Cross-border Financial Declaration Data Verification Method and System Based on Blockchain

Abstract

The present invention discloses a cross-border financial declaration data verification method and system based on blockchain. The method includes: obtaining the data content and declaration parameters of the cross-border financial declaration data to be verified; screening out a target verification neural network from multiple candidate verification neural networks according to the declaration parameters and a preset parameter screening algorithm; pulling the historical on-chain data corresponding to the data content from a target blockchain according to the declaration parameters and a preset parameter association algorithm; inputting the data content and the historical on-chain data into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data; and the data verification result is used to indicate the authenticity and rationality corresponding to the cross-border financial declaration data. It can be seen that the present invention can more efficiently and accurately verify the cross-border financial declaration data, reducing the costs and errors caused by manual work.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a cross-border financial declaration data verification method and system based on a blockchain. Background Art

[0002] With the development of the blockchain, more and more industries have started to apply the blockchain. In the financial industry, the blockchain has attracted more and more enterprises and banks to store transaction information on the blockchain due to its characteristics of information being non-forgeable and non-tamperable. In the cross-border financial transaction declaration process, most of the existing technologies still use simple data rules and manual reviews, without fully considering the use of blockchain information and transaction data and combining neural network algorithms to achieve more efficient and accurate declaration verification. Therefore, its verification efficiency is too low and the cost is too high. It can be seen that the existing technology has defects and urgently needs to be solved. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a cross-border financial declaration data verification method and system based on a blockchain, which can more efficiently and accurately verify cross-border financial declaration data, and reduce the costs and errors caused by humans.

[0004] To solve the above technical problem, in the first aspect of the present invention, a cross-border financial declaration data verification method based on a blockchain is disclosed, and the method includes:

[0005] Obtain the data content and declaration parameters of the cross-border financial declaration data to be verified;

[0006] According to the declaration parameters and a preset parameter screening algorithm, select a target verification neural network from multiple candidate verification neural networks;

[0007] According to the declaration parameters and a preset parameter association algorithm, pull the historical on-chain data corresponding to the data content from the target blockchain;

[0008] Input the data content and the historical on-chain data into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data; the data verification result is used to indicate the authenticity and rationality corresponding to the cross-border financial declaration data.

[0009] As an optional implementation manner, in the first aspect of the present invention, the declaration parameters include transaction subject information, transaction channel bank information, transaction time information, transaction location information, and transaction industry type information.

[0010] As an optional implementation manner, in the first aspect of the present invention, screening out the target verification neural network from multiple candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm includes:

[0011] For each candidate verification neural network, obtain the training data set and historical input data corresponding to the candidate verification neural network;

[0012] Count the declared parameters corresponding to all training declared data in the training data set to obtain a training declared parameter set;

[0013] Count the declared parameters corresponding to all input declared data in the historical input data to obtain a historical input declared parameter set;

[0014] Calculate a first similarity between the training declared parameter set and the declared parameters;

[0015] Calculate a second similarity between the historical input declared parameter set and the declared parameters;

[0016] Calculate a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity;

[0017] Determine the candidate verification neural network with the highest network priority parameter as the target verification neural network.

[0018] As an optional implementation manner, in the first aspect of the present invention, calculating the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity includes:

[0019] Calculate a weighted sum average of the first similarity and the second similarity to obtain a network priority parameter corresponding to the candidate verification neural network; wherein, the weighted calculation weights corresponding to the first similarity include a first weight and a second weight; the first weight is proportional to the total data volume of all the training declared data corresponding to the corresponding training data set; the second weight is proportional to the prediction accuracy rate of the candidate verification neural network in the verification stage; wherein, the weighted calculation weights corresponding to the second similarity include a third weight and a fourth weight; the third weight is proportional to the total data volume of all the input declared data in the corresponding historical input data; the fourth weight is proportional to the total number of times the candidate verification neural network is selected as the target verification neural network in all historical time periods.

[0020] As an optional implementation manner, in the first aspect of the present invention, pulling the historical on-chain data corresponding to the data content from the target blockchain according to the declared parameters and a preset parameter association algorithm includes:

[0021] Determine all the blockchains associated with each parameter data in the declared parameters in the blockchain set to obtain multiple candidate blockchains;

[0022] According to the similarity algorithm of blockchain data, calculate the blockchain priority parameter of each candidate blockchain;

[0023] Screen out the candidate blockchains with blockchain priority parameters greater than the parameter threshold from all the candidate blockchains to obtain multiple target blockchains;

[0024] According to the declared parameters and the data content, pull historical on-chain data on each target blockchain.

[0025] As an optional implementation manner, in the first aspect of the present invention, the calculating the blockchain priority parameter of each candidate blockchain according to the similarity algorithm of blockchain data includes:

[0026] For each candidate blockchain, obtain the associated blockchain data corresponding to each parameter data in the candidate blockchain;

[0027] Calculate the third similarity between the associated blockchain data of the candidate blockchain and the associated blockchain data of any other candidate blockchain;

[0028] Calculate the average value of the third similarities between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0029] As an optional implementation manner, in the first aspect of the present invention, the pulling historical on-chain data on each target blockchain according to the declared parameters and the data content includes:

[0030] For each target blockchain, input the declared parameters and the data content into the data pulling contract on the target blockchain to obtain the corresponding enterprise bank uploaded data; the data pulling contract is used to analyze the declared parameters and the data content to obtain the corresponding enterprise association information, bank association information, and payment association information, and based on this, match the corresponding enterprise bank uploaded data in all blockchain data;

[0031] Based on the pre-stored private certificate and temporary certificate, decrypt the enterprise bank uploaded data to obtain decrypted data;

[0032] Determine the decrypted data corresponding to all the target blockchains as the historical on-chain data.

[0033] As an optional implementation manner, in the first aspect of the present invention, the target verification neural network is a random forest model, which is trained by a training data set including a plurality of training declaration data and corresponding declaration parameter annotations, historical on-chain data annotations, and data verification result annotations.

[0034] The second aspect of the embodiments of the present invention discloses a cross-border financial declaration data verification system based on a blockchain. The system includes:

[0035] An acquisition module, configured to acquire the data content and declaration parameters of the cross-border financial declaration data to be verified;

[0036] A screening module, configured to screen out a target verification neural network from a plurality of candidate verification neural networks according to the declaration parameters and a preset parameter screening algorithm;

[0037] A pulling module, configured to pull the historical on-chain data corresponding to the data content from a target blockchain according to the declaration parameters and a preset parameter association algorithm;

[0038] A verification module, configured to input the data content and the historical on-chain data into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data; the data verification result is used to indicate the authenticity and rationality corresponding to the cross-border financial declaration data.

[0039] As an optional implementation manner, in the second aspect of the present invention, the declaration parameters include transaction subject information, transaction channel bank information, transaction time information, transaction location information, and transaction industry type information.

[0040] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the screening module screens out a target verification neural network from a plurality of candidate verification neural networks according to the declaration parameters and a preset parameter screening algorithm includes:

[0041] For each candidate verification neural network, acquire the training data set and historical input data corresponding to the candidate verification neural network;

[0042] Statistically analyze the declaration parameters corresponding to all the training declaration data in the training data set to obtain a training declaration parameter set;

[0043] Statistically analyze the declaration parameters corresponding to all the input declaration data in the historical input data to obtain a historical input declaration parameter set;

[0044] Calculate a first similarity between the training declaration parameter set and the declaration parameters;

[0045] Calculate the second similarity between the set of historical input declaration parameters and the declaration parameters;

[0046] Calculate the network priority parameters corresponding to the candidate verification neural network according to the first similarity and the second similarity;

[0047] Determine the candidate verification neural network with the highest network priority parameters as the target verification neural network.

[0048] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the screening module calculates the network priority parameters corresponding to the candidate verification neural network according to the first similarity and the second similarity includes:

[0049] Calculate the weighted sum average of the first similarity and the second similarity to obtain the network priority parameters corresponding to the candidate verification neural network; wherein, the weighted calculation weights corresponding to the first similarity include a first weight and a second weight; the first weight is proportional to the total data volume of all the training declaration data corresponding to the training data set; the second weight is proportional to the prediction accuracy rate of the candidate verification neural network in the verification stage; wherein, the weighted calculation weights corresponding to the second similarity include a third weight and a fourth weight; the third weight is proportional to the total data volume of all the input declaration data in the corresponding historical input data; the fourth weight is proportional to the total number of times the candidate verification neural network is selected as the target verification neural network in all historical time periods.

[0050] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the pulling module pulls the historical on-chain data corresponding to the data content from the target blockchain according to the declaration parameters and a preset parameter association algorithm includes:

[0051] Determine all the blockchains associated with each parameter data in the declaration parameters in the blockchain set to obtain a plurality of candidate blockchains;

[0052] Calculate the blockchain priority parameters of each candidate blockchain according to the blockchain data similarity algorithm;

[0053] Screen out all the candidate blockchains with blockchain priority parameters greater than the parameter threshold from all the candidate blockchains to obtain a plurality of target blockchains;

[0054] Pull the historical on-chain data on each target blockchain according to the declaration parameters and the data content.

[0055] As an alternative embodiment, in the second aspect of the present invention, the specific manner in which the pulling module calculates the blockchain priority parameter of each candidate blockchain according to the similarity algorithm of blockchain data includes:

[0056] For each candidate blockchain, obtain the associated blockchain data corresponding to each parameter data in the candidate blockchain;

[0057] Calculate the third similarity between the associated blockchain data of the candidate blockchain and the associated blockchain data of any other candidate blockchain;

[0058] Calculate the average value of the third similarities of the candidate blockchain with all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0059] As an alternative embodiment, in the second aspect of the present invention, the specific manner in which the pulling module pulls historical on-chain data on each target blockchain according to the declared parameters and the data content includes:

[0060] For each target blockchain, input the declared parameters and the data content into the data pulling contract on the target blockchain to obtain the corresponding enterprise bank upload data; the data pulling contract is used to analyze the declared parameters and the data content to obtain the corresponding enterprise association information, bank association information, and payment association information, and based on this, match the corresponding enterprise bank upload data in all blockchain data;

[0061] Based on the pre-stored private certificate and temporary certificate, decrypt the enterprise bank upload data to obtain decrypted data;

[0062] Determine the decrypted data corresponding to all the target blockchains as historical on-chain data.

[0063] As an alternative embodiment, in the second aspect of the present invention, the target verification neural network is a random forest model, which is trained through a training data set including multiple training declaration data and corresponding declared parameter annotations, historical on-chain data annotations, and data verification result annotations.

[0064] The third aspect of the present invention discloses another cross-border financial declaration data verification system based on blockchain, and the system includes:

[0065] A memory storing executable program code;

[0066] A processor coupled to the memory;

[0067] The processor calls the executable program code stored in the memory and executes some or all of the steps in the method for verifying cross-border financial declaration data based on blockchain disclosed in the first aspect of the present invention.

[0068] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which are used to execute some or all of the steps in the method for verifying cross-border financial declaration data based on blockchain disclosed in the first aspect of the present invention when the computer instructions are called.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] The present invention can screen out a suitable target verification neural network from multiple candidate verification neural networks according to the declaration parameters and the parameter screening algorithm, then pull the historical on-chain data corresponding to the declaration data content from the target blockchain according to the declaration parameters and the parameter association algorithm, and realize data verification based on the target verification neural network and the historical on-chain data, so as to be able to more efficiently and accurately verify cross-border financial declaration data, reduce the costs and errors caused by manual work. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0072] Figure 1 is a schematic flowchart of a method for verifying cross-border financial declaration data based on blockchain disclosed in an embodiment of the present invention.

[0073] Figure 2 is a schematic structural diagram of a system for verifying cross-border financial declaration data based on blockchain disclosed in an embodiment of the present invention.

[0074] Figure 3 is a schematic structural diagram of another system for verifying cross-border financial declaration data based on blockchain disclosed in an embodiment of the present invention.

[0075] Figure 4 is a schematic functional diagram of a blockchain for cross-border financial declaration disclosed in an embodiment of the present invention.

[0076] Figure 5 is a schematic structural diagram of a cross-border financial declaration system based on blockchain disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0077] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0078] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0079] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0080] The present invention discloses a cross-border financial declaration data verification method and system based on blockchain, which can screen out a suitable target verification neural network from multiple candidate verification neural networks according to the declaration parameters and parameter screening algorithms, and then pull the historical on-chain data corresponding to the declaration data content from the target blockchain according to the declaration parameters and parameter association algorithms, and implement data verification based on the target verification neural network and the historical on-chain data, so as to be able to more efficiently and accurately verify cross-border financial declaration data, and reduce the costs and errors caused by manual work. The following will be described in detail respectively.

[0081] Embodiment 1

[0082] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a cross-border financial declaration data verification method based on blockchain disclosed in the embodiments of the present invention. Among them, Figure 1 the described cross-border financial declaration data verification method based on blockchain can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 1As shown in the figure, the blockchain-based cross-border financial declaration data verification method may include the following operations:

[0083] 101. Obtain the data content and declaration parameters of the cross-border financial declaration data to be verified.

[0084] 102. According to the declaration parameters and a preset parameter screening algorithm, screen out a target verification neural network from multiple candidate verification neural networks.

[0085] 103. According to the declaration parameters and a preset parameter association algorithm, pull the historical on-chain data corresponding to the data content from the target blockchain.

[0086] 104. Input the data content and the historical on-chain data into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data.

[0087] Optionally, the data verification result is used to indicate the authenticity and reasonableness corresponding to the cross-border financial declaration data.

[0088] It can be seen that the above invention embodiments can screen out a suitable target verification neural network from multiple candidate verification neural networks according to the declaration parameters and the parameter screening algorithm, then pull the historical on-chain data corresponding to the declaration data content from the target blockchain according to the declaration parameters and the parameter association algorithm, and implement data verification based on the target verification neural network and the historical on-chain data, so as to be able to more efficiently and accurately verify the cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0089] As an optional embodiment, among the above steps, the declaration parameters include transaction subject information, transaction channel bank information, transaction time information, transaction location information, and transaction industry type information.

[0090] Optionally, the declaration parameters can also be obtained by analyzing or predicting the data content through a data analysis algorithm. For example, the cross-border financial declaration data may include list data, customs declaration data, quota data, and document data, and these data may be in text format, picture format, or other data formats, and it is necessary to analyze the declaration parameters in these declaration data through a pre-trained data analysis algorithm model.

[0091] It can be seen that through the above optional embodiment, the specific content of the declaration parameters is defined, which can fully represent the characteristics and information of the corresponding cross-border financial transactions, and is subsequently used to accurately screen the verification model and pull the on-chain data, assisting in more efficiently and accurately verifying the cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0092] As an optional embodiment, in the above steps, screening the target verification neural network from multiple candidate verification neural networks according to the declared parameters and the preset parameter screening algorithm includes:

[0093] For each candidate verification neural network, obtain the training data set and historical input data corresponding to the candidate verification neural network;

[0094] Statistically analyze the declared parameters corresponding to all training declared data in the training data set to obtain a training declared parameter set;

[0095] Statistically analyze the declared parameters corresponding to all input declared data in the historical input data to obtain a historical input declared parameter set;

[0096] Calculate the first similarity between the training declared parameter set and the declared parameters;

[0097] Calculate the second similarity between the historical input declared parameter set and the declared parameters;

[0098] Calculate the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity;

[0099] Determine the candidate verification neural network with the highest network priority parameter as the target verification neural network.

[0100] It can be seen that through the above optional embodiment, the adaptation degree between the candidate verification neural network and the current declared data can be calculated based on the declared parameters in the training data set and historical input data of the candidate verification neural network, so as to screen out the target verification neural network most suitable for verifying the current declared data, which is subsequently used to accurately verify the declared data, assisting in more efficient and accurate data verification of cross-border financial declared data and reducing the costs and errors caused by manual work.

[0101] As an optional embodiment, in the above steps, calculating the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity includes:

[0102] Calculate the weighted sum average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; optionally, among them, the weighted calculation weights corresponding to the first similarity include a first weight and a second weight; the first weight is proportional to the total data volume of all training declared data corresponding to the corresponding training data set; the second weight is proportional to the prediction accuracy rate of the candidate verification neural network in the verification stage; among them, the weighted calculation weights corresponding to the second similarity include a third weight and a fourth weight; the third weight is proportional to the total data volume of all input declared data in the corresponding historical input data; the fourth weight is proportional to the total number of times the candidate verification neural network is selected as the target verification neural network in all historical time periods.

[0103] It can be seen that through the above optional embodiments, it is possible to accurately measure the importance of the similarities corresponding to the training data set and the historical input data respectively based on the pre-set weighted calculation weights, and calculate accurate network priority parameters based on this to screen out the target verification neural network most suitable for verifying the current declared data, and then use it to accurately verify the declared data, assisting in more efficient and accurate data verification of cross-border financial declaration data, and reducing the costs and errors caused by manual work.

[0104] As an optional embodiment, in the above steps, according to the declaration parameters and the pre-set parameter association algorithm, pulling the historical on-chain data corresponding to the data content from the target blockchain includes:

[0105] Determining all the blockchains associated with each parameter data in the declaration parameters in the blockchain set to obtain multiple candidate blockchains;

[0106] Calculating the blockchain priority parameter of each candidate blockchain according to the similarity algorithm of blockchain data;

[0107] Screening out the candidate blockchains with blockchain priority parameters greater than the parameter threshold from all candidate blockchains to obtain multiple target blockchains;

[0108] Pulling the historical on-chain data on each target blockchain according to the declaration parameters and the data content.

[0109] It can be seen that through the above optional embodiments, it is possible to screen out the blockchain storing the most relevant transactions or the most similar transaction data from multiple candidate blockchains based on parameter association and data similarity algorithms, so as to be able to pull the most effective and largest amount of historical on-chain data for data verification in the future, assisting in more efficient and accurate data verification of cross-border financial declaration data, and reducing the costs and errors caused by manual work.

[0110] As an optional embodiment, in the above steps, calculating the blockchain priority parameter of each candidate blockchain according to the similarity algorithm of blockchain data includes:

[0111] For each candidate blockchain, obtaining the associated blockchain data corresponding to each parameter data in the candidate blockchain;

[0112] Calculating the third similarity between the associated blockchain data of the candidate blockchain and the associated blockchain data of any other candidate blockchain;

[0113] Calculating the average value of the third similarities between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0114] It can be seen that through the above optional embodiments, the blockchain priority parameters can be accurately obtained by calculating the data similarity between the candidate blockchain and other blockchains, so as to subsequently assist in screening out the blockchain storing the most relevant transactions or the most similar transaction data, and assist in more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0115] As an optional embodiment, in the above steps, according to the declaration parameters and data content, pulling historical on-chain data on each target blockchain includes:

[0116] For each target blockchain, input the declaration parameters and data content into the data pulling contract on the target blockchain to obtain the corresponding enterprise bank uploaded data; optionally, the data pulling contract is used to analyze the declaration parameters and data content to obtain the corresponding enterprise association information, bank association information, and payment association information, and based on this, match the corresponding enterprise bank uploaded data in all blockchain data;

[0117] Based on the pre-stored private certificate and temporary certificate, decrypt the enterprise bank uploaded data to obtain decrypted data;

[0118] Determine the decrypted data corresponding to all target blockchains as the historical on-chain data.

[0119] It can be seen that through the above optional embodiments, it is possible to pull all associated on-chain data through the data pulling contract on the blockchain, and decrypt it based on the pre-stored certificate to obtain the most comprehensive and accurate on-chain data, so as to subsequently assist in more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0120] As an optional embodiment, in the above steps, the target verification neural network is a random forest model, which is trained through a training data set including multiple training declaration data and corresponding declaration parameter annotations, historical on-chain data annotations, and data verification result annotations.

[0121] It can be seen that through the above optional embodiments, the model type and training details of the target verification neural network are defined, which can capture the data association features between the declaration data and the historical blockchain on-chain data to achieve verification between data at different times and spaces, and achieve more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0122] In a specific implementation scheme, in order to implement the verification method or system in the present invention, a blockchain for cross-border financial declaration is developed, and its functions can refer to Figure 4 , specifically, the blockchain includes multiple contracts:

[0123] 1. Data on-chain contract: Different enterprises and banks declare data or transaction data on the chain with different certificate identities.

[0124] 2. Quota on-chain contract: Enterprises upload and update quota data through private identity certificates, and the blockchain data maintains and traces data in different versions.

[0125] 3. Bank data verification contract: Banks pull and decrypt data in the blockchain through private certificates and enterprise temporary certificates to verify the data.

[0126] More specifically, a cross-border financial declaration system based on the above blockchain is developed, and its architecture can refer to Figure 5 , including enterprise parties, bank parties, and market procurement platform parties. The data verification technology in the present invention is implemented as a risk model therein to be used for verifying and risk analyzing declaration data. Specifically, the operation steps of the risk model can include:

[0127] 1. Collect and sort out relevant data involved in declaration verification, including list data, customs declaration data, quota data, etc.;

[0128] 2. Extract and select features related to declaration data verification from a large amount of data, and use machine learning algorithms for feature selection, model construction, and construction training;

[0129] 3. Construct an automatic declaration model based on the selected features, which can intelligently submit declaration information and simultaneously intelligently verify relevant declaration data during submission;

[0130] 4. According to the cross-border financial risk model algorithm, use list data, quota data, etc. for blockchain encryption on the chain and data traceability of the multi-party manual operation system.

[0131] The advantages of the above specific implementation include:

[0132] 1. Through blockchain cross-chain technology, connect to the data of the cross-border trade public service platform, change the traditional manual declaration verification to the data cross-border financial risk model algorithm, and realize the comprehensive analysis and authenticity verification of enterprise cross-border trade transaction data.

[0133] 2. Through artificial intelligence, the declaration verification model makes intelligent declarations for cross-border finance, greatly saving the time of enterprise and bank staff, and improving the accuracy of verification at the same time.

[0134] 3. Through blockchain technology, make a record of system data and operation data, improving the authenticity of data traceability and verification.

[0135] 4. The temporary key technology ensures the security of data.

[0136] Embodiment 2

[0137] Please refer to Figure 2 , Figure 2 , which is a schematic structural diagram of a cross-border financial declaration data verification system based on blockchain disclosed in an embodiment of the present invention. Among them, Figure 2 The described cross-border financial declaration data verification system based on blockchain can be applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 2 shown, the cross-border financial declaration data verification system based on blockchain may include:

[0138] An acquisition module 201, configured to acquire the data content and declaration parameters of the cross-border financial declaration data to be verified.

[0139] A screening module 202, configured to screen out a target verification neural network from multiple candidate verification neural networks according to the declaration parameters and a preset parameter screening algorithm.

[0140] A pulling module 203, configured to pull the historical on-chain data corresponding to the data content from the target blockchain according to the declaration parameters and a preset parameter association algorithm.

[0141] A verification module 204, configured to input the data content and the historical on-chain data into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data.

[0142] Optionally, the data verification result is used to indicate the authenticity and reasonableness corresponding to the cross-border financial declaration data.

[0143] It can be seen that the above-mentioned invention embodiments can screen out a suitable target verification neural network from multiple candidate verification neural networks according to the declaration parameters and the parameter screening algorithm, then pull the historical on-chain data corresponding to the declaration data content from the target blockchain according to the declaration parameters and the parameter association algorithm, and implement data verification based on the target verification neural network and the historical on-chain data, so as to be able to more efficiently and accurately verify the cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0144] As an optional embodiment, the declaration parameters include transaction subject information, transaction channel bank information, transaction time information, transaction location information, and transaction industry type information.

[0145] It can be seen that through the above optional embodiments, the specific content of the declared parameters is defined, which can fully characterize the characteristics and information of the corresponding cross-border financial transactions, and is subsequently used to accurately screen the verification model and retrieve the data uploaded to the blockchain, assisting in more efficient and accurate data verification of cross-border financial declaration data, and reducing the costs and errors caused by manual operations.

[0146] As an optional embodiment, the specific manner in which the screening module screens out the target verification neural network from multiple candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm includes:

[0147] For each candidate verification neural network, obtain the training data set and historical input data corresponding to the candidate verification neural network;

[0148] Count the declared parameters corresponding to all the training declaration data in the training data set to obtain a training declaration parameter set;

[0149] Count the declared parameters corresponding to all the input declaration data in the historical input data to obtain a historical input declaration parameter set;

[0150] Calculate the first similarity between the training declaration parameter set and the declared parameters;

[0151] Calculate the second similarity between the historical input declaration parameter set and the declared parameters;

[0152] Calculate the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity;

[0153] Determine the candidate verification neural network with the highest network priority parameter as the target verification neural network.

[0154] It can be seen that through the above optional embodiments, the adaptation degree between the candidate verification neural network and the current declaration data can be calculated based on the declared parameters in the training data set and historical input data of the candidate verification neural network, so as to screen out the target verification neural network most suitable for verifying the current declaration data, which is subsequently used to accurately verify the declaration data, assisting in more efficient and accurate data verification of cross-border financial declaration data, and reducing the costs and errors caused by manual operations.

[0155] As an optional embodiment, the specific manner in which the screening module calculates the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity includes:

[0156] Calculate the weighted sum average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; optionally, among them, the weighted calculation weights corresponding to the first similarity include a first weight and a second weight; the first weight is proportional to the total data volume of all training declaration data corresponding to the corresponding training data set; the second weight is proportional to the prediction accuracy of the candidate verification neural network in the verification stage; among them, the weighted calculation weights corresponding to the second similarity include a third weight and a fourth weight; the third weight is proportional to the total data volume of all input declaration data in the corresponding historical input data; the fourth weight is proportional to the total number of times the candidate verification neural network is selected as the target verification neural network in all historical time periods.

[0157] It can be seen that through the above optional embodiments, it is possible to accurately measure the importance of the similarities corresponding to the training data set and the historical input data based on the preset weighted calculation weights, and calculate accurate network priority parameters based on this to screen out the target verification neural network most suitable for verifying the current declaration data, and then use it to accurately verify the declaration data, assisting in more efficient and accurate data verification of cross-border financial declaration data, and reducing the costs and errors caused by manual work.

[0158] As an optional embodiment, the specific manner in which the pulling module pulls the historical on-chain data corresponding to the data content from the target blockchain according to the declaration parameters and the preset parameter association algorithm includes:

[0159] Determine all blockchains associated with each parameter data in the declaration parameters in the blockchain set to obtain multiple candidate blockchains;

[0160] Calculate the blockchain priority parameter of each candidate blockchain according to the blockchain data similarity algorithm;

[0161] Screen out the candidate blockchains whose blockchain priority parameters are greater than the parameter threshold from all candidate blockchains to obtain multiple target blockchains;

[0162] Pull the historical on-chain data on each target blockchain according to the declaration parameters and the data content.

[0163] It can be seen that through the above optional embodiments, it is possible to screen out the blockchain storing the most relevant transactions or the most similar transaction data from multiple candidate blockchains based on the parameter association and data similarity algorithms, so as to be able to pull the most effective and the largest number of historical on-chain data for data verification in the follow-up, assisting in more efficient and accurate data verification of cross-border financial declaration data, and reducing the costs and errors caused by manual work.

[0164] As an optional embodiment, the specific manner in which the pulling module calculates the blockchain priority parameter of each candidate blockchain according to the similarity algorithm of blockchain data includes:

[0165] For each candidate blockchain, obtain the associated blockchain data corresponding to each parameter data in the candidate blockchain;

[0166] Calculate the third similarity between the associated blockchain data of the candidate blockchain and the associated blockchain data of any other candidate blockchain;

[0167] Calculate the average value of the third similarities between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0168] It can be seen that through the above optional embodiments, the blockchain priority parameter can be accurately obtained by calculating the data similarity between the candidate blockchain and other blockchains, so as to assist in screening out the blockchain storing the most relevant transactions or the most similar transaction data in the subsequent process, and assist in realizing more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0169] As an optional embodiment, the specific manner in which the pulling module pulls historical on-chain data on each target blockchain according to the declaration parameter and data content includes:

[0170] For each target blockchain, input the declaration parameter and data content into the data pulling contract on the target blockchain to obtain the corresponding enterprise bank uploaded data; optionally, the data pulling contract is used to analyze the declaration parameter and data content to obtain the corresponding enterprise association information, bank association information, and payment association information, and based on this, match the corresponding enterprise bank uploaded data in all blockchain data;

[0171] Based on the pre-stored private certificate and temporary certificate, decrypt the enterprise bank uploaded data to obtain the decrypted data;

[0172] Determine the decrypted data corresponding to all target blockchains as the historical on-chain data.

[0173] It can be seen that through the above optional embodiments, all associated on-chain data can be pulled through the data pulling contract on the blockchain, and the most comprehensive and accurate on-chain data can be obtained by decrypting based on the pre-stored certificate, so as to assist in realizing more efficient and accurate data verification of cross-border financial declaration data in the subsequent process, reducing the costs and errors caused by manual work.

[0174] As an alternative embodiment, the target verification neural network is a random forest model, which is trained by a training data set including a plurality of training declaration data and corresponding declaration parameter annotations, historical blockchain data annotations, and data verification result annotations.

[0175] It can be seen that through the above alternative embodiment, the model type and training details of the target verification neural network are defined. It can capture the data association features between the declaration data and the historical blockchain data to realize the verification between data in different time and space, and achieve more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual work.

[0176] Embodiment III

[0177] Please refer to Figure 3 , Figure 3 which is another cross-border financial declaration data verification system based on blockchain disclosed in the embodiments of the present invention. Figure 3 The described cross-border financial declaration data verification system based on blockchain is applied to a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). As Figure 3 shown, the cross-border financial declaration data verification system based on blockchain may include:

[0178] A memory 301 storing executable program code;

[0179] A processor 302 coupled to the memory 301;

[0180] Wherein, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the cross-border financial declaration data verification method described in Embodiment I.

[0181] Embodiment IV

[0182] The embodiments of the present invention disclose a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the cross-border financial declaration data verification method described in Embodiment I.

[0183] Embodiment V

[0184] The embodiments of the present invention disclose a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps of the cross-border financial declaration data verification method described in Embodiment I.

[0185] The above description is of specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily have to be performed in the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0186] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0187] For convenience of description, when describing the above devices, they are described separately as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0188] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can 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.

[0189] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce a device for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or multiple flows and / or blocks

[0190] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device that implements the functions specified in one or more of the processes Figure 1 or boxes Figure 1 specified in one or more of the processes and / or boxes.

[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing steps for implementing the functions specified in one or more of the processes Figure 1 or boxes Figure 1 specified in one or more of the processes and / or boxes.

[0192] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0193] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0194] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0195] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0196] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0197] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for relevant details.

[0198] Finally, it should be noted that: what is disclosed in an embodiment of a cross-border financial declaration data verification method and system based on blockchain according to the present invention is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention and is not intended to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A cross-border financial declaration data verification method based on blockchain, characterized in that The method includes: Obtaining the data content and declaration parameters of the cross-border financial declaration data to be verified; According to the declaration parameters and a preset parameter screening algorithm, screening out a target verification neural network from multiple candidate verification neural networks, including: For each candidate verification neural network, obtaining the training data set and historical input data corresponding to the candidate verification neural network; Counting the declaration parameters corresponding to all training declaration data in the training data set to obtain a training declaration parameter set; Counting the declaration parameters corresponding to all input declaration data in the historical input data to obtain a historical input declaration parameter set; Calculating a first similarity between the training declaration parameter set and the declaration parameters; Calculating a second similarity between the historical input declaration parameter set and the declaration parameters; Calculating a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; Determining the candidate verification neural network with the highest network priority parameter as the target verification neural network; Pulling the historical on-chain data corresponding to the data content from the target blockchain according to the declaration parameters and a preset parameter association algorithm; Inputting the data content and the historical on-chain data into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data; the data verification result is used to indicate the authenticity and reasonableness of the cross-border financial declaration data.

2. The cross-border financial declaration data verification method based on blockchain according to claim 1, wherein The declaration parameters include transaction subject information, transaction channel bank information, transaction time information, transaction location information, and transaction industry type information.

3. The cross-border financial declaration data verification method based on blockchain according to claim 1, wherein The calculating the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity includes: Calculating a weighted sum average of the first similarity and the second similarity to obtain a network priority parameter corresponding to the candidate verification neural network; wherein, the weighted calculation weights corresponding to the first similarity include a first weight and a second weight; the first weight is proportional to the total data volume of all the training declaration data corresponding to the corresponding training data set; the second weight is proportional to the prediction accuracy rate of the candidate verification neural network in the verification stage; wherein, the weighted calculation weights corresponding to the second similarity include a third weight and a fourth weight; the third weight is proportional to the total data volume of all the input declaration data in the corresponding historical input data; the fourth weight is proportional to the total number of times the candidate verification neural network is selected as the target verification neural network in all historical time periods.

4. The cross-border financial declaration data verification method based on blockchain according to claim 2, wherein The pulling the historical on-chain data corresponding to the data content from the target blockchain according to the declaration parameters and a preset parameter association algorithm includes: Determining all blockchains associated with each parameter data in the declaration parameters in a blockchain set to obtain multiple candidate blockchains; Calculating a blockchain priority parameter for each of the candidate blockchains according to a blockchain data similarity algorithm; Screening out candidate blockchains with all the blockchain priority parameters greater than a parameter threshold from all the candidate blockchains to obtain multiple target blockchains; Pull historical data uploaded to the blockchain on each of the target blockchains according to the declared parameters and the data content.

5. The cross-border financial declaration data verification method based on blockchain according to claim 4, wherein, Calculating the blockchain priority parameters of each candidate blockchain according to the similarity algorithm of blockchain data includes: For each candidate blockchain, obtain the associated blockchain data in the candidate blockchain that is associated with each parameter data; Calculate the third similarity between the associated blockchain data of the candidate blockchain and the associated blockchain data of any other candidate blockchain; Calculate the average value of the third similarities between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

6. The cross-border financial declaration data verification method based on blockchain according to claim 4, wherein, Pulling historical data uploaded to the blockchain on each of the target blockchains according to the declared parameters and the data content includes: For each target blockchain, input the declared parameters and the data content into the data pull contract on the target blockchain to obtain the corresponding enterprise bank upload data; the data pull contract is used to analyze the declared parameters and the data content to obtain the corresponding enterprise association information, bank association information, and payment association information, and based on this, match the corresponding enterprise bank upload data from all blockchain data; Decrypt the enterprise bank upload data based on the pre-stored private certificate and temporary certificate to obtain decrypted data; Determine the decrypted data corresponding to all the target blockchains as the historical data uploaded to the blockchain.

7. A cross-border financial declaration data verification system based on blockchain, characterized in that, The system includes: An acquisition module for acquiring the data content and declared parameters of cross-border financial declaration data to be verified; A screening module for screening out a target verification neural network from multiple candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm, including: For each candidate verification neural network, obtain the training data set and historical input data corresponding to the candidate verification neural network; Count the declared parameters corresponding to all training declaration data in the training data set to obtain a training declaration parameter set; Count the declared parameters corresponding to all input declaration data in the historical input data to obtain a historical input declaration parameter set; Calculate the first similarity between the training declaration parameter set and the declared parameters; Calculate the second similarity between the historical input declaration parameter set and the declared parameters; Calculate the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; Determine the candidate verification neural network with the highest network priority parameter as the target verification neural network; A pulling module for pulling the historical data uploaded to the blockchain corresponding to the data content from the target blockchain according to the declared parameters and a preset parameter association algorithm; A verification module for inputting the data content and the historical data uploaded to the blockchain into the target verification neural network to obtain a data verification result corresponding to the cross-border financial declaration data; the data verification result is used to indicate the authenticity and rationality of the cross-border financial declaration data.

8. A cross-border financial declaration data verification system based on blockchain, characterized in that, The system includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the blockchain-based cross-border financial declaration data verification method according to any one of claims 1-6.

Images