Management Measures for Unified Credit Granting to Multiple Persons in the Field of Credit Risk Control

Abstract

The present invention provides a management method for unified credit granting to multiple people in the field of credit risk control, which belongs to the field of financial management technology. Specifically, the method comprises: determining associated risk users among information-associated users based on credit expenditure data of information-associated users and image recognition results in the credit expenditure process, obtaining the number of associated risk users, and combining the association of credit application information between information-associated users of different associated risk users to determine that the aggregation risk coefficient of the credit user does not meet the requirements, using the target data source to determine the potential associated users of the credit user, taking the potential associated users, information-associated users and credit users as target user groups, and determining the credit management strategy of the target user group based on the analysis results of the credit expenditure data of different users in the target user group, thereby achieving effective control of the credit risk of aggregated fraudulent behavior.

Description

Technical Field

[0001] The present invention belongs to the field of financial management technology, and in particular relates to a management method for unified credit granting to multiple people in the field of credit risk control. Background Art

[0002] In their daily operations, credit institutions often find that people with related relationships, such as couples or fathers and sons, apply for credit in a dispersed manner. Existing technical solutions often dynamically monitor the credit risk of an independent individual in the related group.

[0003] However, people with related relationships may have characteristic behaviors that are clustered together. Once a default occurs, concentrated and clustered defaults may occur. This makes how to achieve unified credit management for multiple people a technical problem that needs to be solved urgently.

[0004] In order to solve the above technical problems, this application provides a management method for unified credit granting to multiple people in the field of credit risk control. Summary of the Invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] Specifically, this application provides a management method for multi-person unified credit in the field of credit risk control, specifically including:

[0007] S1 determines information-associated users of the credit user based on the credit application information of the credit user, and determines the association of image recognition results between different information-associated users during the credit disbursement process. If the association does not meet the requirements, proceed to the next step;

[0008] S2: determining associated risk users among the information-associated users based on the credit expenditure data of the information-associated users and the image recognition results during the credit expenditure process;

[0009] S3 obtains the number of associated risk users, and combines the information of different associated risk users with the correlation of credit application information between associated users. If it is determined that the aggregate risk coefficient of the credit user does not meet the requirements, the target data source is used to determine the potential associated users of the credit user.

[0010] S4 takes the potential associated users, information associated users and the credit granted users as target user groups, and determines the credit management and control strategy for the target user groups based on the analysis results of the credit expenditure data of different users in the target user groups.

[0011] The beneficial effects of the present invention are:

[0012] Based on the credit expenditure data of information-associated users and the image recognition results during the credit expenditure process, the associated risk users among the information-associated users are determined, thereby realizing the screening of associated risk users of information-associated users who have credit expenditure data of multiple merchants under the same image background, ensuring the accuracy of the screening results of associated risk users with group fraud risks, and laying the foundation for evaluating the aggregated risk based on the similarity of the credit information of information-associated users of associated risk users.

[0013] Based on the analysis results of the credit expenditure data of different users in the target user group, the credit management strategy of the target user group is determined, and unified credit risk control management is achieved for the target user group with a related relationship, avoiding the single credit risk control management of a certain user, and preventing the emergence of technical problems such as excessive credit expenditure risks in the field of clustered fraud risks, thereby ensuring the safety and reliability of credit expenditure behavior.

[0014] A further technical solution is that the information-associated users of the credit user are other credit users who have the same information items of credit application information as the credit user.

[0015] A further technical solution is that the association of image recognition results between the information-associated users during the credit application process includes the coexistence of data of face recognition images of different information-associated users during the credit application process and the similarity of image backgrounds.

[0016] A further technical solution is to determine that the association situation does not meet the requirements, specifically including:

[0017] Based on the association of image recognition results between the information-associated users during the credit application process, determining whether different information-associated users have images of other information-associated users in the face recognition images of the credit application process, or whether they have information-associated users with the same image background;

[0018] Information-associated users who are simultaneously present in the same face recognition image are referred to as image-associated users, and information-associated users who are present in the same image background are referred to as background-associated users;

[0019] The image correlation coefficient between the information-associated users is determined based on the average of the proportion of the image-associated users in the information-associated users and the proportion of the background-associated users in the information-associated users, and whether the correlation situation meets the requirements is determined based on the image correlation coefficient.

[0020] A further technical solution is that when the image correlation coefficient is greater than a preset correlation coefficient threshold, it is determined that the correlation condition does not meet the requirements.

[0021] A further technical solution is that when the association situation meets the requirements, there is no need to treat the credit user and the information-associated user as a whole for information management and control.

[0022] A further technical solution is that the method for determining the credit management and control strategy for the target user group is:

[0023] Setting the same exposure limit for the credit user and the information-linked user, and using facial recognition images during the credit disbursement process to determine the association between different users;

[0024] A credit management and control strategy for the target user group is determined based on the association relationship.

[0025] A further technical solution is to determine the credit management and control strategy for the target user group based on the association relationship, specifically including:

[0026] When the proportion of users in the target user group who have appeared in the same face recognition image is greater than the proportion of the preset group, the payment for the target user group will be suspended;

[0027] When the proportion of users in the target user group who have appeared in the same facial recognition image is no greater than the proportion of the preset group, only the exposure limit will be used to carry out credit management and control of users in the target user group.

[0028] A further technical solution is to use exposure limits to conduct credit management and control of users in the target user group, specifically including:

[0029] When the sum of the spending amounts of users in the target user group is greater than the exposure amount, spending for the target user group is suspended.

[0030] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0031] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other features and advantages of the present invention will become more apparent by describing in detail example embodiments thereof with reference to the accompanying drawings;

[0033] Figure 1 It is a flow chart of a management method for unified credit granting by multiple people in the field of credit risk control;

[0034] Figure 2 It is a flow chart for judging whether the association situation does not meet the requirements;

[0035] Figure 3 is a flowchart of a method for determining associated risk users among information associated users;

[0036] Figure 4 It is a flow chart for determining that the aggregate risk coefficient of the credit user does not meet the requirements. DETAILED DESCRIPTION

[0037] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0038] In this application, the relationship between the credit user and other credit users during the credit expenditure process is utilized to uniformly manage the credit risk of the credit users with related relationships, thereby reducing the credit risk of users with clustered risks.

[0039] like Figure 1 As shown, this application provides a management method for multi-person unified credit in the field of credit risk control, specifically including:

[0040] S1 determines information-associated users of the credit user based on the credit application information of the credit user, and determines the association of image recognition results between different information-associated users during the credit disbursement process. If the association does not meet the requirements, proceed to the next step;

[0041] Specifically, determine whether there are images of other information-associated users and information-associated users with the same image background in the face recognition images of different information-associated users in the credit expenditure process, and regard the information-associated users who exist in the same face recognition image at the same time as each other as image-associated users, and regard the information-associated users with the same image background as background-associated users. Determine the image correlation coefficient between the information-associated users based on the average value of the proportion of image-associated users in the information-associated users and the proportion of background-associated users in the information-associated users. When the image correlation coefficient is greater than 0.43, it is determined that the correlation situation does not meet the requirements.

[0042] S2: determining associated risk users among the information-associated users based on the credit expenditure data of the information-associated users and the image recognition results during the credit expenditure process;

[0043] An image background with multiple merchants having the same number of associated expenditures under the same image background is regarded as a suspected risk image background. When the number of credit expenditures of the information-associated user under the suspected risk image background is greater than the preset expenditure threshold, the information-associated user is determined to be an associated risk user.

[0044] S3 obtains the number of associated risk users, and combines the information of different associated risk users with the correlation of credit application information between associated users. If it is determined that the aggregate risk coefficient of the credit user does not meet the requirements, the target data source is used to determine the potential associated users of the credit user.

[0045] Based on the correlation between the credit application information of the information-associated users of different associated risk users, the number of identical information items in the credit application information between the information-associated users of different associated risk users and the information-associated users of other associated risk users is determined; based on the proportion of the number of identical information items, similar associated users among the information-associated users of other associated risk users are determined; based on the number of similar associated users of different information-associated users of each associated risk user, the total number of similar associated users of each associated risk user is determined; when there are associated risk users whose total number of similar associated users is greater than the preset number of similar associated users, it is determined that the aggregation risk coefficient of the credit user does not meet the requirements.

[0046] S4 takes the potential associated users, information associated users and the credit granted users as target user groups, and determines the credit management and control strategy for the target user groups based on the analysis results of the credit expenditure data of different users in the target user groups.

[0047] Set the same exposure limit for credit users and information-linked users, and use facial recognition images during the credit disbursement process to determine the association between different users. When the proportion of users in the target user group who have appeared in the same facial recognition image exceeds the proportion of the preset group, disbursement for the target user group will be suspended;

[0048] When the proportion of users in the target user group who have appeared in the same facial recognition image is no greater than the proportion of the preset group, only the exposure limit will be used to carry out credit management and control of users in the target user group.

[0049] Furthermore, the information associated users of the credit user are other credit users who have the same information items of credit application information as the credit user.

[0050] Specifically, the association of image recognition results between the information-associated users during the credit application process includes the coexistence of data of face recognition images of different information-associated users during the credit application process and the similarity of image backgrounds.

[0051] Specifically, such as Figure 2 As shown, it is determined that the association situation does not meet the requirements, specifically including:

[0052] Based on the association of image recognition results between the information-associated users during the credit application process, determining whether different information-associated users have images of other information-associated users in the face recognition images of the credit application process, or whether they have information-associated users with the same image background;

[0053] Information-associated users who are simultaneously present in the same face recognition image are referred to as image-associated users, and information-associated users who are present in the same image background are referred to as background-associated users;

[0054] The image correlation coefficient between the information-associated users is determined based on the average of the proportion of the image-associated users in the information-associated users and the proportion of the background-associated users in the information-associated users, and whether the correlation situation meets the requirements is determined based on the image correlation coefficient.

[0055] It should be noted that, when the image correlation coefficient is greater than a preset correlation coefficient threshold, it is determined that the correlation condition does not meet the requirements.

[0056] It is understandable that when the association situation meets the requirements, there is no need to treat the credit user and the information-associated user as a whole for information management and control.

[0057] In another possible embodiment, determining that the association condition does not meet the requirement specifically includes:

[0058] Determining whether images of other information-associated users exist in face recognition images of different information-associated users during the credit application process based on associations between image recognition results of the information-associated users during the credit application process;

[0059] Information-associated users who are simultaneously present in the same face recognition image are regarded as image-associated users, and information association coefficients of different information-associated users are determined based on the proportion of the number of image-associated users of different information-associated users in the number of the information-associated users;

[0060] An image correlation coefficient between information-related users is determined according to an average value of information correlation coefficients of different information-related users, and whether the correlation condition meets the requirement is determined based on the image correlation coefficient.

[0061] In another possible embodiment, determining that the association condition does not meet the requirement specifically includes:

[0062] S11 determines, based on the association of image recognition results between the information-associated users during the credit application process, whether images of other information-associated users and information-associated users with the same image background exist in facial recognition images of different information-associated users during the credit application process, and regards the information-associated users that are simultaneously present in the same facial recognition image as image-associated users. Information association coefficients of different information-associated users are determined based on the proportion of the number of image-associated users of different information-associated users to the number of the information-associated users.

[0063] S12: information-associated users with the same image background are regarded as background-associated users, and background-associated coefficients of different information-associated users are determined based on the ratio of the number of background-associated users of different information-associated users among the information-associated users, and the ratio of the number of background-associated users with the same image backgrounds among the information-associated users;

[0064] S13 determines the image correlation coefficient between the information-related users according to the information correlation coefficients and background correlation coefficients of different information-related users, and determines whether the correlation condition meets the requirements based on the image correlation coefficient.

[0065] Furthermore, the image association coefficient is determined based on the sum of the products of the information association coefficients of different information-associated users and the background association coefficients.

[0066] Optionally, step S11 includes the following:

[0067] S111 determines, based on the association of image recognition results between the information-associated users during the credit disbursement process, that if no images of other information-associated users exist in the face recognition images of different information-associated users during the credit disbursement process, and no information-associated users with the same image background, then the association is determined to meet the requirements. If images of other information-associated users exist or information-associated users with the same image background exist, then the process proceeds to step S112.

[0068] S112: Information-associated users who are simultaneously present in the same face recognition image are regarded as image-associated users. If the proportion of the image-associated users in the information-associated users does not meet the requirement, it is determined that the association does not meet the requirement. If the proportion of the image-associated users in the information-associated users meets the requirement, the process proceeds to step S113.

[0069] S113 determines the information correlation coefficient of different information-related users based on the proportion of the number of image-related users of different information-related users in the number of the information-related users. If there is an information-related user whose information correlation coefficient is greater than a preset correlation coefficient threshold, the process proceeds to step S114. If there is no information-related user whose information correlation coefficient is greater than the preset correlation coefficient threshold, the process proceeds to step S12.

[0070] S114: When the number of information-associated users whose information association coefficient is greater than the preset association coefficient threshold does not meet the requirement, it is determined that the association situation does not meet the requirement; when the number of information-associated users whose information association coefficient is greater than the preset association coefficient threshold meets the requirement, the process proceeds to step S12.

[0071] Optionally, step S12 includes the following:

[0072] S121: Information-associated users with the same image background are considered as background-associated users. If the proportion of the background-associated users in the information-associated users does not meet the requirement, it is determined that the association does not meet the requirement. If the proportion of the background-associated users in the information-associated users does meet the requirement, the process proceeds to step S122.

[0073] S122 determines the number of background-associated users under different identical backgrounds. When the number of background-associated users is greater than a preset background-associated user number threshold and the number of identical backgrounds is greater than the preset number of backgrounds, it is determined that the association condition does not meet the requirement. When the number of background-associated users is greater than the preset background-associated user number threshold and the number of identical backgrounds is not greater than the preset number of backgrounds, the process proceeds to step S123.

[0074] S123 determines background correlation coefficients of different information-associated users based on the proportion of background-associated users of different information-associated users among the information-associated users, and the proportion of background-associated users under different identical image backgrounds among the information-associated users, and determines a comprehensive correlation coefficient by multiplying the background correlation coefficient by the information correlation coefficient. If there is an information-associated user whose comprehensive correlation coefficient is greater than a preset correlation coefficient threshold, the process proceeds to step S124; if there is no information-associated user whose comprehensive correlation coefficient is greater than the preset correlation coefficient threshold, the process proceeds to step S13;

[0075] S114: When the number of information-associated users whose comprehensive correlation coefficient is greater than the preset correlation coefficient threshold does not meet the requirement, it is determined that the association situation does not meet the requirement; when the number of information-associated users whose comprehensive correlation coefficient is greater than the preset correlation coefficient threshold meets the requirement, the process proceeds to step S13.

[0076] Furthermore, the credit expenditure data includes the number of credit expenditures and merchants corresponding to different credit expenditure times.

[0077] Specifically, such as Figure 3 As shown, the method for determining the associated risk users among the information associated users is:

[0078] Determining the number of credit expenditures by the information-associated user at different merchants using the credit expenditure data of the information-associated user, and determining the number of associated expenditures between the information-associated user and the credit-granting user based on the merchants corresponding to different credit expenditures;

[0079] Determine the number of associated expenditures under different image backgrounds and the merchants corresponding to the different number of associated expenditures based on image recognition results of different associated expenditures during the credit expenditure process;

[0080] An image background with multiple merchants having the same number of associated expenditures under the same image background is used as a suspected risk image background. Based on the number of credit expenditures of the information-associated user under the suspected risk image background, it is determined whether the information-associated user is an associated risk user.

[0081] Furthermore, when the number of credit withdrawals by the information-associated user in the context of the suspected risk image is greater than a preset withdrawal number threshold, the information-associated user is determined to be an associated risk user.

[0082] Optionally, a method for determining risk-associated users among the information-associated users is:

[0083] Associating the information with the user's credit expenditure data to determine the number of credit expenditures made by the information-associated user at different merchants, and determining the number of credit expenditures under different image backgrounds and the merchants corresponding to the different credit expenditures based on image recognition results of the different credit expenditures during the credit expenditure process;

[0084] An image background with the number of credit withdrawals on the same image background as the credit granting user is used as an associated image background;

[0085] Whether the information-associated user is an associated risk user is determined based on the deviation of merchants corresponding to the credit expenditure times of the information-associated user and the credit-granting user under different associated image backgrounds.

[0086] Furthermore, according to the deviation of the merchants corresponding to the credit withdrawal times of the information-associated user and the credit-granting user under different associated image backgrounds, determining whether the information-associated user is an associated risk user specifically includes:

[0087] The associated image background of the merchant with a deviation corresponding to the credit consumption times of the information-associated user and the credit-granting user is used as the deviation image background;

[0088] When the number of the deviation image backgrounds is greater than a preset image background number threshold, the information-associated user is determined to be an associated risk user.

[0089] In another possible embodiment, a method for determining risk-associated users among the information-associated users is as follows:

[0090] S21 uses the credit expenditure data of the information-associated user to determine the number of credit expenditures by the information-associated user at different merchants, and determines the number of credit expenditures under different image backgrounds and the merchants corresponding to the different credit expenditures based on image recognition results of the different credit expenditures during the credit expenditure process;

[0091] S22: an image background with the number of credit withdrawals of the credit user in the same image background as the credit user is used as an associated image background; and according to the deviation of the merchants corresponding to the number of credit withdrawals of the information-associated user and the credit user under different associated image backgrounds, an associated image background with a deviation in the number of credit withdrawals of the information-associated user and the credit user is used as a deviation image background;

[0092] S23 obtains the number of credit expenditures of the information-associated user under different deviation image backgrounds, the deviation between the merchant corresponding to the different credit expenditure numbers and the credit user under the deviation image background, determines the credit expenditure abnormality coefficient under different deviation image backgrounds, determines the associated risk coefficient of the information-associated user with the credit expenditure abnormality coefficient under different deviation image backgrounds, and uses the associated risk coefficient to determine whether the information-associated user is an associated risk user.

[0093] Furthermore, when the associated risk coefficient is greater than a preset associated risk coefficient threshold, the information associated user is determined to be an associated risk user.

[0094] Optionally, step S22 includes the following:

[0095] S221: If there is no image background with the number of credit disbursements in the same image background as the credit-granting user, it is determined that the information-associated user is not an associated risk user. If there is an image background with the number of credit disbursements in the same image background as the credit-granting user, the process proceeds to step S222;

[0096] S222 uses an image background with the number of credit withdrawals as the associated image background, and according to the deviation of the merchants corresponding to the credit withdrawals of the information-associated user and the credit-granting user under different associated image backgrounds, if there is no associated image background with a deviation of the merchants corresponding to the credit withdrawals of the information-associated user and the credit-granting user, it is determined that the information-associated user is not an associated risk user; if there is an associated image background with a deviation of the merchants corresponding to the credit withdrawals of the information-associated user and the credit-granting user, the process proceeds to step S223;

[0097] S223: Determine the associated image backgrounds of merchants with deviations between the credit withdrawal times of the information-associated user and the credit-granting user as deviation image backgrounds. If the number of deviation image backgrounds does not meet the requirement, determine that the information-associated user is an associated risk user. If the number of deviation image backgrounds meets the requirement, proceed to step S224.

[0098] S224 obtains the sum of the number of credit expenditures of the information-associated user in the background of the deviation image. When the sum of the number of credit expenditures of the information-associated user in the background of the deviation image does not meet the requirements, it is determined that the information-associated user does not belong to an associated risk user. When the sum of the number of credit expenditures of the information-associated user in the background of the deviation image meets the requirements, proceed to step S23.

[0099] Optionally, step S23 includes the following:

[0100] Step S231 obtains the number of credit withdrawals by the information-associated user under different deviation image backgrounds, and the deviations between the merchants corresponding to the different credit withdrawals and the credit-granting user under the deviation image backgrounds, and determines the credit withdrawal anomaly coefficients under the different deviation image backgrounds. If there is a deviation image background whose credit withdrawal anomaly coefficient does not meet the requirements, it is determined that the information-associated user is an associated risk user. If there is no deviation image background whose credit withdrawal anomaly coefficient does not meet the requirements, the process proceeds to step S232.

[0101] S232: When there is a deviation image background with a credit expenditure abnormality coefficient within the preset expenditure abnormality coefficient range, the process proceeds to step S233; when there is no deviation image background with a credit expenditure abnormality coefficient within the preset expenditure abnormality coefficient range, the process proceeds to step S224;

[0102] S233: When the number of deviation image backgrounds of the credit expenditure anomaly coefficient within the preset expenditure anomaly coefficient range does not meet the requirement, it is determined that the information-associated user is an associated risk user. When the number of deviation image backgrounds of the credit expenditure anomaly coefficient within the preset expenditure anomaly coefficient range meets the requirement, the process proceeds to step S234;

[0103] S234 determines the associated risk coefficient of the information-associated user based on the credit expenditure anomaly coefficient under different deviation image backgrounds, and uses the associated risk coefficient to determine whether the information-associated user is an associated risk user.

[0104] Furthermore, the association of the credit application information includes the number of identical information items in the credit application information.

[0105] Specifically, such as Figure 4 As shown, it is determined that the aggregate risk coefficient of the credit user does not meet the requirements, specifically including:

[0106] Determine the number of identical information items in the credit application information between the information-associated users of different associated risk users and the information-associated users of other associated risk users based on the association status of the credit application information between the information-associated users of different associated risk users;

[0107] Determining similar associated users among other information-associated users of the associated risk user based on the proportion of the number of the same information items;

[0108] Based on the number of similar associated users of different information associated users of each associated risk user, the total number of similar associated users of each associated risk user is determined, and the total number of similar associated users is used to determine whether the aggregate risk coefficient of the credit user meets the requirement.

[0109] Furthermore, the similar associated users among the information associated users are information associated users whose number of identical information items accounts for a larger proportion than a preset identical information item number threshold.

[0110] Specifically, when there are associated risk users whose total number of similar associated users is greater than a preset number of similar associated users, it is determined that the aggregate risk coefficient of the credit user does not meet the requirement.

[0111] It is understandable that when the aggregate risk coefficient of the credit user meets the requirements, it is only necessary to treat the credit user and the information-associated user as a whole for information management and control.

[0112] It should be noted that when the credit user and the information-associated user are treated as a whole for information management and control, the same exposure limit is set for the credit user and the information-associated user, and the relationship between the credit user and the information-associated user is determined using facial recognition images during the credit expenditure process.

[0113] Specifically, when the credit user and the information-associated user are treated as a whole for information management and control, the association relationship is determined using the facial recognition images of the credit user and the information-associated user during the credit application process.

[0114] Optionally, determining that the aggregate risk coefficient of the credit user does not meet the requirement specifically includes:

[0115] S31 determines the number of identical information items in the credit application information between the information-associated users of different associated risk users and the information-associated users of other associated risk users based on the association status of the credit application information between the information-associated users of different associated risk users;

[0116] S32: determining the number of similar associated users of the information associated users of the associated risk user among the information associated users of other associated risk users based on the number ratio of the identical information items, and determining the information association coefficient between the associated risk user and other associated risk users based on the number ratio of identical information items of different similar associated users;

[0117] S33 determines an association coefficient evaluation value based on the information association coefficients between different associated risk users, and uses the association coefficient evaluation value to determine whether the aggregate risk coefficient of the credit user meets the requirements.

[0118] Furthermore, when the correlation coefficient evaluation value is greater than a preset evaluation value threshold, it is determined that the aggregation risk coefficient of the credit user does not meet the requirements.

[0119] Optionally, the above step S31 includes the following contents:

[0120] S311 determines the number of identical information items in the credit application information between the information-associated users of different associated risk users and the information-associated users of other associated risk users based on the association of credit application information between the information-associated users of different associated risk users. When the proportion of identical information items in the credit application information between the different information-associated users is less than a preset information item proportion threshold, it is determined that the aggregation risk coefficient of the credit users meets the requirement. When there are information-associated users whose proportion of identical information items in the credit application information is not less than the preset information item proportion threshold, the process proceeds to step S312.

[0121] S312 associates users whose number of identical information items in the credit application information is not less than a preset information item number ratio threshold as similar users. If the number of similar users is greater than the preset similar user number threshold, it is determined that the aggregation risk coefficient of the credit user does not meet the requirement. If the number of similar users is not greater than the preset similar user number threshold, the process proceeds to step S313.

[0122] S313 obtains the number of associated risk users with similar users to the information-associated user. When the number of associated risk users with similar users to the information-associated user is less than the preset threshold value of the number of associated risk users, it is determined that the aggregation risk coefficient of the credit user meets the requirements. When the number of associated risk users with similar users to the information-associated user is not less than the preset threshold value of the number of associated risk users, proceed to step S32.

[0123] Optionally, the above step S32 includes the following contents:

[0124] S321: Determine similar associated users among the information associated users of other associated risk users based on the proportion of the number of identical information items; determine the total number of similar associated users of each associated risk user based on the number of similar associated users of different information associated users of each associated risk user; if there are associated risk users whose total number of similar associated users does not meet the requirement, determine that the aggregate risk coefficient of the credit user does not meet the requirement; if there are no associated risk users whose total number of similar associated users does not meet the requirement, proceed to step S322;

[0125] S322: When the total number of similar associated users of different associated risk users is less than the preset similar associated user number threshold, it is determined that the aggregate risk coefficient of the credit user meets the requirement; when the total number of similar associated users of different associated risk users is not less than the similar associated user number threshold, the process proceeds to step S323;

[0126] S323 determines the number of similar associated users of the information associated users of the associated risk user among the information associated users of other associated risk users, and determines the information correlation coefficient between the associated risk user and other associated risk users based on the proportion of the number of identical information items of different similar associated users. When the average value of the information correlation coefficients between different associated risk users does not meet the requirement, it is determined that the aggregate risk coefficient of the credit user does not meet the requirement. When the average value of the information correlation coefficients between different associated risk users meets the requirement, the process proceeds to step S324.

[0127] S324 regards the associated risk users whose information correlation coefficient is greater than the preset information correlation coefficient threshold as strongly associated users. When the number of the strongly associated users does not meet the requirement, it is determined that the aggregation risk coefficient of the credit user does not meet the requirement. When the number of the strongly associated users meets the requirement, it proceeds to step S33.

[0128] Furthermore, the potential associated user is a user who is associated with the credit application information of the credit user, and is specifically determined based on communication records, social software interaction data, and bank card transfer data.

[0129] Specifically, the method for determining the credit management and control strategy for the target user group is:

[0130] Setting the same exposure limit for the credit user and the information-linked user, and using facial recognition images during the credit disbursement process to determine the association between different users;

[0131] A credit management and control strategy for the target user group is determined based on the association relationship.

[0132] Furthermore, a credit control strategy for the target user group is determined based on the association relationship, specifically including:

[0133] When the proportion of users in the target user group who have appeared in the same face recognition image is greater than the proportion of the preset group, the payment for the target user group will be suspended;

[0134] When the proportion of users in the target user group who have appeared in the same facial recognition image is no greater than the proportion of the preset group, only the exposure limit will be used to carry out credit management and control of users in the target user group.

[0135] It should be noted that the credit management and control of users in the target user group using exposure limits specifically includes:

[0136] When the sum of the spending amounts of users in the target user group is greater than the exposure amount, spending for the target user group is suspended.

[0137] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0138] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0139] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. A management method for unified credit granting to multiple people in the field of credit risk control, characterized by: Specifically include: Determine information-associated users of the credit user based on the credit application information of the credit user, determine the association of image recognition results between different information-associated users during the credit disbursement process, and proceed to the next step if the association does not meet the requirements; Determining associated risk users among the information-associated users based on the credit expenditure data of the information-associated users and image recognition results during the credit expenditure process; Obtaining the number of associated risk users, and combining the information of different associated risk users with the correlation of credit application information between associated users, and determining that the aggregated risk coefficient of the credit user does not meet the requirements, using the target data source to determine the potential associated users of the credit user; Taking the potential associated users, information associated users and credit granted users as target user groups, and determining the credit management and control strategy for the target user groups based on the analysis results of the credit expenditure data of different users in the target user groups; It is determined that the association does not meet the requirements, specifically including: Based on the association of image recognition results between the information-associated users during the credit application process, determining whether different information-associated users have images of other information-associated users in the face recognition images of the credit application process, or whether they have information-associated users with the same image background; Information-associated users who are simultaneously present in the same face recognition image are referred to as image-associated users, and information-associated users who are present in the same image background are referred to as background-associated users; Determining an image correlation coefficient between the information-associated users based on an average of a proportion of the image-associated users among the information-associated users and a proportion of the background-associated users among the information-associated users, and determining whether the correlation condition meets the requirements based on the image correlation coefficient; The method for determining the associated risk users among the information associated users is: Determining the number of credit expenditures by the information-associated user at different merchants using the credit expenditure data of the information-associated user, and determining the number of associated expenditures between the information-associated user and the credit-granting user based on the merchants corresponding to different credit expenditures; Determine the number of associated expenditures under different image backgrounds and the merchants corresponding to the different number of associated expenditures based on image recognition results of different associated expenditures during the credit expenditure process; An image background with multiple merchants' associated payment times under the same image background is used as a suspected risk image background, and based on the number of credit payments made by the information-associated user under the suspected risk image background, whether the information-associated user is an associated risk user is determined; Setting the same exposure limit for the credit user and the information-linked user, and using facial recognition images during the credit disbursement process to determine the association between different users; When the proportion of users in the target user group who have appeared in the same face recognition image is greater than the proportion of the preset group, the payment for the target user group will be suspended; When the proportion of users in the target user group who have appeared in the same facial recognition image is no greater than the proportion of the preset group, only the exposure limit will be used to carry out credit management and control of users in the target user group.

2. The management method for multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: The information associated users of the credit user are other credit users who have the same information items of credit application information as the credit user.

3. The management method for multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: The association of image recognition results between the information-associated users during the credit application process includes the coexistence of data of face recognition images of different information-associated users during the credit application process and the similarity of image backgrounds.

4. The management method for multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: When the image correlation coefficient is greater than a preset correlation coefficient threshold, it is determined that the correlation condition does not meet the requirement.

5. The management method for multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: When the association situation meets the requirements, there is no need to treat the credit user and the information-associated user as a whole for information management and control.

6. The management method for multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: The credit expenditure data includes the number of credit expenditures and merchants corresponding to different credit expenditure times.

7. The management method for multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: The association of the credit application information includes the number of identical information items in the credit application information.

8. The method for managing multi-person unified credit in the field of credit risk control as claimed in claim 1, characterized in that: The potential associated user is a user who is associated with the credit application information of the credit user, and is specifically determined based on communication records, social software interaction data and bank card transfer data.

Images