Get the newsletter
Microsoft · AI / ML · Filed Mar 31, 2025 · USPTO published Oct 1, 2026 · Oct 1 release

Microsoft's New Patent Cuts the Cost of Teaching AI to Connect Information

When AI systems search large document collections, the biggest hidden cost isn't the search itself, it's building the map of concepts the search depends on. Microsoft has filed a patent for a method that trims that upfront cost without sacrificing the quality of the answers.

A graphical user interface shows an AI system breaking down a user's question into multiple sub-queries for processing. Drawing from patent filing US 2026/0300370 A1.
A graphical user interface shows an AI system breaking down a user's question into multiple sub-queries for processing.All 32 drawings ↓
Publication number
US 2026/0300370 A1(US20260300370A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
Mar 31, 2025 · Oct 1, 2026
Inventors
Darren Keith EDGE, Jonathan Karl LARSON, Thu Ha TRINH
Status when we published
Waiting for an examiner
Document
20 claims
US classification
704/9
Examiner
SPOONER, LAMONT M (Art Unit 2657)

What Microsoft's adaptive knowledge graph actually does

Every time an AI assistant answers a question about a large pile of documents, something expensive happens in the background: the system has to read all those documents and build a kind of map showing which ideas appear near each other. That map is what lets it give you a coherent answer instead of random snippets.

The problem is that building a high-quality map is slow and computationally heavy. Microsoft's patent describes a two-step shortcut: start by chopping the documents into larger text blocks to get a rough draft of the concept map quickly, then zero in on smaller blocks only where the map needs more detail. Instead of doing the most expensive work everywhere, you do it only where it counts.

The result is a concept map that's good enough to be useful but built at a fraction of the usual cost. That matters most for companies running AI tools over large internal document libraries, where every query has a real computing price tag.

From the filing · CLAIM 1
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.

Translation: Breaking documents into overlapping pieces and building a concept map, then adjusting the piece size to improve it.

How the chunk-size shift refines the concept graph

The patent covers a technique inside a family of AI retrieval systems called GraphRAG (Graph-based Retrieval-Augmented Generation). GraphRAG works by turning a document collection into a graph, a web of concepts and the relationships between them, so an AI can answer questions by traversing that web rather than scanning raw text.

The specific method works in four steps:

  • Chunking: source documents are split into overlapping text segments (so ideas that span a boundary aren't lost) at a first, larger chunk size.
  • Concept extraction: the system identifies meaningful terms and entities inside each chunk.
  • Co-occurrence graph creation: it records which concepts appear near each other, building a graph where edges represent "these ideas show up together."
  • Refinement: the graph is then improved by switching to a second chunk size, allowing the system to recalibrate where the initial pass was too coarse or too fine.

The key insight is that chunk size drives both cost and accuracy. Larger chunks are cheaper to process but miss fine-grained relationships; smaller chunks catch nuance but multiply the computation. By starting coarse and refining selectively, the patent proposes a way to hit a better cost-quality balance than running a single fixed chunk size from start to finish.

From the filing · THE ABSTRACT
This document relates to providing meaningful information relating to a dataset.

Translation: The technology helps make sense of large amounts of stored data.

What this means for running AI search on real data

For any organization running AI-powered search over its own documents, legal files, research archives, internal wikis, the cost of building and maintaining the underlying knowledge graph is a real operational expense. A method that cuts that cost while preserving answer quality could make GraphRAG-style systems practical at scales where they're currently too expensive to run continuously.

For everyday users, the effect would be invisible but felt: AI assistants that can answer detailed questions about large document sets faster and at lower operating cost, which matters when those costs determine whether a product feature gets built at all. Microsoft's bet on GraphRAG is visible across multiple filings, and this one targets the part of the pipeline that most affects whether the technology stays affordable as document collections grow.

Microsoft's 72nd filing in our Language AI coverage since May adds to a run that includes one on image meaning search and one grouping cloud alerts.

Source: US 2026/0300370 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Microsoft patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 32 sheets

32 drawing sheets from US 2026/0300370 A1 · click any drawing to enlarge

AI information processing system, drawing sheet 1 from US 2026/0300370 A1
Sheet 1 AI information processing system
AI information processing system, drawing sheet 2 from US 2026/0300370 A1
Sheet 2 AI information processing system
Main screen, search and create, drawing sheet 3 from US 2026/0300370 A1
Sheet 3 Main screen, search and create
Create new graph dialog, drawing sheet 4 from US 2026/0300370 A1
Sheet 4 Create new graph dialog
Ingesting a news file, drawing sheet 5 from US 2026/0300370 A1
Sheet 5 Ingesting a news file
Data ingestion progress, drawing sheet 6 from US 2026/0300370 A1
Sheet 6 Data ingestion progress
AI settings, query decomposer, drawing sheet 7 from US 2026/0300370 A1
Sheet 7 AI settings, query decomposer
AI settings, retrieval traversal, drawing sheet 8 from US 2026/0300370 A1
Sheet 8 AI settings, retrieval traversal
Show the other 24 sheets
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 9
Sheet 9
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 10
Sheet 10
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 11
Sheet 11
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 12
Sheet 12
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 13
Sheet 13
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 14
Sheet 14
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 15
Sheet 15
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 16
Sheet 16
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 17
Sheet 17
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 18
Sheet 18
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 19
Sheet 19
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 20
Sheet 20
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 21
Sheet 21
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 22
Sheet 22
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 23
Sheet 23
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 24
Sheet 24
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 25
Sheet 25
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 26
Sheet 26
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 27
Sheet 27
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 28
Sheet 28
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 29
Sheet 29
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 30
Sheet 30
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 31
Sheet 31
Microsoft’s New Patent Cuts the Cost of Teaching AI to Connect Information patent drawing, sheet 32
Sheet 32
Patent filing page

Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.