Method and apparatus for processing loan applications

Abstract

This invention discloses a method and apparatus for processing loan applications, relating to the field of financial information service technology. One specific embodiment of the method includes: receiving a loan application from a target user; obtaining credit data for the target user based on the user information of the target user, the credit data coming from multiple credit reporting agencies; for each credit reporting agency: determining a preprocessing combination corresponding to the credit reporting agency; using the preprocessing combination to preprocess the credit data from the credit reporting agency to obtain standardized credit data corresponding to the credit reporting agency; inputting the standardized credit data corresponding to each credit reporting agency into a credit assessment model to obtain the output result of the credit assessment model; and determining the review result of the loan application based on the output result. This embodiment standardizes credit data across countries and regions, enabling efficient cross-national credit information assessment.

Description

Technical Field

[0001] This invention relates to the field of financial information service technology, and in particular to a method and apparatus for processing loan applications. Background Technology

[0002] Assessing users' credit information has become a crucial aspect of internet finance. Traditional offline processes, which rely on manual verification of submitted physical documents, offer good risk control, but are inefficient. Therefore, the fully online processes advocated by internet finance represent not only a complete simplification of offline procedures but also a significant challenge in the design and development of online systems.

[0003] Credit reporting systems are authoritative and impartial, and can evaluate users' credit information through credit data. However, when conducting cross-national credit information evaluations, due to differences between credit reporting systems in various countries and regions, it usually relies on manual review by financial institution employees to adapt to the business needs of different regions. This method is relatively primitive and inefficient. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method and apparatus for processing loan applications, which standardizes credit data across countries and regions, and can efficiently achieve cross-country credit information assessment.

[0005] In a first aspect, embodiments of the present invention provide a method for processing loan applications, comprising:

[0006] Receive loan applications from target users;

[0007] Based on the user information of the target user, obtain credit data for the target user, wherein the credit data comes from multiple credit reporting agencies;

[0008] For each credit reporting agency: determine the preprocessing combination corresponding to the credit reporting agency; use the preprocessing combination to preprocess the credit reporting data from the credit reporting agency to obtain the standardized credit reporting data corresponding to the credit reporting agency;

[0009] The standardized credit data corresponding to each of the credit reporting agencies is input into the credit assessment model to obtain the output results of the credit assessment model;

[0010] Based on the output results, the review result of the loan application is determined.

[0011] Optionally, the step of using the preprocessing combination to preprocess the credit data from the credit reporting agency to obtain standardized credit data corresponding to the credit reporting agency includes:

[0012] Determine at least one piece of preprocessing information included in the preprocessing combination;

[0013] For each piece of preprocessed information: determine the processing field and preprocessing method corresponding to the preprocessed information; use the preprocessing method to preprocess the data in the processing field of the target credit data, wherein the target credit data is credit data from the credit reporting agency;

[0014] The preprocessed target credit data is identified as the standardized credit data corresponding to the credit reporting agency.

[0015] Optionally, before receiving the loan application from the target user, the method further includes:

[0016] Obtain credit data from the target credit reporting agency;

[0017] Identify multiple alternative preprocessing combinations corresponding to the target credit reporting agency;

[0018] For each of the candidate preprocessing combinations: using the candidate preprocessing combination, preprocess the credit data of the target credit reporting agency to obtain standardized credit data and processing time corresponding to the candidate processing combination; determine the effect data of the standardized credit data corresponding to the candidate processing combination;

[0019] Based on the processing time and effect data corresponding to each of the candidate preprocessing combinations, the preprocessing combination corresponding to the target credit reporting agency is determined from the plurality of candidate preprocessing combinations.

[0020] Optionally, after obtaining credit data for the target user, wherein the credit data comes from multiple credit reporting agencies, the process further includes:

[0021] The system stores credit data for the target user from the multiple credit reporting agencies.

[0022] Optionally, before storing the credit data for the target user from the multiple credit reporting agencies in the system, the method further includes:

[0023] Obtain the data structure information of the credit data from the credit reporting agency;

[0024] Based on the data structure information, create the data table corresponding to the credit reporting agency in the data warehouse;

[0025] The process of storing credit data for the target user from the multiple credit reporting agencies in the system includes:

[0026] From the data warehouse, identify the data table corresponding to the credit reporting agency;

[0027] Credit data from the credit reporting agency is stored in the data table corresponding to the credit reporting agency.

[0028] Optionally, obtaining credit data for the target user includes:

[0029] Incremental credit data of the target user is obtained from multiple credit reporting agencies;

[0030] Obtain the existing credit data of the target user from the system;

[0031] Credit data for the target user is obtained based on the incremental credit data and the existing credit data.

[0032] Optionally, determining the review result of the loan application based on the output result includes:

[0033] Determine the scoring criteria corresponding to the loan application;

[0034] Determine the user rating corresponding to the output result;

[0035] If the user rating meets the rating criteria, the review result indicates that the target user has passed the loan application;

[0036] If the user's rating does not meet the rating criteria, the review result indicates that the target user's loan application has not been approved.

[0037] Optionally, before obtaining the credit data for the target user, the method further includes:

[0038] The authorization statement for the system to obtain credit data;

[0039] Receive selection operation for the aforementioned authorization specification;

[0040] When the selected operation represents consent to the system obtaining credit data, the step of obtaining credit data for the target user is performed.

[0041] Secondly, embodiments of the present invention provide a loan application processing apparatus, comprising:

[0042] The application receiving module is used to receive loan applications from target users;

[0043] The data acquisition module is used to acquire credit data for the target user based on the user information of the target user, wherein the credit data comes from multiple credit reporting agencies;

[0044] The standardization module is used for each credit reporting agency to: determine the preprocessing combination corresponding to the credit reporting agency; and use the preprocessing combination to preprocess the credit reporting data from the credit reporting agency to obtain standardized credit reporting data corresponding to the credit reporting agency.

[0045] The data input module is used to input the standardized credit data corresponding to each of the credit reporting agencies into the credit assessment model in order to obtain the output results of the credit assessment model.

[0046] The result determination module is used to determine the review result of the loan application based on the output result.

[0047] Optionally, the standardization module is specifically used for:

[0048] Determine at least one piece of preprocessing information included in the preprocessing combination;

[0049] For each piece of preprocessed information: determine the processing field and preprocessing method corresponding to the preprocessed information; use the preprocessing method to preprocess the data in the processing field of the target credit data, wherein the target credit data is credit data from the credit reporting agency;

[0050] The preprocessed target credit data is identified as the standardized credit data corresponding to the credit reporting agency.

[0051] Optionally, it also includes:

[0052] The combination determination module is used to obtain credit data from the target credit reporting agency;

[0053] Identify multiple alternative preprocessing combinations corresponding to the target credit reporting agency;

[0054] For each of the candidate preprocessing combinations: using the candidate preprocessing combination, preprocess the credit data of the target credit reporting agency to obtain standardized credit data and processing time corresponding to the candidate processing combination; determine the effect data of the standardized credit data corresponding to the candidate processing combination;

[0055] Based on the processing time and effect data corresponding to each of the candidate preprocessing combinations, the preprocessing combination corresponding to the target credit reporting agency is determined from the plurality of candidate preprocessing combinations.

[0056] Optionally, it also includes:

[0057] The storage module is used to store credit data for the target user from the multiple credit reporting agencies in the system.

[0058] Thirdly, embodiments of the present invention provide an electronic device, including:

[0059] One or more processors;

[0060] Storage device for storing one or more programs.

[0061] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above embodiments.

[0062] Fourthly, embodiments of the present invention provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the above embodiments.

[0063] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the methods described in any of the above embodiments.

[0064] One embodiment of the above invention has the following advantages or beneficial effects: it acquires credit data for a target user from multiple credit reporting agencies. The credit data from different agencies have different data structures. By combining the preprocessing data from each agency, the credit data is standardized, facilitating the establishment of a universal credit assessment model. The solution of this invention can standardize credit data from different countries and regions, and then utilize the credit assessment model to obtain the user's review results, enabling efficient cross-national credit information assessment.

[0065] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0066] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0067] Figure 1 This is a flowchart illustrating a loan application processing method provided in the first embodiment of the present invention;

[0068] Figure 2 This is a flowchart illustrating a loan application processing method provided in the second embodiment of the present invention;

[0069] Figure 3 This is a flowchart illustrating a loan application processing method provided in the third embodiment of the present invention;

[0070] Figure 4 This is a flowchart illustrating a loan application processing method provided in the fourth embodiment of the present invention;

[0071] Figure 5This is a schematic diagram of the structure of a loan application processing device provided in an embodiment of the present invention;

[0072] Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0073] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0074] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0075] Figure 1 This is a flowchart illustrating a loan application processing method provided in the first embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0076] Step 101: Receive loan applications from target users.

[0077] Step 102: Based on the target user's user information, obtain the credit data for the target user. The credit data comes from multiple credit reporting agencies.

[0078] Different countries or regions may establish different credit reporting agencies. Credit data from different credit reporting agencies may have different data structures.

[0079] Step 103: For each credit reporting agency: determine the preprocessing combination corresponding to the credit reporting agency; use the preprocessing combination to preprocess the credit data from the credit reporting agency to obtain the standardized credit data of the credit reporting agency.

[0080] By standardizing credit data through preprocessing combinations corresponding to different credit reporting agencies, a universal credit assessment model can be established. Different credit reporting agencies correspond to different preprocessing combinations, and each preprocessing combination includes at least one preprocessing information, which includes: processing fields and processing methods. Processing methods may include: normalization, removal of extreme values, PCA (Principal Component Analysis), etc.

[0081] Credit data from credit reporting agencies can be preprocessed in the following way: determine at least one preprocessing information included in the preprocessing combination; for each preprocessing information: determine the processing field and preprocessing method corresponding to the preprocessing information; use the preprocessing method to preprocess the data in the processing field of the target credit data, where the target credit data is credit data from a credit reporting agency; and determine the preprocessed target credit data as the standardized credit data corresponding to the credit reporting agency.

[0082] For example, the preprocessing combination corresponding to credit reporting agency 1 includes: preprocessed information 1 and preprocessed information 2. Preprocessed information 1 corresponds to the gender field, and the processing method is normalization. The gender field value of credit reporting agency 1's credit data is: male, female. The normalized gender field value is: 1, 0. Using the above method, the gender field of credit reporting data from multiple credit reporting agencies is uniformly standardized to 1, 0.

[0083] Preprocessing information 2 corresponds to the age field, and the processing method is to remove extreme values, that is, to remove records with an age greater than 120 or less than 10. Using this method can improve data quality and make the output results of the credit assessment model more accurate.

[0084] Step 104: Input the standardized credit data from each credit reporting agency into the credit assessment model to obtain the output results of the credit assessment model.

[0085] Credit assessment models can be created according to business needs, and can be built based on models such as random forests, gradient boosting trees, and logistic regression. Outputs can include recommended credit limits, risk assessment results, scoring cards, and user profiles.

[0086] Step 105: Determine the approval result of the loan application based on the output.

[0087] The system retrieves the loan application requirements and determines whether the output matches those requirements. If the output matches, the review result indicates that the target user's loan application has been approved. If the output does not match, the review result indicates that the target user's loan application has not been approved.

[0088] In this embodiment of the invention, credit data for a target user is acquired from multiple credit reporting agencies. The credit data from different agencies have different data structures. Through preprocessing combinations corresponding to each agency, the credit data is standardized to facilitate the establishment of a universal credit assessment model. This embodiment of the invention can standardize credit data from different countries and regions, and then utilize the credit assessment model to obtain the user's review results, thereby efficiently achieving cross-national credit information assessment.

[0089] The solutions implemented using this invention do not rely on traditional offline processing methods. They directly connect to credit reporting systems in various countries or regions online, eliminating cumbersome offline procedures and situations where applicants falsify materials. This simplifies the review process while increasing the credibility of the materials and improving the online processing level of financial institutions. Through standardized credit scores or data, different credit reporting systems in different regions can be standardized for measurement, facilitating the establishment of a universal credit assessment model.

[0090] Furthermore, unifying credit data from different credit reporting agencies facilitates financial institutions' expansion into new countries or regions, eliminating the need for targeted development for different countries and regions. Expansion can be achieved solely through the preprocessing module of the credit reporting system, thus improving code versatility.

[0091] The solutions in this invention also provide convenient and unified user management for large multinational financial institutions, and add data support for providing more customized products to some high-value but highly mobile users.

[0092] In one embodiment of the present invention, before receiving a loan application from a target user, the method further includes: obtaining credit data from a target credit reporting agency; determining multiple alternative preprocessing combinations corresponding to the target credit reporting agency; for each alternative preprocessing combination: preprocessing the credit data of the target credit reporting agency using the alternative preprocessing combination to obtain standardized credit data and processing time corresponding to the alternative preprocessing combination; determining the effect data of the standardized credit data corresponding to the alternative preprocessing combination; and determining the preprocessing combination corresponding to the target credit reporting agency from multiple alternative preprocessing combinations based on the processing time and effect data corresponding to each alternative preprocessing combination.

[0093] The system simulates preprocessing processes with different combinations. Based on the processing time and performance data of different alternative preprocessing combinations, the system determines the preprocessing combination for the credit reporting agency. Performance data may include accuracy, precision, and recall. Alternative processing combinations with better performance data and shorter processing times can be selected as the preprocessing combination for the credit reporting agency. Therefore, using the credit reporting agency's preprocessing combination can achieve better predictive results and higher processing efficiency.

[0094] In one embodiment of the present invention, before obtaining credit data for a target user, the method further includes: displaying an authorization statement for the system to obtain credit data; receiving a selection operation regarding the authorization statement; and, if the selection operation indicates consent to the system obtaining credit data, executing the step of obtaining credit data for the target user. Credit data for the target user is only obtained when the user authorizes the system to obtain credit data, thereby reducing the risk of misuse of the user's credit data and strengthening the management of user information security.

[0095] Figure 2 This is a flowchart illustrating a loan application processing method according to a second embodiment of the present invention, as shown below. Figure 2 As shown, the method includes:

[0096] Step 201: Obtain the data structure information of the credit reporting agency's credit data.

[0097] Step 202: Based on the data structure information, create the corresponding data tables for the credit reporting agencies in the data warehouse.

[0098] Credit data from different credit reporting agencies have different data structures. Data tables corresponding to each credit reporting agency are created in the data warehouse, and a mapping relationship between credit reporting agencies and these data tables is established.

[0099] Step 203: Receive loan applications from target users and obtain credit data for target users. The credit data comes from multiple credit reporting agencies.

[0100] Step 204: Identify the data tables corresponding to the credit reporting agencies from the data warehouse; store the credit data from the credit reporting agencies in the corresponding data tables. One or more data tables can be set up in the data warehouse for the same credit reporting agency.

[0101] Based on the mapping relationship between credit reporting agencies and data tables, the corresponding data tables for each credit reporting agency are determined in order to store the credit reporting data for that agency.

[0102] Step 205: For each credit reporting agency: determine the preprocessing combination corresponding to the credit reporting agency; use the preprocessing combination to preprocess the credit data from the credit reporting agency to obtain the standardized credit data corresponding to the credit reporting agency.

[0103] Step 206: Input the standardized credit data corresponding to each credit reporting agency into the credit assessment model to obtain the output results of the credit assessment model.

[0104] Step 207: Determine the approval result of the loan application based on the output.

[0105] In this embodiment of the invention, data tables corresponding to each credit reporting agency are created in the data warehouse to uniformly store user credit data from multiple credit reporting agencies. This makes it faster and more convenient for financial institutions to perform routine operations such as user maintenance and risk assessment, thereby effectively eliminating high-risk users and reducing systemic risks for financial institutions.

[0106] In one embodiment of the present invention, obtaining credit data for a target user includes: obtaining incremental credit data for the target user from multiple credit reporting agencies; obtaining existing credit data for the target user from the system; and merging the incremental credit data and the existing credit data to obtain credit data for the target user.

[0107] When obtaining credit data for a target user, first determine whether the system stores such data. If it does, obtain the retention period information for each credit reporting agency within the system. Based on the retention period information of each agency, retrieve the incremental credit data for the target user from each agency. Finally, merge the incremental and existing credit data to obtain the final credit data for the target user.

[0108] Figure 3 This is a flowchart illustrating a loan application processing method provided in the third embodiment of the present invention, as shown below. Figure 3 As shown, the method includes:

[0109] Step 301: Receive loan applications from target users and obtain credit data for target users. The credit data comes from multiple credit reporting agencies.

[0110] Step 302: For each credit reporting agency: determine the preprocessing combination corresponding to the credit reporting agency; use the preprocessing combination to preprocess the credit data from the credit reporting agency to obtain the standardized credit data corresponding to the credit reporting agency.

[0111] Step 303: Input the standardized credit data corresponding to each credit reporting agency into the credit assessment model to obtain the output results of the credit assessment model.

[0112] Step 304: Determine the scoring criteria corresponding to the loan application; determine the user score corresponding to the output result.

[0113] Scoring criteria can include a credit score greater than a threshold, or a risk score less than a threshold. The output of the credit assessment model includes a user score, which can be a credit score, a risk score, etc.

[0114] Step 305: If the user rating meets the rating criteria, determine the review result to indicate that the target user has passed the loan application.

[0115] Step 306: If the user rating does not meet the rating criteria, determine the review result to indicate that the target user's loan application has not been approved.

[0116] In this embodiment of the invention, user credit data is obtained from multiple credit reporting agencies, the credit data from each agency is standardized, and the output of a unified credit assessment model is used to determine the loan application review result. Regardless of whether the user's application is successful or not, the credit analysis result and the final review result are stored to facilitate further improvement of the credit assessment model.

[0117] Figure 4This is a flowchart illustrating a loan application processing method provided in the fourth embodiment of the present invention, as shown below. Figure 4 As shown, the method includes: a pre-process for obtaining user credit information, a user credit information acquisition process, user credit information data preprocessing, user credit information data model calculation, and user credit information data training and model improvement.

[0118] Pre-approval process for obtaining user credit information: When a user initiates an online loan application or other credit-related product, a legally binding authorization statement will be provided for the user to read and agree to. If the user does not agree to credit information extraction, some business processes will be transferred to offline procedures.

[0119] User credit information acquisition process: After obtaining the user's authorization and consent, the system will access the personal credit information system, obtain a certain amount of credit information authorization data, return it to the system and store it for a fixed period of time. Different dimensions of data storage are designed according to the credit information systems of different regions. The credit information data is stored in full to facilitate the system's subsequent learning, comparison and classification of the credit information data.

[0120] User credit data preprocessing: Preprocessing of credit data from different users and regions aims to normalize and unify credit data with various standards, facilitating its input into the intelligent network for standardized calculations and comparisons, and ultimately outputting results. Different combinations of preprocessing are used based on the characteristics of regional data to ensure consistency across different dimensions and a roughly similar range.

[0121] User credit data model calculation: Preprocessed credit data is input into a trained deep learning model for calculation, supplemented by simple post-processing to obtain the corresponding user credit quality analysis. The final model data is stored and the results are output to the credit system. The results are applied according to different scenarios to filter out and mark users with poor credit. If the credit system ultimately rejects the application, a rejection interface is displayed on the front end, and the user's application process ends. Conversely, if the user's credit data is good, the application is approved and the user enters the contract signing and account opening stage. Simultaneously, regardless of whether the user's application is successful or not, the credit analysis results and the final approval result are stored to facilitate further model improvement.

[0122] User credit data training and model refinement: Regularly refine the model and integrate data from different credit reporting systems. Use stored user credit data to improve the model and adjust the preprocessing combinations regionally. For example, if region XX integrates a credit reporting system and begins using credit data simulation, developers will simulate different alternative preprocessing combinations, integrate the original model weights for training calculations, weigh the speed and effectiveness of different alternative preprocessing combinations, and determine the final preprocessing combination. Furthermore, credit data from new systems can be used to train the model, and data augmentation can be performed as needed when data volume is limited.

[0123] The solution presented in this invention addresses the current inability of financial institutions in different regions to uniformly measure users' credit records. This allows for the use of established credit models when expanding into emerging markets, thus accelerating the technological deployment of business expansion. Furthermore, it provides unified storage for user credit records, resolving the issue of storage consistency and enabling the joint storage of users from different regions, thereby reducing the hardware costs required for business deployment to some extent. Additionally, it offers faster online credit analysis, accelerating online business processes, improving user experience, and ultimately enhancing the competitiveness of online business products.

[0124] Figure 5 This is a schematic diagram of the structure of a loan application processing device according to an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes:

[0125] Application receiving module 501 is used to receive loan applications from target users;

[0126] Data acquisition module 502 is used to acquire credit data for the target user, wherein the credit data comes from multiple credit reporting agencies;

[0127] The standardization module 503 is used for each credit reporting agency to: determine the preprocessing combination corresponding to the credit reporting agency; and use the preprocessing combination to preprocess the credit reporting data from the credit reporting agency to obtain standardized credit reporting data of the credit reporting agency.

[0128] The data input module 504 is used to input the standardized credit data corresponding to each of the credit reporting agencies into the credit assessment model in order to obtain the output result of the credit assessment model;

[0129] The result determination module 505 is used to determine the review result of the loan application based on the output result.

[0130] Optionally, the standardization module 503 is specifically used for:

[0131] Determine at least one piece of preprocessing information included in the preprocessing combination;

[0132] For each piece of preprocessed information: determine the processing field and preprocessing method corresponding to the preprocessed information; use the preprocessing method to preprocess the data in the processing field of the target credit data, wherein the target credit data is credit data from the credit reporting agency;

[0133] The preprocessed target credit data is identified as the standardized credit data corresponding to the credit reporting agency.

[0134] Optionally, it also includes:

[0135] The combination determination module 506 is used to obtain credit data from the target credit reporting agency;

[0136] Identify multiple alternative preprocessing combinations corresponding to the target credit reporting agency;

[0137] For each of the candidate preprocessing combinations: using the candidate preprocessing combination, preprocess the credit data of the target credit reporting agency to obtain standardized credit data and processing time corresponding to the candidate processing combination; determine the effect data of the standardized credit data corresponding to the candidate processing combination;

[0138] Based on the processing time and effect data corresponding to each of the candidate preprocessing combinations, the preprocessing combination corresponding to the target credit reporting agency is determined from the plurality of candidate preprocessing combinations.

[0139] Optionally, it also includes:

[0140] The storage module 507 is used to store credit data for the target user from the multiple credit reporting agencies in the system.

[0141] Optionally, the storage module 508 is specifically used for:

[0142] Obtain the data structure information of the credit data from the credit reporting agency;

[0143] Based on the data structure information, create the data table corresponding to the credit reporting agency in the data warehouse;

[0144] From the data warehouse, identify the data table corresponding to the credit reporting agency;

[0145] Credit data from the credit reporting agency is stored in the data table corresponding to the credit reporting agency.

[0146] Optionally, the data acquisition module 502 is specifically used for:

[0147] Incremental credit data of the target user is obtained from multiple credit reporting agencies;

[0148] Obtain the existing credit data of the target user from the system;

[0149] Credit data for the target user is obtained based on the incremental credit data and the existing credit data.

[0150] Optionally, the result determination module 505 is specifically used for:

[0151] Determine the scoring criteria corresponding to the loan application;

[0152] Determine the user rating corresponding to the output result;

[0153] If the user rating meets the rating criteria, the review result indicates that the target user has passed the loan application;

[0154] If the user's rating does not meet the rating criteria, the review result indicates that the target user's loan application has not been approved.

[0155] Optionally, it also includes:

[0156] Authorization module 508 is used to display the authorization instructions for the system to obtain credit data;

[0157] Receive selection operation for the aforementioned authorization specification;

[0158] When the selected operation represents consent to the system obtaining credit data, the step of obtaining credit data for the target user is performed.

[0159] This invention provides an electronic device, comprising:

[0160] One or more processors;

[0161] Storage device for storing one or more programs.

[0162] When one or more programs are executed by one or more processors, the one or more processors implement the methods of any of the above embodiments.

[0163] This invention provides a computer program product, including a computer program that, when executed by a processor, implements the enterprise risk assessment method of this invention.

[0164] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing a terminal device of the present invention. Figure 6The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0165] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0166] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0167] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this invention.

[0168] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0169] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0170] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor, and for example, can be described as: an application receiving module, a data acquisition module, a standardization module, a data input module, and a result determination module. The names of these modules do not necessarily limit the module itself; for example, the data acquisition module can also be described as "a module for receiving loan applications from target users."

[0171] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0172] Receive loan applications from target users;

[0173] Based on the user information of the target user, obtain credit data for the target user, wherein the credit data comes from multiple credit reporting agencies;

[0174] For each credit reporting agency: determine the preprocessing combination corresponding to the credit reporting agency; use the preprocessing combination to preprocess the credit reporting data from the credit reporting agency to obtain the standardized credit reporting data corresponding to the credit reporting agency;

[0175] The standardized credit data corresponding to each of the credit reporting agencies is input into the credit assessment model to obtain the output results of the credit assessment model;

[0176] Based on the output results, the review result of the loan application is determined.

[0177] According to the technical solution of this invention, credit data for a target user is obtained from multiple credit reporting agencies. The credit data from different agencies have different data structures. By combining the preprocessing data from each agency, the credit data is standardized to facilitate the establishment of a universal credit assessment model. This invention can standardize credit data from different countries and regions, and then use the credit assessment model to obtain the user's review result, thereby efficiently achieving cross-national credit information assessment.

[0178] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for processing loan applications, characterized in that, include: Receive loan applications from target users; Based on the user information of the target user, obtain credit data for the target user, wherein the credit data comes from multiple credit reporting agencies; For each credit reporting agency: determine the preprocessing combination corresponding to the credit reporting agency; Using the aforementioned preprocessing combination, credit data from the credit reporting agency is preprocessed to obtain standardized credit data corresponding to the credit reporting agency. This includes: determining at least one preprocessing information included in the preprocessing combination; for each piece of preprocessing information: determining the processing field and preprocessing method corresponding to the preprocessing information; using the preprocessing method to preprocess the data in the processing field of the target credit data, where the target credit data is credit data from the credit reporting agency; and determining the preprocessed target credit data as the standardized credit data corresponding to the credit reporting agency. The standardized credit data corresponding to each of the credit reporting agencies is input into the credit assessment model to obtain the output result of the credit assessment model; wherein, the credit assessment model is periodically improved using the stored user credit data, and the combination of preprocessing processes is adjusted regionally. Based on the output results, the review result of the loan application is determined, including: determining the scoring criteria corresponding to the loan application; determining the user score corresponding to the output results; if the user score meets the scoring criteria, the review result indicates that the target user has passed the loan application; if the user score does not meet the scoring criteria, the review result indicates that the target user has not passed the loan application. Before receiving the loan application from the target user, the method further includes: acquiring credit data from the target credit reporting agency; determining multiple alternative preprocessing combinations corresponding to the target credit reporting agency; for each alternative preprocessing combination: preprocessing the credit data of the target credit reporting agency using the alternative preprocessing combination to obtain standardized credit data and processing time corresponding to the alternative preprocessing combination; determining the effect data of the standardized credit data corresponding to the alternative preprocessing combination; and determining the preprocessing combination corresponding to the target credit reporting agency from the multiple alternative preprocessing combinations based on the processing time and effect data corresponding to each alternative preprocessing combination. It also includes simulating different combinations of preprocessing processes, and determining the preprocessing combination for the credit reporting agency based on the processing time and effect data of different alternative preprocessing combinations; wherein the effect data includes: accuracy, precision, and recall.

2. The method according to claim 1, characterized in that, After obtaining credit data for the target user, wherein the credit data comes from multiple credit reporting agencies, the process further includes: The system stores credit data for the target user from the multiple credit reporting agencies.

3. The method according to claim 2, characterized in that, Before storing the credit data for the target user from the multiple credit reporting agencies in the system, the method further includes: Obtain the data structure information of the credit data from the credit reporting agency; Based on the data structure information, create the data table corresponding to the credit reporting agency in the data warehouse; The process of storing credit data for the target user from the multiple credit reporting agencies in the system includes: From the data warehouse, identify the data table corresponding to the credit reporting agency; Credit data from the credit reporting agency is stored in the data table corresponding to the credit reporting agency.

4. The method according to claim 1, characterized in that, The acquisition of credit data for the target user includes: Incremental credit data of the target user is obtained from multiple credit reporting agencies; Obtain the existing credit data of the target user from the system; Credit data for the target user is obtained based on the incremental credit data and the existing credit data.

5. The method according to claim 1, characterized in that, Before obtaining the credit data for the target user, the process also includes: The authorization statement for the system to obtain credit data; Receive selection operation for the aforementioned authorization specification; When the selected operation represents consent to the system obtaining credit data, the step of obtaining credit data for the target user is performed.

6. A loan application processing device, characterized in that, include: The application receiving module is used to receive loan applications from target users; The data acquisition module is used to acquire credit data for the target user based on the user information of the target user, wherein the credit data comes from multiple credit reporting agencies; The standardization module is used to determine the preprocessing combination corresponding to each credit reporting agency. Using the aforementioned preprocessing combination, credit data from the credit reporting agency is preprocessed to obtain standardized credit data corresponding to the credit reporting agency; The data input module is used to input standardized credit data corresponding to each of the credit reporting agencies into the credit assessment model to obtain the output result of the credit assessment model; wherein, the credit assessment model is periodically improved using the stored user credit data, and the combination of preprocessing processes is adjusted regionally. The result determination module is used to determine the review result of the loan application based on the output result; Also includes: The combination determination module is used to obtain credit data from the target credit reporting agency; Identify multiple alternative preprocessing combinations corresponding to the target credit reporting agency; For each of the candidate preprocessing combinations: using the candidate preprocessing combination, preprocess the credit data of the target credit reporting agency to obtain standardized credit data and processing time corresponding to the candidate processing combination; determine the effect data of the standardized credit data corresponding to the candidate processing combination; Based on the processing time and effect data corresponding to each of the candidate preprocessing combinations, the preprocessing combination corresponding to the target credit reporting agency is determined from the plurality of candidate preprocessing combinations; The standardization module is specifically used for: determining at least one preprocessing information included in the preprocessing combination; for each piece of preprocessing information: determining the processing field and preprocessing method corresponding to the preprocessing information; using the preprocessing method to preprocess the data in the processing field of the target credit data, wherein the target credit data is credit data from the credit reporting agency; and determining the preprocessed target credit data as standardized credit data corresponding to the credit reporting agency. The result determination module is specifically used for: determining the scoring conditions corresponding to the loan application; determining the user score corresponding to the output result; if the user score meets the scoring conditions, determining that the review result indicates that the target user has passed the loan application; if the user score does not meet the scoring conditions, determining that the review result indicates that the target user has not passed the loan application. The standardization module is specifically used to: simulate different combinations of preprocessing processes, and determine the preprocessing combination for credit reporting agencies based on the processing time and effect data of different alternative preprocessing combinations; wherein the effect data includes: accuracy, precision, and recall.

7. The apparatus according to claim 6, characterized in that, Also includes: The storage module is used to store credit data for the target user from the multiple credit reporting agencies in the system.

8. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

9. A computer-readable medium having a computer program stored thereon, characterized in that... When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images