Supplier credit granting method and device, electronic equipment and medium

Abstract

The invention provides a supplier credit granting method and device, electronic equipment and a medium, and can be applied to the field of block chains, the technical field of big data and the technical field of artificial intelligence. The method comprises the steps of collecting historical order data of a supplier, performing data processing on the historical order data, and obtaining historical target data; performing block chain encryption processing on the historical target data to obtain order encrypted data; inputting the order encryption data into a pre-trained order information prediction model, and outputting an order risk prediction result of the supplier; based on the order risk prediction result, obtaining predicted order information of a supplier in a first prediction period; inputting the predicted order information into a pre-constructed dynamic credit extension model, and calculating credit extension information; and providing the credit granting information for the supplier in response to verification of the identity information passed by the supplier, so that the supplier obtains a credit granting result according to the credit granting information.

Description

Technical Field

[0001] The present invention relates to the fields of blockchain, big data technology and artificial intelligence technology, and more specifically to a supplier credit granting method, device, electronic device and medium. Background Art

[0002] In today's globalized business environment, supply chain has become a vital part of business activities. Supply chain covers a series of key activities from raw material procurement, manufacturing, to distribution and sales, and plays an irreplaceable role in the operation and development of enterprises. However, in the operation of supply chain, especially in small and medium-sized enterprises and emerging markets, the flow of funds has become a key bottleneck, and the traditional supply chain financing model has obvious shortcomings in meeting funding needs.

[0003] Specifically, in the traditional financing model, enterprises in the supply chain often face the problem of missing order data. In this case, it is difficult for supply chain financial institutions to accurately understand and analyze the operation status, order volume and future funding needs of enterprises. Due to the lack of order data, it is impossible to accurately match the funding needs of enterprises, resulting in difficulties for enterprises in the supply chain in the financing process, which restricts their production and development. In addition, traditional financing models usually make credit decisions based on static indicators, such as the credit rating of enterprises, historical financial performance, etc. However, this approach ignores the dynamics and complexity of the operation of enterprises in the supply chain. Static indicators cannot fully consider factors such as market changes, supply chain relationships and risk fluctuations, and thus have limitations in matching actual financing needs. Summary of the invention

[0004] In view of the above problems, according to the first aspect of the present invention, a supplier credit method is provided, characterized in that the method includes: collecting historical order data of the supplier, performing data processing on the historical order data, and obtaining historical target data; performing blockchain encryption processing on the historical target data to obtain order encrypted data; inputting the order encrypted data into a pre-trained order information prediction model, and outputting the supplier's order risk prediction result; based on the order risk prediction result, obtaining the supplier's predicted order information within the first prediction period; inputting the predicted order information into a pre-built dynamic credit model to calculate the credit information; and in response to the supplier passing the verification of the identity information, providing the credit information to the supplier, so that the supplier obtains the credit result based on the credit information.

[0005] According to some exemplary embodiments, the historical target data is subjected to blockchain encryption processing to obtain order encrypted data, specifically including: encrypting the historical target data using a hash algorithm to generate a data fingerprint; encapsulating the fingerprint data into transaction information, broadcasting it to the blockchain network, and verifying it using a consensus mechanism; packaging the verified transaction information into blocks and adding them to the end of the blockchain; and obtaining order encrypted data based on the blockchain.

[0006] According to some exemplary embodiments, the order information prediction model is trained using a LightGBM model.

[0007] According to some exemplary embodiments, it is characterized in that before the historical target data is subjected to blockchain encryption processing, the method further includes: using a pre-constructed feature matrix to extract features from the historical target data to obtain order features, wherein the feature matrix is ​​constructed based on indicator features for measuring order prediction capabilities, indicator features for measuring order reliability, and indicator features for measuring order fulfillment capabilities.

[0008] According to some exemplary embodiments, the scale and term prediction model includes N decision trees, where N is a positive integer, and the step of inputting the encrypted order data into a pre-trained scale and term prediction model and outputting the order risk prediction result of the supplier specifically includes: inputting the encrypted order data into the N decision trees to obtain the prediction results corresponding to the N decision trees; calculating the integrated prediction results of the N decision trees based on the decision weights of the N decision trees; and obtaining the order risk prediction result based on the integrated prediction result.

[0009] According to some exemplary embodiments, the credit information includes a credit limit and a credit period, and the pre-built dynamic credit model includes a credit limit calculation model and a credit period calculation model, wherein the credit limit calculation model is expressed as the product of the predicted order size and the credit rating weighted coefficient, and the sum of the risk assessment weighted coefficient; the credit period calculation model is expressed as the product of the predicted order collection time and the credit rating weighted coefficient, and the sum of the risk assessment weighted coefficient.

[0010] According to some exemplary embodiments, in response to the supplier passing the verification of identity information, providing the credit information to the supplier specifically includes: deploying a smart contract on the blockchain, and sending the credit information to the smart contract; authenticating the supplier based on the smart contract; and if the supplier's identity verification passes, providing the credit information to the supplier.

[0011] According to some exemplary embodiments, the method also includes: acquiring the current order data of the supplier in real time, and reacquiring the order risk prediction result based on the current order data; updating the predicted order information when the order risk prediction result changes; and recalculating the credit information based on the updated predicted order information, so that the supplier is granted credit according to the recalculated credit information.

[0012] According to a second aspect of the present invention, a supplier credit device is proposed, which includes: a historical target data acquisition module, which is used to collect the supplier's historical order data, perform data processing on the historical order data, and obtain historical target data; an order encryption data acquisition module, which is used to perform blockchain encryption processing on the historical target data and obtain order encryption data; an order risk prediction result output module, which is used to input the order encryption data into a pre-trained scale and term prediction model, and output the supplier's order risk prediction result; a predicted order information acquisition module, which is used to obtain the supplier's predicted order information within the first prediction period based on the order risk prediction result; a credit information calculation module, which is used to input the predicted order information into a pre-built dynamic credit model to calculate credit information; and a credit information providing module, which is used to provide the supplier with the credit information in response to the supplier passing the identity information verification, so that the supplier obtains the credit result based on the credit information.

[0013] According to some exemplary embodiments, the order encryption data acquisition module may include a blockchain encryption processing module.

[0014] According to some exemplary embodiments, the blockchain encryption processing module includes an encryption unit, a verification unit, a packaging unit, and an order encryption data acquisition unit.

[0015] According to some exemplary embodiments, the encryption unit may be used to encrypt the historical target data using a hash algorithm to generate a data fingerprint.

[0016] According to some exemplary embodiments, the verification unit may be used to encapsulate the fingerprint data into transaction information, broadcast it to the blockchain network, and perform verification using a consensus mechanism.

[0017] According to some exemplary embodiments, the packaging unit may be configured to package the verified transaction information into a block and add the block to the end of the blockchain.

[0018] According to some exemplary embodiments, the order encryption data acquisition unit may be configured to acquire order encryption data based on the blockchain.

[0019] According to some exemplary embodiments, the supplier credit authorization device further includes a feature extraction unit.

[0020] According to some exemplary embodiments, the feature extraction unit can be used to perform feature extraction on the historical target data using a pre-constructed feature matrix to obtain order features, wherein the feature matrix is ​​constructed based on indicator features for measuring order prediction capability, indicator features for measuring order reliability, and indicator features for measuring order fulfillment capability.

[0021] According to some exemplary embodiments, the order risk prediction result output module may include a prediction module.

[0022] According to some exemplary embodiments, the prediction module may include an N-decision tree result acquisition unit, a prediction result integration unit, and an order risk prediction result acquisition unit.

[0023] According to some exemplary embodiments, the N decision tree result acquisition unit may be used to input the order encryption data into the N decision trees to obtain prediction results corresponding to the N decision trees.

[0024] According to some exemplary embodiments, the prediction result integration unit may be used to calculate an integrated prediction result of the N decision trees based on the decision weights of the N decision trees.

[0025] According to some exemplary embodiments, the order risk prediction result acquisition unit may be used to obtain the order risk prediction result based on the integrated prediction result.

[0026] According to some exemplary embodiments, the credit information calculation module may include a credit information calculation module.

[0027] According to some exemplary embodiments, the credit information calculation module may include a credit limit calculation unit and a credit period calculation unit.

[0028] According to some exemplary embodiments, the credit line calculation unit may be used to calculate the credit line based on a pre-built credit line calculation model, wherein the credit line calculation model is represented as the product of the predicted order size and the credit rating weighted coefficient, and the sum of the predicted order size and the risk assessment weighted coefficient.

[0029] According to some exemplary embodiments, the credit period calculation unit can be used to calculate the credit period based on a pre-built credit period calculation model, wherein the credit period calculation model is represented as the product of the predicted order collection time and the credit rating weighted coefficient, and the sum of the predicted order collection time and the risk assessment weighted coefficient.

[0030] According to some exemplary embodiments, the credit information providing module may include a credit information providing module.

[0031] According to some exemplary embodiments, the credit information providing module may include a credit information sending unit, an identity authentication unit and a credit information providing unit.

[0032] According to some exemplary embodiments, the credit information uploading unit may be used to deploy a smart contract on a blockchain and upload the credit information to the smart contract.

[0033] According to some exemplary embodiments, the identity verification unit may be configured to verify the identity of the supplier based on the smart contract.

[0034] According to some exemplary embodiments, the credit information providing unit may be configured to provide the credit information to the supplier if the supplier's identity verification is passed.

[0035] According to some exemplary embodiments, the apparatus may further include a credit information updating module.

[0036] According to some exemplary embodiments, the credit information updating module may include a prediction result re-acquisition unit, a prediction order information updating unit and a re-credit unit.

[0037] According to some exemplary embodiments, the prediction result re-acquisition unit may be used to acquire the current order data of the supplier in real time, and re-acquire the order risk prediction result based on the current order data.

[0038] According to some exemplary embodiments, the predicted order information updating unit may be configured to update the predicted order information when the order risk prediction result changes.

[0039] According to some exemplary embodiments, the re-crediting unit may be used to recalculate the credit information based on the updated forecast order information, so that the supplier is credited according to the recalculated credit information.

[0040] According to a third aspect of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the method as described above.

[0041] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method as described above.

[0042] According to a fifth aspect of the present invention, there is provided a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method as described above is implemented.

[0043] One or more of the above embodiments have the following advantages or beneficial effects: The supplier credit method provided by the present invention combines the blockchain, prediction model, and credit model methods to ensure data security, trust building, decision support, and cooperation enhancement in supply chain management, provide a comprehensive supplier credit assessment, and enhance the scientificity and accuracy of financing decisions. Among them, blockchain technology provides high data security and immutability, and the supplier's credit information and identity verification records will always remain credible and not controlled by any single entity; by integrating the prediction model, the risk and reliability of orders can be more accurately assessed. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above contents and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0045] Figure 1 The application scenario diagram of the supplier credit granting method, apparatus, device, and medium according to an embodiment of the present invention is schematically shown.

[0046] Figure 2 The flowchart of the supplier credit granting method according to an embodiment of the present invention is schematically shown.

[0047] Figure 3 The flowchart of the method for blockchain encryption processing according to an embodiment of the present invention is schematically shown.

[0048] Figure 4 The flowchart of the feature extraction method according to the embodiment of the present invention is schematically shown.

[0049] Figure 5 The flowchart of the method for obtaining prediction results through a prediction model according to an embodiment of the present invention is schematically shown.

[0050] Figure 6 The flowchart of the method for calculating credit information according to an embodiment of the present invention is schematically shown.

[0051] Figure 7 The flowchart of the method for providing credit information to a supplier according to an embodiment of the present invention is schematically shown.

[0052] Figure 8 The flowchart of the method for dynamically updating credit information according to an embodiment of the present invention is schematically shown.

[0053] Fig. 9 The structure block diagram of the supplier credit granting device according to an embodiment of the present invention is schematically shown.

[0054] Fig.10 A block diagram of an electronic device suitable for a supplier credit authorization method according to an embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0055] Below, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of embodiments of the present invention. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of concepts of the present invention.

[0056] The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0057] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0058] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0059] In the technical solution of the present invention, the acquisition, storage and application of user personal information involved all comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0060] First, the technical terms described in this article are explained and described as follows.

[0061] Blockchain: A distributed, decentralized database technology that organizes and stores data in the form of blocks. Each block contains the hash value of the previous block, forming an unalterable chain structure. Blockchain technology ensures the security, transparency and immutability of data, allowing multiple participants to verify and record transactions on a shared network.

[0062] LightGBM (Light Gradient Boosting Machine) is a machine learning framework based on gradient boosting trees. It is a powerful ensemble learning algorithm for processing structured data, such as tabular data. LightGBM builds multiple decision trees in an efficient and accurate way and integrates them into a more powerful prediction model. It has efficient performance and the ability to process large-scale data.

[0063] Smart Contract: A self-executing computing code stored on the blockchain. It defines a set of conditions and actions that will be automatically executed when certain conditions are met. Smart contracts can be used to automate and ensure the execution of transactions without the need for third-party intervention. They are transparent, automated, and secure.

[0064] A decision tree is a machine learning model based on a tree structure, used for classification and regression tasks. In classification tasks, a decision tree gradually splits data into different categories based on input features. In regression tasks, a decision tree predicts continuous values. Each node of a decision tree represents a feature, each branch represents the value of a feature, and the leaf node represents the final prediction result.

[0065] Financing credit: refers to a financial institution's credit commitment to provide a certain amount of financing funds to an enterprise or individual. This means that the financing credit institution agrees to provide financing to the borrower under certain conditions so that the borrower can obtain funds when needed.

[0066] Credit line: refers to the maximum loan amount that a financial institution or creditor is willing to provide to a borrower. It represents the upper limit of the amount that a borrower can borrow from a financial institution within a certain period of time. The credit line is usually determined based on the borrower's credit rating, debt situation and other relevant factors.

[0067] Credit period: refers to the time that the financial institution or creditor agrees that the borrower can extend the loan, that is, the borrower can borrow multiple times within a specific period without having to reapply. The credit period can be a specific period of time, such as one or two years, or it can be indefinite. During the credit period, the borrower can borrow multiple times as needed, but the total loan amount must not exceed the credit limit.

[0068] As the connection between upstream and downstream enterprises in the supply chain becomes closer, supply chain center enterprises and their suppliers have a need for financing based on the transaction orders between the two parties. Banks can provide financing credit to enterprises in the supply chain. However, in the traditional supply chain financing model, due to the lack of order data, it is impossible to accurately match the capital needs of enterprises in the supply chain, and there is also a risk of financing fraud. At the same time, the traditional supply chain financing model usually makes credit decisions based on static indicators, which cannot reflect changes and dynamic needs in the supply chain in a timely manner. Therefore, there is an urgent need to conduct intelligent and automated order forecasting analysis based on real order history data, so as to provide a basis for bank supply chain financing credit and realize dynamic updates.

[0069] Based on this, an embodiment of the present invention provides a supplier credit method, characterized in that the method includes: collecting the supplier's historical order data, performing data processing on the historical order data, and obtaining historical target data; performing blockchain encryption processing on the historical target data to obtain order encryption data; inputting the order encryption data into a pre-trained order information prediction model, and outputting the supplier's order risk prediction result; based on the order risk prediction result, obtaining the supplier's predicted order information in the first prediction period; inputting the predicted order information into a pre-built dynamic credit model to calculate the credit information; and in response to the supplier's verification of identity information, providing the supplier with the credit information, so that the supplier obtains the credit result according to the credit information. According to the supplier credit method provided by the present invention, combined with the method of blockchain, prediction model, and credit model, data security, trust establishment, decision support, and cooperation enhancement in supply chain management are guaranteed, a comprehensive supplier credit assessment is provided, and the scientificity and accuracy of financing decisions are enhanced. Among them, blockchain technology provides high security and tamper-proof of data, and the supplier's credit information and identity authentication records will always remain credible and not controlled by any single entity; by integrating the prediction model, the risk and reliability of orders can be more accurately assessed.

[0070] It should be noted that the supplier credit granting method, device, equipment and medium determined by the present invention can be used in the blockchain field, the big data technology field and the artificial intelligence technology field, and can also be used in the financial field, and can also be used in various fields other than the blockchain field, the big data technology field and the artificial intelligence technology field and the financial field. The application field of the supplier credit granting method, device, equipment and medium provided by the embodiments of the present invention is not limited.

[0071] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0072] Figure 1 The application scenario diagram of the supplier credit granting method, apparatus, device, and medium according to an embodiment of the present invention is schematically shown.

[0073] like Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0074] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0075] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0076] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0077] It should be noted that the supplier credit method provided in the embodiment of the present invention can generally be executed by the server 105. Accordingly, the supplier credit device provided in the embodiment of the present invention can generally be set in the server 105. The supplier credit method provided in the embodiment of the present invention can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the supplier credit device provided in the embodiment of the present invention can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0078] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0079] Figure 2 The flowchart of the supplier credit granting method according to an embodiment of the present invention is schematically shown.

[0080] like Figure 2 As shown, the supplier credit authorization method 200 of this embodiment may include operations S210 to S260.

[0081] In operation S210, historical order data of suppliers is collected, and data processing is performed on the historical order data to obtain historical target data.

[0082] In an embodiment of the present invention, historical order data may be obtained from databases of supply chain center enterprises and their suppliers.

[0083] In an embodiment of the present invention, in order to further focus on key data, appropriate tools (such as SQL query, data analysis software) can be used to extract historical target data such as historical order quantity, order completion time, order price information, product category information, etc. from the historical order data.

[0084] In operation S220, the historical target data is encrypted using blockchain to obtain encrypted order data.

[0085] In an embodiment of the present invention, historical target data may be encrypted using an asymmetric encryption algorithm, and a distributed storage method may be used to disperse and store the data on multiple nodes or servers of a blockchain network.

[0086] Figure 3 The flowchart of the method for blockchain encryption processing according to an embodiment of the present invention is schematically shown.

[0087] like Figure 3As shown, the blockchain encryption processing method of this embodiment may include operations S310 to S340, and the operations S310 to S340 may at least partially perform the above-mentioned operation S220.

[0088] In operation S310, the historical target data is encrypted using a hash algorithm to generate a data fingerprint.

[0089] In an embodiment of the present invention, a hash algorithm is an encryption technology that converts input data into a fixed-length string. By encrypting the order forecast data using a hash algorithm, a string called a "data fingerprint" can be generated. The data fingerprint is unique, and even a slight change in the input data will result in a completely different fingerprint. The above hash encryption process is irreversible, which means that the original data cannot be restored from the data fingerprint.

[0090] In operation S320, the fingerprint data is encapsulated into transaction information, broadcast to the blockchain network, and verified using a consensus mechanism.

[0091] In an embodiment of the present invention, the encrypted data fingerprint is encapsulated into transaction information, which includes the data fingerprint itself and other possible metadata, such as a timestamp, a transaction initiator, etc. The transaction information can be designed as a data structure of a transaction.

[0092] In an embodiment of the present invention, the encapsulated transaction information is broadcast to the blockchain network, and multiple nodes in the network will verify the transaction information. The verification process may involve a consensus mechanism to ensure the legitimacy and consistency of the transaction. Specifically, the consensus mechanism may include proof of work (PoW) and proof of stake (PoS).

[0093] In operation S330, the verified transaction information is packaged into a block and added to the end of the blockchain.

[0094] In an embodiment of the present invention, once the transaction information passes the network verification, multiple verification nodes will package the verified transaction information into a block, which also includes the hash value, timestamp and other information of the previous block to form a continuously growing chain structure.

[0095] In an embodiment of the present invention, the packaged blocks are added to the end of the blockchain, extending the length of the blockchain. This process ensures the immutability of the transaction. Once the data is added to the blockchain, it will become a permanent record that is difficult to change.

[0096] In operation S340, order encryption data is obtained based on the blockchain.

[0097] In an embodiment of the present invention, a decentralized authentication and permission management method can be used to ensure that only authorized users can access the data of the above blockchain. Users can obtain the hash value of a specific order by querying the blockchain and further obtain encrypted data. Once the user obtains the encrypted data, the corresponding encryption key can be used to decrypt the data for subsequent processing.

[0098] In addition, in order to increase the prediction accuracy of the model, the method also includes a feature extraction operation before the historical target data is encrypted by blockchain.

[0099] Figure 4 The flowchart of the feature extraction method according to the embodiment of the present invention is schematically shown.

[0100] like Figure 4 As shown, the feature extraction method of this embodiment may include operation S410.

[0101] In operation S410, feature extraction is performed on the historical target data using a pre-constructed feature matrix to obtain order features, wherein the feature matrix is ​​constructed based on indicator features for measuring order prediction capability, indicator features for measuring order reliability, and indicator features for measuring order fulfillment capability.

[0102] In an embodiment of the present invention, the historical target data may be preprocessed first, and noise and unnecessary information in the data may be eliminated through data cleaning, data transformation, and data reduction, and the historical target data may be organized into a feature matrix, where each row represents an order sample and each column represents a feature.

[0103] In an embodiment of the present invention, feature extraction can be performed through the index features for measuring order prediction capability, the index features for measuring order reliability, and the index features for measuring order fulfillment capability to obtain order features. The index features for order prediction capability will measure the order prediction capability; the index features for order reliability will reflect the reliability of the supplier's order fulfillment; and the index features for order fulfillment capability will reflect whether the supplier can fulfill the order on time and in quantity. These include but are not limited to the indicators described in Table 1.

[0104] Table 1

[0105]

[0106] In an embodiment of the present invention, the order features may replace the original historical target data for subsequent encryption and model input operations to improve model performance.

[0107] Return to reference Figure 2In operation S230, the encrypted order data is input into a pre-trained order information prediction model, and the order risk prediction result of the supplier is output.

[0108] In an embodiment of the present invention, the order information prediction model is trained using the LightGBM model.

[0109] According to an embodiment of the present invention, LightGBM is a powerful tool suitable for order information prediction. Through an efficient gradient boosting tree algorithm, an accurate prediction model can be established based on historical data to support decision making and risk management.

[0110] In an embodiment of the present invention, specifically, the historical target data can be split into a training set and a validation set, the training set is used for model training, and the validation set is used for performance evaluation. Evaluation indicators (such as root mean square error, mean absolute error, etc.) can be used to judge the performance of the model. Furthermore, if the model performance is found to be poor, the model parameters can be adjusted, such as the number of trees, the number of leaf nodes, etc., to optimize the prediction ability of the model. After the training is completed, the trained model can be used to predict order information. New feature data (such as the features of the predicted order) is input into the model to obtain the corresponding prediction results.

[0111] Figure 5 The flowchart of the method for obtaining prediction results through a prediction model according to an embodiment of the present invention is schematically shown.

[0112] like Figure 5 As shown, the method for obtaining a prediction result through a prediction model in this embodiment may include operations S510 to S530, and the operations S510 to S530 may at least partially execute the above operation S230.

[0113] In operation S510, the encrypted order data is input into the N decision trees to obtain prediction results corresponding to the N decision trees.

[0114] In operation S520, based on the decision weights of the N decision trees, an integrated prediction result of the N decision trees is calculated.

[0115] In operation S530, the order risk prediction result is obtained based on the integrated prediction result.

[0116] In an embodiment of the present invention, LightGBM obtains the final prediction value by weighted averaging the prediction results of multiple decision trees. The prediction result of each decision tree depends on the leaf node where it is located, and the value of each leaf node is learned during the training process by the gradient boosting algorithm. Among them, the prediction value representing the i-th order can be expressed by the following formula:

[0117]

[0118] Among them, ntrees represents the number of decision trees, w j Represents the weight of the jth decision tree and predicts the leaf node value ij Represents the predicted value of the leaf node of order i in the jth decision tree.

[0119] Return to reference Figure 2 , in operation S240, based on the order risk prediction result, the predicted order information of the supplier in the first prediction period is obtained.

[0120] In an embodiment of the present invention, the supplier's forecasted order information in the first forecast period indicates the supplier's forecasted order size and forecasted order payment time in the future. The forecasted order size and forecasted order payment time can be used for subsequent credit information calculation.

[0121] In operation S250, the predicted order information is input into a pre-built dynamic credit model to calculate credit information.

[0122] Figure 6 The flowchart of the method for calculating credit information according to an embodiment of the present invention is schematically shown.

[0123] In an embodiment of the present invention, the dynamic credit model can calculate the supplier's credit information based on the supplier's predicted order size and predicted order payment time obtained above. The credit information involves the credit limit and credit period, which helps to determine how much credit should be provided and how long the loan can be extended under the supplier's credit risk.

[0124] like Figure 6 As shown, the method for calculating credit information of this embodiment may include operations S610 to S620, and the operations S610 to S620 may at least partially execute the above-mentioned operation S250.

[0125] In operation S610, the credit limit is calculated based on a pre-built credit limit calculation model, wherein the credit limit calculation model is represented by the product of the predicted order size and the credit rating weighted coefficient, and the sum of the predicted order size and the risk assessment weighted coefficient. The credit limit calculation model can be represented as:

[0126] Credit Line i = Forecast order size i ×Credit rating weighting factor i +Risk Assessment Weighting Factor i (2)

[0127] Among them, i represents the i-th supplier, and the predicted order size iIt represents the order size of supplier i in a certain period of time in the future. The credit rating weighting coefficient and risk assessment weighting coefficient are determined according to the supplier's credit rating and risk level preset by the banking system.

[0128] In operation S620, the credit period is calculated based on the pre-built credit period calculation model, wherein the credit period calculation model is represented by the product of the predicted order payment collection time and the credit rating weighted coefficient, and the sum of the predicted order payment collection time and the risk assessment weighted coefficient. The credit period calculation model can be represented as:

[0129] Credit period i = Predicted payment collection time i ×Credit rating weighting factor i +Risk Assessment Weighting Factor i (3)

[0130] Among them, the predicted payment time i It indicates the payment collection time of supplier i in a certain period in the future.

[0131] It should be noted that operations S610 and S620 may be performed simultaneously or sequentially, and the order of their execution is not critical.

[0132] Return to reference Figure 2 In operation S260, in response to the supplier passing the identity information verification, the credit information is provided to the supplier, so that the supplier obtains a credit result according to the credit information.

[0133] In the embodiment of the present invention, the credit information calculated by predicting the order information reflects the decision on the credit to the supplier, that is, the credit result. According to the credit result, the supplier can decide whether to accept the credit conditions.

[0134] Figure 7 The flowchart of the method for providing credit information to a supplier according to an embodiment of the present invention is schematically shown.

[0135] like Figure 7 As shown, the method for providing credit information to a supplier in this embodiment may include operations S710 to S730, and operations S710 to S730 may at least partially execute the above operation S260.

[0136] In operation S710, a smart contract is deployed on the blockchain, and the credit information is sent to the smart contract.

[0137] In an embodiment of the present invention, a smart contract is a computing code that is automatically executed on a blockchain. Therefore, a smart contract containing credit information verification logic can be deployed to a blockchain network. In the smart contract, the specific steps and conditions for verifying the identity of the supplier and providing credit information will be defined.

[0138] In an embodiment of the present invention, the calculated credit limit and term may be encrypted via an asymmetric algorithm and sent to a smart contract.

[0139] In operation S720, the supplier is authenticated based on the smart contract.

[0140] In the embodiment of the present invention, the identity information of suppliers participating in the supply chain is encrypted and stored in the block. When suppliers obtain the credit result information, they need to authenticate their identity through digital signatures. According to the set authorization rules and conditions, the smart contract automatically determines whether the supplier meets the authorization conditions.

[0141] In operation S730, if the identity authentication of the supplier is passed, the credit information is provided to the supplier.

[0142] In addition, in order to further utilize the real-time changes in order data to dynamically update the credit limit and term, the embodiment of the present invention also provides the following method.

[0143] Figure 8 The flowchart of the method for dynamically updating credit information according to an embodiment of the present invention is schematically shown.

[0144] like Figure 8 As shown, the method for dynamically updating credit information in this embodiment may include operations S810 to S830.

[0145] In operation S810, the current order data of the supplier is acquired in real time, and the order risk prediction result is reacquired based on the current order data.

[0146] In operation S820, when the order risk prediction result changes, the predicted order information is updated.

[0147] In operation S830, the credit information is recalculated based on the updated forecast order information, so that the supplier is granted credit according to the recalculated credit information.

[0148] The supplier credit method provided by the present invention combines blockchain, prediction model, credit model and smart contract methods to ensure data security, trust building, decision support and cooperation enhancement in supply chain management, provide comprehensive supplier credit assessment, and enhance the scientificity and accuracy of financing decisions. Among them, blockchain technology provides high security and immutability of data, and the supplier's credit information and identity verification records will always remain credible and not controlled by any single entity; by integrating the prediction model, the risk and reliability of the order can be more accurately assessed. Specifically, it brings the following beneficial effects:

[0149] 1. Blockchain technology provides high security and immutability of data. Once data is added to the blockchain, it is almost impossible to modify or delete it. This means that the supplier's credit information and identity verification records will always remain credible and not controlled by any single entity;

[0150] 2. LightGBM is a powerful tool for order information prediction. Through the efficient gradient boosting tree algorithm, you can build accurate prediction models based on historical order data to support decision making and risk management

[0151] 3. The characteristics of blockchain enable all transactions and operations to be recorded and verified by every node on the network. This transparency and traceability ensure that suppliers and other relevant parties have access to real-time, reliable information, thereby improving trust and cooperation; blockchain is a decentralized database that does not rely on a single central agency to maintain and manage data. This means that there is no single controller, and all parties involved can jointly maintain and supervise the data, thereby reducing the risk of single point failure and manipulation;

[0152] 4. Smart contracts allow predefined actions to be automatically executed under certain conditions. This means that the supplier's identity verification and credit information provision can be automated, reducing human errors and time consumption;

[0153] 5. It can realize data sharing and collaboration between supply chain center enterprises and suppliers, optimize supply chain financial service processes, improve the overall efficiency of the supply chain, and enhance customer satisfaction and user experience;

[0154] 6. Through real-time updated risk assessment and credit information, the credit limit and term are dynamically updated with strong flexibility. Supply chain managers can better manage potential risks and avoid transactions with high-risk suppliers, thereby reducing the possibility of losses.

[0155] Based on the above supplier credit granting method, the present invention also provides a supplier credit granting device. Fig. 9 The device is described in detail.

[0156] Fig. 9 The structure block diagram of the supplier credit granting device according to an embodiment of the present invention is schematically shown.

[0157] like Fig. 9 As shown, according to this embodiment, the supplier credit device 900 includes an order forecast data extraction module 910, an order encryption data acquisition module 920, an order risk forecast result output module 930, a forecast order information acquisition module 940, a credit information calculation module 950 and a credit information provision module 960.

[0158] The historical target data acquisition module 910 can be used to collect historical order data of suppliers, perform data processing on the historical order data, and acquire historical target data. In one embodiment, the historical target data acquisition module 910 can be used to perform the operation S210 described above, which will not be described in detail here.

[0159] The order encrypted data acquisition module 920 can be used to perform blockchain encryption processing on the historical target data to obtain order encrypted data. In one embodiment, the order encrypted data acquisition module 920 can be used to perform the operation S220 described above, which will not be repeated here.

[0160] The order risk prediction result output module 930 can be used to input the encrypted order data into a pre-trained scale and term prediction model to output the order risk prediction result of the supplier. In one embodiment, the order risk prediction result output module 930 can be used to perform the operation S230 described above, which will not be repeated here.

[0161] The predicted order information acquisition module 940 can be used to obtain the supplier's predicted order information in the first prediction period based on the order risk prediction result, wherein the predicted order information includes the predicted order size and the predicted order payment collection time. In one embodiment, the predicted order information acquisition module 940 can be used to perform the operation S240 described above, which will not be repeated here.

[0162] The credit information calculation module 950 may be used to input the predicted order information into a pre-built dynamic credit model to calculate the credit information. In one embodiment, the credit information calculation module 950 may be used to perform the operation S250 described above, which will not be described in detail here.

[0163] The credit information providing module 960 may be used to provide the credit information to the supplier in response to the supplier passing the identity information verification, so that the supplier obtains the credit result according to the credit information. In one embodiment, the credit information providing module 960 may be used to perform the operation S250 described above, which will not be repeated here.

[0164] According to an embodiment of the present invention, the order encryption data acquisition module 920 may include a blockchain encryption processing module.

[0165] According to an embodiment of the present invention, the blockchain encryption processing module includes an encryption unit, a verification unit, a packaging unit and an order encryption data acquisition unit.

[0166] The encryption unit may be used to encrypt the historical target data using a hash algorithm to generate a data fingerprint. In one embodiment, the encryption unit may be used to perform the operation S310 described above, which will not be described in detail herein.

[0167] The verification unit may be used to encapsulate the fingerprint data into transaction information, broadcast it to the blockchain network, and verify it using a consensus mechanism. In one embodiment, the verification unit may be used to perform the operation S320 described above, which will not be described in detail here.

[0168] The packaging unit may be used to package the verified transaction information into a block and add it to the end of the blockchain. In one embodiment, the packaging unit may be used to perform the operation S330 described above, which will not be described in detail here.

[0169] The order encrypted data acquisition unit may be used to acquire the order encrypted data based on the blockchain. In one embodiment, the order encrypted data acquisition unit may be used to perform the operation S340 described above, which will not be described in detail here.

[0170] According to an embodiment of the present invention, the supplier credit granting device 900 further includes a feature extraction unit.

[0171] The feature extraction unit can be used to extract features from the historical target data using a pre-constructed feature matrix to obtain order features, wherein the feature matrix is ​​constructed based on an indicator feature for measuring order prediction capability, an indicator feature for measuring order reliability, and an indicator feature for measuring order fulfillment capability. In one embodiment, the feature extraction unit can be used to perform the operation S410 described above, which will not be described in detail herein.

[0172] According to an embodiment of the present invention, the order risk prediction result output module 930 may include a prediction module.

[0173] According to an embodiment of the present invention, the prediction module may include N decision tree result acquisition units, a prediction result integration unit and an order risk prediction result acquisition unit.

[0174] The N decision tree result acquisition unit can be used to input the order encryption data into the N decision trees to obtain the prediction results corresponding to the N decision trees. In one embodiment, the N decision tree result acquisition unit can be used to perform the operation S510 described above, which will not be repeated here.

[0175] The prediction result integration unit may be used to calculate the integrated prediction result of the N decision trees based on the decision weights of the N decision trees. In one embodiment, the prediction result integration unit may be used to perform the operation S520 described above, which will not be described in detail here.

[0176] The order risk prediction result acquisition unit may be used to obtain the order risk prediction result based on the integrated prediction result. In one embodiment, the order risk prediction result acquisition unit may be used to perform the operation S530 described above, which will not be described in detail here.

[0177] According to an embodiment of the present invention, the credit information calculation module 950 may include a credit information calculation module.

[0178] The credit information calculation module may include a credit limit calculation unit and a credit period calculation unit.

[0179] The credit limit calculation unit can be used to calculate the credit limit based on a pre-built credit limit calculation model, wherein the credit limit calculation model is represented by the product of the predicted order size and the credit rating weighted coefficient, and the sum of the predicted order size and the risk assessment weighted coefficient. In one embodiment, the credit limit calculation unit can be used to perform the operation S610 described above, which will not be repeated here.

[0180] The credit period calculation unit can be used to calculate the credit period based on a pre-built credit period calculation model, wherein the credit period calculation model is represented by the product of the predicted order payment collection time and the credit rating weighted coefficient, and the sum of the predicted order payment collection time and the risk assessment weighted coefficient. In one embodiment, the credit period calculation unit can be used to perform the operation S620 described above, which will not be repeated here.

[0181] According to an embodiment of the present invention, the credit information providing module 960 may include a credit information providing module.

[0182] The credit information providing module may include a credit information sending unit, an identity verification unit and a credit information providing unit.

[0183] The credit information sending unit can be used to deploy a smart contract on the blockchain and send the credit information to the smart contract. In one embodiment, the credit information sending unit can be used to perform the operation S710 described above, which will not be repeated here.

[0184] The identity verification unit may be used to verify the identity of the supplier based on the smart contract. In one embodiment, the identity verification unit may be used to perform the operation S720 described above, which will not be described in detail herein.

[0185] The credit information providing unit may be used to provide the credit information to the supplier if the supplier's identity verification passes. In one embodiment, the credit information providing unit may be used to perform the operation S730 described above, which will not be described in detail here.

[0186] According to an embodiment of the present invention, the apparatus 900 may further include a credit information updating module.

[0187] According to an embodiment of the present invention, the credit information updating module may include a prediction result re-acquisition unit, a prediction order information updating unit and a re-credit unit.

[0188] The prediction result re-acquisition unit may be used to acquire the current order data of the supplier in real time, and re-acquire the order risk prediction result based on the current order data. In one embodiment, the prediction result re-acquisition unit may be used to perform the operation S810 described above, which will not be described in detail here.

[0189] The predicted order information updating unit may be used to update the predicted order information when the order risk prediction result changes. In one embodiment, the predicted order information updating unit may be used to perform the operation S820 described above, which will not be described in detail here.

[0190] The re-crediting unit may be used to recalculate the credit information based on the updated predicted order information, so that the supplier is credited according to the recalculated credit information. In one embodiment, the re-crediting unit may be used to perform the operation S830 described above, which will not be described in detail here.

[0191] According to an embodiment of the present invention, any multiple modules among the historical target data acquisition module 910, the order encrypted data acquisition module 920, the order risk prediction result output module 930, the predicted order information acquisition module 940, the credit information calculation module 950 and the credit information providing module 960 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the historical target data acquisition module 910, the order encryption data acquisition module 920, the order risk prediction result output module 930, the predicted order information acquisition module 940, the credit information calculation module 950 and the credit information providing module 960 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by an appropriate combination of any of them. Alternatively, at least one of the historical target data acquisition module 910, the order encryption data acquisition module 920, the order risk prediction result output module 930, the predicted order information acquisition module 940, the credit information calculation module 950 and the credit information providing module 960 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be performed.

[0192] Fig.10 A block diagram of an electronic device suitable for a supplier credit authorization method according to an embodiment of the present invention is schematically shown.

[0193] like Fig.10 As shown, the electronic device 1000 according to an embodiment of the present invention includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include an onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0194] In RAM 1003, various programs and data required for the operation of electronic device 1000 are stored. Processor 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004. Processor 1001 performs various operations of the method flow according to the embodiment of the present invention by executing the program in ROM 1002 and / or RAM 1003. It should be noted that the program can also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 can also perform various operations of the method flow according to the embodiment of the present invention by executing the program stored in the one or more memories.

[0195] According to an embodiment of the present invention, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 may further include one or more of the following components connected to the I / O interface 1005: an input portion 1006 including a keyboard, a mouse, etc.; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1008 including a hard disk, etc.; and a communication portion 1009 including a network interface card such as a LAN card, a modem, etc. The communication portion 1009 performs communication processing via a network such as the Internet. The drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that the computer program read therefrom is installed into the storage portion 1008 as needed.

[0196] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0197] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the ROM 1002 and / or RAM 1003 described above and / or one or more memories other than ROM 1002 and RAM 1003.

[0198] The embodiment of the present invention also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present invention.

[0199] The computer program executes the above functions defined in the system / device of the embodiment of the present invention when it is executed by the processor 1001. According to the embodiment of the present invention, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0200] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 1009, and / or installed from the removable medium 1011. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0201] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the processor 1001, the above functions defined in the system of the embodiment of the present invention are performed. According to the embodiment of the present invention, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0202] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written in any combination of one or more programming languages, specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, such as Java, C++, python, "C" language or similar programming languages. The program code can be executed completely on the user computing device, partially on the user device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0203] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0204] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although each embodiment is described above, it does not mean that the measures in each embodiment cannot be used in combination advantageously. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A supplier credit granting method, characterized in that: The method comprises: Collecting historical order data of suppliers, performing data processing on the historical order data, and obtaining historical target data; The historical target data is encrypted by blockchain to obtain encrypted order data; Inputting the encrypted order data into a pre-trained order information prediction model, and outputting the order risk prediction result of the supplier; Based on the order risk prediction result, obtaining the predicted order information of the supplier in the first prediction period; Inputting the predicted order information into a pre-built dynamic credit model to calculate credit information; and In response to the supplier passing the identity information verification, the credit information is provided to the supplier, so that the supplier obtains the credit result according to the credit information.

2. The method according to claim 1, characterized in that The said performing blockchain encryption processing on the said historical target data to obtain the encrypted order data specifically includes: The historical target data is encrypted using a hash algorithm to generate a data fingerprint; Encapsulate the fingerprint data into transaction information, broadcast it to the blockchain network, and verify it using a consensus mechanism; Pack verified transaction information into blocks and add them to the end of the blockchain; and Based on the blockchain, order encryption data is obtained.

3. The method according to claim 1, characterized in that The order information prediction model is trained using the LightGBM model.

4. The method according to any one of claims 1 to 3, characterized in that: Before the historical target data is encrypted by blockchain, the method further includes: The historical target data is subjected to feature extraction using a pre-constructed feature matrix to obtain order features, wherein the feature matrix is ​​constructed based on indicator features for measuring order prediction capability, indicator features for measuring order reliability, and indicator features for measuring order fulfillment capability.

5. The method according to claim 4, characterized in that The scale and term prediction model includes N decision trees, where N is a positive integer. The order encrypted data is input into the pre-trained scale and term prediction model to output the order risk prediction result of the supplier, specifically including: Inputting the encrypted order data into the N decision trees to obtain prediction results corresponding to the N decision trees; Based on the decision weights of the N decision trees, calculating the integrated prediction result of the N decision trees; and Based on the integrated prediction result, the order risk prediction result is obtained.

6. The method according to claim 1, characterized in that The credit information includes a credit limit and a credit period, and the pre-built dynamic credit model includes a credit limit calculation model and a credit period calculation model. Among them, the credit limit calculation model is expressed as the product of the predicted order size and the credit rating weighted coefficient, and the sum of the risk assessment weighted coefficient; the credit period calculation model is expressed as the product of the predicted order collection time and the credit rating weighted coefficient, and the sum of the risk assessment weighted coefficient.

7. The method according to claim 6, characterized in that In response to the supplier passing the identity information verification, providing the supplier with the credit information specifically includes: Deploy a smart contract on the blockchain and send the credit information to the smart contract; Authenticating the supplier based on the smart contract; and If the supplier's identity verification is passed, the credit information is provided to the supplier.

8. The method according to any one of claims 1 to 3, 5 to 7, characterized in that: The method further comprises: Acquire the current order data of the supplier in real time, and re-acquire the order risk prediction result based on the current order data; When the order risk prediction result changes, updating the predicted order information; and Based on the updated forecast order information, the credit information is recalculated so that the supplier is granted credit according to the recalculated credit information.

9. A supplier credit granting device, characterized in that: The device comprises: A historical target data acquisition module is used to: collect historical order data of suppliers, perform data processing on the historical order data, and acquire historical target data; An order encryption data acquisition module is used to: perform blockchain encryption processing on the historical target data to obtain order encryption data; An order risk prediction result output module is used to: input the encrypted order data into a pre-trained scale and term prediction model, and output the order risk prediction result of the supplier; A forecast order information obtaining module, used to: obtain the forecast order information of the supplier in the first forecast period based on the order risk forecast result; a credit information calculation module, used to: input the predicted order information into a pre-built dynamic credit model to calculate the credit information; and The credit information providing module is used to: in response to the supplier passing the identity information verification, provide the credit information to the supplier, so that the supplier obtains the credit result according to the credit information.

10. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 8.

Images