A financial business service management system based on big data

Abstract

The present invention discloses a financial business service management system based on big data, which specifically relates to the financial field, including a financial data batch division module, a financial data acquisition module, a financial data analysis module, a financial data comprehensive evaluation module, and a real-time tracking feedback warning module. The financial data acquisition module includes a customer data acquisition unit and a business data acquisition unit, which are used to collect target data in real time and transmit the collected data to the financial data analysis module; the financial data analysis module includes a customer data analysis unit and a business data analysis unit, which are used to analyze the data transmitted by the financial data acquisition module and transmit the analysis results to the financial data comprehensive evaluation module; the present invention greatly improves the reliability and pertinence of the data source by subdividing various types of data of the financial business service management based on big data into different collection batches.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and more specifically, to a financial business service management system based on big data. Background Art

[0002] With the rapid rise of big data technology, it has brought innovative concepts and methods to improve financial business service management. Relying on big data technology, it is possible to extract core points from massive business data, which helps to quickly understand potential financial risks, thereby enhancing the accuracy and timeliness of service management.

[0003] The existing financial business service management system is mainly composed of data collection module, data flow module, data analysis module and data presentation module. With the help of data collection module, data such as customer credit rating, transaction flow and market fluctuation data are collected; the data flow module transmits the collected data to the data analysis module, which screens, classifies and integrates data from different channels to obtain valuable information, and clearly displays it with the help of data presentation module, so as to detect anomalies in time, reduce financial risks and error rates, and ensure the smooth development and safe operation of financial business.

[0004] However, the current financial service management system still has certain defects. For example, in the data collection process, only some routine business data is collected, and some hidden related data is ignored, which makes the collected data limited, affects the comprehensiveness of the data source, causes deviations in data analysis results, reduces the accuracy of the results, and hinders the reasonable expansion and innovative development of financial services.

[0005] Therefore, there is an urgent need for a financial business service management system based on big data to solve the problems of insufficient data collection and inaccurate data analysis results in the existing service management system. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a financial business service management system based on big data, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a financial business service management system based on big data, comprising:

[0008] Financial data batch division module: used to determine the data to be collected as target data, divide the target data into different batches according to equal time division, and mark them as 1, 2, ..., n in sequence;

[0009] Financial data collection module: including a customer data collection unit and a business data collection unit, which are used to collect target data in real time and transmit the collected data to the financial data analysis module; the customer data collection unit is used to collect customer financial data, customer credit data and customer asset change data; the business data collection unit is used to collect business processing data, business resource utilization data and business risk data;

[0010] Financial data analysis module: including a customer data analysis unit and a business data analysis unit, used to analyze the data transmitted by the financial data acquisition module and transmit the analysis results to the financial data comprehensive evaluation module; the customer data analysis unit includes a customer financial data analysis node, a customer credit data analysis node and a customer asset change data analysis node; the business data analysis unit includes a business processing data analysis node, a business resource utilization data analysis node and a business risk data analysis node;

[0011] Financial data comprehensive evaluation module: including the financial business service management data analysis unit, which is used to conduct comprehensive analysis on the data transmitted by the financial data analysis module and transmit the analysis results to the real-time tracking feedback warning module;

[0012] Real-time tracking feedback warning module: used to establish preset values ​​of the comprehensive evaluation index of financial business service management, judge the value of the comprehensive evaluation index of financial business service management according to the preset values ​​of the comprehensive evaluation index of financial business service management, and send corresponding signals according to the judgment results.

[0013] Preferably, the customer financial data includes the difference between current assets and current liabilities Ad, the net asset size Ns and the financial leverage ratio Fr; the customer credit data includes the credit related party debt burden rate Cr, the credit record repair frequency Cm and the credit risk migration rate Cf; the customer asset change data includes the asset appreciation amount Va and the asset volatility Av; the business processing data includes the loan approval rate and rejection time ratio Ar, the transaction error rate Tr and the business process optimization frequency Bf; the business resource utilization data includes the server resource utilization rate Su, the human input-output ratio Hr and the marketing resource conversion rate Mc; the business risk data includes the non-performing asset recovery rate Nr and the risk asset ratio Wr.

[0014] Preferably, the customer financial data analysis node is used to establish a customer financial data calculation model, import the customer financial data transmitted by the financial data acquisition module into the customer financial data calculation model, and obtain a financial robustness coefficient value. The customer financial data calculation model is specifically expressed as:

[0015] ,

[0016] Among them, αi represents the value of the financial soundness coefficient calculated for the i-th time, Ad i Ns represents the difference between current assets and current liabilities collected for the i-th time. i represents the net asset size of the ith collection, Fr i Represents the financial leverage ratio collected for the i-th time.

[0017] Preferably, the customer credit data analysis node is used to establish a customer credit data calculation model, import the customer credit data transmitted by the financial data acquisition module into the customer credit data calculation model, and obtain a credit risk coefficient value. The customer credit data calculation model is specifically expressed as:

[0018] ,

[0019] Among them, β i Indicates the credit risk coefficient value calculated for the i-th time, Cr i represents the debt burden rate of the credit-related party collected for the i-th time, Cm i represents the credit record repair frequency of the i-th collection, Cf i It represents the credit risk migration rate collected for the i-th time, n is the total number of data collection, i is the serial number of the number of data collection, and n ranges from 1 to n.

[0020] Preferably, the customer asset change data analysis node is used to establish a customer asset change data calculation model, import the customer asset change data transmitted by the financial data acquisition module into the customer asset change data calculation model, and obtain the asset growth health coefficient value. The customer asset change data calculation model is specifically expressed as:

[0021] ,

[0022] Among them, γ i Represents the asset growth health coefficient value calculated for the i-th time, Va i represents the asset value added of the ith collection, Av i Represents the volatility of the asset collected for the i-th time.

[0023] Preferably, the business processing data analysis node is used to establish a business processing data calculation model, import the business processing data transmitted by the financial data acquisition module into the business processing data calculation model, and obtain the business efficiency coefficient value. The business processing data calculation model is specifically expressed as:

[0024] ,

[0025] in, represents the business efficiency coefficient value calculated for the i-th time, Ar iTr represents the ratio of loan approval rate to rejection time collected for the i-th time. i represents the transaction error rate collected for the i-th time, Bf i Indicates the frequency of business process optimization collected for the i-th time.

[0026] Preferably, the business resource utilization data analysis node is used to establish a business resource utilization data calculation model, and the business resource utilization data transmitted by the financial data acquisition module is imported into the business resource utilization data calculation model to obtain a resource utilization efficiency coefficient value. The business resource utilization data calculation model is specifically expressed as:

[0027] ,

[0028] in, Indicates the resource utilization efficiency coefficient value calculated for the i-th time, Su i represents the server resource utilization rate collected for the i-th time, HR i represents the labor input-output ratio of the i-th collection, Mc i It represents the conversion rate of marketing resources collected for the i-th time, n is the total number of data collections, i is the serial number of the number of data collections, and n ranges from 1 to n.

[0029] Preferably, the business risk data analysis node is used to establish a business risk data calculation model, import the business risk data transmitted by the financial data acquisition module into the business risk data calculation model, and obtain the risk prevention and control coefficient value. The business risk data calculation model is specifically expressed as:

[0030] ,

[0031] Among them, χ i Represents the risk control coefficient value calculated for the i-th time, Nr i represents the recovery rate of non-performing assets collected for the i-th time, Wr i Represents the proportion of risky assets collected in the i-th time.

[0032] Preferably, the financial business service management data analysis unit is used to establish a financial business service management data calculation model, and import the financial soundness coefficient value, credit risk coefficient value, asset growth health coefficient value, business efficiency coefficient value, resource utilization efficiency coefficient value and risk prevention and control coefficient value transmitted by the financial data analysis module into the financial business service management data calculation model to obtain the comprehensive evaluation index value of the financial business service management; the financial business service management data calculation model is specifically expressed as:

[0033] ,

[0034] Among them, ME represents the calculated comprehensive evaluation index value of financial business service management, α i represents the value of the financial soundness coefficient calculated for the i-th time, β i represents the credit risk coefficient value calculated for the i-th time, γ i Indicates the asset growth health coefficient value calculated for the i-th time, represents the business efficiency coefficient value calculated for the i-th time, represents the resource utilization efficiency coefficient value calculated for the i-th time, χ i Represents the risk prevention and control coefficient value calculated for the i-th time.

[0035] Technical effects and advantages of the present invention:

[0036] 1. The present invention greatly improves the reliability and pertinence of data sources by subdividing various types of data for financial service management based on big data into different collection batches. By collecting customer financial data, customer credit data, customer asset change data, business processing data, business resource utilization data and business risk data through multiple channels, this multi-angle data collection mode breaks the limitations of traditional data collection and lays a solid and rich data foundation for subsequent in-depth analysis;

[0037] 2. The present invention uses a professional data analysis model to deeply analyze the collected data, thereby accurately calculating the financial soundness coefficient value, credit risk coefficient value, asset growth health coefficient value, business efficiency coefficient value, resource utilization efficiency coefficient value and risk prevention and control coefficient value, clearly revealing the key areas where the business may face risks or opportunities. By systematically weighing and integrating the data interpretation results, the comprehensive evaluation index value of financial business service management is obtained, which significantly enhances the reliability and accuracy of the analysis conclusions;

[0038] 3. The present invention continuously tracks through real-time monitoring, and once an abnormal situation is detected, an early warning message is immediately issued. Relevant business personnel and managers can quickly grasp the real-time dynamics and potential risks of financial business services, and adjust and optimize business plans in a timely manner, providing strong support for the realization of efficient and accurate financial business service management based on big data and scientific and reasonable decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the overall structure of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] As attached Figure 1 The big data-based financial business service management system shown includes a financial data batch division module, a financial data collection module, a financial data analysis module, a financial data comprehensive evaluation module, and a real-time tracking feedback warning module.

[0042] The financial data batch division module is used to determine the data to be collected as target data, divide the target data into different batches in an equal time division manner, and mark them as 1, 2, ..., n in sequence.

[0043] In this embodiment, it is specifically necessary to explain that: the method of dividing by equal time is to divide the database according to the characteristics of each target data through the background system running the database. According to the real-time requirements of each target data, it is collected once at an equal interval and divided into different collection times.

[0044] The financial data collection module includes a customer data collection unit and a business data collection unit, which are used to collect target data in real time and transmit the collected data to the financial data analysis module; the customer data collection unit is used to collect customer financial data, customer credit data and customer asset change data; the business data collection unit is used to collect business processing data, business resource utilization data and business risk data.

[0045] In this embodiment, it is specifically necessary to explain that: the customer financial data includes the difference between current assets and current liabilities Ad, the net asset size Ns and the financial leverage ratio Fr; the customer credit data includes the credit related party debt burden rate Cr, the credit record repair frequency Cm and the credit risk migration rate Cf; the customer asset change data includes the asset appreciation amount Va and the asset volatility Av; the business processing data includes the loan approval rate and rejection time ratio Ar, the transaction error rate Tr and the business process optimization frequency Bf; the business resource utilization data includes the server resource utilization rate Su, the human input-output ratio Hr and the marketing resource conversion rate Mc; the business risk data includes the non-performing asset recovery rate Nr and the risk asset ratio Wr.

[0046] The difference between current assets and current liabilities: This parameter is crucial for the financial service management system based on big data. It clearly presents the customer's short-term debt repayment ability and flexible capital allocation ability. For financial institutions, when considering providing short-term credit services to customers, the difference can be used to determine whether the customer has sufficient funds to repay short-term debts on time. The larger the difference, the stronger the customer's ability to cope with debt and capital needs in the short term, the relatively lower the risk faced by financial institutions, and it also means that customers have greater potential to obtain more support in short-term financial business, such as higher short-term credit lines. At the same time, this parameter can also help financial institutions evaluate the liquidity of customer funds so as to provide customers with financial products and services that are more in line with their capital operation characteristics. The collection method is: In order to obtain accurate current assets and current liabilities The difference, it is necessary to integrate multiple data. First, establish a data docking mechanism with major banks, and obtain customer deposits, current financial products and other current asset information in various bank accounts, as well as credit card arrears, short-term loans and other current liability data through the bank system. At the same time, data is exchanged with securities institutions to obtain financial asset information such as stocks and funds in customer securities accounts, which also belong to the category of current assets. In addition, the data of the third-party payment platform can also be used to count the customer's fund balance and related short-term borrowing on the platform. All the collected current assets and current liabilities data are sorted and calculated to obtain the difference between the two.

[0047] Net asset size (RMB): Net asset size comprehensively reflects the overall financial strength of the customer and is a key basis for financial institutions to formulate financial service strategies. It can help financial institutions determine the customer's tolerance for complex financial products. For example, for customers with a large net asset size, it may be more suitable to invest in some high-risk and high-return financial products, such as private equity funds, complex structured financial derivatives, etc. At the same time, when planning long-term financial services for customers, net asset size is an important reference indicator, which helps financial institutions to tailor comprehensive financial service solutions for customers, including wealth inheritance and asset allocation optimization. In addition, net asset size also reflects the customer's credit risk tolerance to a certain extent. The larger the size, the stronger the customer's risk resistance in the face of economic fluctuations, and the risk of financial institutions doing business with customers is relatively low. The collection method is: Collecting customer net asset size data requires multi-channel collaboration. On the one hand, customers are encouraged to voluntarily declare their assets and liabilities, including fixed assets such as real estate, vehicles, and land, as well as various types of loans, arrears and other liability information. At the same time, financial institutions use their own data resources to share data with banks, securities, insurance and other financial institutions to obtain customer asset information in the financial field, such as deposits, investment products, and policy cash values. For fixed assets, we connect data with official agencies such as the real estate registration department and the vehicle management department to verify the ownership and valuation information of the client's real estate and vehicles. For some special assets, such as artworks and antiques, we can use professional third-party asset appraisal agencies to conduct appraisals. Finally, we add up the value of all assets and subtract all total liabilities to get the client's net asset size.

[0048] The financial leverage ratio: The financial leverage ratio directly reflects the robustness of the customer's financial structure through the ratio of total liabilities to net assets, and is an important parameter for financial institutions to assess customer credit risk. When the ratio is too high, it indicates that the customer has a high debt repayment pressure and may face a high financial risk. This means that financial institutions need to be extra cautious when providing new credit services to customers, and may increase loan interest rates, shorten loan terms or reduce loan amounts to reduce their own risks. On the contrary, a low ratio indicates that the customer's financial structure is relatively robust, and financial institutions can be more confident in conducting various financial businesses with them, and may even provide them with more favorable financial service conditions, such as lower loan interest rates, higher credit limits, etc. In addition, this ratio can also help financial institutions analyze customers' financial strategies and risk preferences, and provide customers with more targeted financial planning advice. The collection method is: To obtain the financial leverage ratio, first accurately collect the customer's total liabilities and net assets data. The collection of total liabilities data requires the integration of customer loan information from different financial institutions, including housing loans, car loans, operating loans, etc., as well as other liabilities such as credit card overdrafts and consumer loans. These data can be obtained by connecting with the data sharing platforms of various financial institutions, and verified and supplemented in combination with the liability records in the credit reporting system. In terms of obtaining net asset data, as mentioned above, asset and liability information is collected through multiple channels and calculated. On the basis of ensuring the accuracy of total liabilities and net asset data, the total liabilities are divided by net assets to obtain the financial leverage ratio.

[0049] Debt burden rate of credit-related parties: In the financial service management system based on big data, the debt burden rate of credit-related parties is used to examine the debt burden of entities that have credit relationships with customers (such as guarantee relationships, co-borrowers, etc.). If the debt burden rate of related parties is too high, it means that the debt repayment pressure of related parties is high, and the possibility of customers being affected by joint credit risks is significantly increased. This is crucial for financial institutions to approve customer business. For example, when approving loans, even if the customer's own credit status is good, if the debt burden of its credit-related parties is too heavy, financial institutions may reassess the risk, tighten loan conditions or reject loan applications to avoid potential credit risks. At the same time, this parameter also helps financial institutions monitor the dynamic changes in customer credit status and adjust risk management strategies in a timely manner. The collection method is: Collecting data on the debt burden rate of credit-related parties requires multiple channels. First, with the help of the credit reporting system, the credit reporting system usually records the credit relationship information of individuals and enterprises and some debt data of related parties, but the information may not be comprehensive enough. Therefore, it is also necessary to establish an information sharing mechanism with financial institutions, and each financial institution provides each other with detailed debt information of customer credit-related parties, including loan amount, repayment status, outstanding balance, etc. In addition, related parties are encouraged to voluntarily declare their own debts. To improve the authenticity and accuracy of the data, related parties may be required to provide relevant debt certification documents, such as loan contracts, repayment records, etc. After obtaining the total debt data of related parties, the income data of related parties is obtained through data connection with tax departments, social security departments, etc., so as to calculate the debt burden rate.

[0050] The credit record repair frequency: The credit record repair frequency reflects the customer's past repair behavior of his own credit status, which is of great reference value for financial institutions to assess the credit risk of customers. A higher repair frequency may imply that the customer has had more credit problems in the past, and there may still be potential credit risks despite the repair measures taken. Financial institutions will take this parameter into consideration when approving new business, such as granting loans or providing credit card services. For customers with a higher frequency of credit record repair, financial institutions may conduct more in-depth credit investigations, including detailed understanding of the reasons for the repair, credit performance after the repair, etc., in order to more accurately assess the customer's credit risk and repayment ability. In addition, this parameter can also help financial institutions predict the customer's future credit behavior and provide customers with targeted credit management suggestions. The collection method is: Obtaining the credit record repair frequency mainly relies on the data of the credit reporting agency. Establish a data interface with the credit reporting agency and directly extract the detailed historical records of the customer's credit record repair from the credit reporting system. The credit reporting system will record the time, reason, credit matters involved, and other information of each credit record repair. By screening and counting these records, the customer's credit record repair frequency can be obtained. To ensure the accuracy and completeness of the data, you can regularly check the data with the credit reporting agency, pay attention to the update and maintenance of the credit reporting system, and obtain the latest credit record repair information in a timely manner.

[0051] The credit risk migration rate: The credit risk migration rate measures the transfer of customer credit risk between different credit levels and is an important indicator of risk management for financial institutions. By observing the proportion of migration from normal credit levels to lower levels such as attention and secondary, financial institutions can intuitively present the dynamic trend of customer credit risk. This helps financial institutions to warn of potential credit risks in advance and adjust risk management strategies in a timely manner. For example, when it is found that the credit risk migration rate of a certain customer group has increased, financial institutions can strengthen post-loan management of the group, increase the frequency of risk monitoring, and take risk mitigation measures in advance, such as requiring customers to provide additional guarantees, adjust repayment plans, etc. In addition, the credit risk migration rate can also be used to evaluate the effectiveness of the credit rating model of financial institutions and provide data support for optimizing the credit rating system. The collection method is as follows: the calculation of the credit risk migration rate requires the use of credit data and data from the internal credit rating system of financial institutions. First, the latest credit rating information of customers is obtained from the credit system on a regular basis. At the same time, customers are rated according to the credit rating standards formulated by the financial institution, and the credit rating of each customer in different time periods is recorded. Then, we use professional data analysis methods to compare the changes in customers’ credit ratings over different time periods and count the number of customers who migrate from one credit rating to another. Finally, we use the formula for calculating the credit risk migration rate to divide the number of migrated customers by the initial number of customers of the corresponding credit rating to arrive at the credit risk migration rate. During the collection and calculation process, we must ensure the consistency and accuracy of credit investigation data and internal credit rating data, and conduct regular verification and correction of the data.

[0052] The asset appreciation amount: The asset appreciation amount reflects the growth of the customer's asset value in a certain period of time, and is an important indicator for evaluating the profitability of customer assets and investment results. For the financial service management system based on big data, it can help financial institutions understand the dynamic changes of customer assets and judge the investment ability and potential of customers. The higher the asset appreciation amount, the stronger the customer's asset operation ability, and the higher the demand and tolerance for investment financial products. Financial institutions can provide customers with more targeted investment advice and asset allocation plans based on this parameter. For example, for customers with higher asset appreciation, some investment products with higher returns but relatively higher risks are recommended to help customers further realize asset appreciation. At the same time, the asset appreciation amount can also be used as a reference factor for evaluating the customer's repayment ability, and provide financial institutions with a more comprehensive decision-making basis when approving loans and other businesses. The collection method is: In order to accurately calculate the asset appreciation amount, it is necessary to conduct a comprehensive assessment of customer assets on a regular basis (such as every year). For the financial assets part, through cooperation with financial market data suppliers, the market value changes of financial products such as stocks, funds, bonds, etc. held by customers are obtained in real time. For fixed assets, such as real estate and vehicles, we establish cooperative relationships with professional asset appraisal institutions and regularly conduct valuation assessments on clients’ real estate and vehicles. For other assets, such as land and intellectual property, we conduct valuations based on relevant market data and professional valuation methods. After obtaining the asset values ​​at the end and beginning of the valuation period, we calculate the difference between the two, which is the asset appreciation amount. To ensure the accuracy and consistency of the assessment, we need to strictly screen and manage the assessment institutions and data suppliers, and regularly review and update the assessment methods and data.

[0053] Asset volatility: asset volatility measures the degree of fluctuation of the value of customer assets and reflects the stability and risk level of assets. In the financial business service management system, this parameter is crucial for financial institutions to assess the risk status of customer assets. A low volatility indicates that the asset value is relatively stable and the risk is relatively small. Such customers may be more suitable for stable financial products, such as time deposits and treasury bonds. Customer assets with higher volatility indicate that they are more risky, but may also be accompanied by higher return potential. Financial institutions can provide them with investment products that match risk and return, such as stock funds, foreign exchange transactions, etc., and provide corresponding risk management advice. In addition, asset volatility can also be used to evaluate the rationality of customer investment portfolios and help financial institutions guide customers to adjust asset allocation to reduce overall risk. The collection method is as follows: to calculate asset volatility, a certain period of time must be selected based on the daily or weekly value data of customer assets. For financial assets, value data such as daily or weekly closing prices can be obtained directly from financial trading systems or data providers. For fixed assets, since their value changes are relatively infrequent, monthly or quarterly assessment value data can be used. Statistical methods are used to calculate the standard deviation of asset returns to obtain asset volatility. For example, first calculate the asset yield at each time point, that is, (current asset value - asset value of the previous cycle) / asset value of the previous cycle, then calculate the average of these yields, and then calculate the square of the difference between each yield and the average, add these square values ​​and divide them by the number of time periods to get the variance, and finally square the variance to get the standard deviation, that is, asset volatility. In the process of collection and calculation, attention should be paid to the accuracy and completeness of the data, and abnormal data should be identified and processed.

[0054] The ratio of loan approval rate to rejection time: This ratio comprehensively reflects the efficiency and quality of the loan approval process in the big data-based financial business service management system. A high ratio indicates that financial institutions can quickly approve reasonable loan applications while effectively rejecting bad loan applications, reflecting the efficiency and accuracy of the approval process. For financial institutions, by analyzing this ratio, it is helpful to find bottlenecks and potential problems in the approval process, and then optimize the approval strategy. For example, if it is found that the rejection time is too long, it may mean that the approval process is too cumbersome or the approval personnel are inefficient, and the approval process needs to be simplified or the personnel needs to be trained. At the same time, this ratio can also be used to evaluate the work performance of different approval teams or approval personnel, and provide data support for performance appraisal. In addition, a higher ratio helps to improve customer satisfaction and enhance the competitiveness of financial institutions in the market. The collection method is: In the loan approval system, each loan application needs to be recorded in detail, including the application submission time, approval time, rejection time and approval result. In a specific time period, the number of loan approvals and rejections is counted, and the average time spent from submission to rejection of the corresponding rejected application is calculated. When calculating specifically, add up the processing time of all rejected applications and divide it by the number of rejected applications to get the average rejection time. Finally, calculate the ratio of loan approval rate (number of approved applications / total number of applications) to the average rejection time to get the ratio of loan approval rate to rejection time. To ensure the accuracy and timeliness of data, the loan approval system should be regularly maintained and cleaned to ensure the integrity of data records.

[0055] The transaction error rate: The transaction error rate reflects the proportion of erroneous transactions in financial business transactions, and is an important indicator for measuring the stability of the business system, the proficiency of operators, and the standardization of business processes. In the financial business service management system, a low transaction error rate indicates that the business operation is mature, which can effectively reduce operating costs, reduce the risk of customer complaints, and improve customer satisfaction and market competitiveness. If the transaction error rate is too high, it may mean that there are loopholes in the business system, insufficient operator skills, or unreasonable business processes, which require financial institutions to conduct timely investigations and improvements. In addition, by classifying and analyzing transaction errors, weak links in business operations can be discovered, providing a basis for targeted strengthening of management and training. The collection method is: the business transaction system should have a complete transaction record function, and monitor and record each transaction in real time, including detailed information such as the time, amount, transaction parties, transaction type, and whether there are transaction errors. In a certain period of time (such as daily, weekly, and monthly), the transaction record data is exported from the business transaction system, and records of transaction errors are screened by writing a special data analysis program, and the number of erroneous transactions and the total number of transactions are counted. Divide the number of erroneous transactions by the total number of transactions, and then multiply by 100% to get the transaction error rate. At the same time, in order to deeply analyze the causes of transaction errors, the erroneous transaction records can be marked in detail, such as the error type (data entry error, system failure, operational error, etc.), the business links involved, etc., so as to carry out targeted improvements and optimizations later.

[0056] The frequency of business process optimization: The frequency of business process optimization reflects the ability of financial institutions to continuously improve their business processes. In a financial business service management system based on big data, a higher optimization frequency means that financial institutions can keenly perceive market changes, customer needs and technological development trends, and quickly adjust and optimize business processes to enhance business competitiveness. By continuously optimizing business processes, financial institutions can improve business processing efficiency, reduce operating costs and enhance customer experience. In addition, the frequency of business process optimization can also be used as an indicator to evaluate the innovation ability and flexibility of financial institutions to adapt to market changes, which is of great significance for attracting customers, investors and partners. The collection method is as follows: Financial institutions should establish a complete business process management document and change record system, and record each business process optimization in detail, including optimization time, optimization content, optimization reasons, business links involved, business process comparison before and after optimization, etc. The business process management document and change record system should be sorted out regularly (such as monthly and quarterly), and the number of optimization records should be counted to determine the number of business process optimizations within a certain period. In order to better evaluate the effectiveness of business process optimization, it is also possible to track and analyze business indicators after each optimization, such as business processing time, customer satisfaction, operating costs, etc., to form a closed-loop management of business process optimization.

[0057] The server resource utilization rate: The server resource utilization rate is used to measure the actual usage ratio of server CPU, memory, storage and other resources in business operation. In the financial business service management system, reasonable resource utilization ensures stable operation of the server, avoids resource waste or overload, and reduces operating costs. If the server resource utilization rate is too high, it may cause slow system response, delayed transaction processing, affect customer experience, and even cause system failure. On the contrary, too low resource utilization means resource waste and increased operating costs. By real-time monitoring of server resource utilization, financial institutions can adjust server resource configuration in time, such as increasing or reducing the number of servers, upgrading hardware equipment, etc., to ensure efficient and stable operation of the business system. The collection method is: by installing professional server monitoring software on the server, such as Zabbix, Nagios, etc., to collect the usage data of various server resources in real time. Taking CPU utilization collection as an example, the monitoring software will obtain the CPU's working status information regularly (such as every second or every minute), including the time proportion of user state, kernel state, idle state, etc., and calculate (1-idle state time proportion) to obtain the CPU utilization rate. For memory utilization, the monitoring software will count the size of used memory and total memory in real time, and get the memory utilization by (used memory / total memory) × 100%. In terms of storage, the monitoring software will monitor the disk read and write rate, used space and total space, and get the storage resource utilization by (used space / total space) × 100%. These monitoring software will organize and store the collected data and generate detailed resource usage reports, which are convenient for financial institution operation and maintenance personnel to view and analyze at any time.

[0058] The human input-output ratio: The human input-output ratio directly reflects the efficiency of human resources in business operations by calculating the ratio of the output value of financial business (such as profit, business volume, etc.) to the human cost input. In the financial business service management system based on big data, this ratio is crucial for financial institutions to rationally plan human resource allocation. A higher human input-output ratio indicates that financial institutions can effectively utilize human resources, employees have high work efficiency, and create relatively more value. Financial institutions can evaluate and adjust the human resource allocation of different business departments and different positions based on this ratio. For example, for departments or positions with relatively high human input-output, resource input can be appropriately increased to further improve business output; for parts with lower ratios, the reasons need to be analyzed, which may be redundant personnel, unreasonable work processes, or mismatched employee skills, and then corresponding improvement measures such as layoffs, process optimization, or targeted training can be taken to improve overall operational efficiency. The collection method is: obtain human cost data from the financial system, and the financial system records in detail various human resource expenditures such as employees' wages, bonuses, benefits, and training expenses. By setting a specific statistical cycle (such as monthly, quarterly or annually), all human-related expense items in the financial system are screened out and summarized to obtain the total human cost investment. At the same time, business output value data is collected from the business system. The output value of different business types is measured differently. For loan business, the interest income from loans issued during the cycle can be counted; for intermediary business, such as payment settlement, agency sales, etc., the handling fee and commission income can be counted; for customer development business, the expected benefits brought by new customers can be included in the calculation. Summarize the output value of each business to obtain the total business output value. Finally, divide the business output value by the total human cost investment to obtain the human input-output ratio. To ensure the accuracy of the data, it is necessary to regularly check and calibrate the data of the financial system and business system to avoid data errors.

[0059] The marketing resource conversion rate: The marketing resource conversion rate indicates the proportion of actual business results brought by marketing investment, and is a key indicator for evaluating the effectiveness of marketing activities of financial institutions. In the financial business service management system, a higher conversion rate indicates that the marketing activities of financial institutions are accurate and effective, and limited marketing resources can be reasonably allocated to the target customer group to maximize the marketing effect. By analyzing the marketing resource conversion rate, financial institutions can understand the effectiveness of different marketing channels and marketing activity forms, thereby optimizing the allocation of marketing budgets and investing more resources in channels and activities with high conversion rates. At the same time, marketing strategies can also be adjusted according to the conversion rate, such as improving marketing content, optimizing target customer positioning, etc., to improve the pertinence and attractiveness of marketing activities and further enhance business growth. The collection method is: before the marketing activities are carried out, the goals and corresponding measurement indicators of the marketing activities are clearly set, such as the number of new customers, business sales, etc. During the marketing activities, the customer relationship management system (CRM) and business system are used to record in detail the investment amount, marketing channels, promotion content and other information of the marketing activities. At the same time, real-time tracking and statistics of actual business results brought about by marketing activities are carried out, such as identifying the source of new customers through specific marketing activity links or discount codes, and counting the number of new customers; for business sales, it is determined whether it is contributed by this marketing activity based on transaction records, and the amount is counted. After the marketing activity is completed, the actual business results are divided by the marketing investment amount, and then multiplied by 100% to obtain the marketing resource conversion rate. In addition, in order to analyze the marketing effect more deeply, the conversion rates of different marketing channels and different time periods can also be segmented and compared, and the most effective marketing methods and time periods can be found to provide reference for subsequent marketing activities.

[0060] The recovery rate of non-performing assets: The recovery rate of non-performing assets shows the recovery ability of financial institutions when dealing with non-performing assets, and is an important indicator for measuring the asset quality and risk management level of financial institutions. In the financial business service management system based on big data, a higher recovery rate indicates that financial institutions can effectively reduce losses caused by non-performing assets and have a high degree of asset quality assurance. This not only helps to enhance the financial stability of financial institutions, but also enhances market confidence and investors' recognition of financial institutions. Through the analysis of the recovery rate of non-performing assets, financial institutions can evaluate the effectiveness of their own non-performing asset disposal strategies, summarize experience and lessons, continuously optimize disposal processes and methods, and improve the recovery efficiency of non-performing assets in the future. At the same time, this indicator can also be used to compare with other financial institutions in the same industry to understand their own advantages and disadvantages in the disposal of non-performing assets, so as to formulate more competitive risk management strategies. The collection method is: when handling non-performing assets, financial institutions will record the relevant information of each non-performing asset in detail, including the initial amount, disposal method, recovery amount and disposal time. In a specific statistical period, the non-performing asset data that has been disposed of in the period is screened out from the non-performing asset disposal record system. The recovery amount of all disposed non-performing assets is summarized, divided by the total initial amount of these non-performing assets, and multiplied by 100% to get the non-performing asset recovery rate. To ensure the accuracy and completeness of the data, it is necessary to strictly regulate and review the identification standards, disposal procedures and data records of non-performing assets to avoid data falsification or omissions. At the same time, the recovery rates of non-performing assets under different disposal methods are separately counted and analyzed to better evaluate the effectiveness of various disposal methods.

[0061] The risk asset ratio: The risk asset ratio is used to measure the risk level of the financial institution's asset portfolio. In the financial business service management system, the higher the ratio, the greater the overall asset risk, and the financial institution needs more capital reserves to cover potential risks. This directly affects the capital planning and risk management strategies of financial institutions. For example, when the risk asset ratio is high, the financial institution may need to increase capital to meet regulatory requirements and its own risk tolerance, or adjust the asset structure to reduce the proportion of high-risk assets to optimize the risk situation. In addition, regulators will also pay attention to the risk asset ratio of financial institutions to assess the systemic risk of financial institutions and formulate corresponding regulatory policies. Therefore, accurately calculating and monitoring the risk asset ratio is of great significance to the sound operation and compliance of financial institutions. The collection method is: According to the risk weight calculation method prescribed by the regulator, financial institutions first need to classify various types of assets, such as cash, loans, securities investment, etc., and determine the risk weights corresponding to each type of asset. These risk weights are usually formulated by regulators based on the risk characteristics of the assets. For example, loans with higher credit risks may be assigned higher risk weights, while low-risk assets such as cash have lower risk weights. Financial institutions count the amount of various types of assets based on their own balance sheets. Then, multiply the amount of each type of asset by its corresponding risk weight to get the amount of risk-weighted assets. Add up all the amounts of risk-weighted assets to get the total amount of risk-weighted assets. Finally, divide the total amount of risk-weighted assets by the total asset amount and multiply by 100% to get the risk asset ratio. During the calculation process, the calculation methods and standards specified by the regulators must be strictly followed to ensure the accuracy and compliance of the data. At the same time, as the asset structure changes and regulatory policies are adjusted, the risk weights and asset data should be updated in a timely manner to ensure the real-time and reliability of the risk asset ratio.

[0062] The financial data analysis module includes a customer data analysis unit and a business data analysis unit, which are used to analyze the data transmitted by the financial data acquisition module and transmit the analysis results to the financial data comprehensive evaluation module; the customer data analysis unit includes a customer financial data analysis node, a customer credit data analysis node and a customer asset change data analysis node; the business data analysis unit includes a business processing data analysis node, a business resource utilization data analysis node and a business risk data analysis node.

[0063] In this embodiment, it is specifically required to be explained that: the customer financial data analysis node is used to establish a customer financial data calculation model, import the customer financial data transmitted by the financial data acquisition module into the customer financial data calculation model, and obtain the financial robustness coefficient value. The customer financial data calculation model is specifically expressed as:

[0064] ,

[0065] Among them, α i represents the value of the financial soundness coefficient calculated for the i-th time, Ad i Ns represents the difference between current assets and current liabilities collected for the i-th time. i represents the net asset size of the ith collection, Fr i Represents the financial leverage ratio collected for the i-th time.

[0066] In this embodiment, it is specifically required to be explained that: the customer credit data analysis node is used to establish a customer credit data calculation model, import the customer credit data transmitted by the financial data acquisition module into the customer credit data calculation model, and obtain the credit risk coefficient value. The customer credit data calculation model is specifically expressed as:

[0067] ,

[0068] Among them, β i Indicates the credit risk coefficient value calculated for the i-th time, Cr i represents the debt burden rate of the credit-related party collected for the i-th time, Cm i represents the credit record repair frequency of the i-th collection, Cf i It represents the credit risk migration rate collected for the i-th time, n is the total number of data collection, i is the serial number of the number of data collection, and n ranges from 1 to n.

[0069] In this embodiment, it is specifically required to be explained that: the customer asset change data analysis node is used to establish a customer asset change data calculation model, and the customer asset change data transmitted by the financial data acquisition module is imported into the customer asset change data calculation model to obtain the asset growth health coefficient value. The customer asset change data calculation model is specifically expressed as:

[0070] ,

[0071] Among them, γ i Represents the asset growth health coefficient value calculated for the i-th time, Va i represents the asset value added of the ith collection, Av i Represents the volatility of the asset collected for the i-th time.

[0072] In this embodiment, it is specifically required to be explained that: the business processing data analysis node is used to establish a business processing data calculation model, import the business processing data transmitted by the financial data acquisition module into the business processing data calculation model, and obtain the business efficiency coefficient value. The business processing data calculation model is specifically expressed as:

[0073] ,

[0074] in, represents the business efficiency coefficient value calculated for the i-th time, Ar i Tr represents the ratio of loan approval rate to rejection time collected for the i-th time. i represents the transaction error rate collected for the i-th time, Bf i Indicates the frequency of business process optimization collected for the i-th time.

[0075] In this embodiment, it is specifically required to be explained that: the business resource utilization data analysis node is used to establish a business resource utilization data calculation model, and the business resource utilization data transmitted by the financial data acquisition module is imported into the business resource utilization data calculation model to obtain the resource utilization efficiency coefficient value. The business resource utilization data calculation model is specifically expressed as:

[0076] ,

[0077] in, Indicates the resource utilization efficiency coefficient value calculated for the i-th time, Su i represents the server resource utilization rate collected for the i-th time, HR i represents the labor input-output ratio of the i-th collection, Mc i It represents the conversion rate of marketing resources collected for the i-th time, n is the total number of data collections, i is the serial number of the number of data collections, and n ranges from 1 to n.

[0078] In this embodiment, it is specifically required to be explained that: the business risk data analysis node is used to establish a business risk data calculation model, import the business risk data transmitted by the financial data acquisition module into the business risk data calculation model, and obtain the risk prevention and control coefficient value. The business risk data calculation model is specifically expressed as:

[0079] ,

[0080] Among them, χ i Represents the risk control coefficient value calculated for the i-th time, Nr i represents the recovery rate of non-performing assets collected for the i-th time, Wr i Represents the proportion of risky assets collected in the i-th time.

[0081] The financial data comprehensive evaluation module includes a financial business service management data analysis unit, which is used to conduct comprehensive analysis on the data transmitted by the financial data analysis module and transmit the analysis results to the real-time tracking feedback warning module.

[0082] In this embodiment, it is specifically required to be explained that: the financial business service management data analysis unit is used to establish a financial business service management data calculation model, and the financial soundness coefficient value, credit risk coefficient value, asset growth health coefficient value, business efficiency coefficient value, resource utilization efficiency coefficient value and risk prevention and control coefficient value transmitted by the financial data analysis module are imported into the financial business service management data calculation model to obtain the comprehensive evaluation index value of the financial business service management; the financial business service management data calculation model is specifically expressed as:

[0083] ,

[0084] Among them, ME represents the calculated comprehensive evaluation index value of financial business service management, α i represents the value of the financial soundness coefficient calculated for the i-th time, β i represents the credit risk coefficient value calculated for the i-th time, γ i Indicates the asset growth health coefficient value calculated for the i-th time, represents the business efficiency coefficient value calculated for the i-th time, represents the resource utilization efficiency coefficient value calculated for the i-th time, χ i Represents the risk prevention and control coefficient value calculated for the i-th time.

[0085] The real-time tracking feedback warning module is used to establish a preset value of the comprehensive evaluation index of the financial business service management, judge the comprehensive evaluation index value of the financial business service management according to the preset value of the comprehensive evaluation index of the financial business service management, and send a corresponding signal according to the judgment result.

[0086] In this embodiment, it should be specifically explained that: the preset value of the comprehensive evaluation index of the financial business service management is recorded as ME def , when ME def <=ME, a normal signal is issued, which indicates that the preset value of the comprehensive evaluation index of the financial service management is less than or equal to the comprehensive evaluation index value of the financial service management, indicating that the overall financial service management situation is good; when ME def >ME, a warning signal is issued to the relevant technical management personnel. This signal indicates that the preset value of the comprehensive evaluation index of the financial business service management is greater than the comprehensive evaluation index value of the financial business service management, indicating that the overall management status of the financial business service is relatively poor and requires adjustments by the relevant technical management personnel.

[0087] The present invention greatly improves the reliability and pertinence of the data source by subdividing various types of data of financial business service management based on big data into different collection batches. By collecting customer financial data, customer credit data, customer asset change data, business processing data, business resource utilization data and business risk data through multiple channels, this multi-angle data collection mode breaks the limitations of traditional data collection and lays a solid and rich data foundation for subsequent in-depth analysis. Through the professional data analysis model, the collected data is deeply analyzed, so as to accurately calculate the financial soundness coefficient value, credit risk coefficient value, asset growth health coefficient value, business efficiency coefficient value, resource utilization efficiency coefficient value and risk prevention and control coefficient value, and clearly reveal the key areas where the business may face risks or opportunities. By systematically weighing and integrating the data interpretation results, the comprehensive evaluation index value of financial business service management is obtained, which significantly enhances the reliability and accuracy of the analysis conclusions. Through real-time monitoring and continuous tracking, once an abnormal situation is detected, early warning information will be issued immediately. Relevant business personnel and managers can quickly grasp the real-time dynamics and potential risks of financial business services, and adjust and optimize business plans in a timely manner, providing strong support for the realization of efficient and accurate big data-based financial business service management and scientific and reasonable decision-making.

[0088] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0089] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A financial business service management system based on big data, characterized in that: include: Financial data batch division module: used to determine the data to be collected as target data, divide the target data into different batches according to equal time division, and mark them as 1, 2, ..., n in sequence; Financial data collection module: including a customer data collection unit and a business data collection unit, which are used to collect target data in real time and transmit the collected data to the financial data analysis module; the customer data collection unit is used to collect customer financial data, customer credit data and customer asset change data; the business data collection unit is used to collect business processing data, business resource utilization data and business risk data; The customer financial data includes the difference between current assets and current liabilities Ad, the net asset size Ns and the financial leverage ratio Fr; the customer credit data includes the credit related party debt burden rate Cr, the credit record repair frequency Cm and the credit risk migration rate Cf; the customer asset change data includes the asset appreciation amount Va and the asset volatility Av; the business processing data includes the loan approval rate and rejection time ratio Ar, the transaction error rate Tr and the business process optimization frequency Bf; the business resource utilization data includes the server resource utilization rate Su, the human input-output ratio Hr and the marketing resource conversion rate Mc; the business risk data includes the non-performing asset recovery rate Nr and the risk asset ratio Wr; Financial data analysis module: including a customer data analysis unit and a business data analysis unit, used to analyze the data transmitted by the financial data acquisition module and transmit the analysis results to the financial data comprehensive evaluation module; the customer data analysis unit includes a customer financial data analysis node, a customer credit data analysis node and a customer asset change data analysis node; the business data analysis unit includes a business processing data analysis node, a business resource utilization data analysis node and a business risk data analysis node; The customer financial data analysis node is used to establish a customer financial data calculation model, import the customer financial data transmitted by the financial data acquisition module into the customer financial data calculation model, and obtain the financial robustness coefficient value. The customer financial data calculation model is specifically expressed as: ， Among them, α i represents the value of the financial soundness coefficient calculated for the i-th time, Ad i Ns represents the difference between current assets and current liabilities collected for the i-th time. i represents the net asset size of the ith collection, Fr i represents the financial leverage ratio collected for the i-th time; the customer credit data analysis node is used to establish a customer credit data calculation model, import the customer credit data transmitted by the financial data collection module into the customer credit data calculation model, and obtain the credit risk coefficient value. The customer credit data calculation model is specifically expressed as: ， Among them, β i Indicates the credit risk coefficient value calculated for the i-th time, Cr i represents the debt burden rate of the credit-related party collected for the i-th time, Cm i represents the credit record repair frequency of the i-th collection, Cf i represents the credit risk migration rate collected for the i-th time, n is the total number of data collections, i is the number of data collections, and the value of i ranges from 1 to n; the customer asset change data analysis node is used to establish a customer asset change data calculation model, import the customer asset change data transmitted by the financial data collection module into the customer asset change data calculation model, and obtain the asset growth health coefficient value. The customer asset change data calculation model is specifically expressed as: ， Among them, γ i Represents the asset growth health coefficient value calculated for the i-th time, Va i represents the asset value added of the ith collection, Av i represents the asset volatility collected for the i-th time; the business processing data analysis node is used to establish a business processing data calculation model, import the business processing data transmitted by the financial data collection module into the business processing data calculation model, and obtain the business efficiency coefficient value. The business processing data calculation model is specifically expressed as: ， in, represents the business efficiency coefficient value calculated for the i-th time, Ar i Tr represents the ratio of loan approval rate to rejection time collected for the i-th time. i represents the transaction error rate collected for the i-th time, Bf i represents the optimization frequency of the business process collected for the i-th time; the business resource utilization data analysis node is used to establish a business resource utilization data calculation model, import the business resource utilization data transmitted by the financial data collection module into the business resource utilization data calculation model, and obtain the resource utilization efficiency coefficient value. The business resource utilization data calculation model is specifically expressed as: ， in, Indicates the resource utilization efficiency coefficient value calculated for the i-th time, Su i represents the server resource utilization rate collected for the i-th time, HR i represents the labor input-output ratio of the i-th collection, Mc i represents the marketing resource conversion rate collected for the i-th time, n is the total number of data collections, i is the number of data collections, and the value of i ranges from 1 to n; the business risk data analysis node is used to establish a business risk data calculation model, import the business risk data transmitted by the financial data collection module into the business risk data calculation model, and obtain the risk prevention and control coefficient value. The business risk data calculation model is specifically expressed as: ， Among them, χ i Represents the risk control coefficient value calculated for the i-th time, Nr i represents the recovery rate of non-performing assets collected for the i-th time, Wr i represents the proportion of risky assets collected in the i-th time; Financial data comprehensive evaluation module: including a financial business service management data analysis unit, which is used to conduct comprehensive analysis on the data transmitted by the financial data analysis module and transmit the analysis results to the real-time tracking feedback warning module; The financial business service management data analysis unit is used to establish a financial business service management data calculation model, and import the financial soundness coefficient value, credit risk coefficient value, asset growth health coefficient value, business efficiency coefficient value, resource utilization efficiency coefficient value and risk prevention and control coefficient value transmitted by the financial data analysis module into the financial business service management data calculation model to obtain the comprehensive evaluation index value of the financial business service management; the financial business service management data calculation model is specifically expressed as: ， Among them, ME represents the calculated comprehensive evaluation index value of financial business service management, α i represents the value of the financial soundness coefficient calculated for the i-th time, β i represents the credit risk coefficient value calculated for the i-th time, γ i Indicates the asset growth health coefficient value calculated for the i-th time, represents the business efficiency coefficient value calculated for the i-th time, represents the resource utilization efficiency coefficient value calculated for the i-th time, χ i Indicates the risk control coefficient value calculated for the i-th time Real-time tracking feedback warning module: used to establish preset values ​​of the comprehensive evaluation index of financial business service management, judge the value of the comprehensive evaluation index of financial business service management according to the preset values ​​of the comprehensive evaluation index of financial business service management, and send corresponding signals according to the judgment results.

Images