Microsoft patents AI method to index large documents using sliding windows
Microsoft has filed a patent application for a method that uses generative AI to create search indexes for very long documents. The system breaks the document into overlapping sections called 'sliding windows' so the AI can describe each page with context from its neighbors, then combines these descriptions into a final index.
In the filing’s own words
Methods, apparatuses, and products for indexing pages of a document include generating, for each page window of a plurality of page windows of a document, a description of each page of a respective page window, including: selecting a particular page window of a plurality of page windows of the document by applying a sliding window to a plurality of pages of the document; prompting a generative artificial intelligence (AI) model to generate a description of each page in the particular page window based on any included visual content and contextual information including each other page in the particular page window; and receiving, as output from the generative AI model, the description of each page in the particular page window; and generating index data for the document based on the output from the generative AI model for each page window of the plurality of page windows.
What exactly they claim (claim 1)
1. A method of sliding window document indexing using generative artificial intelligence (AI), comprising: identifying a plurality of page windows of a document, wherein each page window of the plurality of page windows comprises a plurality of pages and wherein at least one page of the plurality of pages of each page window overlaps with at least one page of another page window of the plurality of page windows, and wherein a size of the document exceeds an input limit of a generative artificial intelligence (AI) model; generating, for each page window of the plurality of page windows of the document, a description of each page of a respective page window, including: applying a sliding window to a plurality of pages of the document by iterating over the plurality of page windows of the document; selecting a particular page window of the plurality of page windows of the document by applying a sliding window to a plurality of pages of the document; prompting the generative AI model to generate a description of each page in the particular page window based on any included visual content and contextual information including each other page in the particular page window; and receiving, as output from the generative AI model, the description of each page in the particular page window; and generating index data for the document based on the output from the generative AI model for each page window of the plurality of page windows.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- SLIDING WINDOW DOCUMENT INDEXING USING GENERATIVE ARTIFICIAL INTELLIGENCE
- Publication number
- US20260277943A1
- Application number
- 19079054
- Filed
- Mar 13, 2025
- Published
- Sep 17, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06F 16/31 Physics & computingG06F 16/93 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.