Post-insurance risk control method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a post-insurance risk control method and system, electronic equipment and a storage medium, and relates to the technical field of lending guarantee, and the method comprises the steps: obtaining the financial data and enterprise management data of a borrower; detecting whether malicious property transfer exists based on the financial data of the borrower; detecting whether there is an enterprise operation risk based on the financial data of the borrower and the enterprise management data; and if the malicious property transfer exists or the enterprise operation risk exists, generating risk prompt information. According to the method, an effective risk monitoring and management tool is provided through comprehensive analysis of the financial and management data of the borrower, the financial institution can be helped to better grasp the actual condition of the borrower, various possible risks can be prevented and processed in advance, then the benefits of the financial institution are protected, and the healthy development of the financial market is promoted.

Description

Technical Field

[0001] The present disclosure relates to the technical field of lending guarantees, and particularly to a post-guarantee risk control method and system, an electronic device, and a storage medium. Background Art

[0002] Artificial intelligence is a technology that simulates and extends human intelligence, aiming to create computer systems that can autonomously learn, reason, solve problems, and perform tasks. In the past few years, the progress of artificial intelligence technology has begun to change our lifestyle, and it is expected to continue to affect all aspects of our lives. A neural network model is a computational model based on artificial neurons, which mimics the connection and information transmission methods between neurons in the human brain. A neural network model usually consists of multiple hidden layers, which can help the neural network extract more complex patterns and structures from input features.

[0003] Lending guarantee refers to a mechanism in a lending relationship where, to protect the rights and interests of the lender (creditor), the borrower provides a third party or property as a guarantee for repayment. The role of the guarantee is that when the borrower fails to repay the loan on time, the lender can recover losses by recourse to the guarantor or disposal of the collateral.

[0004] Currently, the guarantor mainly conducts risk control through pre-loan review and post-loan monitoring. Post-loan monitoring mainly sets specific warning indicators (such as financial ratios, debt levels, etc.), and when these indicators reach the preset threshold, the warning mechanism is triggered. This monitoring method has many limitations.

[0005] In summary, how to apply artificial intelligence technology to post-guarantee risk control is an urgent problem to be solved. Summary of the Invention

[0006] In view of this, the embodiments of the present disclosure provide a post-guarantee risk control method and system, an electronic device, and a storage medium.

[0007] In a first aspect, the embodiments of the present disclosure provide a post-guarantee risk control method, adopting the following technical solutions:

[0008] Obtain the financial data and enterprise management data of the borrower;

[0009] Detect whether there is malicious property transfer based on the financial data of the borrower;

[0010] Detect whether there is enterprise operation risk based on the financial data and enterprise management data of the borrower;

[0011] If there is malicious property transfer or enterprise operation risk, generate a risk warning message.

[0012] As an alternative implementation, detecting whether there is malicious property transfer based on the borrower's financial data includes:

[0013] Screening large-amount expenditure data from the financial data;

[0014] Conducting large-amount property transfer detection on the large-amount expenditure data.

[0015] As an alternative implementation, detecting whether there is malicious property transfer based on the borrower's financial data further includes:

[0016] Screening the expenditure data of newly added payment accounts from the financial expenditure data after screening large-amount expenditures;

[0017] Conducting small-amount property transfer detection on the expenditure data of newly added payment accounts.

[0018] As an alternative implementation, detecting whether there is malicious property transfer based on the borrower's financial data further includes:

[0019] Detecting whether there is shareholder dividend expenditure in the financial data.

[0020] As an alternative implementation, detecting whether there is enterprise operation risk based on the borrower's financial data and enterprise management data includes:

[0021] Detecting enterprise financial operation risk based on the purchase price, sales price, sales volume, and payment collection cycle in the financial data;

[0022] Detecting enterprise management risk based on the personnel transfer and legal disputes in the enterprise management data.

[0023] In a second aspect, the embodiments of the present disclosure further provide a post-guarantee risk control system, including:

[0024] A data acquisition module, which acquires the borrower's financial data and enterprise management data;

[0025] A malicious property transfer detection module, which detects whether there is malicious property transfer based on the borrower's financial data;

[0026] An enterprise operation risk detection module, which detects whether there is enterprise operation risk based on the borrower's financial data and enterprise management data;

[0027] A risk warning information generation module, which generates risk warning information if there is malicious property transfer or enterprise operation risk.

[0028] As an alternative implementation, the malicious property transfer detection module includes:

[0029] A large-amount expenditure data screening module, which screens large-amount expenditure data from the financial data;

[0030] A large - expenditure data detection module for detecting large - scale property transfer of large - expenditure data.

[0031] As an optional implementation, the enterprise operation risk detection module includes:

[0032] An enterprise financial operation risk detection module for detecting the enterprise financial operation risk based on the purchase price, sales price, sales volume, and payment collection cycle in the financial data;

[0033] An enterprise management risk detection module for detecting the enterprise management risk based on the personnel transfer and legal disputes in the enterprise management data.

[0034] Thirdly, the embodiments of the present disclosure also provide an electronic device, adopting the following technical solutions:

[0035] The electronic device includes:

[0036] At least one processor; and,

[0037] A memory communicatively connected to the at least one processor; wherein,

[0038] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute any one of the above - mentioned post - guarantee risk control methods.

[0039] Fourthly, the embodiments of the present disclosure also provide a computer - readable storage medium, which stores computer instructions for causing a computer to execute any one of the above - mentioned post - guarantee risk control methods.

[0040] In summary, the technical effects of the post - guarantee risk control method provided by the present disclosure are as follows:

[0041] The post - guarantee risk control method provided by the present invention has remarkable practicability and foresight in the field of financial lending guarantees, and the technical effects are reflected in the following aspects:

[0042] 1. By regularly obtaining the financial data and enterprise management data of the borrower and analyzing them, this method can detect and early - warn potential malicious property transfer behaviors and enterprise operation risks, thus helping financial institutions take measures in advance to reduce losses.

[0043] 2. This method not only focuses on the analysis of financial data (such as large - scale and small - scale property transfer, price fluctuations in purchase and sales, etc.), but also combines enterprise management data (such as personnel transfer, legal disputes, etc.), providing a more comprehensive perspective for risk assessment. This comprehensive analysis can more accurately judge the operation status and risk level of the enterprise.

[0044] 3. By conducting a detailed inspection of the small - expenditure data of large - amount and newly - added accounts through specific steps, malicious behaviors that attempt to evade monitoring by splitting transactions can be effectively identified. In addition, the analytical method that combines the financial status and management status of an enterprise also helps to more accurately evaluate the actual operation of the enterprise.

[0045] 4. Since this method requires regular collection and update of data, it can achieve dynamic monitoring and evaluation of the borrower's risk status, timely adjust the risk control strategy according to the latest financial and management information, and ensure the timeliness and accuracy of risk assessment.

[0046] 5. For enterprises with normal operations, this method can more clearly display their good credit status, which helps financial institutions provide them with better quality services and support. At the same time, for enterprises with risks, timely risk warnings can enable financial institutions to take appropriate measures to avoid unnecessary economic losses, thereby improving the overall service quality and customer satisfaction.

[0047] In summary, through the comprehensive analysis of the borrower's financial and management data, this method provides an effective risk monitoring and management tool, which can help financial institutions better understand the actual situation of borrowers, prevent and handle various possible risks in advance, and thus protect the interests of financial institutions and promote the healthy development of the financial market.

[0048] The above description is only an overview of the technical solution of the present disclosure. In order to understand the technical means of the present disclosure more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present disclosure more obvious and understandable, the following preferred embodiments are specifically given and described in detail in conjunction with the accompanying drawings as follows. Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings required for the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0050] Figure 1 It is a schematic flow chart of the post - guarantee risk control method provided by the embodiment of the present disclosure;

[0051] Figure 2 It is a schematic structural diagram of the post - guarantee risk control system provided by the embodiment of the present disclosure;

[0052] Figure 3 It is a schematic structural diagram of an electronic device provided by the embodiment of the present disclosure. Detailed Embodiments

[0053] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0054] It should be clear that the implementation modes of the present disclosure are illustrated by specific specific examples below. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific implementation modes. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope protected by the present disclosure.

[0055] It should be noted that the following describes various aspects of embodiments within the scope of the appended claims. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement a device and / or practice a method. Additionally, this device and / or this method can be implemented using other structures and / or functionality in addition to one or more of the aspects described herein.

[0056] It should also be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present disclosure schematically. The diagrams only show the components related to the present disclosure rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and proportion of each component in its actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0057] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0058] Referring to Figure 1 , the first aspect of the present invention provides a post-guarantee risk control method, including:

[0059] Step S1, obtaining the financial data and enterprise management data of the borrower;

[0060] For example, financial data includes: large expenditure data, purchase price, sales price and volume, payment collection cycle, shareholder dividends, etc. Enterprise management data includes: human resource transfer, legal disputes, etc. Among them, financial data can be obtained through the enterprise's financial statements, and enterprise management data can be obtained through enterprise internal documents, publicly available information on the Internet, etc.

[0061] Step S2, detecting whether there is malicious property transfer based on the borrower's financial data;

[0062] Specifically, detecting whether there is malicious property transfer based on the borrower's financial data includes:

[0063] Screen for large expenditure data in the financial data; First of all, it should be noted that the large expenditure data here does not only refer to the data with a large amount, but refers to the data obtained by combining the amount and the receiving account for evaluation. As is well known, suppliers with long-term cooperation have their own independent business scopes and will not help with property transfer. Therefore, generally, newly added transaction accounts and overseas accounts are most likely to conduct property transfer.

[0064] For example, screening for large expenditure data in the financial data includes:

[0065] Input the amount and receiving account of each transfer record in the financial data into the large expenditure screening model to obtain the transfer records output by the model.

[0066] The large expenditure screening model can adopt machine learning methods and, combined with the borrower's historical financial data and account information, dynamically determine the reasonable expenditure threshold for each borrower. The following are the specific steps and methods for training the model:

[0067] 1. Data preparation

[0068] 1.1 Data collection

[0069] Bank statements: including all income and expenditure records.

[0070] Account information: including account type (domestic, overseas, newly established, etc.).

[0071] User background information: including income, total assets, occupation, credit score, etc.

[0072] Timestamp: record the time of each transaction.

[0073] 1.2 Data cleaning

[0074] Remove duplicate records: ensure the uniqueness of the data.

[0075] Handle missing values: fill in the missing financial data, for example, it can be filled with the median or mean.

[0076] Standardized data format: Unify time format, currency unit, etc.

[0077] 2. Feature Engineering

[0078] 2.1 Historical Expenditure Features

[0079] Largest single expenditure: The largest single expenditure amount in the history of each borrower.

[0080] Average single expenditure: The average single expenditure amount in the history of each borrower.

[0081] Expenditure standard deviation: The fluctuation of the historical expenditure amount of each borrower.

[0082] Expenditure frequency: The expenditure frequency in the history of each borrower (e.g., how many large expenditures per month).

[0083] 2.2 Account Features

[0084] Account type: Domestic account, overseas account, newly established account, etc.

[0085] Account age: The length of time since the account was created.

[0086] Account activity: The transaction frequency and amount of the account.

[0087] 2.3 User Background Features

[0088] Monthly income: The monthly income of the borrower.

[0089] Total assets: The total assets of the borrower.

[0090] Historical credit score: The credit score history of the borrower.

[0091] Occupation type: The occupation type of the borrower (e.g., civil servant, corporate employee, etc.).

[0092] 3. Model Training

[0093] 3.1 Select a Model

[0094] Regression models: Such as linear regression, support vector regression (SVR), random forest regression, etc., used to predict the dynamic threshold of large expenditures.

[0095] Classification models: Such as logistic regression, random forest, gradient boosting decision tree (GBDT), neural network, etc., used to determine whether a certain expenditure is a malicious property transfer.

[0096] 3.2 Train the Regression Model

[0097] Target variable: Set a reasonable dynamic threshold, such as 1.5 times the historical maximum expenditure or 3 times the historical average expenditure.

[0098] Input features: the historical expenditure features, account features, and user background features extracted above.

[0099] Model training: Use historical data to train a regression model so that it can dynamically predict the threshold of large expenditures based on the input features.

[0100] 4. Detect malicious property transfer

[0101] 4.1 Preprocess new financial data

[0102] Real-time data: Obtain the latest bank statements and account information of the borrower.

[0103] Feature extraction: Extract the same features as above for model prediction.

[0104] 4.2 Use the regression model to predict the threshold

[0105] Dynamic threshold prediction: Use the trained regression model to predict the large expenditure threshold for each borrower based on the new input features.

[0106] 4.3 Screen large expenditures

[0107] Automated screening: Compare the new expenditure data with the predicted dynamic threshold and screen out the expenditure records that exceed the threshold.

[0108] 4.4 Train a classification model

[0109] Target variable: Mark whether each expenditure exceeding the dynamic threshold is a malicious property transfer (1 means yes, 0 means no).

[0110] Input features: The screened large expenditure records and their features, including account type, account age, account activity, the borrower's income and assets, etc.

[0111] Model training: Use the large expenditure records and their labels in the historical data to train a classification model so that it can accurately determine whether a large expenditure is a malicious property transfer.

[0112] 5. Model evaluation and optimization

[0113] 5.1 Evaluate model performance

[0114] Accuracy: Evaluate the accuracy of the regression model and the classification model to ensure the reliability of the model's prediction results.

[0115] Recall rate and precision rate: For the classification model, evaluate its recall rate and precision rate to balance the model's detection ability and false alarm rate.

[0116] 5.2 Continuously optimize

[0117] Feature Selection: Continuously optimize the feature engineering and select more influential features.

[0118] Hyperparameter Tuning: Use methods such as cross-validation and grid search to tune the hyperparameters of the model.

[0119] Incremental Learning: As new data accumulates, perform incremental learning on the model to improve its adaptability and accuracy.

[0120] 6. Application and Monitoring

[0121] 6.1 Real-time Application

[0122] Real-time Detection System: Deploy the trained model into a real-time detection system to perform dynamic threshold prediction and malicious property transfer detection on the new expenditure data of borrowers.

[0123] Early Warning Mechanism: Set up an early warning mechanism to promptly notify the review team for further verification of large high-risk expenditures.

[0124] 6.2 Regular Monitoring

[0125] Regular Review: Regularly review the performance of the model and check for new malicious property transfer methods.

[0126] User Feedback: Collect user feedback, analyze false alarms and missed detections, and continuously improve the model.

[0127] Perform large-scale property transfer detection on large expenditure data, specifically including:

[0128] Input the expenditure amount, expenditure time, type of receiving account, opening time of receiving account, activity of receiving account, location of receiving account, and name of receiving account in the transfer record into the large-scale property transfer detection model.

[0129] For example, training the large-scale property transfer detection model includes:

[0130] 1. Data Preparation

[0131] 1.1 Data Collection

[0132] Bank Statements: Include all income and expenditure records.

[0133] Account Information: Include detailed information of the expenditure account and the receiving account.

[0134] User Background Information: Include income, total assets, occupation, credit score, etc.

[0135] External Data: Such as tax records, asset certificates, real estate transaction records, vehicle purchase records, etc. (optional).

[0136] 1.2 Data Cleaning

[0137] Remove duplicate records: Ensure data uniqueness.

[0138] Handle missing values: Fill in missing financial data, for example, using the median or mean.

[0139] Standardize data formats: Unify time formats, currency units, etc.

[0140] 2. Feature Engineering

[0141] Extract the following features for training the classification model:

[0142] 2.1 Transaction Features

[0143] Expenditure amount: The specific amount of each expenditure.

[0144] Expenditure time: The timestamp of each expenditure.

[0145] Receiving account type: Whether it is an overseas account, newly established account, supplier account, etc.

[0146] Receiving account opening time: The length of time since the receiving account was created.

[0147] Receiving account activity: The transaction frequency and amount of the receiving account.

[0148] Receiving account location: The country or region where the receiving account is located.

[0149] Receiving account name: The name of the receiving account, which can be used to identify whether it is a related party (such as relatives, friends, etc.).

[0150] 2.2 User Background Features

[0151] Monthly income: The monthly income of the borrower.

[0152] Total assets: The total assets of the borrower.

[0153] Historical credit score: The credit score history of the borrower.

[0154] Occupation category: The occupation type of the borrower.

[0155] Purpose of borrowing: The purpose of borrowing of the borrower.

[0156] Borrowing time: The borrowing time and the time window before and after it.

[0157] 2.3 Historical Transaction Features

[0158] Historical maximum single expenditure: The maximum single expenditure amount in the borrower's history.

[0159] Historical average single expenditure: The average amount of single expenditure in the borrower's history.

[0160] Historical expenditure standard deviation: The fluctuation of the borrower's historical expenditure amount.

[0161] Historical expenditure frequency: The expenditure frequency in the borrower's history (e.g., how many large expenditures per month).

[0162] Historical overseas expenditure frequency: The frequency of overseas expenditures in the borrower's history.

[0163] Historical expenditure frequency for newly established accounts: The expenditure frequency to newly established accounts in the borrower's history.

[0164] 3. Label data

[0165] 3.1 Mark large expenditures

[0166] Whether it is malicious property transfer: The label for each large expenditure, 1 indicates malicious property transfer, 0 indicates no.

[0167] Marking method: It can be marked through known cases in historical data, audit results, or expert judgment.

[0168] 4. Model selection and training

[0169] 4.1 Select model

[0170] Logistic regression: Simple and easy to interpret, suitable for the preliminary model.

[0171] Random forest: Can handle high-dimensional features and has good classification performance.

[0172] Gradient boosting: Has good performance on complex data sets.

[0173] Neural network: Can capture complex non-linear relationships and is suitable for large-scale data sets.

[0174] 4.2 Model training

[0175] Training data set: Historical large expenditure data containing the above features and labels.

[0176] Validation data set: Used to tune model hyperparameters and evaluate model performance.

[0177] Test data set: Used to finally evaluate the generalization ability of the model.

[0178] 5. Feature selection and hyperparameter tuning

[0179] 5.1 Feature selection

[0180] Importance Analysis: Use feature importance analysis (such as the feature importance of random forests, the feature importance of GBDT, etc.) to select the features that have the greatest impact on the model performance.

[0181] Recursive Feature Elimination: Gradually optimize the feature set by recursively removing the least important features.

[0182] 5.2 Hyperparameter Tuning

[0183] Grid Search: Conduct a grid search on the hyperparameters of the model to find the optimal combination of hyperparameters.

[0184] Random Search: Conduct a random search on the hyperparameters, which is applicable when the hyperparameter space is large.

[0185] Cross-Validation: Use cross-validation to evaluate the performance of different hyperparameter combinations.

[0186] 6. Model Evaluation

[0187] 6.1 Evaluation Metrics

[0188] Accuracy: The proportion of the number of correctly classified samples to the total number of samples.

[0189] Precision: The proportion of samples predicted as malicious property transfers that are actually malicious property transfers.

[0190] Recall: The proportion of samples that are actually malicious property transfers and are correctly predicted as malicious property transfers.

[0191] F1-Score: The harmonic mean of precision and recall, comprehensively evaluating the performance of the model.

[0192] 6.2 Confusion Matrix

[0193] True Positive (TP): The number of samples that are actually malicious property transfers and are correctly predicted as malicious property transfers.

[0194] False Positive (FP): The number of samples that are actually normal expenditures but are predicted as malicious property transfers.

[0195] True Negative (TN): The number of samples that are actually normal expenditures and are correctly predicted as normal expenditures.

[0196] False Negative (FN): The number of samples that are actually malicious property transfers but are predicted as normal expenditures.

[0197] 7. Model Application

[0198] 7.1 Real-Time Detection System

[0199] Data Input: Real-time obtain the new expenditure data of the borrower and extract the above features.

[0200] Threshold prediction: Use a regression model to predict the dynamic threshold.

[0201] Classification judgment: Input the expenditure data exceeding the dynamic threshold into the classification model to determine whether it is a malicious property transfer.

[0202] 7.2 Early warning mechanism

[0203] Risk scoring: Generate a risk score for each expenditure. The higher the score, the greater the risk.

[0204] Early warning notice: For high-risk expenditures, promptly notify the review team for further verification.

[0205] In one embodiment, detecting whether there is a malicious property transfer based on the borrower's financial data further includes:

[0206] After screening the financial expenditure data of large expenditures, screen the expenditure data of newly added payment accounts;

[0207] Perform small-scale property transfer detection on the expenditure data of newly added payment accounts.

[0208] Specifically, performing small-scale property transfer detection on the expenditure data of newly added payment accounts includes:

[0209] Input the amount, transaction item information, and transaction frequency in the expenditure data of the newly added payment account into the small-scale property transfer detection model. The small-scale property transfer detection model is trained through historical data and can detect whether it is a small-scale property transfer based on the above information.

[0210] Detecting whether there is a malicious property transfer based on the borrower's financial data further includes:

[0211] Detect whether there is a shareholder dividend expenditure in the financial data.

[0212] Step S3, detect whether there is an enterprise operation risk based on the borrower's financial data and enterprise management data;

[0213] Specifically, detecting whether there is an enterprise operation risk based on the borrower's financial data and enterprise management data includes:

[0214] Detect the enterprise financial operation risk based on the purchase price, sales price, sales volume, and payment collection period in the financial data; specifically, the above data can be input into the enterprise financial operation risk assessment model and the assessment data output by the model can be obtained.

[0215] Detect the enterprise management risk based on the personnel transfer and legal disputes in the enterprise management data. Specifically, when there are personnel transfers, large-scale resignations, a large number of legal disputes, and large-amount legal disputes among the enterprise's senior management, it is detected that there is an enterprise management risk.

[0216] Step S4: If there is malicious property transfer or business operation risk, generate a risk warning message. The guarantee company can take timely actions based on the risk warning message to avoid the expansion of risks.

[0217] The post-guarantee risk control method provided by the present invention has remarkable practicality and foresight in the field of financial lending guarantee. The technical effects are reflected in the following aspects:

[0218] 1. By regularly obtaining the financial data and enterprise management data of the borrower and analyzing them, this method can detect and warn potential malicious property transfer behaviors and business operation risks at an early stage, thus helping financial institutions take measures in advance to reduce losses.

[0219] 2. This method not only focuses on the analysis of financial data (such as large and small property transfers, price fluctuations in purchases and sales, etc.), but also combines enterprise management data (such as personnel transfers, legal disputes, etc.), providing a more comprehensive perspective for risk assessment. This comprehensive analysis can more accurately judge the operation status and risk level of the enterprise.

[0220] 3. By specifically detecting the small expenditure data of large and new accounts through specific steps, malicious behaviors that attempt to avoid monitoring by splitting transactions can be effectively identified. In addition, the analysis method that combines the financial status and management status of the enterprise also helps to more accurately evaluate the actual business situation of the enterprise.

[0221] 4. Since this method requires regular collection and update of data, it can realize the dynamic monitoring and assessment of the borrower's risk status, and timely adjust the risk control strategy according to the latest financial and management information to ensure the timeliness and accuracy of risk assessment.

[0222] 5. For enterprises with normal operations, this method can more clearly show their good credit status, helping financial institutions provide them with better services and support. At the same time, for enterprises with risks, timely risk warnings can enable financial institutions to take appropriate measures to avoid unnecessary economic losses, thereby improving the overall service quality and customer satisfaction.

[0223] In summary, through the comprehensive analysis of the borrower's financial and management data, this method provides an effective risk monitoring and management tool, which can help financial institutions better understand the actual situation of the borrower, prevent and handle various possible risks in advance, and thus protect the interests of financial institutions and promote the healthy development of the financial market.

[0224] On the other hand, referring to Figure 2 , the present invention provides a post-guarantee risk control system, including:

[0225] A data acquisition module that acquires the financial data and enterprise management data of the borrower.

[0226] A malicious property transfer detection module that detects whether there is malicious property transfer based on the financial data of the borrower.

[0227] An enterprise operation risk detection module that detects whether there is enterprise operation risk based on the financial data and enterprise management data of the borrower.

[0228] A risk warning information generation module that generates risk warning information if there is malicious property transfer or enterprise operation risk.

[0229] As an optional implementation, the malicious property transfer detection module includes:

[0230] A large expenditure data screening module that screens large expenditure data in the financial data.

[0231] A large expenditure data detection module that conducts large property transfer detection on the large expenditure data.

[0232] As an optional implementation, the enterprise operation risk detection module includes:

[0233] An enterprise financial operation risk detection module that detects enterprise financial operation risk based on the purchase price, sales price, sales volume, and payment collection cycle in the financial data.

[0234] An enterprise management risk detection module that detects enterprise management risk based on the personnel transfer and legal disputes in the enterprise management data.

[0235] According to an embodiment of the present disclosure, the electronic device includes a memory and a processor. The memory is used to store non-temporary computer-readable instructions. Specifically, the memory may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0236] The processor may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions. In an embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, so that the electronic device executes all or part of the steps of the post-guarantee risk control method of the foregoing embodiments of the present disclosure.

[0237] Those skilled in the art should be able to understand that, in order to solve the technical problem of how to obtain a good user experience effect, this embodiment may also include well-known structures such as communication buses and interfaces, and these well-known structures should also be included in the protection scope of this disclosure.

[0238] As Figure 3 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. It shows a schematic structural diagram of an electronic device suitable for implementing the electronic device in the embodiment of the present disclosure. Figure 3 The shown electronic device is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0239] As Figure 3 As shown, the electronic device may include a processor (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processor, ROM, and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0240] Generally, the following devices may be connected to the I / O interface: an input device including, for example, a sensor or a visual information acquisition device; an output device including, for example, a display screen; a storage device including, for example, a magnetic tape, a hard disk, etc.; and a communication device. The communication device may allow the electronic device to communicate with other devices (such as edge computing devices) wirelessly or wiredly to exchange data. Although Figure 3 the shown electronic device has various devices, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0241] Specifically, according to the embodiments of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication device, or installed from the storage device, or installed from the ROM. When the computer program is executed by the processor, all or part of the steps of the post-guarantee risk control method of the embodiments of the present disclosure are executed.

[0242] For the detailed description of this embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, and details are not repeated here.

[0243] A computer-readable storage medium according to an embodiment of the present disclosure stores non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are run by a processor, all or part of the steps of the post-guarantee risk control method of the various embodiments of the present disclosure described above are executed.

[0244] The above computer-readable storage medium includes, but is not limited to: optical storage media (such as CD-ROMs and DVDs), magneto-optical storage media (such as MOs), magnetic storage media (such as magnetic tapes or external hard drives), media with built-in rewritable non-volatile memories (such as memory cards), and media with built-in ROMs (such as ROM cartridges).

[0245] For a detailed description of this embodiment, reference may be made to the corresponding descriptions in the foregoing embodiments, and details will not be repeated here.

[0246] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. Additionally, the specific details disclosed above are only for illustrative and facilitating understanding purposes and are not limitations. The above details do not limit the present disclosure to necessarily implementing with the above specific details.

[0247] In the present disclosure, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, equipment, and systems involved in the present disclosure are only illustrative examples and do not intend to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The words "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with each other, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with each other.

[0248] In addition, as used herein, the "or" used in the listing of items starting with "at least one" indicates a separate listing, so that for example, the listing of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the term "exemplary" does not mean that the described examples are preferred or better than other examples.

[0249] It should also be noted that in the systems and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure.

[0250] Various changes, substitutions, and alterations to the technologies described herein can be made without departing from the technologies taught by the appended claims. In addition, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and acts described above. Current or later-developed processes, machines, manufactures, compositions of events, means, methods, or acts that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Accordingly, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or acts within their scope.

[0251] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0252] The above description has been presented for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.

Claims

1. A post-insurance risk control method, characterized in that: include: Obtaining financial and business management data of borrowers; Detecting whether there is malicious property transfer based on the borrower's financial data; Detecting whether there is business operation risk based on the borrower's financial data and business management data; If there is malicious property transfer or business operation risk, risk warning information will be generated.

2. The post-insurance risk control method according to claim 1, characterized in that: Detecting whether there is malicious property transfer based on the borrower's financial data includes: Screening the financial data for large expenditure data; Conduct large-value property transfer detection on large-value expenditure data.

3. The post-insurance risk control method according to claim 2, characterized in that: Detecting whether there is malicious property transfer based on the borrower's financial data also includes: After filtering out large expenditures, filter the expenditure data of newly added payment accounts in the financial expenditure data; Conduct small asset transfer detection on the spending data of newly added payment accounts.

4. The post-insurance risk control method according to claim 3 is characterized in that: Detecting whether there is malicious property transfer based on the borrower's financial data also includes: Check whether there is any shareholder dividend expenditure in the financial data.

5. The post-insurance risk control method according to claim 4 is characterized in that: Detecting whether there is business risk based on the borrower's financial data and business management data includes: Detect the financial and operating risks of the enterprise based on the purchase price, sales price, sales volume, and payment collection period in the financial data; Detect enterprise management risks based on human resource transfers and legal disputes in the enterprise management data.

6. A post-insurance risk control system, characterized in that: Data acquisition module, which acquires the borrower's financial data and enterprise management data; A malicious property transfer detection module, which detects whether there is malicious property transfer based on the borrower's financial data; An enterprise operation risk detection module detects whether there is an enterprise operation risk based on the borrower's financial data and enterprise management data; The risk warning information generation module generates risk warning information if there is malicious property transfer or business operation risk.

7. The post-insurance risk control system according to claim 6 is characterized in that: Malicious property transfer detection module includes: A large expenditure data screening module is used to screen large expenditure data from the financial data; The large expenditure data detection module performs large-value property transfer detection on large expenditure data.

8. The post-insurance risk control system according to claim 7 is characterized in that: The enterprise operation risk detection module includes: An enterprise financial operation risk detection module detects the enterprise financial operation risk based on the purchase price, sales price and sales volume, and payment collection period in the financial data; The enterprise management risk detection module detects enterprise management risks based on human resource transfers and legal disputes in the enterprise management data.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the post-insurance risk control method described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the post-insurance risk control method described in any one of claims 1-5.

Images