Large-Model Enhanced Query Rewriting Synthesis Method for Database Logical Error Detection

By combining rule tree search and Monte Carlo tree search techniques enhanced by large language models, the database query rewrite space is dynamically explored, solving the problems of insufficient flexibility and root cause analysis in existing technologies, and achieving efficient logical error detection and accurate root cause analysis.

CN120492487BActive Publication Date: 2026-06-30ZHEJIANG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG UNIV
Filing Date
2025-05-21
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing rule-based database logic error detection methods suffer from insufficient flexibility and poor scalability, difficulty in managing the rewrite search space of complex queries, and a lack of effective root cause analysis mechanisms, resulting in low detection efficiency and limited coverage.

Method used

By combining rule tree search and Monte Carlo tree search techniques enhanced by a large language model, we dynamically explore the query rewriting space by constructing rule trees and Monte Carlo tree search, generate new rewriting rules using a large language model, and perform root cause analysis by combining a historical error pattern repository.

Benefits of technology

It improves the efficiency and coverage of logical error detection, enables more accurate root cause analysis, enhances the flexibility and efficiency of query rewriting, reduces redundant testing, and strengthens system reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120492487B_ABST
    Figure CN120492487B_ABST
Patent Text Reader

Abstract

This invention discloses a large-model-enhanced query rewriting synthesis method for detecting logical errors in database engines. The method includes: constructing a rule tree and systematically traversing all applicable rewriting rules; implementing a large language model-enhanced Monte Carlo tree search, combining Monte Carlo tree search with the large language model; and performing root cause analysis, utilizing a historical error pattern repository to precisely locate the abstract syntax tree nodes leading to the logical errors. This invention systematically explores the query rewriting space by combining rule tree search and large language model-enhanced Monte Carlo tree search techniques, improving the efficiency and coverage of logical error detection.
Need to check novelty before this filing date? Find Prior Art