Block chain-based commission fee reduction agreement signing method and device

Abstract

The embodiment of the invention discloses a service charge reduction agreement signing method and device based on a block chain, which can be applied to the financial science and technology field or other technical fields. The method comprises the steps of determining a service charge reduction and remission agreement signing smart contract corresponding to a target customer according to a credit rating of the target customer and a corresponding relationship between a preset credit rating and the service charge reduction and remission agreement signing smart contract in a block chain system; and signing an intelligent contract according to the corresponding service charge reduction agreement and signing a service charge reduction agreement for the target customer according to the customer information of the target customer, and linking the signed service charge reduction agreement of the target customer to a block chain of the block chain system. According to the invention, the problem of mistakes and omissions easily caused by manual commission fee reduction at present is effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and blockchain technology, and in particular to a method and device for signing a handling fee reduction or exemption agreement based on blockchain. Background Art

[0002] When corporate customers use the bank system to conduct transactions such as intra-bank and inter-bank transfers, they are required to pay a certain fee. Fee reduction is a discount on fees given by banks to different types of customers. The discount is generally based on the customer's credit rating. The higher the credit rating, the greater the fee reduction. Currently, fee reduction requires account managers to perform offline information entry and other operations. Offline manual errors or omissions may cause customers to make mistakes in fee reduction discounts when using transfers, or still be charged the full fee, which brings a bad experience to customers and triggers customer complaints. The existing technology urgently needs an effective solution to solve the problem of errors and omissions that are prone to occur in manual fee reduction. Summary of the invention

[0003] In order to solve at least one technical problem in the above-mentioned background technology, the present invention proposes a method and device for signing a fee reduction or exemption agreement based on blockchain.

[0004] In order to achieve the above object, according to one aspect of the present invention, a method for signing a fee reduction agreement based on blockchain is provided, the method comprising:

[0005] Determine the smart contract for signing a handling fee reduction agreement corresponding to the target customer based on the target customer's credit rating and the correspondence between the preset credit rating and the smart contract for signing a handling fee reduction agreement in the blockchain system;

[0006] A smart contract is signed according to the corresponding fee reduction agreement and the customer information of the target customer. A fee reduction agreement is signed for the target customer, and the signed fee reduction agreement for the target customer is uploaded to the blockchain of the blockchain system. When executing the transaction of the target customer, the transaction system obtains the fee reduction agreement for the target customer from the blockchain, and then performs a fee reduction operation on the transaction according to the fee reduction agreement.

[0007] Optionally, the blockchain-based method for signing a fee reduction agreement of the present invention further includes:

[0008] Obtaining credit rating evaluation indicators of the target customer;

[0009] The credit rating evaluation index is input into a credit rating prediction model to obtain the credit rating of the target customer output by the credit rating prediction model.

[0010] Optionally, the blockchain-based method for signing a fee reduction agreement of the present invention further includes:

[0011] The credit rating prediction model is obtained from the alliance chain nodes in the alliance chain system, wherein the alliance chain nodes include financial institution nodes. The credit rating prediction model is obtained by federated learning with each financial institution node as a participant. During the federated learning process, each financial institution node generates a local training sample based on local customer data, and then trains the local model based on the local training samples.

[0012] Optionally, the credit rating prediction model is trained through multiple rounds of communication iterations of federated learning. In each round of communication iteration, each financial institution node trains the local model based on local training samples. After the training, the trained local model parameters are uploaded to the alliance chain of the alliance chain system. The computing nodes in the alliance chain system obtain the local model parameters of each financial institution node from the alliance chain, and then calculate the global model parameters based on the local model parameters of each financial institution node, and then upload the global model parameters to the alliance chain. Each financial institution node obtains the global model parameters from the alliance chain, and then updates the model parameters of the local model based on the global model parameters.

[0013] Optionally, signing a smart contract based on the corresponding handling fee reduction agreement and the customer information of the target customer to sign a handling fee reduction agreement for the target customer specifically includes:

[0014] The access address of the corresponding handling fee reduction agreement signing smart contract in the blockchain system is obtained, and then the corresponding handling fee reduction agreement signing smart contract is accessed according to the access address to sign a handling fee reduction agreement for the target customer.

[0015] Optionally, the training samples are credit rating evaluation indicators marked with credit rating labels for model training, and the credit rating evaluation indicators specifically include: transaction balance, transaction frequency and historical credit rating.

[0016] Optionally, before uploading the signed fee reduction agreement for the target customer to the blockchain of the blockchain system, the method further includes:

[0017] The signed fee reduction agreement for the target customer is encrypted by a broadcast encryption algorithm.

[0018] In order to achieve the above object, according to another aspect of the present invention, a device for signing a fee reduction agreement based on blockchain is provided, the device comprising:

[0019] A smart contract determination unit, configured to determine a smart contract for signing a handling fee reduction agreement corresponding to the target customer based on the credit rating of the target customer and the correspondence between the preset credit rating and the smart contract for signing a handling fee reduction agreement in the blockchain system;

[0020] The handling fee reduction agreement signing unit is used to sign a smart contract based on the corresponding handling fee reduction agreement and the customer information of the target customer to sign a handling fee reduction agreement for the target customer, and upload the signed handling fee reduction agreement for the target customer to the blockchain of the blockchain system, wherein the transaction system obtains the handling fee reduction agreement for the target customer from the blockchain when executing the transaction of the target customer, and then performs a handling fee reduction operation on the transaction according to the handling fee reduction agreement.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present invention, a computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the above-mentioned blockchain-based method for signing a fee reduction or exemption agreement are implemented.

[0022] In order to achieve the above-mentioned purpose, according to another aspect of the present invention, a computer-readable storage medium is further provided, on which a computer program / instruction is stored, and when the computer program / instruction is executed by a processor, the steps of the above-mentioned blockchain-based method for signing a fee reduction or exemption agreement are implemented.

[0023] The beneficial effects of the present invention are:

[0024] The present invention automatically signs a fee reduction agreement for a target customer through a fee reduction agreement signing smart contract in a blockchain system, and uploads the signed fee reduction agreement for the target customer to the blockchain of the blockchain system. The present invention thus realizes the automatic signing of a fee reduction agreement for the target customer, avoiding the problem of errors and omissions that may occur when manually inputting fee reductions. The present invention also prevents data loss and tampering by uploading the signed fee reduction agreement to the blockchain. When executing a transaction of the target customer, the transaction system obtains the fee reduction agreement for the target customer from the blockchain, and then performs fee reduction operations on the transaction according to the fee reduction agreement, thereby achieving the beneficial effect of accurately and automatically reducing fees during transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0026] Figure 1 It is a flowchart of a method for signing a handling fee reduction or exemption agreement based on blockchain in an embodiment of the present invention;

[0027] Figure 2 is a flow chart of determining the credit rating of a target customer according to an embodiment of the present invention;

[0028] Figure 3 It is a schematic diagram of the architecture of the present invention;

[0029] Figure 4 It is a structural block diagram of a device for signing a handling fee reduction or exemption agreement based on blockchain according to an embodiment of the present invention;

[0030] Figure 5 It is a schematic diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0033] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or apparatus.

[0034] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0035] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.

[0036] It should be noted that the method and device for signing a fee reduction or exemption agreement based on blockchain of the present invention can be used in the financial field, and can also be used in any field other than the financial field. The application field of the method and device for signing a fee reduction or exemption agreement based on blockchain of the present invention is not limited.

[0037] Figure 3 It is a schematic diagram of the system architecture of the present invention, such as Figure 3 As shown, the system architecture of the present invention includes: a consortium chain system and a blockchain system.

[0038] The alliance chain system includes multiple financial institution nodes, each of which corresponds to a financial institution. Each financial institution node acts as a participant in federated learning to train a credit rating prediction model for predicting a customer's credit rating.

[0039] The blockchain system is a system within a financial institution. The blockchain system includes multiple blockchain nodes, all of which are nodes within the financial institution itself. The blockchain system obtains a trained credit rating prediction model from the consortium chain system, and then determines the customer's credit rating based on the credit rating prediction model. The blockchain system stores a smart contract for signing a fee reduction agreement. The blockchain system uses the corresponding fee reduction agreement to sign a smart contract based on the customer's credit rating to sign a fee reduction agreement for the customer, and uploads the signed fee reduction agreement to the blockchain of the blockchain system.

[0040] When a financial institution's transaction system executes a transaction, it can obtain the customer's fee reduction or exemption agreement from the blockchain of the blockchain system, and then automatically reduce or waive the transaction fee based on the fee reduction or exemption agreement.

[0041] like Figure 3 As shown, the financial institution node 1 in the alliance chain system is the node corresponding to financial institution A. Figure 3The blockchain system in the example is the blockchain system of financial institution A. Financial institution A participates in model training through its own financial institution node in the alliance chain system and obtains the finally trained credit rating prediction model. Financial institution A then sends the credit rating prediction model to each blockchain node in the blockchain system of financial institution A. Each blockchain node then determines the customer's credit rating based on the credit rating prediction model, and signs a smart contract using the corresponding fee reduction agreement based on the customer's credit rating to sign a fee reduction agreement for the customer, and uploads the signed fee reduction agreement to the blockchain of the blockchain system.

[0042] It should be noted that the method for signing a transaction fee reduction or exemption agreement based on blockchain in the following embodiments of the present invention is applied to any blockchain node in the above-mentioned blockchain system, that is, the implementing entity of the method for signing a transaction fee reduction or exemption agreement based on blockchain in the following embodiments of the present invention is any blockchain node in the above-mentioned blockchain system.

[0043] Figure 1 is a flowchart of a method for signing a fee reduction or exemption agreement based on blockchain according to an embodiment of the present invention. Figure 1 As shown, in one embodiment of the present invention, the blockchain-based method for signing a fee reduction agreement includes steps S101 to S102.

[0044] Step S101, determining a handling fee reduction agreement signing smart contract corresponding to the target customer according to the target customer's credit rating and the correspondence between the preset credit rating and the handling fee reduction agreement signing smart contract in the blockchain system.

[0045] In the present invention, fee reduction is a fee discount offered by the bank to different types of customers. The discount is generally based on the customer's credit rating. The higher the credit rating, the greater the fee reduction discount. Therefore, the present invention needs to sign fee reduction agreements with different reduction ratios for customers with different credit ratings. Therefore, the present invention sets up a variety of fee reduction agreements to sign smart contracts. Each fee reduction agreement signing smart contract corresponds to a fee reduction ratio, and different credit ratings correspond to different fee reduction ratios. For example, credit ratings include: high, medium and low, and fee reduction ratios include: 3%, 2% and 1%. Among them, the fee reduction ratio corresponding to a high credit rating is 3%, the fee reduction ratio corresponding to a medium credit rating is 2%, and the fee reduction ratio corresponding to a low credit rating is 1%. The present invention sets up three corresponding fee reduction agreements for these three different fee reduction ratios. Before signing a fee reduction agreement according to a smart contract, the present invention needs to determine which fee reduction agreement smart contract to use according to the customer's credit rating to sign.

[0046] In the present invention, a smart contract is developed as a script stored in a blockchain with a unique access address, and is automatically and independently executed in each node when a transaction is assigned to the corresponding address, using the data contained in the triggering transaction as a parameter.

[0047] Step S102, a smart contract is signed according to the corresponding fee reduction agreement and the customer information of the target customer, and a fee reduction agreement is signed for the target customer, and the signed fee reduction agreement for the target customer is uploaded to the blockchain of the blockchain system. When executing the transaction of the target customer, the transaction system obtains the fee reduction agreement for the target customer from the blockchain, and then performs a fee reduction operation on the transaction according to the fee reduction agreement.

[0048] In the present invention, this step obtains the access address of the corresponding fee reduction agreement signing smart contract in the blockchain system, and then accesses the corresponding fee reduction agreement signing smart contract according to the access address to sign a fee reduction agreement for the target customer.

[0049] It can be seen that the present invention automatically signs a fee reduction agreement for the target customer through the smart contract for the fee reduction agreement in the blockchain system, and links the signed fee reduction agreement for the target customer to the blockchain of the blockchain system. Therefore, the present invention realizes the automatic signing of the fee reduction agreement for the target customer, avoiding the problem of errors and omissions in manual input of fee reduction. The present invention links the signed fee reduction agreement to the blockchain to prevent data loss and tampering. When the transaction system executes the transaction of the target customer, it obtains the fee reduction agreement of the target customer from the blockchain, and then reduces the fee for the transaction according to the fee reduction agreement, thereby achieving the beneficial effect of accurate and automatic fee reduction during the transaction.

[0050] Figure 2 is a flow chart of determining the credit rating of a target customer according to an embodiment of the present invention. Figure 2 As shown, in one embodiment of the present invention, the process of determining the credit rating of a target customer includes step S201 and step S202.

[0051] Step S201, obtaining the credit rating evaluation index of the target customer.

[0052] In one embodiment of the present invention, the credit rating evaluation index specifically includes: transaction details, transaction balance, transaction frequency, historical credit rating, etc.

[0053] Step S202, input the credit rating evaluation index into a credit rating prediction model to obtain the credit rating of the target customer output by the credit rating prediction model.

[0054] In one embodiment of the present invention, the blockchain-based method for signing a fee reduction agreement of the present invention further includes:

[0055] The credit rating prediction model is obtained from the alliance chain nodes in the alliance chain system, wherein the alliance chain nodes include financial institution nodes. The credit rating prediction model is obtained by federated learning with each financial institution node as a participant. During the federated learning process, each financial institution node generates a local training sample based on local customer data, and then trains the local model based on the local training samples.

[0056] In one embodiment of the present invention, the training samples are credit rating evaluation indicators marked with credit rating labels for model training, and the credit rating evaluation indicators specifically include: transaction balance, transaction frequency and historical credit rating.

[0057] In one embodiment of the present invention, the credit rating prediction model is trained through multiple rounds of communication iterations of federated learning. In each round of communication iteration, each financial institution node trains the local model based on local training samples. After the training, the trained local model parameters are uploaded to the alliance chain of the alliance chain system. The computing nodes in the alliance chain system obtain the local model parameters of each financial institution node from the alliance chain, and then calculate the global model parameters based on the local model parameters of each financial institution node, and then upload the global model parameters to the alliance chain. Each financial institution node obtains the global model parameters from the alliance chain, and then updates the model parameters of the local model based on the global model parameters.

[0058] Federated learning (FL) is a distributed machine learning framework in which data owners conduct joint training under the coordination of a central server. The original data is retained locally and is not transmitted or shared with any other party, thus breaking down data barriers and achieving data confidentiality. However, the central server of federated learning may become a single point of failure for the security and performance of the entire system, with problems such as privacy leakage and model poisoning. Blockchain technology is a distributed, tamper-proof, traceable, decentralized distributed database that can be used to replace the central server of federated learning and provide a secure data exchange environment for federated learning. In the present invention, a consortium chain system is selected to replace the central server of federated learning to meet the needs of participants for review and relatively stable settings.

[0059] In one embodiment of the present invention, the specific implementation steps of the present invention for training a credit rating prediction model through federated learning are as follows:

[0060] 1. A financial institution node in the alliance chain system publishes the demand for training the model and uploads the initialized model with randomly selected parameters to the alliance chain;

[0061] 2. Each financial institution node (i.e., participant) downloads the initialization model from the alliance chain, collects the customer's credit rating evaluation index data locally, such as transaction details, transaction balance, transaction frequency, historical credit rating, etc., and performs preprocessing (such as using Lagrange interpolation method to handle missing values ​​and delete outliers).

[0062] 3. Each financial institution node (i.e., participant) iterates local model training, updates local model parameters, encrypts the local model parameters using local differential privacy, and then uploads them to the alliance chain.

[0063] The present invention uses noise that obeys Laplace distribution for protection, and the Laplace distribution is as follows:

[0064]

[0065] Where μ and λ are location parameters and scale parameters, and h is the noise variable that obeys the Laplace distribution.

[0066] The parameter data W with added noise is expressed as:

[0067] W′=W+Lap

[0068] The use of local differential privacy can directly protect customers' private data, prevent data leakage from the source, and better maintain data accuracy without causing a decrease in the timeliness or accuracy of the data.

[0069] 4. Aggregate all local model parameters recorded on the alliance chain, use the federation algorithm to calculate the global model parameters, and submit the global model parameters to the alliance chain. The federation algorithm formula is as follows:

[0070]

[0071] Where W t+1 , W t represents the model parameters after the t+1th, tth global update, η is the global model update learning rate, n is the total data of customers participating in this round of training, K is the number of customers participating in this round of training, is the local model of the kth participant selected in the t+1th iteration after training with local data, is the updated gradient of the local data training for the kth participant selected in the t+1th iteration.

[0072] 5. Each financial institution node (i.e., participant) downloads the updated global model parameters from the alliance chain and updates the local model and conducts training again. After the training is completed, the local model update will be uploaded to the alliance chain. The formula for updating the local model is as follows:

[0073]

[0074] In the formula, w t+1 represents the parameters after the t+1th global update, represents the parameters updated by the Kth participant after the t+2th time, K is the number of customers participating in this round of training, η represents the learning rate, Represents the gradient function of the Kth participant.

[0075] 6. Repeat steps 3 and 4 until the federated learning objective function reaches the optimal value or the number of iterations reaches the preset maximum number of iterations. At this point, the training ends and the trained credit rating prediction model is obtained. The objective function formula is as follows:

[0076]

[0077] In the formula, K is the number of customers participating in this round of training, and n represents the total amount of data participating in this round of training. is the predicted loss for the ith customer.

[0078] In an optional embodiment of the present invention, when training a credit rating prediction model through federated learning, the present invention can be trained based on any machine learning model in the prior art, such as a decision tree, a convolutional neural network, an XBG model, an XGBoost model, etc. Depending on the selected model, supervised learning or unsupervised learning can be used for model training.

[0079] In a specific embodiment of the present invention, when training a credit rating prediction model through federated learning, the present invention uses a decision tree for model training, and the training samples used by the present invention are credit rating evaluation indicators for model training with credit ratings marked.

[0080] In one embodiment of the present invention, the credit rating evaluation index specifically includes: transaction details, transaction balance, transaction frequency, historical credit rating, etc.

[0081] In one embodiment of the present invention, the step S102 of signing a smart contract based on the corresponding handling fee reduction agreement and the customer information of the target customer to sign a handling fee reduction agreement for the target customer specifically includes:

[0082] The access address of the corresponding handling fee reduction agreement signing smart contract in the blockchain system is obtained, and then the corresponding handling fee reduction agreement signing smart contract is accessed according to the access address to sign a handling fee reduction agreement for the target customer.

[0083] In one embodiment of the present invention, the smart contract for signing the handling fee reduction agreement is specifically stored in the blockchain of the blockchain system.

[0084] In one embodiment of the present invention, before uploading the signed fee reduction agreement of the target customer to the blockchain of the blockchain system in the above step S102, the method of the present invention further includes:

[0085] The Byzantine fault-tolerant consensus algorithm is used to reach a consensus on the signed fee reduction agreement for the target customer in each blockchain node in the blockchain system.

[0086] After the smart contract is executed, the present invention also uses the Byzantine Fault Tolerant Consensus (PBFT) algorithm to make decisions, propagate, and write the signed fee reduction agreement before uploading it to the blockchain, so as to ensure the correctness and consistency of all node data on the blockchain. The PBFT algorithm is as follows:

[0087] Based on the trust model recommendation value, all consensus nodes are divided into two groups: master node X = {x1, x2, ..., x n}, sub-node Y = {y1, y2, ..., y n}, the trust value of the master node is higher than that of the slave node (the higher the trust value, the less likely the node is a malicious node and the higher the security). The master node is responsible for initiating the consensus process, and the consensus node is responsible for verifying and broadcasting messages. Different from the traditional PBFT algorithm, which defaults to a node's voting weight of 1, the present invention stipulates that the weight Q of the voting of group X nodes is x =2, the weight Q of the Y group nodes when voting y =1, the sum of the voting weights of all nodes is If you have a large malicious node, it can contact other malicious nodes to do evil together. In the traditional PBFT algorithm, it needs to control at least f+1 nodes ( f is the maximum number of malicious nodes allowed by the system in the traditional method, and N is the total number of nodes). However, due to different node weights, if f+1 nodes are all from group Y, it is obvious that the weights controlled by them cannot destroy the consensus system. That is, the division of node weights eliminates the defect that large malicious nodes in the traditional method select nodes with low security to destroy the system network, improves the security of the consensus system, and grouping can reduce the delay of the consensus algorithm. The present invention allows malicious node weights to be When the weighted sum of legitimate information received by the master node is greater than 2F+1, the node writes the information into the blockchain.

[0088] In one embodiment of the present invention, before uploading the signed fee reduction agreement of the target customer to the blockchain of the blockchain system in the above step S102, the method of the present invention further includes:

[0089] The signed fee reduction agreement for the target customer is encrypted by a broadcast encryption algorithm.

[0090] The present invention uses a broadcast encryption algorithm to encrypt the signed fee reduction agreement. Since the contract is deployed on an open and transparent blockchain, all data is publicly visible. To address the problem of data privacy leakage, the present invention uses a broadcast encryption algorithm to solve it. The broadcast encryption algorithm is as follows:

[0091] The present invention uses a broadcast encryption algorithm to achieve that the private data of the transaction is only available to a specific set of users S. First, the elements in S are mapped to L points in a two-dimensional plane, and then a point in the space that is different from the above mapping is taken (set as: through L+1 different points, Lagrange interpolation is used to reconstruct a unique L-order polynomial h s (z) as a safe representation of S, then choose to withdraw h s (z) is different from L points in the set S and is published as ciphertext {(z i ,h s (z i ))} i∈[1,L] . Customer e belonging to a specific user set S will use its own private key (z e ,h s (z e )), and the ciphertext {(z i ,h s (z i ))} i∈[1,L] The polynomial h is correctly reconstructed by Lagrange interpolation s (z), rather than specific users cannot reconstruct correctly. s (z) The formula is as follows:

[0092]

[0093] It can be seen from the above embodiments that the present invention uses blockchain technology and federated learning technology to reduce or exempt handling fees. On the one hand, it avoids the problems of insufficient objectivity and low efficiency under the expert review mechanism, and also avoids the negative impact caused by missed records and delayed records. On the other hand, federated learning uses a local differential privacy algorithm for encryption to avoid customer privacy leakage from the source. The PBFT algorithm implements the division of node weights, which improves the security of the consensus system compared to the traditional PBFT algorithm. At the same time, the use of an optional broadcast encryption algorithm effectively protects customer data privacy, further improving the security of the system.

[0094] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0095] Based on the same inventive concept, an embodiment of the present invention also provides a blockchain-based fee reduction agreement signing device, which can be used to implement the blockchain-based fee reduction agreement signing method described in the above embodiment, as described in the following embodiment. Since the principle of solving the problem by the blockchain-based fee reduction agreement signing device is similar to the blockchain-based fee reduction agreement signing method, the embodiment of the blockchain-based fee reduction agreement signing device can refer to the embodiment of the blockchain-based fee reduction agreement signing method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0096] Figure 4 is a structural block diagram of a device for signing a fee reduction or exemption agreement based on blockchain according to an embodiment of the present invention. Figure 4 As shown, in one embodiment of the present invention, the blockchain-based fee reduction and exemption agreement signing device of the present invention includes:

[0097] A smart contract determination unit 1 is used to determine a smart contract for signing a handling fee reduction agreement corresponding to the target customer based on the credit rating of the target customer and the correspondence between the preset credit rating and the smart contract for signing a handling fee reduction agreement in the blockchain system;

[0098] The fee reduction agreement signing unit 2 is used to sign a smart contract based on the corresponding fee reduction agreement and the customer information of the target customer to sign a fee reduction agreement for the target customer, and upload the signed fee reduction agreement for the target customer to the blockchain of the blockchain system. When the transaction system executes the transaction of the target customer, it obtains the fee reduction agreement for the target customer from the blockchain, and then performs a fee reduction operation on the transaction according to the fee reduction agreement.

[0099] In one embodiment of the present invention, the blockchain-based fee reduction and exemption agreement signing device of the present invention further includes:

[0100] A credit rating evaluation index acquisition unit, used to acquire the credit rating evaluation index of the target customer;

[0101] The credit rating prediction unit is used to input the credit rating evaluation index into the credit rating prediction model to obtain the credit rating of the target customer output by the credit rating prediction model.

[0102] In one embodiment of the present invention, the blockchain-based fee reduction and exemption agreement signing device of the present invention further includes:

[0103] A credit rating prediction model acquisition unit is used to obtain the credit rating prediction model from the alliance chain nodes in the alliance chain system, wherein the alliance chain nodes include financial institution nodes, and the credit rating prediction model is obtained by federated learning with each financial institution node as a participant. During the federated learning process, each financial institution node generates a local training sample based on local customer data, and then trains the local model based on the local training samples.

[0104] In one embodiment of the present invention, the credit rating prediction model is trained through multiple rounds of communication iterations of federated learning. In each round of communication iteration, each financial institution node trains the local model based on local training samples. After the training, the trained local model parameters are uploaded to the alliance chain of the alliance chain system. The computing nodes in the alliance chain system obtain the local model parameters of each financial institution node from the alliance chain, and then calculate the global model parameters based on the local model parameters of each financial institution node, and then upload the global model parameters to the alliance chain. Each financial institution node obtains the global model parameters from the alliance chain, and then updates the model parameters of the local model based on the global model parameters.

[0105] In one embodiment of the present invention, the fee reduction agreement signing unit 2 is specifically used to obtain the access address of the corresponding fee reduction agreement signing smart contract in the blockchain system, and then access the corresponding fee reduction agreement signing smart contract according to the access address to sign the fee reduction agreement for the target customer.

[0106] In one embodiment of the present invention, the blockchain-based fee reduction and exemption agreement signing device of the present invention further includes:

[0107] The consensus unit is used to reach a consensus on the signed fee reduction agreement for the target customer on each blockchain node in the blockchain system through a Byzantine fault-tolerant consensus algorithm before uploading the signed fee reduction agreement for the target customer to the blockchain of the blockchain system.

[0108] In one embodiment of the present invention, the blockchain-based fee reduction and exemption agreement signing device of the present invention further includes:

[0109] The encryption processing unit is used to encrypt the signed fee reduction and exemption agreement for the target customer by broadcasting an encryption algorithm before uploading the signed fee reduction and exemption agreement for the target customer to the blockchain of the blockchain system.

[0110] In order to achieve the above object, according to another aspect of the present application, a computer device is also provided. Figure 5 As shown, the computer device includes a memory, a processor, a communication interface and a communication bus. A computer program that can be executed on the processor is stored in the memory. When the processor executes the computer program, the steps in the above-mentioned embodiment method are implemented.

[0111] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0112] The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and units, such as the corresponding program units in the above method embodiments of the present invention. The processor executes various functional applications of the processor and works data processing by running the non-transitory software programs, instructions and modules stored in the memory, that is, implementing the method in the above method embodiments.

[0113] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0114] The one or more units are stored in the memory, and when executed by the processor, the method in the above embodiment is performed.

[0115] The specific details of the above-mentioned computer device can be understood by referring to the corresponding related descriptions and effects in the above-mentioned embodiments, and will not be repeated here.

[0116] In order to achieve the above purpose, according to another aspect of the present application, a computer-readable storage medium is also provided, wherein the computer-readable storage medium stores a computer program, and the computer program implements the steps in the above-mentioned blockchain-based fee reduction and exemption agreement signing method when executed in a computer processor. Those skilled in the art can understand that the implementation of all or part of the process in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the process of the embodiment of each method as described above when executed. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0117] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is also provided, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned blockchain-based method for signing a fee reduction or exemption agreement.

[0118] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for signing a fee reduction agreement based on blockchain, characterized in that: include: Determine the smart contract for signing a handling fee reduction agreement corresponding to the target customer based on the target customer's credit rating and the correspondence between the preset credit rating and the smart contract for signing a handling fee reduction agreement in the blockchain system; A smart contract is signed according to the corresponding fee reduction agreement and the customer information of the target customer. A fee reduction agreement is signed for the target customer, and the signed fee reduction agreement for the target customer is uploaded to the blockchain of the blockchain system. When executing the transaction of the target customer, the transaction system obtains the fee reduction agreement for the target customer from the blockchain, and then performs a fee reduction operation on the transaction according to the fee reduction agreement.

2. The method for signing a fee reduction agreement based on blockchain according to claim 1, characterized in that: Also includes: Obtaining credit rating evaluation indicators of the target customer; The credit rating evaluation index is input into a credit rating prediction model to obtain the credit rating of the target customer output by the credit rating prediction model.

3. The method for signing a fee reduction agreement based on blockchain according to claim 2, characterized in that: Also includes: The credit rating prediction model is obtained from the alliance chain nodes in the alliance chain system, wherein the alliance chain nodes include financial institution nodes. The credit rating prediction model is obtained by federated learning with each financial institution node as a participant. During the federated learning process, each financial institution node generates a local training sample based on local customer data, and then trains the local model based on the local training samples.

4. The method for signing a fee reduction agreement based on blockchain according to claim 3 is characterized in that: The credit rating prediction model is trained through multiple rounds of communication iterations of federated learning. In each round of communication iteration, each financial institution node trains the local model based on the local training samples. After the training, the trained local model parameters are uploaded to the alliance chain of the alliance chain system. The computing nodes in the alliance chain system obtain the local model parameters of each financial institution node from the alliance chain, and then calculate the global model parameters based on the local model parameters of each financial institution node, and then upload the global model parameters to the alliance chain. Each financial institution node obtains the global model parameters from the alliance chain, and then updates the model parameters of the local model based on the global model parameters.

5. The method for signing a fee reduction agreement based on blockchain according to claim 1, characterized in that: The step of signing a smart contract based on the corresponding handling fee reduction agreement and the customer information of the target customer to sign a handling fee reduction agreement for the target customer specifically includes: The access address of the corresponding handling fee reduction agreement signing smart contract in the blockchain system is obtained, and then the corresponding handling fee reduction agreement signing smart contract is accessed according to the access address to sign a handling fee reduction agreement for the target customer.

6. According to the blockchain-based fee reduction and exemption agreement signing method of claim 3, the training samples are credit rating evaluation indicators for model training marked with credit rating labels, and the credit rating evaluation indicators specifically include: transaction balance, transaction frequency and historical credit rating.

7. The method for signing a fee reduction agreement based on blockchain according to claim 1, characterized in that: Before uploading the signed fee reduction agreement for the target customer to the blockchain of the blockchain system, it also includes: The signed fee reduction agreement for the target customer is encrypted by a broadcast encryption algorithm.

8. A blockchain-based device for signing a fee reduction agreement, characterized in that: include: A smart contract determination unit, configured to determine a smart contract for signing a handling fee reduction agreement corresponding to the target customer based on the credit rating of the target customer and the correspondence between the preset credit rating and the smart contract for signing a handling fee reduction agreement in the blockchain system; The handling fee reduction agreement signing unit is used to sign a smart contract based on the corresponding handling fee reduction agreement and the customer information of the target customer to sign a handling fee reduction agreement for the target customer, and upload the signed handling fee reduction agreement for the target customer to the blockchain of the blockchain system, wherein the transaction system obtains the handling fee reduction agreement for the target customer from the blockchain when executing the transaction of the target customer, and then performs a handling fee reduction operation on the transaction according to the handling fee reduction agreement.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images