IBM Knowledge Base Error Correction US Patent Granted
Summary
US Patent 12,608,589 B2 was granted to International Business Machines Corporation on April 21, 2026, covering a computer-implemented method for detecting and correcting knowledge base errors using propositional logic clauses and model graph-based reasoning. The patent describes a system that alternates reasoning and learning passes at a model graph until convergence to generate updated logical rules and facts exceeding a predetermined threshold. IBM now holds enforceable patent rights to the disclosed knowledge base error correction technology, which has implications for competitors developing similar logic-based AI systems.
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 — 32 changes logged to date.
What changed
US Patent 12,608,589 B2 was formally granted by the USPTO on April 21, 2026, to International Business Machines Corporation, covering a method and system for detecting and correcting knowledge base errors through propositional logic processing. The patented method involves generating logical rules and facts from propositional logic clauses, accumulating facts into a model graph, and performing alternating reasoning and learning passes until convergence to produce updated rules and facts exceeding a threshold.
For competitors and developers of knowledge base systems, this patent represents a protected approach to automated error correction in logic-based AI. Organizations developing similar propositional logic or model graph-based systems for knowledge base validation should conduct freedom-to-operate analyses to assess potential infringement exposure.
Archived snapshot
Apr 23, 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.
Detecting and correcting knowledge base errors
Grant US12608589B2 Kind: B2 Apr 21, 2026
Assignee
International Business Machines Corporation
Inventors
Ndivhuwo Makondo, Francois Pierre Luus, Naweed Aghmad Khan, Ismail Yunus Akhalwaya, Ryan Nelson Riegel, Oarabile Hope Moloko, Thabang Doreen Lebese
Abstract
A computer-implemented method may include processors configured for receiving input data corresponding to a knowledge base comprising a plurality of propositional logic clauses, generating output data corresponding to a first set of logical rules and a first set of facts based on the plurality of propositional logic clauses, accumulating the first set of facts to generate accumulated facts, generating a model graph based on the accumulated facts and the first set of logical rules, alternating reasoning and learning passes at the model graph until convergence to generate a second set of logical rules and a second set of facts, and generating a third set of logical rules and a third set of facts, wherein the third set of logical rules and the third set of facts exceed a first predetermined threshold.
CPC Classifications
G06N 20/00 G06N 3/042 G06N 3/045 G06N 3/084 G06N 5/025 G06N 5/046
Filing Date
2022-06-21
Application No.
17807909
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 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.