Managing a question and answer system

Patent metadata

Field	Value
Publication number	US-2016180237-A1
Application number	US-201514864285-A
Country	US
Kind code	A1
Filing date	Sep 24, 2015
Priority date	Dec 17, 2014
Publication date	Jun 23, 2016
Grant date	—

Abstract

Disclosed aspects include managing data for a Question and Answering (QA) system. Aspects include a set of questions being received by the QA system. In response to receiving the set of questions, a first confidence score for a first answer to a first question of the set of questions is determined. Aspects include determining the first confidence score meets a threshold confidence score. In response to the first confidence score meeting the threshold confidence score, the QA system stores the first question and the first answer for future presentation use as an aid in formulating a second query.

First claim

What is claimed is:

1 . A computer-implemented method of managing data for a Question and Answering (QA) system, the method comprising:
receiving, by the QA system, a set of questions; determining, in response to receiving the set of questions, a first confidence score for a first answer to a first question of the set of questions; storing, by the QA system in response to determining the first confidence score meets at least a threshold confidence score, the first question and the first answer; receiving a second question from a user; determining the second question is related to the first question; and selecting, for presentation to the user, an output.

2 . The method of claim 1 , wherein the output is selected from a group consisting of at least one of: the first question, the first answer, the first confidence score, a group of questions, a group of answers, a group of confidence scores, a first past-user rating, an answer-evaluation value, or a past-user identifier.

3 . The method of claim 2 , further comprising using an entry-expectation feature to receive the second question from the user and to present to the user the output including both the first question and the answer-evaluation value.

4 . The method of claim 1 , further comprising establishing a first answer-evaluation value associated with the first question, the first answer, and the first confidence score.

5 . The method of claim 4 , further comprising:
determining, in response to receiving the set of questions, a second confidence score for a second answer to a second question of the set of questions; storing, by the QA system in response to determining the second confidence score for the second answer to the second question of the set of questions meets at least the threshold confidence score, the second question and the second answer; establishing a second answer-evaluation value associated with the second question, the second answer, and the second confidence score; determining, in response to receiving a third question from a user, the third question is related to both the first question and the second question; determining, in response to determining the third question is related to both the first question and the second question, an output by using the first answer-evaluation value and the second answer-evaluation value, wherein the output includes both the first question and the second question.

6 . The method of claim 5 , further comprising presenting the first question to the user in response to the first answer-evaluation value exceeding the second answer-evaluation value.

7 . The method of claim 5 , further comprising presenting, in response to the first answer-evaluation value being substantially equivalent to the second answer-evaluation value, the second question to the user in response to the second confidence score exceeding the first confidence score.

8 . The method of claim 5 , further comprising presenting the first answer-evaluation value.

9 . The method of claim 1 , further comprising:
determining, using a natural language processing technique of the QA system, a current-user identifier for the user; and determining the current-user identifier matches a first past-user identifier.

10 . The method of claim 1 , further comprising:
determining the first answer to the first question of the set of questions; storing first data configured to be semantically-correlated to the first question and to the first answer; determining a first central idea for at least a portion of a second question of the set of questions; determining, utilizing the first central idea, that at least the portion of the second question is semantically-correlated to a first candidate portion of the first data; and selecting the first candidate portion.

11 . The method of claim 10 , further comprising:
determining, by the QA system analyzing the second question of the set of questions in response to receiving the second question, a second answer to the second question; and storing second data, the second data configured to be semantically-correlated to the second question of the set of questions and to the second answer to the second question.

12 . The method of claim 11 , further comprising:
determining, by analyzing at least a portion of a third question of the set of questions in response to receiving at least the portion of the third question of the set of questions, a second central idea for at least the portion of the third question of the set of questions; and determining, by the QA system utilizing the second central idea for at least the portion of the third question of the set of questions, that at least the portion of the third question of the set of questions is semantically-correlated to a second candidate portion of a group including both the first data and the second data; and selecting, by the QA system, the second candidate portion.

13 . The method of claim 10 , wherein selecting the first candidate portion includes using an entry-expectation feature that utilizes a disambiguated element derived from the first data.

14 . The method of claim 10 , wherein the first central idea for at least the portion of the second question of the set of questions includes a context-based characterization, determined using a natural language processing technique of the QA system, of the second question.

15 . The method of claim 10 , wherein first data includes a syntax characteristic of the first answer determined to have at least a threshold answer-evaluation value.

16 . The method of claim 10 , further comprising presenting, using an entry-expectation feature, the first candidate portion and at least one answer-evaluation value.

17 . The method of claim 10 , wherein storing the first data occurs in response to determining the first answer meets at least a threshold confidence score.

18 . The method of claim 1 , further comprising:
receiving a third question from the user; determining a third confidence score for a third answer to the third question; storing, by the QA system in response to determining the third confidence score meets at least the threshold confidence score, the third question and the third answer; receiving a fourth question from the user; determining the fourth question is related to the third question; and selecting, based on a group of answer-evaluation values for the set of questions, the output, wherein the output includes:
one of the first question and the second question, and
one of the third question and the fourth question.

Assignees

• IBM

Inventors

• Ahuja Salil
• Isensee Scott H
• Johnson Jr Robert C
• Lewis Scott M
• O'Keeffe William G
• Vardy Cale R

Classifications

• G09B7/00 Primary

  Electrically-operated teaching apparatus or devices working with questions and answers (mechanically operated G09B3/00; computing arrangements G06F) · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N5/048 Primary

  Fuzzy inferencing · CPC title