AI That Links Information Across Documents for Better Answers
This patent describes an AI system that improves answers to questions by linking and understanding information across several related documents, rather than just one at a time.
Original patent title: “Inter-document attention mechanism”
This patent describes an AI system that improves answers to questions by linking and understanding information across several related documents, rather than just one at a time. Granted to Microsoft Technology Licensing in 2026 with 24 claims, and it is expected to expire in 2044.
Coverage
What does this patent actually cover?
This technology improves how AI systems answer questions by understanding connections between different documents. When you ask a question, the system first finds several related documents. It then feeds these documents into a special AI model called a transformer, which is designed to 'pay attention' to important words and phrases. Crucially, this model propagates attention from words in a first document to words in a second document (claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1), building a richer understanding. For example, if you ask about a person, and one document mentions their birth city while another mentions their current job, the AI can connect these details by letting the information flow between the documents. This process creates 'contextualized embeddings' for each word, allowing the AI to select the most relevant words to form an accurate answer to your query (claim 1).
The gap
What does this patent NOT cover?
- Does not cover systems that do not use a transformer-based machine learning model for propagating attention between documents.
- Does not cover methods that only propagate attention within a single document, without explicitly linking information between separate documents.
- Does not cover systems where the identification of related documents is not based on similarity to the query or explicit links between documents (claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 2).
- Does not cover AI models that retrieve answers without first processing tokens from multiple result documents through stacked network layers (claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover systems that fail to propagate attention between the query's own words and the words within the retrieved documents (claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 5, 6).
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The clever part is explicitly propagating 'attention' from words in one document to words in another document, rather than treating each document as a separate island. This allows the AI to build a more complete understanding of a topic by connecting related pieces of information spread across different sources.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Advanced search engines like Bing or Google Search
Question-answering systems in customer service bots
AI assistants that summarize research papers
Enterprise search tools for large document repositories
Why it matters
The bigger picture
This patent addresses a core challenge in natural language processing: understanding context across multiple sources. By enabling AI models to propagate attention between documents, it allows for more comprehensive and accurate answers to complex questions. This is crucial for search engines, virtual assistants, and knowledge management systems that need to synthesize information from vast amounts of text. It helps these systems move beyond simple keyword matching to provide more intelligent, nuanced responses.
Filed
May 10, 2024
Granted
June 16, 2026
Market context
Who's building on this
Companies in this space
Microsoft Technology Licensing LLC, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is actively developing and deploying advanced natural language processing technologies in its products like Bing, Microsoft 365 Copilot, and Azure AI services. Other major tech companies such as Google, Amazon, and Meta are also heavily invested in similar inter-document understanding capabilities for their search, AI assistant, and content analysis platforms.
Market impact
This type of technology significantly enhances the capability of search engines and AI assistants to provide more accurate and comprehensive answers. It enables products to synthesize information from disparate sources, moving beyond simple keyword matching to true semantic understanding. This leads to improved user experience in information retrieval and powers more sophisticated AI-driven applications across various industries, making AI systems more 'intelligent' in how they handle complex queries.
Claim 1 — Plain English
What this patent covers
This technology improves how AI systems answer questions by understanding connections between different documents. When you ask a question, the system first finds several related documents. It then feeds these documents into a special AI model called a transformer, which is designed to 'pay attention' to important words and phrases. Crucially, this model propagates attention from words in a first document to words in a second document (claim 1), building a richer understanding. For example, if you ask about a person, and one document mentions their birth city while another mentions their current job, the AI can connect these details by letting the information flow between the documents. This process creates 'contextualized embeddings' for each word, allowing the AI to select the most relevant words to form an accurate answer to your query (claim 1).
The clever bit
The clever part is explicitly propagating 'attention' from words in one document to words in another document, rather than treating each document as a separate island. This allows the AI to build a more complete understanding of a topic by connecting related pieces of information spread across different sources.
What it does not cover
- Does not cover systems that do not use a transformer-based machine learning model for propagating attention between documents.
- Does not cover methods that only propagate attention within a single document, without explicitly linking information between separate documents.
- Does not cover systems where the identification of related documents is not based on similarity to the query or explicit links between documents (claim 2).
- Does not cover AI models that retrieve answers without first processing tokens from multiple result documents through stacked network layers (claim 1).
- Does not cover systems that fail to propagate attention between the query's own words and the words within the retrieved documents (claim 5, 6).
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Moderate
Citation count
0/40
No citations yet
Claim breadth
16/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
20/20
Granted within 5 years
Assignee scale
20/20
Major company or institution
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$37K – $120K
Midpoint $75K · 17.5 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
24 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Bennett, P. N., Zhao, C., Song, X., Tiwary, S. K., ROSSET, C. L., & XIONG, C. (2026). AI That Links Information Across Documents for Better Answers (U.S. Patent No. 12,657,244). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/12657244/inter-document-attention-mechanism-12657244
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US12657244"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 20240338414 · Microsoft Technology Licensing
How AI Understands Answers Across Multiple Documents
US 10664744 · 2020 · Facebook Inc
How Computers Use Memory Networks to Answer Questions
US 10452978 · 2019 · Google LLC
How AI Models Understand Language Using 'Attention'
US 11798529 · 2023 · Microsoft Technology Licensing
Improving AI Language Understanding with Aligned Knowledge Graphs
More to explore
More in Software & Internet
US 4405829 · 1983 · Massachusetts Institute of Technology
How RSA Public-Key Encryption Keeps Digital Messages Secret
US 6285999 · 2001 · Leland Stanford Junior University
How Websites Get Ranked by Importance
US 5960411 · 1999 · Amazon com Inc
How Amazon's One-Click Ordering Works for Online Purchases
US 7669123 · 2010 · Facebook Inc
Displaying Friends' Activities in a Social Network Feed
New to patents?
Common Questions
Frequently Asked Questions
What does AI That Links Information Across Documents for Better Answers cover?
This patent describes an AI system that improves answers to questions by linking and understanding information across several related documents, rather than just one at a time.
Who owns patent US 12657244?
Microsoft Technology Licensing owns this patent, granted in 2026.
When does this patent expire?
This patent is expected to expire on May 10, 2044, when the invention enters the public domain.
What problem does this patent solve?
This patent addresses a core challenge in natural language processing: understanding context across multiple sources. By enabling AI models to propagate attention between documents, it allows for more comprehensive and accurate answers to complex questions. This is crucial for search engines, virtual assistants, and knowledge management systems that need to synthesize information from vast amounts of text. It helps these systems move beyond simple keyword matching to provide more intelligent, nuanced responses.
What does this patent NOT cover?
Does not cover systems that do not use a transformer-based machine learning model for propagating attention between documents.
Same assignee
More from Microsoft Technology Licensing
Patent monitoring