Financial data intelligent management method and system

Abstract

The invention provides a financial data intelligent management method and system, and the system comprises a multi-source heterogeneous data integration module which collects and standardizes fund flow data, bill information and operation index data; the intelligent analysis and decision module analyzes data through a time convolution network, generates a fund dynamic prediction value, calculates a risk coefficient and generates a transaction analysis report; the risk visualization module is used for constructing a fund association network based on the standardized data set, generating an interactive fund chain graph and displaying risk distribution; the auditing tracking module is used for generating a priority auditing list by adopting a path optimization algorithm and improving the auditing efficiency; and the data center module is used for generating a unique identification code for the financial data by using a block chain technology so as to ensure the security and traceability of the data. According to the invention, an intelligent, real-time and safe solution is provided for financial data management, and the transparency and decision support capability of financial management are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data management, and in particular to a financial data intelligent management method and system. Background Art

[0002] Financial data management refers to the entire process of collecting, storing, processing, analyzing, and reporting a company or organization's financial information. It involves multiple steps, including data entry, cleaning, standardization, analysis, and decision support. The goal is to ensure the accuracy, completeness, and timeliness of financial information. With advances in information technology, financial data management systems are gradually shifting from traditional manual operations to automated, intelligent management models. They utilize technologies such as big data, artificial intelligence, and machine learning to improve the efficiency and accuracy of financial data processing and provide companies with real-time cash flow monitoring and risk warnings. Although existing technologies have made certain progress in financial data management, they still have obvious shortcomings. First, existing management systems generally use static rules to process invoices, bank statements and operational data, and lack dynamic cleaning and timestamp alignment mechanisms, resulting in time series gaps in standardized data sets. Second, conventional audit methods rely on full-scale inspections in fixed periods and have not established a dynamic path assessment model based on the intensity of capital flow and node correlation. In actual applications, approximately 65% ​​of audit resources are consumed on low-risk paths (risk coefficient <0.3), while the average identification delay of high-risk nodes (risk coefficient >2.5) exceeds 36 hours. Finally, existing blockchain solutions only implement single-point data notarization and lack a cross-module identification code concatenation mechanism, resulting in the inability to form a traceable verification chain between standardized data, risk analysis reports and audit plans. Statistics show that the failure rate of operation history tracing in abnormal transactions is as high as 72%, seriously restricting the credibility of audit conclusions. These problems make it difficult for existing financial data management systems to meet the needs of modern enterprises in the face of complex and dynamic financial environments. Summary of the Invention

[0003] In order to solve the technical problems mentioned in the current background technology, the purpose of the present invention is to provide a financial data intelligent management method and system.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A financial data intelligent management system, the system comprising: M1, a multi-source heterogeneous data integration module, collects multi-source heterogeneous data, cleans and standardizes the multi-source heterogeneous data, and outputs a standardized financial data set with a timestamp; M2, an intelligent analysis and decision-making module, analyzes the capital flow patterns of the standardized financial data set using a temporal convolutional network and generates a capital dynamics forecast; calculates the deviation rate between the capital dynamics forecast and the actual capital value to derive a capital risk coefficient; further determines whether the capital risk coefficient is abnormal through threshold comparison and outputs a transaction analysis and decision report; M3, a risk visualization module, constructs a capital association network topology model based on the standardized financial data set, calculates the risk thermal value through the capital association network topology model, and finally generates an interactive capital chain map with the risk thermal value through a three-dimensional rendering engine; M4, the audit tracking module, generates a priority audit list using a path optimization algorithm based on the risk heat value distribution in the capital chain map, and outputs an intelligent audit plan with a time window constraint that is bound to the blockchain identification code; M5, the data hub module, establishes a blockchain distributed ledger to store full-process data assets, forming a traceable data relationship chain connected by blockchain identification codes.

[0005] Furthermore, the multi-source heterogeneous data includes cash flow data, structured bill information and operating indicator data; the cash flow data is obtained through a bank transaction interface, the structured bill information is obtained through a tax invoice parser, and the operating indicator data is obtained through an enterprise resource planning adapter.

[0006] Furthermore, the standardized financial data set is modeled as a feature vector sequence in chronological order. X ,and ,in, Indicates the The financial feature vector at each time point, T is the total time length; Will The financial feature vector at time Input time convolution network to extract temporal dynamic features and calculate The hidden state feature vector at time , the specific calculation formula is:

[0007] in, for Hidden state feature vector at time t; The input time series financial feature vector at time point The value of is the length of the convolution kernel; is the dilation coefficient of the dilated convolution; For the The convolution weight matrix corresponding to the time step; is the bias term; is a nonlinear activation function; Based on the Hidden state at the moment For the future The fund flow at each moment is predicted, and the prediction formula is:

[0008] in, Indicates from Time to The forecast value of fund flow at the moment; is the prediction function; is the prediction function parameter; Will The predicted value of capital flow at the time and actual value of funds For comparison, the actual value of the funds is obtained through bank transaction flow, and the calculation Time deviation rate :

[0009] Based on the Time deviation rate Corresponding calculated standard deviation :

[0010] in, is the sample size, which represents the total number of historical deviation rate data points; Based on the Time deviation rate and standard deviation calculate Capital risk factor at the moment :

[0011] Setting thresholds is the standard deviation 2 times, that is ;like Exceeding the set threshold , it is determined to be abnormal capital flow; if Does not exceed the set threshold , then it is determined that the capital flow is normal; Based on the capital risk coefficient Different transaction analysis and decision reports are generated depending on whether there is an abnormality. The transaction analysis and decision reports are divided into normal transaction analysis and decision reports and abnormal transaction analysis and decision reports.

[0012] Furthermore, the step of calculating the risk thermal value includes calculating the amount of capital flow, calculating the frequency of capital flow, calculating the historical abnormal risk score, calculating the capital flow risk coefficient and calculating the risk thermal value; The formula for calculating the amount of funds flowing between two nodes is as follows:

[0013] in, For nodes To Node The amount of funds flowing between For the selected time interval; Indicates at a point in time τ On the node To Node The amount of cash flow; The formula for calculating the frequency of capital flow between two nodes is as follows:

[0014] in, For nodes To Node The number of fund flows between is the indicator function; The historical abnormal risk score is calculated based on the amount of funds flow and the frequency of funds flow. The historical abnormal risk score calculation formula of the two nodes is as follows:

[0015] in, For nodes To Node Historical risk assessment scores between; The weighting factor for scoring the amount of capital flow is used to measure the proportion of the amount's impact on the overall risk score; The weighting factor for the frequency of fund flows is used to measure the impact of frequency on the overall risk score; The maximum amount of funds flowing between all node pairs; It is the maximum number of fund flows between all node pairs.

[0016] Furthermore, the margin is calculated based on the amount of capital flow, frequency of capital flow and historical abnormal risk score. The capital flow risk coefficient , that is, the capital flow risk of this side, is calculated as follows:

[0017] in, 、 and are weight factors, representing the influence of capital flow amount, capital flow frequency and abnormal risk score on capital flow risk coefficient respectively; Calculate the risk heat value of each node based on the capital flow risk coefficient , to reflect the risk level of the node. The risk thermal value is obtained by weighted summation of the risk coefficients of all adjacent edges of the node. The calculation formula is:

[0018] in, For nodes The set of adjacent nodes of node Other nodes with capital flow; is the weight, which indicates the intensity of capital flow; The generated interactive capital chain map is visualized based on the capital association network and the risk heat value. Each node and edge in the map displays different colors or thicknesses according to its corresponding risk heat value and risk coefficient. It also supports visualization and interactive functions of nodes and edges, where the color of the node is used to represent its corresponding risk heat value, and the color or thickness of the edge reflects the risk intensity of the capital flow. At the same time, users can view detailed capital flow data and risk coefficient information by clicking on nodes or edges, and conduct in-depth analysis of the overall network through zooming and rotating functions.

[0019] Furthermore, the steps of generating a priority audit list using the path optimization algorithm include node sorting, path evaluation, path selection and sorting, and generation of a priority audit list; The node sorting is based on the risk heat value of the node in the capital chain map , sort the nodes from high to low, give priority to auditing nodes with higher risk heat values, and the order of nodes is expressed as ,in, Indicates the number Nodes are numbered nodes ; Similarly, Indicates the number Nodes are numbered nodes ; The total number of nodes that need to be audited; The path assessment is to analyze the capital flow path between each high-risk node and other nodes. The risk value of the path is determined by the amount and frequency of capital flow between nodes. The specific assessment formula is:

[0020] in, Indicates a numbered node To numbered node Path risk value; Indicates a numbered node To the middle numbered node The intensity of capital flows; Intermediate numbered nodes To numbered node The intensity of capital flows; is the total number of nodes involved in the path; The path selection and sorting is based on the risk value of each path ,select the path with higher risk value and sort it according to the total risk value of the path, giving priority to auditing the nodes with higher risk on the path; Generate a priority audit node sequence and its related paths based on a path optimization algorithm. The priority audit list includes a high-risk node screening sequence and related transaction tracing rules; The high-risk node screening order is to sort the nodes from high to low according to the risk heat value, and give priority to auditing high-risk nodes; the related transaction tracing rule is to trace the associated transaction paths and capital flows of each high-risk node to discover potential abnormal transactions.

[0021] Furthermore, the intelligent audit scheme includes a high-risk node screening order sorted by risk heat value and related transaction tracing rules, while taking into account time window constraints to ensure that audit activities are performed within a specific time. Each audit scheme is bound to a unique blockchain identification code.

[0022] A method for intelligent management of financial data, comprising the following steps: S1. Collect financial data from multiple sources, including cash flow data, bill information, and operational indicator data, cleanse and standardize this data, and output a standardized financial data set with a timestamp; S2. Analyze the standardized financial data set using a temporal convolutional network to extract capital flow patterns and generate a capital dynamics forecast value. Calculate the deviation rate between the capital dynamics forecast value and the actual capital flow value to obtain a capital risk coefficient. Determine whether the risk coefficient is abnormal based on a threshold value and generate a transaction analysis and decision report. S3. Construct a capital association network topology model based on the standardized financial data set, calculate the risk thermal value, and use a three-dimensional rendering engine to generate an interactive capital chain map to display the risk distribution in capital flow and support user interaction with the map; S4. Based on the risk heat value in the capital chain map, an audit list is generated using a path optimization algorithm, high-risk nodes and related paths are audited first, and an intelligent audit plan with time window constraints is output; S5. Use blockchain technology to generate unique identification codes for all financial data, store standardized financial data sets, transaction analysis and decision reports, interactive capital chain maps and audit plans in the blockchain, form a traceable data relationship chain, and ensure the traceability of financial data throughout its life cycle.

[0023] Compared with the prior art, the advantages of the present invention are: 1. This invention breaks through the structural barriers of traditional heterogeneous data sources, achieving dynamic adaptation and cross-domain semantic alignment of tax receipts, bank statements, and operational indicators. Through high-precision timestamp calibration and spatiotemporal consistency modeling, it builds a global standardized financial data base, eliminates feature drift and information entropy decay caused by data silos, and provides unbiased input for high-level analysis. 2. Based on the dynamic feature extraction of the capital flow network topology, this invention establishes a node risk thermal value assessment system and a path risk intensity quantification model. It uses a multi-dimensional risk propagation algorithm to achieve dynamic optimization configuration of audit paths, significantly improving the early identification capability and response efficiency of high-risk associated nodes in complex capital networks. 3. This invention integrates blockchain distributed ledger technology and cryptographic hash algorithms to build a full-lifecycle traceability network for cross-module data assets. Through the smart contract binding mechanism of unique identification codes, it forms a full-link verifiability architecture from original transaction data, risk analysis maps to audit decisions, and establishes a mathematically credible foundation for financial data governance. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] Figure 1 Schematic diagram of the system workflow of the present invention; Figure 2 This is a flow chart of the intelligent analysis and decision-making module of the present invention; Figure 3 It is a schematic diagram of the risk thermal value calculation process of the present invention. DETAILED DESCRIPTION

[0026] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] To achieve the above objectives, the present invention is implemented through the following technical solutions: the present invention provides an intelligent financial data management system, such as Figure 1-Figure 3 As shown, the system includes: M1, a multi-source heterogeneous data integration module, which collects multi-source heterogeneous data, cleans and standardizes the multi-source heterogeneous data, and outputs a standardized financial data set with a timestamp and a blockchain identification code attached; The multi-source heterogeneous data includes cash flow data, structured bill information, and operational indicator data; the cash flow data is obtained through a bank transaction interface, the structured bill information is obtained through a tax invoice parser, and the operational indicator data is obtained through an enterprise resource planning adapter; In this embodiment, the tax invoice parser is combined with optical character recognition technology to automatically identify and extract key fields from paper and electronic invoices, such as invoice number, amount, tax rate, supplier information, etc., and convert the information into structured data through the tax invoice parser; In this embodiment, the enterprise resource planning adapter is used to automatically extract key operational data, such as revenue, cost, gross profit margin, inventory status, order quantity, etc., from the enterprise's enterprise resource planning system. The data comes from various departments and business modules of the enterprise. The adapter is connected to the enterprise resource planning system through the interface of the adapter to obtain relevant data in real time. The extracted operational indicator data is organized into a structured format. During the data cleaning process, data quality is improved by deleting duplicate records, filling in missing data, and correcting outliers. Standardization includes unifying the formats of fields such as date, time, and amount, ensuring that all data items use uniform naming conventions and units, and ensuring data type consistency. These steps ensure that heterogeneous data from different data sources can be compatible, compared, and used in subsequent analysis. The standardized financial data set is attached with a blockchain identification code. The blockchain identification code is a unique identity generated for each data record based on blockchain technology. It is a string of characters obtained by encrypting the data content through a hash algorithm. It is unique and cannot be tampered with. Specifically, when the standardized financial data set is generated, the system will encrypt and hash each data content (such as time, amount and transaction method) to generate a unique identification code, and write the identification code into the blockchain together with the data. Once the record is on the chain, it cannot be modified or deleted.

[0028] M2, an intelligent analysis and decision-making module, analyzes the capital flow patterns of the standardized financial data set using a temporal convolutional network and generates a capital dynamics forecast; calculates the deviation rate between the capital dynamics forecast and the actual capital value to derive a capital risk coefficient; further determines whether the capital risk coefficient is abnormal through threshold comparison and outputs a transaction analysis and decision report; 1) Model the standardized financial data set output from the M1 module into a feature vector sequence in chronological order X ,and ,in, Indicates the The financial feature vector at each time point, T is the total time length; 2) The financial feature vector at time Input time convolution network to extract temporal dynamic features and calculate The hidden state feature vector at time , the specific calculation formula is:

[0029] in, for Hidden state feature vector at time t; The input time series financial feature vector at time point The value of is the length of the convolution kernel; is the dilation coefficient of the dilated convolution; For the The convolution weight matrix corresponding to the time step; is the bias term; is a nonlinear activation function; In this embodiment, the expansion coefficient The value of is 2; the bias term The value of is 0.1.

[0030] 3) Based on the Hidden state at the moment For the future The fund flow at each moment is predicted, and the prediction formula is:

[0031] in, Indicates from Time to The forecast value of fund flow at the moment; is the prediction function; is the prediction function parameter; 4) The predicted value of capital flow at the time and actual value of funds For comparison, the actual value of the funds is obtained through bank transaction flow, and the calculation Time deviation rate :

[0032] Based on the Time deviation rate Corresponding calculated standard deviation :

[0033] in, is the sample size, which represents the total number of historical deviation rate data points; 5) Based on the Time deviation rate and standard deviation calculate Capital risk factor at the moment :

[0034] Setting thresholds is the standard deviation 2 times, that is ;like Exceeding the set threshold , it is determined to be abnormal capital flow; if Does not exceed the set threshold , then it is determined that the capital flow is normal; 6) Based on the risk factor of the funds Generate different transaction analysis and decision reports based on whether there is an abnormality; When the capital risk coefficient Under normal circumstances, a normal transaction analysis and decision report will be generated. The report content includes: the predicted and actual value of capital flow, deviation rate, risk factor, and normal risk judgment (capital flow is stable, in line with expectations, and risk is low); When the capital risk coefficient When an abnormality occurs, an abnormal transaction analysis and decision report is generated. The report content includes: the predicted and actual value of capital flow, the deviation rate, the risk factor, and an abnormal risk warning (the capital flow is abnormal, there is a high risk, and it is recommended to take measures to adjust it). This embodiment provides relevant recommended measures: ① Immediately review the relevant capital flow data to identify potential errors or abnormalities; ② Strengthen monitoring of capital outflows to prevent possible financial risks; ③ Take capital adjustment measures based on the risk situation to ensure the health and stability of capital flow.

[0035] M3, a risk visualization module, constructs a capital association network topology model based on the standardized financial data set, calculates the risk thermal value through the capital association network topology model, and finally generates an interactive capital chain map with the risk thermal value through a three-dimensional rendering engine.

[0036] The steps of calculating the risk thermal value include calculating the capital flow amount, calculating the capital flow frequency, calculating the historical abnormal risk score, calculating the capital flow risk coefficient and calculating the risk thermal value; 1) Calculate the amount of cash flow The formula for calculating the amount of funds flowing between two nodes is as follows:

[0037] in, For nodes To Node The amount of funds flowing between For the selected time interval; Indicates at a point in time τ On the node To Node The amount of cash flow.

[0038] 2) Calculate the frequency of fund flows The formula for calculating the frequency of capital flow between two nodes is as follows:

[0039] in, For nodes To Node The number of fund flows between is the indicator function; If at the time τ On the node To Node If there is indeed a flow of funds between The value of is 1; if there is no capital flow, then The value of is 0.

[0040] 3) Calculate historical anomaly risk score The historical abnormal risk score is calculated based on the amount of funds flow and the frequency of funds flow. The historical abnormal risk score calculation formula of the two nodes is as follows:

[0041] in, For nodes To Node Historical risk assessment scores between; The weighting factor for scoring the amount of capital flow is used to measure the proportion of the amount's impact on the overall risk score; The weighting factor for the frequency of fund flows is used to measure the impact of frequency on the overall risk score; The maximum amount of funds flowing between all node pairs; The maximum number of fund flows between all node pairs; In this embodiment, the weight factor The value of is 0.7; the weight factor The value is 0.3.

[0042] 4) Calculate the capital flow risk coefficient Calculate the margin based on the amount of funds flow, frequency of funds flow and historical abnormal risk score The capital flow risk coefficient , that is, the capital flow risk of this side, is calculated as follows:

[0043] in, 、 and are weight factors, representing the influence of capital flow amount, capital flow frequency and abnormal risk score on capital flow risk coefficient respectively; In this embodiment, the weight factor The value of is 0.5; the weight factor The value of is 0.2; the weight factor The value is 0.3.

[0044] 5) Calculate the risk heat value Calculate the risk heat value of each node based on the capital flow risk coefficient , to reflect the risk level of the node. The risk thermal value is obtained by weighted summation of the risk coefficients of all adjacent edges of the node. The calculation formula is:

[0045] in, For nodes The set of adjacent nodes of node Other nodes with capital flow; is the weight, which indicates the intensity of capital flow; In this embodiment, the weight The value of is 0.5.

[0046] The generated interactive capital chain map is visualized based on the capital association network and the risk heat value. Each node and edge in the map displays different colors or thicknesses according to its corresponding risk heat value and risk coefficient. It also supports visualization and interactive functions of nodes and edges, where the color of the node is used to represent its corresponding risk heat value, and the color or thickness of the edge reflects the risk intensity of the capital flow. At the same time, users can view detailed capital flow data and risk coefficient information by clicking on nodes or edges, and conduct in-depth analysis of the overall network through zooming and rotating functions.

[0047] This embodiment provides an example: the color of the node gradually changes from green (low risk) to red (high risk), and the thickness of the edge is adjusted according to the risk intensity; Ultimately, the generated interactive capital chain map is embedded in the visual interface of the financial management system for use by decision makers and auditors. Through this map, users can intuitively identify potential high-risk capital flows and abnormal situations.

[0048] M4, the audit tracking module, generates a priority audit list using a path optimization algorithm based on the risk heat value distribution in the capital chain map, and outputs an intelligent audit plan with a time window constraint that is bound to the blockchain identification code; The steps of generating a priority audit list using the path optimization algorithm include node sorting, path evaluation, path selection and sorting, and generation of a priority audit list; 1) Node sorting The node sorting is based on the risk heat value of the node in the capital chain map , sort the nodes from high to low, give priority to auditing nodes with higher risk heat values, and the order of nodes is expressed as ,in, Indicates the number Nodes are numbered nodes ; Similarly, Indicates the number Nodes are numbered nodes ; The total number of nodes that need to be audited.

[0049] 2) Path evaluation The path assessment is to analyze the capital flow path between each high-risk node and other nodes. The risk value of the path is determined by the amount and frequency of capital flow between nodes. The specific assessment formula is:

[0050] in, Indicates a numbered node To numbered node Path risk value; Indicates a numbered node To the middle numbered node The intensity of capital flows; Intermediate numbered nodes To numbered node The intensity of capital flows; is the total number of nodes involved in the path.

[0051] 3) Path selection and sorting The path selection and sorting is based on the risk value of each path , select the path with higher risk value and sort it according to the total risk value of the path, giving priority to auditing the nodes with higher risk on the path.

[0052] 4) Generation of priority audit list Generate a priority audit node sequence and its related paths based on a path optimization algorithm. The priority audit list includes a high-risk node screening sequence and related transaction tracing rules; The high-risk node screening order is to sort the nodes from high to low according to the risk heat value, and give priority to auditing high-risk nodes; the related transaction tracing rule is to trace the transaction path and capital flow associated with each high-risk node to discover potential abnormal transactions; The output intelligent audit plan includes the high-risk node screening order sorted by risk heat value and the related transaction tracing rules, while taking into account the time window constraints to ensure that the audit activities are carried out within a specific time. Each audit plan is bound to a unique blockchain identification code to ensure that its data cannot be tampered with and is traceable, thereby enhancing the transparency and credibility of the audit process.

[0053] M5, the data hub module, establishes a blockchain distributed ledger to store full-process data assets, forming a traceable data relationship chain connected by blockchain identification codes.

[0054] In this embodiment, the blockchain distributed ledger is used for data storage and management. The full-process data assets include the standardized financial data set, transaction analysis and decision-making report, interactive capital chain map and audit plan. At the same time, the blockchain identification code is used to generate a unique identity for each piece of data, and different data elements are connected through the identification code to form a traceable data relationship chain; The full-process data assets support data traceability, accessibility and security, as well as the establishment of data relationship chains; The traceability of data means that once all financial data and related documents (such as reports, maps, etc.) are recorded in the blockchain, each data read can be traced back to its source and modification history through the blockchain identification code to ensure that the data can be verified at any time, prevent data tampering, and improve the transparency of the system; The accessibility and security mentioned above are achieved by ensuring the integrity and immutability of financial data through blockchain technology. At the same time, through a rights management mechanism, different roles (such as auditors, decision makers, etc.) can access the corresponding data according to their authorization. The decentralized nature of blockchain avoids the reliance on a single control point, making data storage and management more decentralized, thereby improving the security and anti-attack capabilities of the system. This structure not only ensures the transparency and traceability of data, but also prevents data tampering or loss, ensuring the security and reliability of financial data. The establishment of the data relationship chain is to connect different data elements (such as financial data, analysis reports, and capital chain maps) through a data relationship chain through blockchain identification codes. The establishment and maintenance of the relationship chain ensures a close connection between the data, so that the output results of each module can verify and support each other.

[0055] A method for intelligent management of financial data, comprising the following steps: S1. Collect financial data from multiple sources, including cash flow data, bill information, and operational indicator data, cleanse and standardize this data, and output a standardized financial data set with a timestamp; S2. Analyze the standardized financial data set using a temporal convolutional network to extract capital flow patterns and generate a capital dynamics forecast value. Calculate the deviation rate between the capital dynamics forecast value and the actual capital flow value to obtain a capital risk coefficient. Determine whether the risk coefficient is abnormal based on a threshold value and generate a transaction analysis and decision report. S3. Construct a capital association network topology model based on the standardized financial data set, calculate the risk thermal value, and use a three-dimensional rendering engine to generate an interactive capital chain map to display the risk distribution in capital flow and support user interaction with the map; S4. Based on the risk heat value in the capital chain map, an audit list is generated using a path optimization algorithm, high-risk nodes and related paths are audited first, and an intelligent audit plan with time window constraints is output; S5. Use blockchain technology to generate unique identification codes for all financial data, store standardized financial data sets, transaction analysis and decision reports, interactive capital chain maps and audit plans in the blockchain, form a traceable data relationship chain, and ensure the traceability of financial data throughout its life cycle.

[0056] The present invention provides a method and system for intelligent management of financial data, aiming to address the deficiencies of existing financial management systems in data integration, capital flow forecasting, risk analysis and auditing. The method standardizes and cleans data from different sources through a multi-source heterogeneous data integration module to ensure the consistency and comparability of financial data. The method uses a temporal convolutional network to intelligently analyze the patterns of capital flow, and determines capital flow anomalies through risk coefficients to generate timely transaction analysis reports. The method provides an intuitive capital flow risk visualization tool through the calculation of capital association networks and risk thermal values, combined with three-dimensional rendering technology, to enhance the efficiency and accuracy of capital flow monitoring. In the audit tracking module, the audit process is optimized through a path optimization algorithm to ensure priority auditing of high-risk nodes and improve the intelligence and timeliness of audit decisions. Finally, the method utilizes blockchain technology to achieve tamper-proof storage of financial data, and constructs a traceable data relationship chain through blockchain identification codes to ensure the security and integrity of the data. Through these technical means, the present invention significantly improves the intelligence, real-time nature and security of the financial data management system, and provides strong support for the financial risk control and decision-making of enterprises.

[0057] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0058] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A financial data intelligent management system, characterized in that: The system includes: M1, a multi-source heterogeneous data integration module, collects multi-source heterogeneous data, cleans and standardizes the multi-source heterogeneous data, and outputs a standardized financial data set with a timestamp; M2, an intelligent analysis and decision-making module, analyzes the capital flow patterns of the standardized financial data set using a temporal convolutional network and generates a capital dynamics forecast; calculates the deviation rate between the capital dynamics forecast and the actual capital value to derive a capital risk coefficient; further determines whether the capital risk coefficient is abnormal through threshold comparison and outputs a transaction analysis and decision report; M3, a risk visualization module, constructs a capital association network topology model based on the standardized financial data set, calculates the risk thermal value through the capital association network topology model, and finally generates an interactive capital chain map with the risk thermal value through a three-dimensional rendering engine; M4, the audit tracking module, generates a priority audit list using a path optimization algorithm based on the risk heat value distribution in the capital chain map, and outputs an intelligent audit plan with a time window constraint that is bound to the blockchain identification code; M5, the data hub module, establishes a blockchain distributed ledger to store full-process data assets, forming a traceable data relationship chain connected by blockchain identification codes.

2. The intelligent financial data management system according to claim 1, characterized in that: The multi-source heterogeneous data includes cash flow data, structured bill information and operating indicator data; the cash flow data is obtained through a bank transaction interface, the structured bill information is obtained through a tax invoice parser, and the operating indicator data is obtained through an enterprise resource planning adapter.

3. The intelligent financial data management system according to claim 1, characterized in that: The standardized financial data set is modeled as a sequence of feature vectors in chronological order. X ,and ,in, Indicates the The financial feature vector at each time point, T is the total time length; Will The financial feature vector at time Input time convolution network to extract temporal dynamic features and calculate The hidden state feature vector at time , the specific calculation formula is: in, for Hidden state feature vector at time t; The input time series financial feature vector at time point The value of is the length of the convolution kernel; is the dilation coefficient of the dilated convolution; For the The convolution weight matrix corresponding to the time step; is the bias term; is a nonlinear activation function; Based on the Hidden state at the moment For the future The fund flow at each moment is predicted, and the prediction formula is: in, Indicates from Time to The predicted value of fund flow at the moment; is the prediction function; is the prediction function parameter; Will The predicted value of capital flow at the time and actual value of funds For comparison, the actual value of the funds is obtained through bank transaction flow, and the calculation Time deviation rate : Based on the Time deviation rate Corresponding calculated standard deviation : in, is the sample size, which represents the total number of historical deviation rate data points; Based on the Time deviation rate and standard deviation calculate Capital risk factor at the moment : Setting thresholds is the standard deviation 2 times of ;like Exceeding the set threshold , it is determined to be abnormal capital flow; if Does not exceed the set threshold , then it is determined that the capital flow is normal; Based on the capital risk coefficient Different transaction analysis and decision reports are generated depending on whether there is an abnormality. The transaction analysis and decision reports are divided into normal transaction analysis and decision reports and abnormal transaction analysis and decision reports.

4. The intelligent financial data management system according to claim 1, characterized in that: The steps of calculating the risk thermal value include calculating the capital flow amount, calculating the capital flow frequency, calculating the historical abnormal risk score, calculating the capital flow risk coefficient and calculating the risk thermal value; The formula for calculating the capital flow amount between two nodes in the capital association network topology model is as follows: in, For nodes To Node The amount of funds flowing between For the selected time interval; Indicates at a point in time τ On the node To Node The amount of cash flow; The formula for calculating the capital flow frequency between two nodes in the capital association network topology model is as follows: in, For nodes To Node The number of fund flows between is the indicator function; The historical abnormal risk score is calculated based on the amount of funds flow and the frequency of funds flow. The historical abnormal risk score calculation formula of the two nodes is as follows: in, For nodes To Node Historical risk assessment scores between; The weighting factor for scoring the amount of capital flow is used to measure the proportion of the amount's impact on the overall risk score; The weighting factor for the frequency of fund flows is used to measure the impact of frequency on the overall risk score; The maximum amount of funds flowing between all node pairs; It is the maximum number of fund flows between all node pairs.

5. The intelligent financial data management system according to claim 4, characterized in that: Calculate the margin based on the amount of funds flow, frequency of funds flow and historical abnormal risk score The capital flow risk coefficient , that is, the capital flow risk of this side, is calculated as follows: in, 、 and are weight factors, representing the influence of capital flow amount, capital flow frequency and abnormal risk score on capital flow risk coefficient respectively; Calculate the risk heat value of each node based on the capital flow risk coefficient , to reflect the risk level of the node. The risk thermal value is obtained by weighted summation of the risk coefficients of all adjacent edges of the node. The calculation formula is: in, For nodes The set of adjacent nodes of node Other nodes with capital flow; is the weight, which indicates the intensity of capital flow; The generated interactive capital chain map is visualized based on the capital association network and the risk heat value. Each node and edge in the map displays different colors or thicknesses according to its corresponding risk heat value and risk coefficient. It also supports visualization and interactive functions of nodes and edges, where the color of the node is used to represent its corresponding risk heat value, and the color or thickness of the edge reflects the risk intensity of the capital flow. At the same time, users can view detailed capital flow data and risk coefficient information by clicking on nodes or edges, and conduct in-depth analysis of the overall network through zooming and rotating functions.

6. The intelligent financial data management system according to claim 1, characterized in that: The steps of generating a priority audit list using the path optimization algorithm include node sorting, path evaluation, path selection and sorting, and generation of a priority audit list; The node sorting is based on the risk heat value of the node in the capital chain map , sort the nodes from high to low, give priority to auditing nodes with higher risk heat values, and the order of nodes is expressed as ,in, Indicates the number Nodes are numbered nodes ; Similarly, Indicates the number Nodes are numbered nodes ; The total number of nodes that need to be audited; The path assessment is to analyze the capital flow path between each high-risk node and other nodes. The risk value of the path is determined by the amount and frequency of capital flow between nodes. The specific assessment formula is: in, Indicates a numbered node To numbered node Path risk value; Indicates a numbered node To the middle numbered node The intensity of capital flows; Intermediate numbered nodes To numbered node The intensity of capital flows; is the total number of nodes involved in the path; The path selection and sorting is based on the risk value of each path ,select the path with higher risk value and sort it according to the total risk value of the path, giving priority to auditing the nodes with higher risk on the path; Generate a priority audit node sequence and its related paths based on a path optimization algorithm. The priority audit list includes a high-risk node screening sequence and related transaction tracing rules; The high-risk node screening order is to sort the nodes from high to low according to the risk heat value, and give priority to auditing high-risk nodes; the related transaction tracing rule is to trace the associated transaction paths and capital flows of each high-risk node to discover potential abnormal transactions.

7. The intelligent financial data management system according to claim 1, characterized in that: The intelligent audit scheme includes the order of screening high-risk nodes sorted by risk heat value and the rules for tracing related transactions, while taking into account time window constraints to ensure that audit activities are carried out within a specific time. Each audit scheme is bound to a unique blockchain identification code.

8. A method for intelligent management of financial data, characterized in that: The method comprises the following steps: S1. Collect financial data from multiple sources, including cash flow data, bill information, and operational indicator data, cleanse and standardize this data, and output a standardized financial data set with a timestamp; S2. Analyze the standardized financial data set using a temporal convolutional network to extract capital flow patterns and generate a capital dynamics forecast value. Calculate the deviation rate between the capital dynamics forecast value and the actual capital flow value to obtain a capital risk coefficient. Determine whether the risk coefficient is abnormal based on a threshold value and generate a transaction analysis and decision report. S3. Construct a capital association network topology model based on the standardized financial data set, calculate the risk thermal value, and use a three-dimensional rendering engine to generate an interactive capital chain map to display the risk distribution in capital flow and support user interaction with the map; S4. Based on the risk heat value in the capital chain map, an audit list is generated using a path optimization algorithm, high-risk nodes and related paths are audited first, and an intelligent audit plan with time window constraints is output; S5. Use blockchain technology to generate unique identification codes for all financial data, store standardized financial data sets, transaction analysis and decision reports, interactive capital chain maps and audit plans in the blockchain, form a traceable data relationship chain, and ensure the traceability of financial data throughout its life cycle.

Images