, filling in false information, etc., to determine whether it is necessary to call the face recognition system to perform face recognition for the user to be verified based on the system technology. That is, when the terminal device detects any type of negative behavior in all the behavior data, it determines that the face recognition system needs to be invoked to perform face recognition for the user to be verified based on the system technology, or the terminal device is detecting When there is no negative behavior of any kind in the whole behavior data, it is determined that it is not necessary to call the face recognition system to perform face recognition for the user to be verified based on the system technology.

In this embodiment, it is determined whether it is necessary to call the face recognition system to perform face recognition on the user based on the system technology based on the analysis of the historical behavior data generated by the user's handling of the enterprise development financial business. When there is a negative behavior in the user's financial business, it is determined that the user's face recognition is used to verify the identity. Based on the analysis of historical behavior data, it is determined that the user's financial business has always been positive, and there is no abnormal negative behavior. , it can be directly determined that the user does not need face recognition and is determined to pass the identity verification, which improves the intelligence of the user's identity verification, avoids the waste of system resources caused by the traditional verification method and reduces the authentication timeliness. Authentication efficiency for user identity verification.

Step S20, if it is determined that face recognition is required according to the historical behavior data, the face data of the user to be verified is collected for identification and a face recognition result is obtained;

If the terminal device determines that it needs to perform face recognition for the user to be verified based on analyzing the historical behavior data of the user to be verified to verify the identity, it calls the face recognition system to start collecting the face data of the user to be verified for identification. , and then the terminal device receives the face recognition result output by the face recognition system after recognizing the face data.

Specifically, for example, as shown in the application process shown in FIG. 5 , the terminal device detects that any type of negative behavior exists in all the behavior data, and thus determines that the face recognition system needs to be invoked to target the identity to be verified based on the system technology. When the user performs face recognition, the terminal device immediately calls the face recognition system (the face-swiping system shown in the figure) to prompt the user to be verified to perform face-swiping, so that the face recognition system is based on the collected data of the user to be verified. face data, and use the existing mature face recognition technology to identify and determine the current user to be verified from multi-factor identification such as facial facial features, facial feature extraction, face identity verification, face living identification, and face attribute recognition. The reliability of the face data is calculated and output to identify the face recognition result, and the terminal device receives the face recognition result.

Further, in a feasible embodiment, as shown in the application process shown in FIG. 5, after the terminal device receives the face recognition result output by the face recognition system, if the face recognition result is identified based on the system technology, If the face recognition authentication is passed, follow-up analysis of the face recognition result is performed to output the asynchronous review process of calling manual asynchronous review; or, if the face recognition result received by the terminal device identifies the face based on the system technology If the recognition authentication fails, the terminal device immediately determines whether the face recognition result complies with the preset "wrong pick and right" rule, and when it is determined to meet the "wrong pick and right" rule, it still conducts follow-up for the user to be verified The process of analyzing the face recognition result to output the asynchronous review method of calling manual asynchronous review. On the contrary, when the terminal device determines that the face recognition result does not meet the preset "wrong pick and right" rule, the terminal device will It is determined that the user to be authenticated has not passed the identity verification, that is, the service processing request initiated by the user is rejected.

It should be noted that, in this embodiment, when the terminal device analyzes the face recognition result for the user to be verified who meets the "wrong pick and right" rule to output the asynchronous audit method that invokes manual asynchronous audit, the terminal The device will directly output the asynchronous audit method that is reviewed first and then passed, so as to directly call the manual to perform identity authentication audit on the user to be verified, and perform identity authentication on the user to be verified in the received review result of the manual feedback. When the verification is passed, the processing of the credit business specified in the business processing request initiated by the user to be verified will begin, otherwise, the terminal device will directly refuse to handle the credit business.

Step S30, analyzing the face recognition result and outputting an asynchronous auditing method, and receiving an auditing result of performing identity verification on the user to be verified according to the asynchronous auditing method;

After the terminal device obtains the face recognition result by calling the face recognition system to perform face recognition on the user to be verified based on the system technology, it analyzes the authentication index mapped by the face recognition result, and the corresponding output based on the level of the authentication index is different. The asynchronous auditing method of the system calls the manual to perform the auditing process according to the asynchronous auditing method, and then the terminal device receives the auditing result of the identity verification of the authenticated user based on the feedback after the manual asynchronous auditing.

Further, please refer to the detailed process of step S30 shown in FIG. 4 , in a feasible embodiment, the asynchronous auditing method output by the terminal device based on the authentication index mapped by analyzing the face recognition result includes: no asynchronous The above-mentioned step S30 may include:

Step S301, if the authentication index value mapped by the face recognition result is found to be high, output the asynchronous auditing not required;

Specifically, for example, as shown in the application process shown in FIG. 5, the terminal device analyzes the face recognition result obtained by invoking the face recognition system based on the system technology for the face recognition of the user to be verified, and detects that the face recognition When the index values of the certification indicators such as "Portrait Comparison Score" and "Liveness Monitoring Score" mapped by the result are high, the terminal device outputs an asynchronous audit method that does not require asynchronous auditing, so that there is no need to call further manual operations for the user to be verified. and directly output the verification result of the identity verification of the user to be verified, so as to start processing the credit business-loan application designated by the application for the business application initiated by the user to be verified.

Step S302, if the authentication index value of the face recognition result mapping is obtained through analysis, output the first pass and then review;

Specifically, for example, as shown in the application process shown in FIG. 5, the terminal device analyzes the face recognition result obtained by invoking the face recognition system based on the system technology for the face recognition of the user to be verified, and detects that the face recognition The index value of the authentication indicators such as "portrait comparison score" and "living monitoring score" mapped by the result is medium, and the terminal device outputs the asynchronous audit method of passing first and then auditing, so as to output the identity authentication verification for the user to be verified first. The approved review result is used to start processing the credit business-loan application specified in the application for the business initiated by the user to be verified, and at the same time or after starting to process the credit business-loan application for the user to be verified, further call Manually conduct further review for the users to be verified.

Step S303 , if the authentication index value mapped by the face recognition result is found to be low after analysis, output the first review and then pass.

Specifically, for example, as shown in the application process shown in FIG. 5, the terminal device analyzes the face recognition result obtained by invoking the face recognition system based on the system technology for the face recognition of the user to be verified, and detects that the face recognition The index values of the certification indicators such as "portrait comparison score" and "living monitoring score" mapped by the result are low, and the terminal device outputs an asynchronous audit method that is reviewed first and then passed, so as to further call the manual for further review of the user to be verified. , and only when the verification is passed, the verification result of the identity verification of the user to be verified is output, so as to start processing the credit business - loan application specified in the application for the business initiated by the verification user.

Step S40, performing corresponding processing on the credit business according to the audit result.

The terminal device outputs the asynchronous review method of first passing and then reviewing, so as to first start to process the credit business specified in the application for the user to initiate the business application, and then the terminal device receives the call manual for the pending credit business at the same time or later. After the verification result of the verification user's identity verification verification, if the verification result indicates that the verification user has passed the verification verification, the credit business will continue to be processed and the prompt information of the verification verification can be output. If the result indicates that the identity authentication review fails, the terminal device will immediately stop processing the credit business or carry out an advance payment dunning operation for the credit business that has already been processed; After calling the manual for the verification result of the identity verification verification for the verified user before starting to process the credit business, if the verification result indicates that the verification of the verification user's identity verification has passed, the credit business will be processed and the identity verification can be output. Prompt information indicating that the verification is passed, or, if the verification result indicates that the identity authentication verification has not passed, the terminal device refuses to handle the credit business and can output the prompt information that the identity verification has not passed.

The embodiment of the present invention provides an anti-fraud method for credit business, which collects the user's history of financial credit business when judging the financial credit business and determining that the user's identity verification needs to be performed before starting to process the credit business request. Behavior data, and then further combined with the historical behavior data to determine whether the user needs face recognition during the nurturing process, and after determining that face recognition is required, collect the user's face data for recognition and obtain the face recognition result. , analyze the face recognition structure and output the asynchronous auditing method that calls manual asynchronous auditing, and finally receive the auditing result of the manual verification of the user according to the asynchronous auditing method, so as to identify the user based on the auditing result. Carry out corresponding processing on credit business according to the situation.

When judging that the credit business applied for by the user needs to be verified for the user, the present invention further combines the historical behavior data of the user to determine whether face recognition needs to be performed for the user, so as to ensure the basic authentication efficiency for the verification of the user. Anti-fraud risk control; and call the face recognition system to collect face data for identification only when it is determined to be necessary, which further improves the intelligence and timeliness of risk control for user identity audit; After analyzing the results and outputting different asynchronous auditing methods to call manual asynchronous auditing, it not only avoids the traditional anti-fraud method to continue to implement manual asynchronous auditing in the application of face recognition system, but also causes serious consumption of human resources and poor timeliness. It achieves a good balance between the anti-fraud risk control of user verification and the timeliness of verification.

Further, based on the above-mentioned first embodiment, a second embodiment of the anti-fraud method for credit business of the present invention is proposed. Please refer to FIG. 3 , which is a schematic flowchart of the second embodiment of the anti-fraud method for credit business according to the present invention.

In this embodiment, in the above step S30, after analyzing the face recognition result and outputting the asynchronous auditing method, and receiving the auditing result of the identity verification of the user to be verified according to the asynchronous auditing method, the present invention credits A business’s anti-fraud approach can also include:

Step S50, if the audit result is not received for a preset period of time, the overall risk level of the credit business is detected.

In the process that the terminal device outputs the corresponding asynchronous audit method based on the analysis of the face recognition result to call the manual to perform identity authentication and verification for the user to be verified, the terminal device starts timing from the moment when the asynchronous audit method is output, and then, if the terminal The device detects that the recorded duration exceeds the preset duration, but still receives the audit result that is fed back by calling the manual to verify the identity of the user to be verified. The overall risk level of the specified credit business is tested.

It should be noted that, in this embodiment, the preset duration can be set to any duration based on the needs of the actual application. 1min.

Specifically, for example, in the application process shown in FIG. 5, the terminal device analyzes the face recognition result obtained by invoking the face recognition system to perform face recognition on the user to be verified based on the system technology, and detects the The index values of the authentication indicators such as "Portrait Comparison Score" and "Life Monitoring Score" mapped by the face recognition result are high or medium, so the corresponding output is passed first and then reviewed and the asynchronous review method of first review and then passed is called to call When the audit result is fed back after manual further auditing of the user to be verified, the terminal device will start timing at the moment of outputting the asynchronous auditing methods of first-pass-then-approval and first-approval-passing, and the timing exceeds the preset time limit. After 1 minute, the terminal device immediately detects the overall risk level of the credit business-loan application specified by the business processing request initiated by the user to be authenticated.

It should be noted that, in this embodiment, the overall risk level of the credit business can be specifically analyzed by analyzing the risk level of the financial business type to which the credit business belongs, and the enterprise staff recorded by the terminal device in advance for the identity of the user to be verified. The degree of risk is comprehensively determined based on factors such as the reliability of the identity recorded after verification. It should be understood that, based on the different needs of practical applications, the overall risk level can of course be detected and determined based on other methods or factors, and the anti-fraud method for credit business of the present invention does not specifically limit the overall risk level for detecting credit business. .

Step S60, if the overall risk level is lower than a preset risk level threshold, the credit business is started by verifying the identity of the user to be verified.

It should be noted that, in this embodiment, the preset risk threshold can be defined by the enterprise staff independently according to the needs of practical applications. Specifically, for example, based on the consideration of the basic authentication efficiency for identity verification, the preset The risk threshold can be defined as 50% by the enterprise staff. It should be understood that, based on different design requirements of practical applications, the preset risk threshold value can of course be set to any other value different from the above-mentioned value in other ways different from those set forth by the staff autonomously. , the anti-fraud method for credit business of the present invention does not specifically limit the size and setting method of the preset risk threshold.

After the terminal device detects the overall risk level of the credit business specified by the business processing request initiated by the user to be verified, if it further detects that the overall risk level is less than the preset risk level threshold set by the enterprise staff in advance, the terminal The device immediately determines that the identity authentication review for the user to be verified has passed, and starts processing the credit business in time.

Specifically, for example, in the application process shown in FIG. 5 , the overall risk level of the credit business-loan application specified by the business processing request initiated by the user to be verified by the terminal device is less than that defined by the enterprise staff. In order to ensure the timeliness of the identity verification for the user, the terminal device can directly determine that the identity authentication verification for the user to be verified has passed, and then start to handle the business initiated by the user to be verified. Handle the credit business specified in the application - loan application.

Further, in another embodiment, after the overall risk level of the credit business is lower than the preset risk level threshold, and the terminal device starts to handle the credit business by verifying the identity of the verified user, it can continue to wait for the call to be called. Manually treat the audit result of the identity authentication audit of the verified user according to the output asynchronous audit method, and perform corresponding processing for the credit business based on the result.

In this embodiment, the terminal device outputs the corresponding asynchronous auditing method based on the analysis of the face recognition result, so as to invoke the process of manually performing identity authentication and verification on the user to be verified, the terminal device outputs the asynchronous auditing method from the moment of output. Start timing, and then, if the terminal device detects that the recorded duration exceeds the preset duration, but still receives the audit result fed back by calling the manual to verify the identity of the user to be verified, the terminal device will respond to the verification result for the user to be verified. The overall risk level of the credit business specified by the business processing request initiated by the user is detected. After the terminal device detects the overall risk level of the credit business specified by the business processing request initiated by the user to be verified, if it further detects that the overall risk level is less than the preset risk level threshold set by the enterprise staff in advance, the terminal The device immediately determines that the identity authentication review for the user to be verified has passed, and starts processing the credit business in time. It avoids the problem that the user waits for too long due to the inconvenience of manual operation and seriously affects the timeliness in the process of invoking manual identity verification for users. A good balance between the anti-fraud risk control of the user and the timeliness of the verification.

Further, based on the above-mentioned first embodiment, a third embodiment of the anti-fraud method for credit business of the present invention is proposed. In this embodiment, in the above step S40, the corresponding processing is performed on the credit business according to the audit result, which may include:

Step S401, if the verification result indicates that the user to be verified has passed the verification, then start processing the credit business;

The terminal device outputs the asynchronous auditing method of first auditing and then passing, so as to call the manual to conduct the identity authentication audit for the user to be verified, and after receiving the audit result fed back by the manual, if the audit result indicates that the identity authentication audit is passed for the verified user , the terminal device starts to handle the credit business specified by the business handling request initiated by the user to be authenticated.

Step S402, if the verification result indicates that the verification of the user to be verified has not passed, stop continuing to handle the credit business that has already been processed, or perform advanced payment processing for the credit business that has been processed.

The terminal device outputs the asynchronous auditing method of first auditing and then passing, so as to call the manual to conduct the identity authentication audit for the user to be verified, and after receiving the manual feedback audit result, if the audit result indicates that the identity authentication audit for the verified user has not been performed. If passed, the terminal device refuses to process the credit business specified in the business processing request initiated by the user to be verified; or, the terminal device directly starts to process the credit business initiated by the user to be verified after outputting the asynchronous verification method of first passing and then reviewing The business handles the credit business specified in the application, and then, at the same time or after starting to handle the credit business for the user to be verified, further calls the manual to conduct identity authentication review for the user to be verified, and after receiving the review result of the manual feedback, if The verification result indicates that the identity authentication verification for the verified user has not passed, and the terminal device immediately stops processing the credit business or performs an advance payment reminder operation for the credit business that has been processed.

Further, in another embodiment, the above step S40 may further include:

Step S403, if the audit result identifies that the user to be verified has malicious attack intentions, the financial account associated with the credit business is detected, and the financial account is managed and controlled.

The terminal device outputs the first review and then passes the asynchronous review method, and after receiving the review result of calling the manual to conduct the identity authentication review on the verified user before starting to handle the credit business, if the review result identifies the user to be verified. The identity authentication review determines that the user to be verified has the intention of maliciously attacking the associated account of the credit business, and then the terminal device immediately refuses to handle the credit business and locks and controls the associated account at the same time. Alternatively, the terminal device outputs the asynchronous review method of first passing and then reviewing, so as to first start to process the credit business specified in the application for the business to be initiated by the authenticated user, and then the terminal device receives the calling manual at the same time or after starting to handle the credit business. After the verification result of the identity authentication review for the user to be verified, if the verification result indicates that the user to be verified has the intention of malicious attacks on the associated account of the credit business, immediately stop processing the credit business and simultaneously target the credit business. Linked accounts are locked and controlled.

In this embodiment, based on whether or not the user identity authentication audit identified by the audit result of invoking manual authentication and verification of the user identity has passed, and whether the user has malicious attack behavior, corresponding to the credit business specified in the business processing request initiated by the user, execute Corresponding processing, termination processing, early payment reminders, and account management and control ensure the control efficiency of risk control for credit business.

The invention also provides an anti-fraud device for credit business.

Referring to FIG. 6, FIG. 6 is a schematic diagram of functional modules of the first embodiment of the anti-fraud device for credit business of the present invention.

As shown in Figure 3, the anti-fraud device for the credit business includes:

The data collection module 10 is used to collect the historical behavior data of the user to be verified when it is determined that the credit business needs to be authenticated;

The data processing module 20 is configured to collect the face data of the user to be verified for identification and obtain a face recognition result if it is determined according to the historical behavior data that face recognition is required;

The auditing and deployment module 30 is configured to analyze the face recognition result and output an asynchronous auditing method, and receive the auditing result of the identity verification of the user to be verified according to the asynchronous auditing method;

The business processing module 40 performs corresponding processing on the credit business according to the audit result.

Further, the anti-fraud device for the credit business also includes:

a risk detection module, configured to detect the overall risk degree of the credit business if the audit result is not received for a preset period of time;

The verification module is configured to start processing the credit business by verifying the identity of the user to be verified if the overall risk is lower than a preset risk threshold.

Further, the data acquisition module 10 includes:

a determination unit, configured to determine that the credit business needs to be authenticated if it is detected that the credit business belongs to a preset high-risk financial business;

A collection unit, configured to mark a user who initiates a business processing request for the credit business as a user to be verified, and collect historical behavior data of the user to be verified.

Further, the anti-fraud device for the credit business also includes:

A face-swiping determination module, configured to determine whether face recognition needs to be performed on the user to be verified according to the historical behavior data;

The face brushing determination module includes:

a first determining unit, configured to determine that face recognition needs to be performed on the user to be verified if it is detected that there is negative behavior data in the historical behavior data;

The second determining unit is configured to determine that face recognition is not required for the user to be verified if it is detected that there is no negative behavior data in the historical behavior data.

Further, the asynchronous review methods include: no need for asynchronous review, first pass and then review, and first review and then pass, and the review and deployment module 30 includes:

a first allocating unit, configured to output the no asynchronous audit required if the authentication index value mapped by the face recognition result is high through analysis;

a second allocating unit, configured to output the first pass and then review if the authentication index value of the face recognition result mapping is obtained by analysis;

The third allocating unit is configured to output the first review and then pass if the authentication index value of the face recognition result mapping is low through analysis.

Further, the business processing module 40 includes:

a first processing unit, configured to start processing the credit business if the verification result indicates that the user to be verified has passed the verification;

a second processing unit, configured to stop continuing to handle the credit business that has already been handled if the audit result indicates that the user to be authenticated has not passed the authentication, or, for the credit business that has been handled and completed in advance Payment processing.

Further, the business processing module 40 also includes:

A third processing unit, configured to detect a financial account associated with the credit business and manage and control the financial account if the audit result identifies that the user to be verified has malicious attack intentions.

The function implementation of each module in the anti-fraud device for credit business corresponds to each step in the embodiment of the anti-fraud method for credit business, and the functions and implementation process thereof will not be repeated here.

The present invention also provides a computer storage medium, on which an anti-fraud program for credit business is stored, and when the anti-fraud program for credit business is executed by a processor, the credit business described in any of the above embodiments is implemented steps of the anti-fraud method.

The specific embodiments of the computer storage medium of the present invention are basically the same as the above-mentioned embodiments of the anti-fraud method for credit business, and will not be repeated here.

It should be noted that, herein, the terms "comprising", "comprising" or any other variation thereof are intended to encompass non-exclusive inclusion, such that a process, method, article or system comprising a series of elements includes not only those elements, It also includes other elements not expressly listed or inherent to such a process, method, article or system. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article or system that includes the element.

The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages or disadvantages of the embodiments.

From the description of the above embodiments, those skilled in the art can clearly understand that the method of the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is better implementation. Based on such understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products are stored in a storage medium (such as ROM/RAM) as described above. , magnetic disk, optical disk), including several instructions to make a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present invention.

The above are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the description and drawings of the present invention, or directly or indirectly applied in other related technical fields , are similarly included in the scope of patent protection of the present invention.

Claims (10)

1. An anti-fraud method for credit services, characterized in that it comprises:

acquiring historical behavior data of a user to be checked in real time when the credit business needs to be checked;

if the need of face recognition is determined according to the historical behavior data, face data of the user to be subjected to the core body is collected for recognition, and a face recognition result is obtained;

analyzing the face recognition result, outputting an asynchronous auditing mode, and receiving an auditing result for identity verification of the user to be verified according to the asynchronous auditing mode;

and performing corresponding processing on the credit service according to the auditing result.

2. The method of credit transaction anti-fraud according to claim 1, further comprising, after the steps of analyzing the face recognition result and outputting an asynchronous auditing manner, and receiving an auditing result for identity verification of the user to be verified according to the asynchronous auditing manner:

if the auditing result is not received after the preset time length is exceeded, detecting the overall risk degree of the credit business;

and if the overall risk degree is lower than a preset risk degree threshold value, the credit business is started to be transacted by verifying the identity of the user to be verified.

3. The method of credit transaction for fraud prevention according to claim 1, wherein said step of collecting historical behavioral data of the user to be credited in determining that said credit transaction requires identity verification comprises:

if the credit business is detected to belong to the preset high-risk financial business, judging that the credit business needs identity verification;

and marking the user initiating the service transaction request aiming at the credit service as a user to be checked, and collecting the historical behavior data of the user to be checked.

4. The method of credit service fraud prevention of claim 1, further comprising, after the step of collecting historical behavioral data of the user to be credited, the steps of:

determining whether the face recognition of the user to be subjected to the core body is needed or not according to the historical behavior data;

the step of determining whether the face recognition needs to be performed on the user to be subjected to the core body according to the historical behavior data comprises the following steps:

if negative behavior data exist in the historical behavior data, determining that face recognition needs to be carried out on the user to be subjected to the body checking;

and if negative behavior data do not exist in the historical behavior data, determining that face recognition is not needed for the user to be subjected to the body checking.

5. The anti-fraud method for credit services of claim 1, characterized in that the asynchronous auditing means include: asynchronous auditing is not needed, the auditing is carried out after the first auditing and the first auditing is carried out after the first auditing is carried out,

the step of analyzing the face recognition result and outputting an asynchronous auditing mode comprises the following steps:

if the authentication index value mapped by the face recognition result is high after analysis, outputting the non-asynchronous audit;

if the authentication index value mapped by the face recognition result is obtained through analysis, outputting the first pass and the second pass;

and if the authentication index value mapped by the face recognition result obtained by analysis is low, outputting the verification before passing.

6. The credit service antifraud method according to claim 1, wherein the step of performing corresponding processing on the credit service according to the audit result comprises:

if the auditing result identifies that the user to be credited passes the crediting operation, starting to transact the credit business;

and if the auditing result indicates that the user to be credited does not pass the crediting process, stopping continuously transacting the credit business started to be transacted, or performing advanced payment urging process on the credit business transacted and completed.

7. The credit service fraud prevention method of claim 1, wherein the step of performing corresponding processing on the credit service according to the audit result further comprises:

and if the auditing result identifies that the user to be verified has a malicious attack intention, detecting the financial account associated with the credit service, and managing and controlling the financial account.

8. An anti-fraud arrangement for credit services, characterized in that it comprises:

the data acquisition module is used for acquiring historical behavior data of the user to be credited in real time when the credit business needs identity verification;

the data processing module is used for collecting the face data of the user to be subjected to the body checking for recognition and acquiring a face recognition result if the need of face recognition is determined according to the historical behavior data;

the auditing and allocating module is used for analyzing the face recognition result, outputting an asynchronous auditing mode and receiving an auditing result for identity verification of the user to be verified according to the asynchronous auditing mode;

and the business processing module is used for executing corresponding processing on the credit business according to the auditing result.

9. A terminal device, characterized in that the terminal device comprises: memory, a processor and an anti-fraud program of a credit service stored on said memory and executable on said processor, said anti-fraud program of a credit service implementing the steps of the anti-fraud method of a credit service according to any one of claims 1 to 7 when executed by said processor.

10. A computer storage medium, characterized in that the computer storage medium has stored thereon an anti-fraud program of a credit service, which when executed by a processor implements the steps of the anti-fraud method of a credit service according to any one of claims 1 to 7.

Images