Intelligent enterprise risk assessment method and system based on big data

Abstract

The embodiment of the invention discloses an enterprise risk intelligent assessment method and system based on big data, electronic equipment and a storage medium, and relates to the technical field of finance, and the method comprises the steps: obtaining a loan amount, financial data of a to-be-assessed enterprise, a credit record and industry data; analyzing based on the loan amount, the financial data, the credit record and the industry data, and generating a risk score and a basis for manual auditing; and obtaining an adjustment basis during manual auditing, and regenerating the score according to the adjusted basis. According to the enterprise risk intelligent assessment method based on big data provided by the invention, a comprehensive and accurate risk assessment result is provided through multi-dimensional data collection and comprehensive analysis of multiple assessment models. The method not only improves the evaluation efficiency, but also ensures the rationality and scientificity of the evaluation result through the intervention of a manual auditing link.

Description

Technical Field

[0001] The present disclosure relates to the field of information screening technology, and particularly to an intelligent enterprise risk assessment method and system, an electronic device, and a storage medium based on big data. Background Art

[0002] Pre-loan assessment refers to a series of comprehensive assessments carried out by credit institutions on the credit status, repayment ability, loan purpose, etc. of borrowers before lending loans to them. This process aims to ensure the safety, rationality, and sustainability of loans, reduce credit risks, and safeguard the capital security of credit institutions and the financial health of borrowers.

[0003] 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 way of life, and it is expected to continue to affect all aspects of our lives.

[0004] Currently, pre-loan assessment generally mainly focuses on credit investigation for assessment, lacking comprehensive assessments in other dimensions, and the assessment results are inaccurate.

[0005] In summary, how to apply artificial intelligence technology to the intelligent enterprise risk assessment based on big data to obtain more accurate assessment results is an urgent problem to be solved. Summary of the Invention

[0006] In view of this, the embodiments of the present disclosure provide an intelligent enterprise risk assessment method and system, an electronic device, and a storage medium based on big data, which perform intelligent enterprise risk assessment based on big data through artificial intelligence technology.

[0007] In a first aspect, the embodiments of the present disclosure provide an intelligent enterprise risk assessment method based on big data, adopting the following technical solutions:

[0008] Obtain the loan amount, financial data, credit record, and industry data of the enterprise to be evaluated;

[0009] Analyze based on the loan amount, financial data, credit record, and industry data to generate a risk score and basis for manual review;

[0010] Obtain the basis adjusted during manual review and regenerate the score according to the adjusted basis.

[0011] As an optional implementation manner, the analysis based on the loan amount, financial data, credit record, and industry data to generate a risk score and basis includes:

[0012] Use a fixed asset evaluation model to evaluate according to the loan amount and financial data, and generate corresponding scores and basis;

[0013] Use the cash - flow evaluation model to evaluate according to the financial data, and generate the corresponding scores and bases.

[0014] Use the credit evaluation model to evaluate according to the credit records, and generate the corresponding scores and bases.

[0015] Use the enterprise development evaluation model to evaluate according to the industry data, and generate the corresponding scores and bases.

[0016] Obtain and summarize the scores and bases output by each evaluation model respectively.

[0017] As an optional implementation method, using the cash - flow evaluation model to evaluate according to the financial data and generate the corresponding scores and bases includes:

[0018] Clean the financial data.

[0019] Input the total cash flow, revenue sources, and fixed expenses in the cleaned financial data into the cash - flow evaluation model.

[0020] Obtain the scores and bases generated by the model.

[0021] As an optional implementation method, using the enterprise development evaluation model to evaluate according to the industry data includes:

[0022] Clean the industry data.

[0023] Input the industry average profit rate, industry growth trend, policy support strength, industry cyclical characteristics, and market competition status in the cleaned industry data into the enterprise development evaluation model.

[0024] Obtain the scores and bases generated by the model.

[0025] As an optional implementation method, it also includes:

[0026] Classify and store the bases adjusted during manual review based on the adjustment reasons.

[0027] Optimize the model based on the classified bases.

[0028] As an optional implementation method, the adjustment reasons include: data quality, feature importance;

[0029] Optimizing the model based on the classified bases includes:

[0030] Improve the data quality based on the bases of the data quality category.

[0031] Adjust the feature weights based on the bases of the feature importance category.

[0032] Retrain the model using the improved data and features.

[0033] In a second aspect, an embodiment of the present disclosure further provides an enterprise risk intelligent assessment system based on big data, including:

[0034] A data acquisition module that acquires the loan amount, financial data, credit records, and industry data of the enterprise to be evaluated;

[0035] An analysis module that analyzes based on the loan amount, financial data, credit records, and industry data to generate a risk score and basis for manual review;

[0036] A score regeneration module that acquires the basis adjusted during manual review and regenerates the score according to the adjusted basis.

[0037] As an optional implementation, the analysis module includes:

[0038] A fixed asset evaluation module that uses a fixed asset evaluation model to evaluate based on the loan amount and financial data to generate corresponding scores and basis;

[0039] A cash flow evaluation module that uses a cash flow evaluation model to evaluate based on financial data to generate corresponding scores and basis;

[0040] A credit evaluation module that uses a credit evaluation model to evaluate based on credit records to generate corresponding scores and basis;

[0041] An enterprise development evaluation module that uses an enterprise development evaluation model to evaluate based on industry data to generate corresponding scores and basis;

[0042] A summary module that respectively acquires the scores and basis output by each evaluation model and summarizes them.

[0043] In a third aspect, an embodiment of the present disclosure further provides an electronic device, adopting the following technical solution:

[0044] The electronic device includes:

[0045] At least one processor; and,

[0046] A memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores instructions executable 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 any one of the above-mentioned enterprise risk intelligent assessment methods based on big data.

[0048] Fourthly, the embodiments of the present disclosure also provide a computer-readable storage medium storing computer instructions for causing a computer to execute the above-mentioned intelligent enterprise risk assessment method based on big data.

[0049] In summary, the technical effects of the intelligent enterprise risk assessment method based on big data provided by the present disclosure are as follows:

[0050] Through multi-dimensional data collection and comprehensive analysis of multiple evaluation models, comprehensive and accurate risk assessment results are provided. This method not only improves the evaluation efficiency, but also ensures the rationality and scientificity of the evaluation results through the intervention of the manual review link. Specifically, the advantages of this method are as follows:

[0051] 1. Comprehensiveness: Comprehensive consideration of financial data, credit records, and industry data ensures the comprehensiveness of the evaluation results.

[0052] 2. Accuracy: The combined use of multiple evaluation models improves the accuracy and reliability of the evaluation.

[0053] 3. High efficiency: The automated and intelligent evaluation process greatly shortens the evaluation time and improves work efficiency.

[0054] 4. Adjustability: The intervention of the manual review link makes the evaluation results more flexible and can be adjusted according to the actual situation.

[0055] 5. Continuous optimization: Recording the adjustment basis helps to continuously optimize and improve the model and enhance the future evaluation effect.

[0056] The above description is only an overview of the technical solutions 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 description. 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0058] Figure 1 It is a schematic flowchart of the intelligent enterprise risk assessment method based on big data provided by the embodiments of the present disclosure;

[0059] Figure 2Schematic diagram of the enterprise risk intelligent assessment system based on big data provided by the embodiments of the present disclosure;

[0060] Figure 3 Schematic diagram of an electronic device provided by the embodiments of the present disclosure. Detailed implementation manners

[0061] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0062] It should be clear that the following uses specific specific examples to illustrate the implementation manners of the present disclosure, and 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 manners, and 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 of protection of the present disclosure.

[0063] It should be noted that the following describes various aspects of the embodiments within the scope of the appended claims. It should be obvious 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 the device and / or practice the method. In addition, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0064] It should also be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present disclosure schematically, and only show the components related to the present disclosure in the diagrams, 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 an arbitrary change, and the component layout type may also be more complex.

[0065] 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.

[0066] Refer to Figure 1, the first aspect of the present invention provides an intelligent enterprise risk assessment method based on big data, including:

[0067] Step S1, obtain the loan amount, financial data, credit record and industry data of the enterprise to be evaluated; the financial data and credit record can be determined through the enterprise's publicly available financial statements or the data provided by the enterprise this time; the industry data can include industry news, national policies, etc.

[0068] Specifically, the financial data includes the balance sheet, income statement, cash flow statement, etc., and these data reflect the financial status and profitability of the enterprise.

[0069] The credit record includes loan repayment records, whether there is default, credit rating, etc., and these data directly reflect the credit status of the enterprise.

[0070] The industry data includes data such as the market condition, competition situation, and industry growth rate of the industry where the enterprise is located, and these data help to evaluate the external environment and industry risks of the enterprise.

[0071] The comprehensiveness and diversity of the data in this step ensure the comprehensiveness and accuracy of the evaluation results, and reduce the bias that may be caused by a single information source.

[0072] Step S2, analyze based on the loan amount, financial data, credit record and industry data to generate a risk score and basis for manual review;

[0073] As an optional implementation manner, the analysis based on the loan amount, financial data, credit record and industry data to generate a risk score and basis includes:

[0074] Use a fixed asset evaluation model to evaluate according to the loan amount and financial data, and generate corresponding scores and bases; the fixed asset evaluation model can evaluate whether the enterprise has sufficient assets as collateral according to the loan amount and the enterprise's fixed assets (such as real estate, equipment, etc.), and generate corresponding scores and bases.

[0075] Use a cash flow evaluation model to evaluate according to the financial data, and generate corresponding scores and bases; the cash flow evaluation model can evaluate the cash flow status of the enterprise based on the financial data, especially the cash flow statement, and judge whether it has sufficient cash flow to repay the loan, and generate corresponding scores and bases.

[0076] Use a credit evaluation model to evaluate according to the credit record, and generate corresponding scores and bases; the credit evaluation model can evaluate the credit risk of the enterprise according to the enterprise's historical credit record, and generate corresponding scores and bases.

[0077] Use an enterprise development evaluation model to evaluate based on industry data, generating corresponding scores and bases; the enterprise development evaluation model can, based on industry data, evaluate the prospects of the industry in which the enterprise is located and the enterprise's competitive position in the industry, generating corresponding scores and bases.

[0078] Obtain the scores and bases output by each evaluation model respectively and summarize them.

[0079] In this step, through the comprehensive analysis of multiple evaluation models, internal and external risk factors of the enterprise are comprehensively considered, improving the scientificity and accuracy of the evaluation. At the same time, the generated risk scores and bases provide strong support for manual review, reducing the subjective judgment of reviewers.

[0080] Step S3: Obtain the basis for adjustment during manual review and regenerate the score according to the adjusted basis.

[0081] The intelligent enterprise risk assessment method based on big data provided by the present invention provides comprehensive and accurate risk assessment results through multi-dimensional data collection and comprehensive analysis of multiple evaluation models. This method not only improves the evaluation efficiency, but also ensures the rationality and scientificity of the evaluation results through the intervention of the manual review link. Specifically, this method has the following advantages:

[0082] 1. Comprehensiveness: Comprehensive consideration of financial data, credit records and industry data to ensure the comprehensiveness of the evaluation results.

[0083] 2. Accuracy: The combined use of multiple evaluation models improves the accuracy and reliability of the evaluation.

[0084] 3. High efficiency: The automated and intelligent evaluation process greatly shortens the evaluation time and improves work efficiency.

[0085] 4. Adjustable: The intervention of the manual review link makes the evaluation results more flexible and can be adjusted according to the actual situation.

[0086] 5. Continuous optimization: Recording the adjustment basis helps the continuous optimization and improvement of the model, enhancing the future evaluation effect.

[0087] In summary, the intelligent enterprise risk assessment method based on big data is an efficient, accurate and scientific risk assessment tool, especially suitable for risk control in enterprise lending by financial institutions.

[0088] In an embodiment, use a cash flow evaluation model to evaluate based on financial data, and the generated corresponding scores and bases include:

[0089] Clean the financial data; the financial data includes: the cash flow statement, the income statement, the balance sheet, other financial indicators such as the current ratio, the quick ratio, the debt-to-asset ratio, the interest coverage ratio, etc. The basic information of the enterprise: such as the industry, the establishment time, the scale, etc.

[0090] Historical loan records: If any, understand the credit history of the enterprise.

[0091] Cleaning the financial data includes:

[0092] Remove missing values: Process the records with missing data, which can be handled by deletion, interpolation, or using the average value, etc.

[0093] Outlier handling: Identify and handle outliers to ensure the accuracy and reliability of the data.

[0094] Standardization: Standardize different indicators to ensure fairness and accuracy when the model processes data of different magnitudes.

[0095] Input the total cash flow, sources of income, and fixed expenses in the cleaned financial data into the cash flow assessment model; specifically, it includes:

[0096] Use the same feature engineering methods as in the model training stage to extract the following features of the new enterprise:

[0097] Cash flow from operating activities: Calculate the mean, variance, maximum value, minimum value, etc. of the cash flow from operating activities in the past few years.

[0098] Cash flow from investing activities: Calculate the net amount of the cash flow from investing activities and its fluctuations.

[0099] Cash flow from financing activities: Calculate the net amount of the cash flow from financing activities and its fluctuations.

[0100] Total cash flow: Calculate the sum of the above three cash flows.

[0101] Cash flow stability: Calculate the standard deviation or coefficient of variation of the cash flow.

[0102] Current ratio: Current assets / Current liabilities.

[0103] Quick ratio: (Current assets - Inventory) / Current liabilities.

[0104] Debt-to-asset ratio: Total liabilities / Total assets.

[0105] Interest coverage ratio: Earnings before interest and taxes / Interest expense.

[0106] Net profit margin: Net profit / Operating revenue.

[0107] Operating revenue growth rate: Calculate the operating revenue growth rate over the past few years.

[0108] Rent payment: Calculate the annual rent payment amount of the enterprise and its proportion in the total expenditure.

[0109] Loan interest payment: Calculate the annual loan interest payment amount of the enterprise and its proportion in the total expenditure.

[0110] Long-term contract payment obligation: Calculate the annual long-term contract payment obligation amount of the enterprise and its proportion in the total expenditure.

[0111] Then input the above features into the model to obtain the score generated by the model, and then use feature importance analysis to understand which financial indicators and cash flow features have the greatest impact on the risk score. For example, the stability of cash flow from operating activities, current ratio, interest coverage ratio, etc.

[0112] Use model interpretation tools (such as SHAP, LIME) to explain the specific impact of each feature on the final score. For example, large fluctuations in the cash flow from operating activities of a certain enterprise may have a greater impact on the risk score.

[0113] It can be known that the model also needs to be trained before implementing this method. The specific training of the model includes:

[0114] Data collection:

[0115] Cash flow statement: Obtain the cash flow from operating activities, cash flow from investing activities, and cash flow from financing activities of the enterprise.

[0116] Income statement: Understand the revenue and profit situation of the enterprise.

[0117] Balance sheet: Obtain the information of the enterprise's assets, liabilities, and owners' equity.

[0118] Other financial indicators: Such as current ratio, quick ratio, asset-liability ratio, interest coverage ratio, etc.

[0119] Enterprise basic information: Such as industry, establishment time, scale, etc.

[0120] Historical loan records: If any, understand the credit history of the enterprise.

[0121] Data cleaning:

[0122] Remove missing values: Process the records with missing data, which can be processed by deletion, interpolation, or using the average value, etc.

[0123] Outlier handling: Identify and handle outliers to ensure the accuracy and reliability of the data.

[0124] Standardization: Standardize different metrics to ensure fairness and accuracy when the model processes data of different magnitudes.

[0125] Feature Engineering

[0126] Cash Flow Features:

[0127] Cash Flow from Operating Activities: Calculate the mean, variance, maximum, minimum, etc. of the cash flow from operating activities over the past few years to evaluate the cash inflows and outflows of operating activities.

[0128] Cash Flow from Investing Activities: Calculate the net amount and its volatility of the cash flow from investing activities to evaluate the company's investment strategy and investment recovery.

[0129] Cash Flow from Financing Activities: Calculate the net amount and its volatility of the cash flow from financing activities to evaluate the company's sources of funds and repayment ability.

[0130] Total Cash Flow: Calculate the sum of the above three cash flows to evaluate the overall cash flow situation of the enterprise.

[0131] Cash Flow Stability: Calculate the standard deviation or coefficient of variation of the cash flow to reflect the volatility of the cash flow. A higher cash flow stability usually indicates a healthier financial position of the enterprise.

[0132] Other Financial Features:

[0133] Current Ratio: Current Assets / Current Liabilities, which is used to evaluate the enterprise's short-term debt repayment ability.

[0134] Quick Ratio: (Current Assets - Inventory) / Current Liabilities, which is used to evaluate the enterprise's more stringent short-term debt repayment ability.

[0135] Debt-to-Asset Ratio: Total Liabilities / Total Assets, which is used to evaluate the enterprise's financial leverage and risk level.

[0136] Interest Coverage Ratio: Earnings Before Interest and Taxes / Interest Expense, which is used to evaluate the enterprise's ability to pay interest.

[0137] Net Profit Margin: Net Profit / Operating Revenue, which is used to evaluate the enterprise's profitability.

[0138] Operating Revenue Growth Rate: Calculate the operating revenue growth rate over the past few years to evaluate the enterprise's growth potential.

[0139] Fixed Expense Features:

[0140] Rent Payment: Calculate the annual rent payment amount of the enterprise and its proportion in the total expenses to evaluate the burden of fixed costs.

[0141] Loan Interest Payment: Calculate the annual loan interest payment amount of the enterprise and its proportion in the total expenses to evaluate the debt burden.

[0142] Long-term contract payment obligation: Calculate the amount of the enterprise's long-term contract payment obligation each year and its proportion in the total expenditure, and evaluate the future financial pressure.

[0143] 3. Model Selection and Training

[0144] Model Selection:

[0145] Linear regression: Suitable for continuous risk score output.

[0146] Logistic regression: Suitable for classifying risks into different levels (such as low, medium, high).

[0147] Random forest: Suitable for dealing with complex non-linear relationships.

[0148] Support vector machine (SVM): Suitable for classification problems.

[0149] Neural network: Suitable for complex models that require higher accuracy.

[0150] Training Data:

[0151] Label data: A dataset with known risk scores or loan default labels is required. Historical data can be used to label the risks of enterprise loans.

[0152] Feature data: Use the features extracted in the above feature engineering.

[0153] Training Process:

[0154] Data partitioning: Partition the dataset into a training set and a test set, usually in a ratio of 70% and 30%.

[0155] Model training: Use the training set to train the model and adjust the model parameters to optimize the performance.

[0156] Model validation: Use the test set to validate the performance of the model and ensure that the model performs well on unseen data.

[0157] Model optimization: Further optimize the model performance through methods such as cross-validation, feature selection, and hyperparameter tuning.

[0158] In another embodiment, using the enterprise development evaluation model to evaluate based on industry data includes:

[0159] Data cleaning of industry data; Industry data is roughly divided into the following categories:

[0160] Enterprise data: Collect the historical financial statements of the target enterprise (including income statement, balance sheet, cash flow statement, etc.), enterprise scale, market position, business scope, development strategy, etc.

[0161] Industry data: including information such as industry average profit rate, industry growth trend, policy support intensity, industry cyclical characteristics, market competition status, etc.

[0162] Macroeconomic data: GDP growth rate, inflation rate, interest rate level, foreign exchange market status, etc.

[0163] Data related to core business: performance of the enterprise's main business, quality and innovation ability of products or services, etc.

[0164] Risk management data: enterprise credit score, debt level, overdue repayment record, etc.

[0165] Input the industry average profit rate, industry growth trend, policy support intensity, industry cyclical characteristics, and market competition status in the cleaned industry data into the enterprise development evaluation model; of course, data can also be selected according to actual needs.

[0166] Obtain the scores and bases generated by the model.

[0167] The model construction method and usage method in this embodiment are the same as above and will not be elaborated here.

[0168] As an optional implementation method, this method further includes:

[0169] Step S4, classify and store the bases adjusted during manual review based on the adjustment reasons; the adjustment reasons include: data quality, feature importance; for example, including:

[0170] Establish a feedback system so that the operator can conveniently delete some evaluation bases when using the model to evaluate an enterprise and record the deletion reasons.

[0171] Automatically record the specific information of each deletion operation, including the deleted basis, deletion reason, operator ID, evaluation time, etc.

[0172] Regularly and automatically analyze the feedback provided by the operator and count the occurrence frequency of each deleted basis.

[0173] Automatically classify the deletion reasons, such as inaccurate industry data, incomplete enterprise data, outdated data, invalid model features, and subjective human judgment, etc.

[0174] Conduct a detailed automatic analysis on each classified deletion reason and generate an analysis report.

[0175] Step S5, optimize the model based on the classified bases.

[0176] Specifically, optimizing the model based on the classified bases includes:

[0177] Step S51, improve data quality based on the basis of data quality categories;

[0178] For example, it includes:

[0179] Automatically check the data sources from which data is frequently deleted, and verify the accuracy and timeliness of the data. For example, obtain the latest data through the API interface and compare the differences between the old data and the new data.

[0180] Automatically improve the data collection and processing methods according to the analysis results. For example, add a data review link, update the data frequency, etc.

[0181] Automatically detect and process outliers and missing values in the data to ensure data quality.

[0182] Step S52, adjust feature weights based on the basis of feature importance categories;

[0183] For example, it includes:

[0184] Use feature importance evaluation methods (such as feature importance scoring, feature contribution analysis, etc.) to automatically evaluate the effectiveness of each feature.

[0185] For features that are frequently deleted and have clear reasons, automatically reduce their weights or completely remove them. For example, use L1 regularization or feature selection algorithms (such as recursive feature elimination RFE) to automatically screen features.

[0186] Automatically generate new features or improve existing features. For example, generate new features by combining existing features and applying data transformations (such as logarithmic transformation, normalization, etc.).

[0187] Step S53, retrain the model using the improved data and features.

[0188] For example, it includes:

[0189] Automatically reconstruct the training set, validation set, and test set using the improved dataset and features.

[0190] Automatically select a suitable machine learning model (such as decision tree, random forest, support vector machine, neural network, etc.) and train it. For example, select the best model and hyperparameters through an automatic selection algorithm (such as grid search, random search).

[0191] Automatically evaluate the performance of the model on the validation set and test set, and pay attention to indicators such as accuracy, recall rate, and F1 score. For example, use cross-validation to automatically calculate the performance indicators of the model.

[0192] Step S54, enhance model interpretability;

[0193] For example, it includes:

[0194] Automatically generate a detailed explanation for each scoring basis to help the operator understand the source and importance of the scoring basis. For example, use the SHAP (SHapley Additive exPlanations) value or the LIME (Local Interpretable Model-agnostic Explanations) method to generate an explanation of the importance of features.

[0195] Automatically introduce the operator's feedback as an auxiliary signal to enhance the adaptability and interpretability of the model in practical applications. For example, adjust the importance of features by introducing feedback weights.

[0196] On the other hand, referring to Figure 2 , the present invention provides an intelligent enterprise risk assessment system based on big data, including:

[0197] A data acquisition module that acquires the loan amount, financial data, credit records, and industry data of the enterprise to be evaluated;

[0198] An analysis module that analyzes based on the loan amount, financial data, credit records, and industry data to generate a risk score and basis for manual review;

[0199] A score regeneration module that obtains the basis adjusted during manual review and regenerates the score according to the adjusted basis.

[0200] As an optional implementation manner, the analysis module includes:

[0201] A fixed asset evaluation module that uses a fixed asset evaluation model to evaluate based on the loan amount and financial data to generate corresponding scores and bases;

[0202] A cash flow evaluation module that uses a cash flow evaluation model to evaluate based on financial data to generate corresponding scores and bases;

[0203] A credit evaluation module that uses a credit evaluation model to evaluate based on credit records to generate corresponding scores and bases;

[0204] An enterprise development evaluation module that uses an enterprise development evaluation model to evaluate based on industry data to generate corresponding scores and bases;

[0205] A summary module that respectively obtains the scores and bases output by each evaluation model and summarizes them.

[0206] An electronic device according to an embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-transitory 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.

[0207] 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 enterprise risk intelligent assessment method based on big data in the foregoing embodiments of the present disclosure.

[0208] Those skilled in the art should understand that, in order to solve the technical problem of how to obtain good user experience effects, known structures such as communication buses and interfaces may also be included in this embodiment, and these known structures should also be included in the protection scope of the present disclosure.

[0209] 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 embodiments 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.

[0210] 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.

[0211] 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, etc.; an output device including, for example, a display screen, etc.; 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 wirelessly or wiredly with other devices (such as edge computing devices) to exchange data. Although Figure 3An electronic device having various devices is shown, but 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.

[0212] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processor, all or part of the steps of the enterprise risk intelligent assessment method based on big data according to the embodiments of the present disclosure are performed.

[0213] 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.

[0214] A computer-readable storage medium according to an embodiment of the present disclosure stores non-temporary computer-readable instructions. When the non-temporary computer-readable instructions are run by a processor, all or part of the steps of the enterprise risk intelligent assessment method based on big data according to the foregoing embodiments of the present disclosure are performed.

[0215] The above-mentioned 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 having built-in rewritable non-volatile memories (such as memory cards), and media having built-in ROMs (such as ROM cartridges).

[0216] 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.

[0217] 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, and it cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above-mentioned specific details are only for illustrative and easy-to-understand purposes, rather than limitations, and the above details do not limit the present disclosure to necessarily adopt the above specific details for implementation.

[0218] In this 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 actual relationship or order between these entities or operations. The block diagrams of the devices, apparatuses, equipment, and systems involved in this 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 way. Words such as "including", "comprising", "having", etc. are open-ended words, 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 it, 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 it.

[0219] In addition, as used herein, the "or" used in the listing of items starting with "at least one" indicates a disjunctive 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 wording "exemplary" does not mean that the examples described are preferred or better than other examples.

[0220] It should also be noted that in the systems and methods of this disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of this disclosure.

[0221] Various changes, substitutions, and alterations to the technologies described herein can be made without departing from the teachings defined by the appended claims. In addition, the scope of the claims of this 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. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or acts within their scope.

[0222] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this 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 this disclosure. Therefore, this 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.

[0223] The foregoing description has been presented for purposes of illustration and description. In addition, this description is not intended to limit embodiments of the present disclosure to the forms disclosed herein. Although several example aspects and embodiments have been discussed above, those skilled in the art will recognize some of their variations, modifications, alterations, additions, and subcombinations.

Claims

1. A method for intelligent enterprise risk assessment based on big data, characterized in that: include: Obtain loan amount, financial data of the company to be assessed, credit history and industry data; Analyze loan amount, financial data, credit history and industry data to generate risk scores and evidence for manual review; Obtain the basis for adjustments during manual review, and regenerate the score based on the adjusted basis.

2. The enterprise risk intelligent assessment method based on big data according to claim 1 is characterized in that: The risk score and basis generated by analyzing the loan amount, financial data, credit history and industry data include: Use the fixed asset valuation model to evaluate based on loan amounts and financial data, and generate corresponding scores and basis; Use cash flow assessment model to evaluate financial data and generate corresponding scores and basis; Use the credit assessment model to assess credit records and generate corresponding scores and bases; Use the enterprise development assessment model to evaluate based on industry data and generate corresponding scores and basis; The scores and bases output by each evaluation model are obtained separately and summarized.

3. The enterprise risk intelligent assessment method based on big data according to claim 2 is characterized in that: Use the cash flow assessment model to evaluate based on financial data, and generate corresponding scores and bases including: Cleaning of financial data; Input the total cash flow, income sources and fixed expenses from the cleaned financial data into the cash flow valuation model; Get the score and rationale generated by the model.

4. The enterprise risk intelligent assessment method based on big data according to claim 3 is characterized in that: Using the Enterprise Development Assessment Model to assess industry data includes: Clean industry data; Input the industry average profit margin, industry growth trend, policy support, industry cyclical characteristics, and market competition status from the cleaned industry data into the enterprise development assessment model; Get the score and rationale generated by the model.

5. The enterprise risk intelligent assessment method based on big data according to claim 4 is characterized in that: Also includes: The basis for adjustments during manual review is classified and stored based on the reasons for the adjustments; The model is optimized based on the classified evidence.

6. The enterprise risk intelligent assessment method based on big data according to claim 5 is characterized in that: Reasons for adjustment include: data quality, feature importance; Model optimization based on the classified evidence includes: Improve data quality based on the data quality categories; Adjust feature weights based on feature importance categories; Retrain the model using the improved data and features.

7. An enterprise risk intelligent assessment system based on big data, characterized in that: include: Data acquisition module, which obtains loan amount, financial data of the enterprise to be evaluated, credit record and industry data; The analysis module analyzes the loan amount, financial data, credit record and industry data to generate risk scores and basis for manual review; The scoring regeneration module obtains the basis for adjustments during manual review and regenerates the score based on the adjusted basis.

8. The enterprise risk intelligent assessment system based on big data according to claim 7 is characterized in that: The analysis modules include: Fixed asset valuation module, which uses the fixed asset valuation model to evaluate based on loan amounts and financial data, and generates corresponding scores and basis; The cash flow assessment module uses the cash flow assessment model to evaluate financial data and generate corresponding scores and bases; The credit assessment module uses the credit assessment model to assess credit records and generate corresponding scores and bases; The enterprise development assessment module uses the enterprise development assessment model to conduct assessments based on industry data and generate corresponding scores and bases; The summary module obtains the scores and bases output by each evaluation model and summarizes them.

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 enterprise risk intelligent assessment method based on big data as described in any one of claims 1-6.

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 enterprise risk intelligent assessment method based on big data as described in any one of claims 1-6.

Images