Adapting AI Models to Fit Device Resources
This patent describes how a computer system can automatically shrink a large artificial intelligence model, specifically a "transformer" type, to fit the available computing power of a phone or other device.
Original patent title: “Data processing method and related device”
This patent describes how a computer system can automatically shrink a large artificial intelligence model, specifically a "transformer" type, to fit the available computing power of a phone or other device. Owned by Huawei Technologies Co with 22 claims and 6 forward citations, and it is expected to expire in 2042.
Key facts
Coverage
What does this patent actually cover?
The patent describes a method for a processing device to adjust an AI model, called a "first neural network model," to better suit a "terminal device" (like a smartphone). It first checks the terminal device's "available resource state" (like how much memory or processing power it has) or a "performance requirement." Based on this, it creates a "second neural network model" by reducing parts of the first model. This reduction can involve making the second model have fewer "attention heads" in its "transformer layers" (claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1), fewer "neurons" in its "intermediate layers" (claim 1), or fewer "transformer layers" overall (claim 1). For example, if a phone has limited memory, the system might remove some attention heads from the original AI model to create a smaller, faster version that still works well on that phone.
The gap
What does this patent NOT cover?
- Does not cover increasing the size of a neural network model based on available resources.
- Does not cover adapting non-transformer neural network architectures.
- Does not cover model adaptation methods that change the type of layers or neurons, only their quantity.
- Does not cover methods where the selection of components to remove is random, as claimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 5 suggests a capability-based selection.
- Does not cover adapting models by changing their data types (e.g., from 32-bit to 16-bit floating point).
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 systematically creating a family of smaller, efficient neural network models from a single larger model by selectively reducing specific structural components (attention heads, neurons, layers) based on a device's real-time resource availability. This allows for dynamic, on-the-fly adaptation rather than needing to pre-train and store many different model sizes.
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
On-device AI assistants (e.g., voice recognition on a smartphone)
Image processing on mobile cameras
Personalized recommendations on edge devices
AI-powered features in smartwatches
Federated learning clients
Why it matters
The bigger picture
This technology is crucial for deploying complex AI models, especially large language models, on devices with limited computing power, such as smartphones, smart home devices, and IoT sensors. It allows these devices to perform advanced AI tasks locally without constantly relying on powerful cloud servers, improving speed, privacy, and offline functionality. Huawei, as a major device manufacturer, would benefit from efficient on-device AI.
Filed
August 8, 2022
Market context
Who's building on this
Companies in this space
Companies like Huawei, Google, Apple, and Qualcomm are actively developing and deploying AI models optimized for edge devices. Startups specializing in AI model compression and efficient inference, such as Deci and Neural Magic, also operate in this space. The original assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, Huawei, continues to integrate advanced AI capabilities into its consumer electronics and telecommunications infrastructure.
Market impact
This type of technology enables a broader deployment of sophisticated AI on resource-constrained devices, expanding the market for on-device AI applications. It helps device manufacturers offer advanced features without requiring constant cloud connectivity, improving user experience and data privacy. It also fosters competition in the mobile AI chip and software sectors by making efficient model execution a key differentiator.
Claim 1 — Plain English
What this patent covers
The patent describes a method for a processing device to adjust an AI model, called a "first neural network model," to better suit a "terminal device" (like a smartphone). It first checks the terminal device's "available resource state" (like how much memory or processing power it has) or a "performance requirement." Based on this, it creates a "second neural network model" by reducing parts of the first model. This reduction can involve making the second model have fewer "attention heads" in its "transformer layers" (claim 1), fewer "neurons" in its "intermediate layers" (claim 1), or fewer "transformer layers" overall (claim 1). For example, if a phone has limited memory, the system might remove some attention heads from the original AI model to create a smaller, faster version that still works well on that phone.
The clever bit
The novelty lies in systematically creating a family of smaller, efficient neural network models from a single larger model by selectively reducing specific structural components (attention heads, neurons, layers) based on a device's real-time resource availability. This allows for dynamic, on-the-fly adaptation rather than needing to pre-train and store many different model sizes.
What it does not cover
- Does not cover increasing the size of a neural network model based on available resources.
- Does not cover adapting non-transformer neural network architectures.
- Does not cover model adaptation methods that change the type of layers or neurons, only their quantity.
- Does not cover methods where the selection of components to remove is random, as claim 5 suggests a capability-based selection.
- Does not cover adapting models by changing their data types (e.g., from 32-bit to 16-bit floating point).
Patent timeline
Application submitted to the patent office
Patent enters public domain
PatentBrief Score
Impact Score
Moderate
Citation count
17/40
Early citations
Claim breadth
15/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
0/20
Older than 20 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
$100K – $319K
Midpoint $200K · 16.1 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
22 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
HOU, L., Jiang, X., & Shang, L. Adapting AI Models to Fit Device Resources (U.S. Patent No. 20,220,383,078). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/20220383078/data-processing-method-and-related-device
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="US20220383078"></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 12574477 · 2026 · Deep Sentinel
Training AI Models Across Different Computers
US 20230162023 · Mitsubishi Electric Research Laboratories
Automated AI for Adapting to New Data Without Retraining
US 10452978 · 2019 · Google LLC
How AI Models Understand Language Using 'Attention'
US 12423586 · 2025 · D5AI
Making AI Smarter by Focusing on Unsure 'Nodes'
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 Adapting AI Models to Fit Device Resources cover?
This patent describes how a computer system can automatically shrink a large artificial intelligence model, specifically a "transformer" type, to fit the available computing power of a phone or other device.
Who owns patent US 20220383078?
This patent is owned by Huawei Technologies Co.
When does this patent expire?
This patent is expected to expire on August 8, 2042, when the invention enters the public domain.
What is patent US 20220383078 cited by?
This patent has been cited by 6 later patents that build on its ideas.
What problem does this patent solve?
This technology is crucial for deploying complex AI models, especially large language models, on devices with limited computing power, such as smartphones, smart home devices, and IoT sensors. It allows these devices to perform advanced AI tasks locally without constantly relying on powerful cloud servers, improving speed, privacy, and offline functionality. Huawei, as a major device manufacturer, would benefit from efficient on-device AI.
What does this patent NOT cover?
Does not cover increasing the size of a neural network model based on available resources.
Patent monitoring