Patent · US Active

Identifying trends associated with topics from natural language text

US10157223B2 · kind B2 · utility

1Cited by
4References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 2, 2016
Grant dateDec 18, 2018
Priority date
Expiry dateFeb 17, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F16/3344
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A device may obtain text to be processed to identify a trend associated with a topic included in the text. The text may include a plurality of text sections, associated with the topic, that may be associated with a plurality of temporal intervals. The device may determine a respective context for the topic in each of the plurality of text sections. The device may calculate a first specificity score based on the respective context for the topic for one or more text sections associated with the first temporal interval. The device may calculate a second specificity score based on the respective context for the topic for one or more text sections associated with the second temporal interval. The device may identify a trend associated with the topic based on the first specificity score and the second specificity score, and may provide information that identifies the trend.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.