Improving AI Language Understanding with Aligned Knowledge Graphs
This patent describes a method for making AI language models smarter by combining them with knowledge modules, which learn from two different, but related, knowledge graphs.
Original patent title: “Generation of optimized knowledge-based language model through knowledge graph multi-alignment”
This patent describes a method for making AI language models smarter by combining them with knowledge modules, which learn from two different, but related, knowledge graphs. Granted to Microsoft Technology Licensing in 2023 with 24 claims and 3 forward citations, and it is expected to expire in 2041.
Coverage
What does this patent actually cover?
This patent details a computer-implemented method to enhance how AI understands language by jointly training a language module with a knowledge module. First, it obtains two separate knowledge graphs, each containing entities (like people or places) and relations (how they connect), as described in ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1. It then aligns these two graphs, finding where entities and relations in one graph match those in the other. A language module, which creates numerical representations (embeddings) for words and concepts, and a knowledge module are accessed. The knowledge module is trained using these embeddings. Crucially, the language and knowledge modules are integrated so they can exchange information: the knowledge module gives 'knowledge information input' to the language module, and the language module provides 'context information input' to the knowledge module, as stated in Claim 1. This integrated system is then further trained using the aligned knowledge graphs to perform 'semantic analysis' for entities and relations, meaning it understands their meaning and relationships better. For example, Claim 4 describes using this system to translate speech from one language to another, leveraging the combined knowledge.
The gap
What does this patent NOT cover?
- Does not cover training a language model without explicitly integrating it with a separate, dedicated knowledge module.
- Does not cover systems that use only a single knowledge graph, as it specifies obtaining and aligning a 'first knowledge graph' with a 'second knowledge graph'.
- Does not cover language models where the knowledge module and language module do not actively exchange information in a two-way flow, providing input to each other.
- Does not cover language understanding systems that do not perform 'semantic analysis for the entities and entity relations' based on learned knowledge.
- Does not cover simple machine translation or speech transcription without the underlying joint training and knowledge graph alignment described.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in the 'joint training' and 'integration' of the language and knowledge modules, where they continuously feed information to each other. This creates a powerful feedback loop, allowing the language module to benefit from structured knowledge and the knowledge module to benefit from contextual language understanding, all while leveraging insights from 'multi-aligned' knowledge graphs.
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 that understand complex queries
Smart virtual assistants like Microsoft Copilot or Google Assistant
Enterprise AI systems for analyzing company-specific documents
Cross-lingual information retrieval systems
Automated content summarization tools
Why it matters
The bigger picture
Understanding language is a core challenge for AI. This patent offers a way to make AI systems much better at grasping meaning by giving them structured knowledge, not just statistical patterns from text. By combining language models with knowledge graphs, AI can move beyond just predicting the next word to truly understanding facts and relationships. This is vital for creating more accurate virtual assistants, search engines, and specialized AI tools that can reason about information.
Filed
May 18, 2021
Granted
October 24, 2023
Market context
Who's building on this
Companies in this space
Microsoft, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is actively developing and integrating advanced AI capabilities into its products, including search engines, cloud services, and productivity tools. Other major technology companies like Google, Amazon, and Meta are also heavily invested in improving natural language understanding through similar knowledge-enhanced AI models, constantly seeking ways to make their AI more intelligent and context-aware.
Market impact
This type of technology contributes to the ongoing advancement of AI systems, particularly in natural language processing. It enables the creation of more sophisticated AI assistants, search algorithms, and enterprise solutions that can understand and process information with greater accuracy and nuance. This leads to better user experiences in consumer products and more efficient data analysis in business applications, driving innovation across various sectors reliant on AI for information retrieval and understanding.
Claim 1 — Plain English
What this patent covers
This patent details a computer-implemented method to enhance how AI understands language by jointly training a language module with a knowledge module. First, it obtains two separate knowledge graphs, each containing entities (like people or places) and relations (how they connect), as described in Claim 1. It then aligns these two graphs, finding where entities and relations in one graph match those in the other. A language module, which creates numerical representations (embeddings) for words and concepts, and a knowledge module are accessed. The knowledge module is trained using these embeddings. Crucially, the language and knowledge modules are integrated so they can exchange information: the knowledge module gives 'knowledge information input' to the language module, and the language module provides 'context information input' to the knowledge module, as stated in Claim 1. This integrated system is then further trained using the aligned knowledge graphs to perform 'semantic analysis' for entities and relations, meaning it understands their meaning and relationships better. For example, Claim 4 describes using this system to translate speech from one language to another, leveraging the combined knowledge.
The clever bit
The novelty lies in the 'joint training' and 'integration' of the language and knowledge modules, where they continuously feed information to each other. This creates a powerful feedback loop, allowing the language module to benefit from structured knowledge and the knowledge module to benefit from contextual language understanding, all while leveraging insights from 'multi-aligned' knowledge graphs.
What it does not cover
- Does not cover training a language model without explicitly integrating it with a separate, dedicated knowledge module.
- Does not cover systems that use only a single knowledge graph, as it specifies obtaining and aligning a 'first knowledge graph' with a 'second knowledge graph'.
- Does not cover language models where the knowledge module and language module do not actively exchange information in a two-way flow, providing input to each other.
- Does not cover language understanding systems that do not perform 'semantic analysis for the entities and entity relations' based on learned knowledge.
- Does not cover simple machine translation or speech transcription without the underlying joint training and knowledge graph alignment described.
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
Strong
Citation count
12/40
Early citations
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
$70K – $225K
Midpoint $140K · 14.7 yr remaining · industry ×1.5
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
Zeng, N., & Zhu, C. (2023). Improving AI Language Understanding with Aligned Knowledge Graphs (U.S. Patent No. 11,798,529). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/11798529/generation-of-optimized-knowledge-based-language-model-through-knowledge-graph-m
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="US11798529"></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 11507851 · 2022 · Samsung Electronics Co
How AI Connects Different Databases Using Knowledge Graphs
US 20240144032 · Alipay Hangzhou Information Technology Co
How to Combine Information from Multiple Knowledge Graphs
US 11989527 · 2024 · Unlikely Artificial Intelligence
How a Computer System Checks and Improves AI Text
US 12073180 · 2024 · Unlikely Artificial Intelligence
How a Computer System Fact-Checks AI Language Models
More to explore
More in AI & Machine Learning
US 10452978 · 2019 · Google LLC
How AI Models Understand Language Using 'Attention'
US 6523026 · 2003 · Huntsman International LLC
How Computers Find Hidden Connections Between Different Fields of Knowledge
US 11615208 · 2023 · Capital One Services LLC
How Cloud Systems Automatically Create and Train AI Data Models
US 10402750 · 2019 · Facebook Inc
How Facebook Uses Deep Learning to Predict What You Might Like
New to patents?
Common Questions
Frequently Asked Questions
What does Improving AI Language Understanding with Aligned Knowledge Graphs cover?
This patent describes a method for making AI language models smarter by combining them with knowledge modules, which learn from two different, but related, knowledge graphs.
Who owns patent US 11798529?
Microsoft Technology Licensing owns this patent, granted in 2023.
When does this patent expire?
This patent is expected to expire on May 18, 2041, when the invention enters the public domain.
What is patent US 11798529 cited by?
This patent has been cited by 3 later patents that build on its ideas.
What problem does this patent solve?
Understanding language is a core challenge for AI. This patent offers a way to make AI systems much better at grasping meaning by giving them structured knowledge, not just statistical patterns from text. By combining language models with knowledge graphs, AI can move beyond just predicting the next word to truly understanding facts and relationships. This is vital for creating more accurate virtual assistants, search engines, and specialized AI tools that can reason about information.
What does this patent NOT cover?
Does not cover training a language model without explicitly integrating it with a separate, dedicated knowledge module.
Same assignee
More from Microsoft Technology Licensing
Patent monitoring