Risk control method and system for calculating core contacts based on graph network

Abstract

The invention provides a risk control method and system for calculating a core contact based on a graph network, and belongs to the technical field of data processing, and the method specifically comprises the steps: determining whether the change condition of the graph network does not meet the requirement based on a construction processing result or not based on the contact data of credit application users of different graph networks and the change condition; according to the method and the device, the update processing schemes of different graph networks are determined, the credit risk control management strategy of the new input user is determined on the basis of the update processing schemes and the credit granting application information of the new input user, and the efficiency of identification processing of the aggregative fraud risk is improved.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a risk control method and system based on graph network calculation of core contacts. Background Technology

[0002] In the field of credit risk control, clustered fraud occurs frequently. Existing technical solutions often identify and process clustered fraud risks by analyzing the correlation of credit application information between different applicants or by using image recognition data. A similar technical solution is presented in invention patent application CN202311000939.3, "A Credit Risk Control Method and System." However, the above-mentioned technical solution has the following technical problems: Users at risk of clustered fraud often share certain connections in their contact information. Therefore, constructing a graph network using these contact details can improve the efficiency and targeting of identifying and handling clustered fraud risks. Consequently, determining the risk control strategy for new applicants based on existing graph network update schemes and the similarity between credit application information of existing credit applicants and new applicants in the graph network has become an urgent technical problem to be solved.

[0003] Therefore, there is an urgent need for a risk control method and system based on graph network computing of core contacts. Summary of the Invention

[0004] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a risk control method based on graph network computing of core contacts, which includes: S1 uses the construction results of the graph network of the core contact person to determine the contact data of the credit application user in different graph networks. Based on the contact data, it determines the construction processing strategy of the graph network of the contact person of the new application user. Based on the construction processing strategy, it performs the construction processing of the graph network of the core contact person. Based on the construction processing results, if it is determined that the changes in the graph network do not meet the requirements, it proceeds to the next step. S2 determines different graph network update processing schemes based on the contact data and changes of credit application users in different graph networks, and determines the credit risk control management strategy for new users based on the update processing schemes and the credit application information of new users.

[0005] The beneficial effects of this invention are as follows: Based on the contact data of credit applicants in different graph networks, a strategy for constructing and processing the graph network of contacts for new applicants is determined. This achieves the goal of constructing and processing the graph network of contacts for new applicants from the perspective of the completeness of the existing graph network of credit applicants, thereby avoiding the technical problem of excessive data processing pressure on the server caused by frequent graph network construction. At the same time, timely graph network construction and processing improves the reliability of identifying and processing clustered fraud risks.

[0006] Based on the updated processing scheme and the credit application information of newly added users, the credit risk control management strategy for newly added users is determined. This takes into account the correlation between the credit application information of newly added users and the credit application information of existing credit application users in the graph network, thereby identifying potential clustered fraud risks. Furthermore, by combining the updated processing scheme of the graph network of related credit application users, the system can identify and process credit application users for clustered fraud risks among newly added users, thus improving the efficiency of clustered fraud risk identification and processing.

[0007] Furthermore, the method for determining the construction result of the graph network of the core contact is as follows: By collecting data on credit applicants and their contacts, a heterogeneous graph network is constructed with credit applicants and their contacts as nodes and relationships as edges. A graph neural network model is used to embed nodes and aggregate the feature information of neighboring nodes to discover the center of influence of credit applicants in the network for each applicant node.

[0008] Furthermore, the contact data of the credit applicant includes the number of credit applicants in the graph network and the number of contacts of the credit applicant.

[0009] Furthermore, the method for determining the construction strategy of the graph network of the contacts of the newly added user is as follows: Based on the contact data, determine the composition of credit application users in the graph network among the existing credit application users; Based on the aforementioned configuration, identify the credit application users who have not undergone graph network construction processing; Based on the credit application user data that has not undergone graph network construction processing, determine the graph network construction processing strategy for the contacts of the newly applied user.

[0010] Specifically, the method for determining the credit risk control management strategy for newly added users is as follows: Based on the credit application information of the newly admitted user, determine the association between the credit application information of the newly admitted user and the credit application information of users in different graph networks; Based on the association of credit application information with credit application users in different graph networks, identify the associated application users in different graph networks and identify the graph networks where associated application users exist. Based on the graph network update processing scheme for users with related applications and the credit application user data, the credit risk control management strategy for the newly applied users is determined.

[0011] Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned risk control method for calculating core contacts based on graph networks when running the computer program.

[0012] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0013] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0014] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0015] Figure 1 This is a flowchart of a risk control method based on graph network computation of core contacts; Figure 2 This is a flowchart illustrating the method for determining the construction results of the graph network of core contacts; Figure 3 This is a flowchart illustrating the method for determining the processing strategy of constructing a graph network of contacts for newly received users. Figure 4 This is a flowchart illustrating the method for determining the update processing scheme of a graph network. Figure 5 This is a flowchart illustrating the method for determining the credit risk control management strategy for new applicants. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0017] In this application, based on the association between the credit application information of new users and credit application users in the graph network, and the update processing scheme of the graph network, the scope of identification and processing of clustered fraud risks of new users is determined, thereby improving the efficiency and reliability of identification and processing of clustered fraud risks.

[0018] Example 1 like Figure 1 As shown, this application provides a risk control method based on graph network computing of core contacts, specifically including: S1 uses the construction results of the graph network of the core contact person to determine the contact data of the credit application user in different graph networks. Based on the contact data, it determines the construction processing strategy of the graph network of the contact person of the new application user. Based on the construction processing strategy, it performs the construction processing of the graph network of the core contact person. Based on the construction processing results, if it is determined that the changes in the graph network do not meet the requirements, it proceeds to the next step. Specifically, such as Figure 2 As shown, the method for determining the construction result of the graph network of the core contact is as follows: By collecting data on credit applicants and their contacts, a heterogeneous graph network is constructed with credit applicants and their contacts as nodes and relationships as edges. A graph neural network model is used to embed nodes and aggregate the feature information of neighboring nodes to discover the center of influence of credit applicants in the network for each applicant node.

[0019] Furthermore, the contact data of the credit applicant includes the number of credit applicants in the graph network and the number of contacts of the credit applicant.

[0020] Specifically, such as Figure 3 As shown, the method for determining the construction strategy of the graph network of contacts for newly added users is as follows: Based on the contact data, determine the composition of credit application users in the graph network among the existing credit application users; Based on the aforementioned configuration, identify the credit application users who have not undergone graph network construction processing; Based on the credit application user data that has not undergone graph network construction processing, determine the graph network construction processing strategy for the contacts of the newly applied user.

[0021] It is understood that the credit application users who have not undergone graph network construction processing are credit application users who are not in the graph network.

[0022] It should be noted that the credit application users refer to all users who have made credit applications in the past.

[0023] Furthermore, based on the credit application user data that has not undergone graph network construction processing, the graph network construction processing strategy for the contacts of the newly applied user is determined, specifically including: Using the credit application user data that has not undergone graph network construction processing, determine the proportion of credit application users that have not undergone graph network construction processing among all credit application users, and use this proportion as the non-construction proportion; Based on the unbuilt proportion, a construction and processing strategy for the graph network of the contacts of the newly added user is determined.

[0024] It is understandable that, based on the aforementioned unbuilt proportion, the strategy for constructing the graph network of the contacts of the newly added user is determined, specifically including: When the unconstructed ratio is greater than a preset ratio threshold, such as 0.3, then when the newly submitted user or the contact person of the newly submitted user overlaps with the contact person of the credit application user, then the graph network construction process of the contact person of the newly submitted user is performed. When the unconstructed ratio is not greater than the preset ratio threshold, and the number of credit applicants whose contacts overlap with the contacts of the new applicants meets the requirements, then the construction of the graph network of the contacts of the new applicants will be carried out.

[0025] Specifically, when the number of credit application users who are the contacts of the new user or the contacts of the new user is not less than a preset threshold, such as not less than 3, then the graph network construction process of the contacts of the new user is carried out. In this way, when the graph network construction process is relatively complete, the technical problem of unstable credit risk control strategy caused by frequent graph network construction is avoided.

[0026] Optionally, the method for determining the construction strategy of the graph network of the contacts of the newly added user is as follows: Based on the contact data, determine the composition of existing credit application users in the graph network, and use the composition to determine the credit application users to be constructed in the graph network. Based on the credit application user data for graph network construction, the credit application users involved in different graph networks are identified. Based on the credit application users involved in different graph networks, determine the graph network construction and processing strategy for the contacts of the newly applied user.

[0027] It should be noted that when the number of graph networks does not meet the requirements, i.e. is less than the threshold, since the number of graph networks is small, if the new applicant or the contact of the new applicant overlaps with the contact of the credit application user, then the graph network construction process for the contact of the new applicant will be performed. Additionally, it can be understood that when the number of graph networks meets the requirements, the credit application users involved in different graph networks are determined. If the number of credit application users involved in different graph networks is less than the preset threshold for the number of application users, then when the new application user or the contact person of the new application user overlaps with the contact person of the credit application user, the graph network construction process of the contact person of the new application user is performed. In other cases, if the number of credit application users involved in different graph networks is not less than the preset threshold for the number of application users, and the number of credit application users whose contacts overlap with the contacts of the credit application users meets the requirements, then the graph network construction process for the contacts of the new application users will be carried out.

[0028] Specifically, determining whether changes to the graph network do not meet the requirements includes: Based on the construction and processing results, determine the changes in the number of users applying for credit in the graph network; Based on the changes in the number of credit application users in the graph network, the graph network in which the number of credit application users changes is determined; Based on the data on the changes in the number of credit applicants in the graph network, determine whether the changes in the graph network meet the requirements.

[0029] It is understandable that when the number of graph networks in which the number of credit application users changes exceeds a preset change threshold, the change in the graph network is determined to be unsatisfactory.

[0030] Additionally, it can be understood that when the number of graph networks in which the number of credit applicants changes is not greater than a preset change threshold, a change factor is determined based on the increase in the number of credit applicants in the graph networks in which the number of credit applicants changes, and the proportion of the number of credit applicants in the graph networks in which the number of credit applicants changes. When the combined change factor of graph networks in which the number of different credit applicants changes is greater than a preset change factor threshold, it is determined that the change in the graph network does not meet the requirements.

[0031] It is understood that the comprehensive variation factor is determined by the sum of the variation factors of the graph network that vary based on the number of different credit application users.

[0032] Optionally, determine if changes to the graph network do not meet the requirements, specifically including: Based on the construction and processing results, determine the changes in the number of users applying for credit in the graph network; Based on the changes in the number of credit application users in the graph network, the graph network in which the number of credit application users changes is determined; Based on the data on the change in the number of credit applicants in the graph network, the change factor of the graph network is determined, and based on the change factor of different graph networks, it is determined whether the change of the graph network meets the requirements.

[0033] It should be noted that, based on different variation factors of the graph network, determining whether the variation of the graph network meets the requirements specifically includes: Based on the variation factors of different graph networks, if the variation factors of different graph networks are all less than a preset variation factor threshold, for example, less than 0.05, then the variation of the graph network is determined to meet the requirements.

[0034] Furthermore, when the variation factors of different graph networks are not all less than a preset variation factor threshold, the graph network with a variation factor not less than the preset variation factor threshold is regarded as the user variation network. When the number of user variation networks does not meet the requirements, for example, when it is more than 10, it is determined that the variation of the graph network does not meet the requirements.

[0035] It should also be noted that when the number of user-modified networks meets the requirements, the modification status of the graph network is determined to meet the requirements.

[0036] S2 determines different graph network update processing schemes based on the contact data and changes of credit application users in different graph networks, and determines the credit risk control management strategy for new users based on the update processing schemes and the credit application information of new users.

[0037] Specifically, the method for determining the update processing scheme of the graph network is as follows: Based on the contact data of the credit application users in the graph network, the number of credit application users in the graph network is determined; Based on the changes in the credit application users of the graph network, the change factor of the graph network is determined, and the graph network with the preset update scheme is determined by using the change factor to perform the update processing scheme. The update processing scheme of the graph network is determined based on the graph network with the preset update scheme and the number of users applying for credit in the graph network.

[0038] Specifically, if the graph network data of the preset update scheme meets the requirements, for example, if the number of graph networks in the preset update scheme is greater than 20, then the update processing scheme of the graph network is determined to be another update scheme.

[0039] Furthermore, if the graph network data of the preset update scheme does not meet the requirements, then the update processing scheme of the graph network is determined based on the number of credit application users in the graph network.

[0040] It should be noted that the preset update scheme is to perform graph network update processing when the contact information of the credit application user or the contact person of the credit application user overlaps with that of the new applicant or the contact person of the new applicant. The other update scheme is to treat the new applicant as an overlapping new applicant when the contact information of the credit application user or the contact person of the credit application user overlaps with that of the new applicant or the contact person of the new applicant. If the number of overlapping new applicants is greater than the preset number of users, for example, more than two, then graph network update processing is performed.

[0041] Optionally, the method for determining the credit risk control management strategy for the newly applied user is as follows: Based on the credit application information of the newly admitted user, determine the association between the credit application information of the newly admitted user and the credit application information of users in different graph networks; Based on the association of credit application information with credit application users in different graph networks, identify the associated application users in different graph networks and identify the graph networks where associated application users exist. Based on the graph network update processing scheme for users with related applications and the credit application user data, the credit risk control management strategy for the newly applied users is determined.

[0042] If the number of graph networks with other update schemes in the graph network of the associated applicant users does not meet the requirements, for example, if it is not less than 2, then the credit risk control management strategy for the new applicant user needs to be further considered, excluding the credit applicant users in the graph network. By determining the similarity between the background information in the credit images of the associated applicant users among the credit applicant users excluding the graph network and the background information in the credit images of the new applicant user, it is determined whether the new applicant user has a risk of clustered fraud. In addition, it is also necessary to determine the similarity between the background information in the credit images of the credit applicant users in the graph network of the associated applicant users and the new applicant user, to determine whether the new applicant user has a risk of clustered fraud.

[0043] Furthermore, if the number of graph networks with other update schemes in the graph network of associated applicant users meets the requirement, then the number of credit applicant users in the graph network of associated applicant users is determined. If the total number of credit applicant users in the graph network of associated applicant users meets the requirement, for example, if the total number of credit applicant users in all graph networks of associated applicant users is less than 10, then the credit risk control management strategy for the new applicant is determined to only consider the similarity of background information between the credit applicant users in the graph network of associated applicant users and the credit image of the new applicant, to determine whether the new applicant has a risk of clustered fraud.

[0044] Furthermore, if the total number of credit applicants in the graph network with associated applicants does not meet the requirements, the credit risk control management strategy for the new applicant is determined to require further consideration of credit applicants outside the graph network. By determining the similarity between the background information in the credit images of associated applicants outside the graph network and the background information in the credit images of the new applicant, it is determined whether the new applicant has a risk of clustered fraud. In addition, it is also necessary to determine the similarity between the background information in the credit images of credit applicants in the graph network with associated applicants and the new applicant to determine whether the new applicant has a risk of clustered fraud.

[0045] Example 2 Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned risk control method for calculating core contacts based on graph networks when running the computer program.

[0046] Specifically, such as Figure 4 As shown, the method for determining the update processing scheme of the graph network is as follows: Based on the contact data of the credit application users in the graph network, the number of credit application users in the graph network is determined; Based on the changes in the credit application users of the graph network, determine the change factor of the graph network; Based on the different variation factors of the graph network and the number of users applying for credit, the update processing scheme of the graph network is determined.

[0047] It is understandable that when the average value of the variation factor of different graph networks is greater than the preset variation factor threshold, the variation of different graph networks is more serious. Therefore, the update processing scheme of all graph networks is determined to be the preset update scheme. Furthermore, when the average value of the variation factor of different graph networks is not greater than the preset variation factor threshold, the construction ratio is determined based on the number of credit application users in the graph network and the proportion of the total number of credit application users in different graph networks to the number of credit users. When the construction ratio is less than the preset construction ratio threshold, for example, less than 0.5, the construction is not comprehensive enough, so the update processing scheme of all graph networks is determined to be the preset update scheme. Additionally, it should be noted that when the construction ratio is not less than the preset construction ratio threshold, the graph network's variation factor is used as the basis. If the graph network's variation factor is greater than the preset variation factor threshold, the graph network's update processing scheme is determined to be the preset update scheme. Additionally, it can be understood that when the variation factor of the graph network is not greater than the preset variation factor threshold, if the graph network data of the preset update scheme meets the requirements, for example, if the number of graph networks in the preset update scheme is greater than 20, then the update processing scheme of the graph network is determined to be another update scheme.

[0048] Furthermore, if the graph network data of the preset update scheme does not meet the requirements, then the update processing scheme of the graph network is determined based on the number of credit application users in the graph network.

[0049] It is understandable that the determination of the graph network update processing scheme based on the number of credit request users in the graph network specifically includes: When the number of credit application users in the graph network does not meet the requirements, that is, when the number of credit application users is small, for example, less than 5, the update processing scheme of the graph network is determined to be the preset update scheme. When the number of credit request users in the graph network meets the requirements, the update processing scheme of the graph network is determined to be another update scheme.

[0050] Example 3 Specifically, such as Figure 5 As shown, the method for determining the credit risk control management strategy for newly added users is as follows: Based on the credit application information of the newly admitted user, determine the association between the credit application information of the newly admitted user and the credit application information of users in different graph networks; Based on the association of credit application information with credit application users in different graph networks, identify the associated application users in different graph networks; Based on the associated application user data in different graph networks and the graph network update processing scheme, the credit risk control management strategy for the newly applied users is determined.

[0051] Furthermore, the associated application user is a credit application user whose number of identical information items with the credit application information of the new application user meets the requirement. For example, a credit application user whose number of identical information items with the credit application information of the new application user is more than 3 is considered as an associated application user of the new application user.

[0052] Furthermore, based on the associated application user data in different graph networks and the graph network update processing scheme, the credit risk control management strategy for the newly applied users is determined, specifically including: Based on the associated application user data in different graph networks, identify the graph networks in which associated application users exist; It should be noted that if there is no graph network of related applicants, the credit risk control management strategy for the new applicant will need to further consider credit applicants other than those in the graph network. By determining the similarity between the background information in the credit images of related applicants other than those in the graph network and the background information in the credit images of the new applicant, it can be determined whether the new applicant has a risk of clustered fraud.

[0053] Furthermore, if a graph network of related applicants exists, and the number of such graph networks is insufficient (i.e., if the number is less than a preset threshold, such as more than three), it indicates a high degree of association with existing credit applicants. Therefore, the credit risk management strategy for the new applicant needs to further consider credit applicants outside the graph network. By determining the similarity between the background information in the credit images of related applicants (excluding those in the graph network) and the background information in the credit images of the new applicant, it can be determined whether the new applicant has a risk of clustered fraud. Additionally, it is necessary to determine the similarity between the background information in the credit images of credit applicants in the graph network of related applicants and the background information in the credit images of the new applicant to determine whether the new applicant has a risk of clustered fraud.

[0054] Additionally, it should be noted that if the number of graph networks with associated applicants meets the requirements, but the number of graph networks with other update schemes in the graph networks with associated applicants does not meet the requirements (e.g., not less than 2), then the credit risk control management strategy for the new applicant is determined to require further consideration of credit applicants other than those in the graph networks. By determining the similarity between the background information in the credit images of associated applicants (excluding those in the graph networks) and the background information in the credit images of the new applicants, it is determined whether the new applicants have a risk of clustered fraud. Furthermore, it is also necessary to determine the similarity between the background information in the credit images of credit applicants in the graph networks with associated applicants and the background information in the credit images of the new applicants to determine whether the new applicants have a risk of clustered fraud.

[0055] Furthermore, if the number of graph networks with other update schemes in the graph network of associated applicant users meets the requirement, then the number of credit applicant users in the graph network of associated applicant users is determined. If the total number of credit applicant users in the graph network of associated applicant users meets the requirement, for example, if the total number of credit applicant users in all graph networks of associated applicant users is less than 10, then the credit risk control management strategy for the new applicant is determined to only consider the similarity of background information between the credit applicant users in the graph network of associated applicant users and the credit image of the new applicant, to determine whether the new applicant has a risk of clustered fraud.

[0056] Furthermore, if the total number of credit applicants in the graph network with associated applicants does not meet the requirements, the credit risk control management strategy for the new applicant is determined to require further consideration of credit applicants outside the graph network. By determining the similarity between the background information in the credit images of associated applicants outside the graph network and the background information in the credit images of the new applicant, it is determined whether the new applicant has a risk of clustered fraud. In addition, it is also necessary to determine the similarity between the background information in the credit images of credit applicants in the graph network with associated applicants and the new applicant to determine whether the new applicant has a risk of clustered fraud.

[0057] Specifically, the credit granting image is an environmental image of the credit granting applicant during the remote risk control inquiry process. If the background of the credit granting image of the credit granting applicant is consistent with that of the credit granting image of the newly submitted user, then it is determined that the newly submitted user has a risk of clustered fraud. It can be understood that the newly submitted user is the user currently making a credit granting application.

[0058] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0059] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0060] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A risk control method based on graph network computation of core contacts, specifically including: Based on the construction results of the graph network of the core contact, the contact data of the credit application users in different graph networks are determined. Based on the contact data, the construction processing strategy of the graph network of the contacts of the new applicants is determined. Based on the construction processing strategy, the graph network of the core contact is constructed. Based on the construction processing results, if the changes in the graph network do not meet the requirements, proceed to the next step. Based on the contact data and changes of credit application users in different graph networks, different graph network update processing schemes are determined. Based on the update processing schemes and the credit application information of newly added users, the credit risk control management strategy for newly added users is determined.

2. The risk control method for calculating core contacts based on graph network computation as described in claim 1, characterized in that, The method for determining the construction result of the graph network of the core contact is as follows: By collecting data on credit applicants and their contacts, a heterogeneous graph network is constructed with credit applicants and their contacts as nodes and relationships as edges. A graph neural network model is used to embed nodes and aggregate the feature information of neighboring nodes to discover the center of influence of credit applicants in the network for each applicant node.

3. The risk control method for calculating core contacts based on graph network computation as described in claim 1, characterized in that, The contact data of the credit applicant includes the number of credit applicants in the graph network and the number of contacts of the credit applicant.

4. The risk control method for calculating core contacts based on graph network computation as described in claim 1, characterized in that, The method for determining the construction strategy of the graph network of contacts for newly added users is as follows: Based on the contact data, determine the composition of credit application users in the graph network among the existing credit application users; Based on the aforementioned configuration, identify the credit application users who have not undergone graph network construction processing; Based on the credit application user data that has not undergone graph network construction processing, determine the graph network construction processing strategy for the contacts of the newly applied user.

5. The risk control method for calculating core contacts based on graph network computation as described in claim 4, characterized in that, The credit application users who have not undergone graph network construction processing are those who are not in the graph network.

6. The risk control method for calculating core contacts based on graph network computation as described in claim 5, characterized in that, The credit granting users are all users who have made credit granting applications in the past.

7. The risk control method for calculating core contacts based on graph network computation as described in claim 1, characterized in that, Based on the credit application user data that has not undergone graph network construction processing, determine the graph network construction processing strategy for the contacts of the newly applied user, specifically including: Using the credit application user data that has not undergone graph network construction processing, determine the proportion of credit application users that have not undergone graph network construction processing among all credit application users, and use this proportion as the non-construction proportion; Based on the unbuilt proportion, a construction and processing strategy for the graph network of the contacts of the newly added user is determined.

8. The risk control method for calculating core contacts based on graph network computation as described in claim 1, characterized in that, The changes to the graph network do not meet the requirements, specifically including: Based on the construction and processing results, determine the changes in the number of users applying for credit in the graph network; Based on the changes in the number of credit application users in the graph network, the graph network in which the number of credit application users changes is determined; Based on the data on the changes in the number of credit applicants in the graph network, determine whether the changes in the graph network meet the requirements.

9. The risk control method for calculating core contacts based on graph network computation as described in claim 1, characterized in that, The method for determining the credit risk control management strategy for newly applied users is as follows: Based on the credit application information of the newly admitted user, determine the association between the credit application information of the newly admitted user and the credit application information of users in different graph networks; Based on the association of credit application information with credit application users in different graph networks, identify the associated application users in different graph networks; Based on the associated application user data in different graph networks and the graph network update processing scheme, the credit risk control management strategy for the newly applied users is determined.

10. A computer system, comprising: A memory and processor with a communication connection, and a computer program stored on the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a risk control method for calculating core contacts based on graph network computing as described in any one of claims 1-9.

Images