Financial fund penetration type supervision method and system based on block chain

Abstract

The invention relates to a financial fund penetration type supervision method and system based on a block chain, and the method comprises the steps: constructing a block chain network, and enabling the nodes of the block chain network to comprise an enterprise unit node, a bank node, a financial department node, and a supervision mechanism node; verifying and auditing the to-be-uploaded data, uploading the data to a front route, and forwarding the data to a block chain network through the route; deploying a supervision model based on a self-attention mechanism on the block chain, and implementing penetrating supervision; and executing the intelligent contract, executing a financial fund related process according to a preset rule, performing automatic approval according to a preset approval process, and returning an approval result. Through construction of a block chain network, data uplink and management, penetrating supervision and intelligent contract automatic execution, comprehensive, real-time and accurate supervision of transaction information, funds and voucher data uplink of a plurality of nodes of an enterprise unit end, a bank end, a financial end and a supervision mechanism end is realized.

Description

Technical Field

[0001] The present invention relates to the field of blockchain technology, and in particular to a blockchain-based fiscal funds penetration supervision method and system. Background Art

[0002] Traditional fiscal funds supervision is carried out through the banking system and relies on the bank's internal audit and compliance processes. Audit agencies regularly audit the use of fiscal funds to ensure compliance. Fund flows and transaction information are usually recorded and archived through paper or electronic documents.

[0003] The traditional financial fund supervision method has problems such as data opacity, cumbersome procedures, and easy tampering, making it difficult to ensure the real-time, security and compliance of fund transaction information. The flow of funds and transaction information are not shared among different institutions, resulting in information islands, making it difficult to achieve comprehensive supervision, and lacking a unified platform to view and verify the flow of funds in real time; the supervision process involves multiple departments and institutions, resulting in complex processes and low efficiency, and the delivery and approval of paper or electronic documents is time-consuming and prone to errors; paper records are easily tampered with, and electronic documents are also at risk of being illegally modified, lacking effective technical means to ensure the immutability and integrity of data; traditional supervision methods make it difficult to achieve real-time monitoring of funds and transaction information, resulting in lagging supervision, and the security of fund flow and transaction information is difficult to guarantee. There is a risk of being attacked by hackers and data leaks, and compliance checks rely on manual audits, which are prone to errors and inefficiency. Summary of the invention

[0004] In order to address the shortcomings of the existing technology, the present invention proposes a method and system for penetrating supervision of financial funds based on blockchain. By constructing a blockchain network, data chain uploading and management, penetrating supervision, and automated execution of smart contracts, comprehensive, real-time, and accurate supervision of transaction information, funds, and voucher data on multiple nodes at the enterprise end, bank end, financial end, and regulatory agency end can be achieved.

[0005] To achieve the above objectives, the technical solutions adopted by the present invention include:

[0006] A blockchain-based fiscal funds penetration supervision method, characterized by including:

[0007] S1. Build a blockchain network, where the nodes of the blockchain network include enterprise nodes, bank nodes, finance department nodes, and regulatory agency nodes;

[0008] S2. Verify and review the uploaded data, upload the data to the front-end router, and forward the data to the blockchain network through the router;

[0009] S3. Deploy a supervision model based on the self-attention mechanism on the blockchain to implement penetrating supervision;

[0010] S4. Execute the smart contract, carry out the financial fund-related processes according to the preset rules, automatically approve according to the preset approval process, and return the approval result.

[0011] Furthermore, the construction of the blockchain network also includes:

[0012] Set node permissions, including access permissions and data operation permissions;

[0013] Use encryption algorithms to encrypt sensitive data.

[0014] Furthermore, the regulatory model based on the self-attention mechanism is deployed on the blockchain, including:

[0015] The self-attention mechanism is introduced to embed the features of fiscal funds into a high-dimensional space and map the features into an embedding vector e i =W i ·x i +b i , where W i is the embedding weight matrix of feature i, b i is the embedding bias vector of feature i, x i is the original eigenvalue;

[0016] Based on the embedded vector, a linear transformation is performed to obtain the query vector Query=W Q ·[e1; e2; …; e n ]、Key vector Key=W K ·[e1; e2; …; e n ]、Value vector Value=W V ·[e1; e2; …; e n ], where [e1; e2; …; e n ] is the stack of all embedding vectors, W Q , W K , W V is the weight matrix after training;

[0017] Calculating attention scores Use the softmax function to obtain the attention weight Attention Weight = softmax (Attention Score);

[0018] The value vector is weighted using the attention weight to obtain the feature representation.

[0019] Furthermore, the method further comprises:

[0020] Add a feedforward network layer, the output of the lth layer is z (l) =σ(W (l) ·z (l-1) +b (l) ), where W (l) is the weight of the lth layer, b (l) is the bias of the lth layer, σ is the activation function ReLU,

[0021] The output layer generates a probability distribution based on the softmax function.

[0022] Furthermore, the deployment of a supervision model based on a self-attention mechanism on the blockchain also includes:

[0023] Add classification task loss function Where N is the number of samples, C is the number of categories, and y ic is the true label (0 or 1) of whether sample i belongs to category c, is the model's prediction that sample i belongs to category c.

[0024] Furthermore, the regulatory model based on the self-attention mechanism is deployed on the blockchain to implement penetrating supervision, including:

[0025] Use the regulatory model to assess the transaction risk level, which includes low, medium and high, and set a risk threshold. When the transaction risk level reaches the risk threshold, further review and monitor the transaction;

[0026] Based on the regulatory model, the characteristics of this transaction and historical transactions are analyzed to evaluate and predict this transaction.

[0027] The present invention also relates to a blockchain-based fiscal funds penetration supervision system, which is characterized by comprising:

[0028] A blockchain construction module, used to construct a blockchain network, wherein the nodes of the blockchain network include enterprise nodes, bank nodes, finance department nodes, and regulatory agency nodes;

[0029] The data uploading module is used to verify and review the uploaded data, upload the data to the front-end router, and forward the data to the blockchain network through the router;

[0030] Model deployment module, used to deploy a supervision model based on the self-attention mechanism on the blockchain to implement penetrating supervision;

[0031] The contract execution module is used to execute smart contracts, execute financial funding related processes according to preset rules, automatically approve according to the preset approval process, and return the approval results.

[0032] The present invention also relates to a computer-readable storage medium, characterized in that a computer program is stored on the storage medium, and the computer program implements the above method when executed by a processor.

[0033] The present invention also relates to an electronic device, characterized in that it comprises a processor and a memory;

[0034] The memory is used to store program instructions;

[0035] The processor is used to execute the above method by calling program instructions.

[0036] The present invention also relates to a computer program product, comprising a computer program and / or instructions, characterized in that the computer program and / or instructions implement the steps of the above method when executed by a processor.

[0037] The beneficial effects of the present invention are:

[0038] The blockchain-based fiscal funds penetration supervision method and system described in the present invention can realize the automated funds supervision of multiple nodes at the enterprise end, bank end, fiscal end, and regulatory agency end in the fiscal funds supervision scenario, and the transaction information, funds, and voucher data can be uploaded to the chain, reducing the repeated communication synchronization and confirmation workload of multiple systems, improving the efficiency and transparency of funds supervision, and ensuring the security and real-time nature of data. The disbursement, clearing, and interbank fund circulation of fiscal funds are all automatically synchronized online, and the transaction information and transaction parties are verified for each transaction, realizing the supervision of funds, transaction information, and vouchers throughout the entire process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0040] Figure 1 This is a flowchart of a blockchain-based fiscal funds penetration supervision method of the present invention;

[0041] Figure 2 This is a schematic diagram of the structure of a blockchain-based fiscal funds penetration supervision system of the present invention;

[0042] Figure 3 The figure is a schematic structural diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. It should be understood that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments, and these embodiments are only used to illustrate the present application and are not used to limit the scope of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0044] like Figure 1 As shown, the embodiment of the present invention discloses a method for penetrating supervision of financial funds based on blockchain, and the steps of the method include:

[0045] Step S1. Build a blockchain network, the nodes of which include enterprise nodes, bank nodes, finance department nodes, and regulatory agency nodes. Set node permissions, which include access permissions and data operation permissions. Use encryption algorithms to encrypt sensitive data.

[0046] Establish a blockchain network consisting of business units, multiple commercial bank nodes, financial department nodes and regulatory agency nodes. These nodes jointly participate in the maintenance and management of the blockchain to form a decentralized and highly transparent data sharing platform.

[0047] Setting different permissions for different nodes ensures that only nodes with corresponding permissions can access and operate relevant data, which helps protect the privacy and security of data while meeting regulatory requirements. For example, the financial department node has the authority to enter data and conduct preliminary review, and the regulatory agency node has the authority to query data and conduct in-depth analysis. Establishing a strict data access control mechanism can prevent data leakage caused by unauthorized data access.

[0048] Using encryption algorithms to encrypt sensitive data can ensure the security of data during transmission and storage.

[0049] Step S2: Verify and review the data to be uploaded, upload the data to the front-end router, and forward the data to the blockchain network through the router.

[0050] Data preparation should be carried out before uploading to the chain, including the financial funds allocation plan, contract data, enterprise data, payment data, transaction information, transaction vouchers and other data, and necessary verification and review should be carried out.

[0051] The prepared data is uploaded to the front-end router in real time, and the information is forwarded to the blockchain network through the router. The immutability of the blockchain can ensure the authenticity and integrity of the data. The blockchain network can track and monitor the entire process of fiscal funds in real time. Every disbursement, circulation and use of fiscal funds will leave an indelible record on the blockchain.

[0052] Step S3. Deploy a supervision model based on the self-attention mechanism on the blockchain to implement penetrating supervision.

[0053] Utilize the transparency and traceability of blockchain to conduct penetrating supervision of fiscal funds. From the disbursement of funds to the final use of funds, every link will be clearly recorded and displayed on the blockchain. The flow and use of fiscal funds can be monitored in real time through the blockchain network to ensure that the flow and use of funds between multiple banks comply with regulations. Once an abnormal situation is found, the system will automatically issue an early warning signal so that the regulatory authorities can intervene in time.

[0054] Deploy a supervision model based on the self-attention mechanism on the blockchain. Adding a supervision model based on the self-attention mechanism aims to improve the efficiency of historical transaction data analysis and accurate detection of abnormal transactions. Specifically, it includes:

[0055] The self-attention mechanism is introduced to embed the characteristics of financial funds (such as fund arrival delay time, payment delay time, settlement time and transaction success rate, etc.) into a high-dimensional space and map the characteristics into an embedding vector e i =W i ·x i +b i , where W i is the embedding weight matrix of feature i, b i is the embedding bias vector of feature i, x i is the original eigenvalue (for numerical features);

[0056] Based on the embedded vector, a linear transformation is performed to obtain the query vector Query=W Q ·[e1; e2; …; e n ]、Key vector Key=W K ·[e1; e2; …; e n ]、Value vector Value=W V ·[e1; e2; …; e n ], where [e1; e2; …; e n ] is the stack of all embedding vectors, W Q , W K , W V is the weight matrix after training;

[0057] Calculating attention scores Use the softmax function to obtain the attention weight Attention Weight = softmax (Attention Score);

[0058] The value vector is weighted using the attention weight to obtain the feature representation.

[0059] In this embodiment, W Q , W K , W V Can be optimized based on model training.

[0060] Deployment of a self-attention mechanism-based supervision model on the blockchain further includes:

[0061] Add a feedforward network layer, the output of the lth layer is z (l) =σ(W (l) ·z (l-1) +b (l) ), where W (l) is the weight of the lth layer, b (l) is the bias of the lth layer, σ is the activation function ReLU,

[0062] For the final layer, the output layer generates a probability distribution based on the softmax function.

[0063] In this embodiment, one or more feed-forward networks are added, which are used to further process the features and generate the final output.

[0064] Specifically, the deployment of a supervision model based on the self-attention mechanism on the blockchain also includes:

[0065] Add classification task loss function Where N is the number of samples, C is the number of categories, and y ic is the true label (0 or 1) of whether sample i belongs to category c, is the model's prediction that sample i belongs to category c.

[0066] The regulatory model is used to evaluate the transaction risk level, which includes low, medium and high. A risk threshold is set. When the transaction risk level reaches the risk threshold, the transaction is further reviewed and monitored to reduce the cost of manual intervention.

[0067] Based on the supervision model, the characteristics of this transaction and historical transactions are analyzed to evaluate and predict this transaction. This supervision model can be used to analyze the delay time of funds arrival, payment delay time and settlement time. If the time delay is long, it may indicate that there are some problems in the transaction process, which need attention and optimization measures. This supervision model can also be used to evaluate and analyze the transaction link nodes and participating nodes.

[0068] Step S4. Execute the smart contract, execute the financial funding related processes according to the preset rules, automatically approve according to the preset approval process, and return the approval result.

[0069] Smart contracts are deployed on the blockchain to automatically execute the disbursement, approval, and supervision of financial funds. Smart contracts automatically judge and execute corresponding operations according to preset rules, reducing the possibility of human intervention and misoperation.

[0070] Smart contracts are used to implement automated review functions. When an enterprise submits an application for the use of funds, the smart contract will automatically verify the authenticity and completeness of the application materials, and automatically approve it according to the preset approval process. The approval results will be fed back to the enterprise and regulatory authorities in real time.

[0071] Taking a local government special financial fund as an example, the specific implementation steps of the present invention are given below.

[0072] Build a blockchain network, including budget unit nodes, commercial bank nodes, municipal finance nodes, and regulatory agency nodes.

[0073] Prepare the special financial fund allocation plan, contract data, enterprise data, payment data, etc. and upload them to the blockchain network.

[0074] The payment process is automatically executed through smart contracts, and funds are transferred from the finance department account to the designated bank account. At the same time, payment records are generated and uploaded to the blockchain.

[0075] When funds flow between multiple banks and accounts, the transparency of blockchain is used to monitor the entire process based on the regulatory model to ensure that the flow of funds complies with regulations.

[0076] The unit that uses the funds submits an application for the use of funds and supporting documents on the blockchain, and the regulatory agency reviews the materials and confirms the use of the funds through the blockchain.

[0077] Based on the above steps, the responses of each node are as follows:

[0078] 1. The budget unit submits a payment application (including vouchers): The budget unit submits a formal payment application containing detailed payment information and corresponding vouchers to the financial department based on actual needs.

[0079] 2. The finance department reviews and confirms the payment instructions: The finance department reviews the payment applications submitted by the budget units to ensure that they comply with financial regulations and budget arrangements; if the review is passed, the payment instructions are formally confirmed and instructions (vouchers) containing payment details are sent to the bank system.

[0080] 3. The bank executes the payment operation: After receiving the payment instruction (voucher) confirmed by the financial department, the bank system immediately processes the payment and transfers the specified amount from the financial account to the recipient's account.

[0081] 4. Multi-party clearing and fund transfer: As payment intermediaries, commercial banks are responsible for clearing funds with the finance department and the People's Bank of China (PBOC). This process ensures that funds are accurately transferred from the finance account to the final recipient through the commercial bank, and completes the final settlement in the PBOC system.

[0082] 5. The regulatory agency (PBOC) implements penetrating supervision: The regulatory agency (PBOC) evaluates the transaction based on the regulatory model, which is used for supervision, initial transaction forecasts, and evaluation of regulatory units.

[0083] like Figure 2 As shown, the embodiment of the present invention discloses a financial fund penetration supervision system based on blockchain, and its structure includes:

[0084] A blockchain construction module, used to construct a blockchain network, wherein the nodes of the blockchain network include enterprise nodes, bank nodes, finance department nodes, and regulatory agency nodes;

[0085] The data uploading module is used to verify and review the uploaded data, upload the data to the front-end router, and forward the data to the blockchain network through the router;

[0086] Model deployment module, used to deploy a supervision model based on the self-attention mechanism on the blockchain to implement penetrating supervision;

[0087] The contract execution module is used to execute smart contracts, execute financial funding related processes according to preset rules, automatically approve according to the preset approval process, and return the approval results.

[0088] By using this system, the above-mentioned operation processing method can be executed and the corresponding technical effects can be achieved.

[0089] An embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method in the above embodiment, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps in the method in the above embodiment are implemented.

[0090] The embodiment of the present invention further provides an electronic device for executing the above method, as a device for implementing the method, and its structure is as follows: Figure 3As shown, the electronic device 300 includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one. It is understandable that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the specific structure of the electronic device 300. In other embodiments of the present application, the electronic device 300 may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware. Optionally, the electronic device may also include a display screen 305 for displaying images, or receiving user operation instructions when necessary.

[0091] The processor 301 is applied in the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 304 may include a receiver and a transmitter. The transceiver 304 is applied in the embodiment of the present application to implement the function of the electronic device of the embodiment of the present application communicating with other devices when executed.

[0092] Processor 301 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0093] The processor 301 may also include one or more processing units, for example, the processor 301 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processor (NPU). Among them, different processing units may be independent devices or integrated into one or more processors. Among them, the controller may be the nerve center and command center of the electronic device 300. The controller may generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory may also be set in the processor 301 for storing instructions and data. In some embodiments, the memory in the processor 301 is a high-speed cache memory. The memory may store instructions or data that the processor 301 has just used or circulated. If the processor 301 needs to use the instruction or data again, it may be directly called from the memory. Repeated access is avoided, the waiting time of the processor 301 is reduced, and the efficiency of the system is improved.

[0094] The processor 301 can run the method provided in the embodiment of the present application. The processor 301 can include different devices. For example, when a CPU and a GPU are integrated, the CPU and the GPU can cooperate to execute the method provided in the embodiment of the present application, for example, part of the algorithm in the method is executed by the CPU, and another part of the algorithm is executed by the GPU to obtain faster processing efficiency.

[0095] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0096] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or may include a high-speed random access memory, or may include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0097] Optionally, the memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the method provided in any embodiment of the present application.

[0098] The memory 303 can be used to store computer executable program codes, which include instructions. The processor 301 executes various functional applications and data processing of the electronic device 300 by running the instructions stored in the memory 303. The memory 303 may include a program storage area and a data storage area. Among them, the program storage area may store the code of the operating system, application program, etc. The data storage area may store data created during the use of the electronic device 300 (such as images, videos, etc. collected by the camera application), etc.

[0099] The memory 303 may also store one or more computer programs corresponding to the method provided in the embodiment of the present application. The one or more computer programs are stored in the above-mentioned memory 303 and are configured to be executed by the one or more processors 301. The one or more computer programs include instructions, and the above-mentioned instructions can be used to execute each step in the above-mentioned corresponding embodiment.

[0100] Of course, the code of the method provided in the embodiment of the present application can also be stored in an external memory. In this case, the processor 301 can run the code of the method stored in the external memory through the external memory interface, and the processor 301 can control the running process.

[0101] The display screen 305 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 300 may include 1 or N display screens 305, where N is a positive integer greater than 1. The display screen 305 can be used to display information input by a user or information provided to a user and various graphical user interfaces (GUI). For example, the display screen 305 can display photos, videos, web pages, or files.

[0102] The electronic device provided in the embodiment of the present application is applicable to any embodiment of the above method. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, which will not be repeated here.

[0103] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 system that specifies the functions of a box or multiple boxes.

[0105] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps of the functions specified in a box or multiple boxes. Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the attached claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0107] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A blockchain-based fiscal funds penetration supervision method, characterized in that: include: S1. Build a blockchain network, where the nodes of the blockchain network include enterprise nodes, bank nodes, finance department nodes, and regulatory agency nodes; S2. Verify and review the uploaded data, upload the data to the front-end router, and forward the data to the blockchain network through the router; S3. Deploy a supervision model based on the self-attention mechanism on the blockchain to implement penetrating supervision; S4. Execute the smart contract, carry out the financial fund-related processes according to the preset rules, automatically approve according to the preset approval process, and return the approval result.

2. The method according to claim 1, characterized in that The construction of the blockchain network further includes: Set node permissions, including access permissions and data operation permissions; Use encryption algorithms to encrypt sensitive data.

3. The method according to claim 1, characterized in that The regulatory model based on the self-attention mechanism deployed on the blockchain includes: The self-attention mechanism is introduced to embed the features of fiscal funds into a high-dimensional space and map the features into an embedding vector e i =W i ·x i +b i , where W i is the embedding weight matrix of feature i, b i is the embedding bias vector of feature i, x i is the original eigenvalue; Based on the embedded vector, a linear transformation is performed to obtain the query vector Query=W Q ·[e1; e2; …; e n ], key vector Key = W K ·[e1; e2; …; e n ]、Value vector Value=W V ·[e1; e2; …; e n ], where [e1; e2; …; e n ] is the stack of all embedding vectors, W Q , W K , W V is the weight matrix after training; Calculating attention scores Use the softmax function to obtain the attention weight Attention Weight = softmax (Attention Score); The value vector is weighted using the attention weight to obtain the feature representation.

4. The method according to claim 3, characterized in that The method further comprises: Add a feedforward network layer, the output of the lth layer is z (l) =σ(W (l) ·z (l-1) +b (l) ), where W (l) is the weight of the lth layer, b (l) is the bias of the lth layer, σ is the activation function ReLU, The output layer generates a probability distribution based on the softmax function.

5. The method according to claim 1, characterized in that The regulatory model based on the self-attention mechanism deployed on the blockchain also includes: Add classification task loss function Where N is the number of samples, C is the number of categories, and y ic is the true label of whether sample i belongs to category c, is the model's prediction that sample i belongs to category c.

6. The method according to claim 1, characterized in that The regulatory model based on the self-attention mechanism is deployed on the blockchain to implement penetrating supervision, including: Use the regulatory model to assess the transaction risk level, which includes low, medium and high, and set a risk threshold. When the transaction risk level reaches the risk threshold, further review and monitor the transaction; Based on the regulatory model, the characteristics of this transaction and historical transactions are analyzed to evaluate and predict this transaction.

7. A blockchain-based fiscal funds penetration supervision system, characterized in that: include: A blockchain construction module, used to construct a blockchain network, wherein the nodes of the blockchain network include enterprise nodes, bank nodes, finance department nodes, and regulatory agency nodes; The data uploading module is used to verify and review the uploaded data, upload the data to the front-end router, and forward the data to the blockchain network through the router; Model deployment module, used to deploy a supervision model based on the self-attention mechanism on the blockchain to implement penetrating supervision; The contract execution module is used to execute smart contracts, execute financial funding related processes according to preset rules, automatically approve according to the preset approval process, and return the approval results.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store program instructions; The processor is configured to execute the method according to any one of claims 1 to 6 by calling program instructions.

10. A computer program product comprising a computer program and / or instructions, characterized in that: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images