Automated list answers for question answering systems patent

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted patent US12585677B2 to International Business Machines Corporation for an automated method of generating improved list-type answers in question answering systems. The patent describes a computer-implemented process using machine learning models to classify text and lists, and to provide relevant answers to users.

View original document View source feed page

What changed

USPTO patent US12585677B2, granted to International Business Machines Corporation, details an automated method for enhancing question answering systems. The patent covers a computer-implemented process that utilizes two machine learning models: one to classify introductory text as redundant or non-redundant, and another to categorize lists based on type. The system then provides users with the non-redundant introductory text, a subset or full list of items, and an indication of list type and completeness.

This patent grant represents a new intellectual property asset for IBM in the field of AI and question answering systems. While it does not impose direct compliance obligations on other entities, it signifies innovation in AI-driven information retrieval. Companies developing or utilizing similar AI-powered question answering technologies may need to consider this patent in their intellectual property strategy and freedom-to-operate analyses.

Source document (simplified)

← USPTO Patent Grants

Automated generation of improved list-type answers in question answering systems

Grant US12585677B2 Kind: B2 Mar 24, 2026

Assignee

International Business Machines Corporation

Inventors

Sara Rosenthal, Odellia Boni, Michal Shmueli-Scheuer, Ora Peled Nakash

Abstract

A computer-implemented method comprising: receiving data comprising: a question provided by a user, a list that constitutes a direct answer to the question, and an introductory text to the list; using a first machine learning model to classify the introductory text as redundant or nonredundant, based on the data; using a second machine learning model to classify the list as belonging to a certain list type out of multiple list types, based on the list; and providing to the user: (a) the introductory text, only if the introductory text has been classified as nonredundant, (b) all or only a subset of the items of the list, (c) an indication as to the number of non-provided items of the list or the number of all items of the list, if only a subset of the items is being provided in (b), and (d) a description of the certain list type.

CPC Classifications

G06F 16/3329 G06F 16/3322 G06F 16/332 G06F 16/334 G06F 16/3344 G06F 16/00 G06F 16/243 G06F 16/24522 G06F 16/90332 G06F 16/953 G06F 16/24578 G06F 16/355 G06F 17/30864 G06F 40/166 G06F 40/30 G06F 40/35 G06F 40/242 G06F 40/279 G06F 40/20 G06F 18/241 G06N 20/00 G06N 5/04 G09B 7/00