Using cohorts to infer attributes for an input case in a question answering system

Patent metadata

Field	Value
Publication number	US-2016247073-A1
Application number	US-201514658973-A
Country	US
Kind code	A1
Filing date	Mar 16, 2015
Priority date	Feb 19, 2015
Publication date	Aug 25, 2016
Grant date	—

Abstract

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.

First claim

1 . An apparatus comprising:
at least one processor; a memory coupled to the at least one processor; a cohort analysis mechanism residing in the memory and executed by the at least one processor that analyzes an input case representing a question and finds cohorts with similar attributes to the input case to infer an attribute for the input case, provides a refined input case that includes the inferred attribute, and answers the question using the refined input case; and wherein the cohorts are entities with similar characteristics to an entity of the input case and available in a corpus of data.

2 . The apparatus of claim 1 wherein the cohort analysis mechanism analyzes the cohorts to find common attributes in the cohorts and finds missing attributes in the case for the common attributes in the cohorts.

3 . The apparatus of claim 2 wherein the cohort analysis mechanism scores the missing attributes.

4 . The apparatus of claim 3 wherein the cohort analysis mechanism applies confidence thresholds to the missing attributes to determine whether to infer the attribute for the refined input case.

5 . The apparatus of claim 4 wherein the cohort analysis mechanism determines whether to dialog with a user to confirm the inferred attribute.

6 . The apparatus of claim 5 wherein the cohort analysis mechanism uses a lower threshold to determine whether to dialog with the user compared to inferring the attribute without dialoging with the user.

7 . The apparatus of claim 1 wherein the input case is a medical question for a patient and the cohort analysis mechanism processes the medical history of the patient and finds the cohorts from medical histories of other patients to infer an attribute for the input case from the cohorts.

8 . The apparatus of claim 1 wherein the cohort analysis mechanism is part of a question answering application that answers a natural language question.

Assignees

• IBM

Inventors

• Clark Adam T
• Huebert Jeffrey K
• Payton Aspen L
• Petri John E
• Stevens Richard J
• Whaley Kathryn L

Classifications

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G06F17/3043

  Physics · mapped topic

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G06F16/90324

  using system suggestions · CPC title

• G06F16/24522

  Translation of natural language queries to structured queries · CPC title