Data risk prediction method based on block chain

Abstract

The invention discloses a data risk prediction method based on a block chain, and relates to the technical field of risk assessment, and the method comprises the following specific steps: block chain platform construction and data collection and storage: constructing a cross-industry data sharing platform based on an alliance chain architecture, establishing an industry data collection node communication link, and carrying out data collection and storage; encrypting and collecting data of each industry, adding a timestamp and a hash value, storing the data to a block chain through a consensus mechanism, and recording data collection information; according to the method, the data newly generated on the block chain and the historical change record of the corresponding data are acquired in real time, and the new and old data are compared and analyzed based on the preset updating algorithm, so that the model can accurately capture the market dynamic state and the data change trend, thereby automatically adjusting the risk assessment parameters and weights, and improving the risk assessment efficiency. The risk prediction result better fits the actual situation, the accuracy and timeliness of risk prediction are effectively improved, accurate risk early warning can be provided for all industries in time, and enterprises are assisted to take risk prevention and response measures in advance.

Description

Technical Field

[0001] The present invention relates to the field of risk assessment technology, and specifically to a data risk prediction method based on blockchain. Background Art

[0002] In the current complex and ever-changing economic environment where industries are increasingly connected, the demand for cross-industry data interaction and integration is becoming more urgent. Different industries have accumulated a large amount of data in the course of their operations. These data contain rich information and are of great significance for comprehensive risk assessment, grasping market dynamics and making scientific decisions. Blockchain technology, with its decentralized, tamper-proof and traceable characteristics, provides new ideas and solutions for the secure sharing and collaborative management of data. At the same time, data processing and risk assessment technologies, as key support, can help us extract valuable information from massive data and achieve effective prediction and management of risks.

[0003] Traditional risk prediction methods primarily focus on single-industry data and lack the ability to integrate and analyze cross-industry data. This limitation makes it difficult for traditional methods to gain comprehensive and in-depth insight into the transmission mechanism of risk across industries and accurately capture the dynamic changes in cross-industry risks, thereby reducing the comprehensiveness and accuracy of risk predictions. Traditional models have numerous drawbacks in terms of data sharing. On the one hand, data security is difficult to effectively guarantee, and data is vulnerable to security threats such as leakage and tampering during transmission and storage, posing significant risks to both data providers and users. On the other hand, access rights management is chaotic, lacking clear rules and effective regulatory mechanisms, leading to frequent problems such as data abuse and unauthorized access, which seriously hinders the rational use and value of data. Furthermore, most existing risk assessment models are static. Once constructed, their assessment parameters and weights are relatively fixed and cannot be adjusted in a timely manner based on dynamic changes in the market environment and the continuous generation of new data. This makes it difficult for these models to adapt to the complex and changing economic landscape and cannot promptly reflect the real-time status of risks. This significantly reduces the timeliness and accuracy of risk prediction results, making it difficult to meet the real-time and precision requirements of risk management in practical applications. Summary of the Invention

[0004] The purpose of this invention is to make up for the shortcomings of the existing technology and provide a data risk prediction method based on blockchain. It can realize the secure collection, storage and sharing of data from various industries by building a cross-industry data sharing and collaboration platform based on the alliance chain architecture, and use smart contracts to define data access rights and usage rules to ensure the compliance and security of data use. Based on the big data processing framework and machine learning association analysis algorithm, it integrates and analyzes cross-industry data, explores the intrinsic connections between industry data, and constructs a dynamic risk assessment model so that it can automatically update and adjust with time and data changes, thereby improving the accuracy and timeliness of risk prediction. Finally, through risk transmission simulation and smart contract-driven risk response strategy execution mechanism, it realizes collaborative management and dynamic response of cross-industry risks, providing a comprehensive and efficient solution for the effective management of cross-industry risks.

[0005] To solve the above technical problems, the present invention provides the following technical solution: a data risk prediction method based on blockchain, which includes the following specific steps: Blockchain platform construction and data collection and storage: Build a cross-industry data sharing platform based on the alliance chain architecture, establish communication links for industry data collection nodes, encrypt and collect data from various industries, add timestamps and hash values, store them on the blockchain through a consensus mechanism, and record data collection information; Definition of data access rights and usage rules: Based on smart contracts, data access rights rules for different user roles are compiled to set the scope, purpose, sharing conditions, and violation handling mechanism of data usage. When users operate, smart contracts are used to verify whether the permissions and operation behaviors are in compliance. Cross-industry data integration and correlation analysis: Utilize a distributed data processing framework to decrypt and integrate cross-industry encrypted data on the blockchain. After cleaning and conversion, a comprehensive data set is constructed. After extracting data features, potential correlations between industry data are explored, the degree of industry correlation is quantified, and the uncertainty of risk propagation is assessed, providing data support for risk assessment. Construction of a dynamic risk assessment model based on blockchain: A dynamic risk assessment model is built based on blockchain historical data and industry association models, with initial weights assigned to assessment indicators. By obtaining new data and historical change records, risk assessment parameters and weights are automatically adjusted after comparative analysis to calculate a comprehensive risk index. Risk transmission simulation and response strategy formulation and execution: Based on the results of dynamic risk assessment, a risk transmission simulation model is constructed, and risk event parameters are set to simulate the transmission process. The direction, intensity and scope of risk transmission are predicted, and risk response strategies are formulated and converted into smart contracts. When the trigger conditions are met, the response measures are automatically executed according to the calculated execution strength, realizing cross-industry risk collaborative response.

[0006] Furthermore, in the steps of building the blockchain platform and collecting and storing data, data from various industries are collected in an encrypted manner. Industry data include interest rates and credit data in the financial industry, prices and supply and demand data in the energy industry, and production and inventory data in the manufacturing industry.

[0007] Furthermore, in the cross-industry data integration and correlation analysis step, based on the distributed data processing framework, the cross-industry encrypted data stored on the blockchain is decrypted and integrated, and data partitioning and parallel processing technology are used to partition the data of different industries according to industry categories and time dimensions for storage and processing. Data cleaning technology is used to remove duplicate, erroneous or incomplete data records, and data conversion technology is used to uniformly convert data in different formats into a standard format. According to preset integration rules, the data of various industries are integrated into a comprehensive data set to build a cross-industry data warehouse. Data feature extraction technology is used to extract key feature information from the integrated cross-industry data. The industry correlation strength formula is used to explore the potential correlation relationship between data from different industries, determine the influencing factors and correlation patterns between industry data, and provide a data basis for risk assessment and simulation. At the same time, the risk transmission path entropy formula is used to assess the uncertainty of risk propagation in the industry network.

[0008] Furthermore, in the cross-industry data integration and correlation analysis step, data feature extraction technology is used to extract key feature information from the integrated cross-industry data, and the industry correlation strength formula is used. Explore the potential correlation between data from different industries and determine the influencing factors and correlation patterns between industry data, including: For the industry and the industry The strength of association, It is The importance weight of each data dimension, Indicates industry and In the The relevance of dimensions, and Industry and In the Dimensional data features, is the total number of data dimensions. By calculating this formula, the degree of correlation between industries can be quantified, providing a data basis for risk assessment and simulation.

[0009] Furthermore, in the cross-industry data integration and correlation analysis step, the risk transmission path entropy formula is used Assess the uncertainty of risk propagation in industry networks, where For risks from the industry arrive The conduction path entropy, It is an industry Probability of a risk event occurring For the industry and The strength of association, The total number of industries.

[0010] Furthermore, in the step of constructing the dynamic risk assessment model based on blockchain, on the blockchain platform, based on the stored historical data and data change records, combined with the cross-industry data association model, a dynamic risk assessment model is constructed, and the risk factors involved in each industry are abstracted as evaluation indicators in the model. Each evaluation indicator corresponds to one or more data features, and an initial weight is assigned to each evaluation indicator. The model adopts a layered architecture design, including a data input layer, a feature processing layer, a risk assessment layer, and a result output layer. The risk assessment function is realized through data transmission and processing logic between each layer. As time goes by and new data is generated and stored on the blockchain, the dynamic risk assessment model automatically monitors and obtains new data and historical change records of corresponding data through data monitoring and acquisition technology, and uses data comparison and analysis technology to compare new data with historical data, analyze the data change trend, fluctuation range and abnormal situation, and according to the data comparison and analysis results, the risk assessment parameters and weights are automatically adjusted based on the risk indicator dynamic weight adjustment formula, and the adjusted weights are used to calculate the comprehensive risk index.

[0011] Furthermore, in the step of constructing the dynamic risk assessment model based on blockchain, the risk indicator dynamic weight adjustment formula ,According to the results of data comparison and analysis, the risk assessment parameters and weights are automatically adjusted, For time Time Indicator Weight Is the indicator of the previous period The weight of For indicators The credibility change rate, is the weight-adjusted sensitivity coefficient, is the time attenuation coefficient, is an indicator The last update time of the adjusted weight is used to calculate the comprehensive risk index, which is calculated as follows: ,in For time The comprehensive risk index, is an indicator The risk value mapping function, is the time interval since the last evaluation, is the time influencing factor.

[0012] Furthermore, in the risk transmission simulation and response strategy formulation execution step, a risk transmission simulation model is constructed based on the risk assessment results output by the dynamic risk assessment model. Each industry is represented as a node in the simulation model, and the correlation between industries is abstracted as the connecting edges between nodes. The weights of the connecting edges are determined based on the results of cross-industry data correlation analysis. By setting the initial parameters of risk events in different industries, the risk transmission intensity prediction formula is used to simulate the occurrence and evolution process of risk events in the industry network, and the transmission direction and intensity of risks between industries are predicted. At the same time, the risk impact range prediction formula is used to estimate the range of industries that the risk may affect. Based on the output results of the risk transmission simulation model, targeted risk response strategies are formulated, and the risk response strategies are converted into smart contract codes. The triggering conditions of risk events are set in the smart contract. The triggering conditions are based on the threshold of the risk assessment indicator or the risk transmission simulation results. When the blockchain monitors that the actual risk event meets the triggering conditions of the smart contract, the risk response trigger function is used to determine whether to execute the response measures, thereby achieving coordinated response to cross-industry risks.

[0013] Furthermore, in the risk transmission simulation and response strategy formulation execution steps, the risk transmission intensity prediction formula is used Simulate the occurrence and evolution of risk events in the industry network, including: For the industry exist The risk value at the moment, It is an industry The risk value at time For the industry and The strength of association, is the conduction attenuation coefficient, It is an industry arrive The conduction distance, is the path entropy influence coefficient, The entropy of the risk transmission path is calculated by the formula to predict the transmission direction and intensity of risks between industries. At the same time, the risk spread range prediction formula is used Estimate the scope of industries that the risk may affect, including For time The scope of risk, is a step function used for threshold judgment, is the risk transmission threshold.

[0014] Furthermore, in the risk transmission simulation and response strategy formulation execution step, when the blockchain monitors that the actual risk event meets the triggering conditions of the smart contract, the risk response trigger function Determine whether to implement countermeasures, including For time The trigger factor, is an indicator In time The risk value, is an indicator The trigger threshold, is the response attenuation coefficient, is an indicator exist The risk change rate at the moment, if triggered, the smart contract automatically executes the corresponding countermeasures, through the countermeasure intensity formula Determine the implementation strength of the measures, including For time the intensity of response measures, is an indicator The response weight, It is a nonlinear response coefficient, thereby achieving coordinated response to cross-industry risks.

[0015] Compared with existing technologies, this blockchain-based data risk prediction method has the following beneficial effects: 1. This invention obtains newly generated data on the blockchain and the historical change records of the corresponding data in real time, and compares and analyzes the new and old data based on a preset update algorithm. The model can accurately capture market dynamics and data change trends, thereby automatically adjusting risk assessment parameters and weights to make risk prediction results more in line with actual conditions, effectively improving the accuracy and timeliness of risk prediction, and can provide accurate risk warnings to various industries in a timely manner, helping enterprises to prepare risk prevention and response measures in advance.

[0016] 2. The present invention fully records historical data changes and the risk assessment process through the tamper-proof and traceable characteristics of blockchain. Any changes in data in various links such as data collection, storage and subsequent processing will be recorded in detail on the blockchain, providing a reliable historical data basis for risk analysis, making the data source clear and the operation process transparent, greatly enhancing the credibility of the data. At the same time, it also makes the risk assessment process highly auditable, facilitating the subsequent tracing and verification of risk assessment results.

[0017] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0019] Figure 1 This is a flowchart of the data risk prediction method based on blockchain; Figure 2 The flowchart of the data risk prediction method based on blockchain. DETAILED DESCRIPTION

[0020] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments. Example 1

[0021] In the energy industry, smart sensors are deployed at oil and gas field production sites to collect data such as oil and natural gas production volume and quality parameters in real time. In the energy trading market, by connecting to the trading system, real-time transaction prices, transaction volumes, import and export volumes and other data of energy are obtained. In the financial industry, in addition to collecting data such as the scale of bank credit issuance to energy companies, interest rates, and non-performing loan rates on a daily basis, financial statement data of energy companies are also collected, including indicators such as debt-to-asset ratio, current ratio, net profit, and corporate credit rating data. After the data is collected, it is encrypted, such as Figure 1 As shown, to ensure the security of data during transmission and storage, add a timestamp and hash value accurate to the second for each data, and then store the data in the blockchain through the consensus mechanism of the alliance chain. During the data storage process, the data credibility scoring mechanism is strictly implemented, and the data is evaluated from multiple dimensions such as the reliability of the source, the stability of the collection frequency, and the consistency with historical data. For data with credibility lower than the set threshold, it is automatically marked and the manual review process is triggered. If the review fails, it will be eliminated to ensure data quality from the source. Based on the distributed data processing framework, the massive data of the financial and energy industries stored on the blockchain are decrypted and integrated, and data feature extraction is performed using technologies such as autoencoders to dig out the deep features hidden behind the data. By using the industry correlation strength formula Quantify the degree of correlation between industries, among which, For the industry and the industry The strength of association, It is The importance weight of each data dimension, Indicates industry and In the The relevance of dimensions, and Industry and In the Dimensional data features, is the total number of data dimensions. For example, when oil prices continue to fall by more than 15% and last for 30 days, the formula calculation and analysis shows that about 70% of oil extraction companies will see a 20%-30% drop in revenue and a 30%-40% drop in net profit. This deterioration in operating conditions will cause the company's credit rating to drop by an average of 1-2 levels within 3 months, thereby increasing the probability of credit default risk of these companies by financial institutions from the original 5% to 15%-20%. At the same time, using the risk transmission path entropy formula Assess the uncertainty of risk propagation in industry networks, where For risks from the industry arrive The conduction path entropy, It is an industry The probability of a risk event occurring, For the industry and The strength of association, The total number of industries.

[0022] Construct a dynamic risk assessment model, comprehensively consider the supply and demand situation of the energy market, the policy environment, the credit policy and capital status of financial institutions and other factors, and assign initial weights to risk assessment indicators such as energy price fluctuations, corporate revenue, credit scale of financial institutions, and policy changes. As new data are continuously generated, the model automatically obtains data and historical change records through the real-time data monitoring interface, and uses the risk indicator dynamic weight adjustment formula ,According to the data change trend and credibility change, the weight of each indicator is accurately adjusted, among which, For time Time Indicator The weight of Is the indicator of the previous period The weight of For indicators The credibility change rate, is the weight-adjusted sensitivity coefficient, is the time attenuation coefficient, is an indicator For example, when the country introduces a new energy subsidy policy to vigorously support the development of clean energy, the model will quickly identify this policy change and increase the weight of energy policy-related indicators from the initial 15% to 30% in a short period of time through this formula. At the same time, the weight of traditional energy price fluctuation indicators is correspondingly reduced. Through the comprehensive risk index calculation formula Real-time calculation of comprehensive risk index, including For time The comprehensive risk index, is an indicator The risk value mapping function, is the time interval since the last evaluation, It is a time impact factor that reflects the current risk level in the intersection of the financial and energy industries.

[0023] Using the risk transmission simulation model, we set the extreme risk event parameters of a sudden and sharp drop of 30% in oil prices, simulated its transmission process in the financial and energy industry network, and used the risk transmission intensity prediction formula to predict the risk of oil price drop. Predict the direction and intensity of risk transmission between industries, including: For the industry exist The risk value at the moment, It is an industry Value at risk at time For the industry and The strength of association, is the conduction attenuation coefficient, It is an industry arrive The conduction distance is the path entropy influence coefficient, is the risk transmission path entropy. By calculating this formula, it is predicted that the risk will first be transmitted from oil extraction companies to oil processing companies, resulting in a decrease in the raw material costs of processing companies, but at the same time, the product sales price will also decrease, and the profit space of companies will be compressed. This impact will be further transmitted to financial institutions that provide credit support to these companies. It is expected that within 6 months, the non-performing loan rate of relevant financial institutions to energy companies will increase from the current 3% to about 8%, and the quality of credit assets will decline significantly. At the same time, using the risk spread prediction formula Estimate the scope of industries that the risk may affect, including For time The scope of risk, is a step function used for threshold judgment, Based on the simulation results, financial institutions, energy companies and regulatory authorities jointly formulate a comprehensive response strategy for the risk propagation threshold and convert it into a smart contract. When the blockchain monitors that the actual energy price drop meets the trigger conditions, the risk response trigger function Determine whether to implement countermeasures, including For time The trigger factor, is an indicator In time The risk value, is an indicator The trigger threshold, is the response attenuation coefficient, is an indicator exist The risk change rate at the moment, if triggered, the smart contract automatically executes the corresponding response measures, through the response measures intensity formula Determine the implementation strength of the measures, including For time the intensity of response measures, is an indicator The response weight, It is a nonlinear response coefficient. As for financial institutions, the loan interest rate for energy companies will be increased by 10%-15% one month in advance, the credit line will be tightened, and the scale of new credit will be reduced by 30%. At the same time, energy companies will be required to supplement collateral or provide additional guarantees. Energy companies will initiate cost-cutting plans, optimize production processes, reduce production scale by 20%-30%, reduce unnecessary expenses, strengthen communication with suppliers and customers, and strive for more favorable transaction terms to ease financial pressure. In addition, regulatory authorities will also adjust regulatory policies in a timely manner according to risk conditions, strengthen supervision of financial institutions and energy companies, ensure stable market operation, and minimize risk impact. Example 2

[0024] In the manufacturing sector, in addition to collecting basic data such as production plans, raw material inventory, and product output, equipment operating status data, such as equipment failure rate, operating time, and energy consumption data, are also obtained from the Internet of Things system of production equipment. Raw material procurement cycles, supplier delivery punctuality rates, and raw material quality spot check data are collected from the supplier management system. In the consumer industry, e-commerce platforms not only provide product sales and sales volume data, but also collect consumers' browsing time, added-to-cart product lists, and product evaluation text data. Retail stores collect daily store traffic and conversion rate data by installing customer flow counters, and also collect member consumption habit data, including consumption frequency, preferred brands, and consumption time periods. All collected data is encrypted to prevent data leakage, and an accurate timestamp and unique hash value are added to each piece of data to ensure data traceability and integrity. The data is stored in the blockchain network through the blockchain's alliance chain consensus mechanism. When storing data, a data credibility scoring mechanism is used to evaluate from multiple angles such as the stability of the data collection equipment, the continuity of data upload, and the matching degree of data with industry benchmark data.

[0025] With the help of distributed data processing frameworks such as Figure 2 As shown, the manufacturing and consumer industry data stored on the blockchain are decrypted and integrated, sentiment analysis and keyword extraction are performed on consumers' product evaluation texts, consumers' potential needs and dissatisfaction are explored, and cluster analysis is used to classify consumers' purchasing behavior data to divide different consumer groups and consumption preference types. Through correlation analysis, it was found that when the positive review rate of a certain type of smart wearable product among young consumers suddenly increased by 20% within a month and the search volume of the product on the e-commerce platform increased by 30%, if the related manufacturing companies failed to adjust their production plans in time, their inventory turnover rate would drop by 15%-20% in the next two months, and the order loss rate due to out-of-stock would reach 10%-15%. Further analysis also found that the increased attention paid by consumers to the appearance design of products will drive the manufacturing companies to increase their investment in R&D and design, and this impact will be reflected in the changes in the product's market share in 3-6 months. A dynamic risk assessment model is constructed for the manufacturing and consumer industries, which comprehensively considers factors such as consumer market trends, manufacturing production capacity, and supply chain stability. Initial weights are assigned to risk assessment indicators such as changes in consumer demand, product inventory levels, raw material supply reliability, and production equipment failure rates. As consumption data and manufacturing production data are updated in real time, the model automatically obtains new data and historical data change records through the data monitoring module. Machine learning algorithms are used to analyze data and determine data change trends and potential risks. When early seasonal fluctuations in market demand for a certain type of consumer product are detected, the model will quickly adjust the weight of the consumer demand change indicator from the initial 20% to 35% based on historical data and current trends. At the same time, the weight of the inventory backlog risk indicator caused by untimely production plan adjustments will be reduced. By calculating the comprehensive risk index in real time and displaying the risk evolution trend in the form of dynamic charts, it provides companies and regulatory authorities with intuitive risk assessment results, facilitating timely decision-making.

[0026] Using the risk transmission simulation model, we set the risk event parameter of a sudden 40% drop in consumer demand for a popular consumer electronic product, and simulated its transmission process in the manufacturing and consumer industry network. Through analysis and prediction, it is predicted that the risk will first affect the manufacturing companies producing this product, resulting in a sharp drop in the company's order volume and an increase in the idle rate of production equipment. Then it will be transmitted to the raw material suppliers, causing their inventory backlogs and difficulty in recovering funds. Subsequently, it will also affect the retail stores selling this product, resulting in a decrease in customer flow and a decline in sales. It is estimated that within 3 months, the profit margins of related manufacturing companies will drop by 25%-30%, and the operating profits of retail stores will drop by 15%-20%. Based on the simulation results, manufacturing companies, suppliers, retail stores and industry associations are organized to jointly formulate response strategies and convert them into smart contracts. When the blockchain monitors the changes in actual consumption data that meet the trigger conditions, the smart contract automatically executes the response measures. Manufacturing companies immediately adjust their production plans and reduce the output of the product by 50%. At the same time, they increase investment in new product research and development, adjust product structure, negotiate with suppliers, reduce raw material procurement, and optimize inventory management. Suppliers adjust production plans according to corporate needs, reduce inventory levels, and open up new customer channels. Retail stores carry out promotional activities, clear inventory goods, strengthen market research, adjust product display and sales strategies, and introduce new popular products. Industry associations strengthen market information sharing, coordinate resources from all parties, promote the coordinated development of the industrial chain, and jointly reduce losses caused by risks.

[0027] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. The data risk prediction method based on blockchain is characterized by: The method comprises the following specific steps: Blockchain platform construction and data collection and storage: Build a cross-industry data sharing platform based on the alliance chain architecture, establish communication links for industry data collection nodes, encrypt and collect data from various industries, add timestamps and hash values, store them on the blockchain through a consensus mechanism, and record data collection information; Definition of data access rights and usage rules: Based on smart contracts, data access rights rules for different user roles are compiled to set the scope, purpose, sharing conditions, and violation handling mechanism of data usage. When users operate, smart contracts are used to verify whether the permissions and operation behaviors are in compliance. Cross-industry data integration and correlation analysis: Utilize a distributed data processing framework to decrypt and integrate cross-industry encrypted data on the blockchain. After cleaning and conversion, a comprehensive data set is constructed. After extracting data features, potential correlations between industry data are explored, the degree of industry correlation is quantified, and the uncertainty of risk propagation is assessed, providing data support for risk assessment. Construction of a dynamic risk assessment model based on blockchain: A dynamic risk assessment model is built based on blockchain historical data and industry association models, with initial weights assigned to assessment indicators. By obtaining new data and historical change records, risk assessment parameters and weights are automatically adjusted after comparative analysis to calculate a comprehensive risk index. Risk transmission simulation and response strategy formulation and execution: Based on the results of dynamic risk assessment, a risk transmission simulation model is constructed, and risk event parameters are set to simulate the transmission process. The direction, intensity and scope of risk transmission are predicted, and risk response strategies are formulated and converted into smart contracts. When the trigger conditions are met, the response measures are automatically executed according to the calculated execution strength, realizing cross-industry risk collaborative response.

2. The data risk prediction method based on blockchain according to claim 1 is characterized in that: During the steps of building the blockchain platform and collecting and storing data, data from various industries are collected in an encrypted manner. The industry data include interest rates and credit data in the financial industry, prices and supply and demand data in the energy industry, and production and inventory data in the manufacturing industry.

3. The data risk prediction method based on blockchain according to claim 1 is characterized in that: In the cross-industry data integration and correlation analysis step, based on the distributed data processing framework, the cross-industry encrypted data stored on the blockchain is decrypted and integrated, and data partitioning and parallel processing technology is used to partition the data of different industries according to industry categories and time dimensions for storage and processing. Data cleaning technology is used to remove duplicate, erroneous or incomplete data records, and data conversion technology is used to uniformly convert data in different formats into a standard format. According to preset integration rules, the data of various industries are integrated into a comprehensive data set to build a cross-industry data warehouse. Data feature extraction technology is used to extract key feature information from the integrated cross-industry data. The industry correlation strength formula is used to explore the potential correlation relationship between data from different industries, determine the influencing factors and correlation patterns between industry data, and provide a data basis for risk assessment and simulation. At the same time, the risk transmission path entropy formula is used to assess the uncertainty of risk propagation in the industry network.

4. The data risk prediction method based on blockchain according to claim 3 is characterized in that: In the cross-industry data integration and correlation analysis steps, data feature extraction technology is used to extract key feature information from the integrated cross-industry data, and the industry correlation strength formula is used. Explore the potential correlation between data from different industries and determine the influencing factors and correlation patterns between industry data, including: For the industry and the industry The strength of association, It is The importance weight of each data dimension, Indicates industry and In the The relevance of dimensions, and Industry and In the Dimensional data features, is the total number of data dimensions. By calculating this formula, the degree of correlation between industries can be quantified, providing a data basis for risk assessment and simulation.

5. The data risk prediction method based on blockchain according to claim 4 is characterized in that: In the cross-industry data integration and correlation analysis steps, the risk transmission path entropy formula is used Assess the uncertainty of risk propagation in industry networks, where For risks from the industry arrive The conduction path entropy, It is an industry Probability of a risk event occurring For the industry and The strength of association, The total number of industries.

6. The data risk prediction method based on blockchain according to claim 1 is characterized in that: In the step of constructing the dynamic risk assessment model based on blockchain, on the blockchain platform, based on the stored historical data and data change records, combined with the cross-industry data association model, a dynamic risk assessment model is constructed, and the risk factors involved in each industry are abstracted as evaluation indicators in the model. Each evaluation indicator corresponds to one or more data features, and an initial weight is assigned to each evaluation indicator. The model adopts a layered architecture design, including a data input layer, a feature processing layer, a risk assessment layer, and a result output layer. The risk assessment function is realized through data transmission and processing logic between each layer. As time goes by and new data is generated and stored on the blockchain, the dynamic risk assessment model automatically monitors and obtains new data and historical change records of corresponding data through data monitoring and acquisition technology, and adopts data comparison and analysis technology to compare new data with historical data, analyze the data change trend, fluctuation range and abnormal situation, and according to the data comparison and analysis results, the risk assessment parameters and weights are automatically adjusted based on the risk indicator dynamic weight adjustment formula, and the adjusted weights are used for comprehensive risk index calculation.

7. The data risk prediction method based on blockchain according to claim 6 is characterized in that: In the step of constructing the dynamic risk assessment model based on blockchain, the dynamic weight adjustment formula based on risk indicators is ,According to the results of data comparison and analysis, the risk assessment parameters and weights are automatically adjusted, For time Time Indicator Weight Is the indicator of the previous period The weight of For indicators The credibility change rate, is the weight-adjusted sensitivity coefficient, is the time attenuation coefficient, is an indicator The last update time of the adjusted weight is used to calculate the comprehensive risk index, which is calculated as follows: ,in For time The comprehensive risk index, is an indicator The risk value mapping function, is the time interval since the last evaluation, is the time influencing factor.

8. The data risk prediction method based on blockchain according to claim 1 is characterized in that: In the risk transmission simulation and response strategy formulation execution step, a risk transmission simulation model is constructed based on the risk assessment results output by the dynamic risk assessment model. Each industry is represented as a node in the simulation model, and the correlation between industries is abstracted as the connection edge between the nodes. The weight of the connection edge is determined according to the results of the cross-industry data correlation analysis. By setting the initial parameters of risk events in different industries, the risk transmission intensity prediction formula is used to simulate the occurrence and evolution process of risk events in the industry network, and the transmission direction and intensity of risks between industries are predicted. At the same time, the risk impact range prediction formula is used to estimate the range of industries that the risk may affect. According to the output results of the risk transmission simulation model, targeted risk response strategies are formulated, and the risk response strategies are converted into smart contract codes. The trigger conditions of risk events are set in the smart contract. The trigger conditions are based on the threshold of the risk assessment indicator or the risk transmission simulation results. When the blockchain monitors that the actual risk event meets the trigger conditions of the smart contract, the risk response trigger function is used to determine whether to execute the response measures, thereby realizing coordinated response to cross-industry risks.

9. The data risk prediction method based on blockchain according to claim 8 is characterized in that: In the risk transmission simulation and response strategy formulation execution steps, the risk transmission intensity prediction formula is used Simulate the occurrence and evolution of risk events in the industry network, including: For the industry exist The risk value at the moment, It is an industry The risk value at time For the industry and The strength of association, is the conduction attenuation coefficient, It is an industry arrive The conduction distance, is the path entropy influence coefficient, The entropy of the risk transmission path is calculated by the formula to predict the transmission direction and intensity of risks between industries. At the same time, the risk spread range prediction formula is used Estimate the scope of industries that the risk may affect, including For time The scope of risk, is a step function used for threshold judgment, is the risk transmission threshold.

10. The data risk prediction method based on blockchain according to claim 8 is characterized in that: In the risk transmission simulation and response strategy formulation execution step, when the blockchain monitors that the actual risk event meets the triggering conditions of the smart contract, the risk response trigger function Determine whether to implement countermeasures, including For time The trigger factor, is an indicator In time The risk value, is an indicator The trigger threshold, is the response attenuation coefficient, is an indicator exist The risk change rate at the moment, if triggered, the smart contract automatically executes the corresponding countermeasures, through the countermeasure intensity formula Determine the implementation strength of the measures, including For time the intensity of response measures, is an indicator The response weight, It is a nonlinear response coefficient, thereby achieving coordinated response to cross-industry risks.

Images