Financial institution business auxiliary method and device

Abstract

The invention relates to the technical field of artificial intelligence, and particularly provides a financial institution business auxiliary method and device, and the method comprises the following steps: S1, carrying out the marketing extension; s2, risk monitoring; and S3, a model center. Compared with the prior art, a more efficient and convenient anti-fraud and supervision means can be provided for digital intelligence finance, and a finance system is promoted to be more stable.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and specifically provides a business assistance method and device for financial institutions. Background Art

[0002] Currently, banking and financial institutions face dual challenges in customer development and risk management: on the one hand, customer acquisition is highly dependent on the personal connections and experience accumulation of relationship managers, and the fragmented manual collection channels have led to prominent information silos, and delayed data updates and insufficient authenticity verification have formed a structural contradiction; on the other hand, the mainstream enterprise information service platforms in the market are mostly designed for consumer-end scenarios and lack in-depth analysis of financial business logic. There is a gap between their data dimensions and update frequency and the core needs of institutions such as precision marketing and credit assessment, making it difficult to meet the customized data needs of scenarios such as pre-loan due diligence and industry analysis.

[0003] This lack of adaptability between business scenarios and data tools has become a key bottleneck restricting the digital business development efficiency of financial institutions. Summary of the Invention

[0004] The present invention aims to address the deficiencies of the above-mentioned prior art and provides a highly practical business assistance method for financial institutions.

[0005] A further technical task of the present invention is to provide a financial institution business assistance device that is rationally designed, safe and applicable.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] The financial institution business assistance method comprises the following steps:

[0008] S1. Marketing and customer acquisition;

[0009] S2. Risk monitoring;

[0010] S3, model center.

[0011] Furthermore, in step S1, it includes:

[0012] S1.1. Tag marketing: providing multi-dimensional screening tools based on the full amount of industrial and commercial enterprise data;

[0013] S1.2. Map acquisition: Based on the company's longitude and latitude coordinate data, a tool is built to efficiently mine high-quality corporate resources in the region.

[0014] S1.3, bidding information opportunities, through intelligent screening mechanism, accurate search and real-time push of bidding information;

[0015] S1.4. For newly added enterprises, based on a multi-dimensional screening engine, the latest registered enterprise information is captured and presented.

[0016] Furthermore, in step S1.1, the two major search modes of basic retrieval and deep exploration are integrated, combining keyword positioning + multi-dimensional condition filtering technology, accessing the data source in real time through the API gateway, and using the DeepSeek-NLP engine to parse unstructured data. According to business needs, the original data is processed with indicator logic to form an ES library, and data processing and updates are performed at different cycles according to different business attributes.

[0017] Furthermore, in step S1.2, with the help of geographic information technology, two search strategies, namely surrounding exploration and address positioning, are applied. Users only need to enter a specific location and set a personalized search radius of 1 to 5 kilometers to retrieve all relevant companies within the range with one click.

[0018] Furthermore, in step S1.3, users set screening conditions according to their own needs to locate and obtain valuable bidding information opportunities. In addition, it also supports the convenient export of bidding information.

[0019] Furthermore, in step S1.4, screening conditions are set to quickly filter out the newly added enterprise list that meets specific needs, add an enterprise search experience, quickly lock in the target enterprise through multi-dimensional condition screening, and export the results.

[0020] Furthermore, in step S2, enterprise monitoring is first carried out, and the monitoring scope is expanded from its own customer base to any designated enterprise. On the basis of retaining the original risk classification management mechanism and real-time dynamic update, a visualization statistical tool for monitoring information and a monitoring enterprise management module are newly added;

[0021] Then, we conduct enterprise risk monitoring, continuously track the risk information of client companies, and support automatic generation of risk reports at different frequencies of daily, weekly, and monthly according to user needs.

[0022] Furthermore, in step S3, it includes:

[0023] S3.1. Corporate credit score, which is divided into company growth, capital background, operating quality, enterprise scale, intellectual property rights and risk status;

[0024] S3.2, Shell Index;

[0025] S3.3, Enterprise portrait;

[0026] S3.4, agricultural theme database;

[0027] S3.5, admission model.

[0028] Furthermore, in step S3.2, the corporate shell index includes the authenticity of the business premises, the form of assets, the composition of corporate employees, actual business activities, legal business qualifications and risk records, and identifies and marks corporate entities with abnormalities or not conducting normal business activities.

[0029] In step S3.3, machine learning technology optimizes the labeling system and classification strategy to build an enterprise labeling model;

[0030] In step S3.4, a professional agricultural comprehensive information database is constructed, integrating detailed information on agricultural business entities, including authoritative data on agricultural intellectual property rights, and dynamic information on the rural e-commerce market;

[0031] In step S3.5, two sub-models are included: blacklist access and litigation information access. The blacklist access is built based on a detailed blacklist database to identify and exclude high-risk or unwelcome entities;

[0032] The access to litigation information is based on in-depth analysis of judicial litigation data to assess the applicant's legal dispute situation to ensure compliance.

[0033] A financial institution business assistance device, comprising: at least one memory and at least one processor;

[0034] The at least one memory is configured to store a machine-readable program;

[0035] The at least one processor is configured to call the machine-readable program to execute the financial institution business assistance method.

[0036] Compared with the prior art, the financial institution business assistance method and device of the present invention have the following outstanding beneficial effects:

[0037] (1) 2,500+ tags, including industry rankings, registered capital, and company types, can be generated to quickly screen companies within the jurisdiction of financial institutions according to the access requirements of different financial products and obtain a list of high-quality customers; 60 types of business opportunities, including winning bid information, business expansion, new qualifications, recruitment dynamics, investment and financing information, etc., can be obtained in real time and proactively pushed to find corporate customers with funding needs.

[0038] (2) Provide special marketing modules such as technology finance, green finance, and inclusive finance to assist financial institutions in finding target enterprises in areas that are key supported by national policies, and help financial services serve the real economy.

[0039] (3) Risk management runs through the entire process of financial business, including pre-loan, mid-loan and post-loan. The product integrates data outside the financial system, such as corporate industrial and commercial changes, operating risks, and judicial litigation, to establish a risk monitoring model, and regularly push corporate customers' own risks, related risks, internal risks, etc., to complete the risk control system of financial institutions.

[0040] (IV) Improve business efficiency: The product is integrated into the office processes of front-line account managers, enabling one-click batch customer acquisition, corporate due diligence and risk monitoring; the product integrates multi-source data to resolve data inconsistencies and reduce the workload of business personnel such as multi-platform queries and data comparisons; the product provides analytical tools such as customer analysis and data export to meet the data statistics needs of internal daily reporting, fit business scenarios, and improve business efficiency.

[0041] Financial institutions can use big data to analyze customer behavior, assist with pricing and risk prediction, and reduce financial service risks. At the same time, digital finance can provide more efficient and convenient anti-fraud and regulatory measures, making the financial system more robust. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is a schematic diagram of the architecture for business support for financial institutions. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the solutions of the present invention, the present invention will be further described in detail below in conjunction with specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0045] A best embodiment is given below:

[0046] like Figure 1 As shown, the financial institution business assistance in this embodiment has the following steps:

[0047] S1. Marketing and customer acquisition;

[0048] include:

[0049] S1.1, label marketing;

[0050] Based on comprehensive industrial and commercial enterprise data, this tool provides flexible, multi-dimensional screening tools. It integrates two search modes: "Basic Search" and "In-Depth Exploration." It incorporates "keyword targeting + multi-dimensional conditional filtering" technology, allowing users to conduct preliminary screening based on keywords such as "company name, credit code, legal representative, business scope, and official website link." Furthermore, it supports complex screening based on 50 in-depth criteria, including "establishment date, total registered capital, paid-in capital, operating status, business nature, organizational structure type, and industry tags," comprehensively covering enterprise characteristics and helping to accurately reach target markets. Through an API gateway, it connects to over 20 data sources, including core banking systems, mobile apps, and the WeChat ecosystem, integrating 12 types of data, including basic customer attributes, transaction behavior, and social networks. It uses the DeepSeek-NLP engine to parse unstructured data such as account manager work logs and call recordings. This enables omnichannel data integration, forming the data foundation for marketing systems. Based on the data foundation feature factory, it automatically generates over 300 tags, including static tags such as identity characteristics and asset size, and dynamic customer profiles, providing a matching foundation for various marketing campaigns. Based on business needs, raw data is logically processed into indicators to form an ES database. Data processing and updates are performed at different intervals according to different business attributes. This is the basis for enterprise profiling and multi-dimensional screening. Full-dimensional search and screening can be performed based on more than 30 dimensions, including years of establishment, region, and regional expansion.

[0051] S1.2, map customer development;

[0052] Leveraging precise longitude and latitude coordinate data, this powerful tool is designed to efficiently identify high-quality businesses within a region, with the core goal of optimizing the cost-effectiveness of new customer acquisition. Leveraging advanced geographic information technology, users can easily identify high-quality businesses within a target area, flexibly applying both "surrounding exploration" and "address location" search strategies. Simply enter a specific location and set a personalized search radius of 1 to 5 kilometers to instantly retrieve all relevant businesses within that radius, ideal for offline sales visits and market development.

[0053] S1.3, bidding information business opportunities;

[0054] The Bidding Opportunities feature uses an intelligent filtering mechanism to accurately search and deliver bidding information in real time. Users can customize filtering criteria to quickly locate and acquire valuable bidding opportunities. Furthermore, this feature supports convenient export of bidding information, enabling easy data management and supporting subsequent analysis and follow-up. Whether identifying potential partnerships or understanding market trends, the Bidding Opportunities feature is a powerful tool for businesses to expand their business.

[0055] S1.4. Newly added enterprises:

[0056] The newly added enterprise search function relies on a powerful multi-dimensional screening engine to accurately capture and present the latest registered enterprise information. Users can flexibly set screening conditions, including but not limited to the company's establishment date, type and specific geographical location (province, city, district), so as to quickly filter out the list of new companies that meet specific needs. In addition, this function also provides a result export option, allowing users to easily save the screening results as a file for subsequent in-depth analysis or sharing with team members. This innovative design aims to create an efficient information acquisition platform for users, helping them to accurately grasp the pulse of the market, understand the latest developments of new companies, and lay a solid foundation for the company's strategic planning, business development and competitor analysis.

[0057] To further meet users' highly sensitive needs for market dynamics, we've optimized the search experience for newly added companies. Not only can users quickly identify target companies through multi-dimensional screening, but they can also immediately grasp the basic information of these emerging companies, including their founding background, business scope, and development trends. This instant and comprehensive information acquisition capability is undoubtedly key for companies to seize market opportunities and develop targeted strategies. Furthermore, the ability to export results provides users with tremendous convenience, enabling seamless integration for internal report preparation, client profile updates, and market research data support, significantly improving work efficiency and decision-making quality.

[0058] S2. Risk monitoring;

[0059] include:

[0060] S2.1, Enterprise Monitoring;

[0061] The Enterprise Monitoring Service expands the scope of monitoring beyond your own customer base to any designated enterprise. While retaining the existing risk classification management mechanism and real-time dynamic updates, it adds a new visualization tool for monitoring information and a monitoring enterprise management module, providing users with a more intuitive and efficient monitoring experience and powerful management capabilities.

[0062] S2.2, Risk Dynamics;

[0063] For enterprise risk monitoring, the system continuously tracks risk information for client companies and, based on user needs, automatically generates risk reports on a daily, weekly, or monthly basis. Monitoring focuses on three core dimensions: operational risk, legal disputes, and corporate changes, ensuring comprehensive coverage of potential risk points. This system aims to help financial institutions rapidly respond to changes in customer information, provide early warning of financial risks, and effectively implement risk prevention strategies.

[0064] S3, model center;

[0065] include:

[0066] S3-1, corporate credit score;

[0067] The corporate credit score is a comprehensive quantitative indicator that deeply analyzes multiple key aspects of a company to comprehensively and objectively assess its overall condition. This scoring system covers the following core dimensions:

[0068] 1) Company Growth: This evaluates a company's future development potential and growth rate, including indicators such as market share growth, revenue growth rate, and profit growth rate. Companies with strong growth potential typically demonstrate greater market competitiveness and sustainable development capabilities.

[0069] 2) Capital Background: This examines a company's capital strength, shareholder structure, and financing channels, reflecting its financial strength and soundness. A strong capital background often indicates a company has more resources and greater resilience to risks.

[0070] 3) Operational Quality: This evaluates the quality and effectiveness of a company's operations by analyzing its operational efficiency, cost control, profitability, and other aspects. Good operational quality is the cornerstone of a company's sustainable development.

[0071] 4) Company size: This factor considers factors such as the number of employees, total assets, and market share to reflect a company's relative position and influence within the industry. Larger companies typically have greater market control and resource allocation capabilities.

[0072] 5) Intellectual Property: This assesses a company's accumulation and protection of intellectual property rights, such as patents, trademarks, and copyrights, reflecting its technological innovation capabilities and core competitiveness. A strong intellectual property portfolio is key to a company's continued innovation and competitive advantage.

[0073] 6) Risk Profile: Comprehensively consider a company's legal, financial, and operational risks, assessing its potential risk profile and resilience. Companies with a healthy risk profile are generally better able to navigate market fluctuations and uncertainties.

[0074] Through comprehensive calculation and analysis of the above-mentioned dimensions, corporate credit scores can provide valuable reference information for the company itself, financial institutions, investors, etc., and more accurately understand the company's comprehensive strength and potential risk level.

[0075] S3-2, Shell Index;

[0076] The Corporate Shell Index provides a comprehensive and in-depth analysis of companies across six key dimensions: authenticity of business premises, asset structure, employee composition, actual business activities, legal operating qualifications, and risk history. It aims to accurately identify and flag entities such as clones, zombie companies, and shell companies that exhibit abnormalities or are not engaging in normal business activities. This index provides a powerful tool for corporate assessment, financial regulation, and market oversight, helping all parties effectively mitigate the risks of partnering with high-risk or fraudulent entities.

[0077] S3-3, Enterprise portrait;

[0078] Leveraging advanced machine learning technology to optimize labeling systems and classification strategies, we've built a comprehensive enterprise labeling model. This model encompasses over 500 refined feature tags, designed to deeply characterize the multi-dimensional attributes of enterprise users. This model enables financial institutions to efficiently build accurate profiles of enterprise users, accelerating the identification and targeting of high-quality customer groups, providing strong support for key processes such as credit assessment, marketing, and risk management.

[0079] S3-4, agricultural theme library;

[0080] Build a professional, comprehensive agricultural information database that deeply integrates detailed information on agricultural business entities (such as farmers, cooperatives, and agricultural enterprises), comprehensively includes authoritative data on agricultural intellectual property (such as patents, variety rights, and geographical indications), and dynamic information on the rural e-commerce market. Building on this solid foundation, further develop diversified, high-value agricultural applications, including but not limited to agricultural big data analysis platforms, intelligent agricultural decision support systems, and agricultural product traceability systems, to meet the needs of the agricultural industry at all levels and promote agricultural modernization.

[0081] S3-5, admission model;

[0082] The access model system consists of two core sub-models: blacklist access and litigation information access. The former is built on a comprehensive blacklist database to identify and exclude high-risk or undesirable entities; the latter relies on in-depth analysis of judicial litigation data to assess the applicant's legal dispute status to ensure compliance. Both models follow clear rules and logic and fall into the category of rule-based models.

[0083] Based on the above method, the financial institution business support device in this embodiment includes: at least one memory and at least one processor;

[0084] The at least one memory is configured to store a machine-readable program;

[0085] The at least one processor is configured to call the machine-readable program to execute the financial institution business assistance method.

[0086] The above-mentioned specific implementation methods are only specific cases of the present invention. The patent protection scope of the present invention includes but is not limited to the above-mentioned specific implementation methods. Any technical solutions that conform to the above-mentioned specific implementation methods of the present invention and any appropriate changes or substitutions made thereto by ordinary technicians in the relevant technical field shall fall within the patent protection scope of the present invention.

[0087] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A financial institution business assistance method, characterized in that: The steps are as follows: S1. Marketing and customer acquisition; S2. Risk monitoring; S3, model center.

2. The financial institution business assistance method according to claim 1, characterized in that: In step S1, it includes: S1.

1. Tag marketing: providing multi-dimensional screening tools based on the full amount of industrial and commercial enterprise data; S1.

2. Map acquisition: Based on the company's longitude and latitude coordinate data, a tool is built to efficiently mine high-quality corporate resources in the region. S1.3, bidding information opportunities, through intelligent screening mechanism, accurate search and real-time push of bidding information; S1.

4. For newly added enterprises, based on a multi-dimensional screening engine, the latest registered enterprise information is captured and presented.

3. The financial institution business assistance method according to claim 2, characterized in that: In step S1.1, the two major search modes of basic retrieval and deep exploration are integrated, combining keyword positioning + multi-dimensional condition filtering technology, real-time access to data sources through the API gateway, and the DeepSeek-NLP engine is used to parse unstructured data. According to business needs, the original data is processed with indicator logic to form an ES library, and data processing and updates are performed at different cycles according to different business attributes.

4. The financial institution business assistance method according to claim 3, characterized in that: In step S1.2, with the help of geographic information technology, two search strategies, namely surrounding exploration and address positioning, are applied. Users only need to enter a specific location and set a personalized search radius of 1 to 5 kilometers to retrieve all relevant companies within the range with one click.

5. The financial institution business assistance method according to claim 4, characterized in that: In step S1.3, users set filtering conditions according to their own needs to locate and obtain valuable bidding information opportunities. In addition, it also supports the convenient export of bidding information.

6. The financial institution business assistance method according to claim 5, characterized in that: In step S1.4, set the screening conditions to quickly filter out the newly added enterprise list that meets specific needs, add a new enterprise search experience, quickly lock the target enterprise through multi-dimensional condition screening, and export the results.

7. The financial institution business assistance method according to claim 6, characterized in that: In step S2, enterprise monitoring is first carried out, expanding the monitoring scope from its own customer base to any designated enterprise. While retaining the original risk classification management mechanism and real-time dynamic updates, a new visualization statistical tool for monitoring information and a monitoring enterprise management module are added; Then, we conduct enterprise risk monitoring, continuously track the risk information of client companies, and support automatic generation of risk reports at different frequencies of daily, weekly, and monthly according to user needs.

8. The financial institution business assistance method according to claim 7, characterized in that: In step S3, it includes: S3.

1. Corporate credit score, which is divided into company growth, capital background, operating quality, enterprise scale, intellectual property rights and risk status; S3.2, Shell Index; S3.3, Enterprise portrait; S3.4, agricultural theme database; S3.5, admission model.

9. The financial institution business assistance method according to claim 8, characterized in that: In step S3.2, the corporate shell index includes the authenticity of the business premises, the form of assets, the composition of corporate employees, actual business activities, legal business qualifications and risk records, and identifies and marks corporate entities with abnormalities or not conducting normal business activities. In step S3.3, machine learning technology optimizes the labeling system and classification strategy to build an enterprise labeling model; In step S3.4, a professional agricultural comprehensive information database is constructed, integrating detailed information on agricultural business entities, including authoritative data on agricultural intellectual property rights, and dynamic information on the rural e-commerce market; In step S3.5, two sub-models are included: blacklist access and litigation information access. The blacklist access is built based on a detailed blacklist database to identify and exclude high-risk or unwelcome entities; The access to litigation information is based on in-depth analysis of judicial litigation data to assess the applicant's legal dispute situation to ensure compliance.

10. A financial institution business support device, characterized in that: include: at least one memory and at least one processor; The at least one memory is configured to store a machine-readable program; The at least one processor is configured to call the machine-readable program to execute the method according to any one of claims 1 to 9.

Images