A financial data full-link monitoring method and system
By constructing a full-link map of financial data and using machine learning algorithms, the problems of data silos and inefficiency in traditional financial data monitoring have been solved, enabling full-link monitoring and risk warning, and improving data transparency and monitoring efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID SHANDONG ELECTRIC POWER CO CAO COUNTY POWER SUPPLY CO
- Filing Date
- 2026-04-01
- Publication Date
- 2026-07-14
AI Technical Summary
Traditional financial data monitoring methods suffer from severe data silos, low monitoring efficiency, and a lack of early warning mechanisms, making it difficult to achieve full-chain monitoring and real-time requirements.
By constructing a full-link graph of financial data, machine learning algorithms are used for data association and anomaly detection, and graph databases and rule engines are combined for real-time monitoring and risk warning.
It enables end-to-end monitoring of financial data, improves data transparency and monitoring efficiency, promptly identifies potential risks, and reduces labor costs and corporate losses.
Smart Images
Figure CN122388041A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of financial data processing technology, specifically a method and system for monitoring the entire financial data chain. Background Technology
[0002] Traditional financial data monitoring methods mainly rely on manual operation and basic information technology. Their core is to ensure the accuracy and compliance of financial data through manual review, comparison and analysis. Although financial software is used in financial work, it still mainly relies on manual input and verification of data.
[0003] As enterprises grow, the scale of financial data continues to expand, and the complexity of business operations increases, traditional financial data monitoring methods have the following problems: 1. Severe data silos: Financial data is scattered across various business systems, lacking effective integration and correlation analysis, making it difficult to achieve end-to-end monitoring; 2. Low monitoring efficiency: Relying on manual data verification and anomaly detection is inefficient, prone to errors, and difficult to meet real-time requirements; 3. Lack of early warning mechanism: It is impossible to detect potential risks in a timely manner, making it difficult to achieve early warning and in-process control.
[0004] To address the above issues, designing a method and system for full-link monitoring of financial data is an urgent problem to be solved in this field. Summary of the Invention
[0005] The purpose of this invention is to provide a method and system for full-link monitoring of financial data. It achieves full-link monitoring of financial data by constructing a full-link map of financial data, breaking down data silos and improving data transparency.
[0006] To achieve the above objectives, the present invention employs the following technical solution: On the one hand, a method for monitoring financial data across the entire value chain is provided, including the following steps: S1: Collect financial data from financial business systems, including but not limited to: transaction data, accounting data, and capital data; S2: Clean the collected financial data, including: data format conversion, missing value handling, and outlier handling; S3: Based on preset association rules, link financial data from different sources to construct a full-link map of financial data; S4: Based on the constructed full-link map of financial data, monitor financial data in real time, including but not limited to: data consistency monitoring, data integrity monitoring, and data anomaly monitoring; S5: Based on preset risk warning rules, issue risk warnings for the detected abnormal data and generate warning reports.
[0007] Preferably, missing value processing is performed on the collected financial data, specifically as follows: Use statistical methods or visualization tools to identify the location of missing values in financial data; The system assesses missing values. If the percentage of missing values is greater than or equal to a set threshold, the financial data segment containing missing values is deleted. If the percentage of missing values is less than the set threshold, the financial data segment containing missing values is filled in. Perform integrity verification on the populated financial data segment.
[0008] Preferably, outlier handling is performed on the collected financial data, specifically as follows: Use statistical indicators such as standard deviation and quantiles to identify outliers: ; ; in, Standard deviation; Identified outliers are assessed and marked: Set an error data threshold. If the identified outlier is greater than or equal to the threshold, the outlier will be deleted; if the identified outlier is less than the threshold, the outlier will be replaced with the mean or median. ; in, These are the sorted data points.
[0009] Preferably, step S3 specifically includes: S31: Preset rules for primary key association, time association, amount association, and business logic association. S32: Define entities in financial data as nodes; S33: Define the relationships in financial data as edges; S34: Construct graphs using graph databases or graph computing frameworks; S35: Import nodes and edges into a graph database to form a full-link graph of financial data.
[0010] Preferably, the primary key association includes: associating financial data data sources through unique identifiers; The time association includes: associating financial data within the same time period through timestamps; The monetary association includes: matching related transactions through monetary amounts; The business logic associations include: associating financial data according to business rules, including but not limited to: customer-account relationships and supplier-invoice relationships.
[0011] Preferably, in step S4, the financial data is monitored in real time, specifically as follows: Machine learning algorithms are used to detect anomalies in financial data, including: the Isolation Forest algorithm and the Local Anomaly Factor algorithm; The isolated forest algorithm is used to detect outliers in the data: ; in, For data points Path length in an isolated tree This is the expected value of the path length. For the sample size The average path length at that time; The local anomaly factor algorithm is used to detect local outliers in the data: ; in, For data points of Nearest neighbor set For data points The locally achievable density.
[0012] Preferably, step S5 specifically includes: S51: Define risk warning rules according to business needs. The warning rules include, but are not limited to: transaction amount exceeding a threshold and account balance falling below a threshold. S52: Match the detected abnormal data with the risk warning rules to determine whether a warning is triggered; S53: If an alert is triggered, an alert message is generated and sent.
[0013] On the other hand, a financial data end-to-end monitoring system is provided, based on the aforementioned financial data end-to-end monitoring method, including: Data acquisition module: Used to collect financial data from various business systems; Data cleaning module: Used to clean the collected financial data; Data association module: Used to associate financial data from different sources and build a full-link map of financial data; Data monitoring module: Used to monitor financial data in real time based on the constructed full-link financial data map; Risk warning module: Used to issue risk warnings for detected abnormal data based on preset risk warning rules; Visualization module: Used to visualize monitoring results and early warning information.
[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. Achieve end-to-end monitoring of financial data: By constructing an end-to-end map of financial data, we can achieve end-to-end monitoring of financial data, break down data silos, and improve data transparency.
[0015] 2. Improve monitoring efficiency: Employ machine learning algorithms for anomaly detection to improve monitoring efficiency and reduce labor costs.
[0016] 3. Enable risk warning: Through rule engine technology, enable risk warning, promptly identify potential risks, and reduce corporate losses. Attached Figure Description
[0017] Figure 1 This is an overall flowchart of a financial data end-to-end monitoring method according to the present invention; Figure 2 This is a flowchart illustrating the construction of a full-link financial data graph, a method for monitoring the entire financial data chain according to the present invention. Figure 3 This is a risk warning flowchart of a financial data end-to-end monitoring method according to the present invention; Figure 4 This is a schematic diagram of the structure of a financial data end-to-end monitoring system according to the present invention. Detailed Implementation
[0018] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined in this application.
[0019] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.
[0020] Example: like Figure 1 As shown, this embodiment provides a method for monitoring the entire financial data chain, including the following steps: S1: Collect financial data from financial business systems, including but not limited to: transaction data, accounting data, and capital data; S2: Clean the collected financial data, including: data format conversion, handling missing values and outlier handling, etc. S3: Based on preset association rules, link financial data from different sources to construct a full-link map of financial data; S4: Based on the constructed full-link map of financial data, monitor financial data in real time, including but not limited to: data consistency monitoring, data integrity monitoring, and data anomaly monitoring; S5: Based on preset risk warning rules, issue risk warnings for the detected abnormal data and generate warning reports.
[0021] Specifically, missing value handling was performed on the collected financial data, as follows: Use statistical methods or visualization tools to identify the location of missing values in financial data; The system assesses missing values. If the percentage of missing values is greater than or equal to a set threshold, the financial data segment containing missing values is deleted. If the percentage of missing values is less than the set threshold, the financial data segment containing missing values is filled in. Perform integrity verification on the populated financial data segment.
[0022] Outlier handling is performed on the collected financial data, specifically as follows: Use statistical indicators such as standard deviation and quantiles to identify outliers: ; ; in, Standard deviation; Identified outliers are assessed and marked: Set an error data threshold. If the identified outlier is greater than or equal to the threshold, the outlier will be deleted; if the identified outlier is less than the threshold, the outlier will be replaced with the mean or median. ; in, These are the sorted data points.
[0023] like Figure 2 As shown, step S3 specifically includes: S31: Preset rules for primary key association, time association, amount association, and business logic association. Primary key association includes: associating financial data data sources through unique identifiers. Time association includes: associating financial data within the same time period through timestamps. Amount association includes: associating transactions through amount matching. Business logic association includes: associating financial data according to business rules. The business logic includes, but is not limited to: customer-account relationship and supplier-invoice relationship. S32: Define entities in financial data, such as customers, suppliers, accounts, and transactions, as nodes; S33: Define the relationships in financial data, such as the relationship between customers and accounts, and the relationship between transactions and accounts, as edges; S34: Construct graphs using graph databases or graph computing frameworks; S35: Import nodes and edges into a graph database to form a full-link graph of financial data.
[0024] In step S4, the financial data is monitored in real time, specifically as follows: Machine learning algorithms are used to detect anomalies in financial data, including: the Isolation Forest algorithm and the Local Anomaly Factor algorithm; The isolated forest algorithm is used to detect outliers in the data: ; in, For data points Path length in an isolated tree This is the expected value of the path length. For the sample size The average path length at that time; The local anomaly factor algorithm is used to detect local outliers in the data: ; in, For data points of Nearest neighbor set For data points The locally achievable density.
[0025] like Figure 3 As shown, step S5 specifically involves: S51: Define risk warning rules according to business needs. The warning rules include, but are not limited to: transaction amount exceeding a threshold and account balance falling below a threshold. S52: Match the detected abnormal data with the risk warning rules to determine whether a warning is triggered; S53: If an alert is triggered, an alert message is generated and sent.
[0026] In addition, step S5 also includes: visualizing the monitoring results and early warning information in the form of charts, dashboards, etc., to facilitate user viewing and analysis.
[0027] like Figure 4 As shown, this embodiment also provides a financial data end-to-end monitoring system, including: Data acquisition module: Used to collect financial data from various business systems; Data cleaning module: Used to clean the collected financial data; Data association module: Used to associate financial data from different sources and build a full-link map of financial data; Data monitoring module: Used to monitor financial data in real time based on the constructed full-link financial data map; Risk warning module: Used to issue risk warnings for detected abnormal data based on preset risk warning rules; Visualization module: Used to visualize monitoring results and early warning information.
[0028] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.
Claims
1. A method for monitoring the entire financial data chain, characterized in that, Includes the following steps: S1: Collect financial data from financial business systems, including but not limited to: transaction data, accounting data, and capital data; S2: Clean the collected financial data, including: data format conversion, missing value handling, and outlier handling; S3: Based on preset association rules, link financial data from different sources to construct a full-link map of financial data; S4: Based on the constructed full-link map of financial data, monitor financial data in real time, including but not limited to: data consistency monitoring, data integrity monitoring, and data anomaly monitoring; S5: Based on preset risk warning rules, issue risk warnings for the detected abnormal data and generate warning reports.
2. The method for full-link monitoring of financial data according to claim 1, characterized in that, Missing values were handled in the collected financial data, specifically as follows: Use statistical methods or visualization tools to identify the location of missing values in financial data; The system assesses missing values; if the percentage of missing values is greater than or equal to a set threshold, the financial data segment containing missing values is deleted. If the percentage of missing values is less than the set threshold, then the financial data segments containing missing values will be filled. Perform integrity verification on the populated financial data segment.
3. The method for full-link monitoring of financial data according to claim 1, characterized in that, Outlier handling is performed on the collected financial data, specifically as follows: Use statistical indicators such as standard deviation and quantiles to identify outliers: ； ； in, Standard deviation; Identified outliers are assessed and marked: Set an error data threshold. If the identified outlier is greater than or equal to the threshold, the outlier will be deleted; if the identified outlier is less than the threshold, the outlier will be replaced with the mean or median. ； in, These are the sorted data points.
4. The method for full-link monitoring of financial data according to claim 1, characterized in that, Step S3 specifically includes: S31: Preset rules for primary key association, time association, amount association, and business logic association. S32: Define entities in financial data as nodes; S33: Define the relationships in financial data as edges; S34: Construct graphs using graph databases or graph computing frameworks; S35: Import nodes and edges into a graph database to form a full-link graph of financial data.
5. The method for full-link monitoring of financial data according to claim 4, characterized in that, The primary key association includes: associating financial data data sources through unique identifiers; The time association includes: associating financial data within the same time period through timestamps; The monetary association includes: matching related transactions through monetary amounts; The business logic associations include: associating financial data according to business rules, including but not limited to: customer-account relationships and supplier-invoice relationships.
6. The method for full-link monitoring of financial data according to claim 1, characterized in that, In step S4, the financial data is monitored in real time, specifically as follows: Machine learning algorithms are used to detect anomalies in financial data, including: the Isolation Forest algorithm and the Local Anomaly Factor algorithm; The isolated forest algorithm is used to detect outliers in the data: ； in, For data points Path length in an isolated tree This is the expected value of the path length. For the sample size The average path length at that time; The local anomaly factor algorithm is used to detect local outliers in the data: ； in, For data points of Nearest neighbor set For data points The locally achievable density.
7. The method for full-link monitoring of financial data according to claim 1, characterized in that, Step S5 specifically includes: S51: Define risk warning rules according to business needs. The warning rules include, but are not limited to: transaction amount exceeding a threshold and account balance falling below a threshold. S52: Match the detected abnormal data with the risk warning rules to determine whether a warning is triggered; S53: If an alert is triggered, an alert message is generated and sent.
8. A financial data end-to-end monitoring system, characterized in that, The financial data end-to-end monitoring method as described in claim 1 includes: Data acquisition module: Used to collect financial data from various business systems; Data cleaning module: Used to clean the collected financial data; Data association module: Used to associate financial data from different sources and build a full-link map of financial data; Data monitoring module: Used to monitor financial data in real time based on the constructed full-link financial data map; Risk warning module: Used to issue risk warnings for detected abnormal data based on preset risk warning rules; Visualization module: Used to visualize monitoring results and early warning information.