Block chain-based cross-border financial declaration data verification method and system

Abstract

The invention discloses a block chain-based cross-border financial declaration data verification method and system. The method comprises the steps of obtaining data content and declaration parameters of to-be-verified cross-border financial declaration data; screening a target verification neural network from a plurality of candidate verification neural networks according to the declaration parameters and a preset parameter screening algorithm; according to the declaration parameter and a preset parameter association algorithm, pulling historical uplink data corresponding to the data content from a target block chain; inputting the data content and the historical uplink 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 for indicating authenticity and rationality corresponding to the cross-border financial declaration data. Therefore, the cross-border financial declaration data can be verified more efficiently and accurately, and the cost and errors caused by manpower are reduced.

Description

Technical Field

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

[0002] With the development of blockchain, more and more industries have begun to apply blockchain. In the financial industry, blockchain has attracted more and more companies and banks to store transaction information on the blockchain because its information cannot be forged or tampered with. In the cross-border financial transaction declaration process, most of the existing technologies still use simple data rules and manual review, and do not fully consider the use of blockchain information and transaction data and the combination of 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 that need to be solved urgently. Summary of the invention

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

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a cross-border financial declaration data verification method based on blockchain, the method comprising: Obtain the data content and declaration parameters of the cross-border financial declaration data to be verified; According to the declared parameters and a preset parameter screening algorithm, a target verification neural network is screened out from a plurality of candidate verification neural networks; Pull the historical on-chain data corresponding to the data content from the target blockchain according to the declared parameters and the preset parameter association algorithm; The data content and the historical on-chain data are input 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.

[0005] As an optional implementation, 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.

[0006] As an optional implementation, in the first aspect of the present invention, the step of selecting a target verification neural network from a plurality of candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm comprises: For each candidate verification neural network, obtaining a training data set and historical input data corresponding to the candidate verification neural network; Counting the declaration parameters corresponding to all the 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 declared parameter set and the declared parameters; Calculating a second similarity between the historical input declared parameter set and the declared parameter; Calculating a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; The candidate verification neural network with the highest network priority parameter is determined as the target verification neural network.

[0007] As an optional implementation, 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: Calculate the weighted average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; wherein the weighted calculation weight corresponding to the first similarity includes 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 of the candidate verification neural network in the verification stage; wherein the weighted calculation weight corresponding to the second similarity includes 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.

[0008] As an optional implementation, 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 the preset parameter association algorithm includes: Determine in the blockchain set all blockchains associated with each parameter data in the declared parameter to obtain multiple candidate blockchains; Calculate the blockchain priority parameter of each candidate blockchain according to the blockchain data similarity algorithm; Filter out all candidate blockchains whose blockchain priority parameters are greater than a parameter threshold from all the candidate blockchains to obtain multiple target blockchains; According to the declared parameters and the data content, historical on-chain data is pulled on each of the target blockchains.

[0009] As an optional implementation, in the first aspect of the present invention, the blockchain priority parameter of each candidate blockchain is calculated according to the similarity algorithm of the blockchain data, including: For each of the candidate blockchains, obtain the associated blockchain data associated with each of the parameter data in the candidate blockchain; Calculating a third similarity between the blockchain data associated with the candidate blockchain and the blockchain data associated with any other candidate blockchain; Calculate the average value of the third similarity between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0010] As an optional implementation, in the first aspect of the present invention, pulling historical chain data on each target blockchain according to the declared parameters and the data content includes: For each of the target blockchains, the declaration parameters and the data content are input into the data extraction contract on the target blockchain to obtain the corresponding corporate bank uploaded data; the data extraction contract is used to analyze the declaration parameters and the data content to obtain the corresponding corporate association information, bank association information and payment association information, and based on this, the corresponding corporate bank uploaded data is matched in all blockchain data; Based on the pre-stored private certificate and temporary certificate, decrypt the data uploaded by the enterprise bank to obtain decrypted data; The decrypted data corresponding to all the target blockchains are determined as historical on-chain data.

[0011] As an optional embodiment, 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 multiple training declaration data and corresponding declaration parameter annotations, historical chain data annotations and data verification result annotations.

[0012] The second aspect of the embodiment of the present invention discloses a cross-border financial declaration data verification system based on blockchain, the system comprising: An acquisition module is used to obtain the data content and declaration parameters of the cross-border financial declaration data to be verified; A screening module, used to screen out a target verification neural network from a plurality of candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm; A pulling module, used to pull 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; A verification module is used 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 of the cross-border financial declaration data.

[0013] As an optional implementation, 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.

[0014] As an optional implementation, 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 declared parameters and a preset parameter screening algorithm includes: For each candidate verification neural network, obtaining a training data set and historical input data corresponding to the candidate verification neural network; Counting the declaration parameters corresponding to all the 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 declared parameter set and the declared parameters; Calculating a second similarity between the historical input declared parameter set and the declared parameter; Calculating a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; The candidate verification neural network with the highest network priority parameter is determined as the target verification neural network.

[0015] As an optional implementation, in the second aspect of the present invention, 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: Calculate the weighted average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; wherein the weighted calculation weight corresponding to the first similarity includes 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 of the candidate verification neural network in the verification stage; wherein the weighted calculation weight corresponding to the second similarity includes 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.

[0016] As an optional implementation, 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 declared parameters and the preset parameter association algorithm includes: Determine in the blockchain set all blockchains associated with each parameter data in the declared parameter to obtain multiple candidate blockchains; Calculate the blockchain priority parameter of each candidate blockchain according to the blockchain data similarity algorithm; Filter out all candidate blockchains whose blockchain priority parameters are greater than a parameter threshold from all the candidate blockchains to obtain multiple target blockchains; According to the declared parameters and the data content, historical on-chain data is pulled on each of the target blockchains.

[0017] As an optional implementation, 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 blockchain data similarity algorithm includes: For each of the candidate blockchains, obtain the associated blockchain data associated with each of the parameter data in the candidate blockchain; Calculating a third similarity between the blockchain data associated with the candidate blockchain and the blockchain data associated with any other candidate blockchain; Calculate the average value of the third similarity between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0018] As an optional implementation, in the second aspect of the present invention, the specific manner in which the pulling module pulls the historical chain data on each of the target blockchains according to the declared parameters and the data content includes: For each of the target blockchains, the declaration parameters and the data content are input into the data extraction contract on the target blockchain to obtain the corresponding corporate bank uploaded data; the data extraction contract is used to analyze the declaration parameters and the data content to obtain the corresponding corporate association information, bank association information and payment association information, and based on this, the corresponding corporate bank uploaded data is matched in all blockchain data; Based on the pre-stored private certificate and temporary certificate, decrypt the data uploaded by the enterprise bank to obtain decrypted data; The decrypted data corresponding to all the target blockchains are determined as historical on-chain data.

[0019] As an optional embodiment, in the second aspect of the present invention, the target verification neural network is a random forest model, which is trained by a training data set including multiple training declaration data and corresponding declaration parameter annotations, historical chain data annotations and data verification result annotations.

[0020] The third aspect of the present invention discloses another cross-border financial declaration data verification system based on blockchain, the system comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the blockchain-based cross-border financial declaration data verification method disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the blockchain-based cross-border financial declaration data verification method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: 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, and 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, thereby enabling more efficient and accurate data verification of cross-border financial declaration data, reducing costs and errors caused by manual labor. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a cross-border financial declaration data verification method based on blockchain disclosed in an embodiment of the present invention.

[0025] Figure 2 It is a structural diagram of a cross-border financial declaration data verification system based on blockchain disclosed in an embodiment of the present invention.

[0026] Figure 3 It is a structural diagram of another blockchain-based cross-border financial declaration data verification system disclosed in an embodiment of the present invention.

[0027] Figure 4 It is a functional schematic diagram of a blockchain for cross-border financial reporting disclosed in an embodiment of the present invention.

[0028] Figure 5 It is a structural diagram of a cross-border financial reporting system based on blockchain disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] 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 are within the scope of protection of the present invention.

[0030] 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 "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. 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 may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The present invention discloses a cross-border financial declaration data verification method and system based on blockchain, which can select a suitable target verification neural network from multiple candidate verification neural networks according to the declaration parameters and parameter screening algorithm, and then pull the historical chain data corresponding to the declaration data content from the target blockchain according to the declaration parameters and parameter association algorithm, and realize data verification based on the target verification neural network and the historical chain data, so as to more efficiently and accurately verify the cross-border financial declaration data and reduce the cost and errors caused by manual labor. The following are detailed descriptions.

[0033] Embodiment 1 See also Figure 1 , Figure 1 This is a flow chart of a cross-border financial declaration data verification method based on blockchain disclosed in an embodiment of the present invention. Figure 1 The blockchain-based cross-border financial declaration data verification method described 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). Figure 1 As shown, the blockchain-based cross-border financial declaration data verification method may include the following operations: 101. Obtain the data content and declaration parameters of the cross-border financial declaration data to be verified.

[0034] 102. According to the declared parameters and the preset parameter screening algorithm, a target verification neural network is screened out from multiple candidate verification neural networks. 103. According to the declared parameters and the preset parameter association algorithm, pull the historical on-chain data corresponding to the data content from the target blockchain. 104. Input the data content and historical on-chain data into the target verification neural network to obtain the data verification results corresponding to the cross-border financial declaration data.

[0035] Optionally, the data verification results are used to indicate the authenticity and rationality of the corresponding cross-border financial declaration data.

[0036] It can be seen that the above-mentioned embodiments of the 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, and 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, thereby enabling more efficient and accurate data verification of cross-border financial declaration data, reducing costs and errors caused by manual labor.

[0037] As an optional embodiment, in 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.

[0038] Optionally, the declaration parameters can also be obtained by analyzing or predicting the data content through a data analysis algorithm. For example, cross-border financial declaration data may include list data, customs declaration data, quota data and document data. These data may be in text format, image format or other data formats. It is necessary to use a pre-trained data analysis algorithm model to analyze the declaration parameters in these declaration data.

[0039] It can be seen that through the above optional embodiments, the specific content of the declaration parameters is limited, which can fully characterize the characteristics and information of the corresponding cross-border financial transactions, and is subsequently used to accurately screen and verify models and pull chain data, thereby assisting in more efficient and accurate data verification of cross-border financial declaration data and reducing costs and errors caused by manual labor.

[0040] As an optional embodiment, in the above steps, selecting a target verification neural network from a plurality of candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm includes: For each candidate verification neural network, obtaining a training data set and historical input data corresponding to the candidate verification neural network; Count the declaration parameters corresponding to all training declaration data in the training data set to obtain a training declaration parameter set; Count the declaration parameters corresponding to all input declaration data in the historical input data to obtain a set of historical input declaration parameters; Calculating a first similarity between the training declared parameter set and the declared parameters; Calculating a second similarity between the historical input declared parameter set and the declared parameters; Calculate a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; The candidate verification neural network with the highest network priority parameter is determined as the target verification neural network.

[0041] It can be seen that through the above-mentioned optional embodiments, the degree of adaptation between the candidate verification neural network and the current declaration data can be calculated based on the training data set of the candidate verification neural network and the declaration parameters in the historical input data, so as to screen out the target verification neural network that is most suitable for verification of the current declaration data, which is subsequently used to accurately verify the declaration data, thereby assisting in achieving more efficient and accurate data verification of cross-border financial declaration data and reducing costs and errors caused by manual labor.

[0042] As an optional embodiment, in the above step, calculating the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity includes: Calculate the weighted average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; optionally, the weighted calculation weight corresponding to the first similarity includes 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; wherein the weighted calculation weight corresponding to the second similarity includes 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.

[0043] It can be seen that through the above-mentioned optional embodiments, the importance of the similarities corresponding to the training data set and the historical input data can be accurately measured based on the pre-set weighted calculation weights, and based on this, accurate network priority parameters can be calculated to screen out the target verification neural network that is most suitable for the current declaration data verification, which is subsequently used to accurately verify the declaration data, assist in achieving more efficient and accurate data verification of cross-border financial declaration data, and reduce costs and errors caused by manual labor.

[0044] As an optional embodiment, in the above steps, according to the declared parameters and the preset parameter association algorithm, the historical chain data corresponding to the data content is pulled from the target blockchain, including: Determine all blockchains associated with each parameter data in the declared parameters in the blockchain set to obtain multiple candidate blockchains; Calculate the blockchain priority parameters of each candidate blockchain based on the similarity algorithm of blockchain data; Filter out candidate blockchains whose blockchain priority parameters are greater than the parameter threshold from all candidate blockchains to obtain multiple target blockchains; Pull historical on-chain data from each target blockchain based on the declared parameters and data content.

[0045] It can be seen that through the above optional embodiments, it is possible to screen out blockchains that store the most relevant transactions or the most similar transaction data from multiple candidate blockchains based on parameter association and data similarity algorithms, so that the most effective and largest number of historical on-chain data can be pulled for data verification in the future, thereby assisting in achieving more efficient and accurate data verification of cross-border financial declaration data and reducing costs and errors caused by manual labor.

[0046] As an optional embodiment, in the above steps, calculating the blockchain priority parameter of each candidate blockchain according to the blockchain data similarity algorithm includes: For each candidate blockchain, obtain the associated blockchain data associated with each parameter data in the candidate blockchain; Calculating a third similarity between the blockchain data associated with the candidate blockchain and the blockchain data associated with any other candidate blockchain; Calculate the average of the third similarities between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0047] 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 assist in screening out the blockchains that store the most relevant transactions or the most similar transaction data, and assist in achieving more efficient and accurate data verification of cross-border financial declaration data, thereby reducing costs and errors caused by manual labor.

[0048] As an optional embodiment, in the above steps, pulling historical chain data on each target blockchain according to the declared parameters and data content includes: For each target blockchain, the declaration parameters and data content are input into the data pull contract on the target blockchain to obtain the corresponding corporate bank upload data; optionally, the data pull contract is used to analyze the declaration parameters and data content to obtain the corresponding corporate association information, bank association information and payment association information, and based on this, the corresponding corporate bank upload data is matched in all blockchain data; Based on the pre-stored private certificate and temporary certificate, the data uploaded by the corporate bank is decrypted to obtain the decrypted data; Determine the decrypted data corresponding to all target blockchains as historical on-chain data.

[0049] It can be seen that through the above optional embodiments, all related on-chain data can be pulled through the data pull 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 more efficient and accurate data verification of cross-border financial declaration data in the future, and reduce costs and errors caused by manual labor.

[0050] As an optional embodiment, in the above steps, the target verification neural network is a random forest model, which is trained by a training data set including multiple training declaration data and corresponding declaration parameter annotations, historical chain data annotations and data verification result annotations.

[0051] It can be seen that through the above optional embodiments, the model type and training details of the target verification neural network are limited, which can capture the data correlation features between the declared data and the historical blockchain data to realize the verification between the data in different time and space, and realize more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual labor.

[0052] In a specific embodiment, in order to implement the verification method or system of the present invention, a blockchain for cross-border financial reporting is developed, and its functions can be referred to Figure 4 Specifically, the blockchain includes multiple contracts: 1. Data on-chain contract: Different companies and banks use different certificates to upload declaration data or transaction data to the chain.

[0053] 2. Credit limit on-chain contract: The enterprise uploads and updates credit limit data on-chain through a private identity certificate, and the blockchain data is maintained and traced in different versions.

[0054] 3. Bank verification data contract: The bank uses private certificates and corporate temporary certificates to pull and decrypt data in the blockchain and verify the data.

[0055] More specifically, a cross-border financial reporting system based on the above blockchain has been developed, and its architecture can be referred to Figure 5 , including enterprises, banks and market procurement platforms. The data verification technology in the present invention is implemented as a risk model therein to verify and analyze the risk of the declared data. Specifically, the operation steps of the risk model may include: 1. Collect and organize relevant data involved in declaration and verification, including inventory data, customs declaration data, quota data, etc.; 2. Extract and select features related to the verification of declared data from a large amount of data, and use machine learning algorithms for feature selection, model construction, and training; 3. Build an automatic declaration model based on the selected features, which can intelligently submit declaration information and intelligently verify relevant declaration data when submitting; 4. According to the cross-border financial risk model algorithm, the corresponding usage list data, quota data, etc. are encrypted and uploaded to the blockchain, and the data of the manual operating system of multiple stakeholders is recorded.

[0056] Advantages of the above specific implementation scheme include: 1. Through blockchain cross-chain technology, the data of the cross-border trade public service platform is connected, and the traditional human declaration and verification is transformed into a data cross-border financial risk model algorithm, so as to realize the comprehensive analysis and authenticity verification of the cross-border trade transaction data of enterprises.

[0057] 2. Through artificial intelligence, the declaration and verification model makes intelligent declarations for cross-border finance, which saves a great deal of time for enterprises and bank staff, while improving the accuracy of verification.

[0058] 3. Through blockchain technology, system data and operation data are traced to improve the authenticity of data traceability and verification.

[0059] 4. Temporary key technology ensures data security.

[0060] Embodiment 2 See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a cross-border financial declaration data verification system based on blockchain disclosed in an embodiment of the present invention. Figure 2 The blockchain-based cross-border financial declaration data verification system described 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). Figure 2 As shown, the blockchain-based cross-border financial declaration data verification system may include: The acquisition module 201 is used to obtain the data content and declaration parameters of the cross-border financial declaration data to be verified.

[0061] The screening module 202 is used to screen out a target verification neural network from multiple candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm. The pulling module 203 is used to pull the historical on-chain data corresponding to the data content from the target blockchain according to the declared parameters and the preset parameter association algorithm. Verification module 204 is used to input data content and historical on-chain data into the target verification neural network to obtain data verification results corresponding to cross-border financial declaration data.

[0062] Optionally, the data verification results are used to indicate the authenticity and rationality of the corresponding cross-border financial declaration data.

[0063] It can be seen that the above-mentioned embodiments of the 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, and 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, thereby enabling more efficient and accurate data verification of cross-border financial declaration data, reducing costs and errors caused by manual labor.

[0064] 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.

[0065] It can be seen that through the above optional embodiments, the specific content of the declaration parameters is limited, which can fully characterize the characteristics and information of the corresponding cross-border financial transactions, and is subsequently used to accurately screen and verify models and pull chain data, thereby assisting in more efficient and accurate data verification of cross-border financial declaration data and reducing costs and errors caused by manual labor.

[0066] As an optional embodiment, the specific method of the screening module screening out the target verification neural network from multiple candidate verification neural networks according to the declared parameters and the preset parameter screening algorithm includes: For each candidate verification neural network, obtaining a training data set and historical input data corresponding to the candidate verification neural network; Count the declaration parameters corresponding to all training declaration data in the training data set to obtain a training declaration parameter set; Count the declaration parameters corresponding to all input declaration data in the historical input data to obtain a set of historical input declaration parameters; Calculating a first similarity between the training declared parameter set and the declared parameters; Calculating a second similarity between the historical input declared parameter set and the declared parameters; Calculate a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; The candidate verification neural network with the highest network priority parameter is determined as the target verification neural network.

[0067] It can be seen that through the above-mentioned optional embodiments, the degree of adaptation between the candidate verification neural network and the current declaration data can be calculated based on the training data set of the candidate verification neural network and the declaration parameters in the historical input data, so as to screen out the target verification neural network that is most suitable for verification of the current declaration data, which is subsequently used to accurately verify the declaration data, thereby assisting in achieving more efficient and accurate data verification of cross-border financial declaration data and reducing costs and errors caused by manual labor.

[0068] 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: Calculate the weighted average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; optionally, the weighted calculation weight corresponding to the first similarity includes 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; wherein the weighted calculation weight corresponding to the second similarity includes 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.

[0069] It can be seen that through the above-mentioned optional embodiments, the importance of the similarities corresponding to the training data set and the historical input data can be accurately measured based on the pre-set weighted calculation weights, and based on this, accurate network priority parameters can be calculated to screen out the target verification neural network that is most suitable for the current declaration data verification, which is subsequently used to accurately verify the declaration data, assist in achieving more efficient and accurate data verification of cross-border financial declaration data, and reduce costs and errors caused by manual labor.

[0070] As an optional embodiment, the specific method of the pulling module pulling the historical chain data corresponding to the data content from the target blockchain according to the declared parameters and the preset parameter association algorithm includes: Determine all blockchains associated with each parameter data in the declared parameters in the blockchain set to obtain multiple candidate blockchains; Calculate the blockchain priority parameters of each candidate blockchain based on the similarity algorithm of blockchain data; Filter out candidate blockchains whose blockchain priority parameters are greater than the parameter threshold from all candidate blockchains to obtain multiple target blockchains; Pull historical on-chain data from each target blockchain based on the declared parameters and data content.

[0071] It can be seen that through the above optional embodiments, it is possible to screen out blockchains that store the most relevant transactions or the most similar transaction data from multiple candidate blockchains based on parameter association and data similarity algorithms, so that the most effective and largest number of historical on-chain data can be pulled for data verification in the future, thereby assisting in achieving more efficient and accurate data verification of cross-border financial declaration data and reducing costs and errors caused by manual labor.

[0072] As an optional embodiment, the specific method of calculating the blockchain priority parameter of each candidate blockchain by the pulling module according to the similarity algorithm of the blockchain data includes: For each candidate blockchain, obtain the associated blockchain data associated with each parameter data in the candidate blockchain; Calculating a third similarity between the blockchain data associated with the candidate blockchain and the blockchain data associated with any other candidate blockchain; Calculate the average of the third similarities between the candidate blockchain and all other candidate blockchains to obtain the blockchain priority parameter corresponding to the candidate blockchain.

[0073] 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 assist in screening out the blockchains that store the most relevant transactions or the most similar transaction data, and assist in achieving more efficient and accurate data verification of cross-border financial declaration data, thereby reducing costs and errors caused by manual labor.

[0074] As an optional embodiment, the specific method of the pulling module pulling the historical chain data on each target blockchain according to the declared parameters and data content includes: For each target blockchain, the declaration parameters and data content are input into the data pull contract on the target blockchain to obtain the corresponding corporate bank upload data; optionally, the data pull contract is used to analyze the declaration parameters and data content to obtain the corresponding corporate association information, bank association information and payment association information, and based on this, the corresponding corporate bank upload data is matched in all blockchain data; Based on the pre-stored private certificate and temporary certificate, the data uploaded by the corporate bank is decrypted to obtain the decrypted data; Determine the decrypted data corresponding to all target blockchains as historical on-chain data.

[0075] It can be seen that through the above optional embodiments, all related on-chain data can be pulled through the data pull 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 more efficient and accurate data verification of cross-border financial declaration data in the future, and reduce costs and errors caused by manual labor.

[0076] As an optional 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 chain data annotations and data verification result annotations.

[0077] It can be seen that through the above optional embodiments, the model type and training details of the target verification neural network are limited, which can capture the data correlation features between the declared data and the historical blockchain data to realize the verification between the data in different time and space, and realize more efficient and accurate data verification of cross-border financial declaration data, reducing the costs and errors caused by manual labor.

[0078] Embodiment 3 See also Figure 3 , Figure 3 It is another blockchain-based cross-border financial declaration data verification system disclosed in an embodiment of the present invention. Figure 3 The 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). Figure 3 As shown, the blockchain-based cross-border financial declaration data verification system may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; Among them, the processor 302 calls the executable program code stored in the memory 301 to execute the steps of the blockchain-based cross-border financial declaration data verification method described in Example 1.

[0079] Embodiment 4 An embodiment of the present invention discloses a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the blockchain-based cross-border financial declaration data verification method described in Example 1.

[0080] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the blockchain-based cross-border financial declaration data verification method described in Example 1.

[0081] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0082] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0083] For the convenience of description, the above device is described in 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.

[0084] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0085] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0089] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0090] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be 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 technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, 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 temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0091] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0092] This specification may 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 may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0093] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0094] Finally, it should be noted that the cross-border financial declaration data verification method and system based on blockchain disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A cross-border financial declaration data verification method based on blockchain, characterized in that: The method comprises: Obtain the data content and declaration parameters of the cross-border financial declaration data to be verified; According to the declared parameters and a preset parameter screening algorithm, a target verification neural network is screened out from a plurality of candidate verification neural networks; Pull the historical on-chain data corresponding to the data content from the target blockchain according to the declared parameters and the preset parameter association algorithm; The data content and the historical on-chain data are input 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.

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

3. The blockchain-based cross-border financial declaration data verification method according to claim 1 is characterized in that: The step of selecting a target verification neural network from a plurality of candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm includes: For each candidate verification neural network, obtaining a training data set and historical input data corresponding to the candidate verification neural network; Counting the declaration parameters corresponding to all the 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 declared parameter set and the declared parameters; Calculating a second similarity between the historical input declared parameter set and the declared parameter; Calculating a network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity; The candidate verification neural network with the highest network priority parameter is determined as the target verification neural network.

4. The cross-border financial declaration data verification method based on blockchain according to claim 3 is characterized in that: The calculating the network priority parameter corresponding to the candidate verification neural network according to the first similarity and the second similarity includes: Calculate the weighted average of the first similarity and the second similarity to obtain the network priority parameter corresponding to the candidate verification neural network; wherein the weighted calculation weight corresponding to the first similarity includes 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 of the candidate verification neural network in the verification stage; wherein the weighted calculation weight corresponding to the second similarity includes 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.

5. The cross-border financial declaration data verification method based on blockchain according to claim 2 is characterized in that: The step of pulling the historical chain data corresponding to the data content from the target blockchain according to the declared parameters and the preset parameter association algorithm includes: Determine in the blockchain set all blockchains associated with each parameter data in the declared parameter to obtain multiple candidate blockchains; Calculate the blockchain priority parameter of each candidate blockchain according to the blockchain data similarity algorithm; Filter out all candidate blockchains whose blockchain priority parameters are greater than a parameter threshold from all the candidate blockchains to obtain multiple target blockchains; According to the declared parameters and the data content, historical on-chain data is pulled on each of the target blockchains.

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

7. The cross-border financial declaration data verification method based on blockchain according to claim 5 is characterized in that: Pulling historical chain data on each target blockchain according to the declared parameters and the data content includes: For each of the target blockchains, the declaration parameters and the data content are input into the data extraction contract on the target blockchain to obtain the corresponding corporate bank uploaded data; the data extraction contract is used to analyze the declaration parameters and the data content to obtain the corresponding corporate association information, bank association information and payment association information, and based on this, the corresponding corporate bank uploaded data is matched in all blockchain data; Based on the pre-stored private certificate and temporary certificate, decrypt the data uploaded by the enterprise bank to obtain decrypted data; The decrypted data corresponding to all the target blockchains are determined as historical on-chain data.

8. The blockchain-based cross-border financial declaration data verification method according to claim 1 is characterized in that: 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 chain data annotations and data verification result annotations.

9. A cross-border financial declaration data verification system based on blockchain, characterized in that: The system comprises: An acquisition module is used to obtain the data content and declaration parameters of the cross-border financial declaration data to be verified; A screening module, used to screen out a target verification neural network from a plurality of candidate verification neural networks according to the declared parameters and a preset parameter screening algorithm; A pulling module, used to pull 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; A verification module is used 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 of the cross-border financial declaration data.

10. A cross-border financial declaration data verification system based on blockchain, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the blockchain-based cross-border financial declaration data verification method as described in any one of claims 1 to 8.

Images