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:
Nov. 07, 2023

Filed:

Mar. 06, 2020
Applicant:

Microsoft Technology Licensing, Llc, Redmond, WA (US);

Inventors:

Adi Miller, Herzilya, IL;

Shira Weinberg, Herzliya, IL;

Haim Somech, Herzliya, IL;

Hen Fitoussi, Ramat HaSharon, IL;

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 25/00 (2013.01); G10L 21/00 (2013.01); G06F 40/35 (2020.01); G06Q 10/06 (2023.01); G06Q 50/00 (2012.01); G06Q 10/04 (2023.01); G10L 15/183 (2013.01); G10L 15/22 (2006.01); G10L 15/26 (2006.01); G10L 15/00 (2013.01);
U.S. Cl.
CPC ...
G06F 40/35 (2020.01); G06Q 10/04 (2013.01); G06Q 10/06 (2013.01); G06Q 50/01 (2013.01); G10L 15/183 (2013.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01); G06F 2203/0381 (2013.01); G10L 15/00 (2013.01);
Abstract

Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.


Find Patent Forward Citations

Loading…