Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 4, 2026International Journal of Software and Informatics

Natural Language Query Transformation Method for Spatial Databases Based on Large Language Model

View Full Paper
Ask AI
Bookmark
Share

Authors

LMLiu MengyiXJXU JianqiuTYTong Yongxin

Discussion

Loading...

Member takes

Overview

This research proposes a method that converts natural language queries to executable languages in spatial databases, indicating improved user accessibility.

Key Points

  • The aim is to simplify interactions between non-expert users and spatial databases through an innovative query transformation method.
  • Develop a natural language understanding phase to extract key query entities.
  • Construct a spatial data query corpus using large language models.
  • Select a structured language model based on the identified query type.
  • Map entities into the selected structured language model to generate executable language.
  • Demonstrated efficient transformation of natural language queries into executable languages.
  • Experimental results show applicability on multiple real-world datasets.

Cite This Study

Mengyi et al. (2026) studied this question.

synapsesocial.com/papers/69d0ae68659487ece0fa46cahttps://doi.org/10.21655/ijsi.1673-7288.00370
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Text‐to‐SpatialSQL: A LLM Based Method for Generating Spatial SQL Queries With Geo‐Knowledge Extracted From Software User Manual2026
  2. 2An Automated Framework for Natural Language-Based Spatial Query Using Large Language Models2026 · 2 citations
  3. 3Queries to Nonrelational Data Using Natural Language Based on a Large Language Model2026
  4. 4A Survey of NL2SQL with Large Language Models: Where are we, and where are we going?2024 · 6 citations
  5. 5Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL2024 · 17 citations