A data model-based enterprise cash flow data monitoring system and method

Abstract

This invention discloses a data model-based enterprise cash flow data monitoring system and method, belonging to the field of data analysis technology. The enterprise cash flow data monitoring method specifically includes the following steps: collecting relevant enterprise data; preprocessing the relevant enterprise data; establishing a data model based on the preprocessed relevant enterprise data; calculating the risk assessment value of each data node based on the data model; visually displaying the global risk index through a 3D dashboard based on the calculated risk assessment value of each data node; and visually monitoring the cash flow data through a heatmap matrix. This invention combines a 3D dashboard and a heatmap matrix for visualization, intuitively presenting the overall risk situation and local abnormal behaviors, improving the interpretability of risk identification and the efficiency of monitoring.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to a data model-based enterprise cash flow data monitoring system and method. Background Technology

[0002] With the development of the digital economy and the increasing complexity of corporate financial activities, the security and compliance of corporate cash flows have become increasingly prominent issues. Due to the high frequency of transactions, the large number of participants, and the complexity of fund paths, traditional fund supervision methods are insufficient to comprehensively and in real time grasp the actual flow of corporate funds and potential risks. Therefore, there is an urgent need to build an efficient, intelligent, data-driven corporate cash flow supervision mechanism.

[0003] Currently, some enterprises primarily rely on static reports and periodic audits for cash flow monitoring. This approach suffers from drawbacks such as poor timeliness, information lag, and significant human intervention. While some institutions have begun to introduce data visualization and graph data analysis technologies, these are mostly focused on monitoring total cash flows or identifying individual anomalies, lacking the ability to deeply model the overall cash flow network structure and assess systemic risks. Furthermore, monitoring of dynamic risk trends is relatively weak, failing to effectively identify potential systemic risk nodes and their diffusion paths.

[0004] In recent years, the development of graph models and machine learning algorithms has provided strong support for constructing complex relationship networks and dynamic evolutionary analysis. However, a systematic approach integrating data collection, preprocessing, graph modeling, indicator extraction, and visual monitoring is still lacking. Especially in risk visualization, effectively integrating key indicators from multiple dimensions to form comprehensive risk monitoring and dynamically displaying it through visualization remains a significant technological gap. Therefore, there is an urgent need to propose a data model-based method for monitoring corporate cash flow data, enabling intelligent and visual monitoring of corporate cash flow data. Summary of the Invention

[0005] The purpose of this invention is to provide a data model-based enterprise cash flow data monitoring system and method to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring enterprise cash flow data based on a data model, wherein the method specifically includes the following steps:

[0007] Collect relevant enterprise data;

[0008] The relevant data of the enterprise is preprocessed;

[0009] A data model is established based on the preprocessed enterprise-related data;

[0010] Based on the data model, calculate the risk assessment value of each data node;

[0011] Based on the calculated risk assessment value of each data node, the global risk index is visualized and displayed through a 3D dashboard; and the flow data is visualized and monitored through a heat map matrix.

[0012] Obtain the company's cash flow data through legal means such as its own financial system and bank account inquiries;

[0013] Specifically:

[0014] Collect enterprise-related data, including enterprise registration information and enterprise transaction data;

[0015] The enterprise transaction data includes transaction counterparties and transaction fund flow data;

[0016] The relevant enterprise data is preprocessed, specifically as follows:

[0017] The preprocessing includes data alignment and data normalization;

[0018] The data alignment is used to obtain continuous transaction fund flow data;

[0019] Preferably, the data normalization is Max-Min normalization;

[0020] Based on the preprocessed enterprise-related data, a data model is established, specifically as follows:

[0021] The data model includes data nodes, directed data edges, and edge weights;

[0022] The data nodes include enterprises, trading partners, and intermediary institutions;

[0023] The directed edges in the data are used to represent transaction fund flow data between data nodes;

[0024] The edge weights include flow time data and the number of intermediate nodes;

[0025] Based on the data model, the risk assessment value of each data node is calculated, specifically including the following steps:

[0026] Construct a weighted transition matrix, and obtain the PageRank of the data node in the data model based on iterative calculation of the weighted transition matrix;

[0027] The formula for calculating PageRank, the system importance in the data model, is as follows:

[0028]

[0029] Where PageRank(u) represents the system importance of data node u; u, v, and k represent the data node labels; N represents the total number of data nodes in the data model, where N is a positive integer; d represents the damping coefficient; B u The set of all data nodes pointing to data node u is represented; PageRank(v) represents the system importance of data node v; w v→u O represents the edge weight from data node v to data node u; v w represents the set of all outgoing target data nodes of data node v; v→k This represents the edge weight from data node v to data node k;

[0030] The edge weights are represented by normalized flow time data.

[0031] Extract the normalized enterprise-related data and normalize the out-degree data of the data nodes in the data model. The ratio of the normalized out-degree data to the enterprise registered capital data in the enterprise-related data is recorded as the capital flow rate.

[0032] The ratio of the number of shortest funding paths passing through a data node to the total number of shortest paths in the data model is denoted as the betweenness centrality. A certain time interval Δ is set, and the betweenness centrality of the same data node before and after the certain time interval Δ is used as the basis to calculate the chain change rate of the betweenness centrality.

[0033] The specific steps for calculating the chain-recurrence rate of change of betweenness centrality are as follows:

[0034] Calculate betweenness centrality: Where BC(i) represents the betweenness centrality of data node i; σ st (i) represents the number of shortest paths from data node s through data node i to data node t; σ st This represents the number of shortest paths from data node s to data node t; (transaction timeliness).

[0035] A certain time interval Δ is set as the preferred option, where Δ can be one natural cycle.

[0036] Store snapshots of the data model (data nodes, directed edges, and edge weights) at regular time intervals Δ.

[0037] Preferably, at least the four most recent Δ data model snapshots are retained for backtracking calculations;

[0038] Calculate the rate of change of betweenness centrality:

[0039] Where ΔBC(i) represents the cycle rate of change of the betweenness centrality of data node i; BC cur (i) represents the betweenness centrality of the current data node i; BC pre (i) represents the betweenness centrality of the data node i before Δ;

[0040] The risk assessment value of a data node is obtained by using the PageRank, cash flow rate, and betweenness centrality rate of the same data node in the data model.

[0041] The formula for representing the risk assessment value of the data node is as follows:

[0042]

[0043] Where RiskScore represents the risk assessment value of the data node; α, β, and γ represent regression coefficients; OutDegree represents the out-degree data of the normalized data node; and Cap represents the registration cost data of the normalized data node.

[0044] As an option,

[0045] The regression coefficients α, β, and γ were obtained by regression fitting of historical default data;

[0046] Based on the calculated risk assessment value of each data node, the global risk index is visualized and displayed through a 3D dashboard; and the flow data is monitored and visualized through a heatmap matrix.

[0047] Preferably, the system importance of the data node is used as the weight, and a global risk index is calculated based on the risk assessment value of the data node. The formula is as follows:

[0048] GlobalRisk=[Σ i＝1 N RiskScore(i)*PageRank(i)] / N*RiskScore(i)_max;

[0049] Where GlobalRisk represents the global risk index; RiskScore(i) represents the risk assessment value of data node i; PageRank(i) represents the system importance of data node i; N represents the total number of data nodes in the data model, where N is a positive integer; and RiskScore_max represents the maximum risk assessment value of all data nodes.

[0050] Optionally, the RiskScore_max can also be set to the maximum risk threshold based on historical data, so that the overall risk can be intuitively perceived by observing the three-dimensional dashboard;

[0051] Optionally, flow data can be visualized and monitored using a heatmap matrix, with the specific representation formula as follows:

[0052] AnomalyScore(i,j)=|w ij -μ ij | / δ ij ;

[0053] Where AnomalyScore(i,j) represents the flow amplitude; w ij μ represents the edge weight (transaction amount) from data node i to data node j; ij δ represents the average transaction value from data node i to data node j during the same historical period; ij This represents the standard deviation of transaction amounts from data node i to data node j during the same historical period.

[0054] A data model-based enterprise cash flow data monitoring system, comprising a data acquisition module, a preprocessing module, a data modeling module, a data node risk assessment module, and a visualization module;

[0055] The data acquisition module is used to collect enterprise-related data, including enterprise registration information and enterprise transaction data; the enterprise transaction data includes transaction objects and transaction fund flow data; and the collected data is stored.

[0056] The preprocessing module is used to preprocess the collected enterprise-related data;

[0057] The data modeling module is used to establish a data model based on the preprocessed enterprise-related data, including data nodes, directed data edges, and edge weights.

[0058] The data node risk assessment module is used to calculate the risk assessment value of each data node based on the data model.

[0059] The visualization module is used to visualize the global risk index through a 3D dashboard and to visualize and monitor flow data through a heat map matrix.

[0060] Specifically:

[0061] The enterprise transaction data is obtained from internal access within the enterprise after authorization.

[0062] Specifically:

[0063] Provides data backup and storage;

[0064] The calculation method for the risk assessment value of the data node is optimized by using the data backup and storage data as historical data.

[0065] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a data model-based method for monitoring enterprise cash flow data, enabling dynamic modeling of enterprise cash flow data. It integrates multi-dimensional indicators such as PageRank, cash flow rate, and the rate of change of betweenness centrality to construct a scientific and reasonable risk assessment system, effectively improving the comprehensiveness and accuracy of risk identification. This method supports real-time monitoring and comprehensive analysis of risks, using graph model snapshots and dynamic indicator calculations to promptly assess the risks of data nodes. Simultaneously, it combines a 3D dashboard and heatmap matrix for visualization, intuitively presenting the overall risk situation and local abnormal behaviors, improving the interpretability of risk identification and regulatory efficiency. By training model parameters with historical risk data, it possesses adaptive learning and optimization capabilities, enhancing model robustness and adaptability. Overall, this method has a high degree of automation and strong applicability, significantly improving the intelligence level and responsiveness of enterprise self-inspection, and has good practical value and promising prospects for promotion. Attached Figure Description

[0066] Figure 1 This is a schematic diagram illustrating the steps of a data model-based method for monitoring enterprise cash flow data according to the present invention.

[0067] Figure 2 This is a schematic diagram of a three-dimensional risk dashboard in Embodiment 2 of the enterprise cash flow data monitoring system based on a data model according to the present invention;

[0068] Figure 3 This is a schematic diagram of the heat map matrix of the flow amplitude in Embodiment 2 of the enterprise capital flow data monitoring system based on the data model of the present invention. Detailed Implementation

[0069] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] Example: Figures 1-3 As shown, the present invention provides a technical solution, a method for monitoring enterprise cash flow data based on a data model, wherein the method for monitoring enterprise cash flow data specifically includes the following steps:

[0071] Collect relevant enterprise data;

[0072] The relevant data of the enterprise is preprocessed;

[0073] A data model is established based on the preprocessed enterprise-related data;

[0074] Based on the data model, calculate the risk assessment value of each data node;

[0075] Based on the calculated risk assessment value of each data node, the global risk index is visualized and displayed through a 3D dashboard; and the flow data is visualized and monitored through a heat map matrix.

[0076] Obtain the company's cash flow data through legal means such as its own financial system and bank account inquiries;

[0077] Specifically:

[0078] Collect enterprise-related data, including enterprise registration information and enterprise transaction data;

[0079] The enterprise transaction data includes transaction counterparties and transaction fund flow data;

[0080] The relevant enterprise data is preprocessed, specifically as follows:

[0081] The preprocessing includes data alignment and data normalization;

[0082] The data alignment is used to obtain continuous transaction fund flow data;

[0083] Preferably, the data normalization is Max-Min normalization;

[0084] Based on the preprocessed enterprise-related data, a data model is established, specifically as follows:

[0085] The data model includes data nodes, directed data edges, and edge weights;

[0086] The data nodes include enterprises, trading partners, and intermediary institutions;

[0087] The directed edges in the data are used to represent transaction fund flow data between data nodes;

[0088] The edge weights include flow time data and the number of intermediate nodes;

[0089] Based on the data model, the risk assessment value of each data node is calculated, specifically including the following steps:

[0090] Construct a weighted transition matrix, and obtain the PageRank of the data node in the data model based on iterative calculation of the weighted transition matrix;

[0091] The formula for calculating PageRank, the system importance in the data model, is as follows:

[0092]

[0093] Where PageRank(u) represents the system importance of data node u; u, v, and k represent the data node labels; N represents the total number of data nodes in the data model; d represents the damping coefficient; B u The set of all data nodes pointing to data node u is represented; PageRank(v) represents the system importance of data node v; w v→u O represents the edge weight from data node v to data node u; v w represents the set of all outgoing target data nodes of data node v; v→k This represents the edge weight from data node v to data node k;

[0094] The edge weights use normalized flow time data;

[0095] Extract the normalized enterprise-related data and normalize the out-degree data of the data nodes in the data model. The ratio of the normalized out-degree data to the enterprise registered capital data in the enterprise-related data is recorded as the capital flow rate.

[0096] The ratio of the number of shortest funding paths passing through a data node to the total number of shortest paths in the data model is denoted as the betweenness centrality. A certain time interval Δ is set, and the betweenness centrality of the same data node before and after the certain time interval Δ is used as the basis to calculate the chain change rate of the betweenness centrality.

[0097] The specific steps for calculating the chain-recurrence rate of change of betweenness centrality are as follows:

[0098] Calculate betweenness centrality: Where BC(i) represents the betweenness centrality of data node i; σ st (i) represents the number of shortest paths from data node s through data node i to data node t; σ st This represents the number of shortest paths from data node s to data node t; (transaction timeliness).

[0099] A certain time interval Δ is set as the preferred option, where Δ can be one natural cycle.

[0100] Store snapshots of the data model (data nodes, directed edges, and edge weights) at regular time intervals Δ.

[0101] Preferably, at least the four most recent Δ data model snapshots are retained for backtracking calculations;

[0102] Calculate the rate of change of betweenness centrality:

[0103] Where ΔBC(i) represents the cycle rate of change of the betweenness centrality of data node i; BC cur (i) represents the betweenness centrality of the current data node i; BC pre (i) represents the betweenness centrality of the data node i before Δ;

[0104] The risk assessment value of a data node is obtained by using the PageRank, cash flow rate, and betweenness centrality rate of the same data node in the data model.

[0105] The formula for representing the risk assessment value of the data node is as follows:

[0106]

[0107] Where RiskScore represents the risk assessment value of a data node; α, β, and γ represent regression coefficients; OutDegree represents the out-degree data of a normalized data node (the transaction data expenditure of the data node); and Cap represents the registration cost data of a normalized data node.

[0108] Example 1: An auto parts manufacturer A (registered capital A');

[0109] Related parties: Supplier B (steel supplier, registered capital B'); Distributor C (agent, registered capital C'); Bank D (cooperative lending institution, registered capital D').

[0110] Monitoring period: Week 1 to Week 4 of Month 20**;

[0111] Transaction record (Week 1) A→B: Procurement of steel (flow time 2 days, 1 intermediate node);

[0112] A→C: Selling products (flow time 1 day, no intermediate nodes);

[0113] B→D: Loan repayment (transfer time 0.5 days, 2 intermediate nodes);

[0114] Normalization is performed using the Max-Min method;

[0115] Using normalized flow time as the weight:

[0116] The weight from A to B is 0.4.

[0117] The weight from A to C is 0.2.

[0118] The weight from B to D is 0.1.

[0119] Obtain the data model;

[0120] 1. PageRank Calculation (Week 1)

[0121] Transition matrix:

[0122] From\To A B C D A 0 0.4 / (0.4+0.2)≈0.667 0.2 / (0.4+0.2)≈0.333 0 B 0 0 0 1.0 C 0 0 0 0 D 0 0 0 0

[0123] Table 1

[0124] Iterative calculation (d = 0.85):

[0125] After 10 iterations, the PageRank stable value is:

[0126] A: 0.316; B: 0.398;

[0127] C: 0.154; D: 0.132;

[0128] Liquidity ratio calculation:

[0129] The out-degree normalized value of B = 0.1 (weight of edge B→D);

[0130] B's liquidity ratio is 1.25;

[0131] Betweenness centrality year-over-year change rate (week 2):

[0132] New transactions in week 2: C→A inflow of 3 million (flow time 0.3 days); Changes in BC value in week 2:

[0133] The BC value of B increased from 0.12 to 0.35;

[0134] ΔBC(B)=(0.35-0.12) / 0.12×100%=191.67%;

[0135] Node risk assessment value (Week 2):

[0136] Based on historical default data, the parameters were simulated as follows: α = 0.6, β = 0.3, γ = 0.1;

[0137] B's risk score:

[0138] RiskScore(B)=0.6×0.398+0.3×1.25+0.1×1.9167=0.789;

[0139] Based on the calculated risk assessment value of each data node, the global risk index is visualized and displayed through a 3D dashboard; and the flow data is monitored and visualized through a heatmap matrix.

[0140] Using the system importance of the data nodes as weights, a global risk index is calculated based on the risk assessment values ​​of the data nodes. The formula is as follows:

[0141] GlobalRisk=[Σ i＝1 N RiskScore(i)*PageRank(i)] / N*RiskScore(i)_max;

[0142] Where GlobalRisk represents the global risk index; RiskScore(i) represents the risk assessment value of data node i; PageRank(i) represents the system importance of data node i; N represents the total number of data nodes in the data model, where N is a positive integer; and RiskScore_max represents the maximum risk assessment value of all data nodes.

[0143] RiskScore_max can also be set as the maximum risk threshold based on historical data, allowing you to intuitively perceive the overall risk by observing the 3D dashboard;

[0144] The flow data is visualized and monitored using a heatmap matrix, with the specific representation formula as follows:

[0145] AnomalyScore(i,j)=|w ij -μ ij | / δ ij ;

[0146] Where AnomalyScore(i,j) represents the flow amplitude; w ij μ represents the edge weight (transaction amount) from data node i to data node j; ij δ represents the average transaction value from data node i to data node j during the same historical period; ij This represents the standard deviation of transaction amounts from data node i to data node j during the same historical period.

[0147] Example 2,

[0148] like Figure 2 As shown, data is imported in batches and automatically generated into a 3D risk dashboard using Python:

[0149] X-axis: PageRank value of data nodes (system importance);

[0150] Y-axis: RiskScore of data nodes;

[0151] Z-axis: Global risk index (fixed height plane);

[0152] Colored scatter plots: The distribution of each data node in the risk space; the warmer the color, the greater the risk assessment value of the node.

[0153] Gray plane: The current global risk index level, facilitating intuitive comparison;

[0154] Hovering the mouse over a data node can display any single data item, such as the data node's PageRank value and risk assessment value.

[0155] Supports mouse drag-and-drop view rotation;

[0156] like Figure 3 As shown,

[0157] Heatmap matrix of flow amplitude:

[0158] Line: Outflow of funds data (source data node);

[0159] Column: Inflow of funds (target data node);

[0160] Color: Red indicates a significant difference in flow amplitude compared to the same period in history (excessive increase), light blue indicates an excessive decrease;

[0161] Pink indicates that the difference (increase) in flow amplitude compared to the same period in history is within a reasonable range;

[0162] Brown indicates that the difference (reduction) in flow amplitude compared to the same period in history is within a reasonable range;

[0163] Dark blue indicates no cash flow, but a related party relationship exists;

[0164] The displayed heatmap matrix values ​​are the standardized flow amplitudes (Z-score);

[0165] Diagonal blanks represent internal transaction data monitoring content of the enterprise itself;

[0166] Administrators can click to view detailed transaction information.

[0167] A data model-based enterprise cash flow data monitoring system, comprising a data acquisition module, a preprocessing module, a data modeling module, a data node risk assessment module, and a visualization module;

[0168] The data acquisition module is used to collect enterprise-related data, including enterprise registration information and enterprise transaction data; the enterprise transaction data includes transaction objects and transaction fund flow data; and the collected data is stored.

[0169] The preprocessing module is used to preprocess the collected enterprise-related data;

[0170] The data modeling module is used to establish a data model based on the preprocessed enterprise-related data, including data nodes, directed data edges, and edge weights.

[0171] The data node risk assessment module is used to calculate the risk assessment value of each data node based on the data model.

[0172] The visualization module is used to visualize the global risk index through a 3D dashboard and to visualize and monitor flow data through a heat map matrix.

[0173] Specifically:

[0174] The enterprise transaction data is obtained from internal access within the enterprise after authorization.

[0175] Specifically:

[0176] Provides data backup and storage;

[0177] The calculation method for the risk assessment value of the data node is optimized by using the data backup and storage data as historical data.

[0178] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for monitoring enterprise cash flow data based on a data model, characterized in that: The method for monitoring corporate cash flow data specifically includes the following steps: Collect relevant enterprise data; The relevant data of the enterprise is preprocessed; A data model is established based on the preprocessed enterprise-related data; Based on the data model, the risk assessment value of each data node is calculated, specifically including the following steps: constructing a weighted transition matrix, and obtaining the system importance PageRank of the data node in the data model based on the iterative calculation of the weighted transition matrix; Extract the normalized enterprise-related data and normalize the out-degree data of the data nodes in the data model. The ratio of the normalized out-degree data to the enterprise registered capital data in the enterprise-related data is recorded as the cash flow rate. The ratio of the number of shortest funding paths passing through a data node to the total number of shortest paths in the data model is denoted as the betweenness centrality. A certain time interval Δ is set, and the betweenness centrality of the same data node before and after the certain time interval Δ is used as the basis to calculate the chain change rate of the betweenness centrality. The risk assessment value of a data node is obtained by using the PageRank, cash flow rate, and betweenness centrality rate of the same data node in the data model. The formula for calculating PageRank, the system importance in the data model, is as follows: ； in, The system importance of data node u is represented by u, v, and k; the labels of data nodes are u, v, and k; N represents the total number of data nodes in the data model, where N is a positive integer; and d represents the damping coefficient. This represents the set of all data nodes that point to data node u; This indicates the system importance of data node v; This represents the edge weight from data node v to data node u; This represents the set of all outgoing target data nodes of data node v; This represents the edge weight from data node v to data node k; The formula for characterizing the rate of change of betweenness centrality is: ； in, This represents the betweenness centrality of data node i; This represents the number of shortest paths from data node s through data node i to data node t; This represents the number of shortest paths from data node s to data node t; ； in, This represents the rate of change of the betweenness centrality of data node i over the same period of time. This represents the betweenness centrality of the current data node i; This represents the betweenness centrality of the data node i before Δ; The formula for calculating the risk assessment value of the data node is as follows: ； in, This represents the risk assessment value of the data node; , and Represents the regression coefficient; This represents the out-degree data of the data node that has completed normalization; This represents the registration cost data of the data nodes that have completed normalization; Based on the calculated risk assessment value of each data node, the global risk index is visualized and displayed through a 3D dashboard; and the flow data is visualized and monitored through a heat map matrix.

2. The method for monitoring enterprise cash flow data based on a data model according to claim 1, characterized in that: Specifically: Collect enterprise-related data, including enterprise registration information and enterprise transaction data; The enterprise transaction data includes transaction counterparties and transaction fund flow data.

3. The method for monitoring enterprise cash flow data based on a data model according to claim 2, characterized in that: The relevant enterprise data is preprocessed, specifically as follows: The preprocessing includes data alignment and data normalization.

4. The method for monitoring enterprise cash flow data based on a data model according to claim 3, characterized in that: Based on the preprocessed enterprise-related data, a data model is established, specifically as follows: The data model includes data nodes, directed data edges, and edge weights; The data nodes include enterprises, trading partners, and intermediary institutions; The directed edges in the data are used to represent transaction fund flow data between data nodes; The edge weights include flow time data and the number of intermediate nodes.

5. The method for monitoring enterprise cash flow data based on a data model according to claim 4, characterized in that: Based on the calculated risk assessment value of each data node, the global risk index is visualized and displayed through a 3D dashboard; and the flow data is monitored and visualized through a heatmap matrix. Using the system importance of the data nodes as weights, a global risk index is calculated based on the risk assessment values ​​of the data nodes. The formula is as follows: GlobalRisk=[Σ i=1 N RiskScore(i)*PageRank(i)] / N*RiskScore(i)_max; Where GlobalRisk represents the global risk index; RiskScore(i) represents the risk assessment value of data node i; PageRank(i) represents the system importance of data node i; and RiskScore_max represents the maximum risk assessment value of all data nodes. The flow data is visualized and monitored using a heatmap matrix, with the specific representation formula as follows: AnomalyScore(i,j)=|w i j -m ij | / d ij ; Where AnomalyScore(i,j) represents the flow amplitude; w ij μ represents the edge weight from data node i to data node j. ij δ represents the average transaction value from data node i to data node j during the same historical period; ij This represents the standard deviation of transaction amounts from data node i to data node j during the same historical period.

6. A data model-based enterprise cash flow data monitoring system, employing the data model-based enterprise cash flow data monitoring method as described in any one of claims 1-5, characterized in that: The enterprise cash flow data monitoring system includes a data acquisition module, a preprocessing module, a data modeling module, a data node risk assessment module, and a visualization module. The data acquisition module is used to collect enterprise-related data, including enterprise registration information and enterprise transaction data; the enterprise transaction data includes transaction objects and transaction fund flow data. The collected data is stored. The preprocessing module is used to preprocess the collected enterprise-related data; The data modeling module is used to establish a data model based on the preprocessed enterprise-related data, including data nodes, directed data edges, and edge weights. The data node risk assessment module is used to calculate the risk assessment value of each data node based on the data model. The visualization module is used to visualize and display the global risk index through a three-dimensional dashboard. And the flow data is visualized and monitored through a heatmap matrix.

7. A data model-based enterprise cash flow data monitoring system according to claim 6, characterized in that: Specifically: The enterprise transaction data is obtained from internal access within the enterprise after authorization.

8. The enterprise cash flow data monitoring system based on a data model according to claim 7, characterized in that: Specifically: Provides data backup and storage; The calculation method for the risk assessment value of the data node is optimized by using the data backup and storage data as historical data.

Images