Natural Language to SQL Methods, Devices, and Storage Media Applied to the Securities Industry

By utilizing knowledge graph matching and triplet extraction techniques in the securities industry, a natural language to SQL conversion method specific to the securities industry is generated, solving the problem of insufficient accuracy of natural language to SQL conversion methods in the securities industry and achieving higher accuracy and reliability.

CN121833757BActive Publication Date: 2026-05-26HUAAN SECURITIES CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUAAN SECURITIES CO LTD
Filing Date
2026-03-13
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing natural language to SQL conversion methods are difficult to guarantee accuracy in the securities industry, especially when faced with complex and ever-changing natural language and massive securities industry data, making it difficult to generate accurate SQL query statements.

Method used

By receiving natural language data from the securities industry, the system uses a pre-defined knowledge graph to generate a target sub-graph, extracts entities and relationships from triples, filters relevant text fragments based on weight information, fills them into a table template to generate tabular formal language, and finally generates accurate SQL statements.

Benefits of technology

This improves the accuracy of natural language to SQL conversion methods in the securities industry, ensuring that the generated SQL statements are more reliable and accurate, and adapting to the complex data needs of the securities industry.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121833757B_ABST
    Figure CN121833757B_ABST
Patent Text Reader

Abstract

This invention discloses a method, apparatus, and storage medium for converting natural language to SQL in the securities industry, relating to the field of natural language processing technology. The invention first matches natural language with a knowledge graph to obtain a target sub-graph. Then, it extracts all triples from the target sub-graph and matches each triple with the original text fragment from the natural language. Each triple can be used as a smaller unit of the text fragment for semantic querying, thereby retrieving the original text fragment from the natural language. This invention uses triples in the target sub-graph to segment the natural language, thus filtering out the most reasonable M text fragments. Because the process of determining the text fragments is relatively reliable and reasonable, the table template determined based on the text fragments is also more reliable. Filling the table template with natural language yields a more reliable tabular language, and ultimately, based on the tabular language, a more accurate SQL statement can be obtained.
Need to check novelty before this filing date? Find Prior Art