Patent · US Active

Determining a category of a request by word vector representation of a natural language text string with a similarity value

US11972490B2 · kind B2 · utility

0Cited by
5References
15Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 19, 2019
Grant dateApr 30, 2024
Priority date
Expiry dateApr 22, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V30/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The current invention relates to a computer-implemented method for determining a category of a request provided by a user by means of a user device; said user device comprising connection means and means for receiving a request description relating to said request from said user; the method comprising a plurality of steps among which: receiving, from said user, said request description, by means of said device; uploading said request description to a server, said server having access to a database comprising a plurality of previously categorized requests each comprising a category and a vocabulary comprising a plurality of word vector representations; identifying, by said server, a plurality of component words belonging to a natural language text string comprised in said request description; obtaining, for at least one of said plurality of component words, an associated word vector representation from said vocabulary; and determining a request vector, based on said at least one obtained word vector representation.

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