How Samsung Uses Two AI Models to Improve Sentence Generation
A method for training an AI to write better sentences by using a second model that reads or generates text in a different order to grade the first model's work.
Original patent title: “Method of updating sentence generation model and sentence generating apparatus”
A method for training an AI to write better sentences by using a second model that reads or generates text in a different order to grade the first model's work. Granted to Samsung Electronics Co Ltd in 2023 with 29 claims and 1 forward citation, and it is expected to expire in 2038.
Coverage
What does this patent actually cover?
This patent describes a way to train a machine learning model to generate text more accurately. It uses two 'decoding models'—essentially the parts of an AI that pick the next word in a sentence. The first model generates a target sentence, while the second model acts as a critic by generating words in a different order (such as backward) to calculate 'reward information.' This reward information acts like a score, telling the first model how good its sentence was, which is then used to update the first model's internal weights to improve future performance.
The gap
What does this patent NOT cover?
- Does not cover simple text generation that lacks a secondary, order-reversed validation model.
- Does not cover training methods that rely solely on human-provided labels or static datasets.
- Does not cover architectures that do not use neural network weight resetting as the primary training mechanism.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
By forcing the second model to process or generate words in a different order (like backward), the system gains a structural check on the first model's output, helping to catch errors that a forward-only model might consistently repeat.
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
Samsung Bixby voice assistant responses
Automated machine translation software
Predictive text and smart reply features in mobile operating systems
Why it matters
The bigger picture
As AI-driven text generation becomes standard in consumer electronics, improving the quality of machine-generated language without massive amounts of human-labeled data is a major technical hurdle. This approach helps Samsung refine its virtual assistants and automated translation tools by creating a self-improving loop between two different AI perspectives.
Filed
June 21, 2018
Granted
August 15, 2023
Market context
Who's building on this
Companies in this space
Samsung Electronics remains the primary entity developing this technology, integrating it into their proprietary AI frameworks. Other major players in the generative AI space, such as Google and OpenAI, utilize similar reinforcement learning techniques, though often with different architectural approaches like Reinforcement Learning from Human Feedback (RLHF).
Market impact
This patent reflects the industry-wide shift toward 'self-supervised' or 'reinforcement learning' training methods, which reduce the need for expensive human intervention in training AI. It strengthens Samsung's position in the competitive landscape of mobile AI assistants by providing a method to refine models locally or with less reliance on massive external training sets.
Claim 1 — Plain English
What this patent covers
This patent describes a way to train a machine learning model to generate text more accurately. It uses two 'decoding models'—essentially the parts of an AI that pick the next word in a sentence. The first model generates a target sentence, while the second model acts as a critic by generating words in a different order (such as backward) to calculate 'reward information.' This reward information acts like a score, telling the first model how good its sentence was, which is then used to update the first model's internal weights to improve future performance.
The clever bit
By forcing the second model to process or generate words in a different order (like backward), the system gains a structural check on the first model's output, helping to catch errors that a forward-only model might consistently repeat.
What it does not cover
- Does not cover simple text generation that lacks a secondary, order-reversed validation model.
- Does not cover training methods that rely solely on human-provided labels or static datasets.
- Does not cover architectures that do not use neural network weight resetting as the primary training mechanism.
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
6/40
Early citations
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
$62K – $200K
Midpoint $125K · 12.0 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
29 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Lee, H., & NA, H. (2023). How Samsung Uses Two AI Models to Improve Sentence Generation (U.S. Patent No. 11,727,263). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/11727263/method-of-updating-sentence-generation-model-and-sentence-generating-apparatus
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="US11727263"></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 20220383078 · Huawei Technologies Co
Adapting AI Models to Fit Device Resources
US 10289962 · 2019 · Google LLC
How to Shrink Large AI Models Using Knowledge Distillation
US 10452978 · 2019 · Google LLC
How AI Models Understand Language Using 'Attention'
US 20250363357 · Ubotica Technologies
How to Update AI on Small Devices with Slow Internet
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 Samsung Uses Two AI Models to Improve Sentence Generation cover?
A method for training an AI to write better sentences by using a second model that reads or generates text in a different order to grade the first model's work.
Who owns patent US 11727263?
Samsung Electronics Co Ltd owns this patent, granted in 2023.
When does this patent expire?
This patent is expected to expire on June 21, 2038, when the invention enters the public domain.
What is patent US 11727263 cited by?
This patent has been cited by 1 later patents that build on its ideas.
What problem does this patent solve?
As AI-driven text generation becomes standard in consumer electronics, improving the quality of machine-generated language without massive amounts of human-labeled data is a major technical hurdle. This approach helps Samsung refine its virtual assistants and automated translation tools by creating a self-improving loop between two different AI perspectives.
What does this patent NOT cover?
Does not cover simple text generation that lacks a secondary, order-reversed validation model.
Same assignee
More from Samsung Electronics Co Ltd
Patent monitoring