IBM Granted US Patent for AI Anomaly Detection
Summary
International Business Machines Corporation (IBM) has been granted US Patent 12,608,625 B2 for methods and systems of automatically training and implementing artificial intelligence-based anomaly detection models. The patent covers techniques for analyzing observability data in IT operations environments, modelling data as time series, and identifying time periods associated with normal activity levels to perform automated actions. The patent names 10 inventors and contains 19 claims.
“Methods, systems, and computer program products for automatically detecting periods of normal activity by analyzing observability data in IT operations environments are provided herein.”
About this source
GovPing monitors USPTO Patent Grants - AI & Computing (G06N) for new telecom & technology regulatory changes. Every update since tracking began is archived, classified, and available as free RSS or email alerts — 20 changes logged to date.
What changed
IBM has been granted US Patent 12,608,625 B2, titled 'Automatically training and implementing artificial intelligence-based anomaly detection models,' by the United States Patent and Trademark Office. The patent covers computer-implemented methods for detecting normal activity periods in IT operations environments by obtaining multiple types of observability data, modelling data as time series, automatically identifying time periods associated with given data activity levels, and performing automated actions based on those identified periods. Ten inventors are named: Shashank Mujumdar, Hima Patel, Sambaran Bandyopadhyay, Pooja Aggarwal, Anbang Xu, Hau-Wen Chang, Harshit Kumar, Katherine Guo, Rama Kalyani T. Akkiraju, and Gargi B. Dasgupta.
The patent is primarily relevant to AI/ML practitioners, enterprise software vendors, and providers of IT operations monitoring and observability tools. While patent grants do not directly impose compliance obligations, organisations developing AI-based IT operations or AIOps solutions should be aware of IBM's intellectual property position in the anomaly detection and automated time-series analysis space when assessing their own product development and licensing strategies.
Archived snapshot
Apr 22, 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.
Automatically training and implementing artificial intelligence-based anomaly detection models
Grant US12608625B2 Kind: B2 Apr 21, 2026
Assignee
International Business Machines Corporation
Inventors
Shashank Mujumdar, Hima Patel, Sambaran Bandyopadhyay, Pooja Aggarwal, Anbang Xu, Hau-Wen Chang, Harshit Kumar, Katherine Guo, Rama Kalyani T. Akkiraju, Gargi B. Dasgupta
Abstract
Methods, systems, and computer program products for automatically detecting periods of normal activity by analyzing observability data in IT operations environments are provided herein. A computer-implemented method includes obtaining multiple types of data related to one or more artificial intelligence-related information technology operations; modelling at least a portion of the obtained data as time series data; automatically identifying, from the time series data, one or more time periods associated with one or more given levels of data activity; and performing one or more automated actions, in at least one artificial intelligence-related information technology operations environment, based at least in part on the data corresponding to the one or more identified time periods.
CPC Classifications
G06N 5/022
Filing Date
2022-02-28
Application No.
17681984
Claims
19
Mentioned entities
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 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 Grants - AI & Computing (G06N) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.