Financial risk control system based on big data and block chain

Abstract

The invention discloses a financial risk control system based on big data and a block chain. An operation method of the system comprises the following steps of 1, performing liquidity monitoring on funds of a borrower by connecting a data source; 2, realizing risk assessment by monitoring related industry information of the borrowers; thirdly, borrower industry risk assessment is achieved through a comprehensive risk scoring system; 4, the repayment ability of the borrower is comprehensively evaluated and uploaded to a block chain for storage, and the industry risk evaluation module is used for collecting and analyzing industry data, constructing an industry network atlas, evaluating a risk transfer model and deeply knowing the incidence relation between different industries; and the comprehensive risk score and block chain storage module is used for comprehensively considering individual and industry risks, generating a comprehensive risk score, and realizing safe and non-tampering data storage through a block chain, and the financial risk monitoring system has the characteristic of more comprehensive and accurate financial risk monitoring.

Description

Technical Field

[0001] The present invention relates to the field of financial risk control technology, and specifically to a financial risk control system based on big data and blockchain. Background Art

[0002] Traditional financial risk control systems mainly rely on credit records for assessment. However, this method has some significant drawbacks. First, risk assessment based solely on credit records tends to ignore the individual's actual economic situation and cash flow. Although credit records reflect past repayment history, they cannot fully understand the borrower's current economic situation and future repayment ability. More importantly, many traditional risk control methods only focus on credit assessment before the loan occurs, while ignoring the actual cash flow during the loan cycle. Even if the borrower has a good credit record, he may still face repayment difficulties during the loan cycle due to capital chain pressure and other reasons. Therefore, it is difficult to accurately predict the borrower's future repayment performance by relying solely on past credit record analysis, which has become a limitation of traditional risk control methods.

[0003] At the same time, the rise of blockchain technology provides a more secure and transparent means of data processing in the financial sector. Through blockchain, decentralized data storage and tamper-proof transaction records can be achieved, enhancing the credibility and security of data. Introducing blockchain into the financial risk control system is expected to improve the overall anti-attack and anti-tampering capabilities of the system. Therefore, this patent combines big data and blockchain technology, and through in-depth analysis of various data such as individual capital flows and industry risk associations, builds a more comprehensive and accurate financial risk control system based on big data and blockchain to improve the prediction and management level of borrower default risks. Summary of the invention

[0004] The purpose of the present invention is to provide a financial risk control system based on big data and blockchain to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a financial risk control system based on big data and blockchain, the operation method of the system includes the following steps:

[0006] Step 1: Monitor the liquidity of borrowers’ funds by connecting to data sources;

[0007] Step 2: Conduct risk assessment by monitoring the borrower’s relevant industry information;

[0008] Step 3: Implement the borrower industry risk assessment through a comprehensive risk scoring system;

[0009] Step 4: Conduct a comprehensive assessment of the borrower’s repayment ability and upload it to blockchain storage.

[0010] According to the above technical solution, the step of monitoring the liquidity of the borrower's funds by connecting to the data source includes:

[0011] A funds monitoring module is established in the system. This module is connected to the borrower's bank system and electronic payment platform through a standard API interface to collect the borrower's fund flow information. Based on the fund flow information, real-time monitoring and analysis are carried out through big data analysis. First, the working capital information is preprocessed, including cleaning, deduplication and filling of missing values. Then, key features are extracted from the transaction records, such as transaction frequency, transaction amount, and common payment methods. The system uses these features to build a fund flow model. Then, the system automatically identifies abnormal patterns through the trained model. Finally, thresholds are set and borrowers are monitored in real time. Once an abnormal pattern exceeding the preset threshold is detected, the alarm system is immediately triggered to notify the risk management team to conduct an investigation and assessment.

[0012] According to the above technical solution, the steps of implementing risk assessment by monitoring the relevant industry information of the borrower include:

[0013] Establish an industry network map and identify the correlation between different industries through network analysis methods in graph theory;

[0014] Use Monte Carlo simulation methods to generate a large number of random samples to simulate different economic conditions and market volatility scenarios.

[0015] According to the above technical solution, the step of establishing an industry network map and identifying the correlation between different industries through a network analysis method in graph theory includes:

[0016] The system obtains data of relevant industries from public databases, industry reports, and corporate financial statements, including but not limited to economic indicators, industrial chain relationships, and market shares, and then performs data preprocessing. Through the collected data, the system uses the network analysis method in graph theory to establish an industry network map. In the map, different industries are regarded as nodes in the graph, and edges are constructed through the relationships between them. Subsequently, the established industry network map is analyzed through covariance analysis to identify the correlation between different industries and select the industry with the greatest correlation. In this embodiment, the Internet technology industry is selected as the industry with the greatest correlation. Finally, a risk transfer model is formulated based on the established industry network map and the correlation analysis results. First, the system confirms the correlation between the Internet technology industry and the financial services industry based on the established industry network map and correlation analysis, which includes the potential connection between the two industries in cooperation, competition, and supply chain. Next, the system selects key indicators, such as the user growth rate of Internet companies, the loan issuance volume of the financial services industry, and the stock market index. Then, by establishing a mathematical model, the system models these indicators into random variables, combines the correlation and probability distribution between them, and uses the Monte Carlo simulation method to generate a large number of random samples to simulate different economic conditions and market fluctuation scenarios.

[0017] According to the above technical solution, the step of using the Monte Carlo simulation method to generate a large number of random samples and simulate different economic conditions and market fluctuation scenarios includes:

[0018] First, define the risk transfer model and select the user growth rate X in the Internet technology industry. 互联网 , the loan default rate in the financial services industry is Y 金融 , the stock market index is Z 股市 , establish a simplified risk transfer model, the model is as follows: Y 金融 =a*X 互联网 +b*Z 股市 +∈, where a and b are correlation coefficients, ∈ is the error term, and next, select the probability distribution when X 互联网 and Z 股市 When they obey normal distribution, their mean μ and standard deviation δ are calculated, and then random samples are generated using Monte Carlo simulation, where X 互联网 and Z 股市 The simulation method is as follows: Among them, i represents the i-th simulation. In the simulation experiment stage, the random samples obtained by simulation are substituted into the risk transfer model to calculate Y 金融 The value of for the i-th simulation: Through multiple simulations, the system can obtain different Y 金融The value of is used to form a probability distribution. Finally, through statistical analysis and result summary, the system can calculate the risk transmission probability and impact degree. At the same time, sensitivity analysis is performed, the correlation coefficients a and b are adjusted, and the response of the model to parameter changes is observed.

[0019] According to the above technical solution, the steps of implementing the borrower industry risk assessment through the comprehensive risk scoring system include:

[0020] The system obtains the distribution of risk transfer probability through the risk transfer model, divides the risk transfer probability into low, medium and high levels, and then divides the probability into intervals corresponding to the overall distribution. Similarly, the impact degree is divided into mild, medium and severe levels. Then, the levels of transfer probability and impact degree are mapped to corresponding scores, and the total score is obtained. The comprehensive score can be calculated by the following formula: Comprehensive score = risk transfer probability score + impact degree score. The comprehensive risk score is divided into different risk levels, such as low risk, medium risk and high risk. Then, a real-time monitoring system is set to regularly update the real-time data of the borrower's industry and recalculate the risk score. Once the score exceeds the pre-set threshold, the early warning system can be triggered to notify the financial institution to take corresponding risk management measures. Based on the comprehensive risk score, the system generates a risk assessment report for the borrower's industry. The report includes an overview of the risk level, specific description of the risk factors, impact scenarios and recommended risk mitigation measures.

[0021] According to the above technical solution, the step of comprehensively evaluating the borrower's repayment ability and uploading it to the blockchain for storage includes:

[0022] A comprehensive assessment model is established to comprehensively assess the individual risk U (i.e., the capital risk in step one) and the industry risk V, and the comprehensive risk index W is set as follows: W = T*U+(1-T)*V, where T is the weight coefficient, which indicates the relative importance of the individual risk in the comprehensive assessment. By adjusting the weight, the system can flexibly balance the contribution of individual and industry risks to the comprehensive assessment. In addition, a threshold for the comprehensive risk index is set. When W is greater than the fixed threshold, a real-time warning is triggered. A smart contract is created on the blockchain to automatically perform the verification and storage of uploaded data. The smart contract contains a verification algorithm to ensure that the uploaded data complies with the pre-defined rules and stores the verified data in the corresponding block on the blockchain. At the same time, the blockchain provides a shared ledger, and all parties can operate on the same data without worrying about data inconsistency.

[0023] According to the above technical solution, the system includes:

[0024] Fund liquidity monitoring module, used to monitor borrowers' fund flows in real time, identify abnormal transaction behaviors, and strengthen risk management;

[0025] Industry risk assessment module, which is used to collect and analyze relevant industry data, build industry network maps, evaluate risk transfer models, and gain an in-depth understanding of the relationships between different industries;

[0026] The comprehensive risk scoring and blockchain storage module is used to comprehensively consider individual and industry risks, generate a comprehensive risk score, and achieve secure and tamper-proof data storage through blockchain to promote multi-party cooperation and information sharing.

[0027] According to the above technical solution, the fund liquidity monitoring module includes:

[0028] Data access and real-time collection module, which is used to connect to the data source through the API interface, collect borrower's capital flow information in real time, and ensure timely data update;

[0029] The fund monitoring module building module is used to build a fund monitoring module, use big data analysis technology to monitor abnormal transaction behavior, and improve the accuracy of abnormal pattern identification;

[0030] The abnormal pattern recognition and early warning system module is used to use the capital flow model to automatically identify abnormal patterns, set thresholds for real-time monitoring, trigger the alarm system, and strengthen the real-time investigation and evaluation of the risk management team.

[0031] According to the above technical solution, the industry risk assessment module includes:

[0032] Relevant industry data collection module, used to obtain relevant industry data from multiple data sources to provide a comprehensive information basis for industry risk assessment;

[0033] The industry network map building module is used to build an industry network map using network analysis methods, gain an in-depth understanding of the relationship between different industries, and provide a basis for the risk transfer model;

[0034] The correlation analysis and risk transfer model module is used to identify correlations through covariance analysis, establish risk transfer models, and use Monte Carlo simulation to evaluate the probability and impact of risk transfer.

[0035] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, first, monitors the liquidity of the borrower's funds by connecting to the data source, and uses the big data analysis method to identify abnormal transaction behaviors. Subsequently, the system realizes risk assessment by monitoring the relevant information of the borrower's industry, including establishing an industry network map and correlation analysis, and then formulating a risk transfer model. In step three, a comprehensive risk scoring system is used to combine the risk transfer probability and the degree of impact, and a comprehensive risk score is formulated. A real-time monitoring system is established, as well as updating the borrower's industry data and triggering an early warning system, providing financial institutions with clear risk management information. Finally, in step four, a comprehensive assessment model is established to comprehensively consider individual and industry risks, and the comprehensive assessment results are uploaded to the blockchain for secure storage, thereby realizing a comprehensive and integrated borrower industry risk assessment and data sharing. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0037] Figure 1 A flowchart of a financial risk control method based on big data and blockchain provided in Example 1 of the present invention;

[0038] Figure 2 A schematic diagram of the module composition of a financial risk control system based on big data and blockchain provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Embodiment 1: Figure 1 This is a flowchart of a financial risk control method based on big data and blockchain provided in Example 1 of the present invention. This embodiment can be applied to the scenario of bank risk monitoring. The method can be executed by a financial risk control system based on big data and blockchain provided in this embodiment. Figure 1 As shown, the method specifically comprises the following steps:

[0041] Step 1: Monitor the liquidity of borrowers’ funds by connecting to data sources;

[0042] In the embodiment of the present invention, by accessing the borrower's bank transaction records, electronic payment information and other data sources, the borrower's fund flow information is collected and updated in real time, and a fund flow model is constructed to identify abnormal transaction behaviors;

[0043] Exemplarily, a funds monitoring module is established in the system. The module is connected to the borrower's bank system, electronic payment platform and other data sources through a standard API interface to collect the borrower's fund flow information. Based on the fund flow information, real-time monitoring and analysis are performed through big data analysis. First, the working capital information is preprocessed, including cleaning, deduplication and filling of missing values. Then, key features are extracted from the transaction records, such as transaction frequency, transaction amount, and common payment methods. The system uses these features to build a fund flow model. Then, the system automatically identifies abnormal patterns through the trained model, such as frequent large withdrawals or overdrafts. Finally, thresholds are set and borrowers are monitored in real time. Once an abnormal pattern exceeding the preset threshold is detected, the alarm system is immediately triggered to notify the risk management team to conduct an investigation and assessment. Through this step, the system can identify the borrower's abnormal fund flow pattern with a high degree of accuracy, providing strong support for risk management.

[0044] Step 2: Conduct risk assessment by monitoring the borrower’s relevant industry information;

[0045] In the embodiment of the present invention, the system collects data of various related industries and then analyzes the risks of the related industries;

[0046] Exemplarily, the system obtains data on related industries from public databases, industry reports, corporate financial statements and other data sources, including but not limited to economic indicators, industrial chain relationships, and market shares, and then performs data preprocessing. Through the collected data, the network analysis method in graph theory is used to establish an industry network map. In the map, different industries are regarded as nodes in the graph, and edges are constructed through the relationship between them. Subsequently, the established industry network map is analyzed through covariance analysis to identify the correlation between different industries and select the industry with the greatest correlation. In this embodiment, the Internet technology industry is selected as the industry with the greatest correlation. Finally, for the established industry network Based on the results of the graph and correlation analysis, the system developed a risk transfer model. First, based on the established industry network graph and correlation analysis, the system confirmed the correlation between the Internet technology industry and the financial services industry, including the potential connection between the two industries in terms of cooperation, competition and supply chain. Then, the system selected key indicators, such as the user growth rate of Internet companies, the loan issuance volume of the financial services industry and the stock market index. Then, by establishing a mathematical model, the system modeled these indicators into random variables, combined the correlation and probability distribution between them, and used the Monte Carlo simulation method to generate a large number of random samples to simulate different economic conditions and market fluctuation scenarios.

[0047] For example, the Monte Carlo simulation method is used, and its specific implementation method is as follows: First, define the risk transfer model, select the user growth rate X in the Internet technology industry 互联网 , the loan default rate in the financial services industry is Y 金融 , the stock market index is Z 股市 , establish a simplified risk transfer model, the model is as follows: Y 金融 =a*X 互联网 +b*Z 股市 +∈, where a and b are correlation coefficients, ∈ is the error term, and next, select the probability distribution when X 互联网 and Z 股市 When they obey normal distribution, their mean μ and standard deviation δ are calculated, and then random samples are generated using Monte Carlo simulation, where X 互联网 and Z 股市 The simulation method is as follows: Among them, i represents the i-th simulation. In the simulation experiment stage, the random samples obtained by simulation are substituted into the risk transfer model to calculate Y 金融 The value of for the i-th simulation: Through multiple simulations, the system can obtain different Y 金融The value of forms a probability distribution. Finally, through statistical analysis and result summary, the system can calculate the risk transfer probability and impact degree. At the same time, sensitivity analysis is performed, the correlation coefficients a and b are adjusted, and the response of the model to parameter changes is observed. In this step, simulation methods are used to more comprehensively understand the uncertainty in the risk transfer model, and provide probabilistic information about the risk transfer effect to support more accurate risk assessment and decision making.

[0048] Step 3: Implement the borrower industry risk assessment through a comprehensive risk scoring system;

[0049] In the embodiment of the present invention, a comprehensive risk score is formulated by comprehensively considering the risk transmission probability and the impact degree;

[0050] Exemplarily, the system obtains the distribution of risk transfer probability through the risk transfer model, divides the risk transfer probability into low, medium and high levels, and then divides the probability into intervals corresponding to the overall distribution. Similarly, the impact level is divided into slight, medium and severe levels. Then, the levels of transfer probability and impact level are mapped to corresponding scores, and the total score is obtained. The comprehensive score can be calculated by the following formula: Comprehensive score = risk transfer probability score + impact level score. The comprehensive risk score is divided into different risk levels, such as low risk, medium risk and high risk. Then, a real-time monitoring system is set to regularly update the real-time data of the borrower's industry and recalculate the risk score. Once the score exceeds a pre-set threshold, the early warning system can be triggered to notify the financial institution to take corresponding risk management measures. Based on the comprehensive risk score, the system generates a risk assessment report for the borrower's industry. The report should include an overview of the risk level, specific descriptions of risk factors, possible impact scenarios and recommended risk mitigation measures. Through this step, clear information can be provided to financial institutions to help them understand the risks of the borrower's industry and formulate corresponding risk management strategies.

[0051] Step 4: Conduct a comprehensive assessment of the borrower’s repayment ability and upload it to blockchain storage.

[0052] Exemplarily, a comprehensive assessment model is established to comprehensively assess individual risk U (i.e., the financial risk in step one) and industry risk V, and the comprehensive risk index W is set as follows: W = T*U+(1-T)*V, where T is the weight coefficient, which represents the relative importance of individual risk in the comprehensive assessment. By adjusting the weight, the system can flexibly balance the contribution of individual and industry risks to the comprehensive assessment. In addition, a threshold for the comprehensive risk index is set. When W is greater than the fixed threshold, a real-time warning is triggered. A smart contract is created on the blockchain to automatically perform verification and storage of uploaded data. The smart contract contains a verification algorithm to ensure that the uploaded data complies with pre-defined rules and stores the verified data in the corresponding block on the blockchain. At the same time, the blockchain provides a shared ledger, and all parties can operate on the same data without worrying about data inconsistency. This enables financial institutions, regulators and other parties to refer to the same comprehensive risk assessment results to promote cooperation and information sharing.

[0053] Embodiment 2: Embodiment 2 of the present invention provides a financial risk control system based on big data and blockchain. Figure 2 A schematic diagram of the module composition of a financial risk control system based on big data and blockchain provided in Embodiment 2 of the present invention is shown in FIG. Figure 2 As shown, the system includes:

[0054] Fund liquidity monitoring module, used to monitor borrowers' fund flows in real time, identify abnormal transaction behaviors, and strengthen risk management;

[0055] Industry risk assessment module, which is used to collect and analyze relevant industry data, build industry network maps, evaluate risk transfer models, and gain an in-depth understanding of the relationships between different industries;

[0056] Comprehensive risk scoring and blockchain storage module, which is used to comprehensively consider individual and industry risks, generate comprehensive risk scores, and achieve secure and tamper-proof data storage through blockchain to promote multi-party cooperation and information sharing;

[0057] In some embodiments of the present invention, the fund liquidity monitoring module includes:

[0058] Data access and real-time collection module, which is used to connect to the data source through the API interface, collect borrower's capital flow information in real time, and ensure timely data update;

[0059] Funds monitoring module building module, used to build a funds monitoring module, using big data analysis technology to monitor abnormal trading behavior and improve the accuracy of abnormal pattern identification;

[0060] The abnormal pattern recognition and early warning system module is used to use the capital flow model to automatically identify abnormal patterns, set thresholds for real-time monitoring, trigger the alarm system, and strengthen the real-time investigation and evaluation of the risk management team;

[0061] In some embodiments of the present invention, the industry risk assessment module includes:

[0062] Relevant industry data collection module, used to obtain relevant industry data from multiple data sources to provide a comprehensive information basis for industry risk assessment;

[0063] The industry network map building module is used to build an industry network map using network analysis methods, gain an in-depth understanding of the relationship between different industries, and provide a basis for the risk transfer model;

[0064] The correlation analysis and risk transfer model module is used to identify correlations through covariance analysis, establish risk transfer models, and use Monte Carlo simulation to evaluate the probability and impact of risk transfer;

[0065] In some embodiments of the present invention, the comprehensive risk scoring and blockchain storage module includes:

[0066] The risk transfer probability and impact comprehensive scoring module is used to comprehensively score the risk transfer probability and impact, and ensure the accuracy of risk scoring through real-time monitoring system and regular data updates;

[0067] Comprehensive assessment model building module, which is used to use the comprehensive assessment model to balance individual and industry risks, set comprehensive risk indicators, and adjust weights to suit actual conditions;

[0068] The blockchain upload and smart contract execution module is used to use smart contracts to ensure that data complies with the rules, upload it to the blockchain for storage, provide a shared ledger, and promote multi-party cooperation and information sharing.

[0069] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device 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 device.

[0070] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A financial risk control method based on big data and blockchain, characterized by: The method comprises the following steps: Step 1: Monitor the liquidity of borrowers’ funds by connecting to data sources; Step 2: Conduct risk assessment by monitoring the borrower’s relevant industry information; Step 3: Implement the borrower industry risk assessment through a comprehensive risk scoring system; Step 4: Conduct a comprehensive assessment of the borrower’s repayment ability and upload it to blockchain storage.

2. A financial risk control method based on big data and blockchain according to claim 1, characterized in that: The step of monitoring the liquidity of the borrower's funds by connecting to the data source includes: A funds monitoring module is established in the system. This module is connected to the borrower's bank system and electronic payment platform through a standard API interface to collect the borrower's fund flow information. Based on the fund flow information, real-time monitoring and analysis are carried out through big data analysis. First, the working capital information is preprocessed, including cleaning, deduplication and filling of missing values. Then, key features are extracted from the transaction records, such as transaction frequency, transaction amount, and common payment methods. The system uses these features to build a fund flow model. Then, the system automatically identifies abnormal patterns through the trained model. Finally, thresholds are set and borrowers are monitored in real time. Once an abnormal pattern exceeding the preset threshold is detected, the alarm system is immediately triggered to notify the risk management team to conduct an investigation and assessment.

3. A financial risk control method based on big data and blockchain according to claim 2, characterized in that: The steps of implementing risk assessment by monitoring the relevant industry information of the borrower include: Establish an industry network map and identify the correlation between different industries through network analysis methods in graph theory; Use Monte Carlo simulation methods to generate a large number of random samples to simulate different economic conditions and market volatility scenarios.

4. A financial risk control method based on big data and blockchain according to claim 3, characterized in that: The steps of establishing an industry network map and identifying the correlation between different industries through a network analysis method in graph theory include: The system obtains data on relevant industries from public databases, industry reports, and corporate financial statements, including but not limited to economic indicators, industrial chain relationships, and market shares, and then performs data preprocessing. Through the collected data, the system uses the network analysis method in graph theory to establish an industry network map. In the map, different industries are regarded as nodes in the graph, and edges are constructed through the relationships between them. Subsequently, the established industry network map is analyzed through covariance analysis to identify the correlation between different industries, and the Internet technology industry is selected as the industry with the greatest correlation. Finally, a risk transfer model is formulated based on the established industry network map and correlation analysis results. First, based on the established industry network map and correlation analysis, the system confirms the correlation between the Internet technology industry and the financial services industry, which includes the potential connection between the two industries in cooperation, competition, and supply chain. Next, the system selects key indicators, such as the user growth rate of Internet companies, the loan issuance volume of the financial services industry, and the stock market index. Then, by establishing a mathematical model, the system models these indicators into random variables, combines the correlation and probability distribution between them, and uses the Monte Carlo simulation method to generate a large number of random samples to simulate different economic conditions and market fluctuation scenarios.

5. A financial risk control method based on big data and blockchain according to claim 4, characterized in that: The steps of using the Monte Carlo simulation method to generate a large number of random samples and simulate different economic conditions and market fluctuation scenarios include: First, define the risk transfer model and select the user growth rate X in the Internet technology industry. 互联网 , the loan default rate in the financial services industry is Y 金融 , the stock market index is Z 股市 , establish a simplified risk transfer model, the model is as follows: Y 金融 =a*X 互联网 +b*Z 股市 +∈, where a and b are correlation coefficients, ∈ is the error term, and next, select the probability distribution when X 互联网 and Z 股市 When they obey normal distribution, their mean μ and standard deviation δ are calculated, and then random samples are generated using Monte Carlo simulation, where X 互联网 and Z 股市 The simulation method is as follows: Among them, i represents the i-th simulation. In the simulation experiment stage, the random samples obtained by simulation are substituted into the risk transfer model to calculate Y 金融 The value of for the i-th simulation: Through multiple simulations, the system can obtain different Y 金融 The value of is used to form a probability distribution. Finally, through statistical analysis and result summary, the system can calculate the risk transmission probability and impact degree. At the same time, sensitivity analysis is performed, the correlation coefficients a and b are adjusted, and the response of the model to parameter changes is observed.

6. A financial risk control method based on big data and blockchain according to claim 5, characterized in that: The steps for implementing the borrower industry risk assessment through the comprehensive risk scoring system include: The system obtains the distribution of risk transfer probability through the risk transfer model, divides the risk transfer probability into low, medium and high levels, and then divides the probability into intervals corresponding to the overall distribution. Similarly, the impact degree is divided into mild, medium and severe levels. Then, the levels of transfer probability and impact degree are mapped to corresponding scores, and the total score is obtained. The comprehensive score can be calculated by the following formula: Comprehensive score = risk transfer probability score + impact degree score. The comprehensive risk score is divided into different risk levels, such as low risk, medium risk and high risk. Then, a real-time monitoring system is set to regularly update the real-time data of the borrower's industry and recalculate the risk score. Once the score exceeds the pre-set threshold, the early warning system can be triggered to notify the financial institution to take corresponding risk management measures. Based on the comprehensive risk score, the system generates a risk assessment report for the borrower's industry. The report includes an overview of the risk level, specific description of the risk factors, impact scenarios and recommended risk mitigation measures.

7. A financial risk control method based on big data and blockchain according to claim 6, characterized in that: The steps of comprehensively evaluating the borrower's repayment ability and uploading it to the blockchain for storage include: A comprehensive assessment model is established to comprehensively evaluate individual risk U and industry risk V, and the comprehensive risk index W is set as follows: W = T*U+(1-T)*V, where T is the weight coefficient, which represents the relative importance of individual risk in the comprehensive assessment. By adjusting the weight, the system can flexibly balance the contribution of individual and industry risks to the comprehensive assessment. In addition, a threshold for the comprehensive risk index is set. When W is greater than the fixed threshold, a real-time warning is triggered. A smart contract is created on the blockchain to automatically perform the verification and storage of uploaded data. The smart contract contains a verification algorithm to ensure that the uploaded data complies with the pre-defined rules and stores the verified data in the corresponding block on the blockchain. At the same time, the blockchain provides a shared ledger so that all parties can operate on the same data without worrying about data inconsistency.

8. A financial risk control system based on big data and blockchain, characterized by: The system comprises: Fund liquidity monitoring module, used to monitor borrowers' fund flows in real time, identify abnormal transaction behaviors, and strengthen risk management; Industry risk assessment module, which is used to collect and analyze relevant industry data, build industry network maps, evaluate risk transfer models, and gain an in-depth understanding of the relationships between different industries; The comprehensive risk scoring and blockchain storage module is used to comprehensively consider individual and industry risks, generate a comprehensive risk score, and achieve secure and tamper-proof data storage through blockchain to promote multi-party cooperation and information sharing.

9. A financial risk control system based on big data and blockchain according to claim 8, characterized in that: The fund liquidity monitoring module includes: Data access and real-time collection module, which is used to connect to the data source through the API interface, collect borrower's capital flow information in real time, and ensure timely data update; The fund monitoring module building module is used to build a fund monitoring module, use big data analysis technology to monitor abnormal transaction behavior, and improve the accuracy of abnormal pattern identification; The abnormal pattern recognition and early warning system module is used to use the capital flow model to automatically identify abnormal patterns, set thresholds for real-time monitoring, trigger the alarm system, and strengthen the real-time investigation and evaluation of the risk management team.

10. A financial risk control system based on big data and blockchain according to claim 9, characterized in that: The industry risk assessment module includes: Relevant industry data collection module, used to obtain relevant industry data from multiple data sources to provide a comprehensive information basis for industry risk assessment; The industry network map building module is used to build an industry network map using network analysis methods, gain an in-depth understanding of the relationship between different industries, and provide a basis for the risk transfer model; The correlation analysis and risk transfer model module is used to identify correlations through covariance analysis, establish risk transfer models, and use Monte Carlo simulation to evaluate the probability and impact of risk transfer.

Images