Credit risk information determination method and system, electronic equipment and storage medium

Abstract

The invention provides a credit risk information determination method and system, electronic equipment and a storage medium. The method comprises the steps of inputting to-be-assessed data of multiple credit assessment dimensions of an application user into a credit risk assessment model to obtain a credit risk level corresponding to the application user; determining a target credit risk type corresponding to the application user according to the similarity between the to-be-evaluated data and historical evaluation data corresponding to each credit risk type; and generating credit risk information corresponding to the application user according to the credit risk level corresponding to the application user, the target credit risk type and the similarity between the to-be-assessed data and the historical assessment data corresponding to the target credit risk type. Through the mode of the application, the determination efficiency is improved, human errors are avoided, and the accuracy of determining the credit risk information is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, system, electronic device and storage medium for determining credit risk information. Background Art

[0002] In the field of credit review for credit card applications, in order to reduce the credit risk of financial institutions and ensure the stable operation of financial institutions, a large amount of information needs to be manually reviewed to determine the credit risk information of applicant users. When the credit risk information meets the requirements, the credit card application of the applicant user will be approved.

[0003] However, the traditional credit review process is inefficient in determining the credit risk information of applicant users, and is prone to human errors, reducing the accuracy of determining credit risk information, increasing the credit risk of financial institutions, and affecting the stable operation of financial institutions. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, system, electronic device and storage medium for determining credit risk information, which can determine credit risk information based on the data to be evaluated under multiple credit evaluation dimensions and the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type, improving the determination efficiency, avoiding human errors, increasing the accuracy of determining credit risk information, reducing the credit risk of financial institutions, and ensuring the stable operation of financial institutions.

[0005] In a first aspect, an embodiment of this application provides a method for determining credit risk information, the method comprising:

[0006] Obtain the data to be evaluated including multiple credit evaluation dimensions of an applicant user within a preset evaluation period, and the historical evaluation data corresponding to each credit risk type;

[0007] Input the data to be evaluated into a credit risk assessment model to obtain the credit risk level corresponding to the applicant user;

[0008] Determine the target credit risk type corresponding to the applicant user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type;

[0009] Generate the credit risk information corresponding to the applicant user according to the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type.

[0010] In a possible implementation, the evaluation dimensions include the historical transaction information dimension, the repayment behavior information dimension, and the social and economic background information dimension; the step of inputting the data to be evaluated into the credit risk assessment model to obtain the credit risk level corresponding to the applicant user includes:

[0011] Determining the transaction index information corresponding to the applicant user based on the data to be evaluated under the historical transaction information dimension;

[0012] Determining the repayment punctuality rate corresponding to the applicant user based on the data to be evaluated under the repayment behavior information dimension;

[0013] Determining the repayment ability score corresponding to the applicant user based on the data to be evaluated under the social and economic background information dimension;

[0014] Inputting the data to be evaluated, the transaction index information, the repayment punctuality rate, and the repayment ability score into the credit risk assessment model to obtain the credit risk level corresponding to the applicant user.

[0015] In a possible implementation, the step of determining the repayment ability score corresponding to the applicant user based on the data to be evaluated under the social and economic background information dimension includes:

[0016] Scoring each data to be evaluated under the social and economic background information dimension according to a preset scoring rule to obtain the score corresponding to each data to be evaluated under the social and economic background information dimension; different data to be evaluated under the social and economic background information dimension correspond to different preset scoring rules;

[0017] Performing weighted summation on the scores corresponding to all the data to be evaluated under the social and economic background information dimension to obtain the repayment ability score corresponding to the applicant user.

[0018] In a possible implementation, the data to be evaluated under the social and economic background information dimension includes income data, occupation information, educational background information, and residential area information; the step of scoring each data to be evaluated under the social and economic background information dimension according to a preset scoring rule to obtain the score corresponding to each data to be evaluated under the social and economic background information dimension includes:

[0019] Determining the first preset score corresponding to the income range where the income data is located as the first score;

[0020] Determining the second preset score corresponding to the occupation information as the second score;

[0021] Determining the third preset score corresponding to the educational background information as the third score;

[0022] Determine the fourth preset score corresponding to the residential area information as the fourth score;

[0023] Perform a weighted sum of the first score, the second score, the third score, and the fourth score to obtain the repayment ability score corresponding to the applying user.

[0024] In a possible implementation manner, the generating the credit risk information corresponding to the applying user according to the credit risk level corresponding to the applying user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type includes:

[0025] Input the credit risk level corresponding to the applying user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type into a large language model to obtain the credit risk information corresponding to the applying user;

[0026] Wherein, the credit risk information includes at least one of information such as a credit risk level, a credit risk type, risk factors, and risk improvement suggestions.

[0027] In a possible implementation manner, the method further includes:

[0028] If the credit risk level corresponding to the applying user is higher than the historical credit risk level corresponding to the applying user, or the number of the target credit risk types is greater than 1, perform a risk warning according to the credit risk information corresponding to the applying user.

[0029] In a possible implementation manner, the method further includes:

[0030] Obtain evaluation sample data under multiple credit evaluation dimensions and the actual credit risk levels corresponding to the evaluation sample data;

[0031] Use the evaluation sample data as samples and the actual credit risk levels corresponding to the evaluation sample data as labels to train the credit risk assessment model.

[0032] In a possible implementation manner, the method further includes:

[0033] Store the data to be evaluated as target sample data and the actual credit risk level corresponding to the data to be evaluated as the label corresponding to the target sample data into an updated dataset;

[0034] If the number of target sample data in the updated dataset is greater than a preset number, or the non-updated duration of the credit risk assessment model is greater than a preset update duration, then update the credit risk assessment model according to the target sample data and corresponding labels in the updated dataset.

[0035] In a second aspect, an embodiment of the present application further provides a system for determining credit risk information, and the system includes:

[0036] An acquisition module, configured to acquire the data to be evaluated including multiple credit evaluation dimensions of an application user within a preset evaluation duration, and historical evaluation data corresponding to each credit risk type;

[0037] An input module, configured to input the data to be evaluated into a credit risk assessment model to obtain the credit risk level corresponding to the application user;

[0038] A determination module, configured to determine the target credit risk type corresponding to the application user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type;

[0039] A generation module, configured to generate credit risk information corresponding to the application user according to the credit risk level corresponding to the application user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type.

[0040] In a possible implementation manner, the evaluation dimensions include a historical transaction information dimension, a repayment behavior information dimension, and a social and economic background information dimension; the input module is specifically configured to determine the transaction index information corresponding to the application user based on the data to be evaluated under the historical transaction information dimension; determine the repayment punctuality rate corresponding to the application user based on the data to be evaluated under the repayment behavior information dimension; determine the repayment ability score corresponding to the application user based on the data to be evaluated under the social and economic background information dimension; and input the data to be evaluated, the transaction index information, the repayment punctuality rate, and the repayment ability score into the credit risk assessment model to obtain the credit risk level corresponding to the application user.

[0041] In a possible implementation manner, the input module is further configured to:

[0042] Score each data to be evaluated under the social and economic background information dimension according to a preset scoring rule to obtain the score corresponding to each data to be evaluated under the social and economic background information dimension; different data to be evaluated under the social and economic background information dimension correspond to different preset scoring rules;

[0043] Weighted sum the scores corresponding to all the data to be evaluated under the dimension of the socio - economic background information to obtain the repayment ability score corresponding to the applicant user.

[0044] In a possible implementation manner, among the data to be evaluated under the dimension of the socio - economic background information, there are income data, occupation information, educational background information, and residential area information; the input module is specifically configured to determine the first preset score corresponding to the income range where the income data is located as the first score; determine the second preset score corresponding to the occupation information as the second score; determine the third preset score corresponding to the educational background information as the third score; determine the fourth preset score corresponding to the residential area information as the fourth score; and perform a weighted sum of the first score, the second score, the third score, and the fourth score to obtain the repayment ability score corresponding to the applicant user.

[0045] In a possible implementation manner, the generation module is specifically configured to input the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type into a large - language model to obtain the credit risk information corresponding to the applicant user; where the credit risk information includes at least one of credit risk level, credit risk type, risk factors, and risk improvement suggestions.

[0046] In a possible implementation manner, the system further includes: a warning module;

[0047] The warning module is configured to perform a risk warning according to the credit risk information corresponding to the applicant user if the credit risk level corresponding to the applicant user is higher than the historical credit risk level corresponding to the applicant user, or the number of the target credit risk types is greater than 1.

[0048] In a possible implementation manner, the input module is further configured to:

[0049] Obtain evaluation sample data and the corresponding actual credit risk levels under multiple credit evaluation dimensions;

[0050] Use the evaluation sample data as samples and the actual credit risk levels corresponding to the evaluation sample data as labels to train the credit risk assessment model.

[0051] In a possible implementation manner, the input module is further configured to:

[0052] Store the data to be evaluated as target sample data and the actual credit risk level corresponding to the data to be evaluated as the label corresponding to the target sample data into the updated dataset;

[0053] If the number of target sample data in the updated dataset is greater than a preset number, or the non-updated duration of the credit risk assessment model is greater than a preset update duration, then update the credit risk assessment model according to the target sample data in the updated dataset and the corresponding labels.

[0054] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus. The processor executes the machine-readable instructions to perform the steps of the method for determining credit risk information according to any one of the first aspects.

[0055] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, it performs the steps of the method for determining credit risk information according to any one of the first aspects.

[0056] An embodiment of the present application provides a method, a system, an electronic device, and a storage medium for determining credit risk information. The method includes: obtaining data to be evaluated including multiple credit evaluation dimensions of an applying user within a preset evaluation duration, and historical evaluation data corresponding to each credit risk type; inputting the data to be evaluated into a credit risk assessment model to obtain a credit risk level corresponding to the applying user; determining a target credit risk type corresponding to the applying user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type; generating credit risk information corresponding to the applying user according to the credit risk level corresponding to the applying user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type. The present application can determine credit risk information based on the data to be evaluated under multiple credit evaluation dimensions and the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type, improving the determination efficiency, avoiding human errors, increasing the accuracy of determining credit risk information, reducing the credit risk of financial institutions, and ensuring the stable operation of financial institutions. Description of the Drawings

[0057] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1The flowchart of a method for determining credit risk information provided by an embodiment of the present application is shown;

[0059] Figure 2 The flowchart of another method for determining credit risk information provided by an embodiment of the present application is shown;

[0060] Figure 3 The schematic structural diagram of a system for determining credit risk information provided by an embodiment of the present application is shown;

[0061] Figure 4 The schematic structural diagram of an electronic device provided by an embodiment of the present application is shown. Detailed implementation manners

[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application are only for the purposes of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual scale. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowchart may not be implemented in sequence, and the steps without logical context relationships may be reversed or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.

[0063] In addition, the described embodiments are only some embodiments of the present application, rather than all embodiments. The components of the embodiments of the present application usually described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0064] To enable those skilled in the art to use the content of the present application, the following implementation manners are given in combination with a specific application scenario, the "data processing technology field". For those skilled in the art, without departing from the spirit and scope of the present application, the general principles defined here can be applied to other embodiments and application scenarios. Although the present application is mainly described around the "data processing technology field", it should be understood that this is only an exemplary embodiment.

[0065] It should be noted that the term "including" will be used in the embodiments of the present application to indicate the existence of the features stated thereafter, but does not exclude the addition of other features.

[0066] A method for determining credit risk information provided by an embodiment of the present application will be described in detail below.

[0067] Refer to Figure 1 As shown, it is a flowchart of a method for determining credit risk information provided by an embodiment of the present application. The following will describe each step of the embodiment of the present application by way of example:

[0068] S101. Obtain the data to be evaluated including multiple credit evaluation dimensions of the applying user within a preset evaluation period, and the historical evaluation data corresponding to each credit risk type.

[0069] In the embodiment of the present application, the applying user refers to the user applying for a credit card. The credit evaluation dimensions are included in the user information dimensions corresponding to the applying user; the data to be evaluated for the credit evaluation dimensions refers to the user data of the applying user under the corresponding user information dimensions; the user information dimensions may include the historical transaction information dimension, the repayment behavior information dimension, the social and economic background information dimension, etc., and then the credit evaluation dimensions may also include the historical transaction information dimension, the repayment behavior information dimension, the social and economic background information dimension, etc. Each piece of data to be evaluated includes user information of multiple credit evaluation dimensions; the preset evaluation period may be one year, half a year, etc.

[0070] Here, the data to be evaluated including multiple credit evaluation dimensions can comprehensively reflect the economic situation and behavior pattern of the applying user, provide rich data support for the subsequent determination of credit risk information, and improve the accuracy and comprehensiveness of determining credit risk information.

[0071] In addition, different historical evaluation data corresponds to each credit risk type. The credit risk type may be fraud application, default risk (referring to the risk that the borrower fails to fulfill the repayment obligation according to the agreed repayment plan), liquidity risk (referring to the risk that the borrower is unable to repay the debt on time due to financial difficulties in capital turnover), etc. For each credit risk type, the historical evaluation data corresponding to the credit risk type refers to the typical historical evaluation data with the credit risk corresponding to the credit risk type; the historical evaluation data and the credit evaluation dimensions corresponding to the data to be evaluated are the same.

[0072] S102. Input the data to be evaluated into the credit risk assessment model to obtain the credit risk level corresponding to the applying user.

[0073] In the embodiment of the present application, the credit risk assessment model may be pre-trained through the evaluation sample data and the actual credit risk levels corresponding to the evaluation sample data.

[0074] Specifically, referring to Figure 2 The following is a schematic flowchart of the method for determining the credit risk level provided by the embodiment of the present application:

[0075] S201. Determine the transaction index information corresponding to the applicant user based on the data to be evaluated under the dimension of historical transaction information.

[0076] In the embodiment of the present application, the data to be evaluated under the dimension of historical transaction information may include the transaction amount, transaction location, transaction category (such as shopping, dining, medical treatment, etc.), and transaction time of the applicant user. Among them, the transaction index information may include the transaction frequency, total transaction amount, average transaction amount, etc.

[0077] Here, the ratio of the number of data to be evaluated under the dimension of historical transaction information to the preset evaluation duration is determined as the transaction frequency corresponding to the applicant user. The sum value of the transaction amounts in all the data to be evaluated under the dimension of historical transaction information is determined as the total transaction amount corresponding to the applicant user. The ratio of the total transaction amount to the number of data to be evaluated under the dimension of historical transaction information is determined as the average transaction amount.

[0078] S202. Determine the repayment punctuality rate corresponding to the applicant user based on the data to be evaluated under the dimension of repayment behavior information.

[0079] In the embodiment of the present application, the data to be evaluated under the dimension of repayment behavior information may include the repayment completed amount, amount to be repaid, repayment completion date, latest repayment date, repayment type (such as credit card, housing loan, etc.), etc.

[0080] Here, among the data to be evaluated under the dimension of repayment behavior information, count the number of data to be evaluated where the repayment completion date is less than or equal to the latest repayment date and the repayment completed amount is equal to the amount to be repaid, to obtain the target number; the ratio of the target number to the number of data to be evaluated under the dimension of repayment behavior information is determined as the repayment punctuality rate corresponding to the applicant user.

[0081] S203. Determine the repayment ability score corresponding to the applicant user based on the data to be evaluated under the dimension of social and economic background information.

[0082] i. Score each data to be evaluated under the dimension of social and economic background information according to the preset scoring rules, to obtain the score corresponding to each data to be evaluated under the dimension of social and economic background information; different data to be evaluated under the dimension of social and economic background information correspond to different preset scoring rules.

[0083] In the embodiments of the present application, the data to be evaluated in the dimension of economic background information may include income data, occupation information, educational background information, residential area information, etc. Residential area information; the income data may refer to the total income within a preset income period (one year, half a year, etc.).

[0084] Specifically, each data to be evaluated in the dimension of social and economic background information is scored according to a preset scoring rule, including:

[0085] Step 1: Determine the first preset score corresponding to the income range where the income data is located as the first score.

[0086] In the embodiments of the present application, multiple income ranges are preset, and different income ranges correspond to different first preset scores. The larger the value corresponding to the income range, the larger the first preset score corresponding to the income range.

[0087] Step 2: Determine the second preset score corresponding to the occupation information as the second score.

[0088] In the embodiments of the present application, different occupation information corresponds to different second preset scores. The second preset scores corresponding to each occupation information are determined in advance through the following steps, including: the occupation information may include years of service, rank of appointment, position of appointment, etc.; calculate the average salary of multiple employees corresponding to each occupation information; based on the average salary corresponding to each occupation information, determine the second score corresponding to each occupation information; the higher the salary, the higher the second preset score corresponding to the occupation information.

[0089] Step 3: Determine the third preset score corresponding to the educational background information as the third score.

[0090] In the embodiments of the present application, different educational background information (such as primary school, junior high school, high school, bachelor's degree from XXX school, master's degree from XXX school, doctor's degree from XXX school, etc.) corresponds to different third preset scores. The better the school corresponding to the educational background information and the higher the educational level, the higher the corresponding third preset score.

[0091] Step 4: Determine the fourth preset score corresponding to the residential area information as the fourth score.

[0092] In the embodiments of the present application, different residential area information corresponds to different fourth preset scores. The residential area information may include the average salary of the residential area, the administrative region division level of the area where it is located (city, town, village, etc.), and the comprehensive development level of the area where it is located (such as first-tier, second-tier, and third-tier, etc.). The higher the average salary of the residential area, the higher the administrative region division level of the area where it is located, and the higher the comprehensive development level of the area where it is located, the higher the fourth score corresponding to the residential area information.

[0093] Calculate the fourth preset score corresponding to each residential area information through the following steps:

[0094] (1) Determine the preset score corresponding to the salary range where the average salary of the residential area is located as the residential area salary score corresponding to the residential area information;

[0095] (2) Determine the preset score corresponding to the administrative region division level of the region where it is located as the administrative region score corresponding to the residential area information;

[0096] (3) Determine the preset score corresponding to the comprehensive development level of the region where it is located as the development level score corresponding to the residential area information;

[0097] (4) Perform weighted summation on the residential area salary score, administrative region score, and development level score corresponding to the residential area information to obtain the fourth preset score corresponding to each residential area information.

[0098] ii. Perform weighted summation on the scores corresponding to all the data to be evaluated under the dimension of social and economic background information to obtain the repayment ability score of the applying user.

[0099] The method further includes: obtaining evaluation sample data under multiple credit evaluation dimensions and the corresponding actual credit risk levels; using the evaluation sample data as samples and the corresponding actual credit risk levels of the evaluation sample data as labels to train the credit risk assessment model.

[0100] S204. Input the data to be evaluated, transaction index information, repayment punctuality rate, and repayment ability score into the credit risk assessment model to obtain the credit risk level of the applying user.

[0101] In addition, train the credit risk assessment model through the following steps:

[0102] Step 1. Obtain evaluation sample data under multiple credit evaluation dimensions and the corresponding actual credit risk levels.

[0103] In the embodiment of the present application, obtain the initial evaluation sample data and the corresponding actual credit risk levels of multiple applying users under multiple credit evaluation dimensions from channels such as the banking system and credit investigation agencies; perform cleaning (removing noise, filling missing values, etc.), duplicate removal, and formatting processing on the initial evaluation sample data to ensure data quality and consistency, and obtain the target evaluation sample data and the corresponding actual credit risk levels.

[0104] Step 2. Use the evaluation sample data as samples and the corresponding actual credit risk levels of the evaluation sample data as labels to train the credit risk assessment model.

[0105] In the embodiment of the present application, the evaluation sample data is input into the credit risk assessment model to obtain the predicted credit risk level corresponding to the evaluation sample data; the credit risk assessment model is trained according to the actual credit risk level and the predicted credit risk level corresponding to the evaluation sample data.

[0106] Here, inputting the evaluation sample data into the credit risk assessment model to obtain the predicted credit risk level corresponding to the applying user includes: determining the transaction index information sample based on the evaluation sample data in the dimension of historical transaction information; determining the repayment punctuality rate sample based on the evaluation sample data in the dimension of repayment behavior information; determining the repayment ability score sample based on the evaluation sample data in the dimension of social and economic background information; inputting the evaluation sample data, the transaction index information sample, the repayment punctuality rate sample and the repayment ability score sample into the credit risk assessment model to obtain the predicted credit risk level corresponding to the evaluation sample data.

[0107] Optionally, the method further includes: storing the data to be evaluated as the target sample data and the actual credit risk level corresponding to the data to be evaluated as the label corresponding to the target sample data into the updated dataset; if the number of target sample data in the updated dataset is greater than the preset number, or the non-updated duration of the credit risk assessment model is greater than the preset update duration, then update the credit risk assessment model according to the target sample data and the corresponding labels in the updated dataset.

[0108] Here, the present application updates the credit risk assessment model regularly to adapt to market changes and new fraud means, and enhance the adaptability and robustness of the model.

[0109] S103. Determine the target credit risk type corresponding to the applying user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type.

[0110] In the embodiment of the present application, the credit risk type of the historical evaluation data with a similarity greater than the preset similarity to the data to be evaluated is determined as the target credit risk type corresponding to the applying user. If all similarities are less than the preset similarity, it means that the applying user has no risk in all credit risk types.

[0111] S104. Generate the credit risk information corresponding to the applying user according to the credit risk level corresponding to the applying user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type.

[0112] In an embodiment of the present application, the credit risk level corresponding to the applicant user, the target credit risk type, the data to be evaluated, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type are input into a large language model to obtain the credit risk information corresponding to the applicant user; wherein, the credit risk information includes at least one of a credit risk level, a credit risk type, a risk factor, and a risk improvement suggestion (such as reducing the debt ratio, increasing income, etc.).

[0113] Among them, the risk factor refers to the reason why the applicant user has this credit risk level and this credit risk type.

[0114] Optionally, if the credit risk level corresponding to the applicant user is higher than the historical credit risk level corresponding to the applicant user, or the number of target credit risk types is greater than 1, then risk warning (such as voice broadcast, SMS reminder, etc.) is performed according to the credit risk information corresponding to the applicant user.

[0115] Furthermore, the credit risk information corresponding to the applicant user is sent to the review personnel for credit card application, so that the review personnel can conduct credit card application review based on the credit risk information corresponding to the applicant user.

[0116] An embodiment of the present application provides a method for determining credit risk information. The method includes: obtaining the data to be evaluated of the applicant user under multiple credit evaluation dimensions within a preset evaluation duration, and the historical evaluation data corresponding to each credit risk type; inputting the data to be evaluated into a credit risk evaluation model to obtain the credit risk level corresponding to the applicant user; determining the target credit risk type corresponding to the applicant user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type; generating the credit risk information corresponding to the applicant user according to the credit risk level corresponding to the applicant user, the target credit risk type, the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type. The present application can determine credit risk information based on the data to be evaluated under multiple credit evaluation dimensions and the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type, improving the determination efficiency, avoiding human errors, improving the accuracy of determining credit risk information, reducing the credit risk of financial institutions, and ensuring the stable operation of financial institutions.

[0117] Based on the same inventive concept, an embodiment of the present application also provides a system for determining credit risk information corresponding to the method for determining credit risk information. Since the principle of solving problems by the system in the embodiment of the present application is similar to the method for determining credit risk information in the above embodiment of the present application, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be elaborated.

[0118] Refer to Figure 3As shown in the figure, it is a schematic diagram of a system for determining credit risk information provided by an embodiment of the present application. The system for determining credit risk information includes:

[0119] An acquisition module 301, configured to acquire data to be evaluated including multiple credit evaluation dimensions of an applicant user within a preset evaluation period, and historical evaluation data corresponding to each credit risk type;

[0120] An input module 302, configured to input the data to be evaluated into a credit risk assessment model to obtain a credit risk level corresponding to the applicant user;

[0121] A determination module 303, configured to determine a target credit risk type corresponding to the applicant user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type;

[0122] A generation module 304, configured to generate credit risk information corresponding to the applicant user according to the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type.

[0123] In a possible implementation manner, the evaluation dimensions include a historical transaction information dimension, a repayment behavior information dimension, and a social and economic background information dimension; the input module 302 is specifically configured to determine transaction index information corresponding to the applicant user based on the data to be evaluated under the historical transaction information dimension; determine the repayment punctuality rate corresponding to the applicant user based on the data to be evaluated under the repayment behavior information dimension; determine the repayment ability score corresponding to the applicant user based on the data to be evaluated under the social and economic background information dimension; and input the data to be evaluated, the transaction index information, the repayment punctuality rate, and the repayment ability score into the credit risk assessment model to obtain a credit risk level corresponding to the applicant user.

[0124] In a possible implementation manner, the input module 302 is further configured to:

[0125] Score each data to be evaluated under the social and economic background information dimension according to a preset scoring rule to obtain a score corresponding to each data to be evaluated under the social and economic background information dimension; different data to be evaluated under the social and economic background information dimension correspond to different preset scoring rules;

[0126] Perform weighted summation on the scores corresponding to all the data to be evaluated under the social and economic background information dimension to obtain the repayment ability score corresponding to the applicant user.

[0127] In a possible implementation, the data to be evaluated under the dimension of the socio-economic background information includes income data, occupation information, educational background information, and residential area information; the input module 302 is further configured to:

[0128] Determine the first preset score corresponding to the income range where the income data is located as the first score;

[0129] Determine the second preset score corresponding to the occupation information as the second score;

[0130] Determine the third preset score corresponding to the educational background information as the third score;

[0131] Determine the fourth preset score corresponding to the residential area information as the fourth score;

[0132] Perform weighted summation on the first score, the second score, the third score, and the fourth score to obtain the repayment ability score corresponding to the applying user.

[0133] In a possible implementation, the generation module 304 is specifically configured to input the credit risk level corresponding to the applying user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type into a large language model to obtain the credit risk information corresponding to the applying user; wherein, the credit risk information includes at least one of the credit risk level, the credit risk type, the risk factors, and the risk improvement suggestions.

[0134] In a possible implementation, the system further includes: a warning module 305;

[0135] The warning module 305 is configured to perform risk warning according to the credit risk information corresponding to the applying user if the credit risk level corresponding to the applying user is higher than the historical credit risk level corresponding to the applying user, or the number of the target credit risk types is greater than 1.

[0136] In a possible implementation, the input module 302 is further configured to:

[0137] Obtain the evaluation sample data and the corresponding actual credit risk levels under multiple credit evaluation dimensions;

[0138] Use the evaluation sample data as samples and the actual credit risk levels corresponding to the evaluation sample data as labels to train the credit risk assessment model.

[0139] In a possible implementation, the input module 302 is further configured to:

[0140] Store the data to be evaluated as target sample data and the actual credit risk level corresponding to the data to be evaluated as the label corresponding to the target sample data in the updated dataset;

[0141] If the number of target sample data in the updated dataset is greater than the preset number, or the non-updated duration of the credit risk assessment model is greater than the preset update duration, update the credit risk assessment model according to the target sample data and the corresponding labels in the updated dataset.

[0142] An embodiment of the present application provides a system for determining credit risk information. The system includes: an acquisition module 301 for acquiring data to be evaluated of an applicant user under multiple credit evaluation dimensions within a preset evaluation duration, and historical evaluation data corresponding to each credit risk type; an input module 302 for inputting the data to be evaluated into a credit risk assessment model to obtain the credit risk level corresponding to the applicant user; a determination module 303 for determining the target credit risk type corresponding to the applicant user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type; a generation module 304 for generating credit risk information corresponding to the applicant user according to the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type. The present application can determine credit risk information based on the data to be evaluated under multiple credit evaluation dimensions and the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type, improving the determination efficiency, avoiding human errors, increasing the accuracy of determining credit risk information, reducing the credit risk of financial institutions, and ensuring the stable operation of financial institutions.

[0143] As Figure 4 shown, an electronic device 400 provided by an embodiment of the present application includes: a processor 401, a memory 402, and a bus. The memory 402 stores machine-readable instructions executable by the processor 401. When the electronic device runs, the processor 401 communicates with the memory 402 through the bus, and the processor 401 executes the machine-readable instructions to perform the steps of the method for determining credit risk information as described above.

[0144] Specifically, the above-mentioned memory 402 and processor 401 can be general-purpose memory and processor, which are not specifically limited here. When the processor 401 runs the computer program stored in the memory 402, it can execute the method for determining credit risk information as described above.

[0145] Corresponding to the above method for determining credit risk information, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the above method for determining credit risk information.

[0146] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems and devices can refer to the corresponding processes in the method embodiments, and will not be elaborated in the present application. In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, and the indirect coupling or communication connection of the devices or modules may be in an electrical, mechanical, or other form.

[0147] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0149] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the information processing method described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0150] The above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining credit risk information, characterized in that: The method comprises: Obtain the applicant's data to be assessed within the preset assessment period, including multiple credit assessment dimensions, and the historical assessment data corresponding to each credit risk type; Inputting the data to be evaluated into a credit risk evaluation model to obtain the credit risk level corresponding to the applicant; Determining the target credit risk type corresponding to the applicant user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type; Credit risk information corresponding to the applicant user is generated according to the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type.

2. The method for determining credit risk information according to claim 1, characterized in that: The credit assessment dimensions include historical transaction information, repayment behavior information, and socioeconomic background information; The step of inputting the data to be evaluated into a credit risk evaluation model to obtain a credit risk level corresponding to the applicant user includes: Determine the transaction indicator information corresponding to the applicant user based on the data to be evaluated under the historical transaction information dimension; Determine the repayment punctuality rate corresponding to the applicant user based on the data to be evaluated under the repayment behavior information dimension; Determine the repayment ability score corresponding to the applicant user based on the data to be evaluated under the dimension of the socioeconomic background information; The data to be evaluated, the transaction index information, the repayment punctuality rate and the repayment ability score are input into the credit risk evaluation model to obtain the credit risk level corresponding to the applicant user.

3. The method for determining credit risk information according to claim 2, characterized in that: The step of determining the repayment ability score corresponding to the applicant user based on the data to be evaluated under the dimension of the socioeconomic background information includes: Scoring each data to be evaluated under the dimension of the socioeconomic background information according to a preset scoring rule to obtain a score corresponding to each data to be evaluated under the dimension of the socioeconomic background information; different data to be evaluated under the dimension of the socioeconomic background information corresponds to different preset scoring rules; The scores corresponding to all the data to be evaluated under the dimension of the socioeconomic background information are weighted and summed to obtain the repayment ability score corresponding to the applicant user.

4. The method for determining credit risk information according to claim 3, characterized in that: The data to be evaluated under the dimension of the socioeconomic background information includes income data, occupation information, educational background information, and residential area information; scoring each data to be evaluated under the dimension of the socioeconomic background information according to the preset scoring rules to obtain a score corresponding to each data to be evaluated under the dimension of the socioeconomic background information includes: Determine a first preset score corresponding to the income range within which the income data falls as a first score; Determine the second preset score corresponding to the occupation information as the second score; Determine the third preset score corresponding to the educational background information as the third score; A fourth preset score corresponding to the residential area information is determined as the fourth score.

5. The method for determining credit risk information according to claim 1, characterized in that: The generating of the credit risk information corresponding to the applicant user according to the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type includes: Inputting the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type into the large language model to obtain the credit risk information corresponding to the applicant user; The credit risk information includes at least one of credit risk level, credit risk type, risk factors, and risk enhancement suggestions.

6. The method for determining credit risk information according to claim 1, characterized in that: The method further comprises: If the credit risk level corresponding to the applicant user is higher than the historical credit risk level corresponding to the applicant user, or the number of target credit risk types is greater than 1, a risk warning is issued based on the credit risk information corresponding to the applicant user.

7. The method for determining credit risk information according to any one of claims 1 to 6, characterized in that: The method further comprises: Obtaining assessment sample data under multiple credit assessment dimensions and actual credit risk levels corresponding to the assessment sample data; The credit risk assessment model is trained by taking the assessment sample data as samples and the actual credit risk level corresponding to the assessment sample data as labels.

8. The method for determining the credit risk level according to claim 6, characterized in that: The method further comprises: The data to be evaluated is used as target sample data, and the actual credit risk level corresponding to the data to be evaluated is used as a label corresponding to the target sample data and stored in an update data set; If the number of target sample data in the updated data set is greater than the preset number, or the non-updated time length of the credit risk assessment model is greater than the preset update time length, the credit risk assessment model is updated according to the target sample data in the updated data set and the corresponding labels.

9. A system for determining credit risk information, characterized in that: The system comprises: The acquisition module is used to obtain the data to be evaluated under multiple credit evaluation dimensions of the applicant within the preset evaluation period, as well as the historical evaluation data corresponding to each credit risk type; An input module, used to input the data to be evaluated into a credit risk evaluation model to obtain the credit risk level corresponding to the applicant; A determination module, used to determine the target credit risk type corresponding to the applicant user according to the similarity between the data to be evaluated and the historical evaluation data corresponding to each credit risk type; A generation module is used to generate credit risk information corresponding to the applicant user according to the credit risk level corresponding to the applicant user, the target credit risk type, and the similarity between the data to be evaluated and the historical evaluation data corresponding to the target credit risk type.

10. An electronic device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the storage medium communicate via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for determining credit risk information as described in any one of claims 1 to 8.

Images