Financial data processing method and device, electronic equipment and storage medium

Abstract

The invention provides a financial data processing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring transaction data generated by a financial service system from a block chain node in real time; performing tagging processing on the transaction data according to a preset rule, wherein the tagging dimension comprises a transaction type, a risk level and a data flow direction; based on a graph data model, converting the tagged transaction data into a structured relationship including nodes and edges, the nodes representing a transaction subject, and the edges including a transaction amount, transaction time and a data flow direction; and displaying the structured relationship in a dynamic graph form. The method is used for achieving the effect of improving financial data processing efficiency and accuracy.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a financial data processing method, device, electronic device and storage medium. Background Art

[0002] Within the financial industry, financial data-related businesses are a core component of financial institutions' operations. The scale of these businesses profoundly impacts their profitability and market competitiveness, while the quality of their financial data assets directly impacts their capital stability and risk tolerance. With the rise of digital finance, financial data business models are gradually shifting from traditional, single-offline operations to a hybrid online and offline model. Leveraging digital platforms, such as mobile financial terminals, financial institutions offer market participants a one-stop service for online financial data application, rapid approval, and issuance, effectively expanding their business boundaries and improving processing efficiency. However, this evolution in business models has also significantly increased the difficulty of managing financial data risks.

[0003] As financial data services develop, financial institutions have established a basic regulatory approach during traditional operations to ensure the security and compliance of their operations. The identification of transaction entities primarily relies on manual processes, collecting and reviewing basic materials such as supporting documents and historical transaction records submitted by the transaction entities to verify their legitimacy and compliance. Risk assessment utilizes relatively simple assessment rules, combining limited data such as the transaction entity's past behavior within the financial system and basic financial information to make a preliminary assessment of the transaction entity's potential risk, assessing its ability to fulfill its financial data-related obligations and the potential level of risk. During the data application and approval phase, the business system typically first screens basic rules such as format and conditions, followed by a detailed manual review. The decision on whether to approve the data application is made based on a comprehensive consideration of factors such as the transaction entity's qualifications and the legitimacy of the business needs. In the post-use management phase, regular manual checks and review of transaction records are used to track the progress of data use and the transaction entity's compliance with the contract, allowing for the timely identification and resolution of any anomalies.

[0004] However, the above-mentioned financial data processing method relies on manual operations and the circulation of paper documents, resulting in a long business processing cycle and low efficiency. At the same time, manual operations are prone to errors, increasing the risk of business errors and disputes. Summary of the Invention

[0005] The embodiments of the present application provide a financial data processing method, apparatus, electronic device, and storage medium to improve the efficiency and accuracy of financial data processing.

[0006] In a first aspect, an embodiment of the present application provides a financial data processing method, comprising:

[0007] Collect transaction data generated by financial business systems from blockchain nodes in real time;

[0008] Transaction data is labeled according to preset rules. The labeling dimensions include transaction type, risk level, and data flow direction.

[0009] Based on the graph data model, the labeled transaction data is converted into a structured relationship consisting of nodes and edges. The nodes represent the transaction entities, and the edges include the transaction amount, transaction time, and data flow direction.

[0010] Display structured relationships in the form of dynamic graphs.

[0011] In a second aspect, an embodiment of the present application provides a financial data processing device, comprising:

[0012] The collection module is used to collect transaction data generated by the financial business system from blockchain nodes in real time;

[0013] The processing module is used to label transaction data according to preset rules. The labeling dimensions include transaction type, risk level and data flow direction;

[0014] The processing module is also used to convert the labeled transaction data into a structured relationship consisting of nodes and edges based on the graph data model. The nodes represent the transaction subjects, and the edges contain the transaction amount, transaction time, and data flow direction.

[0015] The display module is used to display structured relationships in the form of dynamic graphs.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0017] Memory stores computer-executable instructions;

[0018] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0021] The financial data processing method, device, electronic device and storage medium provided in this application obtain transaction data in real time through blockchain technology, and use intelligent label classification technology to perform multi-dimensional annotation of transaction data. Based on graph database construction technology, the labeled transaction data is converted into a network topology structure containing transaction subject nodes and transaction data flow edges, and finally dynamically displayed through an interactive visualization platform. This method effectively overcomes the problems of data silos, risk identification lags, and data link ambiguity in traditional financial supervision. It ensures the authenticity and reliability of transaction data through the distributed characteristics of blockchain, deeply mines transaction associations with the help of graph computing technology, and uses visualization methods to improve regulatory transparency, thereby building an intelligent risk control system covering the entire process, improving the efficiency and accuracy of financial data processing, and improving the risk warning capabilities of financial institutions and the regulatory response speed to financial data. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0023] Figure 1 A flowchart of a financial data processing method provided in this application;

[0024] Figure 2 A flowchart of another financial data processing method provided in this application;

[0025] Figure 3 A schematic diagram of the structure of a consortium chain network provided for this application;

[0026] Figure 4 A schematic diagram of a transaction data processing flow provided for this application;

[0027] Figure 5 A schematic diagram of the structure of a financial data processing device provided in this application;

[0028] Figure 6 This is a schematic diagram of the structure of an electronic device provided in this application.

[0029] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0030] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0031] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] First, let’s explain the terms involved in this application:

[0033] Blockchain: A distributed database technology characterized by decentralization, data immutability, transparency, and security. It records data in a chain-like structure called "blocks," each cryptographically linked to the previous one. Data recorded on the blockchain cannot be tampered with, ensuring a high degree of trust and transparency.

[0034] Consortium Chain: Blockchains can be categorized into three models based on their degree of decentralization: public, consortium, and private. While public chains are fully open to everyone and private chains are confined to a single institution, consortium chains are semi-open. Only authorized institutions and organizations can join the blockchain network, and consortium chains are maintained by all members of the consortium.

[0035] Cross-chain technology: A technology that enables data sharing and interaction between different blockchains. In this application, cross-chain technology is used to integrate financial data stored in different blockchain systems, ensuring seamless traceability of financial data across platforms or institutions, and increasing the comprehensiveness of financial data tracking.

[0036] Financial risk management: Its core goal is to identify, control and reduce various risks that may arise in the flow of financial data through means such as evaluating the credit status of financial entities, managing and supervising the flow of financial data.

[0037] As a core asset of modern financial institutions, the efficiency and quality of financial data circulation directly impacts the institutions' operating efficiency and market competitiveness. In the context of digital transformation, the financial data circulation model has shifted from traditional offline processing to collaborative online and offline processing, enabling online applications and intelligent approvals through digital platforms. With the increasing complexity of financial operations, the importance of risk management in data circulation relationships has become increasingly prominent, and regulatory authorities continue to raise their requirements for data security and compliance. Establishing a risk management system covering the entire lifecycle and ensuring the compliance and traceability of data circulation has become a key issue in improving the quality of financial operations. The financial industry urgently needs to establish a more intelligent and efficient financial data supervision solution to cope with the increasingly complex financial risk environment.

[0038] Existing financial data processing primarily utilizes technical solutions such as identity verification mechanisms, risk assessment models, business approval processes, and post-event tracking mechanisms. Identity verification uses a multi-factor authentication process, employing digital certificates and biometrics to confirm the identity of the transaction subject. Risk assessment utilizes statistical models to analyze the creditworthiness of the transaction subject and assess its ability to fulfill its obligations. Business approval utilizes a combination of rule-based engines and manual review to conduct business audits. Post-event tracking monitors financial data trends through transaction flow analysis and generates regular risk assessment reports. While this model emphasizes full-process risk management, it still primarily relies on a combination of pre-set rules and manual intervention, presenting significant limitations when addressing complex financial scenarios.

[0039] The above-mentioned financial data processing methods are inefficient, multi-step audits result in high time costs, and are prone to operational risks; risk assessments rely on static data and historical records, and the lag in cross-institutional data synchronization causes serious information asymmetry problems; the monitoring capabilities of complex transaction networks are insufficient, making it difficult to timely identify risk transmission in multi-level flows; the early warning mechanism responds with delays, and the identification of abnormal transactions often lags behind the occurrence of risks.

[0040] To address the above issues, this application provides a financial data processing method, device, electronic device, and storage medium. By collecting blockchain transaction data in real time and performing multi-dimensional labeling processing, this method constructs a graph structure relationship between transaction entities and enables dynamic visualization. This method can effectively address the problems of information lag, one-sided risk assessment, and difficulty in tracking data flows in traditional financial data processing. It ensures data authenticity and timeliness through blockchain, fully presents complex transaction networks using graph models, and provides intuitive visualization supervision tools, thereby significantly improving the accuracy of financial data risk identification and regulatory efficiency.

[0041] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0042] Figure 1 A flowchart of a financial data processing method provided in this application is shown as follows: Figure 1 As shown, with the electronic device as the execution subject, the method of this embodiment includes the following steps:

[0043] S101. Collect transaction data generated by the financial business system from blockchain nodes in real time.

[0044] In this embodiment, the electronic device can obtain transaction data in real time through a data acquisition module deployed in the blockchain network.

[0045] Alternatively, the electronic device can use the Ethereum subscription method to subscribe to new block generation events and transaction events on the Ethereum blockchain, establishing a real-time monitoring connection through the HTTP interface. When a new block is generated, the node will actively push event data containing transaction details.

[0046] S102: Label the transaction data according to preset rules.

[0047] Among them, the labeled dimensions include transaction type, risk level and data flow.

[0048] Electronic devices classify and label transaction data according to preset rules, including operation types such as contract signing, asset transfer, settlement, as well as high, medium, and low risk levels and data flow dimensions such as input and output.

[0049] S103. Based on the graph data model, the labeled transaction data is converted into a structured relationship including nodes and edges.

[0050] The electronic device converts the classified and labeled transaction data into a graph structure, where nodes represent transaction entities, such as financial institutions and individual users. Edges represent key attribute information of the transaction data, such as transaction amount, transaction time, and data flow.

[0051] Optionally, the electronic device may use a graph traversal algorithm to analyze the data flow and merge duplicate records on the same path to optimize the display effect.

[0052] S104. Display structured relationships in the form of dynamic graphs.

[0053] In this embodiment, the dynamic graph is used to present the data flow status of the current financial business system. Optionally, the electronic device can use different identifiers to distinguish high-risk data flows and related transaction entities, and provide interactive query functions to support full-link data tracking.

[0054] The financial data processing method provided in the embodiment of the present application obtains transaction data in real time through blockchain technology, and uses intelligent label classification technology to perform multi-dimensional annotation on transaction data. Based on graph database construction technology, the labeled transaction data is converted into a network topology structure containing transaction subject nodes and transaction data flow edges, and finally dynamically displayed through an interactive visualization platform. This method effectively overcomes the problems of data silos, risk identification lags, and data link ambiguity in traditional financial supervision. It ensures the authenticity and reliability of transaction data through the distributed characteristics of blockchain, deeply mines transaction associations with the help of graph computing technology, and uses visualization methods to improve regulatory transparency, thereby building an intelligent risk control system covering the entire process, improving the efficiency and accuracy of financial data processing, and improving the risk warning capabilities of financial institutions and the regulatory response speed to financial data.

[0055] Figure 2 A flowchart of a financial data processing method provided in this application is shown as follows: Figure 2 As shown, with the electronic device as the execution subject, the method of this embodiment includes the following steps:

[0056] S201. Establish a consortium chain network among multiple financial institutions.

[0057] In this embodiment, the financial business system includes multiple financial institutions. Electronic devices can employ a digital certificate-based access mechanism, setting a dynamically updated membership list to ensure that only authorized financial institutions can join the consortium chain network. This network, combining openness and privacy, is suitable for scenarios requiring a foundation of trust and data collaboration. It also features access control and enables efficient data exchange among consortium members.

[0058] By building a consortium chain network among financial institutions, data privacy is guaranteed. Only consortium members can join the nodes of the consortium chain. At the same time, transaction data is public among consortium members, avoiding information interruption in a single financial institution and solving the problem of inability to continuously track transaction information. The natural "chain" attribute of blockchain is used to facilitate transaction tracing.

[0059] S202. Deploy cross-chain communication protocols and data verification mechanisms based on the alliance chain network.

[0060] S203. Through cross-chain communication protocols and data verification mechanisms, transaction data that has undergone data verification is collected in real time from blockchain nodes of multiple financial institutions.

[0061] In this application, considering that regulators have their own blockchain networks and financial institutions need to protect user privacy, they cannot share all data with regulators. To avoid creating information silos, cross-chain data integration has emerged. Cross-chain data integration refers to the sharing and integration of data between different blockchain platforms to achieve broader collaboration and data consistency.

[0062] Based on this, this embodiment uses the Inter-Blockchain Communication (IBC) protocol as a cross-chain communication protocol to securely transmit financial data between blockchains. Cross-chain data sharing and integration are achieved through the relay chain. Simultaneously, using zero-knowledge authentication technology, blockchains can verify the authenticity of financial data during cross-chain transmission without leaking its content, ensuring consistency and privacy.

[0063] The data verification mechanism leverages the distributed ledger nature of blockchain, subscribing to new block generation events, transaction events, and other data through Ethereum subscription methods, and monitoring these event data in real time using an HTTP interface. When a new transaction or event occurs, the node pushes the event data that meets the criteria, and the electronic device performs preliminary verification of this data to ensure its integrity and accuracy.

[0064] In addition, if Figure 3 As shown, smart contracts are deployed on each financial institution node in the consortium chain network. Through blockchain smart contracts, every step of the financial data process, from approval to issuance, use, and repayment, can be recorded, ensuring that every financial data flow can be transparently traced. Financial data is monitored through smart contracts, ensuring every step of financial data management is tracked, and data is solidified into the blockchain through an unchangeable program. Using smart contracts, blockchain restructures every step of the financial data flow, making the financial data processing process more efficient and automated while reducing the risk of information asymmetry.

[0065] S204: Label the transaction data according to preset rules.

[0066] Specifically, the electronic device also deploys a real-time stream computing platform. After receiving transaction data, the stream computing platform classifies and labels the transaction data. The categories mainly include transaction type (such as contract signing, issuance, repayment, account movement, etc.), risk level (such as high, medium, low), transaction risk type (such as large, suspicious, normal, complex, etc.), transaction direction (inflow or outflow), etc. For example, large transactions can be marked as "high risk", multiple cross-chain transactions can be classified as "complex transactions", and frequently occurring reverse transactions can be marked as "suspicious transactions".

[0067] Furthermore, since the entire consortium chain network is essentially a distributed ledger, in principle, every node receives the same transaction data. However, there is a delay in data synchronization between nodes. To ensure that users of transaction data can obtain financial data transaction information immediately, this embodiment adopts a "quantity for quality" approach. Electronic devices actively monitor transaction events at every node in the consortium chain network, which inevitably generates a large amount of duplicate data. The stream computing platform has the ability to deduplicate data based on distributed primary keys. Leveraging its high throughput, it deduplicates collected transaction data in real time and then labels the deduplicated transaction data.

[0068] S205: Based on the graph data model, the labeled transaction data is converted into a structured relationship including nodes and edges.

[0069] In this embodiment, the graph data model is a graph data structure built based on Neo4j, in which nodes represent transaction entities (such as financial institutions, third-party institutions, etc.), and edges represent transaction amounts, transaction times, and data flows, thereby graphically representing directional flow relationships.

[0070] S206: Use a stream processing framework to perform real-time calculations on the structured relationship, merge repeated paths, and mark the broken nodes of the transaction data to obtain a simplified structured relationship.

[0071] Specifically, the stream processing framework builds a relationship graph based on the above structured relationship based on depth-first search (DFS), marks the breakpoints, and merges the data flows on the same path into one edge when the same flow occurs multiple times within a preset time, so as to optimize the display effect of the graph and reduce redundancy.

[0072] S207. Display the simplified structured relationship in the form of a dynamic graph.

[0073] Optionally, the electronic device can intuitively display the current data flow status of the financial institution through a large visual screen, showing high-risk transactions, suspicious transactions, risk assessment status, etc.

[0074] S208. Based on the structured relationship, extract the credit behavior data of the transaction subject.

[0075] Specifically, the electronic device can construct a credit score for the transaction subject based on the transaction subject's credit behavior, such as whether the transaction subject repays the loan on time, etc. When the credit score drops by more than a preset threshold, it can be considered that the probability of default of the transaction subject has increased.

[0076] S209. Input the credit behavior data into the pre-trained machine learning model to calculate the probability of default.

[0077] In this embodiment, the electronic device constructs a default prediction model based on a support vector machine (SVM) and the Cox proportional risk model. This machine learning model is trained using historical credit behavior data to predict the likelihood of future default by the transaction subject. Furthermore, the model predicts the future probability of default by analyzing the transaction subject's historical time series. Based on past behavior, the model can identify potential default trends.

[0078] S210. When the probability of default is greater than a preset threshold, an early warning is triggered.

[0079] In this embodiment, after the warning is triggered, the electronic device can execute a preset emergency response strategy, including adjusting terms, triggering a review procedure, and notifying relevant personnel.

[0080] S211. Dynamically configure preset compliance rules through the rule engine.

[0081] Pre-set compliance rules are determined based on regulatory requirements.

[0082] Specifically, electronic devices can determine preset compliance rules based on regulatory requirements and dynamically configure the preset compliance rules through a rule engine, such as credit behavior warnings, default risk warnings, data flow warnings, and other preset compliance rules.

[0083] S212. Based on structured relationships, compare the data flow in transaction data with preset compliance rules in real time to identify abnormal data flows.

[0084] S213. When abnormal data flow is detected, an early warning is triggered.

[0085] The electronic device determines whether the data flow in the transaction data is compliant based on the preset compliance rules, thereby identifying abnormal data flow. It can be understood that abnormal data flow refers to data flow that does not comply with the preset compliance rules.

[0086] Detecting abnormal data flows triggers an alert. Similarly, electronic devices can execute pre-set emergency response strategies, including adjusting terms, triggering review procedures, and notifying relevant personnel.

[0087] The financial data processing method of this embodiment (the transaction data processing process can also refer to Figure 4), by establishing a consortium chain network to protect data privacy and achieve transaction information traceability, using cross-chain communication protocols and data verification mechanisms to safely share and integrate data, real-time collection and labeling of transaction data, based on graph data models and stream processing frameworks to build and simplify structured relationships, intuitively display data flow status in the form of dynamic graphs, extract the credit behavior data of transaction entities and input them into machine learning models to calculate the probability of default and trigger early warnings. At the same time, through the rule engine, dynamically configure compliance rules and compare data flows in real time to identify anomalies and trigger early warnings, effectively strengthening the risk management of data throughout its life cycle, preventing data abuse or flowing into high-risk areas, and improving the quality of relevant financial data. Blockchain technology is used to ensure data security and immutability, and cross-chain technology is used to break data silos and increase tracking comprehensiveness, realizing real-time stream computing technology to monitor and warn risks in real time, reduce early warning delays and improve regulatory efficiency, and continuously iterate and optimize preset rules through feedback, ultimately better performing data management work.

[0088] Specifically, the specific implementation method of step S203 includes:

[0089] S2031. Utilize cross-chain communication protocols to establish data collection channels with multiple financial institutions.

[0090] In this step, the IBC protocol is used as the cross-chain communication protocol. Through relay chain technology, a secure data transmission channel between different blockchain platforms is constructed to ensure that data can be shared and integrated safely and efficiently among financial institutions, thereby establishing a data collection channel with multiple financial institutions.

[0091] S2032. Collect transaction data in real time from blockchain nodes of multiple financial institutions through data collection channels.

[0092] Utilizing the Ethereum subscription method, through the established data collection channel, we subscribe to new block generation events, transaction events, etc. of each financial institution's blockchain nodes, and use the HTTP interface to monitor these event data in real time. Once a new transaction or event occurs, relevant data, including transaction data, can be captured immediately.

[0093] S2033. Verify the authenticity of transaction data through a data verification mechanism.

[0094] The data verification mechanism leverages the distributed ledger nature of blockchain to perform preliminary verification of captured transaction data during the data collection process to ensure data integrity and accuracy. Furthermore, it utilizes zero-knowledge proof technology to verify data authenticity during cross-chain transmission without revealing specific data content, thus achieving data consistency and privacy protection.

[0095] S2034. Store the verified transaction data into a real-time processing queue.

[0096] In this step, the authenticity-verified transaction data is sent to the Kafka message queue in real time. It can be understood that the Kafka message queue is a real-time processing queue. At this point, the transaction data is encrypted.

[0097] Accordingly, the specific implementation of step S204 includes:

[0098] S2041. Retrieve verified transaction data from the real-time processing queue.

[0099] S2042. Label the verified transaction data according to preset rules.

[0100] Specifically, as a consumer of the Kafka message queue, the real-time stream computing platform retrieves the verified transaction data stored in the Kafka message queue in real time, decodes and deduplicates the transaction data, and then classifies and labels the transaction data according to preset rules.

[0101] In this embodiment, transaction data is collected in real time through a data collection channel and verified for authenticity using a data verification mechanism, ensuring data integrity and accuracy. Zero-knowledge proof technology is also used to achieve data consistency and privacy protection. Verified transaction data is stored in a real-time processing queue, providing a reliable data foundation for subsequent data processing and analysis, effectively improving the efficiency and accuracy of data collection and processing. Labeling transaction data not only improves data processing efficiency but also provides strong data support for subsequent risk identification, analysis, and early warning. This helps financial institutions promptly identify potential risks and respond quickly, thereby enhancing overall risk management capabilities.

[0102] Figure 5 A schematic diagram of the structure of a financial data processing device provided in this application, such as Figure 5 As shown, the financial data processing device 10 of this embodiment is used to implement the operations corresponding to the electronic device in any of the above method embodiments. The financial data processing device 10 provided in this embodiment includes:

[0103] The collection module 11 is used to collect transaction data generated by the financial business system from the blockchain node in real time;

[0104] Processing module 12, used to label transaction data according to preset rules. Labeling dimensions include transaction type, risk level and data flow direction;

[0105] The processing module 12 is further configured to convert the labeled transaction data into a structured relationship comprising nodes and edges based on a graph data model, wherein the nodes represent the transaction subjects and the edges include the transaction amount, transaction time, and data flow direction;

[0106] The display module 13 is used to display the structured relationship in the form of a dynamic graph.

[0107] In a possible embodiment, the processing module 12 is further configured to use a stream processing framework to perform real-time calculations on the structured relationship, merge repeated paths, and mark broken nodes of the transaction data to obtain a simplified structured relationship.

[0108] The display module 13 is specifically used to display the simplified structured relationship in the form of a dynamic graph.

[0109] In a possible embodiment, the processing module 12 is further configured to extract the credit behavior data of the transaction subject based on the structured relationship;

[0110] Input credit behavior data into a pre-trained machine learning model to calculate the probability of default;

[0111] When the probability of default is greater than the preset threshold, an early warning is triggered.

[0112] In a possible embodiment, the processing module 12 is further configured to compare data flows in the transaction data with preset compliance rules in real time based on structured relationships to identify abnormal data flows;

[0113] When abnormal data flow is detected, an early warning is triggered.

[0114] In a possible embodiment, the processing module 12 is further configured to dynamically configure preset compliance rules through a rule engine, where the preset compliance rules are determined according to regulatory requirements.

[0115] In one possible embodiment, the financial business system includes a plurality of financial institutions;

[0116] The processing module 12 is also used to establish a consortium chain network among multiple financial institutions;

[0117] Deploy cross-chain communication protocols and data verification mechanisms based on the alliance chain network;

[0118] The collection module 11 is specifically used to collect data-verified transaction data in real time from the blockchain nodes of multiple financial institutions through cross-chain communication protocols and data verification mechanisms.

[0119] In one possible embodiment, the processing module 12 is used to establish data collection channels with multiple financial institutions using a cross-chain communication protocol;

[0120] The collection module 11 is used to collect transaction data from blockchain nodes of multiple financial institutions in real time through data collection channels;

[0121] The processing module 12 is further used to verify the authenticity of the transaction data through a data verification mechanism;

[0122] Store verified transaction data into the real-time processing queue;

[0123] Retrieve verified transaction data from the real-time processing queue;

[0124] The transaction data that has passed the verification is labeled according to the preset rules.

[0125] The financial data processing device 10 provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0126] Figure 6 This is a schematic diagram of the structure of an electronic device provided by this application. Figure 6 As shown, the electronic device 20 provided in this embodiment includes: a memory 21 and at least one processor 22. Optionally, the device 20 also includes a communication component 23. The memory 21, the processor 22 and the communication component 23 are connected via a bus 24.

[0127] During the specific implementation process, at least one processor 22 executes the computer-executable instructions stored in the memory 21, so that the at least one processor 22 performs the above method.

[0128] The specific implementation process of the processor 22 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0129] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules in the processor.

[0130] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0131] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0132] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0133] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0134] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0135] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in a device as discrete components.

[0136] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0137] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0140] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0141] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A financial data processing method, characterized in that: include: Collect transaction data generated by financial business systems from blockchain nodes in real time; Labeling the transaction data according to preset rules, where the labeling dimensions include transaction type, risk level, and data flow direction; Based on a graph data model, the labeled transaction data is converted into a structured relationship comprising nodes and edges, wherein the nodes represent transaction entities, and the edges include transaction amounts, transaction times, and data flow directions; The structured relationship is displayed in the form of a dynamic graph.

2. The method according to claim 1, characterized in that Before displaying the structured relationship in the form of a dynamic graph, the method further includes: A stream processing framework is used to perform real-time calculations on the structured relationship, merge repeated paths, and mark the broken nodes of the transaction data to obtain a simplified structured relationship; The structured relationship is displayed in the form of a dynamic graph, specifically: The simplified structured relationship is displayed in the form of a dynamic graph.

3. The method according to claim 1, characterized in that After displaying the structured relationship in the form of a dynamic graph, the method further includes: Based on the structured relationship, extracting the credit behavior data of the transaction subject; Inputting the credit behavior data into a pre-trained machine learning model to calculate the probability of default; When the default probability is greater than a preset threshold, an early warning is triggered.

4. The method according to claim 1, wherein After displaying the structured relationship in the form of a dynamic graph, the method further includes: Based on the structured relationship, the data flow in the transaction data is compared with the preset compliance rules in real time to identify abnormal data flow; When the abnormal data flow is detected, an early warning is triggered.

5. The method according to claim 4, characterized in that The method further comprises: The preset compliance rules are dynamically configured through a rule engine, and the preset compliance rules are determined according to regulatory requirements.

6. The method according to any one of claims 1 to 5, characterized in that The financial business system includes multiple financial institutions; before collecting transaction data generated by the financial business system from the blockchain node in real time, the method further includes: Establishing a consortium chain network among the multiple financial institutions; Deploy cross-chain communication protocols and data verification mechanisms based on the consortium chain network; The real-time collection of transaction data generated by the financial business system from the blockchain node includes: Through the cross-chain communication protocol and data verification mechanism, transaction data that has undergone data verification is collected in real time from the blockchain nodes of the multiple financial institutions.

7. The method according to claim 6, characterized in that The cross-chain communication protocol and data verification mechanism are used to collect data-verified transaction data from the blockchain nodes of the multiple financial institutions in real time, including: Utilizing the cross-chain communication protocol, establishing data collection channels with the multiple financial institutions; Collecting the transaction data in real time from the blockchain nodes of the multiple financial institutions through the data collection channel; Verifying the authenticity of the transaction data through the data verification mechanism; Store verified transaction data into the real-time processing queue; The labeling process of the transaction data according to preset rules includes: Retrieving the verified transaction data from the real-time processing queue; The transaction data that has passed the verification is labeled according to preset rules.

8. A financial data processing device, characterized in that: include: The collection module is used to collect transaction data generated by the financial business system from blockchain nodes in real time; A processing module, configured to label the transaction data according to preset rules, wherein the labeling dimensions include transaction type, risk level, and data flow direction; The processing module is further configured to convert the labeled transaction data into a structured relationship comprising nodes and edges based on a graph data model, wherein the nodes represent transaction entities and the edges comprise transaction amounts, transaction times, and data flow directions; The display module is used to display the structured relationship in the form of a dynamic graph.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images