Credit assessment method, system and device based on enterprise information and storage medium

Abstract

The invention discloses a credit assessment method, system and device based on enterprise information, and a storage medium. The method comprises the steps of obtaining enterprise industry and commerce information, operation risk information, legal risk information and financial information; performing data preprocessing on the enterprise industry and commerce information, the operation risk information, the legal risk information and the financial information to obtain industry and commerce data, operation risk data, legal risk data and financial data; extracting enterprise credit evaluation indexes from the industry and commerce data, the operation risk data, the legal risk data and the financial data; performing quantitative scoring on the enterprise credit evaluation indexes through a credit evaluation model to obtain an enterprise comprehensive credit score and an enterprise credit grade; and credit evaluation of the enterprise information is realized based on the enterprise comprehensive credit score and the enterprise credit rating. According to the method and the system, various data analysis and machine learning models are utilized, automatic, high-precision and comprehensive-coverage-dimension enterprise credit assessment is realized, and the cooperation efficiency is improved while the risk is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of credit management, and in particular relates to a credit assessment method, system, device and storage medium based on enterprise information. Background Art

[0002] With the development of the digital economy, the demand for credit risk assessment of enterprises is increasing. Traditional credit assessment methods are mostly based on single data sources such as financial information of financial institutions and bank credit records, which cannot fully reflect the actual operating conditions and risk conditions of enterprises. At the same time, the traditional assessment process usually involves manual review, which is inefficient and difficult to meet the needs of modern enterprises for dynamic assessment and real-time decision-making. Therefore, how to automate credit assessment for multi-dimensional data has become a technical problem that needs to be solved urgently.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a credit evaluation method, system, device and storage medium based on enterprise information, aiming to solve the technical problem of how to automatically evaluate credit for multi-dimensional data.

[0005] To achieve the above object, the present invention provides a credit evaluation method based on enterprise information, the credit evaluation method based on enterprise information comprising:

[0006] Obtain business information, operational risk information, legal risk information and financial information of enterprises;

[0007] Preprocessing the business information, the business risk information, the legal risk information and the financial information of the enterprise to obtain business data, business risk data, legal risk data and financial data;

[0008] Extracting enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data;

[0009] Quantitatively score the enterprise credit assessment indicators through a credit assessment model to obtain the enterprise's comprehensive credit score and enterprise credit rating;

[0010] A credit assessment of the enterprise information is achieved based on the enterprise comprehensive credit score and the enterprise credit rating.

[0011] Optionally, the step of extracting enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data includes:

[0012] Matching and integrating the industrial and commercial data, the business risk data, the legal risk data, and the financial data to generate an enterprise data portrait;

[0013] Enterprise credit assessment indicators are extracted from the enterprise data portrait.

[0014] Optionally, the step of quantitatively scoring the enterprise credit assessment indicators through a credit assessment model to obtain a comprehensive enterprise credit score and an enterprise credit rating includes:

[0015] Calculate the comprehensive credit score of the enterprise based on the credit assessment model and the credit assessment indicators of the enterprise through a multi-dimensional weighted formula;

[0016] The enterprise credit rating corresponding to the enterprise comprehensive credit score is determined according to the credit rating evaluation rules.

[0017] Optionally, the step of implementing credit assessment of enterprise information based on the enterprise comprehensive credit score and the enterprise credit rating includes:

[0018] Generate an enterprise credit assessment report based on the enterprise comprehensive credit score and the enterprise credit rating;

[0019] A credit evaluation of the enterprise information is implemented based on the enterprise credit evaluation report.

[0020] Optionally, the step of generating an enterprise credit assessment report according to the enterprise comprehensive credit score and the enterprise credit rating includes:

[0021] Perform risk point analysis based on the enterprise comprehensive credit score and the enterprise credit rating to obtain enterprise risk analysis results;

[0022] generating a risk optimization strategy based on the enterprise risk analysis results;

[0023] An enterprise credit assessment report is generated based on the enterprise comprehensive credit score, the enterprise credit rating, the enterprise risk analysis results and the risk optimization strategy.

[0024] In addition, to achieve the above-mentioned purpose, the present invention also proposes a credit evaluation system based on enterprise information, and the credit evaluation system based on enterprise information includes:

[0025] The acquisition module is used to obtain business information, business risk information, legal risk information and financial information of enterprises;

[0026] A processing module, used to perform data preprocessing on the business information of the enterprise, the business risk information, the legal risk information and the financial information, respectively, to obtain business data, business risk data, legal risk data and financial data;

[0027] An extraction module, used to extract enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data;

[0028] An evaluation module, used to quantify and score the enterprise credit evaluation indicators through a credit evaluation model to obtain a comprehensive credit score and enterprise credit rating of the enterprise;

[0029] The evaluation module is also used to implement credit evaluation of enterprise information based on the enterprise comprehensive credit score and the enterprise credit level.

[0030] In addition, to achieve the above-mentioned purpose, the present invention also proposes a credit assessment device based on enterprise information, which includes: a memory, a processor, and a credit assessment program based on enterprise information stored on the memory and executable on the processor, wherein the credit assessment program based on enterprise information is configured to implement the steps of the credit assessment method based on enterprise information as described above.

[0031] In addition, to achieve the above objectives, the present invention also proposes a storage medium, on which a credit assessment program based on enterprise information is stored. When the credit assessment program based on enterprise information is executed by a processor, the steps of the credit assessment method based on enterprise information as described above are implemented.

[0032] The present invention first obtains the business information, business risk information, legal risk information and financial information of the enterprise, and then pre-processes the business information, business risk information, legal risk information and financial information of the enterprise respectively to obtain business data, business risk data, legal risk data and financial data, and then extracts the enterprise credit assessment index from the business data, business risk data, legal risk data and financial data, and finally quantitatively scores the enterprise credit assessment index through the credit assessment model to obtain the enterprise comprehensive credit score and enterprise credit rating, and realizes the credit assessment of enterprise information based on the enterprise comprehensive credit score and enterprise credit rating. The present invention integrates the business information, legal risk information, business risk information of the enterprise, and the financial data uploaded by the enterprise, and uses a variety of data analysis and machine learning models to realize the enterprise credit assessment with automation, high accuracy and comprehensive coverage, which is helpful for timely warning and avoidance of potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a structural diagram of a credit assessment device based on enterprise information in a hardware operating environment involved in an embodiment of the present invention;

[0034] Figure 2 It is a flowchart of the first embodiment of the credit assessment method based on enterprise information of the present invention;

[0035] Figure 3 It is a structural block diagram of the first embodiment of the credit evaluation system based on enterprise information of the present invention.

[0036] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0037] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0038] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the structure of a credit assessment device based on enterprise information in the hardware operating environment involved in the embodiment of the present invention.

[0039] like Figure 1 As shown, the credit assessment device based on enterprise information may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage system independent of the aforementioned processor 1001.

[0040] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the credit assessment device based on enterprise information, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0041] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a credit assessment program based on enterprise information.

[0042] exist Figure 1In the enterprise information-based credit assessment device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the enterprise information-based credit assessment device of the present invention can be set in the enterprise information-based credit assessment device, and the enterprise information-based credit assessment device calls the enterprise information-based credit assessment program stored in the memory 1005 through the processor 1001, and executes the enterprise information-based credit assessment method provided in the embodiment of the present invention.

[0043] The embodiment of the present invention provides a credit evaluation method based on enterprise information. Figure 2 , Figure 2 It is a flowchart of the first embodiment of the credit evaluation method based on enterprise information of the present invention.

[0044] In this embodiment, the credit assessment method based on enterprise information includes the following steps:

[0045] Step S10: Obtaining business information, operational risk information, legal risk information and financial information of the enterprise.

[0046] It is easy to understand that the execution subject of this embodiment can be a credit assessment system based on enterprise information with functions such as data processing, network communication and program running, or other computer equipment with similar functions, etc., and this embodiment is not limited.

[0047] In this embodiment, the enterprise registration information (such as registered capital, establishment time, shareholder structure, etc.) is captured through the enterprise industrial and commercial system as the enterprise industrial and commercial information. The industrial and commercial information includes the enterprise name, registered capital, paid-in capital, establishment time, shareholder information, enterprise change information, etc. For example, the establishment time is "2010-03-15", and the shareholders hold 60% and 40% of the shares respectively.

[0048] Obtain the enterprise's business risk data (such as dishonesty records, administrative penalties, lists of abnormal operations, etc.) from third-party data platforms as business risk information. Business risk information includes administrative penalties, abnormal operations, corporate tax arrears and lists of serious violations, etc. For example, there has been one environmental protection penalty in the past three years, and there has been no dishonesty or abnormal operations.

[0049] Obtain information on litigation and arbitration related to the enterprise through the legal information platform as legal risk information. Legal risk information includes information on court announcements, case filings, persons subject to enforcement, and records of dishonesty involving the enterprise and its principal persons in charge. For example, there have been two civil lawsuits in the past five years, which have been closed without major disputes.

[0050] The enterprise shall upload its own financial statements (such as balance sheet, income statement, cash flow statement, etc.) as the enterprise's financial information. Financial information includes balance sheet, income statement, cash flow statement, including key financial data such as operating income, operating expenses, operating profit, liabilities, etc. For example, the debt-to-asset ratio is 37.5%, the operating income is 120 million yuan, and the net profit is 10 million yuan.

[0051] Step S20: Preprocess the business information, the business risk information, the legal risk information and the financial information of the enterprise respectively to obtain business data, business risk data, legal risk data and financial data.

[0052] It should be noted that data from different sources are cleaned, formatted and standardized to ensure accuracy and consistency. The accuracy of input data is ensured through methods such as deduplication and outlier detection.

[0053] In the specific implementation, the method of pre-processing the business information of the enterprise is: unifying the unit of registered capital into "10,000 yuan"; converting the establishment time into a timestamp format to facilitate the calculation of the age of the enterprise.

[0054] The method of pre-processing business risk information is as follows: classify and code the penalty type: environmental protection type is marked as "R"; mark the penalty record time for timeliness analysis.

[0055] The method of preprocessing legal risk information is to standardize the case description, such as marking "closed case" as a status value of 0.

[0056] The financial information is pre-processed by checking the logical consistency (such as debt-to-asset ratio) and formatting the amount to two decimal places.

[0057] It should be understood that the system will also perform data verification on the financial data uploaded by the enterprise to ensure the authenticity of the data. The verification methods include format verification, numerical consistency verification, external data comparison, historical data comparison and tampering detection.

[0058] Format verification:

[0059] Verification rules: verify the file format of the uploaded data (such as Excel, CSV, db package) to ensure that the format meets the predetermined standards; processing logic: use regular expressions or template matching to check whether the file structure contains necessary fields (such as total assets, net profit); error feedback: if the format is incorrect, the system returns a specific error prompt and requires the company to re-upload.

[0060] Numerical consistency check:

[0061] Verification of asset balance relationships: Check whether the formula relationships in the balance sheet are valid; Verification of financial indicators: Calculation of key financial indicators (such as current ratio, debt-to-asset ratio) to see whether they are within a reasonable range for the industry; Internal data matching: For example, the ending cash balance of the cash flow statement should be consistent with the monetary funds in the balance sheet.

[0062] External data comparison:

[0063] Government data comparison: connect to national tax and industrial and commercial data interfaces (such as corporate tax declaration data) to verify whether the uploaded financial data is consistent with the actual declared data; third-party credit data: cross-verify with bank statements or credit rating agency data to ensure that the financial data has not been tampered with.

[0064] Historical data comparison:

[0065] Trend analysis: Compare the currently uploaded data with the company's historical data to identify the rationality of the financial data (such as whether the profit growth trend matches the operating income).

[0066] Tamper Detection:

[0067] Hash verification: Generate a unique hash value for the uploaded file to verify whether the file has been modified; Watermark check: If the file comes from a third-party organization, verify whether the electronic watermark or digital signature of the file is valid.

[0068] Step S30: extracting enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data.

[0069] Furthermore, the industrial and commercial data, business risk data, legal risk data and financial data are matched and integrated to generate a corporate data portrait; and corporate credit assessment indicators are extracted from the corporate data portrait.

[0070] Enterprise credit assessment indicators include industrial and commercial indicators, operational risk indicators, legal risk indicators and financial indicators.

[0071] In this embodiment, the industrial and commercial indicators include the age of the enterprise and the stability of the shareholder structure, for example, the age of the enterprise = current year - year of establishment = 14 years, the stability of the shareholder structure = high (the major shareholder holds 60%). The operating risk indicators include the number of administrative penalties, for example, the number of administrative penalties = 1, the risk score is 80 points (minus 20 points); the legal risk indicators include the number of civil lawsuits, for example, the number of civil lawsuits = 2, the risk score is 70 points; the financial indicators include the net profit margin and the debt-to-asset ratio, for example, the net profit margin = 1000 ÷ 12000 ≈ 8.33%, the debt-to-asset ratio = 37.5%.

[0072] Step S40: quantifying and scoring the enterprise credit assessment indicators through a credit assessment model to obtain the enterprise's comprehensive credit score and enterprise credit rating.

[0073] It should be noted that the credit assessment model is a machine learning module with a built-in multi-dimensional scoring algorithm, which uses the multi-dimensional scoring algorithm to perform weighted processing on different types of data. Different scoring weights are set for industrial and commercial information, operating risks, legal risks and financial data to quantitatively score the comprehensive credit of the enterprise.

[0074] The credit assessment model also includes a hierarchical system of credit scores (i.e., credit rating rules). According to the comprehensive score of the enterprise, it is divided into different credit levels, such as A, B, C, D, etc., so that users can intuitively understand the credit status of the enterprise.

[0075] Furthermore, based on the credit assessment model, the comprehensive credit score of the enterprise is calculated through a multi-dimensional weighted formula according to the enterprise credit assessment indicators; and the enterprise credit grade corresponding to the comprehensive credit score of the enterprise is determined according to the credit grade evaluation rules.

[0076] Credit rating assessment rules are user-defined.

[0077] In the specific implementation, the multi-dimensional weighted formula is:

[0078] Credit score = ∑(score of each dimension × weight)Credit score = \sum(score of each dimension × weight)Credit score = ∑(score of each dimension × weight)

[0079] The indicator weights can be adjusted according to industry dynamics.

[0080] For example: Business information score:

[0081] Company age (60) × 50% + shareholder stability (80) × 50% = 70 points.

[0082] Business Risk Score:

[0083] Administrative penalty score = 80 × 30% = 24 points.

[0084] Legal Risk Score:

[0085] Civil litigation score = 70 × 20% = 14 points.

[0086] Financial data score:

[0087] Comprehensive financial score = 80 × 30% = 24 points.

[0088] Total score = 70×20%+24+14+24=76 points.

[0089] Determine the corporate credit rating corresponding to the total score based on pre-set credit rating evaluation rules.

[0090] Step S50: Implementing credit assessment of enterprise information based on the enterprise comprehensive credit score and the enterprise credit rating.

[0091] Furthermore, an enterprise credit assessment report is generated based on the enterprise's comprehensive credit score and enterprise credit rating; and credit assessment of enterprise information is achieved based on the enterprise credit assessment report.

[0092] The processing method for generating an enterprise credit assessment report based on the enterprise's comprehensive credit score and enterprise credit rating is to conduct risk point analysis based on the enterprise's comprehensive credit score and enterprise credit rating to obtain enterprise risk analysis results; generate a risk optimization strategy based on the enterprise risk analysis results; and generate an enterprise credit assessment report based on the enterprise's comprehensive credit score, enterprise credit rating, enterprise risk analysis results and risk optimization strategy.

[0093] Examples of enterprise risk analysis results include operational risks: records of environmental penalties; legal risks: litigation cases exposing contract management issues, etc.

[0094] Risk optimization strategies can be used to strengthen environmental compliance and avoid penalties; optimize contract management and reduce litigation risks; and adjust financial structures to ensure sustainable development.

[0095] In this embodiment, the business information, business risk information, legal risk information and financial information of the enterprise are first obtained, and then the business information, business risk information, legal risk information and financial information of the enterprise are preprocessed to obtain business data, business risk data, legal risk data and financial data, and then the enterprise credit assessment indicators are extracted from the business data, business risk data, legal risk data and financial data, and finally the enterprise credit assessment indicators are quantitatively scored through the credit assessment model to obtain the comprehensive credit score and credit rating of the enterprise, and the credit assessment of the enterprise information is realized based on the comprehensive credit score and credit rating of the enterprise. This embodiment integrates the business information, legal risk information, business risk information of the enterprise, and the financial data uploaded by the enterprise, and uses a variety of data analysis and machine learning models to realize the automatic, high-precision and comprehensive enterprise credit assessment, which helps to timely warn and avoid potential risks.

[0096] Reference Figure 3 , Figure 3 It is a structural block diagram of the first embodiment of the credit evaluation system based on enterprise information of the present invention.

[0097] like Figure 3 As shown, the credit evaluation system based on enterprise information proposed in the embodiment of the present invention includes:

[0098] The acquisition module 3001 is used to obtain the business information, business risk information, legal risk information and financial information of the enterprise;

[0099] The processing module 3002 is used to perform data preprocessing on the business information, the business risk information, the legal risk information and the financial information of the enterprise to obtain business data, business risk data, legal risk data and financial data;

[0100] Extraction module 3003, used to extract enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data;

[0101] Evaluation module 3004, used to quantify and score the enterprise credit evaluation index through a credit evaluation model to obtain a comprehensive credit score and credit rating of the enterprise;

[0102] The evaluation module 3004 is also used to implement credit evaluation of enterprise information based on the enterprise comprehensive credit score and the enterprise credit rating.

[0103] Other embodiments or specific implementations of the credit evaluation system based on enterprise information of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0104] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0105] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0106] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0107] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A credit assessment method based on enterprise information, characterized in that: The credit assessment method based on enterprise information comprises the following steps: Obtain business information, operational risk information, legal risk information and financial information of enterprises; Preprocessing the business information, the business risk information, the legal risk information and the financial information of the enterprise to obtain business data, business risk data, legal risk data and financial data; Extracting enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data; Quantitatively score the enterprise credit assessment indicators through a credit assessment model to obtain the enterprise's comprehensive credit score and enterprise credit rating; A credit assessment of the enterprise information is achieved based on the enterprise comprehensive credit score and the enterprise credit rating.

2. The method according to claim 1, characterized in that The step of extracting enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data includes: Matching and integrating the industrial and commercial data, the business risk data, the legal risk data, and the financial data to generate an enterprise data portrait; Enterprise credit assessment indicators are extracted from the enterprise data portrait.

3. The method according to claim 1 or 2, characterized in that The step of quantitatively scoring the enterprise credit assessment indicators through the credit assessment model to obtain the enterprise comprehensive credit score and enterprise credit rating includes: Calculate the comprehensive credit score of the enterprise based on the credit assessment model and the credit assessment indicators of the enterprise through a multi-dimensional weighted formula; The enterprise credit rating corresponding to the enterprise comprehensive credit score is determined according to the credit rating evaluation rules.

4. The method according to claim 3, characterized in that The step of implementing credit assessment of enterprise information based on the enterprise comprehensive credit score and the enterprise credit rating includes: Generate an enterprise credit assessment report based on the enterprise comprehensive credit score and the enterprise credit rating; A credit evaluation of the enterprise information is implemented based on the enterprise credit evaluation report.

5. The method according to claim 4, characterized in that The step of generating an enterprise credit assessment report based on the enterprise comprehensive credit score and the enterprise credit rating includes: Perform risk point analysis based on the enterprise comprehensive credit score and the enterprise credit rating to obtain enterprise risk analysis results; generating a risk optimization strategy based on the enterprise risk analysis results; An enterprise credit assessment report is generated based on the enterprise comprehensive credit score, the enterprise credit rating, the enterprise risk analysis results and the risk optimization strategy.

6. A credit evaluation system based on enterprise information, characterized in that: The credit evaluation system based on enterprise information includes: The acquisition module is used to obtain business information, business risk information, legal risk information and financial information of enterprises; A processing module, used to perform data preprocessing on the business information of the enterprise, the business risk information, the legal risk information and the financial information, respectively, to obtain business data, business risk data, legal risk data and financial data; An extraction module, used to extract enterprise credit assessment indicators from the industrial and commercial data, the business risk data, the legal risk data and the financial data; An evaluation module, used to quantify and score the enterprise credit evaluation indicators through a credit evaluation model to obtain a comprehensive credit score and enterprise credit rating of the enterprise; The evaluation module is also used to implement credit evaluation of enterprise information based on the enterprise comprehensive credit score and the enterprise credit level.

7. A credit assessment device based on enterprise information, characterized in that: The device comprises: a memory, a processor, and a credit assessment program based on enterprise information stored in the memory and executable on the processor, wherein the credit assessment program based on enterprise information is configured to implement the steps of the credit assessment method based on enterprise information as described in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a credit assessment program based on enterprise information, and when the credit assessment program based on enterprise information is executed by a processor, the steps of the credit assessment method based on enterprise information as described in any one of claims 1 to 5 are implemented.

Images