Weighting search criteria based on similarities to an ingested corpus in a question and answer (QA) system

Patent metadata

Field	Value
Publication number	US-9715531-B2
Application number	US-201615042744-A
Country	US
Kind code	B2
Filing date	Feb 12, 2016
Priority date	Jun 10, 2014
Publication date	Jul 25, 2017
Grant date	Jul 25, 2017

Abstract

A mechanism is provided, in a data processing system comprising a processor and a memory configured to implement a question and answer (QA) system, for weighting search criteria based on similarities to an ingested corpus in the QA system. A set of question characteristics found in a received input question are compared to a set of data characteristics respectively describing data in each corpus of a corpora. For each question characteristic in the set of found question characteristics, a first weight is assigned to the corpus within which data associated with the data characteristic resides in response to the question characteristic being more related to a data characteristic; otherwise a second weight is assigned, where the first weight is greater than the second weight. A selective search is then performed for an answer to the received input question in one or more corpora with a higher weighting.

First claim

What is claimed is:

1. A method, in a data processing system comprising a processor and a memory configured to implement a question and answer (QA) system, for weighting search criteria based on similarities to an ingested corpus in the QA system, the method comprising:
parsing a received input question having a set of question characteristics;
comparing the set of question characteristics found in the received input question to a set of data characteristics respectively describing data in each corpus of a corpora;
for each question characteristic in the set of found question characteristics:
responsive to the question characteristic being more related to a data characteristic in the set of data characteristics, assigning a first weight to the corpus within which data associated with the data characteristic resides; and
responsive to the question characteristic being less related to the data characteristic in the set of data characteristics, assigning a second weight to the corpus within which the data associated with the data characteristic resides, wherein the first weight is greater than the second weight; and

selectively searching for an answer to the received input question in one or more corpora with a higher weighting preferentially to one or more corpora with a lower weighting.

2. The method of claim 1 , wherein the first weight and the second weight are based on a set of predetermined weighting characteristics.

3. The method of claim 1 , wherein the first weight and the second weight are defined by a user.

4. The method of claim 1 , wherein the set of data characteristics are identified by the method comprising:
analyzing each data for a set of data characteristics; and
storing the set of data characteristics in a characteristics data structure as being associated with a corpus where the data is ingested.

5. The method of claim 4 , wherein the set of data characteristics is one or more of an average sentence length, various counts of sentence sub-structure, phrase boundaries, average word length, number of characters in a sentence, number of words in a passage, number of sentences in a passage, or average sentence lexical composition.

6. The method of claim 1 , wherein the set of question characteristics is one or more of an average sentence length, various counts of sentence sub-structure, phrase boundaries, average word length, number of characters in a sentence, number of words in a passage, number of sentences in a passage, or average sentence lexical composition.

7. The method of claim 1 , wherein the data comprises one or more of media, blogs, personal experiences, books, journal and magazine articles, expert opinions, encyclopedias, or web pages.

Assignees

• IBM

Inventors

• Jamrog Daniel M
• Lavoie Jason D
• Orrick Nicholas W
• Witherspoon Kristin A

Classifications

• G06F16/24578 Primary

  using ranking · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F17/30864

  Physics · mapped topic

• G06F17/3053 Primary

  Physics · mapped topic