Data processing method and device, computer device, and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a data processing method, device, equipment and storage medium to improve blacklist processing capability. The method part comprises the following steps: receiving a loan approval request sent by a target business system, the loan approval request carrying loan approval data, the loan approval data comprising a system type of the target business system and attribute information of an applicant; calling a blacklist interface corresponding to the system type to obtain a system blacklist; judging whether the applicant is a user in the system blacklist according to the attribute information of the applicant; when the applicant is not a user in the system blacklist, a platform blacklist of an automatic approval platform is called; judging whether the applicant is a user in the platform blacklist according to the attribute information of the applicant; when the applicant is a user in the platform blacklist, a loan service corresponding to the loan approval request is rejected, and rejection result information is generated and fed back to the target business system.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a data processing method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Currently, to unify and implement the vision of unified risk control in retail, some solutions exist that build a customer-level unified risk control platform to align the risk control capabilities of various departments, primarily aiming to achieve unified risk management and efficient system decision-making. In traditional solutions, loan approval data is processed based on the loan initiation system's blacklist. However, this approach only considers the blacklist of the loan initiation system, which is not conducive to identifying blacklisted users. Summary of the Invention

[0003] This application provides a data processing method, apparatus, computer equipment, and storage medium to address the technical problem of insufficient risk control capabilities and risks associated with traditional solutions.

[0004] A data processing method for use in an automated approval platform, the method comprising:

[0005] Receive a loan approval request sent by the target business system. The loan approval request carries loan approval data, which includes the system type of the target business system and the applicant's attribute information.

[0006] Call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system;

[0007] Based on the applicant's attribute information, determine whether the applicant is a user on the system's blacklist;

[0008] If the applicant is not a user in the system blacklist, the platform blacklist of the automatic approval platform is invoked, wherein the automatic approval platform includes blacklist users recorded by multiple different target business systems;

[0009] Based on the applicant's attribute information, determine whether the applicant is a user on the platform's blacklist;

[0010] If the applicant is a user on the platform's blacklist, the loan application corresponding to the loan approval request will be rejected, and a rejection result will be generated and fed back to the target business system.

[0011] Optionally, after determining whether the applicant is a user on the platform's blacklist based on the applicant's attribute information, the method further includes:

[0012] If the applicant is not a user on the platform's blacklist, then the loan approval process strategy corresponding to the system type is selected;

[0013] According to the loan approval process strategy, the corresponding target approval data is obtained, and the loan business is approved according to the target approval data to obtain a first approval result, wherein the first approval result is used to indicate whether the loan business has been approved by the platform.

[0014] The first approval result is fed back to the target business system.

[0015] Optionally, the step of obtaining the corresponding target approval data according to the loan approval process strategy, and approving the loan business according to the target approval data to obtain a first approval result includes:

[0016] Based on the loan approval process strategy, determine the manual approval process strategy information and the face-to-face interview process strategy information;

[0017] Obtain manually approved data; the manually approved data refers to the approval data generated by manual approval in accordance with the manually approved process strategy information.

[0018] Obtain face-to-face approval data, wherein the face-to-face data is the face-to-face data generated by the target business system in accordance with the face-to-face strategy process information;

[0019] The manual approval data and the face-to-face approval data are analyzed to determine the first approval result.

[0020] Optionally, after obtaining the corresponding target approval data according to the loan approval process strategy and approving the loan business according to the target approval data to obtain the first approval result, the method further includes:

[0021] When the first approval result indicates that the loan business has been approved, the first data indication information and the second data indication information corresponding to the system type of the target business system are obtained. The first data indication information is used to indicate the acquisition of first data, and the second data indication information is used to indicate the acquisition of second data. The first data is data acquired according to the first strategy uniformly configured for each of the target business systems, and the second data is data acquired according to the second strategy individually configured for the target business system.

[0022] A data acquisition request is sent to the target business system, the data acquisition request including the first data indication information and the second data indication information;

[0023] Obtain the first and second data returned by the target business system in response to the corresponding data acquisition request.

[0024] Based on the first data, a fraud and credit analysis is performed on the loan business to obtain the first analysis result;

[0025] Based on the second data, a fraud and credit analysis is performed on the loan business to obtain a second analysis result;

[0026] From the first analysis result and the second analysis result, the worst result in the fraud analysis and credit analysis is selected as the final result, and the applicant's loan business is associated with the final result and recorded.

[0027] Optionally, selecting the worst result from the fraud and credit analysis between the first and second analysis results as the final result includes:

[0028] Based on the final result, the loan amount data corresponding to the loan business is generated.

[0029] Optionally, the step of performing fraud and credit analysis on the loan business based on the second data to obtain a second analysis result includes "

[0030] The second data is input into a pre-trained loan fraud model to obtain loan fraud index values, and the second data is input into a pre-trained loan credit profile model to obtain loan credit profile index values.

[0031] The second analysis result is obtained by summarizing the loan fraud index value and the loan credit index value.

[0032] Optionally, the target business system includes multiple systems, and after receiving the loan approval request sent by the target business system, the method further includes:

[0033] Loan approval requests sent by all target business systems are processed asynchronously.

[0034] A data processing apparatus, comprising:

[0035] The receiving module is used to receive loan approval requests sent by the target business system. The loan approval requests carry loan approval data, which includes the system type of the target business system and the applicant's attribute information.

[0036] The first calling module is used to call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system;

[0037] The first judgment module is used to determine whether the applicant is a user in the system blacklist based on the applicant's attribute information;

[0038] The second calling module is used to call the platform blacklist of the automatic approval platform when the applicant is not a user in the system blacklist, wherein the automatic approval platform includes blacklist users recorded by different target business systems;

[0039] The second judgment module is used to determine whether the applicant is a user on the platform's blacklist based on the applicant's attribute information.

[0040] The processing module is used to reject the loan application corresponding to the loan approval request and generate rejection result information when the applicant is a user on the platform's blacklist.

[0041] The sending module is used to send the rejection result information back to the target business system.

[0042] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the data processing method described above.

[0043] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described data processing method.

[0044] As can be seen from the above-mentioned data processing method, device, computer equipment and storage medium, the applicant's loan request is first verified through the system blacklist of the target business system, and then further approved and verified by the unified automatic approval platform based on the platform blacklist. The platform blacklist is obtained based on multiple different target business systems, which can improve risk control capabilities and effectively screen blacklist users from multiple aspects. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of an application environment for a data processing method according to an embodiment of this application;

[0047] Figure 2 This is a flowchart of a data processing method in one embodiment of this application;

[0048] Figure 3 This is another flowchart of a data processing method in one embodiment of this application;

[0049] Figure 4 yes Figure 3 A flowchart illustrating a specific implementation of step S80;

[0050] Figure 5 This is another flowchart of a data processing method in one embodiment of this application;

[0051] Figure 6 This is a schematic diagram of the structure of a data processing device in one embodiment of this application;

[0052] Figure 7 This is a schematic diagram of the structure of a computer device according to one embodiment of this application. Detailed Implementation

[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] The data processing method provided in this application embodiment can be applied to, for example, Figure 1In this application environment, the client interacts and communicates with multiple target business systems via a network, such as target business system 1, target business system 2, ..., target business system N. These multiple target business systems are connected to the automated approval platform. Each of these target business systems can be implemented through a server. The client can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be a standalone server or a server cluster consisting of multiple servers. A target business system is a system capable of providing loan services. The loan services provided by different target business systems are generally different, but they can also be the same, such as a car loan system, a certain type of wallet, a credit card system, or other types of loan systems. In some application scenarios, the target business systems mentioned above in this application are various target business systems under the same group or company. These target business systems are uniformly connected to the designated automated approval platform through an interface. It should be noted that in conventional solutions, the target business system usually completes the approval process itself. However, in this embodiment, the automatic approval platform establishes communication and interaction relationships with these different target business systems through a unified interface, thereby making the data approval process uniform, enabling unified management, improving risk control capabilities, and reducing risk risk through a new approach. The following is a description through specific embodiments.

[0055] In one embodiment, such as Figure 2 As shown, a data processing method is provided, which is applied to... Figure 1 Taking the automated approval platform in China as an example, the process includes the following steps:

[0056] S10: Receive a loan approval request sent by the target business system. The loan approval request carries loan approval data, which includes the system type of the target business system and the applicant's attribute information.

[0057] In this embodiment, an applicant can trigger a loan operation for a specific business through a client. For example, taking a target business system as an auto loan system and the loan business triggered by the applicant as auto loan business A, the applicant can interact with the auto loan system through the client to trigger a loan request for auto loan business A. This loan request carries relevant loan approval data for auto loan business A. This loan approval data includes the system type of the auto loan system (indicating it to be an auto loan system), the applicant's attribute information, and detailed information about the loan business. The detailed information includes the loan business type (auto loan business A), and the attribute information includes the applicant's identity information. The loan request is then sent to the auto loan system. After receiving the loan request, the auto loan system forwards it to the automatic approval platform via an interface as a loan approval request. It should be noted that in traditional solutions, the auto loan system directly performs subsequent approval processing upon receiving a loan request; however, in this embodiment, the request is forwarded to the automatic approval platform.

[0058] It should be noted that the above example uses a car loan system. In other embodiments, the target business system can also be other system types, such as a credit card system. The applicant triggers an interaction process for a credit card loan business through the credit card system, which is similar to the car loan system described above. It will not be described in detail here.

[0059] S20: Call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system.

[0060] For an automated approval platform, upon receiving a loan approval request, it can parse the loan approval data to determine the system type being called. Then, it calls the corresponding blacklist interface to retrieve the system blacklist, which includes blacklisted users recorded by the target business system. For example, after receiving a loan approval request forwarded from the auto loan system, the automated approval platform can determine that the target business system is an auto loan system. Therefore, it will first call the blacklist interface corresponding to that auto loan system to retrieve its system blacklist. This system blacklist includes blacklisted users recorded by the auto loan system.

[0061] It should be noted that the auto loan system can maintain its own system blacklist. This system blacklist consists of blacklisted users recorded by the auto loan system in its past loan practices, including blacklisted users identified during the auto loan system's own approval process. For example, the system blacklist includes applicant 1, applicant 2, ..., applicant n. Applicants can be marked and recorded using their identity information, thus forming a system blacklist of users.

[0062] S30: Based on the applicant's attribute information, determine whether the applicant is a user in the system's blacklist.

[0063] S40: If the applicant is not a user in the system blacklist, the platform blacklist of the automatic approval platform is invoked, wherein the automatic approval platform includes blacklisted users recorded by multiple different target business systems.

[0064] S50: Based on the applicant's attribute information, determine whether the applicant is a user on the platform's blacklist.

[0065] S60: If the applicant is a user on the platform's blacklist, the loan application corresponding to the loan approval request will be rejected, and a rejection result will be generated and fed back to the target business system.

[0066] Furthermore, after calling the blacklist interface corresponding to the system type to obtain the system blacklist, the system determines whether the applicant is a user on the system blacklist based on the applicant's attribute information. If the applicant is not on the system blacklist, the system calls the platform blacklist of the automated approval platform. The automated approval platform includes blacklisted users recorded by multiple target business systems. The automated approval platform also maintains a blacklist, called the platform blacklist, which includes blacklisted users recorded by multiple target business systems. Then, based on the applicant's attribute information, the system determines whether the applicant is a user on the platform blacklist. If the applicant is a user on the platform blacklist, the loan application corresponding to the loan approval request is rejected, and a rejection result is generated and fed back to the target business system. The target business system then forwards the rejection result to the client.

[0067] For example, the automated approval platform also includes blacklisted users recorded by credit card systems, wallet systems, etc. Continuing with the example of a car loan system, if the applicant is not a user on the car loan system's blacklist, the automated approval platform's platform blacklist is invoked. This automated approval platform includes blacklisted users from different credit card systems, wallet systems, etc. Then, based on the applicant's attribute information, it determines whether the applicant is a user on the platform's blacklist. If the applicant is a user on the platform's blacklist, the car loan application corresponding to the loan approval request is rejected, and a rejection result is generated and fed back to the car loan system. The car loan system then forwards the rejection result information back to the client.

[0068] As can be seen from the embodiments of this application, after verification by the system blacklist of the target business system, further approval and verification are carried out by the unified configuration automatic approval platform based on the platform blacklist, which can improve risk control capabilities, effectively screen out blacklist users from multiple aspects, and reduce loan risks.

[0069] In one embodiment, such as Figure 3 As shown, in step S50, after determining whether the applicant is a user on the platform's blacklist based on the applicant's attribute information, the data processing method further includes:

[0070] S70: If the applicant is not a user on the platform's blacklist, then select the loan approval process strategy corresponding to the system type.

[0071] S80: Obtain the corresponding target approval data according to the loan approval process strategy, and approve the loan business according to the target approval data to obtain a first approval result, wherein the first approval result is used to indicate whether the loan business has been approved by the platform.

[0072] S90: Feedback the first approval result back to the target business system.

[0073] As mentioned above, in step S50, after determining whether the applicant is a user on the platform's blacklist based on the applicant's attribute information, if the applicant is a user on the platform's blacklist, the loan application corresponding to the loan approval request is rejected, and a rejection result is generated and fed back to the target business system, at which point the request process ends. In this embodiment, if the applicant is not a user on the platform's blacklist, normal subsequent loan approval operations will be performed. Unlike traditional solutions, this application embodiment first selects the loan approval process strategy corresponding to the system type, then obtains the corresponding target approval data according to the loan approval process strategy, and approves the loan application according to the target approval data to obtain a first approval result. The first approval result is used to indicate whether the loan application has been approved by the platform, and then the first approval result is fed back to the target business system. That is to say, the automatic approval platform has different loan approval processes for different target business systems. The target approval data is the approval data that the automatic approval platform needs to obtain and process to implement the loan approval process strategy.

[0074] For example, taking a car loan system as an example, when the applicant is not a user on the platform's blacklist, the system selects the corresponding loan approval process strategy. Then, it obtains the relevant target approval data based on this strategy and approves the car loan application according to the target approval data, obtaining the first approval result. This first approval result indicates whether the car loan application has been approved by the platform. In the car loan system, the target approval data includes the approver, approval node, specific approval process, and other relevant data to be obtained during the car loan approval process. This other relevant data may include the car loan type, loan amount, loan purpose, or other interactive data during the approval process, etc.

[0075] As can be seen, in this embodiment, the automatic approval platform integrates the approval process strategies of multiple target business systems, so as to better approve loans according to the loan business provided by the target business systems, reduce the risk control risks brought by each target business system, and realize a unified deployment solution with good application scenarios.

[0076] In one embodiment, in step S80, as Figure 4 As shown, the process involves obtaining the corresponding target approval data according to the loan approval process strategy, and approving the loan business according to the target approval data to obtain the first approval result. Specifically, this includes the following steps:

[0077] S81: Based on the loan approval process strategy, determine the manual approval process strategy information and the face-to-face signing process strategy information.

[0078] S82: Obtain manual approval data; the manual approval data is the approval data generated by manual approval in accordance with the manual approval process strategy information.

[0079] S23: Obtain the face-to-face approval data, wherein the face-to-face data is the face-to-face data generated by the target business system in accordance with the face-to-face strategy process information.

[0080] S24: Analyze the manual approval data and the face-to-face approval data to determine the first approval result.

[0081] This embodiment provides a specific implementation method for obtaining corresponding target approval data according to the loan approval process strategy, and approving the loan business according to the target approval data to obtain a first approval result. In this embodiment, face-to-face verification and manual approval processes are set. First, based on the loan approval process strategy, manual approval process strategy information and face-to-face verification strategy process information are determined. The manual approval process strategy information indicates the specific approval process of the manual approval process strategy, and the face-to-face verification strategy process information indicates the specific approval process of the face-to-face verification approval process strategy. After obtaining the manual approval process strategy information and the face-to-face verification strategy process information, these are fed back to the corresponding target business system. Upon receiving the manual approval process strategy information and the face-to-face verification strategy process information, the target business system interacts with the client based on these information to obtain the face-to-face verification approval data generated during the interaction. The face-to-face verification approval data is the face-to-face verification data generated by the target business system performing face-to-face verification according to the face-to-face verification strategy process information, and the manual approval data is the approval data generated by manual approval according to the manual approval process strategy information. The first approval result indicates that the loan transaction has been approved or has not been approved.

[0082] For example, specifically, the face-to-face approval strategy process information can instruct the applicant to record corresponding video clips according to the face-to-face questions. These video clips include recordings of the applicant's responses to the face-to-face questions, and the face-to-face approval data includes these video clips. As another example, the manual approval process strategy information can instruct each approver in each manual approval flow to perform electronic signature confirmation at the corresponding approval node, and the manual approval data includes the aforementioned electronic signature confirmation. For example, if all electronic signatures are available and verified correctly, the manual approval process is considered successful; if the applicant's answers in the video clips meet the requirements, the face-to-face approval process is considered successful. It should be noted that the approval process strategy based on manual and face-to-face processes can be combined with other situations, without specific limitations or explanations. The main purpose of this application embodiment is to uniformly deploy and make decisions on the loan approval process strategies corresponding to various target business systems using an automated approval process, thereby improving overall risk control and facilitating unified deployment.

[0083] In one embodiment, in step S80, as Figure 5 As shown, after obtaining the corresponding target approval data according to the loan approval process strategy, and approving the loan business according to the target approval data to obtain the first approval result, the method further includes the following steps:

[0084] S110: When the first approval result indicates that the loan business has been approved, the first data indication information and the second data indication information corresponding to the system type of the target business system are obtained. The first data indication information is used to indicate the acquisition of first data, and the second data indication information is used to indicate the acquisition of second data. The first data is data acquired according to the first strategy uniformly configured for each of the target business systems, and the second data is data acquired according to the second strategy individually configured for the target business system.

[0085] In this embodiment, when the first approval result indicates that the loan application has been approved, further verification and judgment will be performed to determine the final loan result. It should be noted that in this embodiment, "the loan application has been approved" only indicates that the approval process has been completed and passed. This embodiment still requires further data acquisition for subsequent analysis to determine results such as the loan amount.

[0086] Specifically, when the first approval result indicates that the loan business has been approved, the system type of the target business system is used to obtain the first data indication information and the second data indication information. The first data indication information is used to indicate the acquisition of the first data, and the second data indication information is used to indicate the acquisition of the second data. The first data is the data acquired according to the first strategy uniformly configured for each of the target business systems, and the second data is the data acquired according to the second strategy individually configured for each target business system.

[0087] As can be seen, this application embodiment sets up two strategies. The second strategy is a strategy set separately for each target business system. That is, different target business systems correspond to different second strategies, and the second strategy configured for each target business system is uniquely associated with that target business system. The first strategy, on the other hand, is a strategy uniformly set for all target business systems. That is, the first strategy is the same for each target business system. For example, a car loan system has a first strategy and a second strategy. The second strategy is a strategy configured separately for the car loan system, while the first strategy is a uniformly deployed strategy. For example, a credit card system also has this first strategy.

[0088] It should be noted that the first and second data to be obtained by the first and second strategies are data required for subsequent fraud analysis and credit analysis. The specific data types depend on the specific fraud analysis and credit analysis strategies adopted, and no specific restrictions are made here.

[0089] S120: Feedback a data acquisition request to the target business system, the data acquisition request including the first data indication information and the second data indication information.

[0090] After obtaining the first data indication information and the second data indication information, the automatic approval platform will generate a feedback data acquisition request, which includes the first data indication information and the second data indication information, and then send the data acquisition request back to the target business system, which also includes the first data indication information and the second data indication information.

[0091] S130: Obtain the first data and the second data returned by the target business system in response to the data acquisition request.

[0092] After receiving the data acquisition request, the target business system will respond to the first data indication information and the second data indication information in the data acquisition request, acquire the corresponding first data and second data, and then feed back the acquired first data and second data to the automatic approval platform. The automatic approval platform can then obtain the first data and second data fed back by the target business system in response to the data acquisition request.

[0093] S140: Based on the first data, perform fraud and credit analysis on the loan business to obtain the first analysis result.

[0094] S150: Based on the second data, perform fraud and credit analysis on the loan business to obtain the second analysis result.

[0095] After obtaining the first and second data, the automated approval platform conducts two separate fraud and credit analyses on the loan business based on these two sets of data, thus obtaining the first and second analysis results.

[0096] In one embodiment, specifically, the step of performing fraud and credit analysis on the loan business based on the second data to obtain a second analysis result includes: inputting the second data into a pre-trained loan fraud model to obtain loan fraud index values, and inputting the second data into a pre-trained loan credit model to obtain loan credit index values; summing the loan fraud index values ​​and loan credit index values ​​to obtain the second analysis result. Similarly, the first analysis result can also be obtained based on an artificial intelligence model. The specific implementation method is the same as that for the second analysis result, and will not be detailed here, except that the data input to the models is different—one is the first data, and the other is the second data. Therefore, in order to obtain the above-mentioned first and second analysis results, a total of four models are required: the loan fraud model and the loan credit model used for the first data, and the loan fraud model and the loan credit model used for the second data.

[0097] It should be noted that the loan fraud model and the loan creditworthiness model are pre-built deep learning network models used to output loan fraud index values ​​and loan creditworthiness index values, respectively. The loan fraud index value and the loan creditworthiness index value represent the probability of loan fraud and the reliability of the loan creditworthiness, respectively. These loan fraud model and loan creditworthiness model can be implemented using existing deep learning network frameworks, and no specific limitation is imposed. During training, a large amount of initial data is used as input training data to train the loan fraud network and the loan creditworthiness network, thereby obtaining the loan fraud model and the loan creditworthiness model.

[0098] S160: From the first analysis result and the second analysis result, select the worst result from the fraud analysis and credit analysis as the final result, and associate the applicant's loan business with the final result.

[0099] After obtaining the first and second analysis results, the worst result from the fraud and credit analysis is selected as the final result, and the applicant's loan application is linked to this final result. For example, this linking can be recorded in a blockchain network; no specific limitation is made.

[0100] In this embodiment, relevant data for fraud and credit analysis is acquired through separate and unified deployment strategies. Then, fraud and credit analysis are performed separately, and the worst result in the fraud and credit analysis is selected as the final result. In this way, loan risk can be reduced to the greatest extent and risk control capabilities can be further improved.

[0101] It should be noted that, in one embodiment, after obtaining the final result, the automatic approval platform can also determine matters such as loan amount data based on the final result, without any specific limitations.

[0102] In one embodiment, the target business systems include multiple systems. After receiving loan approval requests from the target business systems, the method further includes asynchronously processing the loan approval requests sent by all target business systems. By processing each target business system asynchronously, the processing efficiency of the automated approval platform can be improved, enabling the platform to respond quickly to requests from each target business system.

[0103] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0104] In one embodiment, a data processing apparatus is provided, which corresponds one-to-one with the data processing methods described in the above embodiments. For example... Figure 6 As shown, the data processing device 10 includes a receiving module 101, a first calling module 102, a first judging module 103, a second calling module 104, a second judging module 105, a processing module 106, and a sending module 107. Detailed descriptions of each functional module are as follows:

[0105] The receiving module 101 is used to receive a loan approval request sent by the target business system. The loan approval request carries loan approval data, which includes the system type of the target business system and the applicant's attribute information.

[0106] The first calling module 102 is used to call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system;

[0107] The first judgment module 103 is used to determine whether the applicant is a user in the system blacklist based on the applicant's attribute information;

[0108] The second calling module 104 is used to call the platform blacklist of the automatic approval platform when the applicant is not a user in the system blacklist, wherein the automatic approval platform includes blacklist users recorded by different target business systems.

[0109] The second judgment module 105 is used to determine whether the applicant is a user in the platform's blacklist based on the applicant's attribute information.

[0110] The processing module 106 is used to reject the loan application corresponding to the loan approval request and generate rejection result information when the applicant is a user in the platform's blacklist.

[0111] The sending module 107 is used to send the rejection result information back to the target business system.

[0112] In one embodiment, the data processing device 10 is further configured to:

[0113] If the applicant is not a user on the platform's blacklist, then the loan approval process strategy corresponding to the system type is selected;

[0114] According to the loan approval process strategy, the corresponding target approval data is obtained, and the loan business is approved according to the target approval data to obtain a first approval result, wherein the first approval result is used to indicate whether the loan business has been approved by the platform.

[0115] The first approval result is fed back to the target business system.

[0116] In one embodiment, the data processing device 10 is further specifically used for:

[0117] Based on the loan approval process strategy, determine the manual approval process strategy information and the face-to-face interview process strategy information;

[0118] Obtain manually approved data; the manually approved data refers to the approval data generated by manual approval in accordance with the manually approved process strategy information.

[0119] Obtain face-to-face approval data, wherein the face-to-face data is the face-to-face data generated by the target business system in accordance with the face-to-face strategy process information;

[0120] The manual approval data and the face-to-face approval data are analyzed to determine the first approval result.

[0121] In one embodiment, the data processing device 10 is further specifically used for:

[0122] When the first approval result indicates that the loan business has been approved, the first data indication information and the second data indication information corresponding to the system type of the target business system are obtained. The first data indication information is used to indicate the acquisition of first data, and the second data indication information is used to indicate the acquisition of second data. The first data is data acquired according to the first strategy uniformly configured for each of the target business systems, and the second data is data acquired according to the second strategy individually configured for the target business system.

[0123] A data acquisition request is sent to the target business system, the data acquisition request including the first data indication information and the second data indication information;

[0124] Obtain the first and second data returned by the target business system in response to the data acquisition request;

[0125] Based on the first data, a fraud and credit analysis is performed on the loan business to obtain the first analysis result;

[0126] Based on the second data, a fraud and credit analysis is performed on the loan business to obtain a second analysis result;

[0127] From the first analysis result and the second analysis result, the worst result in the fraud analysis and credit analysis is selected as the final result, and the applicant's loan business is associated with the final result and recorded.

[0128] In one embodiment, the data processing device 10 is further specifically used for:

[0129] Based on the final result, the loan amount data corresponding to the loan business is generated.

[0130] In one embodiment, the data processing device 10 is further specifically used for:

[0131] The second data is input into a pre-trained loan fraud model to obtain loan fraud index values, and the second data is input into a pre-trained loan credit profile model to obtain loan credit profile index values.

[0132] The second analysis result is obtained by summarizing the loan fraud index value and the loan credit index value.

[0133] In one embodiment, the data processing device 10 is further specifically used for:

[0134] Loan approval requests sent by all target business systems are processed asynchronously.

[0135] Specific limitations regarding the data processing device can be found in the limitations regarding the data processing method described above, and will not be repeated here. Each module in the aforementioned data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0136] In one embodiment, a computer device is provided, which is the automatic approval platform of this application. The platform can be a server, and its internal structure diagram can be as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data or information. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a data processing method.

[0137] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0138] Receive a loan approval request sent by the target business system. The loan approval request carries loan approval data, which includes the system type of the target business system and the applicant's attribute information.

[0139] Call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system;

[0140] Based on the applicant's attribute information, determine whether the applicant is a user on the system's blacklist;

[0141] If the applicant is not a user in the system blacklist, the platform blacklist of the automatic approval platform is invoked, wherein the automatic approval platform includes blacklist users recorded by multiple different target business systems;

[0142] Based on the applicant's attribute information, determine whether the applicant is a user on the platform's blacklist;

[0143] If the applicant is a user on the platform's blacklist, the loan application corresponding to the loan approval request will be rejected, and a rejection result will be generated and fed back to the target business system.

[0144] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0145] Receive a loan approval request sent by the target business system. The loan approval request carries loan approval data, which includes the system type of the target business system and the applicant's attribute information.

[0146] Call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system;

[0147] Based on the applicant's attribute information, determine whether the applicant is a user on the system's blacklist;

[0148] If the applicant is not a user in the system blacklist, the platform blacklist of the automatic approval platform is invoked, wherein the automatic approval platform includes blacklist users recorded by multiple different target business systems;

[0149] Based on the applicant's attribute information, determine whether the applicant is a user on the platform's blacklist;

[0150] If the applicant is a user on the platform's blacklist, the loan application corresponding to the loan approval request will be rejected, and a rejection result will be generated and fed back to the target business system.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0152] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0153] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A data processing method, characterized in that, For use in an automated approval platform, the method includes: Receive a loan approval request sent by the target business system. The loan approval request carries loan approval data, which includes the system type of the target business system and the applicant's attribute information. Call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system; Based on the applicant's attribute information, determine whether the applicant is a user on the system's blacklist; If the applicant is not a user in the system blacklist, the platform blacklist of the automatic approval platform is invoked, wherein the automatic approval platform includes blacklist users recorded by multiple different target business systems; Based on the applicant's attribute information, determine whether the applicant is a user on the platform's blacklist; If the applicant is a user on the platform's blacklist, the loan application corresponding to the loan approval request will be rejected, and a rejection result will be generated and fed back to the target business system. If the applicant is not a user on the platform's blacklist, the corresponding loan approval process strategy for the system type is selected; the corresponding target approval data is obtained according to the loan approval process strategy, and the loan business is approved according to the target approval data to obtain a first approval result, wherein the first approval result is used to indicate whether the loan business has been approved by the platform; the first approval result is fed back to the target business system. When the first approval result indicates that the loan business has been approved, the first data indication information and the second data indication information corresponding to the system type of the target business system are obtained. The first data indication information is used to indicate the acquisition of first data, and the second data indication information is used to indicate the acquisition of second data. The first data is data acquired according to the first strategy uniformly configured for each of the target business systems, and the second data is data acquired according to the second strategy individually configured for the target business system. A data acquisition request is sent to the target business system, the data acquisition request including the first data indication information and the second data indication information; Obtain the first and second data returned by the target business system in response to the data acquisition request; Based on the first data, a fraud and credit analysis is performed on the loan business to obtain the first analysis result; Based on the second data, a fraud and credit analysis is performed on the loan business to obtain a second analysis result; From the first analysis result and the second analysis result, the worst result in the fraud analysis and credit analysis is selected as the final result, and the applicant's loan business is associated with the final result and recorded. The automated approval platform establishes communication and interaction with multiple target business systems of different system types through a unified interface. The target business systems provide different loan services and include auto loan systems, wallet systems, and credit card systems. The first strategy is a uniform and identical strategy set for all target business systems, while the second strategy is a unique strategy configured separately for each target business system.

2. The data processing method as described in claim 1, characterized in that, The step of obtaining the corresponding target approval data according to the loan approval process strategy, and approving the loan business according to the target approval data to obtain a first approval result includes: Based on the loan approval process strategy, determine the manual approval process strategy information and the face-to-face interview process strategy information; Acquire manual approval data, wherein the manual approval data is the approval data generated by the target business system in accordance with the manual approval process strategy information; Obtain face-to-face verification approval data, wherein the face-to-face verification approval data is the face-to-face verification data generated by the target business system in accordance with the face-to-face verification strategy process information; The manual approval data and the face-to-face approval data are analyzed to determine the first approval result.

3. The data processing method as described in claim 1, characterized in that, After selecting the worst result from the fraud and credit analyses from the first and second analysis results as the final result, the method further includes: Based on the final result, the loan amount data corresponding to the loan business is generated.

4. The data processing method as described in claim 1, characterized in that, The step of performing fraud and credit analysis on the loan business based on the second data to obtain a second analysis result includes: The second data is input into a pre-trained loan fraud model to obtain loan fraud index values, and the second data is input into a pre-trained loan credit profile model to obtain loan credit profile index values. The second analysis result is obtained by summarizing the loan fraud index value and the loan credit index value.

5. The data processing method according to any one of claims 1-4, characterized in that, The target business systems include multiple systems, and after receiving the loan approval request sent by the target business systems, the method further includes: Loan approval requests sent by all target business systems are processed asynchronously.

6. A data processing apparatus for implementing the method as described in claim 1, characterized in that, For use in an automated approval platform, the device includes: The receiving module is used to receive loan approval requests sent by the target business system. The loan approval requests carry loan approval data, which includes the system type of the target business system and the applicant's attribute information. The first calling module is used to call the blacklist interface corresponding to the system type to obtain the system blacklist, wherein the system blacklist includes blacklisted users recorded by the target business system; The first judgment module is used to determine whether the applicant is a user in the system blacklist based on the applicant's attribute information; The second calling module is used to call the platform blacklist of the automatic approval platform when the applicant is not a user in the system blacklist, wherein the automatic approval platform includes blacklist users recorded by different target business systems; The second judgment module is used to determine whether the applicant is a user on the platform's blacklist based on the applicant's attribute information. The processing module is used to reject the loan application corresponding to the loan approval request and generate rejection result information when the applicant is a user on the platform's blacklist. The sending module is used to send the rejection result information back to the target business system.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the data processing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the data processing method as described in any one of claims 1 to 5.

Images