USING COHORTS TO INFER ATTRIBUTES FOR AN INPUT CASE IN A QUESTION ANSWERING SYSTEM

Patent №

US 9,818,062

Granted

2017-11-14

Filed 2015

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

AI components

5

ml · nlp · kr · planning · evo

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

14626052

A cohort analysis mechanism analyzes cohorts to infer one or more additional attributes for an input case to provide a refined input case to answer a question in a question answering system. The refined input case is then used to answer a question in the question answering system. The refined input case can be used in a traditional question answering flow or in a flow that again uses cohort analysis to extract relevant data to answer the question. The cohort analysis mechanism analyzes cohorts to find common attributes in the cohorts and then determines whether to infer the common attributes into the refined input case. The cohort analysis mechanism may determine to dialog with a user to confirm an inferred attribute.

AI classification

Natural language1.00
Planning1.00
Machine learning1.00
Knowledge representation1.00
Evolutionary computation0.81
AI hardware0.37
Speech0.05
Vision0.03

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 349850220

Assignors

CLARK, ADAM T., HUEBERT, JEFFREY K., PAYTON, ASPEN L., PETRI, JOHN E., STEVENS, RICHARD J., WHALEY, KATHRYN L.

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC