Supply chain financial risk monitoring and intelligent early warning system and storage medium

Abstract

The invention discloses a supply chain financial risk monitoring and intelligent early warning system and a storage medium. The supply chain financial risk monitoring and intelligent early warning system comprises an information acquisition module, a data processing module and an intelligent early warning module, relates to the technical field of supply chain finance, and solves the technical problem of low accuracy of monitoring and early warning of supply chain finance risks in the prior art. According to the invention, the customer quality score of each enterprise in the supply chain is calculated based on the customer composition information; calculating the performance reputation score of each enterprise in the supply chain based on the historical performance information; calculating a financing risk score of each enterprise in the supply chain based on the customer quality score and the performance reputation score; and performing early warning on the supply chain financial risk based on the financing risk score prediction value. According to the invention, the customer quality score and the performance reputation score are substituted into a formula to calculate the financing risk score, so that the financing risk score can reflect the financial risk of each enterprise in the supply chain more comprehensively, and the accuracy of monitoring and early warning of the financial risk of the supply chain is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of supply chain finance, and specifically relates to a supply chain finance risk monitoring and intelligent early warning system and a storage medium. Background Art

[0002] In the context of the globalized economy, supply chain finance, as a bridge connecting suppliers, manufacturers, distributors, and end-users, its stability and security are crucial for the operation of the entire economic system. However, with the increasing complexity of supply chain finance operations, risks have also increased. To address this challenge, the present invention proposes a supply chain finance risk monitoring and intelligent early warning system, aiming to achieve precise identification and early warning of risks through technical means.

[0003] The prior art monitors and warns supply chain finance risks by obtaining the historical performance information of supply chain enterprises and based on the past performance of the enterprises. However, in the actual production and operation of the supply chain, the customer quality of each enterprise is different, and the customer quality of an enterprise can to a certain extent reflect the solvency of the enterprise. The prior art is difficult to conduct financial risk assessment based on the customer composition of supply chain enterprises, resulting in low accuracy in monitoring and warning supply chain finance risks.

[0004] The present invention proposes a supply chain finance risk monitoring and intelligent early warning system and a storage medium to solve the above technical problems. Summary of the Invention

[0005] The present invention aims to at least solve one of the technical problems existing in the prior art; for this purpose, the present invention proposes a supply chain finance risk monitoring and intelligent early warning system, which is used to solve the technical problem that in the actual production and operation of the supply chain, the customer quality of each enterprise is different, and the customer quality of an enterprise can to a certain extent reflect the solvency of the enterprise, and the prior art is difficult to conduct financial risk assessment based on the customer composition of supply chain enterprises, resulting in low accuracy in monitoring and warning supply chain finance risks.

[0006] To achieve the above object, the first aspect of the present invention provides a supply chain finance risk monitoring and intelligent early warning system, including: a data processing module, and an information collection module and an intelligent early warning module connected thereto;

[0007] The information collection module: is used to collect the historical performance information and customer composition information of each enterprise in the supply chain;

[0008] The data processing module: is used to calculate the customer quality score of each enterprise in the supply chain based on the customer composition information; calculate the performance credit score of each enterprise in the supply chain based on the historical performance information; calculate the financing risk score of each enterprise in the supply chain based on the customer quality score and the performance credit score;

[0009] The intelligent early warning module: used to input the financing risk score into the financing risk prediction model to obtain the predicted value of the financing risk score; based on the predicted value of the financing risk score, early warning of supply chain financial risks is carried out; among them, the financing risk prediction model is constructed based on an artificial intelligence model.

[0010] Preferably, the supply chain financial risk monitoring and intelligent early warning system further includes a data transmission module, and the data transmission module is used for data communication between the information collection module, the data processing module and the intelligent early warning module.

[0011] Preferably, calculating the customer quality score of each enterprise in the supply chain based on the customer composition information includes:

[0012] Extracting the customer composition information of each enterprise in the supply chain; among them, the customer composition information includes the number of large customers and the number of stable customers;

[0013] Calculating the customer quality score KZXi of enterprise i through the formula KZXi = a×DKSi + b×WKSi; where DKSi is the number of large customers of enterprise i, and WKSi is the number of stable customers of enterprise i; a and b are both weight coefficients greater than 0, and a + b = 1; i = 1, 2,..., n, and n is the total number of enterprises in the supply chain.

[0014] Preferably, the number of large customers is obtained in the following way:

[0015] Extracting the historical customer cooperation data of each enterprise in the supply chain; among them, the historical customer cooperation data includes the cooperation amount and the number of cooperation times;

[0016] Judging whether the cooperation amount or the number of cooperation times is greater than the corresponding preset threshold; if so, marking the customer scale label of the corresponding customer as 1; if not, marking the customer scale label of the corresponding customer as 0;

[0017] Marking the total number of customers with a customer scale label value of 1 as the number of large customers.

[0018] Preferably, the number of stable customers is obtained in the following way:

[0019] Extracting the number of cooperation times between each enterprise in the supply chain and the corresponding customers within several consecutive periods; fitting the number of customer cooperation times of each enterprise in the supply chain within several consecutive periods to obtain the cooperation times change curve fi(t); taking the derivative of the cooperation times change curve fi(t) to obtain the cooperation times change derivative function; extracting the maximum value of the cooperation times change derivative function and marking it as the cooperation times change characteristic value;

[0020] Determine whether the change characteristic value of the cooperation times is less than the preset times change threshold; if yes, set the stability label of the corresponding customer to 1; if no, set the stability label of the corresponding customer to 0;

[0021] Mark the total number of customers with a stability label value of 1 as the number of stable customers.

[0022] Preferably, calculating the performance credit score of each enterprise in the supply chain based on historical performance information includes:

[0023] Extract the historical performance information of each enterprise in the supply chain; among them, the historical performance information includes the number of repayment defaults, the repayment delay duration, and the delivery on-time rate;

[0024] Through the formula Calculate the performance credit score LXPi of each enterprise in the supply chain; where WYSi is the number of repayment defaults of enterprise i, HYS i is the repayment delay duration of enterprise i, JFLi is the delivery on-time rate of enterprise i; c, d, and f are all proportionality coefficients greater than 0; e is the natural constant.

[0025] It should be noted that the specific values of the proportionality coefficients c and d are related to the loan amount of the enterprise. When the loan amount of the enterprise is larger, the specific values of the proportionality coefficients c and d are set correspondingly larger; the value of the proportionality coefficient f is related to the value of the products produced and sold by the enterprise. When the value of the products produced and sold by the enterprise is higher, the specific value of the proportionality coefficient f is set correspondingly larger.

[0026] Preferably, calculating the financing risk score of each enterprise in the supply chain based on the customer quality score and the performance credit score includes:

[0027] Extract the customer quality score KZXi and the performance credit score LXPi of each enterprise in the supply chain; through the formula Calculate the financing risk score RFPi of enterprise i; where α and β are both proportionality coefficients greater than 0.

[0028] Preferably, the financing risk prediction model is constructed based on an artificial intelligence model, including:

[0029] Extract the financing risk scores of each enterprise in several consecutive periods and integrate them into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a financing risk prediction model with the input being the carbon financing risk scores of each enterprise in the most recent several consecutive periods and the output being the financing risk scores of each enterprise in the prediction period; where the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0030] Preferably, the early warning of supply chain finance risks based on the predicted value of financing risk scores includes:

[0031] Extract the predicted values of the financing risk scores of each enterprise in the supply chain and set the risk score threshold;

[0032] Determine whether the predicted value of the financing risk score is greater than the preset risk threshold; if yes, save the number of the corresponding enterprise to the enterprise risk control early warning sequence; if no, continue to monitor the supply chain finance risks;

[0033] Sort the numbers of the enterprises in the enterprise risk control early warning sequence in descending order according to the financing risk scores to obtain the early warning priority sequence;

[0034] Successively extract the number corresponding to the enterprise with the highest financing risk score from the early warning priority sequence and generate the financial risk early warning information of the corresponding enterprise.

[0035] The second aspect of the present invention provides a storage medium, which includes a stored program. When the program runs, it controls the device where the storage medium is located to execute the method in the above-mentioned supply chain finance risk monitoring and intelligent early warning system.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] 1. By comprehensively evaluating the customer quality and performance credit of each enterprise in the supply chain, accurately calculating the financing risk score, and using the prediction model for risk early warning, the present invention effectively improves the accuracy and timeliness of supply chain finance risk identification. This method can timely discover potential risk points, provide a scientific basis for decision-makers, and thus is conducive to improving the stability of supply chain finance and promoting the healthy development of the overall supply chain.

[0038] 2. The present invention comprehensively considers the influence of the customer quality score and the performance credit score on the financing risk of enterprises, multiplies the customer quality score and the performance credit score by the corresponding proportionality coefficients and calculates the financing risk score through a formula, so that the calculated financing risk score can more comprehensively reflect the financial risks of each enterprise in the supply chain, and thus is conducive to improving the accuracy of monitoring and early warning of supply chain finance risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0040] Figure 1This is the overall flowchart of the supply chain finance risk monitoring and intelligent early warning system of the present invention;

[0041] Figure 2 This is the system schematic diagram of the supply chain finance risk monitoring and intelligent early warning system of the present invention. Specific embodiments

[0042] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the embodiments. Obviously, the described embodiments are only a 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 those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0043] Please refer to Figure 1 - Figure 2 , an embodiment of the first aspect of the present invention provides a supply chain finance risk monitoring and intelligent early warning system, including: a data processing module, and an information collection module and an intelligent early warning module connected thereto;

[0044] Information collection module: used to collect the historical performance information and customer composition information of each enterprise in the supply chain;

[0045] Data processing module: used to calculate the customer quality score of each enterprise in the supply chain based on the customer composition information; calculate the performance credit score of each enterprise in the supply chain based on the historical performance information; calculate the financing risk score of each enterprise in the supply chain based on the customer quality score and the performance credit score;

[0046] Intelligent early warning module: used to input the financing risk score into the financing risk prediction model to obtain the predicted value of the financing risk score; give an early warning of the supply chain finance risk based on the predicted value of the financing risk score; wherein, the financing risk prediction model is constructed based on an artificial intelligence model.

[0047] In this embodiment, a supply chain finance risk monitoring and intelligent early warning system further includes a data transmission module, and the data transmission module is used for data communication between the information collection module, the data processing module and the intelligent early warning module.

[0048] In this embodiment, calculating the customer quality score of each enterprise in the supply chain based on the customer composition information includes:

[0049] Extracting the customer composition information of each enterprise in the supply chain; wherein, the customer composition information includes the number of large customers and the number of stable customers;

[0050] Calculate the customer quality score KZXi of enterprise i through the formula KZXi = a × DKSi + b × WKSi; where DKSi is the number of large customers of enterprise i, and WKSi is the number of stable customers of enterprise i; both a and b are weight coefficients greater than 0, and a + b = 1; i = 1, 2,..., n, where n is the total number of enterprises in the supply chain.

[0051] The present invention respectively obtains the customer composition information of each enterprise in the supply chain, multiplies the number of large customers and the number of stable customers in the customer composition information by the corresponding weight coefficients to calculate the customer quality score, so that the calculated customer quality score can comprehensively reflect the impact of the customer composition of each enterprise in the supply chain on the customer quality, thereby making the subsequent financing risk score calculated based on the customer quality score more accurate, which is beneficial to improving the accuracy of monitoring and early warning of supply chain financial risks.

[0052] Exemplarily, set the weight coefficients a = 0.3 and b = 0.7; the number of large customers DKS1 of enterprise 1 is 2, and the number of stable customers WKS1 of enterprise 1 is 3; the customer quality score KZX1 of enterprise 1 is calculated to be 2.7 through the formula.

[0053] In this embodiment, the number of large customers is obtained in the following manner:

[0054] Extract the historical customer cooperation data of each enterprise in the supply chain; where the historical customer cooperation data includes the cooperation amount and the number of cooperation times;

[0055] Judge whether the cooperation amount or the number of cooperation times is greater than the corresponding preset threshold; if so, mark the customer scale label of the corresponding customer as 1; if not, mark the customer scale label of the corresponding customer as 0;

[0056] Mark the total number of customers with the customer scale label value of 1 as the number of large customers.

[0057] Exemplarily, it is set that enterprise 1 in the supply chain has three customers, namely customer 1, customer 2, and customer 3; the preset threshold corresponding to the cooperation amount is set to 1 million yuan, and the preset threshold corresponding to the number of cooperation times is set to 3 times;

[0058] Set the cooperation amount between enterprise 1 and customer 1 to 1.5 million yuan and the number of cooperation times to 2 times; the cooperation amount between enterprise 1 and customer 2 to 1 million yuan and the number of cooperation times to 5 times; the cooperation amount between enterprise 1 and customer 3 to 600,000 yuan and the number of cooperation times to 1 time;

[0059] Since the cooperation amount between Enterprise 1 and Customer 1 is greater than the corresponding preset threshold, the customer scale label of Customer 1 is marked as 1; since the number of cooperation times between Enterprise 1 and Customer 2 is greater than the corresponding preset threshold, the customer scale label of Customer 2 is marked as 1; since both the cooperation amount and the number of cooperation times between Enterprise 1 and Customer 3 are less than the corresponding preset thresholds, the customer scale label of Customer 3 is marked as 0; the total number of customers with the customer scale label value of 1 is marked as the number of large customers, that is, the number of large customers DKS1 of Enterprise 1 = 2.

[0060] In this embodiment, the number of stable customers is obtained in the following way:

[0061] Extract the number of cooperation times between each enterprise in the supply chain and the corresponding customers within several consecutive periods; fit the number of customer cooperation times of each enterprise in the supply chain within several consecutive periods to obtain the cooperation times change curve fi(t); take the derivative of the cooperation times change curve fi(t) to obtain the cooperation times change derivative function; extract the maximum value of the cooperation times change derivative function and mark it as the cooperation times change characteristic value;

[0062] Judge whether the cooperation times change characteristic value is less than the preset number change threshold; if yes, set the stability label of the corresponding customer to 1; if not, set the stability label of the corresponding customer to 0;

[0063] Mark the total number of customers with the stability label value of 1 as the number of stable customers.

[0064] In the present invention, by fitting the number of customer cooperation times of each enterprise within several consecutive periods, a cooperation times change curve is obtained, and after taking the derivative of the number change curve, a cooperation times change characteristic value is obtained; the total number of customers with the cooperation times change characteristic value less than the preset number change threshold is used as the number of stable customers, so that the number of stable customers can more accurately reflect the production and sales stability degree of each enterprise in the supply chain, which is convenient for calculating the customer quality score of each enterprise according to the number of stable customers subsequently, and thus is beneficial to improving the accuracy of monitoring and early warning of supply chain financial risks.

[0065] Exemplarily, set the cooperation times change characteristic value between Enterprise 1 and Customer 2 to 2, and the preset number change threshold to 3 times; since the cooperation times change characteristic value between Enterprise 1 and Customer 2 is less than the preset number change threshold, the stability label of Customer 2 is set to 1; assuming that the total number of customers with the stability label value of 1 is 3, then the number of stable customers WKS1 of Enterprise 1 = 3.

[0066] In this embodiment, calculating the performance credit score of each enterprise in the supply chain based on historical performance information includes:

[0067] Extract the historical performance information of each enterprise in the supply chain; among them, the historical performance information includes the number of repayment defaults, the duration of repayment extension, and the delivery on-time rate.

[0068] Through the formula Calculate the performance credit score LXPi of each enterprise in the supply chain; where WYSi is the number of repayment defaults of enterprise i, HYSi is the duration of repayment extension of enterprise i, and JFLi is the delivery on-time rate of enterprise i; c, d, and f are all proportionality coefficients greater than 0, and the specific values of c, d, and f are set by experts in relevant fields according to experience; e is the natural constant.

[0069] It should be noted that the specific values of the proportionality coefficients c and d are related to the loan amount of the enterprise. When the loan amount of the enterprise is larger, the specific values of the proportionality coefficients c and d are set correspondingly larger; the value of the proportionality coefficient f is related to the value of the products produced and sold by the enterprise. When the value of the products produced and sold by the enterprise is higher, the specific value of the proportionality coefficient f is set correspondingly larger.

[0070] The present invention obtains the historical performance information of each enterprise in the supply chain and substitutes the historical performance information into a specific formula to calculate the performance credit score, comprehensively considering the impact of the number of repayment defaults, the duration of repayment extension, and the delivery on-time rate on the performance credit, so that the subsequent financing risk score calculated according to the customer quality score is more accurate, and thus it is beneficial to improve the accuracy of monitoring and early warning of supply chain financial risks.

[0071] Exemplarily, set the proportionality coefficients c = 4, d = 2.5, f = 3; the number of repayment defaults WYS1 of enterprise 1 = 3, the duration of repayment extension HYS1 of enterprise 1 = 20 days, and the delivery on-time rate JFS1 of enterprise 1 = 95%; the performance credit score LXP1 of enterprise 1 is calculated to be approximately 7.86 through the formula.

[0072] In this embodiment, calculating the financing risk score of each enterprise in the supply chain based on the customer quality score and the performance credit score includes:

[0073] Extract the customer quality score KZXi and the performance credit score LXPi of each enterprise in the supply chain; through the formula Calculate the financing risk score RFPi of enterprise i; where α and β are both proportionality coefficients greater than 0, and the specific values of α and β are set by experts in relevant fields according to experience.

[0074] Exemplarily, set the proportionality coefficients α = 0.01, β = 0.005; the customer quality score KZX1 of enterprise 1 = 2.7, and the performance credit score LXP1 of enterprise 1 = 7.86; the financing risk score RFP1 of enterprise 1 is calculated to be approximately 15.08 through the formula.

[0075] The present invention comprehensively considers the impacts of customer quality scores and performance credit scores on the financing risks of enterprises, multiplies the customer quality scores and performance credit scores by corresponding proportionality coefficients, and calculates the financing risk scores through a formula, so that the calculated financing risk scores can more comprehensively reflect the financial risks of each enterprise in the supply chain, thereby facilitating improving the accuracy of monitoring and early warning of supply chain financial risks.

[0076] In this embodiment, the financing risk prediction model is constructed based on an artificial intelligence model, including:

[0077] Extract the financing risk scores of each enterprise for several consecutive periods and integrate them into several groups of original data. Take 80% of the original data as training data and 20% as test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally obtain a financing risk prediction model with the input being the carbon financing risk scores of each enterprise for several recent consecutive periods and the output being the financing risk scores of each enterprise in the prediction period; wherein, the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0078] The present invention extracts the financing risk scores of each enterprise for several consecutive periods to train the artificial intelligence model. After training, a financing risk prediction model is obtained. By inputting the financing risk scores of each enterprise for several consecutive periods into the financing risk prediction model, the predicted values of the financing risk scores of each enterprise in the prediction period are obtained, which is conducive to investment institutions estimating in advance the financing risks of the corresponding enterprises and facilitating investment institutions to adjust the loan amounts, thereby helping to reduce supply chain financial risks.

[0079] In this embodiment, early warning of supply chain financial risks based on the predicted values of financing risk scores includes:

[0080] Extract the predicted values of the financing risk scores of each enterprise in the supply chain and set a risk score threshold;

[0081] Judge whether the predicted value of the financing risk score is greater than the preset risk threshold; if yes, save the number of the corresponding enterprise to the enterprise risk control early warning sequence; if no, continue to monitor the supply chain financial risks;

[0082] Sort the numbers of the enterprises in the enterprise risk control early warning sequence in descending order according to the financing risk scores to obtain an early warning priority sequence;

[0083] Successively extract the number of the enterprise with the highest financing risk score from the early warning priority sequence and generate financial risk early warning information for the corresponding enterprise.

[0084] Exemplarily, the predicted value of the financing risk score of enterprise 1 is set to 22, and the preset risk threshold is 20; since the predicted value of the financing risk score of enterprise 1 is greater than the preset risk threshold, the number corresponding to the enterprise is saved to the enterprise risk control warning sequence; successively extract the number corresponding to the enterprise with the highest financing risk score from the warning priority sequence, and generate the financial risk warning information corresponding to the enterprise.

[0085] An embodiment of the second aspect of the present invention provides a storage medium, the storage medium includes a stored program, wherein when the program runs, it controls the device where the storage medium is located to execute the method in the above-mentioned supply chain financial risk monitoring and intelligent warning system.

[0086] Some data in the above formula is the numerical value calculated after removing the dimension, and the formula is a formula that is closest to the actual situation obtained through software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0087] The working principle of the present invention:

[0088] The present invention collects the historical performance information and customer composition information of each enterprise in the supply chain; calculates the customer quality score of each enterprise in the supply chain based on the customer composition information; calculates the performance credit score of each enterprise in the supply chain based on the historical performance information; calculates the financing risk score of each enterprise in the supply chain based on the customer quality score and the performance credit score; inputs the financing risk score into the financing risk prediction model to obtain the predicted value of the financing risk score; and warns of the supply chain financial risk based on the predicted value of the financing risk score.

[0089] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A supply chain financial risk monitoring and intelligent early warning system, comprising: The data processing module, and the information collection module and intelligent early warning module connected thereto are characterized in that: The information collection module is used to collect the historical performance information and customer composition information of each enterprise in the supply chain; The data processing module is used to calculate the customer quality score of each enterprise in the supply chain based on the customer composition information; calculate the contract performance credit score of each enterprise in the supply chain based on the historical contract performance information; calculate the financing risk score of each enterprise in the supply chain based on the customer quality score and the contract performance credit score; The intelligent early warning module is used to input the financing risk score into the financing risk prediction model to obtain a financing risk score prediction value; and to issue an early warning for supply chain financial risks based on the financing risk score prediction value; wherein the financing risk prediction model is constructed based on an artificial intelligence model.

2. A supply chain financial risk monitoring and intelligent early warning system according to claim 1, characterized in that: It also includes a data transmission module, which is used for data communication between the information collection module, the data processing module and the intelligent early warning module.

3. A supply chain financial risk monitoring and intelligent early warning system according to claim 1, characterized in that: The calculation of the customer quality score of each enterprise in the supply chain based on the customer composition information includes: Extract the customer composition information of each enterprise in the supply chain, and mark the number of each enterprise in the supply chain as i; the customer composition information includes the number of major customers and the number of stable customers; i = 1, 2, ..., n, n is the total number of enterprises in the supply chain; Multiply the number of major customers and the number of stable customers by the corresponding weight coefficients and sum them up to obtain the customer quality score KZXi.

4. A supply chain financial risk monitoring and intelligent early warning system according to claim 3, characterized in that: The number of major customers is obtained in the following way: Extract the historical customer cooperation data of each enterprise in the supply chain; the historical customer cooperation data includes the cooperation amount and the number of cooperation times; Determine whether the cooperation amount or the number of cooperation times is greater than the corresponding preset threshold; if yes, mark the customer scale label of the corresponding customer as 1; if no, mark the customer scale label of the corresponding customer as 0; The total number of customers whose customer size label value is 1 is marked as the number of large customers.

5. A supply chain financial risk monitoring and intelligent early warning system according to claim 3, characterized in that: The number of stable customers is obtained in the following ways: Extract the number of cooperations between each enterprise in the supply chain and the corresponding customer in several consecutive cycles; fit the number of customer cooperations of each enterprise in the supply chain in several consecutive cycles to obtain a curve of the change of the number of cooperations; derive the curve of the change of the number of cooperations to obtain a derivative function of the change of the number of cooperations; extract the maximum value of the derivative function of the change of the number of cooperations and mark it as the characteristic value of the change of the number of cooperations; Determine whether the characteristic value of the number of cooperation changes is less than the preset number of changes threshold; if yes, set the stability label of the corresponding customer to 1; If not, set the stability label of the corresponding customer to 0; The total number of customers whose stability label value is 1 is marked as the number of stable customers.

6. A supply chain financial risk monitoring and intelligent early warning system according to claim 3, characterized in that: The calculation of the contract performance credit score of each enterprise in the supply chain based on historical contract performance information includes: Extract the historical performance information of each enterprise in the supply chain; the historical performance information includes the number of repayment defaults, the length of repayment extension and the on-time delivery rate; By formula Calculate the performance credit score LXPi of each enterprise in the supply chain; among them, WYSi is the number of repayment defaults of enterprise i, HYSi is the repayment extension period of enterprise i, and JFLi is the on-time delivery rate of enterprise i; c, d, and f are all proportional coefficients greater than 0; e is a natural constant.

7. A supply chain financial risk monitoring and intelligent early warning system according to claim 6, characterized in that: The calculation of the financing risk score of each enterprise in the supply chain based on the customer quality score and the performance credit score includes: Extract the customer quality score KZXi and the fulfillment credit score LXPi of each enterprise in the supply chain; through the formula Calculate the financing risk score RFPi of enterprise i; where α and β are both proportional coefficients greater than 0.

8. A supply chain financial risk monitoring and intelligent early warning system according to claim 1, characterized in that: The financing risk prediction model is constructed based on an artificial intelligence model and includes: Extract the financing risk scores of several consecutive cycles of each enterprise and integrate them into several groups of training data and test data; use the training data to train the artificial intelligence model; use the test data to test the trained artificial intelligence model, and adjust the artificial intelligence model according to the test results; finally, obtain a financing risk prediction model whose input is the carbon financing risk scores of several recent consecutive cycles of each enterprise and whose output is the financing risk scores of each enterprise in the prediction cycle; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

9. A supply chain financial risk monitoring and intelligent early warning system according to claim 1, characterized in that: The early warning of supply chain financial risks based on the predicted value of the financing risk score includes: Extract the predicted value of financing risk score of each enterprise in the supply chain and set the risk score threshold; Determine whether the predicted value of the financing risk score is greater than the preset risk threshold; if yes, save the corresponding enterprise number to the enterprise risk control warning sequence; if no, continue to monitor the supply chain financial risk; Sort the enterprise numbers in the enterprise risk control warning sequence in descending order according to the financing risk scores to obtain the warning priority sequence; The numbers corresponding to the enterprises with the highest financing risk scores are extracted from the warning priority sequence in turn, and financial risk warning information of the corresponding enterprises is generated.

10. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute a method in a supply chain financial risk monitoring and intelligent early warning system as described in any one of claims 1 to 9.

Images