Data asset evaluation and credit granting system

Abstract

The invention discloses a data asset evaluation and credit granting system, and relates to the technical field of asset evaluation, and the system comprises a data search and investigation module which generates a data resource directory list; the data asset identification and analysis module is used for analyzing the inflow of economic benefits; the data quality evaluation module is used for building a data quality evaluation model, executing data quality exploration and generating a data quality evaluation report; the data asset evaluation module is used for issuing a data asset evaluation report; the financial institution credit granting module is used for carrying out credit granting evaluation and providing financing credit granting for enterprises; and the post-loan supervision module carries out continuous evaluation and risk monitoring on the data assets. According to the method, a multi-level, multi-dimension and comprehensive assessment and decision-making system is formed through comprehensive data search and ranking, compliance examination, data quality assessment, value measurement and calculation, financial credit granting and post-loan supervision functions, so that the accuracy of credit granting decision-making of a financial institution can be improved, the financing efficiency can be improved, and the risk can be reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of asset evaluation, and in particular to a data asset evaluation and credit granting system. Background Art

[0002] With the rapid development and widespread application of data, data, as one of the core assets of enterprises, is increasingly included in the evaluation and decision-making process in the fields of finance and commerce. The data assets of enterprises include not only traditional financial information and customer data, but also cover multiple levels such as business processes, production management, and market behavior. How to evaluate data assets, confirm their potential economic benefits, ensure the compliance and legality of data, and on this basis provide enterprises with reasonable credit and financial services has become an important issue in the current financial industry and corporate development.

[0003] Existing data asset management mostly focuses on data collection and storage, while comprehensive consideration of data compliance review, economic benefit analysis, quality assessment, application scenario design, etc. is relatively weak. At the same time, when providing credit services to enterprises, financial institutions rely more on corporate financial statements and traditional credit assessments, lacking in-depth understanding and quantitative analysis of corporate data assets, leading to increased financing risks. Existing technologies mainly solve the problems of data storage, data analysis and financial auditing, but lack a cross-departmental and cross-field comprehensive data assessment and credit service system. Therefore, it is necessary to establish a systematic data asset assessment and credit platform with data as the core, through comprehensive investigation, compliance review, quality assessment, value measurement and other multi-dimensional analysis, to help financial institutions make scientific credit decisions, which can effectively reduce financial risks and improve the accuracy and scientificity of financial services. Summary of the invention

[0004] In order to solve the above technical problems, a data asset evaluation and credit granting system is provided. This technical solution solves the above problems.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A data asset evaluation and credit granting system, comprising:

[0007] Data survey and investigation module: used to collect enterprise information construction results, investigate business and system status, and generate a data resource catalog list;

[0008] Data asset identification and analysis module: The data asset identification and analysis module is electrically connected to the data investigation and survey module. The data asset identification and analysis module is used to identify the compliance of potential data assets, analyze the inflow of economic benefits that can be generated, and issue a data asset compliance review and data ownership legal opinion;

[0009] Data quality evaluation module: The data quality evaluation module is electrically connected to the data asset identification and analysis module. The data quality evaluation module is used to build a data quality evaluation model and perform data quality exploration to generate a data quality evaluation report;

[0010] Data asset evaluation module: The data asset evaluation module is electrically connected to the data quality evaluation module. The data asset evaluation module is used to plan and design data application scenarios, calculate the value of data application scenarios, select appropriate evaluation method paths, and issue a data asset evaluation report;

[0011] Financial institution credit granting module: The financial institution credit granting module is electrically connected to the data asset evaluation module. The financial institution credit granting module is used to conduct credit assessment based on the materials submitted by the enterprise and provide financing credit to the enterprise;

[0012] Post-loan supervision module: The post-loan supervision module is electrically connected to the credit granting module of the financial institution. The post-loan supervision module is used by the financial institution to continuously evaluate and monitor the risks of data assets, and issue regular security assessment reports.

[0013] Preferably, the data investigation and survey module specifically includes:

[0014] Enterprise informatization construction achievement collection unit: collect documents and materials related to enterprise informatization construction, including enterprise IT infrastructure construction, system architecture, application software and database system technical documents, interview the enterprise's technical team, IT department heads and business department personnel to obtain the strategic planning, development direction and implementation status of enterprise informatization, and collect project reports, investment plans, project achievements and implementation records related to informatization;

[0015] Business and system status survey unit: Through cooperation with various business departments, investigate and sort out the key business processes of the enterprise, clarify which businesses involve data generation, storage, processing and exchange, obtain the enterprise's existing IT system architecture, including ERP, CRM, financial system and production management system, identify the system boundaries of data generation and flow, investigate the flow path of enterprise data, identify the input source, flow direction, processing links and output results of data, and investigate the enterprise's existing data storage structure, database type, data storage platform, and data management and security control measures;

[0016] Data resource survey and list generation: Classify data according to different business fields and application scenarios, confirm data types, preliminarily evaluate data integrity, check whether data is redundant or missing, and generate a data resource directory list;

[0017] Data resource identification and classification unit: Assign a unique identifier to each type of data, classify the data based on its business value, frequency of use and sensitivity, determine the priority of different categories of data, and confirm the ownership of the data.

[0018] Preferably, the data asset identification and analysis module specifically includes:

[0019] Economic Benefit Analysis Unit: Analyze the potential economic value of each data asset, estimate the benefits it can bring to the enterprise, share data with partners, use data analysis to optimize decision-making, and provide personalized services to customers;

[0020] Data asset compliance review report unit: after compliance assessment and review, a data asset compliance review report is generated. The report content includes the identification and classification of data assets, data compliance assessment results, and economic benefit analysis of data;

[0021] Opinion generation unit: Based on the compliance review results of data assets, a data opinion is issued to clarify the ownership, usage rights and licensing rights of the data.

[0022] Preferably, the use of data analysis to optimize decision-making and provide personalized services to customers specifically includes:

[0023] Among them, the data analysis optimization decision formula is:

[0024]

[0025] In the formula, f is the decision optimization benefit, n represents different decision optimization fields, i represents the number of the current optimization decision, and g i Refers to the i-th optimization decision.

[0026] Preferably, the data quality evaluation module specifically includes:

[0027] Data collection and preprocessing unit: collect, clean and preprocess the data to be evaluated, and the preprocessing steps include removing missing values, removing duplicate records, standardizing formats, and data conversion and format adjustment;

[0028] Design a data quality assessment model building unit: discover potential problems in the data based on machine learning algorithms;

[0029] Data quality scoring unit: Based on the weighted average algorithm, it calculates the score of each data quality dimension and assigns different weights to each dimension according to weight and importance;

[0030] Generate data quality evaluation report unit: Based on the above exploration and scoring results, generate a data quality evaluation report, including the scoring and analysis of each data quality dimension, detailed description and location of the problem data, data quality improvement suggestions, and comprehensive data quality score and its corresponding risk assessment.

[0031] Preferably, the method of discovering potential problems in data based on a machine learning algorithm specifically includes:

[0032] Among them, the potential problem identification formula is:

[0033]

[0034] Where J is the objective function, N is the total number of data points, K is the number of clusters, and x i is the data point i, μ k is the center point of cluster K, and rik is the indicator function.

[0035] Preferably, the calculation of the score of each data quality dimension based on the weighted average algorithm specifically includes:

[0036] Among them, the weighted average algorithm formula is:

[0037]

[0038] In the formula, F is the comprehensive data quality score, i is the index of the quality dimension, n is the total number of data quality dimensions, and D i is the score of the i-th quality dimension, W i is the weight of the quality dimension score, indicating the importance of the i-th dimension.

[0039] Preferably, the data asset evaluation module specifically includes:

[0040] Data asset classification and archiving unit: classify, organize, archive and identify all data resources within the organization;

[0041] Data application scenario planning and design unit: Plan and design data application scenarios based on the organization's business needs to ensure that data assets can be connected with specific business needs;

[0042] Data application value calculation unit: calculate the actual value of data application scenarios, quantify the specific value of data assets, and evaluate the benefits and potential risks brought by data assets;

[0043] Data asset evaluation report generation unit: issue a data asset evaluation report, including an overview of data assets, application value of data assets and benefit analysis.

[0044] Preferably, the financial institution credit granting module specifically includes:

[0045] Credit line calculation unit: obtain financing line according to the enterprise's financial status, business scale, industry characteristics and credit score factors, set credit period according to the enterprise's cash flow, repayment ability and financing needs, and determine the interest rate level of credit according to the enterprise's credit unit status and market interest rate;

[0046] Credit decision-making unit: Make the final credit decision based on the aforementioned evaluation results;

[0047] Credit contract signing and fund disbursement unit: prepare and sign the credit contract based on the credit approval results, and disburse loan funds on demand based on the company's financing needs and contract terms.

[0048] Preferably, the post-loan supervision module specifically includes:

[0049] Post-loan information collection and data update unit: regularly obtain the company's financial statements, monitor the company's industry dynamics and market changes, update the company's business activity data, and collect credit record update information;

[0050] Risk Assessment and Monitoring Unit: Analyze the financial health of the enterprise, monitor changes in financial indicators, monitor the credit status of the enterprise, and assess the repayment risk of the enterprise based on external factors such as industry conditions and changes in the market environment;

[0051] The post-loan risk management and emergency response unit takes corresponding measures to deal with potential risks discovered, establishes a risk early warning mechanism, and issues alerts for possible overdue, default and financial abnormal risks.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention proposes to form a multi-level, multi-dimensional, comprehensive evaluation and decision-making system through comprehensive data investigation, compliance review, data quality assessment, value measurement, financial credit and post-loan supervision and other functions. This system not only helps to improve the scientificity and accuracy of financial institutions' credit decisions, but also provides enterprises with practical data asset management solutions, improves financing efficiency, reduces risks, and provides technical support for the compliance, economic benefits and application value of data assets. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a system framework diagram of the present invention. DETAILED DESCRIPTION

[0055] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0056] Reference Figure 1 As shown, a data asset evaluation and credit granting system includes:

[0057] A data asset evaluation and credit granting system, comprising:

[0058] Data investigation and research module:

[0059] Enterprise informatization construction achievement collection unit: collect documents and materials related to enterprise informatization construction, including enterprise IT infrastructure construction, system architecture, application software and database system technical documents, interview the enterprise's technical team, IT department heads and business department personnel to obtain the strategic planning, development direction and implementation status of enterprise informatization, and collect project reports, investment plans, project achievements and implementation records related to informatization;

[0060] Business and system status survey unit: Through cooperation with various business departments, investigate and sort out the key business processes of the enterprise, clarify which businesses involve data generation, storage, processing and exchange, obtain the enterprise's existing IT system architecture, including ERP, CRM, financial system and production management system, identify the system boundaries of data generation and flow, investigate the flow path of enterprise data, identify the input source, flow direction, processing links and output results of data, and investigate the enterprise's existing data storage structure, database type, data storage platform, and data management and security control measures;

[0061] Data resource survey and list generation: Classify data according to different business fields and application scenarios, confirm data types, preliminarily evaluate data integrity, check whether data is redundant or missing, and generate a data resource directory list;

[0062] Data resource identification and classification unit: Assign a unique identifier to each type of data, classify the data based on its business value, frequency of use and sensitivity, determine the priority of different categories of data, and confirm the ownership of the data.

[0063] Data asset identification and analysis module:

[0064] Economic Benefit Analysis Unit: Analyze the potential economic value of each data asset, estimate the benefits it can bring to the enterprise, share data with partners, use data analysis to optimize decision-making, and provide personalized services to customers;

[0065] Among them, the data analysis optimization decision formula is:

[0066]

[0067] In the formula, f is the decision optimization benefit, n represents different decision optimization fields, i represents the number of the current optimization decision, and g irefers to the i-th optimization decision;

[0068] Data asset compliance review report unit: after compliance assessment and review, a data asset compliance review report is generated. The report content includes the identification and classification of data assets, data compliance assessment results, and economic benefit analysis of data;

[0069] Opinion generation unit: Based on the compliance review results of data assets, a data opinion is issued to clarify the ownership, usage rights and licensing rights of the data.

[0070] Data quality evaluation module:

[0071] Data collection and preprocessing unit: collect, clean and preprocess the data to be evaluated, and the preprocessing steps include removing missing values, removing duplicate records, standardizing formats, and data conversion and format adjustment;

[0072] Design a data quality assessment model building unit: discover potential problems in the data based on machine learning algorithms;

[0073] Among them, the potential problem identification formula is:

[0074]

[0075] Where J is the objective function, N is the total number of data points, K is the number of clusters, and x i is the data point i, μ k is the center point of cluster K, and rik is the indicator function.

[0076] Data quality scoring unit: Based on the weighted average algorithm, it calculates the score of each data quality dimension and assigns different weights to each dimension according to weight and importance;

[0077] Among them, the weighted average algorithm formula is:

[0078]

[0079] In the formula, F is the comprehensive data quality score, i is the index of the quality dimension, n is the total number of data quality dimensions, and D i is the score of the i-th quality dimension, W i is the weight of the quality dimension score, indicating the importance of the i-th dimension;

[0080] Data asset assessment module:

[0081] Data asset classification and archiving unit: classify, organize, archive and identify all data resources within the organization;

[0082] Data application scenario planning and design unit: Plan and design data application scenarios based on the organization's business needs to ensure that data assets can be connected with specific business needs;

[0083] Data application value calculation unit: calculate the actual value of data application scenarios, quantify the specific value of data assets, and evaluate the benefits and potential risks brought by data assets;

[0084] Data asset evaluation report generation unit: issue a data asset evaluation report, including an overview of data assets, application value of data assets and benefit analysis.

[0085] Financial institution credit granting module:

[0086] Credit line calculation unit: obtain financing line according to the enterprise's financial status, business scale, industry characteristics and credit score factors, set credit period according to the enterprise's cash flow, repayment ability and financing needs, and determine the interest rate level of credit according to the enterprise's credit unit status and market interest rate;

[0087] Credit decision-making unit: Make the final credit decision based on the aforementioned evaluation results;

[0088] Credit contract signing and fund disbursement unit: prepare and sign the credit contract based on the credit approval results, and disburse loan funds on demand based on the company's financing needs and contract terms.

[0089] Post-loan supervision module:

[0090] Post-loan information collection and data update unit: regularly obtain the company's financial statements, monitor the company's industry dynamics and market changes, update the company's business activity data, and collect credit record update information;

[0091] Risk Assessment and Monitoring Unit: Analyze the financial health of the enterprise, monitor changes in financial indicators, monitor the credit status of the enterprise, and assess the repayment risk of the enterprise based on external factors such as industry conditions and changes in the market environment;

[0092] The post-loan risk management and emergency response unit takes corresponding measures to deal with potential risks discovered, establishes a risk early warning mechanism, and issues alerts for possible overdue, default and financial abnormal risks.

[0093] In summary, the advantages of the present invention are:

[0094] Through the data investigation and survey module, the system can comprehensively collect the results of enterprise information construction, sort out key business processes, clarify the specific links of data generation, storage, processing and exchange, form a complete data resource catalog list, and provide basic data support for subsequent asset evaluation and decision-making;

[0095] The data asset identification and analysis module can not only identify the compliance of data assets, but also deeply analyze the economic benefits that each data asset may bring, including optimizing decision-making, improving enterprise operational efficiency, enhancing customer experience, etc., to ensure that the financing provided by financial institutions to enterprises has reasonable risk assessment and value support;

[0096] Through the data quality evaluation module, the system can conduct data quality assessment based on machine learning algorithms, identify potential quality issues and provide improvement suggestions, thereby ensuring the accuracy and integrity of data assets. This quantitative evaluation method provides a more reliable data basis for financial institutions to grant credit;

[0097] The data asset assessment module helps enterprises and financial institutions to scientifically plan data application scenarios, quantify the actual value of data assets, help financial institutions better understand the potential risks and benefits of data assets, and provide a more accurate basis for credit decision-making;

[0098] The credit granting module of financial institutions calculates the credit limit based on multi-dimensional data such as the company's financial status, business scale, credit score, etc., and generates a personalized credit granting plan based on factors such as the company's cash flow and repayment ability. This process realizes the intelligence and dataization of credit granting decisions, and improves the accuracy and efficiency of credit granting decisions.

[0099] The post-loan supervision module regularly obtains information such as corporate financial statements and credit records, monitors the company's financial status, market changes and other external factors, helps financial institutions to promptly identify loan risks, and provides effective risk warning and emergency response mechanisms to ensure the effectiveness of post-loan management and loan security;

[0100] During the process of data asset identification and analysis, the system issues a clear data asset compliance review report and a legal opinion on data ownership through the compliance review unit to ensure the legal use of data, protect the legitimate rights and interests of both financial institutions and enterprises, and avoid legal risks caused by data infringement or non-compliant use;

[0101] The collaboration of various modules enables financial institutions to conduct more efficient cross-departmental information sharing and collaboration based on comprehensive data support. Especially in the financial credit process, the system can automatically integrate information from various departments of the enterprise to provide comprehensive risk assessment and decision-making support.

[0102] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A data asset evaluation and credit granting system, characterized in that: include: Data survey and investigation module: used to collect enterprise information construction results, investigate business and system status, and generate a data resource catalog list; Data asset identification and analysis module: The data asset identification and analysis module is electrically connected to the data investigation and survey module. The data asset identification and analysis module is used to identify the compliance of potential data assets, analyze the inflow of economic benefits that can be generated, and issue a data asset compliance review and data ownership legal opinion; Data quality evaluation module: The data quality evaluation module is electrically connected to the data asset identification and analysis module. The data quality evaluation module is used to build a data quality evaluation model and perform data quality exploration to generate a data quality evaluation report; Data asset evaluation module: The data asset evaluation module is electrically connected to the data quality evaluation module. The data asset evaluation module is used to plan and design data application scenarios, calculate the value of data application scenarios, select appropriate evaluation method paths, and issue a data asset evaluation report; Financial institution credit granting module: The financial institution credit granting module is electrically connected to the data asset evaluation module. The financial institution credit granting module is used to conduct credit assessment based on the materials submitted by the enterprise and provide financing credit to the enterprise; Post-loan supervision module: The post-loan supervision module is electrically connected to the credit granting module of the financial institution. The post-loan supervision module is used by the financial institution to continuously evaluate and monitor the risks of data assets, and issue regular security assessment reports.

2. A data asset evaluation and credit granting system according to claim 1, characterized in that: The data investigation and survey module specifically includes: Enterprise informatization construction achievement collection unit: collect documents and materials related to enterprise informatization construction, obtain the strategic planning, development direction and implementation status of enterprise informatization, and collect project reports, investment plans, project achievements and implementation records related to informatization; Business and system status survey unit: Through cooperation with various business departments, investigate and sort out the key business processes of the enterprise, obtain the enterprise's existing IT system architecture, identify the input source, flow, processing links and output results of data, and investigate the enterprise's existing data storage structure, database type, data storage platform, and data management and security control measures; Data resource survey and list generation: Classify data according to different business fields and application scenarios, confirm data types, preliminarily evaluate data integrity, check whether data is redundant or missing, and generate a data resource directory list; Data resource identification and classification unit: Assign a unique identifier to each type of data, classify the data based on its business value, frequency of use and sensitivity, determine the priority of different categories of data, and confirm the ownership of the data.

3. A data asset evaluation and credit granting system according to claim 2, characterized in that: The data asset identification and analysis module specifically includes: Economic Benefit Analysis Unit: Analyze the potential economic value of each data asset, estimate the benefits it can bring to the enterprise, share data with partners, use data analysis to optimize decision-making, and provide personalized services to customers; Data asset compliance review report unit: after compliance assessment and review, a data asset compliance review report is generated. The report content includes the identification and classification of data assets, data compliance assessment results, and economic benefit analysis of data; Opinion generation unit: Based on the compliance review results of data assets, a data opinion is issued to clarify the ownership, usage rights and licensing rights of the data.

4. A data asset evaluation and credit granting system according to claim 3, characterized in that: The use of data analysis to optimize decision-making and provide customers with personalized services is described in detail. include: Among them, the data analysis optimization decision formula is: In the formula, f is the decision optimization benefit, n represents different decision optimization fields, i represents the number of the current optimization decision, and g i Refers to the i-th optimization decision.

5. A data asset evaluation and credit granting system according to claim 4, characterized in that: The data quality evaluation module specifically includes: Data collection and preprocessing unit: collect, clean and preprocess the data to be evaluated, and the preprocessing steps include removing missing values, removing duplicate records, standardizing formats, and data conversion and format adjustment; Design a data quality assessment model building unit: discover potential problems in the data based on machine learning algorithms; Data quality scoring unit: Based on the weighted average algorithm, it calculates the score of each data quality dimension and assigns different weights to each dimension according to weight and importance; Generating data quality evaluation report unit: generating a data quality evaluation report based on the above-mentioned detection and scoring results.

6. A data asset evaluation and credit granting system according to claim 5, characterized in that: The method of discovering potential problems in data based on machine learning algorithms is described in detail. include: Among them, the potential problem identification formula is: Where J is the objective function, N is the total number of data points, K is the number of clusters, and x i is the data point i, μ k is the center point of cluster K, and rik is the indicator function.

7. A data asset evaluation and credit granting system according to claim 6, characterized in that: The weighted average algorithm is used to calculate the score of each data quality dimension. include: Among them, the weighted average algorithm formula is: In the formula, F is the comprehensive data quality score, i is the index of the quality dimension, n is the total number of data quality dimensions, and D i is the score of the i-th quality dimension, W i is the weight of the quality dimension score, indicating the importance of the i-th dimension.

8. A data asset evaluation and credit granting system according to claim 7, characterized in that: The data asset evaluation module specifically includes: Data asset classification and archiving unit: classify, organize, archive and identify all data resources within the organization; Data application scenario planning and design unit: Plan and design data application scenarios based on the organization's business needs to ensure that data assets can be connected with specific business needs; Data application value calculation unit: calculate the actual value of data application scenarios, quantify the specific value of data assets, and evaluate the benefits and potential risks brought by data assets; Data asset evaluation report generation unit: issue a data asset evaluation report, including an overview of data assets, application value of data assets and benefit analysis.

9. A data asset evaluation and credit granting system according to claim 8, characterized in that: The financial institution credit granting module specifically includes: Credit line calculation unit: obtain financing line according to the enterprise's financial status, business scale, industry characteristics and credit score factors, set credit period according to the enterprise's cash flow, repayment ability and financing needs, and determine the interest rate level of credit according to the enterprise's credit unit status and market interest rate; Credit decision-making unit: Make the final credit decision based on the aforementioned evaluation results; Credit contract signing and fund disbursement unit: prepare and sign the credit contract based on the credit approval results, and disburse loan funds on demand based on the company's financing needs and contract terms.

10. A data asset evaluation and credit granting system according to claim 9, characterized in that: The post-loan supervision module specifically includes: Post-loan information collection and data update unit: regularly obtain the company's financial statements, monitor the company's industry dynamics and market changes, update the company's business activity data, and collect credit record update information; Risk Assessment and Monitoring Unit: Analyze the financial health of the enterprise, monitor changes in financial indicators, monitor the credit status of the enterprise, and assess the repayment risk of the enterprise based on external factors such as industry conditions and changes in the market environment; The post-loan risk management and emergency response unit takes corresponding measures to deal with potential risks discovered, establishes a risk early warning mechanism, and issues alerts for possible overdue, default and financial abnormal risks.

Images