US 12,255,749 B2
Meeting insights with large language models
Shawn Cantin Callegari, Bellevue, WA (US); Umesh Madan, Bellevue, WA (US); Samuel Edward Schillace, Portola Valley, CA (US); Abby Harrison, Woodinville, WA (US); Gina Elizabeth Triolo, Redmond, WA (US); Mark Karle, Seattle, WA (US); LeRoy F. Miller, Tacoma, WA (US); Devis Lucato, Kirkland, WA (US); Tara Eve Walker, Atlanta, GA (US); Brian Krabach, Snohomish, WA (US); Adrian Wyatt Bonar, Seattle, WA (US); Alexander Chao, Irvine, CA (US); and Nicholas Becker, Boulder, CO (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Mar. 31, 2023, as Appl. No. 18/129,758.
Claims priority of provisional application 63/440,590, filed on Jan. 23, 2023.
Claims priority of provisional application 63/433,619, filed on Dec. 19, 2022.
Claims priority of provisional application 63/433,627, filed on Dec. 19, 2022.
Prior Publication US 2024/0205037 A1, Jun. 20, 2024
Int. Cl. H04L 12/18 (2006.01)
CPC H04L 12/1822 (2013.01) [H04L 12/1831 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for facilitating a collaborative meeting, the method comprising:
monitoring activities of participants of the collaborative meeting;
extracting insights from meeting contents shared by the participants, wherein the insights are extracted using a generative machine learning model;
selecting data from the insights that is deemed important based on engagement and interests of the participants;
generating a structured summary log based on the selected data from the insights associated with the collaborative meeting, wherein the structured summary log is generated using the generative machine learning model;
presenting the structured summary log in a collaborative canvas accessible by the participants during the collaborative meeting; and
generating one or more customized meeting summaries for one or more participants after the collaborative meeting, wherein the one or more customized meeting summaries are generated using the generative machine learning model.