Credit card quota approval method and device and storage medium

Abstract

The invention discloses a credit card quota approval method and device and a storage medium. The credit card quota approval method comprises the steps that when a credit card quota application request of an application user is received, associated information of the user is acquired; performing risk identification on the associated information through a large language model to obtain a risk type of the application user; when it is determined that the risk type is no risk, credit scoring is performed on the associated information through a credit scoring model to obtain a credit score of the user, and an adjustment coefficient is obtained according to the credit score and a coefficient adjustment rule; and adjusting the application quota according to the adjustment coefficient to obtain an approval quota, and feeding back the approval quota to the application user. The association information of the application user is analyzed through the large language model to obtain the risk type, and the approval quota is automatically determined in combination with the credit scoring model and the coefficient adjustment rule under the risk-free condition, so that a personalized quota approval scheme is provided according to the risk characteristics of the application user, and the quota approval efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention relates to the field of financial technology, and in particular to a method, apparatus and storage medium for approving credit card limits. Background Technology

[0002] With the continuous development of the credit card business, credit card installment business has become an important growth point for banks. At present, when banks approve credit card installment limits, they mainly rely on manual review to determine the approval limit for applicants.

[0003] However, manual review is inefficient and subjective, leading to inaccurate and inconsistent approval results. Therefore, the existing manual review method cannot meet the current demand for high-volume and high-accuracy review processes. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for approving credit card limits, so as to achieve accurate and efficient review of credit card limits.

[0005] According to a first aspect of this invention, a method for approving credit card limits is provided, comprising: obtaining the user's associated information when receiving a credit card limit application request from an applicant, wherein the credit card application request includes the requested limit;

[0006] The risk type of the applicant user is obtained by performing risk identification on the associated information using a large language model, wherein the risk type includes no risk, risky, and unknown risk;

[0007] When the risk type is determined to be risk-free, the user's credit score is obtained by performing a credit scoring on the associated information through a credit scoring model, and an adjustment coefficient is obtained according to the credit score and coefficient adjustment rules.

[0008] The application amount is adjusted according to the adjustment coefficient to obtain the approved amount, and the approved amount is then fed back to the applicant.

[0009] According to another aspect of the present invention, a credit card limit approval device is provided, comprising: an association information acquisition module, configured to acquire the user's association information when a credit card limit application request is received from an applicant user, wherein the credit card application request includes the requested limit;

[0010] The risk type identification module is used to identify the risk of the applicant user by using a large language model to identify the associated information. The risk type includes no risk, risky, and unknown risk.

[0011] The adjustment coefficient acquisition module is used to obtain the user's credit score by performing a credit scoring on the associated information through a credit scoring model when the risk type is determined to be risk-free, and to obtain the adjustment coefficient according to the credit score and the coefficient adjustment rule.

[0012] The approval quota acquisition module is used to adjust the application quota according to the adjustment coefficient to obtain the approval quota, and then feed back the approval quota to the applicant user.

[0013] According to another aspect of the present invention, a terminal device is provided, the terminal device comprising: one or more processors;

[0014] Storage device for storing one or more programs.

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the present invention.

[0016] According to another aspect of the present invention, a storage medium for computer-executable instructions is provided, on which a computer program is stored, which, when executed by a processor, implements the method as described in any of the embodiments of the present invention.

[0017] The technical solution of this invention analyzes the associated information of applicant users through a large language model, mines potential credit risks and repayment ability information to obtain risk types, and automatically determines the approval limit by combining a credit scoring model and coefficient adjustment rules in the absence of risk. Thus, based on the risk characteristics of applicant users, it provides personalized credit limit approval solutions, improving the efficiency and accuracy of credit limit approval.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of a credit card limit approval method according to Embodiment 1 of the present invention;

[0021] Figure 2 This is a flowchart of a credit card limit approval method according to Embodiment 2 of the present invention.

[0022] Figure 3 This is a schematic diagram of the structure of a credit card limit approval device according to Embodiment 3 of the present invention;

[0023] Figure 4 This is a structural block diagram of a terminal device provided in Embodiment 4 of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or terminal device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or terminal devices. Moreover, the information collected in this embodiment is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, necessary confidentiality measures have been taken, public order and good morals have not been violated, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0026] Example 1

[0027] Figure 1 This is a flowchart illustrating a method for executing a database query statement according to an embodiment of the present invention. This embodiment is applicable to situations involving the execution of database query statements. The method can be executed by a database query statement execution device, which can be implemented in hardware and / or software, and can be integrated into a terminal device. Figure 1 As shown, the method includes:

[0028] Step S101: When a credit card limit application request is received from an applicant, obtain the user's associated information.

[0029] Optionally, when a credit card limit application request is received from an applicant, the associated information of the applicant is obtained, including: when a credit card limit application request is received from an applicant, retrieving the database associated with the applicant, wherein the database includes a social media database, a consumption behavior database, and a financial institution database; when it is determined that the applicant has signed a data disclosure agreement for the database, the associated information of the applicant is queried from the database, wherein the associated information includes social media data, consumption behavior data, and financial status data.

[0030] Specifically, when an applicant needs to apply for a credit card, they submit a credit card limit application request on the financial system platform, including the requested limit amount. For example, the requested limit might be 3000. This is just an example and does not limit the specific amount requested. The financial system platform then reviews the application to determine whether to disburse funds according to the requested limit. Upon receiving the application, the platform retrieves data from databases associated with the applicant. This may involve establishing connections with the bank's internal system, third-party data providers, and social media platforms through designated interfaces. The platform accesses the bank's internal financial institution database, the third-party data provider's consumer behavior database, and the social media platform's social media database to collect multi-source data on the applicant in real time. Again, this is just an example and does not limit the specific types of databases used.

[0031] Before collecting relevant data from the aforementioned database, it is necessary to confirm that the applicant has signed a data disclosure agreement. This means that the database will only be used to query the applicant's related information, such as social media data, consumption behavior data, and financial information. Social media data can reflect whether the applicant has any debt relationships or social comments with other users. Consumption behavior data can reflect the applicant's consumption level. Financial information can reflect the applicant's account balance and transaction records. Of course, related information may also include basic information such as the applicant's length of service and occupation. This embodiment is only an example and does not limit the specific content of the related information of the applicant. As long as the related data is obtained with the permission of the applicant and through legal means, it is within the scope of protection of this application.

[0032] It should be noted that the associated information collected in this embodiment includes various forms. For example, social comments in social media data are unstructured data, transaction records in financial data are structured data, while consumption behavior is unstructured data. Therefore, the associated data obtained in this embodiment includes multi-source data in various forms, thereby ensuring the comprehensiveness and diversity of the associated information obtained.

[0033] Step S102: Use a large language model to identify risks in the associated information to obtain the risk type of the applicant user.

[0034] Optionally, risk identification of the associated information can be performed using a large language model to obtain the risk type of the applicant, including: preprocessing the associated information to obtain preprocessed associated information; extracting target features that affect credit card limit approval from the preprocessed associated information; and using a large language model to analyze the target features to obtain the applicant's repayment ability and determine the risk type based on the repayment ability.

[0035] Optionally, when the risk type is determined to be risky, an approval failure message is generated based on the risk type and the approval failure message is sent back to the approving user; when the risk type is determined to be unknown risk, an assistance approval message is generated based on the risk type and the approval amount specified by the approving user based on the assistance approval message is received.

[0036] Specifically, this embodiment introduces a large language model to analyze the aforementioned associated information. Because large language models possess powerful natural language processing and data analysis capabilities, they can deeply understand and mine structured data. Before inputting the associated information into the large language model, the collected information needs to be preprocessed. Preprocessing operations specifically include text cleaning, transformation, and feature extraction to remove duplicate, erroneous, and invalid data, and to uniformly transform data of different formats to extract target features that influence credit card limit approval. For structured data, duplicate and erroneous data are removed, and missing values ​​are filled. For unstructured data, text cleaning is performed to remove stop words and punctuation, and lexical segmentation and syntactic analysis are conducted. This embodiment is merely illustrative and does not limit the specific types of preprocessing operations. The extracted target features may include consumption frequency, consumption amount, consumption type, and social activity, etc. Again, this embodiment is merely illustrative and does not limit the specific types of target features; anything that can influence credit card limit approval is within the scope of this application.

[0037] In this implementation, after acquiring the target features and a pre-trained large language model, the target features are input into the large language model. The large language model analyzes the target features to obtain the applicant's repayment ability. For example, the large language model can analyze whether the applicant has a tendency to overspend and whether there is potential financial pressure. Of course, this implementation is only an example and does not limit the output of the large language model. The terminal device can determine the risk type based on the applicant's repayment ability output by the large language model. The risk type includes no risk, risky, and unknown risk. No risk means that the applicant's repayment credit is reliable and the subsequent approval credit limit can be issued. Risky means that the applicant's repayment credit is unreliable and the subsequent approval credit limit will not be issued. Furthermore, the terminal device will determine the risk type based on the current situation. The risk type is determined as follows: if there is risk, an approval rejection message is generated and sent to the approving user, thus informing the applicant of the approval result; if there is unknown risk, it indicates that the applicant may be a new user, and the available information is insufficient to accurately assess the user's risk profile. In this case, manual assistance is required. Specifically, an assistance approval message is generated based on the risk type and sent to the approving user, who then assists in the approval process. This assistance may involve retrieving more information about the applicant from other relevant legal channels or conducting a site visit to obtain assistance information. Based on this assistance information and related information, an approval limit is determined. This application primarily addresses the application scenario of determining the approval limit when the risk type is risk-free; therefore, the methods for determining the approval limit in risky and unknown risk scenarios will not be elaborated upon.

[0038] Step S103: When the risk type is determined to be risk-free, the user's credit score is obtained by performing credit scoring on the associated information through the credit scoring model, and the adjustment coefficient is obtained according to the credit score and coefficient adjustment rules.

[0039] Optionally, a credit score is obtained by scoring the associated information using a credit scoring model, and an adjustment coefficient is obtained based on the credit score and a coefficient adjustment rule. This includes: determining the association between the associated information and the credit score using a credit scoring model, and incorporating the associated information into the association to obtain the credit score; and querying the coefficient adjustment rule based on the credit score to obtain the adjustment coefficient, wherein the coefficient adjustment rule includes the correspondence between the credit score and the adjustment coefficient.

[0040] Specifically, when the risk type is determined to be risk-free, a credit card limit can be issued to the applicant. However, the specific amount issued requires further judgment. This application incorporates a credit scoring model during the approval process, using the aforementioned associated information of the applicant to calculate a credit score. The credit scoring model includes the correlation between associated information and credit scores. When the applicant's associated information is known, their credit score can be determined based on this correlation. In other words, when the applicant's risk type is risk-free, it can be predicted that the applicant is likely to repay, but on-time repayment is not guaranteed. Therefore, to further ensure the financial institution's fund security, this implementation method uses a credit scoring model to score applicants based on associated information. Since the associated information of each applicant is different, each applicant will receive a different credit score. This implementation method does not limit the specific numerical value of each applicant's credit score.

[0041] In this implementation, the adjustment coefficient for the applied credit limit is determined based on the credit score and pre-set coefficient adjustment rules. The coefficient adjustment rules include the correspondence between the credit score and the adjustment coefficient, as shown in Table 1 below as an example of the coefficient adjustment rules:

[0042]

[0043] Table 1 only uses two credit score ranges as examples for illustration, and the system adjustment rules can be predetermined. This implementation does not impose any specific limitations on the content of the coefficient adjustment rules. Therefore, when the applicant's credit score is determined, the corresponding adjustment coefficient can be obtained by referring to the frequency adjustment rules. The adjustment coefficient also includes a specific adjustment direction; the higher the credit score, the larger the corresponding downward adjustment coefficient.

[0044] Step S104: Adjust the application amount according to the adjustment coefficient to obtain the approved amount, and then provide the approved amount back to the applicant.

[0045] Optionally, the application amount can be adjusted according to the adjustment coefficient to obtain the approval amount, including: determining the adjustment amount and adjustment direction according to the adjustment coefficient, and adjusting the application amount according to the adjustment direction to obtain the initial amount; determining whether the initial amount is within the standard approval amount range. If so, the initial amount is directly used as the approval amount; otherwise, the initial amount is fed back to the approval user, and the approval amount is determined according to the verification instructions of the approval user.

[0046] Specifically, after obtaining the adjustment coefficient, this application needs to adjust the application amount according to the adjustment coefficient. For example, if the applicant's application amount is 2500 and the adjustment coefficient is a 2% reduction, the adjusted amount will be 2450. The adjusted amount will be used as the approval amount, and the determined approval amount will be fed back to the applicant. That is, the application amount is the user's submitted request, while the approval amount is the amount actually issued to the applicant after review. In general, the approval amount is less than the application amount. Of course, this embodiment is only an example and does not limit the specific value of the approval amount. Therefore, even if different applicants submit the same application amount, the approval amount fed back to different applicants may be different, thereby realizing personalized approval for applicants.

[0047] Specifically, in this implementation, the approved amount can be notified to the applicant via SMS or application message, and the approval process and results can be recorded on the financial system platform to facilitate subsequent problem tracing. Furthermore, this implementation will also feed the approval results back to the large language model, thereby enabling its optimization and updates. For example, if a certain feature is found to have a significant impact on the approved amount during the approval process, the feature extraction method of the large language model can be adjusted.

[0048] It is worth mentioning that this implementation method can perform in-depth analysis of unstructured data through a large language model, and uncover potential credit risk and repayment ability information, thereby improving the accuracy of credit card installment limit approval;

[0049] Based on the specific circumstances and risk characteristics of the applicant, a personalized installment limit approval plan is provided to meet the needs of different cardholders; in addition, this implementation method can also capture changes in the applicant's credit status and consumption behavior in real time, and adjust the installment limit in a timely manner to reduce credit risk.

[0050] The technical solution of this invention analyzes the associated information of applicant users through a large language model, mines potential credit risks and repayment ability information to obtain risk types, and automatically determines the approval limit by combining a credit scoring model and coefficient adjustment rules in the absence of risk. Thus, based on the risk characteristics of applicant users, it provides personalized credit limit approval solutions, improving the efficiency and accuracy of credit limit approval.

[0051] Example 2

[0052] Figure 2This is a flowchart of a credit card limit approval method provided by an embodiment of the present invention. Based on the above embodiment, after feeding back the approved limit to the applicant user, the method further includes: recording the applicant user's credit card repayment status and obtaining repayment records; when the repayment records indicate that the applicant user has a repayment risk, the method of disbursing the credit card limit in installments to the applicant user is suspended. Figure 2 As shown, the method includes:

[0053] Step S201: When a credit card limit application request is received from an applicant, obtain the user's associated information.

[0054] Optionally, when a credit card limit application request is received from an applicant, the associated information of the applicant is obtained, including: when a credit card limit application request is received from an applicant, retrieving the database associated with the applicant, wherein the database includes a social media database, a consumption behavior database, and a financial institution database; when it is determined that the applicant has signed a data disclosure agreement for the database, the associated information of the applicant is queried from the database, wherein the associated information includes social media data, consumption behavior data, and financial status data.

[0055] Step S202: Use a large language model to identify risks in the associated information to obtain the risk type of the applicant user.

[0056] Optionally, risk identification of the associated information can be performed using a large language model to obtain the risk type of the applicant, including: preprocessing the associated information to obtain preprocessed associated information; extracting target features that affect credit card limit approval from the preprocessed associated information; and using a large language model to analyze the target features to obtain the applicant's repayment ability and determine the risk type based on the repayment ability.

[0057] Optionally, when the risk type is determined to be risky, an approval failure message is generated based on the risk type and the approval failure message is sent back to the approving user; when the risk type is determined to be unknown risk, an assistance approval message is generated based on the risk type and the approval amount specified by the approving user based on the assistance approval message is received.

[0058] Step S203: When the risk type is determined to be risk-free, the user's credit score is obtained by performing credit scoring on the associated information through the credit scoring model, and the adjustment coefficient is obtained according to the credit score and coefficient adjustment rules.

[0059] Optionally, a credit score is obtained by scoring the associated information using a credit scoring model, and an adjustment coefficient is obtained based on the credit score and a coefficient adjustment rule. This includes: determining the association between the associated information and the credit score using a credit scoring model, and incorporating the associated information into the association to obtain the credit score; and querying the coefficient adjustment rule based on the credit score to obtain the adjustment coefficient, wherein the coefficient adjustment rule includes the correspondence between the credit score and the adjustment coefficient.

[0060] Step S204: Adjust the application amount according to the adjustment coefficient to obtain the approved amount, and then provide the approved amount back to the applicant.

[0061] Optionally, the application amount can be adjusted according to the adjustment coefficient to obtain the approval amount, including: determining the adjustment amount and adjustment direction according to the adjustment coefficient, and adjusting the application amount according to the adjustment direction to obtain the initial amount; determining whether the initial amount is within the standard approval amount range. If so, the initial amount is directly used as the approval amount; otherwise, the initial amount is fed back to the approval user, and the approval amount is determined according to the verification instructions of the approval user.

[0062] Step S205: Record the credit card repayment status of the applicant user and obtain the repayment record. When the repayment record indicates that the applicant user has a repayment risk, the installment disbursement to the applicant user according to the approved amount will be suspended.

[0063] Specifically, the repayment process for applicants is recorded, including any overdue or non-payment instances. These records help identify potential repayment risks. Even if a credit limit has been approved based on the applicant's historical information, unforeseen circumstances such as company bankruptcy could impact repayments. These financial crises are reflected in the repayment records. Therefore, if an applicant makes payments but is overdue more than twice or for a specified period, a repayment risk is identified. Continuing to disburse funds according to the approved limit would jeopardize the financial institution's security. This is just an example and does not limit the specific types of repayment risks. Any repayment behavior that impacts the financial institution's security can be identified through the repayment records, thus indicating a repayment risk.

[0064] In this process, when it is determined that an applicant has a repayment risk, an alert will be issued to the user to avoid further losses to the financial institution's funds, urging the user to repay on time. If the number of alerts exceeds a specified number, but the applicant still has overdue or non-payment issues, the installment disbursement to the applicant based on the approved amount will be suspended. In addition, if the applicant makes a repayment within the specified number of alerts, the terminal device will re-determine the applicant's adjustment coefficient based on the overdue repayment information, and re-determine the approved amount according to the updated adjustment coefficient. The re-determined approved amount is usually lower than the initially determined approved amount. Of course, this implementation is only an example and does not limit the specific value of the approved amount.

[0065] It should be noted that there is a limit to the number of times an applicant can update their coefficient adjustment. For example, if the coefficient adjustment is updated twice, the approval of the credit limit will be suspended. In other words, if an applicant has more than two overdue payments, the funds will no longer be disbursed.

[0066] The technical solution of this invention analyzes the associated information of applicant users through a large language model, mines potential credit risks and repayment ability information to obtain risk types, and automatically determines the approval limit by combining a credit scoring model and coefficient adjustment rules in the absence of risk. Thus, based on the risk characteristics of applicant users, it provides personalized credit limit approval solutions, improving the efficiency and accuracy of credit limit approval.

[0067] Example 3

[0068] Figure 3 This is a schematic diagram of a credit card limit approval device provided in an embodiment of the present invention. Figure 3 As shown, the device includes: an associated information acquisition module 310, a risk type identification module 320, an adjustment coefficient acquisition module 330, and an approval quota acquisition module 340.

[0069] The associated information acquisition module 310 is used to acquire the user's associated information when it receives the credit card limit application request from the applicant user, wherein the credit card application request includes the application limit;

[0070] The risk type identification module 320 is used to identify the risk of the applicant user by using a large language model to identify the risk of the associated information. The risk types include no risk, risky, and unknown risk.

[0071] The adjustment coefficient acquisition module 330 is used to obtain the user's credit score by performing credit scoring on the associated information through the credit scoring model when the risk type is determined to be no risk, and to obtain the adjustment coefficient according to the credit score and coefficient adjustment rules.

[0072] The approval quota acquisition module 340 is used to adjust the application quota according to the adjustment coefficient to obtain the approval quota, and then feed back the approval quota to the applicant user.

[0073] Optionally, the associated information acquisition module is used to retrieve the database associated with the applicant user when a credit card limit application request is received. The database includes social media databases, consumer behavior databases, and financial institution databases.

[0074] Once it is determined that the applicant has signed a data disclosure agreement for the database, the database will be queried to retrieve the applicant's associated information, which includes social media data, consumption behavior data, and financial information.

[0075] Optionally, a risk type identification module is used to preprocess the associated information to obtain the preprocessed associated information;

[0076] Extract target features that influence credit card limit approval from the preprocessed associated information;

[0077] By using a large language model to analyze target characteristics, we can obtain the repayment ability of applicants and determine the risk type based on their repayment ability.

[0078] Optionally, an adjustment coefficient acquisition module is used to determine the correlation between related information and credit score through a credit scoring model, and to input the related information into the correlation relationship to obtain the credit score;

[0079] The adjustment coefficient is obtained by querying the coefficient adjustment rules based on the credit score. The coefficient adjustment rules include the correspondence between the credit score and the adjustment coefficient.

[0080] Optionally, there is an approval limit acquisition module, which is used to determine the adjustment limit and adjustment direction based on the adjustment coefficient, and adjust the application limit according to the adjustment limit and adjustment direction to obtain the initial limit;

[0081] Determine if the initial limit is within the standard approval limit range. If so, use the initial limit as the approval limit directly. Otherwise, return the initial limit to the approving user and determine the approval limit based on the approving user's verification instructions.

[0082] Optionally, the approval limit acquisition module is also used to generate an approval failure message based on the risk type when the risk type is determined to be risky, and to send the approval failure message back to the approving user.

[0083] When the risk type is determined to be an unknown risk, an assistance approval message is generated based on the risk type, and the approval amount specified by the approving user based on the assistance approval message is received.

[0084] Optionally, the device also includes a repayment record module for recording and obtaining repayment records of the applicant's credit card repayment status;

[0085] If a repayment risk is identified in the repayment history of the applicant, the installment disbursement to the applicant based on the approved amount will be suspended.

[0086] The credit card limit approval device provided in this embodiment of the invention can execute the credit card limit approval method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0087] Example 4

[0088] Figure 4 A schematic diagram of a terminal device 10 that can be used to implement embodiments of the present invention is shown. The terminal device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The terminal device can also represent various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0089] The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0090] like Figure 4 As shown, the terminal device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the terminal device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] Multiple components in terminal device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows terminal device 10 to exchange information / data with other terminal devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as credit card limit approval methods.

[0093] In some embodiments, the credit card limit approval method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on terminal device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the credit card limit approval method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the credit card limit approval method by any other suitable means (e.g., by means of firmware).

[0094] Various embodiments of the apparatuses and techniques described above herein can be implemented in digital electronic circuit devices, integrated circuit devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), device-on-a-chip (SoCs), complex programmable logic terminal devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable device including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage device, at least one input device, and at least one output device, and transmitting data and instructions to the storage device, the at least one input device, and the at least one output device.

[0095] Computer programs used to implement the credit card limit approval method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other non-stop data migration device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution apparatus, device, or terminal device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage terminal devices, magnetic storage terminal devices, or any suitable combination thereof.

[0097] To provide interaction with a user, the apparatus and techniques described herein can be implemented on a terminal device having: a display device (e.g., a touchscreen) for displaying information to the user; and buttons through which the user can provide input to the terminal device. Other types of apparatus can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and input from the user can be received in any form (including voice input, speech input, or haptic input).

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for approving credit card limits, characterized in that, The method includes: When a credit card limit application request is received from a user, the user's associated information is obtained, wherein the credit card application request includes the requested credit limit; The risk type of the applicant user is obtained by performing risk identification on the associated information using a large language model, wherein the risk type includes no risk, risky, and unknown risk; When the risk type is determined to be risk-free, the user's credit score is obtained by performing a credit scoring on the associated information through a credit scoring model, and an adjustment coefficient is obtained according to the credit score and coefficient adjustment rules. The application amount is adjusted according to the adjustment coefficient to obtain the approved amount, and the approved amount is then fed back to the applicant.

2. The method according to claim 1, characterized in that, The step of obtaining the user's associated information when receiving a credit card limit application request from a user includes: When a credit card limit application request is received from the applicant, the database associated with the applicant is retrieved, including a social media database, a consumer behavior database, and a financial institution database. When it is determined that the applicant user has signed a data disclosure agreement for the database, the associated information of the applicant user is queried from the database, wherein the associated information includes social media data, consumption behavior data, and financial status data.

3. The method according to claim 1, characterized in that, The step of obtaining the risk type of the applicant user by performing risk identification on the associated information using a large language model includes: The associated information is preprocessed to obtain preprocessed associated information; Extract target features that affect credit card limit approval from the preprocessed association information; The large language model is used to analyze the target features to obtain the repayment ability of the applicant user, and the risk type is determined based on the repayment ability.

4. The method according to claim 1, characterized in that, The step of obtaining a user's credit score by performing a credit scoring on the associated information using a credit scoring model, and obtaining an adjustment coefficient based on the credit score and coefficient adjustment rules, includes: The credit scoring model is used to determine the correlation between the related information and the credit score, and the related information is then incorporated into the correlation to obtain the credit score. The adjustment coefficient is obtained by querying the coefficient adjustment rules based on the credit score, wherein the coefficient adjustment rules include the correspondence between the credit score and the adjustment coefficient.

5. The method according to claim 1, characterized in that, The step of adjusting the application amount according to the adjustment coefficient to obtain the approved amount includes: The adjustment amount and adjustment direction are determined according to the adjustment coefficient, and the applied amount is adjusted according to the adjustment direction to obtain an initial amount. Determine whether the initial limit is within the standard approval limit range. If so, use the initial limit as the approval limit directly. Otherwise, return the initial limit to the approving user and determine the approval limit based on the approving user's verification instruction.

6. The method according to claim 2, characterized in that, The method further includes: When the risk type is determined to be "risky", an approval failure message is generated based on the risk type and the approval failure message is sent back to the approving user. When the risk type is determined to be the unknown risk, an assistance approval message is generated according to the risk type, and the approval amount specified by the approval user based on the assistance approval message is received.

7. The method according to any one of claims 1 to 6, characterized in that, After the approved amount is fed back to the applicant user, the process also includes: Record the credit card repayment status of the applicant user to obtain repayment records; If the repayment record indicates that the applicant has a repayment risk, the installment disbursement to the applicant based on the approved amount will be suspended.

8. A credit card limit approval device, characterized in that, The device includes: The associated information acquisition module is used to acquire the user's associated information when a credit card limit application request is received from the applicant user, wherein the credit card application request includes the application limit; The risk type identification module is used to identify the risk of the applicant user by using a large language model to identify the associated information. The risk type includes no risk, risky, and unknown risk. The adjustment coefficient acquisition module is used to obtain the user's credit score by performing a credit scoring on the associated information through a credit scoring model when the risk type is determined to be risk-free, and to obtain the adjustment coefficient according to the credit score and the coefficient adjustment rule. The approval quota acquisition module is used to adjust the application quota according to the adjustment coefficient to obtain the approval quota, and then feed back the approval quota to the applicant user.

9. A terminal device, characterized in that, The terminal device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A storage medium for computer-executable instructions, wherein a computer program is stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images