Financial service real-time big data rule engine processing method and system

Abstract

The invention relates to the technical field of digital finance, and discloses a financial service real-time big data rule engine processing system which comprises a data collection module, a data processing module, a data analysis module, a data security module, a real-time monitoring module, a machine learning module and an anomaly detection module. The data collection module is used for collecting transaction records, account changes, credit records and behavior data of personal loan business; and the data processing module fills the missing data by using the mean value and the median, and processes the transaction, transfer and exchange of the virtual currency. By collecting the number of transactions in unit time, the number of times of high-frequency application of loans in a short period and the number of times of repeated application of the same or similar amount of loans, whether an abnormal transaction phenomenon exists in the loan business of the individual user can be efficiently and accurately determined.

Description

Technical Field

[0001] The present invention relates to the field of digital financial technology, and more specifically to a method and system for processing a real-time big data rule engine for financial services. Background Art

[0002] The application of real-time big data rule engine technology in the financial industry is becoming increasingly important, especially in risk management, compliance monitoring, customer service, transaction analysis, etc. Real-time big data rule engine technology provides the financial industry with powerful data processing and decision support capabilities, which can effectively improve business efficiency and risk management capabilities. With the continuous development of technology, its application scenarios will be more extensive in the future, promoting the digital transformation of the financial industry.

[0003] Financial business mainly involves the processing of personal loan credit and business data. This will break the information blockage of the personal loan bad industry, and introduce big data computing power models to achieve a comprehensive analysis of personal loan business.

[0004] The existing patent discloses a business data processing method and system based on blockchain and digital finance (publication number CN1 18313943A), which specifically relates to the field of digital financial technology, including a sub-region division module, a sub-region clearing information collection module, a sub-region clearing efficiency analysis module, a target region clearing efficiency analysis module, a judgment module, and an interactive feedback module. In the technology disclosed in this patent, for personal loan business, there is a lack of how to specifically analyze the financial credit issues of personal loans, and a lack of judgment on whether there are abnormalities in specific financial loan transactions. Summary of the invention

[0005] The main technical problem solved by the present invention is to provide a financial business real-time big data rule engine processing method and system, which solves the problems in the above-mentioned background technology.

[0006] To solve the above technical problems, according to one aspect of the present invention, more specifically, a financial business real-time big data rule engine processing system includes a data collection module, a data processing module, a data analysis module, a data security module, a real-time monitoring module, a machine learning module and an anomaly detection module;

[0007] The data collection module is used to collect transaction records, account changes, credit records and behavioral data of personal loan business;

[0008] The data processing module fills in missing data by using the mean and median, and processes the buying, selling, transfer and exchange of virtual currencies;

[0009] The data analysis module is used to analyze the basic characteristics of the data, the changing trend of the data and the risk assessment of the personal loan business;

[0010] The data security module ensures the security of data during storage and transmission through data encryption technology, and sets permissions so that only authorized personnel can access sensitive data;

[0011] The real-time monitoring module is used to monitor the access status of personal loan business to ensure that the detected anomalies can be handled in time;

[0012] The anomaly detection module is used to identify unusual or abnormal patterns in the data and feed the anomaly back to the data processing module;

[0013] The machine learning module is used to train models based on historical data and to make automated financial transaction decisions based on data analysis and prediction results.

[0014] Furthermore, the data processing module specifically includes: a data integration module and a currency transaction module;

[0015] The data integration module is used to merge data from different sources into a unified data set;

[0016] The currency transaction module is used to process the sale, transfer and exchange of virtual currency; and the currency transaction module includes a currency supervision module;

[0017] The currency supervision module is used to supervise the process of currency transactions and terminate the transaction when there is an abnormal transaction.

[0018] Furthermore, the data integration module specifically includes: an on-chain integration module and a data aggregation module;

[0019] The on-chain integration module is used to integrate data collected by different blockchains and digital financial platforms, and use blockchain analysis tools to track and analyze on-chain activities;

[0020] The data aggregation module is used to aggregate data collected from different sources into a unified data set.

[0021] Furthermore, in the personal loan business data collected by the anomaly detection module, the creditworthiness of individual users is determined based on the proportion of the amount of personal loans used to purchase valuables in the loan amount, the length of time the personal loan account has been opened, and the debt-to-income ratio, as follows:

[0022]

[0023] In the formula, c represents the credit coefficient of the individual user in the loan business, a represents the proportion of the amount of personal loans for purchasing valuables in the loan amount, t represents the length of time the personal loan account is opened, and s represents the ratio of the total liabilities to the total income of the borrower in the personal loan business.

[0024] Furthermore, the anomaly detection module determines the probability of anomaly transactions in the personal user loan business based on the number of transactions collected within a unit time, the number of high-frequency loan applications in a short period of time, and the number of repeated applications for the same or similar amount of loans, as follows:

[0025]

[0026] Where W represents the probability of anomalies in transactions of personal user loan business, and:

[0027]

[0028] In the formula, m represents the transaction abnormality coefficient of individual users in loan business, n represents the number of transactions of individual users in loan business per unit time, u represents the number of high-frequency loan applications in a short period of time, and g represents the number of repeated applications for loans of the same or similar amount;

[0029] When W≤45%, it indicates that there are transaction abnormalities in the loan business of the individual user.

[0030] Furthermore, the data analysis module specifically includes: a descriptive analysis module, a predictive analysis module and a risk analysis module;

[0031] The descriptive analysis module is used for the mean, variance and frequency distribution of statistical data;

[0032] The predictive analysis module is used to analyze historical data through time series and predict future trends;

[0033] The risk analysis module is used to assess the risk of personal loans and conduct scenario analysis based on the risk assessment of personal loans.

[0034] Furthermore, the data security module specifically includes: a data encryption module and an access control module;

[0035] The data encryption module is used to encrypt sensitive data to protect privacy;

[0036] The access control module is used to set access rights and ensure that only authorized personnel can access sensitive data.

[0037] A processing method of a financial business real-time big data rule engine processing system comprises the following steps:

[0038] S 1. Collect data on personal loan business;

[0039] S2. Process and integrate the collected data, and make changes to the post-transaction data;

[0040] S3. Monitor and collect transaction change data in real time;

[0041] S4. Analyze and evaluate the creditworthiness of individual users in personal loan business;

[0042] S5. When it is determined that a user has made abnormal transactions, immediate feedback will be provided to the currency regulatory department.

[0043] The beneficial effects of the financial business real-time big data rule engine processing method and system of the present invention are:

[0044] 1. The present invention can efficiently and accurately determine whether there are any abnormal transactions in the loan business of individual users by collecting the number of transactions per unit time, the number of high-frequency loan applications in a short period of time, and the number of repeated applications for loans of the same or similar amount.

[0045] 2. The present invention determines the credit factor of individual users by collecting personal loan business data, including the proportion of the amount of personal loans for purchasing valuables in the loan amount, the length of time the personal loan account is opened, and the debt-to-income ratio. The credit factor can be used to intuitively judge the risk of lending to individual users. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0047] Figure 1 This is a flow chart of data processing in financial services in the present invention. DETAILED DESCRIPTION

[0048] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0049] like Figure 1 According to one aspect of the present invention, a processing method of a financial business real-time big data rule engine processing system is provided, comprising the following steps:

[0050] Step 1: Collect data on personal loan business;

[0051] Step 2: Process and integrate the collected data, and make changes to the post-transaction data;

[0052] Step 3: Monitor and collect transaction change data in real time;

[0053] Step 4: Analyze and evaluate the credit worthiness of individual users in the personal loan business;

[0054] Step 5: When it is determined that the user has made abnormal transactions, immediate feedback will be provided to the currency regulator.

[0055] like Figure 1 As shown, a real-time big data rule engine processing system for financial services includes a data collection module, a data processing module, a data analysis module, a data security module, a real-time monitoring module, a machine learning module, and an anomaly detection module. The data collection module is used to collect transaction records, account changes, credit records, and behavioral data of personal loan services; the data processing module uses the mean and median to fill in missing data, and processes the sale, transfer, and exchange of virtual currencies; the data analysis module is used to analyze the basic characteristics of the data, the trend of data changes, and the risk assessment of personal loan services; in this way, by collecting the personal loan business data, the proportion of the amount of personal loans for purchasing valuables in the loan amount, the length of time the personal loan account is opened, and the debt-to-income ratio, the credit coefficient of the individual user is determined, and the risk of lending to the individual user can be intuitively judged through the credit coefficient.

[0056] The data security module uses data encryption technology to ensure the security of data during storage and transmission, and sets permissions so that only authorized personnel can access sensitive data; the real-time monitoring module is used to monitor the access status of personal loan business to ensure that detected anomalies can be handled in a timely manner; the anomaly detection module is used to identify unusual or abnormal patterns in the data and feed the anomaly back to the data processing module; the machine learning module is used to train models based on historical data and make automated financial transaction decisions based on the results of data analysis and prediction. In this way, by collecting the number of transactions per unit time, the number of high-frequency loan applications in a short period of time, and the number of repeated applications for the same or similar amount of loans, it is possible to efficiently and accurately determine whether there are transaction anomalies in the personal user's loan business.

[0057] In this embodiment, the data processing module specifically includes: a data integration module and a currency transaction module; the data integration module is used to merge data from different sources into a unified data set; the currency transaction module is used to process the sale, transfer and exchange of virtual currency; and the currency transaction module includes a currency supervision module; the currency supervision module is used to supervise the process of currency transactions and terminate the transaction when there is an abnormal transaction.

[0058] In this embodiment, the data integration module specifically includes: an on-chain integration module and a data aggregation module; the on-chain integration module is used to integrate data collected from different blockchains and digital financial platforms, and use blockchain analysis tools to track and analyze on-chain activities; the data aggregation module is used to aggregate data collected from different sources into a unified data set. The personal loan business data collected by the anomaly detection module determines the creditworthiness of individual users based on the proportion of the amount of personal loans used to purchase valuables in the loan amount, the length of time the personal loan account has been opened, and the debt-to-income ratio.

[0059]

[0060] In the formula, c represents the credit coefficient of the individual user in the loan business, a represents the proportion of the amount of personal loans for purchasing valuables in the loan amount, t represents the length of time the personal loan account is opened, and s represents the ratio of the total liabilities to the total income of the borrower in the personal loan business.

[0061] When dividing the credit coefficient of user X, the proportion of the amount of user X's personal loan for purchasing valuables in the loan amount is a=73%, the length of time that user X's personal loan account is opened is t=13 (months), and the ratio of the total debt and total income of the borrower in user X's personal loan business is s=3.2, then:

[0062]

[0063] Then, the reputation coefficient of user X is c=5.7.

[0064] The anomaly detection module determines the probability of transaction anomalies in individual user loan business based on the number of transactions collected within a unit time, the number of high-frequency loan applications in a short period of time, and the number of repeated applications for the same or similar loan amounts. The following are the probability of anomalies in individual user loan business transactions:

[0065]

[0066] Where W represents the probability of anomalies in transactions of personal user loan business, and:

[0067]

[0068] In the formula, m represents the transaction abnormality coefficient of individual users in loan business, n represents the number of transactions of individual users in loan business per unit time, u represents the number of high-frequency loan applications in a short period of time, and g represents the number of repeated applications for loans of the same or similar amount;

[0069] When W≤45%, it indicates that there are transaction abnormalities in the loan business of the individual user.

[0070] For user X, the number of transactions per unit time in the loan business is n = 16 (times / day), the number of high-frequency loan applications in the short term is u = 12 (times / month), and the number of repeated applications for the same or similar amount of loans is g = 8 (times / month), then:

[0071]

[0072] From the calculation of the above coefficients, it can be known that the transaction abnormality coefficient of individual users in loan business is m=5.

[0073] Among them, when m≥2.6, it means that the individual user's transaction in the loan business is in an abnormal state.

[0074] Then, the probability of anomalies in the loan business of individual user X is:

[0075]

[0076] From the above calculation, it can be known that there are abnormal transactions in the loan business of user X.

[0077] In this embodiment, the data analysis module specifically includes: a descriptive analysis module, a predictive analysis module and a risk analysis module; the descriptive analysis module is used to analyze the mean, variance and frequency distribution of statistical data; the predictive analysis module is used to analyze historical data through time series and predict future trends; the risk analysis module is used to assess the risk of personal loans and conduct scenario analysis based on the risk assessment of personal loans. The data security module specifically includes: a data encryption module and an access control module; the data encryption module is used to encrypt sensitive data to protect privacy; the access control module is used to set access rights and ensure that only authorized personnel can access sensitive data.

[0078] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by ordinary technicians in this technical field within the essential scope of the present invention also fall within the protection scope of the present invention.

Claims

1. A real-time big data rule engine processing system for financial services, characterized in that: It includes data collection module, data processing module, data analysis module, data security module, real-time monitoring module, machine learning module and anomaly detection module; The data collection module is used to collect transaction records, account changes, credit records and behavioral data of personal loan business; The data processing module fills in missing data by using the mean and median, and processes the buying, selling, transfer and exchange of virtual currencies; The data analysis module is used to analyze the basic characteristics of the data, the changing trend of the data and the risk assessment of the personal loan business; The data security module ensures the security of data during storage and transmission through data encryption technology, and sets permissions so that only authorized personnel can access sensitive data; The real-time monitoring module is used to monitor the access status of personal loan business to ensure that the detected anomalies can be handled in time; The anomaly detection module is used to identify unusual or abnormal patterns in the data and feed the anomaly back to the data processing module; The machine learning module is used to train models based on historical data and to make automated financial transaction decisions based on data analysis and prediction results.

2. The financial business real-time big data rule engine processing system according to claim 1, characterized in that: The data processing module specifically includes: a data integration module and a currency transaction module; The data integration module is used to merge data from different sources into a unified data set; The currency transaction module is used to process the sale, transfer and exchange of virtual currency; and the currency transaction module includes a currency supervision module; The currency supervision module is used to supervise the process of currency transactions and terminate the transaction when there is an abnormal transaction.

3. The financial business real-time big data rule engine processing system according to claim 2, characterized in that: The data integration module specifically includes: an on-chain integration module and a data aggregation module; The on-chain integration module is used to integrate data collected by different blockchains and digital financial platforms, and use blockchain analysis tools to track and analyze on-chain activities; The data aggregation module is used to aggregate data collected from different sources into a unified data set.

4. The financial business real-time big data rule engine processing system according to claim 1, characterized in that: In the personal loan business data collected by the anomaly detection module, the creditworthiness of individual users is determined based on the proportion of the amount of personal loans used to purchase valuables in the loan amount, the length of time the personal loan account has been opened, and the debt-to-income ratio, as follows: In the formula, c represents the credit coefficient of the individual user in the loan business, a represents the proportion of the amount of personal loans for purchasing valuables in the loan amount, t represents the length of time the personal loan account is opened, and s represents the ratio of the total liabilities to the total income of the borrower in the personal loan business.

5. The financial business real-time big data rule engine processing system according to claim 4 is characterized by: The anomaly detection module determines the probability of anomaly in the transaction of individual user loan business based on the number of transactions collected within a unit time, the number of high-frequency loan applications in a short period of time, and the number of repeated applications for the same or similar amount of loans, which are: Where W represents the probability of anomalies in transactions of personal user loan business, and: In the formula, m represents the transaction abnormality coefficient of individual users in loan business, n represents the number of transactions of individual users in loan business per unit time, u represents the number of high-frequency loan applications in a short period of time, and g represents the number of repeated applications for loans of the same or similar amount; When W≤45%, it indicates that there are transaction abnormalities in the loan business of the individual user.

6. The financial business real-time big data rule engine processing system according to claim 1, characterized in that: The data analysis module specifically includes: a descriptive analysis module, a predictive analysis module and a risk analysis module; The descriptive analysis module is used for the mean, variance and frequency distribution of statistical data; The predictive analysis module is used to analyze historical data through time series and predict future trends; The risk analysis module is used to assess the risk of personal loans and conduct scenario analysis based on the risk assessment of personal loans.

7. The financial business real-time big data rule engine processing system according to claim 1, characterized in that: The data security module specifically includes: a data encryption module and an access control module; The data encryption module is used to encrypt sensitive data to protect privacy; The access control module is used to set access rights and ensure that only authorized personnel can access sensitive data.

8. A processing method for a financial business real-time big data rule engine processing system according to any one of claims 1 to 7, characterized in that: The following steps are involved: S 1. Collect data on personal loan business; S2. Process and integrate the collected data, and make changes to the post-transaction data; S3. Monitor and collect transaction change data in real time; S4. Analyze and evaluate the creditworthiness of individual users in personal loan business; S5. When it is determined that a user has made abnormal transactions, immediate feedback will be provided to the currency regulatory department.

Images