A spatial database-oriented intelligent interaction method, system and related device

CN122240640APending Publication Date: 2026-06-19BEIJING SUPERMAP SOFTWARE CO LTD

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner: BEIJING SUPERMAP SOFTWARE CO LTD
Filing Date: 2026-03-02
Publication Date: 2026-06-19

AI Technical Summary

Technical Problem

Traditional intelligent interaction methods are prone to problems such as spatial semantic errors, uncontrollable computational costs, and migration failures in spatial scenarios.

Method used

A knowledge base is built by extracting metadata from a spatial database. Natural language requests are received to generate structured query plans, which are then corrected and cost estimated. Pre-configured strategies are injected to generate target SQL statements, which are then executed to address spatial semantic errors and uncontrollable computational costs.

Benefits of technology

It effectively reduces spatial semantic errors, controls computational costs, improves system response efficiency, avoids migration failures, and achieves stability and efficiency in intelligent interaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN122240640A_ABST

Patent Text Reader

Abstract

This invention provides an intelligent interaction method, system, and related equipment for spatial databases. It extracts spatial metadata from the spatial database and constructs a knowledge base based on the spatial metadata; receives natural language requests and generates a structured query plan based on the natural language requests and the knowledge base; corrects the structured query plan; generates SQL statements based on the corrected structured query plan, and performs cost estimation and index detection based on the SQL statements to obtain cost estimation results and index detection results; if the cost estimation results and index detection results meet the policy injection conditions, a pre-configured policy is injected into the corrected structured query plan to obtain a target structured query plan; and uses the target structured query plan to generate a target SQL statement and execute the target SQL statement to obtain the corresponding execution results. This approach can avoid spatial semantic errors, uncontrollable computational costs, and migration failures when dealing with spatial scenarios.

Need to check novelty before this filing date? Find Prior Art