Data query methods, devices, equipment, and media based on natural language recognition

By training a target large language model and vector database, combined with power corpus and business terminology dictionary, multiple query statements are generated and evaluated, solving the problems of accuracy and security of data query in the power field, and realizing an automated power data query and decision-making closed loop.

CN121722904BActive Publication Date: 2026-06-30BEIJING JOIN BRIGHT DIGITAL POWER TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202511900660.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-16
Publication Date
2026-06-30
Estimated Expiration
2045-12-16

AI Technical Summary

Technical Problem

Existing natural language recognition data query technologies suffer from semantic ambiguity, query structure errors, and the need for manual processing of query results in the power sector, leading to low efficiency in power business decision-making and security risks.

Method used

By training a target large language model based on an electricity corpus dataset and a hierarchical progressive fine-tuning strategy, and combining it with a pre-built business terminology dictionary and vector database, multiple candidate query statements are generated, and multi-dimensional scoring and verification are performed to ensure query accuracy and security.

Benefits of technology

It has improved the accuracy and security of data queries in the power sector, enabled automatic semantic verification and visualization, and reduced the risks and efficiency barriers to power business decision-making.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This application provides a data query method, apparatus, device, and medium based on natural language recognition, belonging to the field of data query technology. The method includes: obtaining extended keywords based on user natural language queries; obtaining pattern information and business knowledge based on the extended keywords, user natural language queries, and a vector database; generating target prompt words based on the pattern information, business knowledge, user natural language queries, and system prompt word templates; generating multiple candidate query statements through a target large language model based on the target prompt words and model generation parameters, and determining the optimal query statement; executing the optimal query statement in a database test environment, obtaining an execution result set and capturing abnormal information; validating the execution result set and obtaining a verification result; if the abnormal information is empty and the verification result is qualified, then generating a visualization chart based on the extended keywords, the optimal query statement, and the qualified result set. This application can improve the accuracy of power data queries.
Need to check novelty before this filing date? Find Prior Art