US 12,443,596 B2
Systems and methods for generating a contextually and conversationally correct response to a query
Gayle McElvain, Arlington, VA (US); Tonya Custis, Minneapolis, MN (US); Matthew A. Surprenant, St. Paul, MN (US); and Erik Lindberg, Minneapolis, MN (US)
Assigned to Thomson Reuters Enterprise Centre GmbH, Zug (CH)
Filed by Thomson Reuters Enterprise Centre GmbH, Zug (CH)
Filed on Aug. 16, 2021, as Appl. No. 17/403,858.
Application 17/403,858 is a continuation of application No. 16/402,100, filed on May 2, 2019, granted, now 11,106,664.
Claims priority of provisional application 62/666,281, filed on May 3, 2018.
Prior Publication US 2021/0382878 A1, Dec. 9, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/242 (2019.01); G06F 16/248 (2019.01); G06N 5/046 (2023.01)
CPC G06F 16/243 (2019.01) [G06F 16/248 (2019.01); G06N 5/046 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A method performed by a computing system, the method comprising:
analyzing, by a question/answer processor of the computing system, a linguistic and syntactic structure of a question in a query to determine at least a context of the question;
pre-processing, by the question/answer processor, the question prior to the analyzing, the pre-processing includes determining whether the question is of a type that can be answered by a headnote by at least one of:
performing a matching operation using a lookup table which defines static questions to be excluded; or
determining whether the question is a factoid-based question;
obtaining, by a query generator of the computing system, a plurality of candidate answers to the question based on a search query, wherein the question is paired with individual candidate answers of the plurality of candidate answers to form a plurality of question-answer pairs, wherein a candidate answer of the plurality of candidate answers is a headnote;
scoring, by a ranking model of a candidate ranker of the computing system, a question-answer pair of the plurality of question-answer pairs, wherein scoring the question-answer pair includes:
extracting at least one feature for the question-answer pair of the plurality of question-answer pairs, the at least one feature includes a verb tense of an answer portion of the question-answer pair;
feeding the extracted at least one feature for the question-answer pair into the ranking model, and a score for the question-answer pair represents a probability that the candidate answer of the question-answer pair is a correct answer to the question; and
providing, by an answer detector of the computing system, at least one of the plurality of candidate answers as an answer to the question based on the score of the at least one of the plurality of candidate answers.