Task Agnostic Embedding Based Labeling Escalation On Fly
Summary
The USPTO published patent application US20260099728A1 for a machine learning method involving task-agnostic embedding-based labeling escalation. The invention uses a two-pass system: a first-pass model makes an initial decision, and if embedding analysis indicates a need for escalation, a higher-complexity second-pass model generates a final decision. The application was filed on October 7, 2024, by inventors MohammadReza GHAEINI and Muhaimenul ADNAN and classified under CPC G06N 5/01.
What changed
The USPTO published patent application US20260099728A1, disclosing a machine learning method for task-agnostic embedding-based labeling escalation on the fly. The method uses a first-pass model with lower complexity to make initial decisions, generates task embeddings in an embedding space, identifies the top K subspace with K closest embedding distances, and escalates to a second-pass model with higher complexity when determined by embedding label analysis.
Affected parties include technology companies, manufacturers, and any entity developing machine learning systems that require adaptive decision-making across varying task complexities. The published application does not create immediate compliance obligations but signals emerging intellectual property claims in AI embedding techniques. Patent applicants and AI developers should monitor this application for competitive intelligence and freedom-to-operate considerations.
Archived snapshot
Apr 17, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
TASK AGNOSTIC EMBEDDING BASED LABELING ESCALATION ON FLY
Application US20260099728A1 Kind: A1 Apr 09, 2026
Inventors
MohammadReza GHAEINI, Muhaimenul ADNAN
Abstract
Aspects of the disclosure include machine learning architectures with task agnostic embedding-based labeling escalation on fly. A method includes receiving a request corresponding to a task and generating, by a first pass system, a first decision. The first pass system includes a first pass model having a first complexity. The method includes generating, for the task, a task embedding in an embedding space, determining, in the embedding space, a top K subspace having K embeddings having K closest distances to the task embedding, and determining embedding labels for the K embeddings. The method includes determining to escalate the task to a second pass system having a second pass model having a second, higher complexity and, responsive to determining the embedding labels, generating, by the second pass system, a second decision for the task and returning, responsive to receiving the request, a response including the second decision.
CPC Classifications
G06N 5/01
Filing Date
2024-10-07
Application No.
18907811
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.