E-commerce loan financing online return clearing supervision system and method

Abstract

The invention relates to the technical field of financial supervision, in particular to an e-commerce loan financing online return clearing supervision system and method. According to the invention, through refined classification of the transaction data and accurate identification of the type of the returned money, independent processing of different types of returned money is ensured, the risk of fund confusion is reduced, and the transparency of fund flow direction is improved. The accurate matching of the return fund and the financing order enables each fund to be quickly cleared according to a preset rule, and improves the efficiency of fund collection and repayment. Based on the real-time evaluation of the shop refunding condition, a plurality of dimensions such as sales fluctuation, refunding proportion and refunding arrival time are comprehensively considered, a stability index is established, the business state of a merchant can be accurately judged, and misjudgment caused by short-term abnormal fluctuation is avoided. In combination with the fund return stability index and the merchant credit score, the credit rating system is optimized, so that the dynamic adjustment of the credit score better conforms to the real business condition of the merchant.

Description

Technical Field

[0001] This invention relates to the field of financial regulatory technology, and in particular to an online repayment clearing and supervision system and method for e-commerce loan financing. Background Technology

[0002] The field of financial regulatory technology encompasses the research and application of technical means and systems for risk management, transaction monitoring, and compliance review in financial activities. Its core content covers financial data analysis, payment and settlement monitoring, fund flow supervision, and credit risk control. It primarily achieves control over financial transaction behavior by establishing standardized data exchange mechanisms, automated risk control models, and real-time monitoring platforms.

[0003] The e-commerce loan financing online repayment and clearing supervision system refers to a regulatory technology solution for online monitoring and clearing of loan repayment processes generated on e-commerce platforms. This system primarily involves the identification, collection, and classification of loan repayments. Relying on an automated data interaction mechanism, it accurately matches borrowers' repayment funds and completes the distribution according to preset rules. The system typically employs a transaction-based fund tracking method to verify received repayment funds and process them according to the fund allocation plan stipulated in the loan agreement, ensuring a clear and traceable repayment path.

[0004] Traditional methods for loan financing on e-commerce platforms have significant limitations in tracking and clearing fund repayments. Distinguishing repayment categories relies on basic transaction flow information, making it difficult to accurately identify different sources of repayments. This leads to some funds being misclassified, affecting subsequent clearing and repayment. The matching of repayment funds with financing orders lacks fine-grained processing; some repayments may be held up due to inaccurate verification, reducing capital utilization and potentially causing additional overdue risks for the borrower due to delayed repayments. Assessing merchant operating conditions relies solely on a single transaction indicator, failing to comprehensively reflect the stability of store operations. This results in a lag in credit score adjustments, making it impossible to accurately match the merchant's actual operating situation. Fixed-ratio fund release and freezing mechanisms fail to dynamically adjust based on merchant repayment performance, potentially leading to some merchants, even those with good operations, being subject to strict funding restrictions, impacting normal operations. Overall, existing technologies have room for improvement in fund identification accuracy, repayment matching accuracy, merchant credit assessment dimensions, and fund supervision flexibility, hindering the efficient operation of e-commerce platform financing. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing an online repayment clearing and monitoring system and method for e-commerce loan financing.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an online repayment clearing and monitoring system for e-commerce loan financing includes: The transaction recognition module acquires transaction data from e-commerce platform stores, distinguishes between various categories of transactions such as normal sales revenue, refund revenue, and after-sales compensation, and obtains revenue category information. Based on the repayment category information, the order matching and clearing module establishes the association between repayment funds and financing orders, determines whether the current repayment funds meet the outstanding amount of the corresponding financing order, marks the repayment funds that are still not cleared, and obtains the clearing data of the financing orders. Based on the financing order clearing data, the operation evaluation module analyzes the merchant's payment status, calculates the merchant's cash payment stability index, and classifies the store's operation status to obtain the store operation stability classification results. The credit score adjustment module calculates the merchant's credit score based on the payment stability index of each type of store in the store operation stability classification results, analyzes the trend of credit score changes, formulates the priority of fund release, and obtains credit priority information. Based on the credit priority information and financing order clearing data, the fund release and freezing module determines the amount that the merchant's account can freely withdraw, marks the remaining frozen funds, and obtains the store account's available funds supervision record.

[0007] As a further aspect of the present invention, the repayment category information includes normal sales repayment, refund repayment, after-sales compensation repayment, transaction settlement amount, and arrival time. The financing order clearing data includes the correlation between repayment funds and financing orders, the outstanding amount of financing orders, the proportion of principal repayment, the proportion of interest repayment, the proportion of service fee repayment, and the mark of uncleared repayment funds. The store operation stability classification results include sales amount fluctuation value, average daily number of transactions, order cancellation rate, refund rate, repayment arrival time difference, fund repayment stability index, and store operation status category. The credit priority information includes repayment stability index, on-time repayment rate of financing orders, number of overdue payments, merchant credit score, credit rating, and fund release priority. The store account available funds supervision record includes the fund release ratio corresponding to the credit rating, the fund freezing ratio, the amount of freely withdrawable funds in the merchant account, and the mark of remaining frozen funds.

[0008] As a further aspect of the present invention, the transaction identification module includes: The transaction data acquisition submodule acquires transaction data from e-commerce platform stores, including sales orders, settlement orders, refund orders, after-sales orders, and store account payment records. It extracts multiple parameters such as order number, transaction amount, transaction type, and transaction time, and establishes transaction data records. The payment category module determines the transaction type of each transaction based on the transaction data records, distinguishes between normal sales payments, refund payments, and after-sales compensation payments, calculates the settlement amount and arrival time, and establishes payment category information.

[0009] As a further aspect of the present invention, the order matching and clearing module includes: The repayment fund matching submodule, based on the repayment category information, calls the outstanding repayment amount data of the financing order, matches the corresponding repayment funds, establishes the association between the repayment funds and the financing order, determines whether the current repayment funds meet the outstanding repayment amount of the corresponding financing order, and obtains the fund matching status data; The repayment ratio calculation submodule, based on the aforementioned fund matching status data, extracts the matched repayment amount and the outstanding repayment amount of the financing order, using the following formula: ; Calculate the proportion of principal repayment and obtain the repayment ratio data; in, This represents the proportion of funds used to repay the principal. This represents the amount of funds that have been matched for repayment. The first loan term that has been repaid in the representative financing order Item cost amount, This represents the amount of interest to be paid. This represents the amount of service fees still owed. The unresolved funds marking submodule filters out outstanding repayment funds based on the fund matching status data and fund repayment ratio data, marks some funds, and obtains financing order clearing data.

[0010] As a further aspect of the present invention, the business evaluation module includes: Based on the financing order clearing data, the payment data analysis submodule obtains the store's sales amount, number of transactions, number of order cancellations, refund amount, and payment arrival time within a specified period, and extracts the corresponding sales amount fluctuation value, average daily number of transactions, order cancellation ratio, refund ratio, and payment arrival time difference to generate a payment data feature set; The stability index calculation submodule uses the formula based on the aforementioned collection data feature set: ; Calculate the stability index of fund collection ; in, Represents the number of days within the statistical period. This represents the sales amount on day j. This represents the average sales amount within the statistical period. This represents the number of order cancellations. Represents the refund amount. This represents the time difference in the receipt of payments. These represent the maximum values ​​of the number of order cancellations, the amount of refunds, and the time difference between the arrival of funds within the statistical period, respectively. The business status classification submodule compares the fund recovery stability index with multiple preset interval thresholds to classify stores into three categories: stable operation, fluctuating operation, and risky operation, generating a store operation stability classification result.

[0011] As a further aspect of the present invention, the credit score adjustment module includes: The credit score calculation submodule uses the formula based on the store's operational stability classification results: ; Calculate merchant credit score ; in, This represents the number of transactions within the statistical period. This represents the stability index of repayments corresponding to transaction a. This represents the order amount for the a-th transaction. This represents the order amount for transaction b. The on-time repayment rate of representative financing orders, Represents the number of historical overdue payments. The number of financing rounds within a specified time period. Represents the transaction failure rate. Represents the highest historical transaction failure rate; The credit priority adjustment submodule sets a threshold for the change trend of the credit score based on the merchant's credit score, adjusts the merchant's credit level, calls the credit level information, divides the priority of fund release according to the credit level, and generates credit priority information.

[0012] As a further aspect of the present invention, the fund release and freezing module includes: The credit rating fund calculation submodule extracts the credit priority parameters and order clearing amount corresponding to each credit rating based on the credit priority information and financing order clearing data, calculates the fund release and freezing ratio under each credit rating, calculates the fund release amount according to the ratio of the release weight corresponding to the credit rating to the order clearing amount, and determines the corresponding freezing ratio in combination with the frozen fund base, thus obtaining a set of fund release and freezing ratios. The merchant account funds management submodule calculates the amount of funds that a merchant account can freely withdraw under the current credit rating based on the set of fund release and freeze ratios. It calculates the available funds in the account according to the release ratio, marks the remaining frozen funds, divides the funds into available funds and frozen funds, obtains the amount of funds that a merchant account can freely withdraw, marks the remaining frozen funds, and obtains the store account available funds supervision record.

[0013] A method for online repayment clearing and supervision of e-commerce loan financing, wherein the method is executed based on the aforementioned online repayment clearing and supervision system for e-commerce loan financing, and includes the following steps: S1: Obtain transaction data from e-commerce platform stores, distinguish between normal sales revenue, refund revenue, and after-sales compensation transactions, and obtain revenue category information; S2: Based on the repayment category information, establish the association between repayment funds and financing orders, determine whether the current repayment funds meet the outstanding amount of the corresponding financing order, mark the repayment funds that are still not cleared, and obtain the clearing data of the financing orders; S3: Based on the financing order clearing data, analyze the merchant's payment status, calculate the merchant's fund payment stability index, and classify the store's operating status to obtain the store operating stability classification result; S4: Calculate the merchant credit score based on the payment stability index of each type of store in the store operation stability classification results, analyze the trend of credit score changes and formulate the priority of fund release, and obtain credit priority information; S5: Based on the credit priority information and financing order clearing data, determine the amount that the merchant account can freely withdraw, mark the remaining frozen funds, and obtain the store account available funds supervision record.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: This invention ensures independent processing of different types of payments through refined classification of transaction data and accurate identification of payment categories, reducing the risk of fund confusion and improving the transparency of fund flows. Precise matching of payment funds with financing orders allows each fund to be quickly cleared according to preset rules, improving the efficiency of fund collection and repayment. Based on real-time assessment of store payment status, a stability index is established, comprehensively considering multiple dimensions such as sales fluctuations, refund ratios, and payment arrival times. This helps to accurately judge the merchant's operating status and avoid misjudgments caused by short-term abnormal fluctuations. Combining the fund payment stability index with merchant credit scores optimizes the credit rating system, making dynamic adjustments to credit scores more consistent with the merchant's actual operating situation. Based on this, fund release priorities are set, ensuring that high-credit merchants enjoy higher liquidity, reducing credit risk while improving capital utilization. By calculating the fund release ratio corresponding to credit ratings, a dynamic balance is ensured between withdrawable funds and frozen funds in the account, avoiding the problem of a broken capital chain due to unreasonable fund freezing ratios, making fund supervision more targeted and flexible. Attached Figure Description

[0015] Figure 1 This is a system flowchart of the present invention; Figure 2 This is a flowchart of the transaction identification module of the present invention; Figure 3 This is a flowchart of the order matching and clearing module of the present invention; Figure 4 This is a flowchart of the business evaluation module of the present invention; Figure 5 This is a flowchart of the credit score adjustment module of the present invention; Figure 6 This is a flowchart of the fund release and freezing module of the present invention. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0018] Please see Figure 1 This invention provides a technical solution: an online repayment clearing and monitoring system for e-commerce loan financing, comprising: The transaction identification module acquires transaction data from e-commerce platform stores, including sales orders, settlement orders, refund orders, after-sales orders, and store account payment records. It distinguishes between various types of transactions, such as normal sales payments, refund payments, and after-sales compensation, and determines the settlement amount and arrival time of each transaction to obtain payment category information. The order matching and clearing module establishes the relationship between the repayment funds and the financing orders based on the repayment category information, determines whether the current repayment funds meet the outstanding amount of the corresponding financing order, calculates the proportion of funds that can be used to repay the principal, interest and service fees, marks the repayment funds that are still not cleared, and obtains the clearing data of the financing orders. The business assessment module analyzes the merchant's payment status based on the financing order clearing data, including the fluctuation value of the store's sales amount within a specified period, the average number of transactions per day, the order cancellation rate, the refund rate, and the time difference of payment arrival. It calculates the merchant's fund payment stability index and classifies the store's business status to obtain the store business stability classification results. The credit score adjustment module calculates the merchant's credit score based on the repayment stability index, on-time repayment rate of financing orders, and number of historical overdue payments for each type of store in the store operation stability classification results. It adjusts the merchant's credit rating according to the trend of credit score changes, sets the priority of fund release with reference to the credit rating, and obtains credit priority information. The fund release and freeze module calculates the fund release and freeze ratio for each credit level based on credit priority information and financing order clearing data. It determines the amount that the merchant account can freely withdraw based on the fund release and freeze ratio, marks the remaining frozen funds, and obtains the store account's available fund supervision record. The information on payment categories includes normal sales payments, refund payments, after-sales compensation payments, transaction settlement amounts, and arrival times. Financing order clearing data includes the relationship between payment funds and financing orders, the outstanding amount of financing orders, the proportion of principal repaid, the proportion of interest repaid, the proportion of service fee repaid, and the flag of uncleared payment funds. Store operational stability classification results include sales amount fluctuation, average daily transaction volume, order cancellation rate, refund rate, payment arrival time difference, payment stability index, and store operational status category. Credit priority information includes payment stability index, on-time repayment rate of financing orders, historical overdue payments, merchant credit score, credit rating, and fund release priority. Store account available funds monitoring records include the fund release ratio corresponding to the credit rating, the fund freeze ratio, the amount of funds freely withdrawable from the merchant account, and the flag of remaining frozen funds.

[0019] Please see Figure 2 The transaction identification module includes: The transaction data acquisition submodule acquires transaction data from e-commerce platform stores, including sales orders, settlement orders, refund orders, after-sales orders, and store account payment records. It extracts multiple parameters such as order number, transaction amount, transaction type, and transaction time, and establishes transaction data records. The transaction data acquisition submodule retrieves various order data from the store in batches by calling the e-commerce platform's API interface. This includes sales orders, settlement orders, refund orders, after-sales orders, and the store's account payment history. For each transaction, the order number is first parsed. Using a unique identifier field in the order structure, such as "order_id" or "transaction_id," the module matches the order information in the database and compares it with historical records to avoid duplicate retrieval. Then, the transaction amount is extracted. This amount can be obtained from the "total_amount" field in the order details. For sales orders, this amount is directly taken from the total order amount field. For refund orders, it is obtained from the "refund_amount" field. For after-sales orders, the compensation amount needs to be calculated. The compensation amount is calculated as follows: Compensation unit price × Compensation quantity. The compensation unit price can be set in tiers based on the degree of damage to the goods. For example, the compensation unit price is 50 yuan for minor damage, 100 yuan for moderate damage, and 200 yuan for severe damage. If an order involves two moderately damaged goods, the compensation amount is 100 × 2 = 200 yuan. The transaction type is determined based on the order status field. For example, if the "order_status" field value is "completed", it is a sales order; if the value is "refund_completed", it is a refund order; and if the value is "after_sales_compensated", it is an after-sales order. The transaction time is extracted based on the "transaction_time" field returned by the platform. The time is converted into a standard format and stored in the database to finally establish a complete transaction data record.

[0020] The payment category module determines the transaction type of each transaction based on transaction data records, distinguishes between normal sales payments, refund payments, and after-sales compensation payments, calculates the settlement amount and arrival time, and establishes payment category information. The payment category module first calls the transaction data records and analyzes the transaction type of each transaction to determine the payment category. If the transaction type is a sales order, it is classified as a normal sales payment and its settlement amount is recorded. This amount can be obtained by calculating the receivable amount - platform deduction - commission fee. Assuming a transaction amount of 500 yuan, a platform deduction rate of 5%, and a fixed commission fee of 10 yuan, the settlement amount is calculated as follows: Settlement amount = 500 - 500 × 5% - 10 = 475 - 10 = 465 yuan. If the transaction type is a refund order, the refund amount is calculated. The refund amount is equal to the original order's refund amount. Assuming a refund order's refund amount is 300 yuan, the refund amount is calculated as follows: The amount is 300 yuan. If the transaction type is an after-sales order, the after-sales compensation amount is calculated based on the compensation policy. For example, if the compensation amount for an after-sales compensation order is 150 yuan, then the after-sales compensation amount is 150 yuan. The arrival time is determined based on the platform's payment cycle. Generally, e-commerce platforms use T+7 settlement for sales payments, meaning the payment arrives 7 days after the transaction is completed. Refund payments usually arrive within 1-3 days after the refund is approved. After-sales compensation payments are based on the compensation policy. Assuming the compensation arrives on T+5, the arrival time for an after-sales compensation order can be calculated as the transaction completion date + 5 days. For example, if the transaction completion date is March 1, then the arrival time is March 6, thus forming the final payment category information.

[0021] Please see Figure 3 The order matching and clearing module includes: The repayment funds matching submodule, based on repayment category information, calls the outstanding repayment amount data of financing orders, matches the corresponding repayment funds, establishes the association between repayment funds and financing orders, determines whether the current repayment funds meet the outstanding repayment amount of the corresponding financing order, and obtains the fund matching status data; First, the category of each payment needs to be determined, such as sales payment, lease payment, or other payment types. Then, based on the repayment requirements of the financing order, the payment funds are matched with the financing order. The matching method is based on a one-to-one filtering of payment amount, due date, and order type. In practical application, if the outstanding amount of a financing order is 100,000 yuan and the corresponding payment amount is 60,000 yuan, the matching status is marked as partial match. If the payment amount is greater than or equal to the outstanding amount of the financing order, it is marked as a complete match. The specific matching rules are as follows: Table 1 Classification of Fund Matching Status As shown in Table 1, if some of the recovered funds are still not matched, it is necessary to redistribute the unmatched funds to obtain fund matching status data.

[0022] The repayment ratio calculation submodule extracts the matched repayment amount and the outstanding amount of financing orders based on the fund matching status data, using the following formula: ; Calculate the proportion of principal repayment and obtain the repayment ratio data; in, This represents the proportion of funds used to repay the principal. This represents the amount of funds that have been matched for repayment. The first loan term that has been repaid in the representative financing order Item cost amount, This represents the amount of interest to be paid. This represents the amount of service fees still owed.

[0023] Assuming the matched repayment amount is 80,000 yuan, the outstanding amount of the financing order is 100,000 yuan, including 15,000 yuan in interest and 5,000 yuan in service fees, and repaid costs including management fees and overdue fees of 3,000 yuan and 2,000 yuan respectively, and the principal is 80,000 yuan, the proportion of funds available for principal repayment is calculated as follows: ; in, ; Substitute the specific values ​​into the formula to calculate: .

[0024] Calculated This indicates that the repayment fully covers the principal, and the excess can be used to repay interest and service fees. Therefore, the repayment ratio is adjusted as follows: principal repayment ratio 100%, interest repayment ratio 100%, and service fee repayment ratio 100%. If the excess still exists, it can be used for the outstanding amount of future orders or reallocated to other unmatched orders. The calculation results will be recorded in the financing order repayment data to obtain the repayment ratio data.

[0025] The unresolved funds marking submodule filters out outstanding repayment funds based on fund matching status data and fund repayment ratio data, marks these funds, and obtains financing order clearing data. The process involves filtering out outstanding repayments. For example, in the previous calculation step, if the repayment amount for a financing order was 100,000 yuan, and the repayment amount was 80,000 yuan, then 20,000 yuan remains outstanding. This outstanding amount needs to be marked and recorded in the pending list. The specific data is as follows: Table 2. Undistributed Funds Marking Table As shown in Table 2, there are still 20,000 yuan of undistributed funds that need to be processed further to obtain financing order distribution data.

[0026] Please see Figure 4 The business evaluation module includes: The payment collection data analysis submodule, based on financing order clearing data, obtains the store's sales amount, number of transactions, number of order cancellations, refund amount, and payment collection arrival time within a specified period. It then extracts the corresponding sales amount fluctuation value, average daily number of transactions, order cancellation ratio, refund ratio, and payment collection arrival time difference to generate a payment collection data feature set. Assuming we obtain transaction data for a store from March 1, 2024 to March 5, 2024, specifically including daily sales amount, number of transactions, number of order cancellations, refund amount, and payment arrival time, daily sales amount can be summarized through the store's transaction history, as shown in Table 3: Calculate the daily sales fluctuation value, which is the deviation between the daily sales amount and the average sales amount within the period. For example, if the total sales amount over 5 days is 53,800 yuan, then the average daily sales amount is: ; If sales on a certain day are 12,000 yuan, then the fluctuation value for that day is: ; The order cancellation rate is calculated as the ratio of the number of cancelled orders to the total number of orders. For example, if 5 orders were cancelled on March 3rd and the total number of orders was 82, then the cancellation rate would be: ; The refund ratio is calculated as the ratio of the refund amount to the sales revenue for that day. For example, if the refund amount on March 5th is 700 yuan and the total sales revenue is 11,300 yuan, then the refund ratio is: ; The time difference for payment arrival is calculated as the difference between the order creation time and the actual arrival time. For example, if an order is created at 12:00 on March 1st and arrives at 14:00 on March 3rd, the time difference is: Finally, based on the above calculated data, a feature set of repayment data is generated.

[0027] The stability index calculation submodule is based on the feature set of payment collection data and uses the following formula: ; Calculate the stability index of fund collection ; in, Represents the number of days within the statistical period. This represents the sales amount on day j. This represents the average sales amount within the statistical period. This represents the number of order cancellations. Represents the refund amount. This represents the time difference in the receipt of payments. These represent the maximum values ​​of the number of order cancellations, refund amount, and time difference of payment arrival within the statistical period, respectively, and the data is normalized.

[0028] like (Statistical period in days), calculate the average fluctuation of sales amount: ; In the order cancellation data, The number of order cancellations on March 2nd was 3. After normalization: ; In the refund amount data, The refund amount on March 2nd was 400 yuan, after normalization: ; In the data on the time difference of payment receipt, The time difference between the receipt of funds on March 2nd and the arrival of funds is 50 hours. After normalization: ; Final calculation: .

[0029] The result indicates that the store's cash flow stability index is 1.976, which can be used for further classification.

[0030] The business status classification submodule compares the fund recovery stability index with multiple preset interval thresholds to divide the store into three categories: stable operation, fluctuating operation, and risky operation, generating a store business stability classification result. Based on the cash flow stability index and statistical analysis of historical transaction data, and by summarizing the characteristics of cash flow data from a large number of stores, combined with industry standards and market averages, different threshold ranges are set to classify stores into three categories: stable operation, fluctuating operation, and risky operation. The thresholds are set as follows: Stable operation: Fluctuating operations: High-risk operation: Regarding the aforementioned calculation results The store is classified as operating under fluctuating conditions, meaning that its cash flow performance fluctuates to some extent, but does not reach the risk level.

[0031] Table 4 Example of Calculating Store Cash Flow Stability Index As shown in Table 4, different dates are categorized into corresponding operating status categories based on the calculated fund recovery stability index. This categorization can be further used for adjusting operating strategies.

[0032] Please see Figure 5 The credit score adjustment module includes: The credit score calculation submodule uses the formula based on the store's operational stability classification results: ; Calculate merchant credit score ; in, This represents the number of transactions within the statistical period. This represents the stability index of repayments corresponding to transaction a. This represents the order amount for the a-th transaction. This represents the order amount for transaction b. The on-time repayment rate of representative financing orders, Represents the number of historical overdue payments. The number of financing rounds within a specified time period. Represents the transaction failure rate. This represents the highest historical transaction failure rate.

[0033] To obtain the payment stability index, on-time repayment rate of financing orders, and historical overdue number of transactions for each type of store, combined with the total order amount of the merchant, the number of financing transactions in the past 6 months, and the transaction failure rate, firstly, obtain the transaction data of all stores over a period of time and extract relevant information. For example, count the payment time of all orders and calculate the payment stability index corresponding to each order. If a store has 5, 4, 6, 5, and 4 orders successfully repaid in the past five days, with a total of 24 transactions, and the daily order amounts are 50,000 yuan, 40,000 yuan, 60,000 yuan, 55,000 yuan, and 45,000 yuan respectively, then the total order amount is 250,000 yuan. Assuming the payment stability index of each order is 0.85, 0.80, 0.88, 0.87, and 0.82 respectively, the weighted calculation of the payment stability index is as follows: ; .

[0034] Secondly, calculate the on-time repayment rate for financing orders. This metric measures a merchant's creditworthiness regarding financing orders. Assuming a store applied for 10 financing orders in the past 6 months, with 8 on-time repayments and 2 overdue, the on-time repayment rate would be calculated as follows: Furthermore, the system retrieves historical overdue payment records, analyzing the store's overdue payment history over the past 12 months. For example, if a store has 5 overdue payments, the value of this indicator is 5. Simultaneously, it tracks the merchant's financing activities over the past 6 months. For instance, if a merchant has 4 financing activities in 6 months, the value of this indicator is 4. The transaction failure rate is calculated by determining the percentage of orders that were rejected or failed out of all the store's transactions. For example, if a store had 24 transactions in the past five days, and 2 of them were cancelled due to payment failure or customer rejection, the transaction failure rate would be calculated as follows: Assuming the merchant's historical maximum transaction failure rate is 0.12, the credit score is calculated using the following formula: ; The result indicates that the merchant's credit score is 0.5739, which can be used for further credit rating.

[0035] The credit priority adjustment submodule adjusts the merchant's credit rating based on the merchant's credit score, sets a threshold for the trend of the score change, retrieves the credit rating information, divides the priority of fund release according to the credit rating, and generates credit priority information. Set a threshold for rating trend changes, adjust merchant credit ratings, obtain merchant credit scores over different periods, and determine the trend of credit score changes. If the credit score decreases for two consecutive periods, the merchant's credit rating is lowered. For example, if a merchant's credit score was 0.75 in the previous period and 0.57 in the current period, the credit rating will be lowered by one level due to the continuous decline. Conversely, if the credit score increases for two consecutive periods, the credit rating is raised. For example, if a merchant's credit scores were 0.9 and 1.2 in the past two months, the credit rating will be raised by one level. This establishes the credit rating division. The standard classifies merchants into three levels: A-level (credit score greater than 1.5), B-level (credit score between 1.0 and 1.5), and C-level (credit score less than 1.0). For example, if a merchant's latest credit score is 0.5739, it would be classified as a C-level merchant. Fund release priority is determined based on credit rating, with A-level merchants receiving priority, followed by B-level merchants, and C-level merchants receiving restrictions. For instance, if a platform has a fund pool of 5 million yuan, 3 million yuan will be released to A-level merchants first, 1.5 million yuan to B-level merchants, and only 500,000 yuan to C-level merchants, ultimately generating credit priority information.

[0036] Please see Figure 6 The fund release and freezing module includes: The credit rating funding calculation submodule extracts the credit priority parameters and order clearing amount corresponding to each credit rating based on credit priority information and financing order clearing data. It calculates the funding release and freezing ratio under each credit rating, calculates the funding release amount based on the ratio of the release weight corresponding to the credit rating to the order clearing amount, and determines the corresponding freezing ratio based on the frozen fund base, thus obtaining a set of funding release and freezing ratios. Extract the credit priority parameters and order clearing amounts corresponding to each credit rating, and calculate the fund release and freezing ratios for each credit rating. First, obtain the financing order clearing data for merchants of each credit rating, including the transaction amount, settlement time, and merchant credit priority for each order. Assume that the credit ratings are divided into three levels: A, B, and C, corresponding to 30, 40, and 50 merchants respectively. The financing order clearing amount is different for each merchant. For example, the order amount for a merchant in level A is... Yuan, the order amount for B-level merchants is Yuan, the order amount for C-level merchants is If the amount is in yuan, then calculate the total clearing amount corresponding to each credit rating: ; in, Represents credit rating The total amount of order clearing (A, B, or C) Represents credit rating The number of merchants below Represents credit rating The order settlement amount for the oth merchant.

[0037] The total order clearing amount for each credit rating is calculated as follows: ; ; ; Calculate the total settlement amount for all credit ratings: ; The formula for calculating the funding release ratio for each credit rating is as follows: ; in, Represents credit rating The proportion of funds released from (A, B, or C) This represents the total amount cleared across all credit ratings.

[0038] The release ratios for each level are calculated as follows: ; ; ; Subsequently, the amount of funds released based on the credit rating is calculated using the following formula: ; in, Represents credit rating The amount of funds released (A, B, or C), This represents the total pool of funds that can be released.

[0039] Assuming the total size of the funding pool is 2,000,000 yuan, the funding release amount for each credit rating is calculated as follows: ; ; ; Finally, the freezing ratio is calculated based on the base amount of frozen funds, using the following formula: ; in, Represents credit rating The freezing ratio of (A, B, or C).

[0040] The calculation is as follows: ; ; ; The results show that when the amount of funds released exceeds the total amount to be cleared, the proportion of frozen funds is negative. The actual amount of frozen funds needs to be set to a minimum to prevent excessive release of funds. Finally, a set of fund release and freezing ratios is generated.

[0041] The merchant account funds management submodule calculates the amount of funds that a merchant account can freely withdraw under the current credit rating based on the set of fund release and freezing ratios. It calculates the available funds in the account according to the release ratio and marks the remaining frozen funds. It divides the funds into available funds and frozen funds, obtains the amount of funds that a merchant account can freely withdraw, marks the remaining frozen funds, and obtains the store account available funds supervision record. First, obtain the merchant's current withdrawable funds, calculated using the following formula: ; in, Represents credit rating The freely withdrawable amount of (A, B, or C) Represents credit rating (A, B, or C) Funds that have been released but not yet withdrawn.

[0042] Assuming that a Level A merchant has 250,000 yuan released but not withdrawn, a Level B merchant has 180,000 yuan, and a Level C merchant has 140,000 yuan, the calculation is as follows: ; ; ; Secondly, the available funds in the account are calculated based on the release ratio using the following formula: ; in, Represents credit rating Available funds for a single merchant (A, B, or C) Represents credit rating The number of merchants (A, B, or C).

[0043] Assuming there are 30 merchants at level A, 40 at level B, and 50 at level C, the calculation is as follows: ; ; ; Finally, mark the remaining frozen funds and divide the funds into available funds and frozen funds using the formula: ; in, Represents credit rating The remaining frozen funds of (A, B or C).

[0044] The calculation is as follows: ; ; ; Finally, a record of available funds for monitoring the store account is generated.

[0045] A method for online repayment clearing and supervision of e-commerce loan financing, which is implemented based on the aforementioned online repayment clearing and supervision system for e-commerce loan financing, includes the following steps: S1: Obtain transaction data from e-commerce platform stores, distinguish between normal sales revenue, refund revenue, and after-sales compensation transactions, and obtain revenue category information; S2: Based on the repayment category information, establish the relationship between repayment funds and financing orders, determine whether the current repayment funds meet the outstanding amount of the corresponding financing order, mark the repayment funds that are still not cleared, and obtain the clearing data of financing orders; S3: Based on the financing order clearing data, analyze the merchant's payment status, calculate the merchant's payment stability index, and classify the store's operating status to obtain the store operating stability classification results; S4: Calculate the merchant credit score based on the payment stability index of each type of store in the store operation stability classification results, analyze the trend of credit score changes and formulate the priority of fund release, and obtain credit priority information; S5: Based on credit priority information and financing order clearing data, determine the amount of cash that the merchant's account can freely withdraw, mark the remaining frozen funds, and obtain the store account's available funds supervision record.

[0046] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. An online repayment clearing and monitoring system for e-commerce loan financing, characterized in that, The system includes: The transaction recognition module acquires transaction data from e-commerce platform stores, distinguishes between various categories of transactions such as normal sales revenue, refund revenue, and after-sales compensation, and obtains revenue category information. Based on the repayment category information, the order matching and clearing module establishes the association between repayment funds and financing orders, determines whether the current repayment funds meet the outstanding amount of the corresponding financing order, marks the repayment funds that are still not cleared, and obtains the clearing data of the financing orders. Based on the financing order clearing data, the operation evaluation module analyzes the merchant's payment status, calculates the merchant's cash payment stability index, and classifies the store's operation status to obtain the store operation stability classification results. The credit score adjustment module calculates the merchant's credit score based on the payment stability index of each type of store in the store operation stability classification results, analyzes the trend of credit score changes, formulates the priority of fund release, and obtains credit priority information. Based on the credit priority information and financing order clearing data, the fund release and freezing module determines the amount that the merchant's account can freely withdraw, marks the remaining frozen funds, and obtains the store account's available funds supervision record.

2. The online repayment and clearing supervision system for e-commerce loan financing according to claim 1, characterized in that, The repayment category information includes normal sales repayment, refund repayment, after-sales compensation repayment, transaction settlement amount, and arrival time. The financing order clearing data includes the correlation between repayment funds and financing orders, the outstanding amount of financing orders, the proportion of principal repayment, the proportion of interest repayment, the proportion of service fee repayment, and the mark of uncleared repayment funds. The store operation stability classification results include sales amount fluctuation value, average daily number of transactions, order cancellation rate, refund rate, repayment arrival time difference, fund repayment stability index, and store operation status category. The credit priority information includes repayment stability index, on-time repayment rate of financing orders, number of overdue payments, merchant credit score, credit rating, and fund release priority. The store account available funds supervision record includes the fund release ratio corresponding to the credit rating, the fund freezing ratio, the amount of freely withdrawable funds in the merchant account, and the mark of remaining frozen funds.

3. The online repayment clearing and monitoring system for e-commerce loan financing according to claim 1, characterized in that, The transaction identification module includes: The transaction data acquisition submodule acquires transaction data from e-commerce platform stores, including sales orders, settlement orders, refund orders, after-sales orders, and store account payment records. It extracts multiple parameters such as order number, transaction amount, transaction type, and transaction time, and establishes transaction data records. The payment category module determines the transaction type of each transaction based on the transaction data records, distinguishes between normal sales payments, refund payments, and after-sales compensation payments, calculates the settlement amount and arrival time, and establishes payment category information.

4. The online repayment and clearing supervision system for e-commerce loan financing according to claim 1, characterized in that, The order matching and clearing module includes: The repayment fund matching submodule, based on the repayment category information, calls the outstanding repayment amount data of the financing order, matches the corresponding repayment funds, establishes the association between the repayment funds and the financing order, determines whether the current repayment funds meet the outstanding repayment amount of the corresponding financing order, and obtains the fund matching status data; The repayment ratio calculation submodule, based on the aforementioned fund matching status data, extracts the matched repayment amount and the outstanding repayment amount of the financing order, using the following formula: ； Calculate the proportion of principal repayment and obtain the repayment ratio data; in, This represents the proportion of funds used to repay the principal. This represents the amount of funds that have been matched for repayment. The first loan term that has been repaid in the representative financing order Cost amount, This represents the amount of interest to be paid. This represents the amount of service fees still owed. The unresolved funds marking submodule filters out outstanding repayment funds based on the fund matching status data and fund repayment ratio data, marks some funds, and obtains financing order clearing data.

5. The online repayment and clearing supervision system for e-commerce loan financing according to claim 1, characterized in that, The operational evaluation module includes: Based on the financing order clearing data, the payment data analysis submodule obtains the store's sales amount, number of transactions, number of order cancellations, refund amount, and payment arrival time within a specified period, and extracts the corresponding sales amount fluctuation value, average daily number of transactions, order cancellation ratio, refund ratio, and payment arrival time difference to generate a payment data feature set; The stability index calculation submodule uses the formula based on the aforementioned collection data feature set: ； Calculate the stability index of fund collection ; in, Represents the number of days within the statistical period. This represents the sales amount on day j. This represents the average sales amount within the statistical period. This represents the number of order cancellations. Represents the refund amount. This represents the time difference in the receipt of payments. These represent the maximum values ​​of the number of order cancellations, the amount of refunds, and the time difference between the arrival of funds within the statistical period, respectively. The business status classification submodule compares the fund recovery stability index with multiple preset interval thresholds to classify stores into three categories: stable operation, fluctuating operation, and risky operation, generating a store operation stability classification result.

6. The online repayment and clearing supervision system for e-commerce loan financing according to claim 1, characterized in that, The credit score adjustment module includes: The credit score calculation submodule uses the formula based on the store's operational stability classification results: ； Calculate merchant credit score ; in, This represents the number of transactions within the statistical period. This represents the stability index of repayments corresponding to transaction a. This represents the order amount for the a-th transaction. This represents the order amount for transaction b. The on-time repayment rate of representative financing orders, Represents the number of historical overdue payments. The number of financing rounds within a specified time period. Represents the transaction failure rate. Represents the highest historical transaction failure rate; The credit priority adjustment submodule sets a threshold for the change trend of the credit score based on the merchant's credit score, adjusts the merchant's credit level, calls the credit level information, divides the priority of fund release according to the credit level, and generates credit priority information.

7. The online repayment and clearing supervision system for e-commerce loan financing according to claim 1, characterized in that, The fund release and freezing module includes: The credit rating fund calculation submodule extracts the credit priority parameters and order clearing amount corresponding to each credit rating based on the credit priority information and financing order clearing data, calculates the fund release and freezing ratio under each credit rating, calculates the fund release amount according to the ratio of the release weight corresponding to the credit rating to the order clearing amount, and determines the corresponding freezing ratio in combination with the frozen fund base, thus obtaining a set of fund release and freezing ratios. The merchant account funds management submodule calculates the amount of funds that a merchant account can freely withdraw under the current credit rating based on the set of fund release and freeze ratios. It calculates the available funds in the account according to the release ratio, marks the remaining frozen funds, divides the funds into available funds and frozen funds, obtains the amount of funds that a merchant account can freely withdraw, marks the remaining frozen funds, and obtains the store account available funds supervision record.

8. A method for online repayment and clearing supervision of e-commerce loan financing, characterized in that, The online repayment and clearing supervision system for e-commerce loan financing according to any one of claims 1-7 includes the following steps: S1: Obtain transaction data from e-commerce platform stores, distinguish between normal sales revenue, refund revenue, and after-sales compensation transactions, and obtain revenue category information; S2: Based on the repayment category information, establish the association between repayment funds and financing orders, determine whether the current repayment funds meet the outstanding amount of the corresponding financing order, mark the repayment funds that are still not cleared, and obtain the clearing data of the financing orders; S3: Based on the financing order clearing data, analyze the merchant's payment status, calculate the merchant's fund payment stability index, and classify the store's operating status to obtain the store operating stability classification result; S4: Calculate the merchant credit score based on the payment stability index of each type of store in the store operation stability classification results, analyze the trend of credit score changes and formulate the priority of fund release, and obtain credit priority information; S5: Based on the credit priority information and financing order clearing data, determine the amount that the merchant account can freely withdraw, mark the remaining frozen funds, and obtain the store account available funds supervision record.

Images