Local device embeddings for automation - Amazon patent grant
Summary
USPTO granted Amazon Technologies, Inc. Patent US12596961B1 covering local device embeddings for network-connected device automation using machine learning. The patent describes inputting device state change data and historical state data into ML models to generate embedding data, which is stored and used to trigger automated actions. The patent contains 20 claims and is classified across AI/ML (G06N) and IoT (H04W) categories.
What changed
USPTO issued a new patent grant to Amazon Technologies, Inc. for local device embeddings enabling automation of network-connected computing devices. The technology involves feeding device state change data and historical state data into machine learning models to generate embedding representations, which are then stored and used to trigger automated device actions. The patent covers the full pipeline from data input through model inference to action execution.
For competitors in the IoT automation and edge AI space, this patent establishes intellectual property rights that could affect product development using local device embeddings for automation. The patent's 20-year term runs from the September 2021 filing date. Third parties should conduct freedom-to-operate analysis before developing similar automation technologies.
What to do next
- Monitor for potential infringement implications if operating in IoT/ML device automation space
- Review patent claims for freedom-to-operate analysis
- Track competitor patent activity in local embedding and device automation domain
Archived snapshot
Apr 7, 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.
Local device embeddings for automation
Grant US12596961B1 Kind: B1 Apr 07, 2026
Assignee
AMAZON TECHNOLOGIES, INC.
Inventors
Sven Eberhardt, Amir Salimi, Jin Long Lee, Maisie Wang, Akanksha Gupta, Kaustubh Anilkumar Vibhute, Biwei Tao, Caglar Iskender
Abstract
Devices and techniques are generally described for local device embeddings for automation. In various examples, first data representing first state change data for network-connected computing devices configured in communication with a first network may be determined. The first data may be input into a first machine learning model. In some examples, the first machine learning model may generate first embedding data representing a combination of the first data and second data. In some examples, the second data may represent historical state change data for the network-connected devices. In some examples, the first embedding data may be stored in memory. A first action may be performed by a first network-connected device based at least in part on the first embedding data.
CPC Classifications
G06N 3/02 G06N 3/04 G06N 3/044 G06N 3/045 G06N 3/0455 G06N 20/00 G06N 20/10 G06N 20/20 G06F 18/21355 G06F 18/214 G06F 40/20 H04W 4/023
Filing Date
2021-09-30
Application No.
17490343
Claims
20
Related changes
Get daily alerts for USPTO Patent Grants - 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 plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - AI & Computing (G06N) publishes new changes.