How Devices Train Shared AI Models While Keeping Your Data Private
This patent describes a method for training a machine learning model across many devices, where each device keeps some parts of the model and its data private, only sharing updates for the common, global parts of the model.
Original patent title: “Partially local federated learning”
This patent describes a method for training a machine learning model across many devices, where each device keeps some parts of the model and its data private, only sharing updates for the common, global parts of the model. Granted to Google in 2025 with 29 claims, and it is expected to expire in 2041.
Key facts
Coverage
What does this patent actually cover?
This patent outlines a method for a client device to help train a larger machine learning model without sending its private data to a central server. The model has two parts: "local parameters" unique to the client, and "global parameters" shared across all devices. The client first receives the current global parameters from a server. Then, using a "support dataset" (a part of its local data not used for global training), it figures out the best values for its own local parameters (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). After that, it uses a "query dataset" (another part of its local data) to train and update only the global parameters (Claim 1). Finally, it sends back only the changes to the global parameters, specifically designed so that the server cannot reconstruct the client's private local data or local parameters (Claim 1). For example, your phone could help improve a predictive text model by training it on your typing habits, but only send back general improvements to the shared dictionary, never your specific messages.
The gap
What does this patent NOT cover?
- Does not cover traditional centralized machine learning where all raw data is sent to a single server for training.
- Does not cover federated learning systems that only have global parameters and no distinct local parameters on the client device.
- Does not cover methods where the client computing device transmits updates to its local parameters to the server.
- Does not cover systems where the parameter update data allows for the recovery of the local data maintained at the client device.
- Does not cover training methods that do not partition the local data into separate "support" and "query" datasets for different training steps.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
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 "partially local" approach, where a client device maintains and refines its own unique "local parameters" alongside the shared "global parameters." Critically, it only sends updates for the global parameters, ensuring that its private local data cannot be reconstructed from the transmitted information, a significant privacy enhancement over earlier federated learning methods.
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
Predictive text suggestions on smartphones
On-device photo categorization and search
Voice assistant personalization
Personalized recommendation engines
Health monitoring applications that train on sensitive user data
Why it matters
The bigger picture
This technology is crucial for developing powerful AI models while protecting user privacy. By allowing models to be trained on data directly on user devices, it avoids the need to collect and store sensitive information centrally. This approach helps companies like Google improve services such as predictive keyboards, voice assistants, and photo organization without ever seeing individual user data, which is increasingly important due to data privacy regulations.
Filed
May 27, 2021
Granted
October 14, 2025
Market context
Who's building on this
Companies in this space
Google LLC, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is a major developer and user of federated learning, applying it in products like Gboard (predictive text) and Google Assistant. Apple also employs similar on-device machine learning for privacy-preserving features. Other companies like NVIDIA and various research institutions are actively advancing federated learning techniques.
Market impact
This patent contributes to the evolution of privacy-preserving AI, enabling the deployment of more intelligent features on user devices without compromising sensitive data. It helps address growing concerns about data privacy and regulatory requirements, fostering trust in AI applications. This approach allows companies to improve their services by leveraging vast amounts of decentralized user data that would otherwise be inaccessible due to privacy constraints, potentially leading to more personalized and effective user experiences.
Claim 1 — Plain English
What this patent covers
This patent outlines a method for a client device to help train a larger machine learning model without sending its private data to a central server. The model has two parts: "local parameters" unique to the client, and "global parameters" shared across all devices. The client first receives the current global parameters from a server. Then, using a "support dataset" (a part of its local data not used for global training), it figures out the best values for its own local parameters (Claim 1). After that, it uses a "query dataset" (another part of its local data) to train and update only the global parameters (Claim 1). Finally, it sends back only the changes to the global parameters, specifically designed so that the server cannot reconstruct the client's private local data or local parameters (Claim 1). For example, your phone could help improve a predictive text model by training it on your typing habits, but only send back general improvements to the shared dictionary, never your specific messages.
The clever bit
The novelty lies in the "partially local" approach, where a client device maintains and refines its own unique "local parameters" alongside the shared "global parameters." Critically, it only sends updates for the global parameters, ensuring that its private local data cannot be reconstructed from the transmitted information, a significant privacy enhancement over earlier federated learning methods.
What it does not cover
- Does not cover traditional centralized machine learning where all raw data is sent to a single server for training.
- Does not cover federated learning systems that only have global parameters and no distinct local parameters on the client device.
- Does not cover methods where the client computing device transmits updates to its local parameters to the server.
- Does not cover systems where the parameter update data allows for the recovery of the local data maintained at the client device.
- Does not cover training methods that do not partition the local data into separate "support" and "query" datasets for different training steps.
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
19/20
Very broad protection
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
$47K – $150K
Midpoint $94K · 14.9 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.
The original legal language
Original claims
29 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Singhal, K., JR., H. S., Garrett, Z. A., WU, S., Rush, J. K., & Prakash, S. (2025). How Devices Train Shared AI Models While Keeping Your Data Private (U.S. Patent No. 12,443,890). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/12443890/partially-local-federated-learning
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="US12443890"></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 20220012637 · Nokia Technologies Oy
Training AI Models Together with Unlabeled Data Using a Teacher
US 12574477 · 2026 · Deep Sentinel
Training AI Models Across Different Computers
US 12518214 · 2026 · Nant Holdings IP
Training AI on Private Data Without Seeing It
US 20220383078 · Huawei Technologies Co
Adapting AI Models to Fit Device Resources
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 How Devices Train Shared AI Models While Keeping Your Data Private cover?
This patent describes a method for training a machine learning model across many devices, where each device keeps some parts of the model and its data private, only sharing updates for the common, global parts of the model.
Who owns patent US 12443890?
Google owns this patent, granted in 2025.
When does this patent expire?
This patent is expected to expire on May 27, 2041, when the invention enters the public domain.
What problem does this patent solve?
This technology is crucial for developing powerful AI models while protecting user privacy. By allowing models to be trained on data directly on user devices, it avoids the need to collect and store sensitive information centrally. This approach helps companies like Google improve services such as predictive keyboards, voice assistants, and photo organization without ever seeing individual user data, which is increasingly important due to data privacy regulations.
What does this patent NOT cover?
Does not cover traditional centralized machine learning where all raw data is sent to a single server for training.
Patent monitoring