/Patent Tracker
MicrosoftPatent applicationAI & softwareInterest 4/10

Microsoft patents method to save resources when using AI on large documents

Patent drawing
Patent drawing from the official filing.

This filing describes a way to make AI systems use less memory and processing power when analyzing large amounts of text. It works by breaking documents into smaller, overlapping pieces, finding key ideas within them, and then adjusting the size of those pieces to improve the connections between those ideas.

Why it mattersThis could help companies run AI tools on their own data more efficiently, potentially lowering costs without needing massive servers.

In the filing’s own words

This document relates to providing meaningful information relating to a dataset. One example can chunk source documents into overlapping text chunks having a first size and extract concepts in the text chunks. The example can create a co-occurrence graph of the concepts and refine the co-occurrence graph by changing to a second chunk size.

What exactly they claim (claim 1)

1. A device-implemented method comprising: chunking source documents into overlapping text chunks having a first size; extracting concepts in the text chunks; creating a co-occurrence graph of the concepts; and, refining the co-occurrence graph by changing to a second chunk size.

Facts

Company
Microsoft (Microsoft Technology Licensing, LLC)
Official title
Resource Conserving GraphRAG
Publication number
US20260300370A1
Application number
19096188
Filed
Mar 31, 2025
Published
Oct 1, 2026
Inventors
3
Claims
20

Classified under

G06F 16/367 Physics & computingG06F 40/289 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Microsoft in AI & software

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.