US 11,809,829 B2
Virtual assistant for generating personalized responses within a communication session
Adi Miller, Herzilya (IL); Shira Weinberg, Herzliya (IL); Haim Somech, Herzliya (IL); and Hen Fitoussi, Ramat HaSharon (IL)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed on Mar. 6, 2020, as Appl. No. 16/811,868.
Application 16/811,868 is a continuation of application No. 15/637,831, filed on Jun. 29, 2017, granted, now 10,585,991.
Prior Publication US 2020/0394366 A1, Dec. 17, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. 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)
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)] 20 Claims
OG exemplary drawing
 
1. A computerized system comprising:
one or more processors; and
computer storage memory having computer-executable instructions stored thereon which, when executed by the one or more processors, implement a method comprising:
receiving content that is exchanged within a communication session (CS), wherein the content includes one or more natural language expressions that encode a portion of a conversation carried out by a plurality of users participating in the CS, wherein the content is associated with a relevance threshold for identifying one or more likely portions of the content and an additional relevance threshold for identifying a highly relevant portion of the one or more portions of the content;
determining a relevance of the content based on a content-relevance model for the first user;
identifying one or more likely-relevant portions of the content based on the relevance of the content, wherein the one or more identified likely-relevant portions of the content are likely-relevant to the first user;
identifying the highly relevant portion from a sub-portion of the one or more likely-relevant portions of the content based on both the relevance threshold and the additional relevance threshold, wherein the sub-portion is associated with the additional relevance threshold that is greater than the relevance threshold; and
generating a notification associated with the one or more identified likely-relevant portions of the content and the highly relevant portion of the content.