Order risk prevention and control system based on dealer big data

Abstract

The invention relates to the field of order risk prevention and control, and particularly discloses an order risk prevention and control system based on dealer big data, which comprises a completed order risk management module used for performing data acquisition on completed orders of dealers, evaluating risk management values corresponding to the completed orders of the dealers, and sending the risk management values to the dealers; therefore, the risk prevention and control threshold value corresponding to the completed order of the dealer is screened out, and a data support basis is provided for the subsequent analysis of the risk prevention and control condition of the uncompleted order. The uncompleted order risk prevention and control module is used for acquiring risk management data corresponding to uncompleted orders of the sales enterprises, monitoring logistics management conditions of the orders in real time, judging risk prevention and control values corresponding to the uncompleted orders of the sales enterprises, and providing powerful support for optimizing order risk management and improving risk response capability; and the order risk prevention and control early warning module is used for carrying out risk prevention and control early warning on the uncompleted orders of the dealers, and can continuously carry out effective management on order risk prevention and control.

Description

Technical Field

[0001] The present invention relates to the technical field of order risk prevention and control, and specifically to an order risk prevention and control system based on dealer big data. Background Art

[0002] With increasingly fierce market competition, the increase in the number and types of orders has made order management more complicated. Sales companies need more effective ways to manage order risks. By collecting, integrating and analyzing large amounts of data in sales companies' orders, real-time monitoring and timely monitoring of abnormal behaviors in order transactions can not only improve sales companies' ability to prevent and control operational risks of orders and reduce sales companies' economic losses, but also ensure the stability of sales companies' order business and improve sales companies' order completion rate. Ultimately, it will enhance sales companies' order risk prevention and control efforts, thereby improving dealers' satisfaction with their services.

[0003] For example, the invention patent with announcement number CN110751493B discloses a risk prevention and control method and device based on historical appointment orders, wherein the risk prevention and control method based on historical appointment orders includes: obtaining historical appointment orders for service appointment creation within a historical time period, further extracting the user's payment information and the service provider's collection information recorded in the historical appointment orders, and obtaining the identity feature information of the user and the service provider, and then constructing an identity connection graph based on the connection relationship between the user's payment information, the service provider's collection information and the identity feature information of the user and the service provider, using a graph algorithm to calculate the identity association of a group consisting of nodes corresponding to at least one user and nodes corresponding to at least one service provider in the identity connection graph, and finally determining the risk level of the users and service providers included in the group based on the calculated identity association.

[0004] In combination with the above technical solution, it is found that in the analysis of order risk control, the above application obtains historical appointment orders for service appointment creation within the historical time period, and determines the risk level of users and service providers included in the grouping by calculating the identity association, but lacks risk control for unfinished orders. At the same time, in the process of obtaining relevant data, the accuracy of information acquisition by the data collection platform used, such as the order risk control platform, is not explained in detail. Not only will the relevant data obtained have a certain degree of numerical deviation, but the risk level finally obtained by calculation will deviate to a large extent from the actual risk level, which leads to a lack of management strength for order risk control and causes great economic losses to sales companies. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a system that can effectively solve the problems involved in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an order risk prevention and control system based on dealer big data, including a completed order risk management module, which is used to collect data on completed orders of dealers, obtain historical management data corresponding to completed orders of dealers, and evaluate the risk management value corresponding to completed orders of dealers, thereby screening out the risk prevention and control thresholds corresponding to completed orders of dealers; an unfinished order risk prevention and control module, which is used to obtain the risk management data corresponding to the unfinished orders of sales companies, and determine the risk prevention and control values ​​corresponding to the unfinished orders of sales companies; an order risk prevention and control early warning module, which is used to compare the risk prevention and control values ​​corresponding to the unfinished orders of sales companies with the risk prevention and control thresholds corresponding to the completed orders of dealers, and finally issue risk prevention and control early warnings for the unfinished orders of sales companies; an order risk prevention and control platform, which is used to store transaction reference amounts, transaction permission duration, overdue permission days, sales customer credit permission amount, sales customer credit permission account period, sales customer in-transit permission days, production reference quantity, production permission cost, inventory reference days, detention permission duration, and risk prevention and control thresholds corresponding to each risk management value interval.

[0007] As a further solution, the risk management value corresponding to the completed orders of the dealer is specifically analyzed by the formula:

[0008]

[0009] In the formula, μ is the risk management value corresponding to the dealer's completed orders, ε is the operation degree coefficient corresponding to the dealer's completed orders, δ is the transaction degree coefficient corresponding to the dealer's completed orders, A1 is the predefined weight factor of the operation degree coefficient, and A2 is the predefined weight factor of the transaction degree coefficient.

[0010] As a further solution, the operation degree coefficient corresponding to the completed orders of the dealer, the specific analysis process is as follows:

[0011] Based on the historical management data corresponding to the dealer's completed orders, wherein the historical management data includes historical operation data and historical transaction data; based on the historical operation data corresponding to the dealer's completed orders, wherein the historical operation data includes the number of transactions, the number of successful transactions, and the total types of payments; a comprehensive analysis is performed to obtain the operation degree coefficient corresponding to the dealer's completed orders.

[0012] As a further solution, the transaction degree coefficient corresponding to the completed orders of the dealer is specifically analyzed in the following process: through the historical transaction data corresponding to the completed orders of the dealer, where the historical transaction data includes the transaction amount, transaction duration and overdue days corresponding to each completed order; extracting the transaction reference amount, transaction permission duration and overdue days from the order risk prevention and control platform; analyzing to obtain the transaction degree coefficient corresponding to the completed orders of the dealer.

[0013] As a further solution, the risk control thresholds corresponding to the dealer's completed orders are screened out, and the specific analysis process is: the risk management value corresponding to the dealer's completed orders is matched with the risk control thresholds corresponding to each risk management value interval defined in the order risk control platform, thereby screening out the risk control thresholds corresponding to the dealer's completed orders.

[0014] As a further solution, the risk control value corresponding to the uncompleted orders of the sales enterprise is specifically formulated as follows:

[0015]

[0016] In the formula, α is the risk prevention and control value corresponding to the unfinished orders of the sales enterprise, φ is the risk management coefficient corresponding to the unfinished orders of the sales enterprise, τ is the risk handling coefficient corresponding to the unfinished orders of the sales enterprise, B1 is the predefined weight factor of the risk management coefficient corresponding to the unfinished orders of the sales enterprise, and B2 is the predefined weight factor of the risk handling coefficient corresponding to the unfinished orders of the sales enterprise.

[0017] As a further solution, the risk management coefficient corresponding to the unfinished orders of the sales enterprise, the specific analysis process is: according to the risk management data corresponding to the unfinished orders of the sales enterprise, wherein the risk management data includes production chain risk data, distribution chain risk data and risk handling data; through the production chain risk data corresponding to the unfinished orders of the sales enterprise, wherein the production chain risk data includes production quantity and production cost; extracting the production reference quantity and production license cost from the order risk prevention and control platform; comprehensively analyzing the production quantity and production cost of the unfinished orders of the sales enterprise with the production reference quantity and production license cost extracted from the order risk prevention and control platform, and finally obtaining the sales The production chain management coefficient of the company's unfinished orders; the distribution chain risk data corresponding to the sales company's unfinished orders, where the distribution chain risk data includes the sales customer's total credit limit, the sales customer's total credit account period and the sales customer's total in-transit days; the sales customer's credit permission limit, the sales customer's credit permission account period and the sales customer's in-transit permission days are extracted from the order risk prevention and control platform; and finally the distribution chain management coefficient corresponding to the sales company's unfinished orders is analyzed; the production chain management coefficient of the sales company's unfinished orders and the distribution chain management coefficient corresponding to the sales company's unfinished orders are weighted averaged to finally obtain the risk management coefficient corresponding to the sales company's unfinished orders.

[0018] As a further solution, the risk handling coefficient corresponding to the unfinished orders of the sales enterprise is specifically analyzed as follows: based on the risk handling data corresponding to the unfinished orders of the sales enterprise, where the risk handling data includes the estimated inventory days, maximum detention time and sales customer satisfaction score corresponding to each unfinished order; the inventory reference days and permitted detention time are extracted from the order risk prevention and control platform; and the risk handling coefficient corresponding to the unfinished orders of the sales enterprise is obtained by analysis.

[0019] As a further solution, risk prevention and control warnings are issued for the sales company's unfinished orders. The specific warning process is: by comparing the risk prevention and control values ​​corresponding to the sales company's unfinished orders with the risk prevention and control thresholds corresponding to the dealer's completed orders. If the risk prevention and control values ​​corresponding to the sales company's unfinished orders are lower than the risk prevention and control thresholds corresponding to the dealer's completed orders, a risk prevention and control warning is issued for the sales company's unfinished orders.

[0020] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0021] (1) The present invention provides an order risk prevention and control system based on dealer big data. First, data is collected on the dealer's completed orders, and all data in the completed orders can be fully obtained, thereby screening out the risk prevention and control thresholds corresponding to the dealer's completed orders, providing more accurate data basis for the subsequent risk prevention and control of unfinished orders; the risk management data corresponding to the sales company's unfinished orders are obtained, and the risk prevention and control values ​​corresponding to the sales company's unfinished orders are determined, and compared with the risk prevention and control thresholds corresponding to the dealer's completed orders. Finally, the sales company's unfinished orders are issued a risk prevention and control warning, which can timely discover and handle potential risk problems in the orders, further improve the order completion rate, and thus reduce the sales company's order loss behavior.

[0022] (2) The present invention collects data on the dealer's completed orders to obtain historical operation data and historical transaction data, and respectively evaluates the operation degree coefficient corresponding to the dealer's completed orders and the transaction degree coefficient corresponding to the dealer's completed orders, which can provide more accurate support for the subsequent analysis of the risk status of unfinished orders, thereby improving the risk prevention and control capabilities of orders.

[0023] (3) By collecting data on the unfinished orders of the sales company, the present invention can track and monitor the risk control status of the unfinished orders in real time, obtain production chain risk data, supply and marketing chain risk data and risk processing data, and respectively evaluate the risk management coefficient corresponding to the unfinished orders and the risk processing coefficient corresponding to the unfinished orders, so that the order management personnel can have a more comprehensive understanding of the risk processing status of the orders, providing strong support for optimizing risk management and improving risk response capabilities.

[0024] (4) The present invention compares the risk control value corresponding to the sales enterprise's unfinished orders with the risk control threshold corresponding to the dealer's completed orders, and issues risk control warnings for the sales enterprise's unfinished orders, which helps order management personnel optimize resource allocation, thereby enhancing dealer trust and satisfaction, and providing strong guarantees for the sustainable development of sales enterprises' order management. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0026] Figure 1 It is a schematic diagram of system module connection of the present invention. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] See also Figure 1 As shown, an embodiment of the present invention provides a technical solution: an order risk prevention and control system based on dealer big data, including a completed order risk management module, an uncompleted order risk prevention and control module, an order risk prevention and control early warning module and an order risk prevention and control platform.

[0029] The completed order risk management module is connected to the uncompleted order risk prevention and control module, the uncompleted order risk prevention and control module is connected to the order risk prevention and control early warning module, the order risk prevention and control platform is connected to the completed order risk management module, and the order risk prevention and control platform is connected to the uncompleted order risk prevention and control module.

[0030] The completed order risk management module is used to collect data on the dealer's completed orders, obtain historical management data corresponding to the dealer's completed orders, and evaluate the risk management value corresponding to the dealer's completed orders, thereby screening out the risk prevention and control thresholds corresponding to the dealer's completed orders.

[0031] In a specific embodiment, the present invention collects data on the dealer's completed orders to obtain historical operation data and historical transaction data, and respectively evaluates the operation degree coefficient corresponding to the dealer's completed orders and the transaction degree coefficient corresponding to the dealer's completed orders, which can provide more accurate support for the subsequent analysis of the risk status of unfinished orders, thereby improving the risk prevention and control capabilities of orders.

[0032] Specifically, the operation degree coefficient corresponding to the completed orders of the dealer, the specific analysis process is as follows:

[0033] Based on the historical management data corresponding to the dealer's completed orders, the historical management data includes historical operation data and historical transaction data.

[0034] Based on the historical operating data corresponding to the dealer's completed orders, the historical operating data includes the number of transactions, the number of successful transactions, and the total types of payments.

[0035] It should be explained that the above transaction quantity can be obtained from the sales statistics table of the order; the above successful transaction number is extracted from the order management system; the above total payment types are obtained through order transaction records.

[0036] Comprehensive analysis is performed to obtain the operating degree coefficient corresponding to the dealer's completed orders. In a specific embodiment, a neural network model can be used to analyze order-related characteristics such as order quantity, order amount, order cycle and other factors to obtain the operating degree coefficient corresponding to the dealer's completed orders.

[0037] In this embodiment, the operating degree coefficient corresponding to the completed orders of the above-mentioned dealers is obtained by comprehensively analyzing the number of transactions, the number of successful transactions, and the total types of payments to obtain the data of the operating degree corresponding to the completed orders of the dealers. The specific application algorithm is as follows:

[0038]

[0039] Wherein ε is the operation degree coefficient corresponding to the completed orders of the dealer. In this embodiment, a low success transaction rate may mean that the sales customer is not satisfied with the product or service, or encounters problems in the purchase process, which in turn affects the brand image and long-term profitability of the sales company; a high failure transaction rate may indicate that the sales company has problems in order processing, inventory management or logistics distribution, which may lead to a poor dealer experience and thus increase dealer costs; a small number of payment types may mean that the sales company lacks diversified payment methods, because some sales customers may give up purchasing because they cannot find a suitable payment method; therefore, by analyzing the numerical changes of the above-mentioned multiple factors, the degree of change of the operation degree coefficient corresponding to the completed orders of the dealer can be accurately analyzed, and finally the operation status of the dealer's completed orders can be determined, so as to achieve the effect of optimizing the operation process and improving sales customer satisfaction.

[0040] YD is the number of successful transactions corresponding to the dealer's completed orders, indicating the number of successfully traded orders in the dealer's orders.

[0041] YG is the number of transactions corresponding to the dealer's completed orders, indicating the total number of transactions that the dealer has completed and recorded.

[0042] YZ is the total payment types corresponding to the dealer's completed orders, indicating the total number of different payment methods used in all completed orders.

[0043] b1 is the correction factor corresponding to the preset success transaction rate, b2 is the impact factor corresponding to the preset failure transaction rate unit value, and b3 is the impact factor corresponding to the preset payment type unit value.

[0044] Furthermore, the transaction degree coefficient corresponding to the completed orders of the dealer is specifically analyzed as follows:

[0045] The historical transaction data corresponding to the completed orders through the dealers, where the historical transaction data includes the transaction amount, transaction duration and overdue days corresponding to each completed order.

[0046] It should be explained that the above transaction amount can be obtained from the dealer's sales records; the above transaction duration is obtained through the order management system; and the above overdue days are obtained by extracting them from the sales records.

[0047] The transaction reference amount, transaction permission duration and number of days of overdue permission are extracted from the order risk prevention and control platform.

[0048] The transaction degree coefficient corresponding to the dealer's completed orders is obtained through comprehensive analysis. In a specific embodiment, a linear regression model can be used to analyze the transaction degree coefficient corresponding to the dealer's completed orders based on the order quantity, order amount, order type, payment method, promotional activities, etc. related to the completed orders.

[0049] In this embodiment, the transaction degree coefficient corresponding to the completed orders of the above dealers is obtained by comprehensively analyzing the transaction amount, transaction time and overdue days to obtain the data of the operation degree corresponding to the completed orders of the dealers. The specific application algorithm is as follows:

[0050]

[0051] In the formula, δ represents the transaction degree coefficient corresponding to the completed orders of the dealer. In this embodiment, a low transaction amount ratio may indicate that the order is a small transaction, and a small transaction may not meet the profit requirements of the sales company; a long transaction time may indicate that the order processing process is not efficient enough, which may lead to customer dissatisfaction or loss of interest. A long transaction time may increase the cost of the order; overdue orders may indicate that the seller fails to fulfill its promise on time, which may damage the customer's trust. Overdue orders may cause customer dissatisfaction and even lead to customer loss. Overdue orders may also increase the operating costs of the sales company. Therefore, it is necessary to analyze the transaction information in the dealer's completed orders to determine the transaction status of the dealer's completed orders, so as to reduce costs and improve sales efficiency.

[0052] JE c It is the transaction amount corresponding to the dealer’s cth completed order, indicating the amount paid by the dealer to the sales enterprise for the dealer’s cth completed order.

[0053] ΔJE is the transaction reference amount, which represents the reference value specified when analyzing the successful transaction amount.

[0054] JS cIt is the transaction duration corresponding to the dealer's cth completed order, indicating the time span from the dealer's cth completed order payment to the confirmation of receipt.

[0055] ΔJS is the permitted transaction time, which indicates the maximum value specified when analyzing the successful transaction time.

[0056] JT c It is the number of overdue days corresponding to the cth completed order of the dealer, indicating that the cth completed order of the dealer exceeds the expected delivery or processing time.

[0057] ΔJT is the number of days allowed for overdue transactions, which represents the maximum value specified when analyzing the number of days for overdue transactions for successful transactions.

[0058] a1 represents the correction factor corresponding to the preset transaction amount, a2 represents the correction factor corresponding to the preset transaction duration, a3 represents the correction factor corresponding to the preset number of overdue days, c represents the number of each completed order, c=1,2,3,...,m, m represents the total number of orders completed by the dealer.

[0059] Specifically, the risk management value corresponding to the completed orders of the dealer is analyzed in the following process:

[0060] According to the operation degree coefficient corresponding to the dealer's completed orders and the transaction degree coefficient corresponding to the dealer's completed orders, a comprehensive analysis is performed to obtain the risk management value corresponding to the dealer's completed orders.

[0061] Comprehensive analysis is performed to obtain the risk management value corresponding to the dealer's completed orders. In a specific embodiment, a decision tree model can be used to obtain the risk management value corresponding to the dealer's completed orders based on information such as the order's payment record and the order's delivery performance.

[0062] In this embodiment, the risk management value corresponding to the completed orders of the above-mentioned dealers is obtained by comprehensive analysis of the operation degree coefficient corresponding to the completed orders of the dealers and the transaction degree coefficient corresponding to the completed orders of the dealers. The specific application algorithm is as follows:

[0063]

[0064] Wherein, μ is the risk management value corresponding to the dealer's completed orders. A low operation degree coefficient of the dealer may mean that the order processing process is not efficient enough and there are problems in production, procurement or logistics. A low transaction degree coefficient may reflect the low transaction activity between the sales company and the sales customer. A large risk management value corresponding to the dealer's completed orders may mean that the sales company's order management faces multiple risks. By evaluating the risk management value corresponding to the dealer's completed orders, risks can be effectively reduced and losses can be minimized.

[0065] ε is the operation degree coefficient corresponding to the completed orders of the dealer, δ is the transaction degree coefficient corresponding to the completed orders of the dealer, A1 is the predefined weight factor of the operation degree coefficient, and A2 is the predefined weight factor of the transaction degree coefficient.

[0066] Furthermore, the risk control threshold corresponding to the completed orders of the selected dealers is specifically analyzed as follows:

[0067] The risk management value corresponding to the dealer's completed orders is matched with the risk control thresholds corresponding to each risk management value interval defined in the order risk control platform, thereby screening out the risk control thresholds corresponding to the dealer's completed orders.

[0068] The unfinished order risk prevention and control module is used to obtain risk management data corresponding to the unfinished orders of the sales enterprise, and determine the risk prevention and control values ​​corresponding to the unfinished orders of the sales enterprise.

[0069] In this embodiment, the above-mentioned sales enterprise is set as a pharmaceutical enterprise. Through the risk control value corresponding to the unfinished orders of the pharmaceutical enterprise, it is possible to ensure the stable operation of the pharmaceutical enterprise, improve operational efficiency, maintain relationships with sales customers, enhance market competitiveness, promote sustainable development, and optimize resource allocation, so as to avoid the order risks of the pharmaceutical enterprise, provide strong support for the decision-making of the pharmaceutical enterprise, and complete the orders of the sales enterprise more punctually and efficiently.

[0070] In a specific embodiment, the present invention collects data on unfinished orders of sales companies to track and monitor the risk management status of unfinished orders in real time, obtains production chain risk data, distribution chain risk data and risk processing data, and respectively evaluates the risk management coefficient corresponding to the unfinished orders and the risk processing coefficient corresponding to the unfinished orders, so that order managers can have a more comprehensive understanding of the risk processing status of the orders, providing strong support for optimizing risk management and improving risk response capabilities.

[0071] Specifically, the risk management coefficient corresponding to the unfinished orders of the sales enterprise is analyzed in the following process:

[0072] Based on the risk management data corresponding to the unfinished orders of the sales company, the risk management data includes production chain risk data, distribution chain risk data and risk processing data.

[0073] The production chain risk data corresponding to the unfinished orders of the sales enterprise, where the production chain risk chain data includes production quantity and production cost.

[0074] It should be explained that the above production quantity and production cost are obtained from the production schedule.

[0075] Extract production reference quantity and production license cost from the order risk prevention and control platform.

[0076] The production quantity and production cost of the sales company's unfinished orders are combined with the production reference quantity and production license cost extracted from the order risk prevention and control platform for a comprehensive analysis to ultimately obtain the production chain management coefficient of the sales company's unfinished orders. In a specific embodiment, a key performance indicator model can be used to conduct a comprehensive analysis based on the completion rate and time of order production to ultimately obtain the production chain management coefficient of the sales company's unfinished orders.

[0077] In this embodiment, the production chain management coefficient of the unfinished orders of the above-mentioned sales enterprise is obtained by comprehensively analyzing the production quantity and production cost of the unfinished orders of the sales enterprise, and the production reference quantity and production license cost extracted from the order risk prevention and control platform. The specific application algorithm is as follows:

[0078]

[0079] Where β is the production chain management coefficient of the sales company's unfinished orders. A large number of unfinished orders may result in dealers not receiving the required products on time, causing dissatisfaction and complaints from dealers, and reducing dealer satisfaction. A high production cost of unfinished orders may lead to poor capital circulation in the sales company, increasing the financial pressure and operational risks of the sales company. Therefore, through the data analysis of the production chain management coefficient of the sales company's unfinished orders, it is possible to avoid delays in order production and increased costs, thereby improving the sales company's order completion rate and dealer satisfaction.

[0080] sm is the production quantity of the sales company's unfulfilled orders, which refers to the total number of orders required to produce the orders.

[0081] Δsm is the production reference quantity, which refers to the maximum production quantity allowed for the order.

[0082] st is the production cost, which refers to the actual cost required to produce the order.

[0083] Δst is the production allowable cost, which refers to the maximum production cost allowed for a production order.

[0084] f1 is the preset production quantity correction factor, and f2 is the preset production cost correction factor.

[0085] The distribution chain risk data corresponding to the unfinished orders of the sales enterprise, wherein the distribution chain risk data includes the total credit limit of the sales customers, the total credit account period of the sales customers and the total days in transit of the sales customers.

[0086] It should be explained that the above-mentioned total credit limit of sales customers can be obtained from the credit assessment of sales customers; the above-mentioned total credit account period of sales customers is obtained from the credit agreement and contract; and the above-mentioned total number of days in transit of sales customers is obtained from the logistics information system.

[0087] Extract the sales customer's credit limit, sales customer's credit period, and sales customer's in-transit days from the order risk prevention and control platform; finally, analyze and obtain the distribution chain management coefficient corresponding to the sales company's unfinished orders;

[0088] The final analysis obtains the distribution chain management coefficient corresponding to the sales company's unfinished orders. In a specific implementation, the prediction algorithm can be used to analyze the order-related logistics data and dealer information to obtain the corresponding distribution chain risk data, and the distribution chain management coefficient can be obtained through comprehensive analysis.

[0089] In this embodiment, the distribution chain risk data corresponding to the unfinished orders of the above-mentioned sales enterprise is obtained by comprehensively analyzing and processing the total credit limit of the sales customer, the total credit period of the sales customer, and the total days in transit of the sales customer to obtain the distribution chain management coefficient corresponding to the unfinished orders of the sales enterprise. The specific application algorithm is as follows:

[0090]

[0091] In the formula, θ is the distribution chain management coefficient corresponding to the sales company's unfinished orders. A low credit limit means that the sales customer may have used a large part of the credit limit, which may slow down the sales company's capital recovery and thus affect the liquidity of the entire supply chain. When the sales customer's credit period utilization rate is low, the sales company may increase inventory to ensure the continuity of supply, which will increase inventory costs and backlog risks. The increase in days in transit may affect the delivery efficiency of the supply chain, because the delivery time from the sales company to the sales customer becomes longer, which may affect the overall performance of the supply chain and the sales customer's satisfaction. Therefore, the numerical abnormalities of the above-mentioned multiple factors will make the supply chain management coefficient corresponding to the sales company's unfinished orders larger. By evaluating the various data of the sales company's unfinished orders, the effect of optimizing inventory management and improving cash flow can be achieved.

[0092] LE is the total credit limit of the sales customers corresponding to the sales company's unfinished orders, indicating the maximum amount of accounts receivable that the sales company allows the sales customers to have unpaid within a certain period of time. It is usually obtained by summing the sales customer's credit limit and the temporary credit limit for the period corresponding to the order document date.

[0093] ΔLE is the sales customer credit limit, which indicates the limit on the amount granted by the sales enterprise based on the sales customer's credit status.

[0094] LZ is the total credit period of the sales customer corresponding to the sales enterprise's unfinished orders, indicating the maximum period of time that the sales customer is allowed to delay payment for the goods or services corresponding to its unfinished orders. It is usually obtained by summing the sales customer's credit period with the temporary credit bill for the period corresponding to the order document date.

[0095] ΔLZ is the sales customer's credit permission period, which means the period during which the sales enterprise allows the sales customer to delay payment of the goods within the specified time.

[0096] ΔLT is the number of days in transit permitted by the sales customer, indicating the time limit allowed by the sales customer for an order to be in transit.

[0097] LT is the total number of days in transit for sales customers corresponding to the sales company's unfinished orders, which is the sum of the transportation transit time of all unfinished orders. The total number of days in transit for sales customers is obtained by summing up the number of days in transit for general sales customers and the temporary number of days in transit during the period corresponding to the order document date.

[0098] e is a natural constant, h1 is the correction factor for the predefined total credit limit of the sales customer, h2 is the correction factor for the predefined total credit period of the sales customer, and h3 is the correction factor for the predefined total days in transit of the sales customer.

[0099] The production chain management coefficient of the sales company's unfinished orders and the distribution chain management coefficient corresponding to the sales company's unfinished orders are finally obtained through the weighted average method to obtain the risk management coefficient corresponding to the sales company's unfinished orders. The specific analysis process is as follows:

[0100]

[0101] In the formula, φ is the risk management coefficient corresponding to the unfinished orders of the sales enterprise. A low production chain management coefficient may mean inefficiency in the production process, which will lead to longer order processing time, thereby increasing the number of unfinished orders and increasing production costs. A low distribution chain management coefficient may cause logistics delays, making it impossible for products to be delivered to dealers in time. A low distribution chain management coefficient may also lead to unstable cooperation between the enterprise and dealers. Therefore, it is necessary to analyze the various coefficients of the risk management coefficient corresponding to the unfinished orders of the sales enterprise to improve the production completion rate of the sales enterprise. By regularly monitoring and evaluating these coefficients, the sales enterprise can promptly discover potential risks and take measures to intervene and formulate corresponding measurements, so as to avoid the expansion of risks or their conversion into actual losses.

[0102] β is the production chain management coefficient of the sales enterprise's unfinished orders, θ is the distribution chain management coefficient corresponding to the sales enterprise's unfinished orders, s1 is the weight factor corresponding to the production chain management coefficient of the sales enterprise's unfinished orders, and s2 is the weight factor of the distribution chain management coefficient corresponding to the sales enterprise's unfinished orders.

[0103] Furthermore, the risk handling coefficient corresponding to the unfinished orders of the sales enterprise is specifically analyzed as follows:

[0104] Based on the risk management data corresponding to the unfinished orders of the sales company, the risk management data includes the estimated inventory days, maximum retention time and sales customer satisfaction score corresponding to each unfinished order.

[0105] In this embodiment, the estimated inventory days can be obtained from the inventory record and management system; the maximum retention time can be obtained from the supply chain agreement and contract; and the sales customer satisfaction score can be obtained from the sales customer feedback survey.

[0106] Extract inventory reference days and permitted detention time from the order risk prevention and control platform.

[0107] This analysis can be used to obtain the risk management coefficient corresponding to the sales company's unfinished orders. In a specific example, the random forest model can be used to analyze the order delivery records and product information to obtain the risk management data corresponding to the dealer's completed orders.

[0108] In this embodiment, the risk handling coefficient corresponding to the unfinished orders of the above-mentioned sales enterprise is obtained by comprehensively analyzing the expected inventory days, the maximum retention time and the sales customer satisfaction score. The specific application algorithm is as follows:

[0109]

[0110] Wherein, τ is the risk handling coefficient corresponding to the unfinished orders of the sales enterprise. In this embodiment, high inventory days means long inventory retention time, which will lead to increased inventory holding costs; high order retention means that the retention time of the order exceeds the expected retention allowance time, which will lead to slower order delivery; low sales customer satisfaction usually means that the sales customer is not loyal to the brand or product, which may lead to the loss of sales customers and increase the cost and difficulty of acquiring new sales customers.

[0111] FT d It is the estimated inventory days corresponding to the dth uncompleted order of the sales enterprise, indicating the number of days that the inventory can support the uncompleted orders.

[0112] ΔFT is the reference inventory days, which means that the estimated inventory days corresponding to the analysis of uncompleted orders is the prescribed reference value.

[0113] FC d The maximum retention time corresponding to the dth unfinished order of the sales enterprise is the longest time from the date when the order is generated or confirmed to the date when the order is fully processed.

[0114] ΔFC is the allowed detention time, which indicates the maximum time that an order or transaction remains in the system or is not completed.

[0115] FN d It is the sales customer satisfaction score corresponding to the dth uncompleted order of the sales enterprise, indicating the sales customer's satisfaction with the product, service or enterprise.

[0116] r1 is the correction factor corresponding to the preset expected inventory days, r2 is the correction factor corresponding to the preset maximum retention time, r3 is the influencing factor of the preset sales customer satisfaction score unit value, d is the number of each unfinished order, d = 1, 2, 3, ..., p, p is the total number of unfinished orders of the sales enterprise.

[0117] Specifically, the risk control value corresponding to the unfinished orders of the sales company in question is analyzed as follows:

[0118] Based on the supply chain management coefficient corresponding to the sales company's unfinished orders and the risk handling coefficient corresponding to the sales company's unfinished orders, a comprehensive analysis is conducted to obtain the risk prevention and control value corresponding to the sales company's unfinished orders.

[0119] In a specific embodiment, a neural network algorithm can be used to analyze the inventory situation of the sales company and the sales customer demand forecast to obtain the risk prevention and control value corresponding to the sales company's unfinished orders.

[0120] In this embodiment, the risk control value corresponding to the unfinished orders of the above-mentioned sales enterprise is obtained by comprehensively analyzing the supply chain management coefficient corresponding to the unfinished orders of the sales enterprise and the risk handling coefficient corresponding to the unfinished orders of the sales enterprise. The specific algorithm is as follows:

[0121]

[0122] In the formula, α is the risk prevention and control value corresponding to the unfinished orders of the sales enterprise. In this embodiment, a low risk management coefficient may mean that the sales enterprise cannot respond to order demands in a timely manner and cannot handle problems in the supply chain in a timely manner, resulting in an increased risk of order retention and delays; a low risk handling coefficient may reflect that the sales enterprise has difficulties in handling risks in the supply chain, which may lead to supply chain instability; by evaluating various data corresponding to the unfinished orders of the sales enterprise, the numerical value of the risk prevention and control value corresponding to the unfinished orders of the sales enterprise can be obtained in real time, and the difficulty of the sales enterprise in order prevention and control can be further understood. Ultimately, it can achieve the effect of optimizing production chain management and distribution chain management, improving order processing efficiency, and reducing the risk of order retention and delays.

[0123] φ is the risk management coefficient corresponding to the unfinished orders of the sales enterprise, τ is the risk handling coefficient corresponding to the unfinished orders of the sales enterprise, B1 is the predefined weight factor of the risk management coefficient corresponding to the unfinished orders of the sales enterprise, and B2 is the predefined weight factor of the risk handling coefficient corresponding to the unfinished orders of the sales enterprise.

[0124] The order risk prevention and control early warning module is used to compare the risk prevention and control value corresponding to the unfinished orders of the sales enterprise with the risk prevention and control threshold value corresponding to the completed orders of the dealer, and finally issue a risk prevention and control early warning for the unfinished orders of the sales enterprise.

[0125] Specifically, the risk prevention and control early warning for the uncompleted orders of the sales enterprise is carried out, and the specific early warning process is as follows:

[0126] By comparing the risk control value corresponding to the sales company's unfinished orders with the risk control threshold corresponding to the dealer's completed orders, if the risk control value corresponding to the sales company's unfinished orders is lower than the risk control threshold corresponding to the dealer's completed orders, a risk control warning will be issued for the sales company's unfinished orders.

[0127] In a specific embodiment, the present invention compares the risk control value corresponding to the sales company's unfinished orders with the risk control threshold corresponding to the dealer's completed orders, and issues risk control warnings for the sales company's unfinished orders, which helps order management personnel optimize resource allocation, thereby enhancing dealer trust and satisfaction, and providing strong guarantees for the sustainable development of sales companies' order management.

[0128] In this embodiment, the risk prevention and control early warning is performed on the uncompleted orders of the sales enterprise. The specific early warning process is as follows:

[0129] Collect the sales company's unfinished order data, integrate relevant information of sales customers, build order risk prevention and control warnings according to business needs, set reasonable thresholds for each order risk prevention and control warning indicator, and conduct risk analysis and assessment on the sales company's unfinished orders. When the risk indicator of the sales company's unfinished orders exceeds the set threshold, the warning system should automatically trigger a warning, and order management personnel should quickly handle the risk, track the results of the handling, ensure that the risk is effectively controlled, and record and provide feedback on the handling process, continuously optimize and adjust the warning model, continuously improve the risk indicator system and threshold setting, and improve the accuracy and effectiveness of the warning.

[0130] The order risk prevention and control platform is used to store transaction reference amount, transaction permission duration, overdue permission days, inventory reference days, detention permission duration, sales customer credit permission limit, sales customer credit permission account period, sales customer in-transit permission days, production reference quantity, production permission cost, and risk prevention and control thresholds corresponding to each risk management value interval.

[0131] In a specific embodiment, the present invention provides an order risk prevention and control system based on dealer big data. First, data collection is performed on the dealer's completed orders, and various data in the completed orders can be fully obtained, thereby screening out the risk prevention and control thresholds corresponding to the dealer's completed orders, providing more accurate data basis for subsequent risk prevention and control of unfinished orders; the risk management data corresponding to the sales company's unfinished orders are obtained, and the risk prevention and control values ​​corresponding to the sales company's unfinished orders are determined, and compared with the risk prevention and control thresholds corresponding to the dealer's completed orders. Finally, risk prevention and control warnings are issued for the sales company's unfinished orders, which can timely discover and handle potential risk issues in orders, further improve the success rate of order completion, and thereby reduce the sales company's order loss behavior.

[0132] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. The order risk prevention and control system based on dealer big data is characterized by: include: The completed order risk management module is used to collect data on the completed orders of dealers, obtain historical management data corresponding to the completed orders of dealers, and evaluate the risk management values ​​corresponding to the completed orders of dealers, thereby screening out the risk prevention and control thresholds corresponding to the completed orders of dealers; The unfinished order risk control module is used to obtain the risk management data corresponding to the unfinished orders of the sales enterprise and determine the risk control value corresponding to the unfinished orders of the sales enterprise; The order risk prevention and control early warning module is used to compare the risk prevention and control value corresponding to the unfinished orders of the sales enterprise with the risk prevention and control threshold corresponding to the completed orders of the dealer, and finally issue a risk prevention and control early warning for the unfinished orders of the sales enterprise; The order risk prevention and control platform is used to store transaction reference amount, transaction permission duration, overdue permission days, sales customer credit permission limit, sales customer credit permission account period, sales customer in-transit permission days, production reference quantity, production permission cost, inventory reference days, detention permission duration, and risk prevention and control thresholds corresponding to each risk management value interval.

2. The order risk prevention and control system based on dealer big data according to claim 1 is characterized by: The risk management value corresponding to the completed orders of the dealer is analyzed by the following formula: In the formula, μ is the risk management value corresponding to the dealer's completed orders, ε is the operation degree coefficient corresponding to the dealer's completed orders, δ is the transaction degree coefficient corresponding to the dealer's completed orders, A1 is the predefined weight factor of the operation degree coefficient, and A2 is the predefined weight factor of the transaction degree coefficient.

3. The order risk prevention and control system based on dealer big data according to claim 2 is characterized by: The operational degree coefficient corresponding to the completed orders of the dealer, the specific analysis process is as follows: Based on the historical management data corresponding to the completed orders of the dealers, the historical management data includes historical operation data and historical transaction data; Based on the historical operation data corresponding to the dealer's completed orders, the historical operation data includes the number of transactions, the number of successful transactions, and the total types of payments; Comprehensive analysis is performed to obtain the operational degree coefficient corresponding to the dealer's completed orders.

4. The order risk prevention and control system based on dealer big data according to claim 2 is characterized by: The transaction degree coefficient corresponding to the completed orders of the dealer, the specific analysis process is as follows: The historical transaction data corresponding to the completed orders through the dealers, where the historical transaction data includes the transaction amount, transaction duration and overdue days corresponding to each completed order; The transaction reference amount, transaction permission duration and number of overdue permission days are extracted from the order risk prevention and control platform; the transaction degree coefficient corresponding to the dealer's completed orders is analyzed.

5. The order risk prevention and control system based on dealer big data according to claim 1 is characterized by: The risk control threshold corresponding to the completed orders of the selected dealers is analyzed in the following specific process: The risk management value corresponding to the dealer's completed orders is matched with the risk control thresholds corresponding to each risk management value interval defined in the order risk control platform, thereby screening out the risk control thresholds corresponding to the dealer's completed orders.

6. The order risk prevention and control system based on dealer big data according to claim 2 is characterized by: The risk control value corresponding to the unfinished orders of the sales enterprise is calculated as follows: In the formula, α is the risk prevention and control value corresponding to the unfinished orders of the sales enterprise, φ is the risk management coefficient corresponding to the unfinished orders of the sales enterprise, τ is the risk handling coefficient corresponding to the unfinished orders of the sales enterprise, B1 is the predefined weight factor of the risk management coefficient corresponding to the unfinished orders of the sales enterprise, and B2 is the predefined weight factor of the risk handling coefficient corresponding to the unfinished orders of the sales enterprise.

7. The order risk prevention and control system based on dealer big data according to claim 6 is characterized by: The risk management coefficient corresponding to the unfinished orders of the sales enterprise is analyzed in the following specific process: Based on the risk management data corresponding to the uncompleted orders of the sales enterprise, the risk management data includes production chain risk data, distribution chain risk data and risk processing data; Through the production chain risk data corresponding to the unfinished orders of the sales enterprise, the production chain risk data includes production quantity and production cost; Extract production reference quantity and production license cost from the order risk prevention and control platform; Comprehensively analyze the production quantity and production cost of the sales company's unfinished orders with the production reference quantity and production license cost extracted from the order risk prevention and control platform to finally obtain the production chain management coefficient of the sales company's unfinished orders; The distribution chain risk data corresponding to the uncompleted orders of the sales enterprise, where the distribution chain risk data includes the total credit limit of the sales customers, the total credit period of the sales customers, and the total days in transit of the sales customers; Extract the sales customer's credit limit, sales customer's credit period, and sales customer's in-transit days from the order risk prevention and control platform; finally, analyze and obtain the distribution chain management coefficient corresponding to the sales company's unfinished orders; The production chain management coefficient of the sales company's unfinished orders and the distribution chain management coefficient corresponding to the sales company's unfinished orders are added together through the weighted average method to finally obtain the risk management coefficient corresponding to the sales company's unfinished orders.

8. The order risk prevention and control system based on dealer big data according to claim 6 is characterized by: The risk handling coefficient corresponding to the unfinished orders of the sales enterprise is analyzed in the following specific process: Risk processing data corresponding to the uncompleted orders of the sales enterprise, including the estimated inventory days, maximum retention time and sales customer satisfaction score corresponding to each uncompleted order; Extract the inventory reference days and permitted detention time from the order risk prevention and control platform; This analysis yields the risk management coefficient corresponding to the sales company’s unfinished orders.

9. The order risk prevention and control system based on dealer big data according to claim 1 is characterized by: The risk prevention and control early warning for the unfinished orders of the sales enterprise is carried out, and the specific early warning process is as follows: By comparing the risk control value corresponding to the sales company's unfinished orders with the risk control threshold corresponding to the dealer's completed orders, if the risk control value corresponding to the sales company's unfinished orders is lower than the risk control threshold corresponding to the dealer's completed orders, a risk control warning will be issued for the sales company's unfinished orders.

Images