The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Mar. 19, 2024

Filed:

Nov. 01, 2021
Applicant:

Sri International, Menlo Park, CA (US);

Inventors:

Ajay Divakaran, Monmouth Junction, NJ (US);

Karan Sikka, Lawrenceville, NJ (US);

Yi Yao, Princeton, NJ (US);

Yunye Gong, West Windsor, NJ (US);

Stephanie Nunn, Hopkins, MN (US);

Pritish Sahu, Piscataway, NJ (US);

Michael A. Cogswell, West Windsor, NJ (US);

Jesse Hostetler, Boulder, CO (US);

Sara Rutherford-Quach, San Carlos, CA (US);

Assignee:

SRI International, Menlo Park, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 40/35 (2020.01); G06F 16/33 (2019.01); G06N 5/04 (2023.01);
U.S. Cl.
CPC ...
G06F 40/35 (2020.01); G06F 16/3335 (2019.01); G06N 5/04 (2013.01);
Abstract

A method, apparatus and system for training an embedding space for content comprehension and response includes, for each layer of a hierarchical taxonomy having at least two layers including respective words resulting in layers of varying complexity, determining a set of words associated with a layer of the hierarchical taxonomy, determining a question answer pair based on a question generated using at least one word of the set of words and at least one content domain, determining a vector representation for the generated question and for content related to the at least one content domain of the question answer pair, and embedding the question vector representation and the content vector representations into a common embedding space where vector representations that are related, are closer in the embedding space than unrelated embedded vector representations. Requests for content can then be fulfilled using the trained, common embedding space.


Find Patent Forward Citations

Loading…