How Training Systems Share AI Knowledge Without Sharing Private Student Data
This patent describes a system where different student training centers can improve their AI models by sharing general learning patterns, not private student data, to make training better for everyone.
Original patent title: “Federated machine learning in adaptive training systems”
This patent describes a system where different student training centers can improve their AI models by sharing general learning patterns, not private student data, to make training better for everyone. Granted to CAE in 2024 with 27 claims and 1 forward citation, and it is expected to expire in 2043.
Coverage
What does this patent actually cover?
This system uses federated machine learning to improve student training across multiple locations while protecting privacy. A first training center uses an AI module to adapt training for its students and develops a 'first learning model' based on their performance metrics (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). A second training center extracts 'statistical properties' from its students' performance metrics, then uses a 'data simulator module' to create fake, but realistic, performance data (Claim 1). This simulated data is used to build a 'second learning model'. A central 'federation computing device' then combines the 'model weights' from both the first and second learning models to create or refine a 'federated model'. For example, in a flight simulator (Claim 8), pilot performance data like control yoke movements (Claim 8) could be used to improve the AI's ability to adapt training for new pilots at different flight schools.
The gap
What does this patent NOT cover?
- Does not cover systems that share raw student performance data directly between training centers.
- Does not cover machine learning systems that centralize all student performance data for model training.
- Does not cover federated learning approaches that exchange full local models instead of just model weights.
- Does not cover training systems where the AI does not adapt individualized training to each student.
- Does not cover systems that don't use simulated data generated from statistical properties for a local model's contribution.
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 how the system allows a training center to contribute to a shared AI model without revealing any actual student data. Instead of sending raw performance metrics, it extracts statistical properties and then generates simulated data, which is then used to train a local model whose 'weights' are shared. This multi-layered approach ensures privacy while still enabling collaborative learning for the AI.
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
Flight simulators for pilot training
Medical training simulations for surgeons
Military training systems for complex equipment operation
Industrial process control training platforms
Why it matters
The bigger picture
This patent is significant because it addresses a major challenge in AI-driven education and training: how to leverage large datasets for model improvement while respecting data privacy. By using federated learning with simulated data, it allows multiple training centers to collaboratively enhance their adaptive training systems without directly sharing sensitive student information. This approach is particularly valuable for high-stakes training environments, such as aviation or medical simulation, where data privacy and robust AI models are critical.
Filed
March 15, 2023
Granted
February 27, 2024
Market context
Who's building on this
Companies in this space
CAE Inc., the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is a global leader in training and simulation technologies, particularly in aviation and defense. Companies like Google, NVIDIA, and various AI/ML startups are actively developing and applying federated learning techniques across different sectors. Other major players in the simulation and adaptive learning space, such as those in healthcare education or industrial training, are likely exploring similar privacy-preserving AI methods.
Market impact
This technology enables training providers to pool their collective knowledge and improve AI-driven adaptive training systems without compromising individual student data privacy. It could lead to more sophisticated and effective training programs across industries that rely on high-fidelity simulations. This approach helps overcome data silos, fostering collaboration and potentially setting new standards for how sensitive performance data is handled in educational and professional development contexts.
Claim 1 — Plain English
What this patent covers
This system uses federated machine learning to improve student training across multiple locations while protecting privacy. A first training center uses an AI module to adapt training for its students and develops a 'first learning model' based on their performance metrics (Claim 1). A second training center extracts 'statistical properties' from its students' performance metrics, then uses a 'data simulator module' to create fake, but realistic, performance data (Claim 1). This simulated data is used to build a 'second learning model'. A central 'federation computing device' then combines the 'model weights' from both the first and second learning models to create or refine a 'federated model'. For example, in a flight simulator (Claim 8), pilot performance data like control yoke movements (Claim 8) could be used to improve the AI's ability to adapt training for new pilots at different flight schools.
The clever bit
The clever part is how the system allows a training center to contribute to a shared AI model without revealing any actual student data. Instead of sending raw performance metrics, it extracts statistical properties and then generates simulated data, which is then used to train a local model whose 'weights' are shared. This multi-layered approach ensures privacy while still enabling collaborative learning for the AI.
What it does not cover
- Does not cover systems that share raw student performance data directly between training centers.
- Does not cover machine learning systems that centralize all student performance data for model training.
- Does not cover federated learning approaches that exchange full local models instead of just model weights.
- Does not cover training systems where the AI does not adapt individualized training to each student.
- Does not cover systems that don't use simulated data generated from statistical properties for a local model's contribution.
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
6/40
Early citations
Claim breadth
18/20
Very broad protection
Recency
20/20
Granted within 5 years
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
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
$62K – $200K
Midpoint $125K · 16.6 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
27 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
DELISLE, J., Singh, N., & Winokur, B. (2024). How Training Systems Share AI Knowledge Without Sharing Private Student Data (U.S. Patent No. 11,915,111). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/11915111/federated-machine-learning-in-adaptive-training-systems
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="US11915111"></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 12518214 · 2026 · Nant Holdings IP
Training AI on Private Data Without Seeing It
US 20220012637 · Nokia Technologies Oy
Training AI Models Together with Unlabeled Data Using a Teacher
US 12443890 · 2025 · Google
How Devices Train Shared AI Models While Keeping Your Data Private
US 12039012 · 2024 · Sharecare AI
Sharing AI Knowledge Between Private Datasets Using Synthetic Data
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 How Training Systems Share AI Knowledge Without Sharing Private Student Data cover?
This patent describes a system where different student training centers can improve their AI models by sharing general learning patterns, not private student data, to make training better for everyone.
Who owns patent US 11915111?
CAE owns this patent, granted in 2024.
When does this patent expire?
This patent is expected to expire on March 15, 2043, when the invention enters the public domain.
What is patent US 11915111 cited by?
This patent has been cited by 1 later patents that build on its ideas.
What problem does this patent solve?
This patent is significant because it addresses a major challenge in AI-driven education and training: how to leverage large datasets for model improvement while respecting data privacy. By using federated learning with simulated data, it allows multiple training centers to collaboratively enhance their adaptive training systems without directly sharing sensitive student information. This approach is particularly valuable for high-stakes training environments, such as aviation or medical simulation, where data privacy and robust AI models are critical.
What does this patent NOT cover?
Does not cover systems that share raw student performance data directly between training centers.
Patent monitoring