Microsoft patents system that uses AI to describe database structures
Microsoft describes a method that maps a database's structure into a visual graph and converts it into text for a language model. The AI then creates detailed descriptions, or descriptors, for each part of the database. These descriptions help a separate system understand how to translate user questions into correct database commands.
In the filing’s own words
A method disclosed herein provides for discovering and extracting database schema information from a database; generating a database graph that graphically depicts the database schema information; generating contextual data that includes or that is derived from the database graph; presenting a language model with the contextual data and an instruction to use the contextual data to generate schema element descriptors for the schema elements; storing the schema element descriptors generated by the language model based on processing of the instruction; and making the stored schema element descriptors available to a query translation system that performs query translation tasks.
What exactly they claim (claim 1)
1. A method comprising: extracting database schema information from a database, the database schema information comprising schema elements, relationships between the schema elements, and value constraint information associated with the schema elements; generating a database graph that graphically depicts the database schema information and the value constraint information, the database graph including nodes corresponding to the schema elements and the value constraint information and edges between nodes that represent the relationships between the schema elements; translating the database graph into a text-based representation readable by a language model; constructing a set of language model inputs that comprise the text-based representation of the database graph and an instruction to use the database schema information including the value constraint information within the text-based representation of the database graph to generate schema element descriptors for the schema elements; in response to providing the set of language model inputs to a language model, receiving the schema element descriptors generated by the language model; and in response to receiving an indication of a subset of the schema elements identified as relevant to a query translation request, returning a corresponding subset of the schema element descriptors for use in processing of the query translation request.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- GRAPH-BASED MODELING FOR DATABASE SCHEMA DESCRIPTOR GENERATION
- Publication number
- US20260300238A1
- Application number
- 19090609
- Filed
- Mar 26, 2025
- Published
- Oct 1, 2026
- Inventors
- 1
- Claims
- 21
Classified under
G06F 16/211 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.