Intelligent public accumulation fund loan approval system, method and equipment based on interpretation of pedestrian credit, and readable storage medium

Abstract

The invention discloses an intelligent public accumulation fund loan approval system, method and device based on interpretation of pedestrian credit investigation and a readable storage medium. In the system, a credit investigation data acquisition module is used for acquiring credit investigation data of a borrower and a common borrower through a central bank credit investigation system; the customer information acquisition module is used for acquiring public accumulation fund loan related data through the public accumulation fund center system; the threshold rule evaluation module is used for analyzing the debt condition and the repayment record of the borrower by verifying the collected data to obtain an auditing result; the approval report generation module is used for screening related data of borrowers and generating a public accumulation fund loan approval report in combination with an audit result; and the loan data pushing module is used for pushing loan information and repayment information related to the borrowers to the central bank credit investigation system after the public accumulation fund loans. According to the method, the problems of low data integration efficiency, different auditing standards, overlong manual auditing time and information leakage risk existing in the existing public accumulation fund loan approval process are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of credit assessment and risk management, and in particular to an intelligent approval system, method, device and readable storage medium for provident fund loans based on interpretation of the credit information of the People's Bank of China. Background Art

[0002] In the traditional housing fund loan approval process, manual review is the core link. This process usually relies on manual operation and subjective judgment of the person in charge. The process is as follows:

[0003] 1. Loan application submission: The borrower submits a loan application to the Provident Fund Center or bank and provides relevant materials, including proof of income, credit report, provident fund payment certificate, etc.

[0004] 2. Loan approval: After the borrower submits the application, the staff of the Provident Fund Center will review the credit report to determine the borrower's credit risk and loan eligibility.

[0005] Manual review is the main method in the traditional loan process, but it has many problems and disadvantages, including:

[0006] 1. Inefficiency: Manual review takes a long time, especially when the borrower's credit data is complex or the materials are incomplete, and it may take multiple rounds to supplement the materials. Since the data needs to be manually compared and processed, the whole process may be delayed for days or even weeks.

[0007] 2. Error-prone: The accuracy of manual operations depends on the experience and meticulousness of the auditors. Faced with a large number of loan applications, auditors are prone to fatigue, resulting in missed inspections and wrong inspections. For example, the overdue situation in the credit report may not be correctly identified, or the debt ratio may be calculated incorrectly, which may lead to deviations in the approval results.

[0008] 3. Low transparency: Since the decision-making process of manual review mainly relies on manual experience and judgment, the entire process lacks transparency, and it is difficult for applicants to understand the specific reasons for rejection or approval. This situation not only reduces the user experience, but is also not conducive to subsequent auditing and supervision.

[0009] 4. High cost: Manual review requires a lot of manpower input, especially for the processing of a large number of loan applications, banks and provident fund centers need to be equipped with sufficient reviewers, which increases operating costs. In addition, training qualified reviewers also takes time and money.

[0010] 5. Difficulty in dealing with complex data: As the credit data of loan applicants becomes more and more complex, it is difficult for auditors to quickly and comprehensively process large amounts of data, especially multi-dimensional data comparisons, such as multiple loans, credit card bills, debt ratios, etc., which can easily lead to information omissions or misjudgments.

[0011] 6. Highly subjective: Reviewers have a certain amount of subjective judgment space when approving applications, and different applicants may have different assessments of the risks of the same application. This kind of artificial subjective factor increases the inconsistency of approval and may cause similar applicants to receive different approval results.

[0012] The Chinese patent with publication number CN117035996A discloses a method, system, device and medium for loan evaluation based on provident fund, the method includes: step S10, the credit server creates a loan evaluation model based on neural network, and trains the loan evaluation model based on loan history data and provident fund history data; step S20, after the mobile terminal performs login verification, it sends a loan request to the credit server based on the input loan application information; step S30, the credit server obtains provident fund payment data through the provident fund server based on the received loan request; step S40, the credit server inputs the loan application information and provident fund payment data into the loan evaluation model, obtains the loan credit limit and feeds it back to the mobile terminal; step S50, the mobile terminal receives and displays the loan credit limit, and performs the loan operation based on the loan credit limit. Although the invention uses neural network and provident fund data for loan evaluation, it cannot accurately evaluate the overall credit risk of the borrower by relying solely on provident fund data. Summary of the invention

[0013] The present invention provides an intelligent housing provident fund loan approval system, method, device and readable storage medium based on interpreting the credit information of the People's Bank of China, aiming to solve the problems of low data integration efficiency, inconsistent review standards, long manual review time and information leakage risk in the existing housing provident fund loan approval process.

[0014] In order to solve the above technical problems, the present invention provides an intelligent approval system for provident fund loans based on interpreting the credit information of the People's Bank of China. The system is communicated with the credit information system of the central bank and the provident fund center system, and includes a credit information data collection module, a customer information collection module, a threshold rule evaluation module, an approval report generation module and a loan data push module.

[0015] The credit data collection module is used to obtain the credit data of the borrower and co-borrowers through the central bank's credit system after the borrower's authorization.

[0016] The customer information collection module is used to obtain provident fund loan related data through the provident fund center system after the borrower's authorization.

[0017] The threshold rule evaluation module is used to calculate the borrower's debt situation and analyze the borrower's repayment record by verifying the credit data and provident fund loan-related data, and obtain the review result of the borrower's application for provident fund loan.

[0018] The approval report generation module is used to screen the relevant data of the borrower and generate a provident fund loan approval report based on the review results of the threshold rule evaluation module.

[0019] The loan data push module is used to clean and format the borrower's related loan information and repayment information after the provident fund loan is disbursed. After verifying the integrity and accuracy of the data, the borrower's related loan information and repayment information are automatically pushed to the central bank's credit reporting system. At the same time, an overdue grace mechanism is set to adjust the interval number of days for pushing the borrower's overdue information according to demand.

[0020] Preferably, the credit data collected by the credit data collection module includes at least: credit loan related data, credit card account, repayment history, overdue status, debt status, repayment ability account, and five-level classified non-essential related data; the provident fund loan related data collected by the customer information collection module includes at least: provident fund contribution base, loan amount, repayment method, loan term, and loan interest rate.

[0021] Preferably, the verification of credit investigation data and provident fund loan related data in the threshold rule evaluation module is specifically as follows:

[0022] According to the policy requirements of the Provident Fund Center, check whether the borrower's credit data meets the Provident Fund loan application standards. If the borrower's credit data and Provident Fund loan-related data are in any of the abnormal states, including bad debt status, abnormal status of the five-level classification, and Provident Fund loan outstanding status, the review result of rejecting the Provident Fund loan application will be directly obtained.

[0023] The bad debt status refers to the credit loan or credit card account shown as a bad debt status in the borrower's credit data.

[0024] The five-level classification abnormal status refers to the credit loan or credit card account in the borrower's credit data being classified into an abnormal status including attention, substandard, doubtful, and loss.

[0025] The unsettled provident fund status refers to the unsettled loan amount in the borrower's provident fund loan related data.

[0026] Preferably, the calculation of the debt situation of the borrower in the threshold rule evaluation module is specifically as follows:

[0027] Based on the credit data and provident fund loan related data, the borrower's family's monthly debt and monthly income data are calculated, the ratio of the borrower's family's monthly debt to monthly income is evaluated, and it is determined whether the borrower has the ability to repay, and the review result of the provident fund loan application is obtained.

[0028] The specific rules for judging whether the borrower has the repayment ability are as follows: setting the passing percentage and the warning percentage. If the product of the monthly family income and the passing percentage is greater than the monthly family debt, the audit result is passed; if the monthly family debt is between the product of the monthly family income and the passing percentage and the product of the monthly family income and the warning percentage, the audit result is passed, but a warning is given; if the monthly family debt exceeds the monthly family income, the audit result is a rejection of the application for provident fund loan.

[0029] Preferably, the monthly family income data is composed of the income of the borrower and the co-borrower, which is obtained from the provident fund payment base; the monthly family debt data is composed of the following four parts:

[0030] The monthly loan payment amount for the borrower and co-borrowers.

[0031] The credit card balance owed by the borrower and co-borrower is multiplied by a set coefficient, where the set coefficient is 1 / number of loan terms, which represents the monthly debt amount converted from the credit card balance for the same number of loan terms.

[0032] The monthly repayment amount of the credit guarantee of the borrower and co-borrower is multiplied by a set coefficient, where the set coefficient is the average amount of default compensation divided by the average guarantee amount.

[0033] The monthly repayment amount of the borrower's provident fund loan is calculated based on the loan amount, loan term, repayment method and loan interest rate; if it is a provident fund combination loan, the monthly commercial loan repayment amount is also calculated.

[0034] Preferably, the threshold rule evaluation module analyzes the borrower's repayment record specifically as follows:

[0035] For each type of loan of the borrower, the overdue warning period and overdue rejection period are preset: the overdue warning period = overdue warning coefficient * default probability, the overdue rejection period = expected rejection coefficient * default probability. The overdue warning coefficient and overdue rejection coefficient of different types of loans are set according to the policy of the Provident Fund Center; the default probability = number of defaulting borrowers / total number of borrowers in the same risk group.

[0036] If the number of overdue periods exceeds the number of overdue warning periods but does not exceed the number of overdue rejection periods, the audit result is passed but a warning is given; if the number of overdue periods exceeds the number of overdue rejection periods, the audit result of directly rejecting the provident fund loan application is obtained.

[0037] Preferably, the approval report generation module screens the relevant data of the borrower and generates a housing fund loan approval report in combination with the review results of the threshold rule evaluation module, specifically:

[0038] The borrower's credit data and loan information are screened, and sensitive information not related to the provident fund loan approval is filtered out. The key indicators required for the provident fund loan approval report are extracted according to the "minimum necessary principle". The key indicators include at least: monthly debt ratio, credit card account, repayment history, overdue status, repayment ability account, and five-level classification of non-essential related data.

[0039] Combined with the review results of the threshold rule evaluation module, a provident fund loan approval report is generated.

[0040] On the other hand, the present invention provides a method for intelligent approval of provident fund loans based on interpretation of the credit information of the People's Bank of China, comprising the following steps:

[0041] After the borrower's authorization, the credit data of the borrower and co-borrowers will be obtained through the central bank's credit reporting system.

[0042] After the borrower's authorization, provident fund loan related data can be obtained through the provident fund center system.

[0043] By verifying the credit data and provident fund loan-related data, calculating the borrower's debt situation and analyzing the borrower's repayment record, the review result of the borrower's application for provident fund loan is obtained.

[0044] The relevant data of the borrower is screened, and the review results of the threshold rule evaluation module are combined to generate a provident fund loan approval report.

[0045] After the provident fund loan is disbursed, the borrower's related loan and repayment information will be cleaned and formatted. After verifying the integrity and accuracy of the data, the borrower's related loan and repayment information will be automatically pushed to the central bank's credit reporting system. At the same time, a late payment grace mechanism will be set up to adjust the number of days between pushes of borrower overdue information as needed, so as to improve the flexibility of the push frequency and the timeliness of credit data updates.

[0046] On the other hand, the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the intelligent approval method for provident fund loans based on interpretation of the credit report of the People's Bank of China as described in any embodiment of the present invention when executing the computer program.

[0047] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent approval method for provident fund loans based on interpretation of the credit information of the People's Bank of China as described in any embodiment of the present invention.

[0048] Compared with the prior art, the present invention has the following technical effects:

[0049] 1. Automatically acquire and process the credit data and housing fund loan information of customers, and use the threshold rule model for evaluation, which significantly reduces manual operations and approval time. In addition, the system of the present invention can process multiple tasks in parallel, realize asynchronous credit data acquisition and analysis, eliminate bottlenecks in the process, and improve the overall approval speed.

[0050] 2. By introducing the threshold rule model, the customer's credit report and loan information can be accurately analyzed. Unlike manual review, the system of the present invention can standardize the assessment of the customer's debt ratio, overdue situation and repayment ability, ensure the consistency and objectivity of the review results, reduce the errors caused by manual subjective judgment, avoid the omission or misdetection that is easy to occur in manual review, and the automated processing eliminates the details that are easily overlooked or misunderstood in the manual processing process, ensuring the comprehensiveness and accuracy of the approval report.

[0051] 3. Adopt the "minimum necessary principle" to display customer data, ensuring that only necessary information is displayed during the approval process, and other sensitive data not related to the approval is deleted, which greatly reduces the risk of leakage of customer privacy information and improves customer data security through privacy data separation and encryption. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is the overall structure diagram of the intelligent approval system for provident fund loans based on interpreting the credit information of the People's Bank of China according to the present invention;

[0053] Figure 2 It is an overall flow chart of the intelligent approval method for provident fund loans based on interpreting the credit information of the People's Bank of China described in the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in combination with specific embodiments of the present application and with reference to the accompanying drawings.

[0055] Embodiment 1

[0056] This embodiment provides a housing fund loan intelligent approval system based on the interpretation of the People's Bank of China's credit information. Through intelligent means, an efficient and safe housing fund loan approval process is realized, loan processing efficiency is improved, errors caused by manual operations are reduced, and customer privacy data is protected. The system is connected to the central bank's credit system and the housing fund center system. Figure 1 As shown, it includes a credit data collection module, a customer information collection module, a threshold rule evaluation module, an approval report generation module and a loan data push module.

[0057] The credit data collection module is used to obtain the credit data of the borrower and co-borrowers through the central bank's credit system after the borrower authorizes it. Specifically, the borrower fills in relevant information through the system and authorizes the credit. After the borrower authorizes it, this module is responsible for sending a request to the central bank's credit system interface to asynchronously obtain credit data and parse the credit data into structured data that can be used for threshold rule evaluation and analysis.

[0058] The customer information collection module is used to obtain the provident fund loan related data through the provident fund center system after the borrower's authorization. Specifically, this module obtains the borrower's provident fund loan related data from the database of the provident fund center, and associates the provident fund loan related data with the credit data to ensure data consistency.

[0059] The threshold rule evaluation module is used to calculate the borrower's debt situation and analyze the borrower's repayment record by verifying the credit data and provident fund loan related data, and obtain the review result of the borrower's application for provident fund loan. The review results include three results: passed, passed but with a warning, and rejected. If the review result is rejected or passed but with a warning, the corresponding reasons for rejection or warning triggering are recorded at the same time.

[0060] The approval report generation module is used to screen the relevant data of the borrower and generate a provident fund loan approval report based on the review results of the threshold rule evaluation module.

[0061] The loan data push module is used to clean and format the loan information and repayment information related to the borrower after the provident fund loan is disbursed. After verifying the integrity and accuracy of the data, the borrower's loan information and repayment information (including loan amount, loan term, repayment status and overdue situation, etc.) are automatically pushed to the central bank's credit reporting system. At the same time, an overdue grace mechanism is set to adjust the interval between the borrower's overdue information push according to demand, so as to optimize and improve the flexibility of the push frequency and the timeliness of credit data update according to actual needs. This module is triggered after the provident fund loan is disbursed to ensure that the borrower's credit information is updated in a timely manner to achieve the purpose of real-time credit reporting.

[0062] As a preferred implementation mode of this embodiment, the credit data collected by the credit data collection module includes at least: credit loan related data, credit card account, repayment history, overdue status, debt status, repayment ability account, and five-level classified non-essential related data; the provident fund loan related data collected by the customer information collection module includes at least: provident fund contribution base, loan amount, repayment method, loan term, and loan interest rate.

[0063] As a preferred implementation of this embodiment, the verification of credit information data and provident fund loan related data in the threshold rule evaluation module is specifically as follows:

[0064] According to the policy requirements of the Provident Fund Center, check whether the borrower's credit data meets the Provident Fund loan application standards. If the borrower's credit data and Provident Fund loan-related data are in any of the abnormal states, including bad debt status, abnormal status of the five-level classification, and Provident Fund loan outstanding status, the review result of rejecting the Provident Fund loan application will be directly obtained.

[0065] The bad debt status refers to the credit loan or credit card account shown as a bad debt status in the borrower's credit data.

[0066] The five-level classification abnormal status refers to the credit loan or credit card account in the borrower's credit data being classified into an abnormal status including attention, substandard, doubtful, and loss.

[0067] The unsettled provident fund status refers to the unsettled loan amount in the borrower's provident fund loan related data.

[0068] As a preferred implementation of this embodiment, the threshold rule evaluation module evaluates the ratio of the borrower's family's monthly debt to monthly income, calculates the borrower's debt situation, and determines the repayment ability specifically as follows:

[0069] Based on the credit data and provident fund loan related data, the borrower's family's monthly debt and monthly income data are calculated, the ratio of the borrower's family's monthly debt to monthly income is evaluated, and it is determined whether the borrower has the ability to repay, and the review result of the provident fund loan application is obtained.

[0070] The specific rules for judging whether the borrower has the repayment ability are as follows: setting the passing percentage and the warning percentage. If the product of the monthly family income and the passing percentage is greater than the monthly family debt, the audit result is passed; if the monthly family debt is between the product of the monthly family income and the passing percentage and the product of the monthly family income and the warning percentage, the audit result is passed, but a warning is given; if the monthly family debt exceeds the monthly family income, the audit result is a rejection of the application for provident fund loan.

[0071] As a preferred implementation of this embodiment, the family monthly income data is composed of the income of the borrower and the co-borrower, which can be obtained from the provident fund payment base, and can also be entered from the payroll or other income certificates in specific implementation. The family monthly debt data consists of the following four parts:

[0072] The monthly loan payment amount for the borrower and co-borrowers.

[0073] The credit card balance of the borrower and co-borrower is multiplied by the set coefficient, where the set coefficient is 1 / number of loan terms, which represents the monthly debt amount converted from the credit card balance for the same number of loan terms. The purpose is to spread the credit card balance over the entire provident fund loan period and calculate the monthly impact on the debt.

[0074] The monthly repayment amount of the credit guarantee of the borrower and co-borrower is multiplied by a set coefficient, where the set coefficient is the average amount of default compensation / average guarantee amount. This coefficient is used to convert the actual repayment liability that the borrower may bear after the guaranteed loan defaults, thereby evaluating the impact of monthly liabilities.

[0075] The monthly repayment amount of the borrower's provident fund loan is calculated based on the loan amount, loan term, repayment method and loan interest rate; if it is a provident fund combination loan, the monthly commercial loan repayment amount is also calculated.

[0076] As a preferred implementation of this embodiment, the threshold rule evaluation module analyzes the borrower's repayment record specifically as follows:

[0077] For various types of loans of borrowers (such as student loans, other commercial loans, and credit card loans, etc.), the number of overdue warning periods and overdue rejection periods are preset: the number of overdue warning periods = overdue warning coefficient * default probability, the number of overdue rejection periods = expected rejection coefficient * default probability. The overdue warning coefficient and overdue rejection coefficient of different types of loans are set according to the policies of the Provident Fund Center; the default probability = the number of defaulting borrowers / the total number of borrowers in the same risk group. Specifically, for each specific loan risk group, the actual default ratio is calculated. For example, if there are 100 borrowers in a 3-period overdue state, and 30 of them eventually default, then the default probability of 3-period overdue is 30%.

[0078] If the number of overdue periods exceeds the number of overdue warning periods but does not exceed the number of overdue rejection periods, the audit result is passed but a warning is given; if the number of overdue periods exceeds the number of overdue rejection periods, the audit result of directly rejecting the provident fund loan application is obtained.

[0079] As a preferred implementation of this embodiment, the approval report generation module screens the relevant data of the borrower and generates a housing fund loan approval report in combination with the review results of the threshold rule evaluation module, specifically:

[0080] The borrower's credit data and loan information are screened, and sensitive information not related to the provident fund loan approval is filtered out (for example, the customer's specific account details, personal address and other information will not be included in the approval report). The key indicators required for the provident fund loan approval report are extracted according to the "minimum necessary principle". The key indicators include at least: monthly debt ratio, credit card account, repayment history, overdue situation, repayment ability account, and five-level classification of non-essential related data.

[0081] Combined with the review results of the threshold rule evaluation module, a housing fund loan approval report is generated. The approval report is presented to the housing fund loan approval personnel through the system interface and provides detailed analysis results to facilitate final decision making.

[0082] As a preferred implementation of this embodiment, the system also includes a security audit module for recording the operation log of each approval step to ensure the compliance of provident fund loan approval. All operations are traceable, which is convenient for later supervision and security audit, meets the audit requirements of the financial industry, and improves the transparency and controllability of intelligent approval.

[0083] Embodiment 2

[0084] Accordingly, this embodiment provides a method for intelligent approval of provident fund loans based on interpretation of the credit information of the People's Bank of China. The method is implemented based on the intelligent approval system for provident fund loans based on interpretation of the credit information of the People's Bank of China described in Embodiment 1. Figure 2 As shown, the following steps are included:

[0085] After the borrower's authorization, the credit data of the borrower and co-borrowers will be obtained through the central bank's credit reporting system.

[0086] After the borrower's authorization, provident fund loan related data can be obtained through the provident fund center system.

[0087] By verifying the credit data and provident fund loan-related data, calculating the borrower's debt situation and analyzing the borrower's repayment record, the review result of the borrower's application for provident fund loan is obtained.

[0088] The relevant data of the borrower is screened, and the review results of the threshold rule evaluation module are combined to generate a provident fund loan approval report.

[0089] After the provident fund loan is disbursed, the borrower's related loan and repayment information will be cleaned and formatted. After verifying the integrity and accuracy of the data, the borrower's related loan and repayment information will be automatically pushed to the central bank's credit reporting system. At the same time, a late payment grace mechanism will be set up to adjust the number of days between pushes of the borrower's overdue information as needed.

[0090] Embodiment 3

[0091] This embodiment provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the intelligent approval method for provident fund loans based on interpretation of the credit information of the People's Bank of China as described in any embodiment of the present invention.

[0092] Embodiment 4

[0093] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for intelligent approval of provident fund loans based on interpretation of the credit information of the People's Bank of China as described in any embodiment of the present invention is implemented.

[0094] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0095] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] In several embodiments provided in the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0098] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent housing fund loan approval system based on interpreting the credit report of the People's Bank of China, characterized by: The system is connected to the central bank's credit reporting system and the provident fund center system, and includes a credit reporting data collection module, a customer information collection module, a threshold rule evaluation module, an approval report generation module, and a loan data push module; The credit data collection module is used to obtain the credit data of the borrower and co-borrowers through the central bank's credit system after the borrower authorizes it; The customer information collection module is used to obtain housing provident fund loan-related data through the housing provident fund center system after the borrower's authorization; The threshold rule evaluation module is used to calculate the borrower's debt situation and analyze the borrower's repayment record by verifying the credit data and provident fund loan-related data, and obtain the review result of the borrower's application for provident fund loan; The approval report generation module is used to screen the relevant data of the borrower and generate a housing fund loan approval report based on the review results of the threshold rule evaluation module; The loan data push module is used to clean and format the borrower's related loan information and repayment information after the provident fund loan is disbursed. After verifying the integrity and accuracy of the data, the borrower's related loan information and repayment information are automatically pushed to the central bank's credit reporting system. At the same time, an overdue grace mechanism is set to adjust the interval number of days for pushing the borrower's overdue information according to demand.

2. The intelligent approval system for provident fund loans based on interpreting the credit report of the People's Bank of China according to claim 1 is characterized in that: The credit data collected by the credit data collection module includes at least: credit loan related data, credit card account, repayment history, overdue status, debt status, repayment ability account, and five-level classified non-essential related data; the provident fund loan related data collected by the customer information collection module includes at least: provident fund contribution base, loan amount, repayment method, loan term, and loan interest rate.

3. The intelligent approval system for provident fund loans based on interpreting the credit report of the People's Bank of China according to claim 2 is characterized in that: The specific verification of credit investigation data and provident fund loan related data in the threshold rule evaluation module is: According to the policy requirements of the Housing Provident Fund Center, check whether the borrower's credit data meets the housing provident fund loan application standards. If the borrower's credit data and housing provident fund loan-related data are in any abnormal state, such as bad debt status, abnormal status of the five-level classification, or housing provident fund loan unsettled status, the application for housing provident fund loan will be directly rejected; The bad debt status refers to the credit loan or credit card account shown as a bad debt status in the borrower's credit data; The five-level classification abnormal status refers to the abnormal status of the credit loan or credit card account in the borrower's credit data being classified as special mention, substandard, doubtful, and loss; The provident fund unsettled status refers to the unsettled loan amount in the borrower's provident fund loan related data.

4. The intelligent housing fund loan approval system based on interpreting the credit report of the People's Bank of China according to claim 2 is characterized in that: The calculation of the borrower's debt situation in the threshold rule evaluation module is specifically as follows: Calculate the monthly debt and monthly income data of the borrower's family based on the credit data and the data related to the provident fund loan, evaluate the ratio of the monthly debt and monthly income of the borrower's family, determine whether the borrower has the repayment ability, and obtain the review result of the application for the provident fund loan; The specific rules for judging whether the borrower has the repayment ability are as follows: setting the passing percentage and the warning percentage. If the product of the monthly family income and the passing percentage is greater than the monthly family debt, the audit result is passed; if the monthly family debt is between the product of the monthly family income and the passing percentage and the product of the monthly family income and the warning percentage, the audit result is passed, but a warning is given; if the monthly family debt exceeds the monthly family income, the audit result is a rejection of the application for provident fund loan.

5. The intelligent housing fund loan approval system based on interpreting the credit report of the People's Bank of China according to claim 4 is characterized in that: The monthly household income data is composed of the income of the borrower and the co-borrower, and is obtained from the provident fund payment base; The monthly household debt data consists of the following four parts: The monthly loan repayment amount of the borrower and co-borrower; The credit card balance owed by the borrower and co-borrower is multiplied by a set coefficient, where the set coefficient is 1 / number of loan terms, which represents the monthly debt amount of the credit card balance converted into the same number of loan terms; The monthly repayment amount of the credit guarantee of the borrower and the co-borrower is multiplied by a set coefficient, where the set coefficient is the average amount of default compensation / average guarantee amount; The monthly repayment amount of the borrower's provident fund loan is calculated based on the loan amount, loan term, repayment method and loan interest rate; if it is a provident fund combination loan, the monthly commercial loan repayment amount is also calculated.

6. The intelligent housing fund loan approval system based on interpreting the credit report of the People's Bank of China according to claim 1 is characterized in that: The threshold rule evaluation module analyzes the borrower's repayment record specifically as follows: For each type of loan of the borrower, the number of overdue warning periods and overdue rejection periods are preset: the number of overdue warning periods = overdue warning coefficient * default probability, the number of overdue rejection periods = expected rejection coefficient * default probability. The overdue warning coefficient and overdue rejection coefficient of different types of loans are set according to the policy of the Provident Fund Center; the default probability = the number of defaulting borrowers / the total number of borrowers in the same risk group; If the number of overdue periods exceeds the number of overdue warning periods but does not exceed the number of overdue rejection periods, the audit result is passed but a warning is given; if the number of overdue periods exceeds the number of overdue rejection periods, the audit result of directly rejecting the provident fund loan application is obtained.

7. The intelligent housing fund loan approval system based on interpreting the credit report of the People's Bank of China according to claim 1 is characterized in that: The approval report generation module screens the borrower's relevant data and generates a housing fund loan approval report based on the review results of the threshold rule evaluation module: Screen the borrower's credit data and loan information, filter out sensitive information that is not related to the housing fund loan approval, and extract the key indicators required for the housing fund loan approval report based on the "minimum necessary principle". The key indicators include at least: monthly debt ratio, credit card account, repayment history, overdue situation, repayment ability account, and five-level classification of non-essential related data; Combined with the review results of the threshold rule evaluation module, a provident fund loan approval report is generated.

8. An intelligent housing fund loan approval method based on interpreting the credit report of the People's Bank of China, characterized by: The method is implemented based on the intelligent approval system for provident fund loans based on interpretation of the credit information of the People's Bank of China according to any one of claims 1 to 7, and comprises the following steps: After the borrower authorizes, the credit data of the borrower and co-borrowers are obtained through the central bank's credit reporting system; After the borrower's authorization, obtain the relevant data of provident fund loans through the provident fund center system; By verifying the credit data and the data related to provident fund loans, the borrower's debt situation is calculated, and the borrower's repayment record is analyzed to obtain the review results of the borrower's application for provident fund loans; Screen the relevant data of the borrower and generate a housing fund loan approval report based on the review results of the threshold rule evaluation module; After the provident fund loan is disbursed, the borrower's related loan and repayment information will be cleaned and formatted. After verifying the integrity and accuracy of the data, the borrower's related loan and repayment information will be automatically pushed to the central bank's credit reporting system. At the same time, a late payment grace mechanism will be set up to adjust the number of days between pushes of the borrower's overdue information as needed.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the intelligent approval method for provident fund loans based on interpretation of the credit information of the People's Bank of China as described in claim 8 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the intelligent approval method for provident fund loans based on interpretation of the credit information of the People's Bank of China as described in claim 8 is implemented.

Images