Bank industry-based same-industry data analysis method

Abstract

The invention discloses a banking industry-based same-industry data analysis method, which comprises the following steps of: analyzing an existing system by using an AI algorithm, and providing a scientific and reasonable micro-service splitting scheme; a required data report is obtained through natural language description; data islands are broken through, seamless integration between systems is achieved, data values are deeply mined, and business innovation is driven. The system integration efficiency is obviously improved, and the API development cost is reduced. And deep insights for business of the same industry are formed, and new business growth points and optimization directions are found. A unified data asset view is constructed, and fine management and decision-making of data driving are supported.

Description

Technical Field

[0001] This invention relates to the field of banking data analysis, and more particularly to a method for analyzing interbank data. Background Technology

[0002] The system is developed based on Java. The database consists of two parts: one part is the application data used for the front-end interface display, and the other part is for offline batch processing and data acquisition.

[0003] Data sources: core system, interbank business line transaction system, bill system.

[0004] Disadvantages of existing technology: The modules are highly coupled, requiring overall deployment for upgrades and maintenance, resulting in poor scalability. The compilation, deployment, and testing processes are slow and technically challenging.

[0005] Fixed reports are inflexible, time-consuming to create, require development intervention for modifications, and have a slow response time.

[0006] The systems are mostly siloed, with information islands being common, making it difficult to share and integrate data, thus hindering business innovation and process optimization.

[0007] Traditional systems, due to their shortcomings in architectural flexibility, data processing efficiency, and automation, do indeed affect business agility and innovation. Summary of the Invention

[0008] In view of the above problems, the present invention is proposed to provide a method for analyzing interbank data to overcome or at least partially solve the above problems.

[0009] According to one aspect of the present invention, a method for analyzing interbank data is provided, the data analysis method comprising: Utilize AI algorithms to analyze existing systems and provide scientifically sound microservice decomposition solutions; Obtain the required data reports through natural language descriptions; Break down data silos, achieve seamless integration between systems, and deeply mine the value of data to drive business innovation.

[0010] Optionally, the provision of a scientific and reasonable microservice decomposition scheme by analyzing existing systems using AI algorithms specifically includes: A multi-objective optimization algorithm is used to analyze the coupling degree between system components, taking into account call frequency, data traffic and business relevance. Based on the domain-driven design principle, AI is used to identify bounded contexts and intelligently define service boundaries. AI model analysis of codebase, database schema and API call chain recommends a highly cohesive service partitioning scheme; Integrate code analysis and visualization tools to generate system dependency graphs and service decomposition suggestions reports.

[0011] Optionally, the multi-objective optimization algorithm is NSGA-II.

[0012] Optionally, the existing system data includes: code repository, API call chain, and database access log.

[0013] Optionally, obtaining the required data report through natural language description specifically includes: Natural Language Query Parsing: Utilizing NLP models to analyze user query intent and identify key dimensions, metrics, and time ranges; SQL intelligent generation and optimization: Converts parsed semantic elements into efficient SQL queries, supporting multi-table joins and complex condition processing; Dynamic visualization: Automatically selects and renders the best chart type based on data characteristics; Intelligent early warning: Based on historical data patterns, it uses machine learning algorithms to dynamically identify anomalies and provide more timely early warnings than fixed rules.

[0014] Optionally, the machine learning algorithm specifically includes: isolated forest and time series anomaly detection.

[0015] Optionally, the process of breaking down data silos, achieving seamless integration between systems, and deeply mining data value to drive business innovation specifically includes: API Intelligent Recommendation and Generation: Analyze existing system interfaces and data models, use algorithms to recommend the optimal integration solution, and automatically generate API adaptation code; In-depth analysis of industry data: By accessing external industry databases and using time series analysis and clustering algorithms, we can benchmark against industry indicators and identify our own strengths, weaknesses and potential areas for improvement. Data-driven innovation: Building business knowledge graphs to uncover hidden business relationships and patterns, providing data support for product innovation and market strategies.

[0016] Optionally, the industry indicators may specifically include: market share, profitability, and risk level.

[0017] This invention provides a data analysis method based on interbank data. The method includes: utilizing AI algorithms to analyze existing systems and provide a scientifically sound microservice decomposition scheme; obtaining required data reports through natural language descriptions; breaking down data silos to achieve seamless system integration; and deeply mining data value to drive business innovation. This significantly improves system integration efficiency and reduces API development costs. It generates deep insights into interbank business, discovering new business growth points and optimization directions. Finally, it constructs a unified data asset view to support data-driven, refined management and decision-making.

[0018] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for analyzing interbank data provided in an embodiment of the present invention. Detailed Implementation

[0021] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0022] The terms "comprising" and "having," and any variations thereof, in the specification, embodiments, claims, and drawings of this invention are intended to cover non-exclusive inclusion, such as including a series of steps or units.

[0023] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0024] like Figure 1 As shown, a data analysis method based on interbank data is proposed. The data analysis method includes: using AI algorithms to analyze existing systems and provide a scientific and reasonable microservice decomposition scheme; obtaining the required data reports through natural language description; breaking down data silos to achieve seamless integration between systems and deeply mining data value to drive business innovation.

[0025] Intelligent microservice decomposition module By leveraging AI algorithms to analyze existing systems, we can provide scientific and reasonable microservice decomposition solutions to address the scalability and maintainability issues of traditional monolithic architectures.

[0026] Multi-objective optimization algorithms (such as NSGA-II) are used to analyze the coupling between system components, taking into account call frequency, data traffic and business relevance.

[0027] Based on Domain-Driven Design (DDD) principles, AI is used to identify bounded contexts and intelligently define service boundaries. The AI ​​model analyzes the codebase, database schema, and API call chain to recommend highly cohesive service partitioning schemes. Integrated code analysis and visualization tools generate system dependency graphs and service decomposition recommendation reports.

[0028] 1. Collect existing system data: code repository, API call chain, database access logs.

[0029] 2. Use clustering algorithms (such as K-Means) to identify functional modules. 3. Generate a splitting scheme based on the communication frequency and data dependencies between modules.

[0030] 4. Display splitting suggestions through visualization tools, supporting manual adjustments and optimizations.

[0031] By splitting services into modules using intelligent microservices, service autonomy can be improved, allowing individual services to be developed, deployed, and scaled independently. System coupling is reduced, and dependencies between services are clear and simplified. Databases are isolated, avoiding direct table sharing across services.

[0032] Natural Language Report Generation Module (NLG) It allows users to obtain the data reports they need through natural language descriptions, greatly reducing the technical threshold for data querying and report generation.

[0033] Natural Language Query (NLQ) parsing: using NLP models (such as BERT, GPT) to parse user query intent and identify key dimensions, metrics, and time ranges.

[0034] SQL Intelligent Generation and Optimization: Converts parsed semantic elements into efficient SQL queries, supporting multi-table joins and complex condition processing.

[0035] Dynamic visualization presentation: Automatically selects and renders the best chart type (line chart, bar chart, pie chart, etc.) based on data characteristics.

[0036] Intelligent early warning: Based on historical data patterns, machine learning algorithms (such as isolated forest and time series anomaly detection) are used to dynamically identify anomalies and provide more timely early warnings than fixed rules.

[0037] Workflow: 1. User input: "Compare and analyze the growth trend of the same industry business in the same period last year and this year".

[0038] 2. NLP engine analysis to identify metrics (business growth trend), time (last year, same period this year), and dimensions (competitor business).

[0039] 3. Automatically generate SQL queries to retrieve data from the data warehouse.

[0040] 4. The results data are rendered by a visualization engine to generate trend comparison charts.

[0041] 5. At the same time, the anomaly detection engine runs, and if it detects an abnormal growth trend, it triggers a dynamic warning.

[0042] After using NLG: the efficiency of business report generation has been significantly improved, from "hours" to "minutes". Business personnel can independently complete data queries and analysis, reducing reliance on developers. Dynamic alerts are more accurate, reducing false alarms and missed alarms.

[0043] Intelligent API Integration and Data Innovation Module Break down data silos, achieve seamless integration between systems, and deeply mine the value of data to drive business innovation.

[0044] API Intelligent Recommendation and Generation: Analyzes existing system interfaces and data models, uses algorithms to recommend the optimal integration solution, and can automatically generate API adaptation code.

[0045] In-depth analysis of peer data: By accessing external peer databases and utilizing time series analysis, clustering algorithms, etc., we can benchmark against peer indicators (such as market share, profitability, and risk level) to identify our own strengths, weaknesses, and potential areas for improvement.

[0046] Data-driven innovation: Building business knowledge graphs to uncover hidden business relationships and patterns, providing data support for product innovation and market strategies. By integrating intelligent APIs and data innovation modules, system integration efficiency can be significantly improved, and API development costs can be reduced. This leads to deep insights into competitor businesses, uncovering new growth points and optimization directions. A unified data asset view is built to support data-driven, refined management and decision-making.

[0047] Ensure a high-quality data foundation (by effectively governing multi-source heterogeneous data to provide reliable input for AI analysis) and select appropriate AI technologies and integrate them in a modular manner (choose NLP, predictive models, etc. based on business scenarios, embed them into existing systems in a loosely coupled manner, and balance innovation and stability).

[0048] Beneficial effects: 1. Intelligent Microservice Decomposition: AI analyzes system call chains and data flows to find more reasonable microservice decomposition points, reducing coupling. AI-Assisted Compilation and Testing: Automates code review, test case generation, and performance prediction, improving efficiency.

[0049] 2. Natural Language Generated Reports (NLG): Describe requirements using natural language; AI automatically generates SQL, calculates metrics, and presents visual reports. Dynamic Intelligent Alerts: AI automatically identifies data patterns and provides dynamic threshold alerts, which are more timely than fixed rules.

[0050] 3. Intelligent API Integration: AI-powered intelligent recommendation and generation system integration solutions connect isolated systems. Data-Driven Innovation: Leveraging AI to access database data, analyze years of relevant industry data to uncover potential business opportunities and optimization points, driving business innovation.

[0051] The above specific embodiments further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for analyzing interbank data, characterized in that, The data analysis methods include: Utilize AI algorithms to analyze existing systems and provide scientifically sound microservice decomposition solutions; Obtain the required data reports through natural language descriptions; Break down data silos, achieve seamless integration between systems, and deeply mine the value of data to drive business innovation.

2. The method for analyzing interbank data according to claim 1, characterized in that, The specific steps of using AI algorithms to analyze existing systems and provide a scientific and reasonable microservice decomposition scheme include: A multi-objective optimization algorithm is used to analyze the coupling degree between system components, taking into account call frequency, data traffic and business relevance. Based on the domain-driven design principle, AI is used to identify bounded contexts and intelligently define service boundaries. AI model analysis of codebase, database schema and API call chain recommends a highly cohesive service partitioning scheme; Integrate code analysis and visualization tools to generate system dependency graphs and service decomposition suggestions reports.

3. The method for analyzing interbank data according to claim 2, characterized in that, The multi-objective optimization algorithm is NSGA-II.

4. The method for analyzing interbank data according to claim 1, characterized in that, The existing system data includes: code repository, API call chain, and database access log.

5. The method for analyzing interbank data according to claim 1, characterized in that, The process of obtaining the required data reports through natural language description specifically includes: Natural Language Query Parsing: Utilizing NLP models to analyze user query intent and identify key dimensions, metrics, and time ranges; SQL intelligent generation and optimization: Converts parsed semantic elements into efficient SQL queries, supporting multi-table joins and complex condition processing; Dynamic visualization: Automatically selects and renders the best chart type based on data characteristics; Intelligent early warning: Based on historical data patterns, it uses machine learning algorithms to dynamically identify anomalies and provide more timely early warnings than fixed rules.

6. The method for analyzing interbank data according to claim 5, characterized in that, The machine learning algorithms specifically include: Isolation Forest and Time Series Anomaly Detection.

7. The method for analyzing interbank data according to claim 1, characterized in that, The process of breaking down data silos, achieving seamless integration between systems, and deeply mining data value to drive business innovation specifically includes: API Intelligent Recommendation and Generation: Analyze existing system interfaces and data models, use algorithms to recommend the optimal integration solution, and automatically generate API adaptation code; In-depth analysis of industry data: By accessing external industry databases and utilizing time series analysis, clustering algorithms, etc., we can benchmark against industry indicators to identify our own strengths, weaknesses, and potential areas for improvement. Data-driven innovation: Building business knowledge graphs to uncover hidden business relationships and patterns, providing data support for product innovation and market strategies.

8. The method for analyzing interbank data according to claim 1, characterized in that, The specific industry indicators include: market share, profitability, and risk level.

Images