×

Detecting and executing data re-ingestion to improve accuracy in a NLP system

  • US 9,245,009 B2
  • Filed: 03/14/2013
  • Issued: 01/26/2016
  • Est. Priority Date: 03/12/2013
  • Status: Active Grant
First Claim
Patent Images

1. A method comprising:

  • receiving first and second queries for processing by a natural language processing (NLP) system;

    identifying first and second data sources related to the first and second queries, respectively, by associating one or more elements of the first and second queries to the first and second data sources;

    upon determining that the first related data source is not in a corpus of the NLP system, ingesting the first related data source into the corpus, wherein the corpus includes a data store comprising information from one or more data sources formatted and stored into one or more objects; and

    upon determining that the second related data source is in the corpus of the NLP system;

    before searching the second data source for at least one answer to the second query, determining a time-sensitivity value associated with the second query indicating a degree to which an accurate answer to the second query is dependent on a staleness of the second related data source, andupon determining that the time-sensitivity value satisfies a staleness threshold, re-ingesting the second related data source into the corpus.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×