A financial big data processing method based on blockchain

By using blockchain technology to anonymize customer consumption expenditure records in financial loan approval, privacy and risk control problems in the process of financial loan approval are solved, and approval speed and risk management effect are improved.

CN112651822BActive Publication Date: 2024-11-15ZHONGDE GAOLU CONSULTING (YUNNAN) CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202011529381.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-22
Publication Date
2024-11-15
Estimated Expiration
2040-12-22

AI Technical Summary

Technical Problem

During the process of financial loan approval, the customer's consumption expenditure records involve sensitive privacy issues. It is difficult to ensure the security of funds by relying solely on the flow of income information, resulting in cumbersome approval process and difficulty in risk control.

Method used

By using blockchain technology to anonymously encrypt customers' consumption expenditure records in financial loan processing methods, and recording consumption data in real time in a distributed ledger, judging repayment capabilities and risks based on income levels, and optimizing the loan approval process.

Benefits of technology

It has improved the speed of loan approval, enhanced risk control, improved the application effect of financial big data processing, and ensured the accuracy and security of financial information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112651822B_ABST
    Figure CN112651822B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of financial big data, and in particular to a financial big data processing method based on blockchain, including record application, blockchain dump, background retrieval, big data processing and conclusion inference; since the consumption expenditure record of a customer involves relatively sensitive privacy issues, it is difficult to effectively ensure the financial security of a loan project by relying solely on the information of cash flow income, which affects the approval of financial loans; therefore, the present invention uses the blockchain technology in the financial loan processing method to anonymize and encrypt the private consumption expenditure record of the loan customer, and records the consumption expenditure data of the customer in real time through the distributed ledger in the blockchain, thereby ensuring the accuracy of the financial information of the blockchain account corresponding to the customer, and then facilitating the judgment of the customer's real repayment ability and the risk control of the financial loan according to the income level, thereby enhancing the approval speed of the loan business, thereby improving the application effect of the financial big data processing method based on blockchain.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of financial big data technology, and in particular to a financial big data processing method based on blockchain. Background Art

[0002] Blockchain is a term in the field of information technology. It is a shared database. The data or information stored in it has the characteristics of being unforgeable, traceable, open and transparent, and collectively maintained. Based on these characteristics, blockchain technology has laid a solid foundation of trust, created a reliable cooperation mechanism, and has broad application prospects, including finance, including various activities related to currency circulation and bank credit.

[0003] Currently, in the approval process of financial loans, customers' consumption expenditure records involve sensitive privacy issues, and it is difficult to effectively ensure the financial security of loan projects by relying solely on cash flow information. At the same time, the limitations of the smaller scope of supporting materials make the current application and approval process more cumbersome, affecting the approval efficiency and risk control of financial loans.

[0004] Some technical solutions for blockchain-based financial big data processing have also appeared in the prior art. For example, a Chinese patent with application number 2019107088707 discloses a blockchain-based financial big data processing method and its system platform, including the following steps: an information entry unit receives input financial transaction data and sends the financial transaction data to a data optimization unit; the data optimization unit receives the financial transaction data, optimizes it, and provides the data management unit with a financial transaction data storage path; this technical solution improves the efficiency of verification and authentication algorithms and protocols, while meeting the diversified needs of the financial system, improving resource utilization and greatly simplifying the user data access experience; however, this technical solution does not solve the risk control management in the financial transaction process, especially the risk control and process optimization of financial loan business.

[0005] In view of this, in order to overcome the above-mentioned technical problems, the present invention proposes a financial big data processing method based on blockchain, which adopts a special financial big data processing method based on blockchain to solve the above-mentioned technical problems. Summary of the invention

[0006] In order to make up for the shortcomings of the prior art, the present invention proposes a financial big data processing method based on blockchain. Through the blockchain technology set in the financial loan processing method, the private consumption expenditure records of the loan customers are anonymized and encrypted, and the customer's consumption expenditure data is recorded in real time through the distributed ledger in the blockchain, ensuring the accuracy of the financial information of the blockchain account corresponding to the customer, and then facilitating the judgment of the actual repayment ability and risk control of financial loans according to the income level, thereby enhancing the approval speed of the loan business, thereby improving the application effect of the financial big data processing method based on blockchain.

[0007] The present invention provides a blockchain-based financial big data processing method, comprising the following steps:

[0008] S1. Record application: Open a blockchain account for the customer who is applying for a loan to store the expenditure record data authorized by the customer and mix it into the distributed ledger of the financial database; use blockchain technology to package the consumption data authorized by the customer to protect the customer's personal privacy and facilitate the control of the risk of the loan business;

[0009] S2, blockchain dump: When S1 records the customer's expenditure data, it also extracts the location information and expenditure records per unit time, encrypts them separately and dumps them to S1's blockchain account, and combines them with the income flow and expenditure status of the loan applicant; after anonymizing the customer data through blockchain technology, comprehensively select their income and expenditure status to further enhance the accuracy of the judgment of the user's repayment ability;

[0010] S3, backend search: After the customer's financial data is converted into a distributed ledger in the blockchain for storage, the data dumped in S2 is compared in the database and searched with the conditions of the loan projects that have been approved in the database history records to find similarities between the data; by searching with the conditions of the historical approved loan data, the existing analysis model can be used to increase the process speed of the loan approval business;

[0011] S4. Big data processing: For blockchain-based customer data, the data provided by customers are classified according to different variables, and a large amount of data is cleaned, sorted and mined to obtain the required data parameters. Through big data processing, the processing efficiency of customer-provided data can be enhanced, and effective parameter variables can be analyzed for financial institutions to make judgments;

[0012] S5, conclusion inference: Based on the retrieval and processing results of the data in S3 and S4, input them into the set variable conditions for inference to obtain the final loan approval result; by retrieving similar data in historical business and processing big data, ensure that the final inferred loan approval result complies with the risk control regulations set by the financial institution and promotes the development of loan business;

[0013] In the approval process of financial loans, since the customer's consumption expenditure records involve sensitive privacy issues, and it is difficult to effectively ensure the financial security of the loan project by relying solely on the information of cash flow income, and the limitation of the small coverage of evidence materials makes the current application and approval process more cumbersome, affecting the approval effect of financial loans; therefore, the present invention uses the blockchain technology set in the financial loan processing method to anonymize and encrypt the private consumption expenditure records of loan customers, and records the customer's consumption expenditure data in real time through the distributed ledger in the blockchain, ensuring the accuracy of the financial information of the blockchain account corresponding to the customer, and then facilitating the judgment of the customer's true repayment ability and the risk control of financial loans based on the income level, thereby enhancing the approval speed of loan business, thereby improving the application effect of the financial big data processing method based on blockchain.

[0014] Preferably, in the big data processing step, the customer's income flow data is recorded as A, and the customer's expenditure flow data is recorded as B. The difference between A and B is compared with the set statistical duration constant C to determine whether it is within the set confidence interval to determine the amount of financial loan issued; in the application process for financial loans, applicants only need to submit provable income flow data, but the applicant's consumption expenditure data has a certain volatility, and it is necessary to obtain accurate income and expenditure level data under limited conditions to control the balance between financial loan risks and returns; by setting the income and expenditure flow data recorded in the big data processing step to be determined, and comparing the statistical time of the income and expenditure data, the loan applicant's repayment ability can be judged more accurately, and the confidence interval of the test is added at the same time, the risk of financial loan issuance is further adjusted to meet financial projects with different conditions, thereby improving the application effect of the financial big data processing method based on blockchain.

[0015] Preferably, the setting range of the confidence interval is also adjusted with reference to the amount of the loan and the credit level of the applicant; as a financial institution that lends money, its risk and return coexist, and it will try to maximize its returns, that is, issue more loans, while controlling the risk; by adding adjustable variables to the confidence interval parameters used to determine loan issuance, adding the amount of the loan and the credit level of the applicant, the range of the confidence interval is expanded to increase the possibility of loan issuance, and its risk is controlled at a lower level, thereby improving the application effect of the financial big data processing method based on blockchain.

[0016] Preferably, in the big data processing step, the region where the customer is located when applying is marked as α, the work region is marked as β, and the set of income and expenditure levels is marked as γ; the three data are compared in combination to determine the accuracy of the data provided by the customer and serve as the basis for the conclusion inference step; in the financial loan approval process, reducing the risk requires screening from multiple angles of data to obtain further judgmental information; by setting up a check on the customer's application information in the data, when the application region α is consistent with the work region β, and the set of income and expenditure status γ provided is within the income and consumption level of the region and occupation between the work region β, the security of the loan business is enhanced; on the contrary, when there is a certain difference between α, β and γ, the risk of the loan business is increased, and it is necessary to further screen and investigate the customers applying for the loan, thereby stabilizing the application effect of the financial big data processing method based on blockchain.

[0017] Preferably, the analysis steps of the big data processing are as follows:

[0018] I. Binary comparison: Compare the location α where the customer applies for a loan with the recorded work location β. If there is a difference, there is a risk of financial fraud. Compare the customer's income and expenditure level set γ with the location α where the customer applies for a loan and the work location β respectively. The authenticity of the data γ and the customer's real repayment ability can be judged by the income and consumption levels of the α and β regions. Through the binary comparison between the data, the relationship between the data variables and the reliability of the information provided by the customer can be fully analyzed.

[0019] II. Cross-validation: After the binary comparison in I is completed, the data of α, β and γ are summarized together to conduct comprehensive verification of the customer to ensure that the risk of the loan application is within a controllable range; through cross-validation, the data points missed in the binary comparison step are compensated and a secondary confirmation effect is achieved;

[0020] III. Result analysis: The results of cross-validation in II are applied to the inference of loan approval, and combined with the adjustment range of the confidence interval, financial institutions can choose the balance between their returns and risks and control the overall stability of the loan business; by cross-referencing the results of cross-validation with the set range of the confidence interval, the security of the loan business of financial institutions is further enhanced.

[0021] Preferably, in the big data processing step, a permanent residence region variable δ is also set, and the variable δ participates in the cross-validation between α, β or γ respectively; when customers apply for loans, there are differences in different living, working and loan consumption areas, and only the set α, β and γ parameters will also limit the accuracy of big data processing; by setting the permanent residence region variable δ, participating in the cross-validation analysis process, the accuracy of the big data processing results is further enhanced to meet the development of loan business, thereby improving the application effect of the financial big data processing method based on blockchain.

[0022] The beneficial effects of the present invention are as follows:

[0023] 1. The present invention uses blockchain technology in the financial loan processing method to anonymize and encrypt the private consumption expenditure records of loan customers, and records the customer's consumption expenditure data in real time through the distributed ledger in the blockchain, thereby ensuring the accuracy of the financial information of the blockchain account corresponding to the customer, and then facilitating the judgment of the customer's actual repayment ability and risk control of financial loans based on the income level, thereby enhancing the approval speed of loan business.

[0024] 2. The present invention determines the repayment ability of loan applicants more accurately by comparing the flow data of income and expenditure recorded in the big data processing step and the statistical time of income and expenditure data, and adds the confidence interval of the test to further adjust the risk of financial loan issuance to meet financial projects with different conditions; by adding adjustable variables to the confidence interval parameters used to determine loan issuance, adding the loan amount and the credit level of the applicant, the range of the confidence interval is expanded to increase the possibility of loan issuance, and its risk is controlled at a lower level.

[0025] 3. The present invention sets a check on the customer application information in the data. When the application area α is consistent with the work area β, and the set of income and expenditure status γ provided is between the work area β and is within the income and consumption level of the region and occupation, the security of the loan business is enhanced. On the contrary, when there is a certain difference between α, β and γ, the risk of the loan business is increased, and it is necessary to further screen and investigate the customers who apply for the loan. The permanent residence area variable δ is set to participate in the cross-validation analysis process, which further enhances the accuracy of the big data processing results to meet the development of the loan business. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The present invention is further described below in conjunction with the accompanying drawings and implementation modes.

[0027] Figure 1 It is a flow chart of the financial big data processing method based on blockchain in the present invention;

[0028] Figure 2It is a flow chart of the big data processing and analysis steps in the present invention. DETAILED DESCRIPTION

[0029] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0030] like Figure 1-Figure 2 As shown, the financial big data processing method based on blockchain described in the present invention includes the following steps:

[0031] S1. Record application: Open a blockchain account for the customer who is applying for a loan to store the expenditure record data authorized by the customer and mix it into the distributed ledger of the financial database; use blockchain technology to package the consumption data authorized by the customer to protect the customer's personal privacy and facilitate the control of the risk of the loan business;

[0032] S2, blockchain dump: When S1 records the customer's expenditure data, it also extracts the location information and expenditure records per unit time, encrypts them separately and dumps them to S1's blockchain account, and combines them with the income flow and expenditure status of the loan applicant; after anonymizing the customer data through blockchain technology, comprehensively select their income and expenditure status to further enhance the accuracy of the judgment of the user's repayment ability;

[0033] S3, backend search: After the customer's financial data is converted into a distributed ledger in the blockchain for storage, the data dumped in S2 is compared in the database and searched with the conditions of the loan projects that have been approved in the database history records to find similarities between the data; by searching with the conditions of the historical approved loan data, the existing analysis model can be used to increase the process speed of the loan approval business;

[0034] S4. Big data processing: For blockchain-based customer data, the data provided by customers are classified according to different variables, and a large amount of data is cleaned, sorted and mined to obtain the required data parameters. Through big data processing, the processing efficiency of customer-provided data can be enhanced, and effective parameter variables can be analyzed for financial institutions to make judgments;

[0035] S5, conclusion inference: Based on the retrieval and processing results of the data in S3 and S4, input them into the set variable conditions for inference to obtain the final loan approval result; by retrieving similar data in historical business and processing big data, ensure that the final inferred loan approval result complies with the risk control regulations set by the financial institution and promotes the development of loan business;

[0036] In the approval process of financial loans, since the customer's consumption expenditure records involve sensitive privacy issues, and it is difficult to effectively ensure the financial security of the loan project by relying solely on the information of cash flow income, and the limitation of the small coverage of evidence materials makes the current application and approval process more cumbersome, affecting the approval effect of financial loans; therefore, the present invention uses the blockchain technology set in the financial loan processing method to anonymize and encrypt the private consumption expenditure records of loan customers, and records the customer's consumption expenditure data in real time through the distributed ledger in the blockchain, ensuring the accuracy of the financial information of the blockchain account corresponding to the customer, and then facilitating the judgment of the customer's true repayment ability and the risk control of financial loans based on the income level, thereby enhancing the approval speed of loan business, thereby improving the application effect of the financial big data processing method based on blockchain.

[0037] As an implementation mode of the present invention, in the big data processing step, the customer's income flow data is recorded as A, and the customer's expenditure flow data is recorded as B. The difference between A and B is compared with the set statistical duration constant C to determine whether it is within the set confidence interval to determine the amount of financial loan issued; in the application process of financial loans, applicants only need to submit provable income flow data, but the applicant's consumption expenditure data has a certain volatility, and it is necessary to obtain accurate income and expenditure level data under limited conditions to control the balance between financial loan risks and returns; by setting the income and expenditure flow data recorded in the big data processing step to be determined, and comparing the statistical time of the income and expenditure data, the loan applicant's repayment ability can be judged more accurately, and the confidence interval of the test is added at the same time, the risk of financial loan issuance is further adjusted to meet financial projects with different conditions, thereby improving the application effect of the financial big data processing method based on blockchain.

[0038] As an implementation mode of the present invention, the setting range of the confidence interval is also adjusted with reference to the amount of the loan and the credit level of the applicant; as a financial institution that lends money, the project is a project with both risks and benefits. Under the premise of controlling the risk, it will try to maximize its benefits, that is, issue more loans; by adding adjustable variables to the confidence interval parameters used to determine loan issuance, adding the amount of the loan and the credit level of the applicant, the range of the confidence interval is expanded to increase the possibility of loan issuance, and its risk is controlled at a lower level, thereby improving the application effect of the financial big data processing method based on blockchain.

[0039] As an implementation mode of the present invention, in the big data processing step, the region where the customer is located when applying is marked as α, the work region is marked as β, and the set of income and expenditure levels is marked as γ; the three data are compared in combination to determine the accuracy of the data provided by the customer and serve as the basis for the conclusion inference step; in the financial loan approval process, reducing the risk requires screening from multiple angles of data to obtain further judgmental information; by setting up a check on the customer's application information in the data, when the application region α is consistent with the work region β, and the set of income and expenditure status γ provided is within the income and consumption level range of the work region β, the security of the loan business is enhanced; on the contrary, when there is a certain difference between α, β and γ, the risk of the loan business is increased, and it is necessary to further screen and investigate the customers applying for the loan, thereby stabilizing the application effect of the financial big data processing method based on blockchain.

[0040] As an implementation of the present invention, the analysis steps of the big data processing are as follows:

[0041] I. Binary comparison: Compare the location α where the customer applies for a loan with the recorded work location β. If there is a difference, there is a risk of financial fraud. Compare the customer's income and expenditure level set γ with the location α where the customer applies for a loan and the work location β respectively. The authenticity of the data γ and the customer's real repayment ability can be judged by the income and consumption levels of the α and β regions. Through the binary comparison between the data, the relationship between the data variables and the reliability of the information provided by the customer can be fully analyzed.

[0042] II. Cross-validation: After the binary comparison in I is completed, the data of α, β and γ are summarized together to conduct comprehensive verification of the customer to ensure that the risk of the loan application is within a controllable range; through cross-validation, the data points missed in the binary comparison step are compensated and a secondary confirmation effect is achieved;

[0043] III. Result analysis: The results of cross-validation in II are applied to the inference of loan approval, and combined with the adjustment range of the confidence interval, financial institutions can choose the balance between their returns and risks and control the overall stability of the loan business; by cross-referencing the results of cross-validation with the set range of the confidence interval, the security of the loan business of financial institutions is further enhanced.

[0044] As an implementation mode of the present invention, a permanent residence region variable δ is further provided in the big data processing step, and the variable δ participates in the cross-validation between α, β or γ respectively; when customers apply for loans, there are differences in different living, working and loan consumption areas, and only the set α, β and γ parameters will also limit the accuracy of big data processing; by setting the permanent residence region variable δ, participating in the cross-validation analysis process, the accuracy of the big data processing results is further enhanced to meet the development of loan business, thereby improving the application effect of the financial big data processing method based on blockchain.

[0045] When in use, the blockchain technology set in the financial loan processing method is used to anonymize and encrypt the private consumption expenditure records of loan customers, and the distributed ledger in the blockchain records the consumption expenditure data of customers in real time to ensure the accuracy of the financial information of the blockchain account corresponding to the customer, so as to facilitate the judgment of the real repayment ability and risk control of financial loans according to the income level, thereby enhancing the approval speed of loan business; the big data processing step is set to judge the recorded income and expenditure flow data, and the statistical time of the income and expenditure data is compared to judge the loan applicant's more accurate repayment ability, and at the same time add the confidence interval of the test to further adjust the risk of financial loan issuance to meet financial projects with different conditions; the confidence interval used to determine the loan issuance The parameters increase the adjustable variables, add the loan amount and the credit level of the applicant, expand the range of the confidence interval to increase the possibility of loan issuance, and control its risk at a lower level; set up a check on the customer application information in the data. When the application area α is consistent with the work area β, and the set of income and expenditure status γ provided is between the work area β and belongs to the income and consumption level of the region and occupation, the security of the loan business is enhanced. On the contrary, when there is a certain difference between α, β and γ, the risk of the loan business is increased, and it is necessary to further screen and investigate the customers who apply for loans; the permanent residence area variable δ is set to participate in the cross-validation analysis process to further enhance the accuracy of the big data processing results to meet the development of the loan business.

[0046] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A financial big data processing method based on blockchain, characterized by: The following steps are involved: S1. Record application: Open a blockchain account for the customer who is applying for a loan to store the authorized expenditure record data and mix it into the distributed ledger of the financial database; S2, blockchain dump: When S1 records the customer's expenditure data, it also extracts the location information and expenditure records per unit time, encrypts them separately and dumps them to S1's blockchain account, and combines them with the income flow and expenditure status of the loan applicant; S3, backend search: After the customer's financial data is converted into a distributed ledger in the blockchain for storage, the data dumped in S2 is compared in the database and searched with the conditions of the loan projects that have passed in the database history records to find similarities between the data; S4. Big data processing: For blockchain-based customer data, the data provided by customers are classified according to different variables, and a large amount of data is cleaned, sorted and mined to obtain the required data parameters; S5, conclusion inference: Based on the retrieval and processing results of the data in S3 and S4, input them into the set variable conditions for inference to obtain the final loan approval result; In the big data processing step, the customer's income flow data is recorded as A, and the customer's expenditure flow data is recorded as B. The difference between A and B is simultaneously compared with the set statistical duration constant C to determine whether it is within the set confidence interval to determine the amount of financial loan issued; The confidence interval is also adjusted based on the amount of the loan and the credit level of the applicant. In the big data processing step, the region where the customer is located when applying is marked as α, the region where the customer works is marked as β, and the set of the customer's income and expenditure levels is marked as γ; the three data are compared with each other to determine the accuracy of the data provided by the customer and serve as the basis for the conclusion inference step; The analysis steps for this big data processing are as follows: I. Binary comparison: Compare the location α where the customer applies for a loan with the recorded work location β. If there is a difference, there is a risk of financial fraud. Compare the customer's income and expenditure level set γ with the location α where the customer applies for a loan and the work location β respectively. The authenticity of the data γ and the customer's actual repayment ability can be judged by the income and consumption levels of the α and β regions. II. Cross-validation: After the binary comparison in I is completed, the data of α, β and γ are summarized together to conduct comprehensive verification of the customer to ensure that the risk of the loan application is within a controllable range; III. Result analysis: Apply the cross-validation results in II to the inference of loan approval, and adjust the confidence interval to help financial institutions choose the balance between their returns and risks, and control the overall stability of the loan business; In the big data processing step, a permanent residence area variable δ is also set, and the variable δ participates in the cross-validation between α, β or γ respectively.

Citation Information

Patent Citations

  • Financial big data processing method based on block chain and system platform thereof

    CN110413649A

  • Financial loan risk control method and server

    CN108492175A

  • Credit risk assessment system and method based on weak variable data

    CN110135971A

  • Loan management method and system based on block chain, and financial institution node

    CN110503547A

  • Loan approval method and device based on machine learning, equipment and storage medium

    CN111369342A