Credit card approval method, device, equipment, medium and program product

Abstract

The invention provides a credit card approval method which can be applied to the technical field of big data. The method comprises the steps of obtaining historical financial behavior data of a user and internal parameters of an approval model, wherein the approval model is used for generating an approval result of a credit card application of the user; based on the historical financial behavior data of the user and the internal parameters of the approval model, training an anomaly recognition model to obtain a trained anomaly recognition model, the trained anomaly recognition model being used for recognizing at least one of data integrity anomaly, system interaction anomaly and credit extension decision deviation in the credit card application process; and approving the credit card application of the user based on the approval model according to an exception result output by the trained exception recognition model. The invention further provides a credit card approval device and equipment, a storage medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of big data, and more specifically to a credit card approval method, apparatus, device, medium, and program product. Background Art

[0002] Currently, after a credit card application is submitted, it is reviewed and approved based on the user's submitted information. Once approved, the credit card is issued. The latest user information is also stored. Currently, credit card applications and approvals rely solely on the information provided by the customer and their previous card application history to calculate the card limit and determine the card's mailing address.

[0003] When a user's current information is insufficient to support credit card approval, only a smaller amount may be approved or the approval may fail. This also covers situations where approval fails due to incorrect customer information, system-wide data issues, or incorrect mailing addresses. Summary of the Invention

[0004] In view of the above problems, the present disclosure provides a credit card approval method, apparatus, device, medium and program product.

[0005] According to a first aspect of the present disclosure, a credit card approval method is provided, the method comprising:

[0006] Obtaining the user's historical financial behavior data and internal parameters of an approval model, wherein the approval model is used to generate an approval result for the user's credit card application;

[0007] Based on the user's historical financial behavior data and internal parameters of the approval model, an anomaly recognition model is trained to obtain a trained anomaly recognition model, wherein the trained anomaly recognition model is used to identify at least one of data integrity anomalies, system interaction anomalies, and credit decision deviations in the credit card application process;

[0008] According to the abnormal result output by the trained abnormality recognition model, the user's credit card application is approved based on the approval model.

[0009] According to an embodiment of the present disclosure, the historical financial behavior data includes historical card application records, historical consumption records on all platforms, and all financial business processing records;

[0010] The internal parameters of the approval model include the intermediate calculation variables of the approval model, temporary credit score data and logical flags triggered by risk control rules.

[0011] According to an embodiment of the present disclosure, the historical financial behavior data includes historical card application records, historical consumption records on all platforms, and all financial business processing records;

[0012] The internal parameters of the approval model include the intermediate calculation variables of the approval model, temporary credit score data and logical flags triggered by risk control rules.

[0013] According to an embodiment of the present disclosure, the abnormal result output by the trained abnormality recognition model includes a system interaction abnormal result;

[0014] Approving the user's credit card application based on the approval model according to the system interaction anomaly result output by the trained anomaly recognition model includes:

[0015] Simulate the interface return value that complies with system rules;

[0016] Based on the interface return value, the approval result of the user's credit card application is obtained using the approval model.

[0017] According to an embodiment of the present disclosure, the abnormal results output by the trained abnormality recognition model include credit decision deviation abnormal results;

[0018] The approving the user's credit card application based on the approval model according to the credit decision deviation abnormality result output by the trained abnormality recognition model includes:

[0019] Obtaining consumption behavior data of the user;

[0020] Adjusting the credit limit of the user's credit card application based on the user's consumption behavior data to obtain third repair data;

[0021] The third repair data is input into the approval model to obtain the approval result of the user's credit card application.

[0022] According to an embodiment of the present disclosure, the method further includes:

[0023] Monitoring log data of the trained anomaly recognition model in real time, wherein the log data includes at least one of input data, execution timestamp, and anomaly alarm information;

[0024] The log data is mapped and associated with the transaction serial number of the credit card application.

[0025] According to an embodiment of the present disclosure, the optimization goal of the trained anomaly recognition model includes at least one of reducing the error compensation rate and improving the quota matching degree.

[0026] A second aspect of the present disclosure provides a credit card approval device, the device comprising:

[0027] An acquisition module, configured to acquire the user's historical financial behavior data and internal parameters of an approval model, wherein the approval model is used to generate an approval result for the user's credit card application;

[0028] a training module for training an anomaly recognition model based on the user's historical financial behavior data and internal parameters of the approval model to obtain a trained anomaly recognition model, wherein the trained anomaly recognition model is used to identify at least one of data integrity anomalies, system interaction anomalies, and credit decision deviations in the credit card application process;

[0029] An approval module is used to approve the user's credit card application based on the approval model according to the abnormal results output by the trained abnormality recognition model.

[0030] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0031] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the computer program or instructions are executed by a processor.

[0032] The fifth aspect of the present disclosure further provides a computer program product, comprising a computer program or instructions, which implement the steps of the above method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0034] Figure 1 Schematically illustrates an application scenario diagram of the credit card approval method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0035] Figure 2 A flowchart of a credit card approval method according to an embodiment of the present disclosure is schematically shown;

[0036] Figure 3 Schematically shows a structural block diagram of a credit card approval device according to an embodiment of the present disclosure; and

[0037] Figure 4 A block diagram of an electronic device suitable for implementing a credit card approval method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0038] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the detailed description below, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0039] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0040] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0041] When expressions such as "at least one of A, B, and C, etc." are used, they should generally be interpreted in accordance with the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0042] In the technical solutions disclosed herein, all user information (including but not limited to user personal information, user image information, user transaction record information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are 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 the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0043] In scenarios where personal information is used for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure all provide users with corresponding operation portals for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge, and skills, and have reached a certain level of professionalism.

[0044] Figure 1 The following schematically illustrates an application scenario of the credit card approval method according to an embodiment of the present disclosure.

[0045] like Figure 1 As shown, the application scenario according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables, etc.

[0046] A user may use a first terminal device 101, a second terminal device 102, or a third terminal device 103 to interact with a server 105 via a network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, or the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0047] The first terminal device 101 , the second terminal device 102 , and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0048] The server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal devices.

[0049] It should be noted that the data processing method provided in the embodiments of the present disclosure can generally be executed by the server 105. Accordingly, the data processing device provided in the embodiments of the present disclosure can generally be set in the server 105. The data processing method provided in the embodiments of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the data processing device provided in the embodiments of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0050] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0051] The following will be based on Figure 1 The scene described by Figure 2 A credit card approval method according to an embodiment of the present disclosure is described in detail.

[0052] Figure 2 The flowchart of the credit card approval method according to the embodiment of the present disclosure is schematically shown.

[0053] like Figure 2 As shown, the credit card approval method of this embodiment includes operations S210 to S230.

[0054] In operation S210 , the user's historical financial behavior data and internal parameters of the approval model are obtained.

[0055] According to an embodiment of the present disclosure, before obtaining a user's historical financial behavior data, the user's consent or authorization may be obtained. For example, before operation S210, a request may be issued to the user to obtain the user's historical financial behavior data. If the user consents or authorizes the acquisition of the user's historical financial behavior data, operation S220 is executed.

[0056] In embodiments of the present disclosure, a corresponding operation portal can be provided for the user to choose to agree or reject the automated decision result. That is, before the anomaly recognition model is trained based on the user's historical financial behavior data, the user's consent or rejection instruction can be obtained through the corresponding operation portal. If the user agrees to the training, the anomaly recognition model is trained based on the user's historical financial behavior data, and step S220 is executed. If the user refuses to proceed with the processing / decision, the expert decision process is entered.

[0057] According to the embodiments of the present disclosure, historical financial behavior data can be structured behavior records generated during the interaction between users and financial institutions. It serves as input features for model training, reflecting the diversity and relevance of the data. Historical financial behavior data can include credit card-related data, cross-platform financial data, and derived indicator data. Credit card-related data can include historical card application records, overdue repayment records, consumption frequency and amount, etc. Cross-platform financial data can include loan records (such as online loans and mortgages), investment and financial management behaviors (such as fund subscriptions), and third-party payment data (such as annual bills from a certain platform). Derived indicator data can include user credit scores and debt-to-income ratios (DTI) calculated from the original data.

[0058] According to an embodiment of the present disclosure, the internal parameters of the approval model may be intermediate variables that are not direct inputs or outputs generated during the operation of the approval model.

[0059] According to an embodiment of the present disclosure, the approval model is used to generate an approval result for a user's credit card application. The approval result is the final output of the credit card application and can be a binary decision: approve / reject. The approval result can also include derivative decisions such as the initial credit limit, card tier (e.g., gold / platinum), and additional conditions (such as the need for supplementary documents).

[0060] According to an embodiment of the present disclosure, the output of the anomaly recognition model will correct or optimize the result (such as increasing the initial credit limit).

[0061] In operation S220 , an anomaly recognition model is trained based on the historical financial behavior data of the user and the internal parameters of the approval model to obtain a trained anomaly recognition model.

[0062] According to the disclosed embodiment, the trained anomaly recognition model is used to identify at least one of data integrity anomalies, system interaction anomalies, and credit decision deviations in the credit card application process. The anomaly recognition model can be generated based on a neural network model, a machine learning model, etc. For example, the neural network model can be a convolutional neural network, a generative adversarial coding model, a recurrent neural network, etc.

[0063] According to the disclosed embodiments, a data integrity anomaly means that certain necessary data is missing or incomplete during the credit card application process. This may affect the approval model's accurate assessment of the user's credit status and, in turn, the credit card approval result. Data integrity anomalies can include missing key fields, out-of-bounds values, logical contradictions, and more. For example, a missing key field could mean a blank ID number. For example, a logical contradiction could mean an age < 18 but the occupation is "engineer."

[0064] According to the disclosed embodiments, system interaction anomalies may occur during the credit card application process when different systems (such as the data acquisition system, approval system, and risk control system) experience problems in their interactions. These problems can include interface call failures, data transmission errors, and response timeouts. Such anomalies can disrupt the normal approval process, preventing the approval model from acquiring accurate or complete data, and thus affecting the accuracy of the credit card approval results.

[0065] According to the embodiments of the present disclosure, a credit decision deviation anomaly may occur when the approval model generates a credit card approval result and the decision on the user's credit limit deviates from normal or reasonable standards. For example, a high-income user may receive a low credit limit.

[0066] According to the embodiment of the present disclosure, a multi-task learning (Multi-taskLearning) architecture can be used to train an anomaly recognition model, share underlying features (such as user portraits), and branch out detection heads of different anomaly types at the upper layer.

[0067] In operation S230 , the user's credit card application is approved based on the approval model according to the abnormality result output by the trained abnormality recognition model.

[0068] According to the disclosed embodiments, data in the credit card application process can be supplemented or adjusted based on abnormal results. This means correcting data integrity anomalies, system interaction anomalies, and credit decision deviations, and then using the repaired results for approval based on the approval model. For example, when a "data integrity anomaly" is detected, third-party data can be automatically supplemented. Approval is then based on the supplemented data.

[0069] According to the disclosed embodiments, user behavior data (dynamic) and model parameters (static) are jointly trained to build cross-dimensional detection capabilities. This trained anomaly recognition model enables intelligent monitoring and compensation throughout the entire credit card approval process. Furthermore, three types of anomalies are systematically categorized in the credit card approval process, covering all risk points throughout the entire process. When data integrity anomalies, system interaction anomalies, and credit decision deviations are detected, the user's credit card application is approved based on the approval model, based on the anomaly results, achieving automated and intelligent decision-making.

[0070] In some embodiments of the present disclosure, historical financial behavior data includes historical card application records, historical consumption records on all platforms, and all financial business processing records.

[0071] Among them, historical card application records may refer to the number of times a user has applied for a credit card in this bank / other banks, the approval results, and the track of changes in the credit limit, which can reflect the stability of the user's credit history (for example, frequent card applications may indicate a tight capital chain).

[0072] Among them, historical consumption records on all platforms can include transaction data of e-commerce, offline payments, and cross-border consumption, dynamically evaluating users' real consumption capacity.

[0073] Financial business records can include the performance of loans, wealth management, and third-party lending. Multi-dimensional verification of a user's debt tolerance is required. For example, if a mortgage and credit loan are both available, special risk control rules are required.

[0074] According to an embodiment of the present disclosure, the internal parameters of the approval model include intermediate calculation variables of the approval model, temporary credit score data, and logical flags triggered by risk control rules.

[0075] Among them, intermediate calculation variables can reflect the intermediate status and calculation results of the approval model during data processing, such as the hidden layer output of the neural network and the node split value of the decision tree.

[0076] Temporary credit score data is generated by the approval model during the calculation of a user's credit score. It reflects the approval model's credit assessment process. Temporary credit score data can be a real-time credit score and its sub-scores (such as repayment history and debt-to-equity ratio).

[0077] Among them, the logical flag of the risk control rule triggering indicates which risk control rules are triggered during the approval process. The logical flag of the risk control rule triggering can be a binary flag set when the rule engine is executed. For example, rule_102=1 indicates that the "high-risk occupation" rule is triggered.

[0078] According to the embodiment of the present disclosure, by clarifying these internal parameters, more accurate input information is provided for training the anomaly recognition model, so as to better identify anomalies in the credit card application process.

[0079] In some embodiments of the present disclosure, the abnormal results output by the trained abnormality recognition model include data integrity abnormal results. Then, based on the data integrity abnormal results output by the trained abnormality recognition model, approving the user's credit card application based on the approval model includes: based on the target third-party data source, supplementing the data in the credit card application process to obtain first complete data; based on the first complete data, using the approval model to obtain the approval result of the user's credit card application.

[0080] In some embodiments of the present disclosure, the abnormal results output by the trained abnormality recognition model include data integrity abnormal results. Then, based on the data integrity abnormal results output by the trained abnormality recognition model, approving the user's credit card application based on the approval model includes: based on the user portrait of the user, supplementing the data in the credit card application process to obtain second complete data; based on the second complete data, using the approval model to obtain the approval result of the user's credit card application.

[0081] According to the embodiments of the present disclosure, when a data integrity anomaly is detected, there are two ways to supplement the data. One is based on the target third-party data source, through cooperation with the third-party data platform, to obtain the missing data, thereby completing the data in the credit card application process and obtaining the first complete data; the other is based on the user's user profile. The user profile usually contains multi-dimensional information about the user, such as age, occupation, consumption preferences, etc. This information can be used to infer or supplement the missing data and obtain the second complete data. These two methods provide different ways to solve the problem of data integrity anomalies, ensuring that there is sufficient and complete data for subsequent approval.

[0082] After obtaining the first or second complete data, this complete data is fed into the approval model, which processes and analyzes the data based on its internal logic and algorithms, ultimately determining the approval result for the user's credit card application. This approach ensures a smooth approval process even when data integrity anomalies exist, by supplementing the data and improving the accuracy and reliability of credit card approvals.

[0083] In some embodiments of the present disclosure, the abnormality results output by the trained abnormality recognition model include system interaction abnormality results. Approving the user's credit card application based on the approval model based on the system interaction abnormality results output by the trained abnormality recognition model includes: simulating an interface return value that complies with system rules; and obtaining an approval result for the user's credit card application using the approval model based on the interface return value.

[0084] According to an embodiment of the present disclosure, when a system interaction anomaly is detected, in order to enable the approval process to continue, an interface return value that complies with the system rules can be simulated. The interface return value refers to the data or status information returned by one system to another system during the system interaction process. Simulating an interface return value that complies with the system rules can be to generate a seemingly normal and expected return value according to the interaction rules and logic pre-set by the system to replace the real return value that cannot be obtained due to the interaction anomaly. This ensures the consistency of the approval process at the data level and enables subsequent approval steps to continue to be executed based on the simulated data.

[0085] According to the disclosed embodiment, the simulated interface return value is input into the approval model. The approval model analyzes and processes this simulated data according to its internal algorithms and rules, ultimately determining the approval result for the user's credit card application. This ensures that even if there are system interaction anomalies, the simulated interface return value ensures that the approval model has sufficient data to make a decision, thereby completing the credit card application approval process and improving the fault tolerance and stability of the approval process.

[0086] In some embodiments of the present disclosure, the abnormal results output by the trained abnormality recognition model include abnormal results indicating a credit decision deviation. Approving a user's credit card application based on the approval model based on the abnormal results indicating a credit decision deviation output by the trained abnormality recognition model includes: obtaining the user's consumption behavior data; adjusting the credit limit of the user's credit card application based on the user's consumption behavior data to obtain third repair data; and inputting the third repair data into the approval model to obtain an approval result for the user's credit card application.

[0087] According to the embodiments of the present disclosure, consumption behavior data can reflect various information such as the user's consumption habits, consumption ability, consumption stability, etc., such as the user's consumption amount, consumption frequency, consumption scenarios (such as online shopping, offline dining, etc.), consumption time distribution, etc.

[0088] According to an embodiment of the present disclosure, the credit limit of a user's credit card application is adjusted based on the acquired user consumption behavior data. If the credit limit originally given by the model approval is too high, which may pose a greater risk, then the limit is appropriately lowered based on the user's consumption capacity; if the credit limit originally given is too low, which may not meet the user's reasonable needs, then the limit is appropriately increased based on the user's consumption habits and repayment ability. The adjusted credit limit data is the third repair data, which is the result of correcting the original biased credit decision.

[0089] According to the disclosed embodiment, the adjusted third repair data (i.e., the corrected credit card application limit) is input into the approval model. Based on this repaired data, combined with its internal algorithms and rules, the approval model re-evaluates and re-decides the user's credit card application, ultimately determining the approval result. This approach corrects credit decision-making biases, making approval results more reasonable and accurate, reducing credit card business risks while improving user satisfaction.

[0090] In some embodiments of the present disclosure, the log data of the trained anomaly recognition model can be monitored in real time, and the log data includes at least one of input data, execution timestamp and anomaly alarm information; and the log data is associated with the transaction serial number mapping of the credit card application.

[0091] Input data records the various data received by the anomaly recognition model during processing, which serves as the basis for the model's anomaly identification. By monitoring input data, we can understand the source and characteristics of the data processed by the model, helping to analyze the anomaly recognition model's performance under different data inputs and determine whether data quality affects the anomaly recognition model's results.

[0092] Execution timestamps record the time at which the anomaly recognition model executes each operation, reflecting its operational efficiency and performance. For example, by analyzing execution timestamps, we can understand the average time it takes for the anomaly recognition model to process a credit card application, determine whether there are processing delays, and implement optimizations accordingly.

[0093] Exception alerts are generated when an anomaly recognition model detects anomalies during operation. These alerts can indicate issues encountered during operation, such as data format errors and system failures. This helps operations personnel identify and resolve issues promptly, ensuring the normal operation of the anomaly recognition model.

[0094] According to the disclosed embodiments, by mapping and associating log data with the credit card application transaction serial number, a complete tracking record can be established for each credit card application. The transaction serial number is a unique identifier in the credit card application process. By associating log data with it, the details of each application during the anomaly recognition model processing can be clearly understood.

[0095] According to the embodiments of the present disclosure, performance data of the model in actual applications can be regularly collected and analyzed, and the model can be iterated and optimized based on the performance data to improve its performance and effect.

[0096] In some embodiments of the present disclosure, the optimization goal of the trained anomaly recognition model includes at least one of reducing the error compensation rate and improving the quota matching degree.

[0097] According to embodiments of the present disclosure, the false compensation rate may be a measure of the likelihood of false compensation occurring during the credit card approval process, when an anomaly recognition model detects an anomaly and takes corresponding compensatory measures (e.g., adjusting the credit limit, supplementing data, etc.). The false compensation rate refers to the proportion of false compensations among all cases where compensation measures were taken, specifically the proportion of cases where no compensation was actually required or where the compensation method was inappropriate, relative to the total number of cases where compensation measures were taken.

[0098] According to the disclosed embodiments, a high error compensation rate means that many unnecessary compensation operations will occur, which may consume a large amount of manpower, material resources, and time resources. For example, incorrectly increasing a user's credit limit may cause the bank to assume higher credit risk; incorrectly supplementing data may increase data processing costs and the complexity of the approval process. Reducing the error compensation rate helps ensure the accuracy and rationality of compensation measures, making credit card approval results more consistent with actual conditions. This can improve the accuracy and reliability of approvals, reduce erroneous decisions caused by error compensation, and protect the interests of banks and users.

[0099] According to the disclosed embodiments, credit limit matching refers to the degree of match between the credit limit determined by the approval model for a user and factors such as the user's actual credit status, repayment ability, and consumption needs. A credit limit with a high credit limit matching can accurately reflect the user's credit level and risk tolerance, meeting the user's reasonable consumption needs without posing excessive credit risk to the bank, thereby avoiding an increase in bad debts due to excessively high credit limits or the loss of high-quality customers due to excessively low credit limits. By improving credit limit matching, banks can achieve a balance between risk and return and optimize risk management strategies.

[0100] Based on the above data processing method, the present disclosure also provides a credit card approval device. Figure 3 The device is described in detail.

[0101] Figure 3 The following schematically shows a structural block diagram of a credit card approval device according to an embodiment of the present disclosure.

[0102] like Figure 3 As shown, the credit card approval device of this embodiment includes an acquisition module 310 , a training module 320 and an approval module 330 .

[0103] The acquisition module 310 is used to obtain the user's historical financial behavior data and the internal parameters of the approval model, which is used to generate the approval result of the user's credit card application. In one embodiment, the acquisition module 310 can be used to perform the operation S210 described above, which will not be repeated here.

[0104] Training module 320 is configured to train an anomaly recognition model based on the user's historical financial behavior data and the internal parameters of the approval model, thereby generating a trained anomaly recognition model. This trained anomaly recognition model is used to identify at least one of data integrity anomalies, system interaction anomalies, and credit decision deviations in the credit card application process. In one embodiment, training module 320 can be configured to perform operation S220 described above and will not be further described here.

[0105] The approval module 330 is used to approve the user's credit card application based on the abnormal result output by the trained abnormal recognition model. In one embodiment, the approval module 330 can be used to perform the operation S230 described above, which will not be repeated here.

[0106] According to an embodiment of the present disclosure, the historical financial behavior data includes historical card application records, historical consumption records on all platforms, and all financial business processing records; the internal parameters of the approval model include the intermediate calculation variables of the approval model, temporary credit score data, and logical flags triggered by risk control rules.

[0107] According to an embodiment of the present disclosure, the abnormal results output by the trained abnormality recognition model include data integrity abnormal results; based on the data integrity abnormal results output by the trained abnormality recognition model, approving the user's credit card application based on the approval model includes: based on the target third-party data source, supplementing the data in the credit card application process to obtain first complete data; or, based on the user portrait of the user, supplementing the data in the credit card application process to obtain second complete data; based on the first complete data or the second complete data, using the approval model to obtain the approval result of the user's credit card application.

[0108] According to an embodiment of the present disclosure, the abnormal results output by the trained abnormality recognition model include system interaction abnormal results; based on the system interaction abnormal results output by the trained abnormality recognition model, approving the user's credit card application based on the approval model includes: simulating the interface return value that complies with system rules; based on the interface return value, using the approval model to obtain the approval result of the user's credit card application.

[0109] According to an embodiment of the present disclosure, the abnormal results output by the trained abnormality recognition model include abnormal results of credit decision deviation; based on the abnormal results of credit decision deviation output by the trained abnormality recognition model, approving the user's credit card application based on the approval model includes: obtaining the user's consumption behavior data; adjusting the credit limit of the user's credit card application based on the user's consumption behavior data to obtain third repair data; inputting the third repair data into the approval model to obtain the approval result of the user's credit card application.

[0110] According to an embodiment of the present disclosure, the device also includes: a monitoring module for monitoring the log data of the trained anomaly recognition model in real time, the log data including at least one of input data, execution timestamp and anomaly alarm information; a mapping module for mapping and associating the log data with the transaction serial number of the credit card application.

[0111] According to an embodiment of the present disclosure, the optimization goal of the trained anomaly recognition model includes at least one of reducing the error compensation rate and improving the quota matching degree.

[0112] According to embodiments of the present disclosure, any multiple modules among the acquisition module 310, training module 320, and approval module 330 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the acquisition module 310, training module 320, and approval module 330 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other suitable means of circuit integration or packaging, or may be implemented in any one of software, hardware, and firmware, or any suitable combination of these. Alternatively, at least one of the acquisition module 410, construction module 420, and determination module 430 may be at least partially implemented as a computer program module that, when executed, performs the corresponding functionality.

[0113] Figure 4 A block diagram of an electronic device suitable for implementing a credit card approval method according to an embodiment of the present disclosure is schematically shown.

[0114] like Figure 4 As shown, the electronic device according to an embodiment of the present disclosure includes a processor 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage portion 408 into a random access memory (RAM) 403. The processor 401 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 401 may also include onboard memory for caching purposes. The processor 401 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiment of the present disclosure.

[0115] Various programs and data required for the operation of the electronic device are stored in RAM 403. Processor 401, ROM 402, and RAM 403 are connected to each other via bus 404. Processor 401 executes the programs in ROM 402 and / or RAM 403 to perform various operations of the method flow according to the embodiment of the present disclosure. It should be noted that the program can also be stored in one or more memories other than ROM 402 and RAM 403. Processor 401 can also execute the programs stored in the one or more memories to perform various operations of the method flow according to the embodiment of the present disclosure.

[0116] According to an embodiment of the present disclosure, the electronic device may further include an input / output (I / O) interface 405, which is also connected to the bus 404. The electronic device 400 may further include one or more of the following components connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 408 including a hard disk; and a communication section 409 including a network interface card such as a LAN card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the removable media can be installed in the storage section 408 as needed.

[0117] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0118] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 402 and / or RAM 403 described above, and / or one or more memories other than ROM 402 and RAM 403.

[0119] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the data processing method provided by the embodiments of the present disclosure.

[0120] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 401 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0121] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 409, and / or installed from a removable medium 411. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0122] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the processor 401, the above-mentioned functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0123] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0125] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of the present disclosure. All such combinations and / or couplings fall within the scope of the present disclosure.

Claims

1. A credit card approval method, characterized in that: The method includes: Obtaining historical financial behavior data of a user and internal parameters of an approval model used to generate an approval result for the user's credit card application; Based on the user's historical financial behavior data and internal parameters of the approval model, an anomaly recognition model is trained to obtain a trained anomaly recognition model, wherein the trained anomaly recognition model is used to identify at least one of data integrity anomalies, system interaction anomalies, and credit decision deviations in the credit card application process; According to the abnormal result output by the trained abnormality recognition model, the user's credit card application is approved based on the approval model.

2. The method according to claim 1, characterized in that The historical financial behavior data includes historical card application records, historical consumption records on all platforms, and all financial business processing records; The internal parameters of the approval model include the intermediate calculation variables of the approval model, temporary credit score data and logical flags triggered by risk control rules.

3. The method according to claim 1 or 2, characterized in that The abnormal results output by the trained abnormality recognition model include data integrity abnormal results; Approving the user's credit card application based on the approval model according to the data integrity anomaly result output by the trained anomaly recognition model includes: Based on the target third-party data source, the data in the credit card application process is supplemented to obtain first complete data; or, based on the user profile of the user, the data in the credit card application process is supplemented to obtain second complete data; Based on the first complete data or the second complete data, the approval result of the user's credit card application is obtained using the approval model.

4. The method according to claim 1 or 2, characterized in that The abnormal results output by the trained abnormality recognition model include system interaction abnormal results; Approving the user's credit card application based on the approval model according to the system interaction anomaly result output by the trained anomaly recognition model includes: Simulate the interface return value that complies with system rules; Based on the interface return value, the approval result of the user's credit card application is obtained using the approval model.

5. The method according to claim 1 or 2, characterized in that The abnormal results output by the trained abnormality recognition model include abnormal results of credit decision deviation; The approving the user's credit card application based on the approval model according to the credit decision deviation abnormality result output by the trained abnormality recognition model includes: Obtaining consumption behavior data of the user; Adjusting the credit limit of the user's credit card application based on the user's consumption behavior data to obtain third repair data; The third repair data is input into the approval model to obtain the approval result of the user's credit card application.

6. The method according to claim 1, characterized in that The method further comprises: Monitoring log data of the trained anomaly recognition model in real time, wherein the log data includes at least one of input data, execution timestamp, and anomaly alarm information; The log data is mapped and associated with the transaction serial number of the credit card application.

7. The method according to claim 1, characterized in that The optimization goal of the trained anomaly recognition model includes at least one of reducing the error compensation rate and improving the quota matching degree.

8. A credit card approval device, characterized in that: The device comprises: An acquisition module, configured to acquire the user's historical financial behavior data and internal parameters of an approval model, wherein the approval model is used to generate an approval result for the user's credit card application; a training module for training an anomaly recognition model based on the user's historical financial behavior data and internal parameters of the approval model to obtain a trained anomaly recognition model, wherein the trained anomaly recognition model is used to identify at least one of data integrity anomalies, system interaction anomalies, and credit decision deviations in the credit card application process; An approval module is used to approve the user's credit card application based on the approval model according to the abnormal results output by the trained abnormality recognition model.

9. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images