CN116342247A

CN116342247A - Authorization management and control method, device, equipment and storage medium for credit support

Info

Publication number: CN116342247A
Application number: CN202310227973.8A
Authority: CN
Inventors: 谢绍恒
Original assignee: WeBank Co Ltd
Current assignee: WeBank Co Ltd
Priority date: 2023-02-28
Filing date: 2023-02-28
Publication date: 2023-06-27

Abstract

The application discloses a credit support authorization management and control method, device and equipment and a storage medium thereof, belonging to the technical field of financial science and technology (Fintech). The credit support authorization control method comprises the following steps: receiving a credit branch request sent by an associated terminal and determining a corresponding transaction type, so as to determine a target evaluation function adapted to the credit branch request in an evaluation function database; extracting target transaction characteristic data corresponding to the credit branch request according to the target evaluation function, and determining a target weight coefficient, wherein the target transaction characteristic data comprises: one or more of customer level, transaction purpose, merchant category, and merchant level; and inputting the target transaction characteristic data and the target weight coefficients into a credit authorization management and control model, obtaining an authorization result of the credit support request, and transmitting the authorization result to the associated terminal. The technical problem that the transaction authorization work efficiency for credit branch in the prior art is low is solved.

Description

Authorization management and control method, device, equipment and storage medium for credit support

Technical Field

The present disclosure relates to the field of financial technology (Fintech), and in particular, to a credit support authorization management and control method, apparatus, device, and storage medium thereof.

Background

With the development of the economy and society in China, the market shows explosive growth, and the integration of the Internet and finance further promotes a series of Internet credit businesses; by means of the advantages of the Internet, the method for realizing the completion of the loan application by the client without going home comprises the following steps: knowing the application conditions of various loans, preparing the application materials, and can be efficiently completed on the Internet until the loan application and the credit support are submitted. Meanwhile, corresponding transaction business supervision measures are not sound, so that the risk of internet credit transaction is high, the healthy development of the industry is limited, and huge risks and hidden dangers are brought to the economy of China.

Aiming at the existing problems, the conventional mode is to enable the labor of different job classes to butt joint different databases based on different terminals by adding a mode of manual intervention of multiple databases and different job classes, thereby realizing credit support management and control; however, the mode needs mutual authorization among terminals of different levels, so that the authorization process of each node in the management and control process is complex, and the work efficiency of credit support management and control is low.

The foregoing is merely provided to facilitate an understanding of the principles of the present application and is not admitted to be prior art.

Disclosure of Invention

The main purpose of the application is to provide a credit support authorization management and control method, device, equipment and storage medium thereof, which aim to solve the technical problem of lower working efficiency in conventional credit support authorization.

To achieve the above object, the present application provides an authorization management method for credit support, including:

receiving a credit branch request sent by an associated terminal, determining a transaction type corresponding to the credit branch request, and determining a target evaluation function adapted to the credit branch request in a preset evaluation function database based on the transaction type;

extracting target transaction characteristic data corresponding to the credit support request according to the target evaluation function, and determining a target weight coefficient of each target transaction characteristic data for the credit support request, wherein the target transaction characteristic data comprises: one or more of customer level, transaction purpose, merchant category, and merchant level;

inputting the target transaction characteristic data and the target weight coefficients into a preset credit authorization management and control model, obtaining an authorization result of the credit support request, and sending the authorization result to the associated terminal.

Optionally, the step of determining, based on the transaction type, a target evaluation function adapted to the credit support request in a preset evaluation function database includes:

traversing each evaluation function in a preset evaluation function database to obtain a function traversing result;

determining the target evaluation function matched with the transaction type according to the function traversal result, wherein a preset evaluation function database comprises: a privacy-to-privacy class assessment function and a privacy-to-business class assessment function.

Optionally, the step of extracting the target transaction characteristic data corresponding to the credit branch request according to the target evaluation function, and determining the target weight coefficient of each target transaction characteristic data for the credit branch request includes:

determining transaction characteristic data to be extracted and a target weight interval corresponding to each transaction characteristic data to be extracted according to the target evaluation function;

extracting target transaction characteristic data of the credit branch request based on the transaction characteristic data to be extracted, and determining target characteristic index values corresponding to the target transaction characteristic data;

and determining each target weight coefficient according to the target characteristic index value and the target weight interval.

Optionally, the step of determining the transaction characteristic data to be extracted according to the objective evaluation function includes:

if the objective evaluation function is a private-private evaluation function, the transaction characteristic data to be extracted is: customer level and transaction use;

if the objective evaluation function is a private-to-commercial evaluation function, the transaction characteristic data to be extracted is: customer level, merchant category, and merchant level.

Optionally, the step of inputting each target transaction characteristic data and each target weight coefficient into a preset credit authorization management model to obtain an authorization result of the credit support request includes:

inputting the target transaction characteristic data and the target weight coefficients into a preset credit authorization management and control model to obtain a credit authorization management and control group identifier matched with the credit support request;

calling a corresponding target credit authorization management and control group according to the credit authorization management and control group identification, controlling the target credit authorization management and control group, and checking the credit limit and the credit times of the credit support request;

if the verification is passed, judging that the authorization result of the credit support request is successful authorization;

If the verification is not passed, judging that the authorization result of the credit support request is authorization failure.

Optionally, before the step of determining the transaction type corresponding to the credit support request, the method further includes:

determining qualification information of a client corresponding to the credit support request, and checking whether the credit support request passes or not based on the qualification information;

if the credit branch request passes, executing the step of determining the transaction type corresponding to the credit branch request;

and if the credit support request does not pass, judging that the authorization result of the credit support request is authorization failure.

Optionally, the step of sending the authorization result to the associated terminal includes:

and acquiring the residual credit limit and the residual credit number of the client corresponding to the credit request, and sending the residual credit limit, the residual credit number and the authorization result to the associated terminal.

The present application also provides a credit is with authorizing controlling device, the credit is with authorizing controlling device includes:

the determining module is used for receiving the credit branch request sent by the associated terminal, determining the transaction type corresponding to the credit branch request, and determining a target evaluation function adapted to the credit branch request in a preset evaluation function database based on the transaction type;

The extracting module is configured to extract target transaction feature data corresponding to the credit support request according to the target evaluation function, and determine a target weight coefficient of each target transaction feature data for the credit support request, where the target transaction feature data includes: one or more of customer level, transaction purpose, merchant category, and merchant level;

the sending module is used for inputting the target transaction characteristic data and the target weight coefficients into a preset credit authorization management and control model, obtaining an authorization result of the credit support request and sending the authorization result to the associated terminal.

The present application also provides a credit support authorization and management apparatus, the credit support authorization and management apparatus comprising: the system comprises a memory, a processor and a credit support authorization management program stored on the memory and capable of running on the processor, wherein the credit support authorization management program is configured to realize the steps of the credit support authorization management method.

The present application also provides a storage medium, which is a computer readable storage medium, where a credit branch authorization control program is stored, where the credit branch authorization control program is executed by a processor to implement the steps of the credit branch authorization control method described above.

The application discloses a credit support authorization management and control method, which comprises the steps of determining a transaction type corresponding to a credit support request by receiving the credit support request sent by an associated terminal, and determining a target evaluation function adapted to the credit support request in a preset evaluation function database based on the transaction type; and then extracting target transaction characteristic data corresponding to the credit support request according to the target evaluation function, and determining a target weight coefficient of each target transaction characteristic data for the credit support request, wherein the target transaction characteristic data comprises: one or more of customer level, transaction purpose, merchant category, and merchant level; by classifying and automatically identifying the transaction types of the credit support requests, the method realizes the retrieval of the adaptive target evaluation functions of the credit support requests belonging to different transaction types, and further extracts the required transaction characteristic data according to the adaptive target evaluation functions, thereby realizing the automatic extraction and dynamic analysis of multi-dimension and multi-angle data of the credit support requests; and then each transaction characteristic data and the target weight coefficient are input into a preset credit authorization management and control model, and through the credit authorization management and control model, the full-automatic evaluation operation of the credit support authorization result is efficiently carried out to obtain the accurate authorization result of the credit support request, so that the authorization accuracy and the working efficiency of the credit support request are improved, and the credit support authorization is accurately and efficiently managed and controlled. The conventional credit support management and control is realized by adding a plurality of databases and manual intervention modes of different levels, and the manual intervention modes of different levels are needed to be based on different databases with different terminal docking and authorization, so that the authorization process of each node is complex and the working efficiency is low; the uncertainty factor is increased due to the need of multiple nodes and manual intervention, so that the security of credit support management and control is reduced; by means of full-automatic credit branch evaluation and authorization, multidimensional transaction characteristic data can be automatically extracted, manual intervention of multi-terminal cooperation and different levels is not needed, the risk of data leakage is further reduced, and the safety and the working efficiency of credit branch management and control are improved; meanwhile, transaction characteristic data for credit branch authorization analysis in the application comprises local and multidimensional information of a customer dimension and a merchant dimension and integral interaction information between transaction uses and customers corresponding to merchant categories, and the characteristic analysis of credit branch requests can be performed in a full aspect through the relevance between the local and the whole and the multiple dimensions so as to obtain more comprehensive transaction characteristics for credit branch; and through the weight proportion among different transaction characteristics, accurate screening analysis is performed on the transaction characteristic data in the most practical way, credit branch risk identification is comprehensively and accurately performed, balance between credit branch risk prevention and control and customer experience is realized, and the customer experience and credit branch authorization management and control accuracy are further improved.

Drawings

FIG. 1 is a schematic diagram of a credit support authorization and management device for a hardware operating environment according to an embodiment of the present application;

FIG. 2 is a flow chart of an authorization management method for credit support according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a credit authorization management group according to an embodiment of the present application;

FIG. 4 is a schematic flow diagram of a more complete embodiment of an embodiment of the present application;

fig. 5 is a schematic frame structure of a credit support authorization management device according to an embodiment of the present application.

The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

Furthermore, the descriptions of "first," "second," and the like, herein are for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, "and/or" throughout this document includes three schemes, taking a and/or B as an example, including a technical scheme, a technical scheme B, and a technical scheme that both a and B satisfy; in addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a credit support authorization management device of a hardware running environment according to an embodiment of the present application.

As shown in fig. 1, the credit support authorization management device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.

It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the credit support authorization management device, and may include more or fewer components than shown, or may combine certain components, or may be a different arrangement of components.

As shown in fig. 1, an operating system, a data storage module, a network communication module, a user interface module, and a credit support authorization management program may be included in the memory 1005 as one storage medium.

In the credit support authorization management device shown in fig. 1, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the credit support authorization and management device may be disposed in the credit support authorization and management device, where the credit support authorization and management device invokes, through the processor 1001, the credit support authorization and management program stored in the memory 1005, and performs the following operations:

Further, the operation of determining, based on the transaction type, a target evaluation function adapted to the credit support request in a preset evaluation function database includes:

Further, the operation of extracting the target transaction characteristic data corresponding to the credit branch request according to the target evaluation function and determining the target weight coefficient of each target transaction characteristic data for the credit branch request includes:

Further, the determining transaction characteristic data to be extracted according to the objective evaluation function includes:

Further, the operation of inputting each target transaction characteristic data and each target weight coefficient into a preset credit authorization management model to obtain the authorization result of the credit support request includes:

Further, the processor 1001 may call the credit support authorization management program stored in the memory 1005, and further perform the following operations:

before the operation of determining the transaction type corresponding to the credit support request, the method further comprises the following steps:

if the credit branch request passes, executing an operation of determining a transaction type corresponding to the credit branch request;

Further, the operation of sending the authorization result to the associated terminal includes:

Based on the above structure, various embodiments of credit support authorization management methods are presented.

Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of an authorization management method for credit support of the present application.

In this embodiment, the execution body of the credit support authorization and control method may be a credit support authorization and control device, or the credit support authorization and control device may be a terminal device or a server, and the credit support authorization and control device may be integrated on a terminal device such as a smart phone or a tablet computer with a data processing function, which is not limited in this embodiment, and the description of the execution body is omitted for convenience. In this embodiment, the credit support authorization control method includes:

step S10, a credit branch request sent by an associated terminal is received, a transaction type corresponding to the credit branch request is determined, and a target evaluation function adapted to the credit branch request is determined in a preset evaluation function database based on the transaction type;

In order to avoid that a customer does not have the capability or does not want to repayment after loan, financial institutions such as banks and the like often need to carry out credit support risk analysis on private customers or enterprises applying for loan so as to determine the available credit support amount and the number of times of support of the customer, thereby judging whether to authorize the credit support request according to the credit support amount and the number of times of support; therefore, if a credit support request sent by a client through an associated terminal is received, the transaction type of the credit support request is analyzed, and accordingly, according to the transaction type of the credit support request, an adaptive evaluation function is screened in a preset evaluation function database to carry out credit risk evaluation.

In this embodiment, it should be noted that the credit support authorization management refers to performing multidimensional and multi-angle credit risk assessment on an initiator of a credit support request, so as to determine a credit support amount and a credit support number standard that meet the requirement of the initiator of the credit support request under a low risk degree, and determine whether to authorize the credit support request according to the determined credit support amount and credit support number standard, so as to implement full-automatic and accurate management of the credit support request.

Credit risk refers to the likelihood that a borrower, securities issuer, or transaction partner will be unwilling or unable to fulfill the contract conditions for any number of reasons, resulting in a loss to the bank, investor, or transaction partner.

The credit application request refers to a loan application initiated by a client through an associated terminal, and the credit application request can be a loan application initiated through the internet, namely, the client completes the loan application through the internet, and the credit application request can comprise: the amount of the equity, type of transaction, purpose of transaction, merchant category of transaction, customer level, etc., which is not limited in this embodiment. The associated terminal refers to a sending terminal of a credit support request, and can be a terminal capable of being connected to a network, such as a mobile phone, a notebook computer, a tablet personal computer and the like.

The transaction type is a type determined according to the nature of the corresponding transaction of the credit branch request, and can comprise private-private transactions, private-business transactions and the like; the private-private transaction can also be called cash transaction, which means that both transaction parties belong to private accounts and carry out transactions such as cash withdrawal, transfer, reddish package and the like; the private-to-merchant transaction may also be referred to as a cashless transaction, which refers to a transaction performed between a private account and a merchant account or company account, where the merchant account may be a supermarket, a hotel, an airline, a restaurant, etc., which is not limited in this embodiment.

The credit limit and the count number refer to the transaction limit and the transaction limit number set for the initiator of the credit request, namely the maximum transaction limit and the transaction count number which can be applied by the initiator in a certain time; the credit may include: the single credit, natural daily credit, natural weekly credit, natural monthly credit, natural annual credit and the like, and the number of credits may include: the number of natural daily counts, the number of natural weekly counts, the number of natural monthly counts, the number of natural annual counts, and the like, which are not limited in this embodiment.

The evaluation function database comprises a plurality of evaluation functions, wherein the evaluation functions refer to a function model for evaluating the whole and partial performances of a credit branch request, and are commonly used for credit risk evaluation, such as loan approval, credit line credit, risk pricing and the like; in this embodiment, different transaction types may correspond to different evaluation functions, for example, the private-to-private evaluation function is applicable to private-to-private transactions, and the private-to-merchant evaluation function is applicable to private-to-merchant transactions; optionally, the private-private class evaluation function and the private-commercial class evaluation function may further each include an evaluation function for evaluating the credit and the number of credits, respectively. The objective evaluation function refers to an evaluation function adapted to the credit support request.

In a possible implementation manner, before the step of determining the transaction type corresponding to the credit support request in step S10, the method further includes:

step S11, determining qualification information of a client corresponding to the credit support request, and checking whether the credit support request passes or not based on the qualification information;

if a credit support request sent by a client through an associated terminal is received, acquiring qualification information of the client corresponding to the credit support request, and checking whether the credit support request can pass or not according to the acquired qualification information so as to ensure that the current credit support request is normally initiated and is not a malicious operation of irrelevant personnel or malicious personnel; wherein, the qualification information may include: the account status, the total remaining amount of the account, the credit rating of the account, etc., where the qualification information may be retrieved from the associated terminal or from the cloud end in which the qualification information is stored, which is not limited in this embodiment.

In a possible implementation manner, if the account state of the client corresponding to the credit support request is normal, the total remaining amount of the account is greater than or equal to the support amount of the credit support request, the account is not in a preset blacklist, the credit level of the account meets the preset credit level standard, fraudulent activity does not exist in the account change, and the like, the credit support request is judged to pass; otherwise, if any of the above criteria is not met, determining that the credit support request is not passed.

Step S12, if the credit support request passes, executing a step of determining a transaction type corresponding to the credit support request;

step S13, if the credit support request does not pass, determining that the authorization result of the credit support request is authorization failure.

If the acquired qualification information is used for judging that the credit support request passes, indicating that the account of the initiator of the credit support request is good in qualification and meets the basic requirement of loan, and if the loan can be performed, executing the step of determining the transaction type corresponding to the credit support request; if the credit support request is judged to not pass according to the qualification information, the account qualification of the initiator of the credit support request is poor, the loan risk assessment level is high, the capability or willingness to repay after the loan is not met, and the basic requirement of the loan is not met, the authorization result of the credit support request is judged to be authorization failure, namely the loan is not approved.

In the embodiment, by acquiring the qualification information of the client corresponding to the credit support request, whether the credit support request passes or not is automatically checked, namely whether the loan is performed or not, so that the automatic basic evaluation of the credit support request is realized, and the sponsor of the current credit support request is ensured to have the loan qualification; and rapidly screening out the loan application of the blacklist customer or the poor credit customer through the qualification information, and further determining whether the customer meets the specific credit limit and credit number standard after the loan initiator has the loan qualification, thereby improving the working efficiency of credit authorization management and control.

In a possible implementation manner, step S10, based on the transaction type, the step of determining, in a preset evaluation function database, an objective evaluation function adapted to the credit support request includes:

step S14, traversing each evaluation function in a preset evaluation function database to obtain a function traversing result;

step S15, determining the target evaluation function matched with the transaction type according to the function traversal result, wherein a preset evaluation function database comprises: a privacy-to-privacy class assessment function and a privacy-to-business class assessment function.

In this embodiment, a plurality of evaluation functions adapted to different transaction types are preset in a preset evaluation function database, and in order to determine a target evaluation function adapted to the credit support request, the preset evaluation functions are sequentially accessed, and a function traversal result can be obtained in each access, so that whether the currently accessed evaluation function is matched with the transaction type of the credit support request or not is judged according to the function traversal result; if the evaluation function is matched, determining the evaluation function as a target evaluation function, and stopping accessing the next evaluation function; if the evaluation functions are not matched, continuing to access the next evaluation function;

The preset evaluation function in the preset evaluation function database may include: a private-to-private class evaluation function and a private-to-commercial class evaluation function; the private-to-private class evaluation function is adapted to private-to-private class transactions, and the private-to-business class evaluation function is adapted to private-to-business class transactions; wherein the privacy class assessment function further comprises: the private-to-private-class credit evaluation function and the private-to-private-class number evaluation function are respectively used for evaluating the branch credit and the branch number of private-to-private transactions; the privacy pair class assessment function further includes: the private-to-business credit evaluation function and the private-to-business times evaluation function are respectively used for evaluating the branch credit and the branch times of private-to-business transactions.

In one possible implementation, different evaluation functions correspond to different transaction characteristic data to be extracted and different weight coefficient intervals.

In the embodiment, the function traversing result is obtained by traversing each evaluation function in the preset evaluation function database, so that the target evaluation function matched with the transaction type is determined, and the automatic and rapid identification and the retrieval of the adaptation target evaluation function adapted to the credit support request are realized; by dividing the evaluation function types, the adaptation degree between the evaluation function and the credit support request is improved, further, by extracting key feature data of different dimensions, the depth and the accuracy analysis of the different credit support requests are realized, further, the credit support risk identification is comprehensively and accurately carried out, the accuracy of credit support authorization management and control is further improved, and by automatic traversal of a preset evaluation function database, multiple nodes and manual intervention are not needed, and the safety and the working efficiency of credit support management and control are improved.

Step S20, extracting target transaction characteristic data corresponding to the credit branch request according to the target evaluation function, and determining a target weight coefficient of each target transaction characteristic data for the credit branch request, where the target transaction characteristic data includes: one or more of customer level, transaction purpose, merchant category, and merchant level;

according to the target evaluation function, determining transaction characteristic data required to be extracted for performing the credit risk evaluation, performing data extraction, and further performing data analysis on the extracted transaction characteristic data to determine characteristic index values corresponding to the transaction characteristic data; the target evaluation function further comprises a preset weight interval corresponding to each transaction characteristic data, and a target weight coefficient corresponding to each transaction characteristic data is determined according to the extracted transaction characteristic data and/or the characteristic index value corresponding to the transaction characteristic data.

The transaction characteristic data are characteristic data of both transaction parties of the extracted credit support request according to the requirements of the target evaluation function; the transaction characteristic data may be real-time characteristic data, for example, real-time transaction purposes corresponding to the present transaction; the transaction characteristic data may also be historical characteristic data, for example, when evaluating the natural month count value unit in the count value unit, historical transaction purpose data of the whole month of the last month of the customer may be extracted; the time corresponding to the extracted data may be one week, one month, one year, etc., which is not limited in this embodiment.

The target transaction characteristic data includes: one or more of customer hierarchy, transaction usage, merchant category, and merchant level.

The client level is classified after comprehensive evaluation according to information such as historical income, historical liability condition, historical credit performance, historical fraud performance and the like of clients; illustratively, information of all relevant clients is extracted to perform client level assessment, and information such as historical income, historical liability conditions, historical credit performance, historical fraud performance and the like of the clients is converted into scores to determine level total scores of all relevant clients, and the clients are classified into 5 levels from high to low according to the level total scores; the higher the hierarchy of the corresponding client, the higher the feature index value corresponding to the client-level transaction feature data.

The transaction purpose refers to transaction modes such as transfer, presentation, red packet generation and the like performed by two transaction parties in private-private type transaction; it should be understood that, the feature index value corresponding to the transaction feature data for each transaction purpose is related to the objective evaluation function used in the evaluation, and the determination of the feature index value may be performed according to the objective evaluation function used; for example, when using the private-private rating function, the amount of the transfer will be generally higher than the amount of the reddish bag, and the corresponding characteristic index value of the transfer will be higher than the characteristic index value of the reddish bag; when the private-to-private frequency evaluation function is used, the frequency of sending the red packet is generally higher than the frequency of transferring, and the characteristic index value corresponding to the corresponding red packet is higher than the characteristic index value corresponding to the transferring.

The merchant category is a division of merchants based on the domain in which each merchant is located, including but not limited to: supermarkets, hotels, restaurants, medical treatment, cosmetology, travel, etc.; when data analysis is performed, analysis and classification can be performed according to stored historical data of different merchant categories, so that corresponding characteristic index values are determined; illustratively, the present embodiment is not limited in this regard, as statistics, ranking are performed based on historical usage frequencies of different merchants in credit-use transactions, or statistics, ranking are performed based on historical amounts of different merchants in credit-use transactions, etc. It should be understood that, the feature index value corresponding to each merchant category transaction feature data is related to the objective evaluation function used in the evaluation, and the determination of the feature index value may be performed according to the objective evaluation function used.

The merchant grade is graded after comprehensive evaluation according to the transaction history, the default record, the transaction anomaly rate, the fraud rate and other information of the merchant; the method comprises the steps of extracting information of all relevant merchants to evaluate merchant grades, converting information of transaction histories, default records, transaction anomaly rates, fraud rates and the like of the merchants into grades, determining grade total grades of all relevant merchants, and sorting according to the grade total grades, so that the merchants are divided into 5 grades from high to low; the higher the corresponding merchant grade, the higher the corresponding characteristic index value of the merchant grade transaction characteristic data.

The feature index value is a representation mode of the number features of the extracted transaction feature data, and it should be understood that the feature index value corresponding to each transaction feature data is related to a target evaluation function used in the evaluation, and the feature index value may be determined according to the target evaluation function used.

Step S30, inputting the target transaction characteristic data and the target weight coefficients into a preset credit authorization management and control model, obtaining an authorization result of the credit support request, and sending the authorization result to the associated terminal.

Inputting the acquired transaction characteristic data and target weight coefficients corresponding to the transaction characteristic data into a pre-trained credit authorization management and control model, and outputting an authorization result obtained after evaluating and verifying the credit support request by the credit authorization management and control model; if the verification is passed, namely the sum and the historical times of the credit support request meet the support limit and the support times, the authorization result is that the authorization is successful; if the verification is not passed, namely the sum and/or the historical times of the credit branch request do not meet the branch sum and the branch times, the authorization result is an authorization failure, and the authorization result is sent back to the associated terminal so as to inform the authorization result and the reason.

The credit authorization management and control model is developed from the angle of natural people, namely clients, and is further a classification model established by logistic regression, GBDT (Gradient Boosting Decision Tree, gradient lifting decision tree), XGBoost (eXtreme Gradient Boosting, extreme gradient lifting tree) and the like based on corresponding transaction characteristic data of the natural people or clients as samples; the credit branch risk prevention and control method can calculate the branch amount and branch times standard meeting the requirements of the clients on the premise of low risk degree, and realizes the balance between credit branch risk prevention and control and client experience.

In a possible implementation manner, historical transaction characteristic data of an associated client is obtained and used as a training sample; determining a credit authorization management model prediction result of the training sample by inputting the training sample into a credit authorization management model to be trained; and based on the credit authorization management and control model prediction result, iteratively optimizing the credit authorization management and control model to be trained by calculating a credit authorization management and control model prediction loss corresponding to the credit authorization management and control model to be trained to obtain a credit authorization management and control model.

In another possible implementation manner, step S30, the step of sending the authorization result to the associated terminal includes:

Step S40, the residual credit limit and the residual credit times of the client corresponding to the credit request are obtained, and the residual credit limit, the residual credit times and the authorization result are sent to the associated terminal.

The method comprises the steps of obtaining the residual credit limit and the residual credit number of a client corresponding to a credit request, and sending the residual credit limit, the residual credit number and the authorization result to an associated terminal so as to inform the client of the authorization result and the reason; for example, the remaining credit number and the authorization result may be sent to the associated terminal to inform the client of the authorization result; if the authorization result is authorization failure, a detailed evaluation report may be generated according to the evaluation result, informing the client of the specific reason of authorization failure, and possible improvement measures, etc., which are not limited in this embodiment.

In this embodiment, the result feedback is performed on the remaining credit limit, the remaining credit number and the authorization result in real time, so that the result of credit support is timely informed to the customer, and the user experience and the working efficiency of credit support management are further improved.

In this embodiment, compared with the conventional credit support management and control, the method has the advantages that multiple databases and manual intervention of different levels are added, and the manual intervention of different levels is needed to dock and authorize different databases based on different terminals, so that the authorization process of each node is complex, and the working efficiency is low; the uncertainty factor is increased due to the need of multiple nodes and manual intervention, so that the security of credit support management and control is reduced; according to the method and the device, through full-automatic credit support assessment and authorization, multidimensional transaction characteristic data can be automatically extracted, manual intervention of multi-terminal cooperation and different levels is not needed, the risk of data leakage is further reduced, and the safety and the working efficiency of credit support management and control are improved; meanwhile, transaction characteristic data for credit branch authorization analysis in the application comprises local and multidimensional information of a customer dimension and a merchant dimension and integral interaction information between transaction uses and customers corresponding to merchant categories, and the characteristic analysis of credit branch requests can be performed in a full aspect through the relevance between the local and the whole and the multiple dimensions so as to obtain more comprehensive transaction characteristics for credit branch; and through the weight proportion among different transaction characteristics, accurate screening analysis is performed on the transaction characteristic data in the most practical way, credit branch risk identification is comprehensively and accurately performed, balance between credit branch risk prevention and control and customer experience is realized, and the customer experience and credit branch authorization management and control accuracy are further improved.

Further, based on the above first embodiment, a second embodiment of the credit support authorization control method of the present application is provided, in this embodiment, step S20 includes:

step S21, determining transaction characteristic data to be extracted and a target weight interval corresponding to each transaction characteristic data to be extracted according to the target evaluation function;

each objective evaluation function can correspond to different transaction characteristic data to be extracted, and each transaction characteristic data to be extracted corresponds to different weight intervals when being evaluated.

The target evaluation function is a private-private evaluation function, the transaction characteristic data to be extracted is a client level and a transaction purpose, the target weight interval corresponding to the client level is 50-70%, and the target weight interval corresponding to the transaction purpose is 30-40%; if the target evaluation function is a private-to-merchant evaluation function, the transaction characteristic data to be extracted are a client level, a merchant category and a merchant level; in addition to the evaluation of the customers of the credit support request in the private-to-business evaluation function, the grade and the category of the corresponding transaction business also play a critical role, so that in the private-to-business evaluation function, the target weight interval of the customer level is reduced by 30-50% compared with the private-to-private evaluation function, the target weight interval of the business category is 20-30%, and the target weight interval of the business level is 20-40%.

In a possible implementation manner, step S21, the step of determining the transaction characteristic data to be extracted according to the objective evaluation function includes:

step S211, if the objective evaluation function is a private-to-private evaluation function, the transaction feature data to be extracted is: customer level and transaction use;

if the target evaluation function is a private-private evaluation function, indicating that the transaction type of the credit branch request is a private-private transaction, and further extracting and analyzing transaction characteristic data of a customer of the credit branch request when performing credit branch risk evaluation; the transaction characteristic data to be extracted includes: customer level and transaction use.

Step S212, if the objective evaluation function is a private-to-business evaluation function, the transaction feature data to be extracted is: customer level, merchant category, and merchant level.

If the target evaluation function is a private-to-merchant evaluation function, the transaction type of the credit branch request is indicated to be private-to-merchant transaction, and when credit branch risk evaluation is carried out, transaction characteristic data of other transaction party-merchants are extracted in addition to the extraction of transaction characteristic data of customers of the credit branch request, so that the damage of partial merchants with higher risk grades to the benefits of the customers is avoided; the transaction characteristic data to be extracted are: customer level, merchant category, and merchant level.

In this embodiment, determining an objective evaluation function adapted to the credit branch request based on the transaction type; further, according to the adaptive target evaluation function, automatically extracting target transaction characteristic data corresponding to the credit support request; by classifying and identifying the transaction types of the credit support requests, the automatic retrieval of the adaptive target evaluation functions of the credit support requests belonging to different transaction types is realized, the required transaction characteristic data are extracted according to the adaptive target evaluation functions, the multi-dimensional and multi-angle data extraction of the credit support requests is realized, the credit support risk identification is comprehensively and accurately carried out, the accuracy of credit support authorization management is further improved, the extraction and evaluation processes of the data are fully automatic, multiple nodes and manual intervention are not needed, and the safety and the working efficiency of the credit support management are further improved.

Step S22, extracting target transaction characteristic data of the credit branch request based on the transaction characteristic data to be extracted, and determining target characteristic index values corresponding to the target transaction characteristic data;

extracting target transaction characteristic data of both transaction sides of a credit support request according to the transaction characteristic data required to be extracted by a target evaluation function, and analyzing the extracted data to determine target characteristic index values corresponding to the target transaction characteristic data, wherein the target characteristic index values comprise: customer level characteristic index value, transaction purpose characteristic index value, merchant category characteristic index value and merchant level characteristic index value.

Illustratively, the customer level in the transaction characteristic data is five levels in total, and the customer level of the credit-support transaction application is one level, i.e., the highest level, then the customer level characteristic index value 100.

In a possible implementation manner, step S22, based on the transaction characteristic data to be extracted, extracts the target transaction characteristic data of the credit support request, and further includes:

step S221, determining a transaction characteristic database stored by each transaction characteristic data to be extracted based on the transaction characteristic data to be extracted;

step S222, sending a data extraction request to each of the transaction characteristic databases, and extracting target transaction characteristic data stored in each of the transaction characteristic databases.

In the embodiment, the data extraction request is automatically sent to the transaction characteristic database storing the transaction characteristic data, so that the data extraction authority is obtained, each transaction characteristic data is automatically extracted, manual intervention of different levels is not needed, and the working efficiency of credit support authorization management is improved;

step S23, determining each target weight coefficient according to the target feature index value and the target weight interval.

And adjusting the intermediate value of each target weight interval by combining the corresponding target characteristic value to determine the target weight coefficient corresponding to each target characteristic data, wherein the target characteristic value and the target weight coefficient are in a proportional relation.

The target weight coefficients include: customer level weight coefficient, transaction purpose weight coefficient, merchant category weight coefficient, and merchant level weight coefficient.

For example, the target weight interval corresponding to the client level is 50-70%, and 60% is taken as a reference; and then combining the target characteristic value, if the client level in the target transaction characteristic data is one level, determining a target characteristic value 100, and then combining the target characteristic value 100, and adjusting the weight coefficient upwards from 60% to determine that the final target weight coefficient is 70%; correspondingly, if the target characteristic value is lower, the weight coefficient is downwards adjusted from 60%, and the specific adjustment proportion is correspondingly adjusted according to the duty ratio of the target characteristic value.

In a possible embodiment, it should be understood that the sum of all the target weight coefficients of the target evaluation function is 1 (100%), so that after determining the target weight coefficient corresponding to each target feature value in the target evaluation function, the target weight coefficient is corrected based on the proportional relationship between each target feature value in the target evaluation function.

Illustratively, the target evaluation function is a privacy-to-privacy class evaluation function, and the target feature values include: the client-level characteristic index value 80 and the transaction purpose characteristic index value 50 correspond to 75% of client-level weight coefficient and 38% of transaction purpose weight coefficient; and the sum of 75% of the client-level weight coefficient and 35% of the transaction purpose weight coefficient is 110% -100%, so that the client-level weight coefficient and the transaction purpose weight coefficient are correspondingly reduced according to the proportional relation between the client-level characteristic index value 80 and the transaction purpose characteristic index value 50, and the correction of the target weight coefficient is realized.

In this embodiment, according to the target evaluation function, determining transaction feature data to be extracted and a target weight interval corresponding to each transaction feature data to be extracted, further extracting target transaction feature data of the credit support request based on the transaction feature data to be extracted, determining a target feature index value corresponding to each target transaction feature data, and further determining each target weight coefficient according to the target feature index value and the target weight interval; the transaction characteristic data for credit branch authorization analysis comprises local and multidimensional information of a customer dimension and a merchant dimension, and integral interaction information between transaction uses and customers corresponding to merchant categories, and the transaction characteristics for more comprehensive credit branch can be obtained by carrying out characteristic analysis of credit branch requests in all aspects through correlation between the local and the whole and multiple dimensions; and through the weight proportion among different transaction characteristics, accurate screening analysis is carried out on transaction characteristic data in a most practical mode, credit branch risk identification is comprehensively and accurately carried out, balance between credit branch risk prevention and control and customer experience is realized, customer experience and credit branch authorization management and control accuracy are further improved, meanwhile, the data extraction and evaluation process is fully automatic, multiple nodes and manual intervention are not needed, and credit branch management and control safety and working efficiency are further improved.

Further, based on the above first and/or second embodiments, a third embodiment of the credit support authorization control method of the present application is provided, in this embodiment, step S30 includes:

step S31, inputting the target transaction characteristic data and the target weight coefficients into a preset credit authorization management model to obtain a credit authorization management group identifier matched with the credit support request;

inputting the obtained target transaction characteristic data and each target weight coefficient into a pre-trained credit authorization management and control model, determining a credit authorization management and control group matched with the credit support request according to the target transaction characteristic data and the target weight coefficient type by the credit authorization management and control model, and outputting the identification of the credit authorization management and control group, referring to fig. 3.

The credit authorization management and control group is a control group for respectively checking and managing the credit limit and the credit times of each credit branch request, and each credit branch request corresponds to one adaptive credit authorization management and control group; the matched credit authorization management and control group refers to a credit authorization management and control group which can furthest meet the loan requirements of clients on the basis of lower risk level; each credit authorization management and control group can correspond to different credit limit and credit times.

In a possible implementation manner, corresponding feature index values are determined according to the obtained transaction feature data, further, a risk score of the credit support request is calculated according to the feature index values and the weight coefficients, and the risk score is input into a pre-trained credit authorization management model to obtain an authorization result of the credit support request.

In another possible implementation manner, after the credit authorization management and control model evaluates the credit branch request, specific branch amount and branch times may be output, which may include a single branch amount, a natural daily branch amount, a natural week branch times, and the like; and setting a credit authorization management and control group as a target credit authorization management and control group, and enabling the target credit authorization management and control group to check the credit payment amount and the payment times of the credit support request so as to determine an authorization result.

In yet another possible embodiment, the number of times of use, etc. is generally fixed due to the natural Zhou Zhiyong credit, natural monthly credit, natural annual credit, etc. of each customer; therefore, according to the preset time, the historical transaction characteristic data of each time period can be respectively extracted, new risk assessment is carried out by the credit authorization management and control model, and the natural Zhou Zhiyong quota, the natural month quota, the natural year quota, the number of times of use and the like are redetermined, so that the relatively fixed quota and the relatively fixed number of times of use are obtained; for the single credit line, real-time risk assessment can be performed according to each initiated credit line request to determine the appropriate single credit line. Compared with the conventional credit support authorization control implemented according to the credit reputation or the transaction type, the standard setting of the credit limit and the credit times is fixed, and the differentiated credit support authorization control is difficult to implement according to the actual transaction condition, so that the credit support authorization control accuracy is lower; in the application, the credit limit and the credit number standard set during the credit authorization control are implemented, so that differentiated and accurate authorization control can be realized according to actual transaction conditions; for example, the client level of the client is higher, the corresponding credit limit is higher, but if the credit request belongs to private-to-business transaction, the merchant level of the corresponding merchant is lower, namely the risk level of the merchant is higher; at this time, through the real-time and differentially set credit line, the large-amount transaction between the user and the merchant is avoided, and the economic loss possibly caused by the user is greatly reduced, so that the safety of the client and the lender is protected.

Step S32, calling a corresponding target credit authorization management and control group according to the credit authorization management and control group identification, controlling the target credit authorization management and control group, and checking the credit limit and the credit times of the credit support request;

and screening a target credit authorization management group from a plurality of preset credit authorization management groups according to the credit authorization management group identification, so that the target credit authorization management group checks the credit limit and the credit times of the credit support request.

The verification is to acquire the single-time count of the credit support request, and the current day count, the current week count, the current month count, the current year count, the current day count, the current week count, the current month count and the current year count of the client of the credit support request; and comparing the used amount and the used times with the branch amount and the branch times standard set by the target credit authorization management and control group, wherein the branch amount standard set by the target credit authorization management and control group comprises: single credit, natural daily credit, natural weekly credit, natural monthly credit, natural annual credit, etc.; the count criteria may include: natural daily count, natural weekly count, natural monthly count, natural annual count, and the like; if the verification result is smaller than or equal to the verification result, judging that the verification is passed; if any one is larger than the first threshold value, judging that the verification is not passed.

Step S33, if the verification is passed, judging that the authorization result of the credit support request is successful authorization;

step S34, if the verification is not passed, judging that the authorization result of the credit support request is authorization failure.

If the verification is passed, the single credit amount of the credit support request and other credit amounts and the credit times are not beyond the credit amount and the credit times standard set by the target credit authorization management and control group, and the loan can be continued, the authorization result of the credit support request is judged to be successful, and the money is dialled according to the credit support request; if the verification fails, indicating that the single credit amount of the credit support request or any one or more of other credit amounts and credit times exceeds the credit limit and credit times standard set by the target credit authorization management and control group, and judging that the authorization result of the credit support request is authorization failure and ending the credit support request.

In this embodiment, compared with the conventional credit support authorization control implemented according to the customer credit or transaction type, the standard setting of the credit limit and the number of times of support is relatively fixed, and it is difficult to implement differentiated and dynamic credit support authorization control according to the actual transaction condition, resulting in lower accuracy of credit support authorization control; in the application, the credit limit and the credit number standard set during the credit support authorization control are implemented, so that dynamic differentiated and accurate authorization control can be realized according to actual transaction conditions; for example, the client level of the client is higher, the corresponding credit limit is higher, but if the credit request belongs to private-to-business transaction, the merchant level of the corresponding merchant is lower, namely the risk level of the merchant is higher; at the moment, through the real-time and differentially set support amount, the large-amount transaction between the user and the merchant is avoided, the economic loss possibly caused by the user is greatly reduced, and the fund safety of the client and the lender is protected; the method realizes balance between credit branch risk prevention and control and customer experience sense, further improves customer experience sense and credit branch authorization control accuracy, simultaneously realizes full automation of data extraction and evaluation process, does not need multi-node and manual intervention, and further improves credit branch management safety and work efficiency.

Further, based on the first, second and/or third embodiments, a more complete embodiment of the credit support authorization and management method of the present application is provided, in this embodiment, referring to fig. 4:

a client initiates a credit branch request through a client association terminal, and credit branch authorization management and control equipment judges the transaction type of the credit branch request; if the transaction is a private-to-private transaction, the acquired transaction characteristic data comprises: customer level and transaction use; if the transaction is a private-to-business transaction, the acquired transaction characteristic data comprises: customer level, merchant category and merchant level; according to the acquired transaction characteristic data, performing multidimensional assessment of credit support risk, outputting an assessed adaptive authorization management and control group identifier through a credit authorization management and control model, and further calling a target authorization management and control group according to the authorization management and control group identifier so as to verify the credit support amount and the support times of a credit support request; wherein, the credit includes: single-pen limit, natural daily limit, natural monthly limit and natural annual limit (limit is branch limit); the number of times of the branch comprises: natural times, natural Zhou Xianci, natural month times and natural years (the times are branch times); and outputting the authorization result of the credit support request according to the verification result, and passing or failing.

Further, an embodiment of the present application further provides a credit support authorization management apparatus, referring to fig. 5, applied to a credit support authorization management device, including:

the determining module 10 is configured to receive a credit support request sent by an associated terminal, determine a transaction type corresponding to the credit support request, and determine a target evaluation function adapted to the credit support request in a preset evaluation function database based on the transaction type;

the extracting module 20 is configured to extract target transaction feature data corresponding to the credit branch request according to the target evaluation function, and determine a target weight coefficient of each target transaction feature data for the credit branch request, where the target transaction feature data includes: one or more of customer level, transaction purpose, merchant category, and merchant level;

the sending module 30 is configured to input each target transaction characteristic data and each target weight coefficient to a preset credit authorization management model, obtain an authorization result of the credit support request, and send the authorization result to the associated terminal.

The specific implementation manner of the credit support authorization and control device is basically the same as that of each embodiment of the credit support authorization and control method, and is not repeated here.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.

The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.

Claims

1. An authorization management and control method for credit support, characterized in that the authorization management and control method for credit support comprises the following steps:

2. The credit support authorization management method according to claim 1, wherein the step of determining an objective evaluation function adapted to the credit support request in a preset evaluation function database based on the transaction type comprises:

3. The credit support authorization management method according to claim 1, wherein the step of extracting target transaction characteristic data corresponding to the credit support request according to the target evaluation function, and determining a target weight coefficient of each of the target transaction characteristic data for the credit support request includes:

4. A credit support authorization management method, as claimed in claim 3, wherein the step of determining transaction characteristic data to be extracted in accordance with the objective assessment function includes:

5. The credit support authorization management method according to claim 1, wherein the step of inputting each of the target transaction characteristic data and each of the target weight coefficients into a preset credit support authorization management model to obtain an authorization result of the credit support request includes:

6. The credit support authorization management method according to claim 1, further comprising, prior to the step of determining the transaction type to which the credit support request corresponds:

7. The credit support authorization management method according to claim 1, wherein the step of transmitting the authorization result to the associated terminal includes:

8. An authorization management device for credit support, the device comprising:

9. An authorization management device for credit support, the device comprising: a memory, a processor, and a credit-use authorization-policing program stored on the memory and executable on the processor, the credit-use authorization-policing program configured to implement the steps of the credit-use authorization-policing method of any one of claims 1 to 7.

10. A storage medium having stored thereon a credit support authorization management program which when executed by a processor performs the steps of the credit support authorization management method according to any of claims 1 to 7.