US 12,271,869 B2
Multi-service business platform system having conversation intelligence systems and methods
Ian Leaman, Salt Lake City, UT (US); Kevin M. Walsh, Marion, MA (US); and Hector Urdiales, Dublin (IE)
Assigned to HubSpot, Inc., Cambridge, MA (US)
Filed by HubSpot, Inc., Cambridge, MA (US)
Filed on Mar. 11, 2022, as Appl. No. 17/654,544.
Claims priority of provisional application 63/160,446, filed on Mar. 12, 2021.
Prior Publication US 2022/0293107 A1, Sep. 15, 2022
Int. Cl. G10L 15/22 (2006.01); G06F 16/951 (2019.01); G06N 5/02 (2023.01); G06Q 10/0631 (2023.01); G06Q 10/0633 (2023.01); G06Q 20/02 (2012.01); G06Q 30/01 (2023.01); G06Q 30/0201 (2023.01); G06Q 30/0203 (2023.01); G06Q 30/0242 (2023.01); G06Q 30/0251 (2023.01); G06Q 30/0601 (2023.01); G10L 15/26 (2006.01)
CPC G06Q 20/02 (2013.01) [G06F 16/951 (2019.01); G06N 5/02 (2013.01); G06Q 10/06315 (2013.01); G06Q 10/0633 (2013.01); G06Q 30/01 (2013.01); G06Q 30/0201 (2013.01); G06Q 30/0203 (2013.01); G06Q 30/0246 (2013.01); G06Q 30/0255 (2013.01); G06Q 30/0271 (2013.01); G06Q 30/0643 (2013.01); G10L 15/26 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
processing a conversation recording to determine speaker identities and to generate a conversation record;
transcribing the conversation recording into a transcript based on the conversation record;
extracting features from the transcript based on data in the transcript and the conversation record, wherein the features are extracted using search indexing based on data in the transcript and the conversation record, wherein the features are extracted using a sentiment model reinforced by a machine learning module that parses transcripts to create training data pairs of features and labels for training and reinforcing the sentiment model; and
in response to the features extracted from the transcript indicating that an occurrence of an event occurred, generating an event notification specifying a type of the event that occurred;
presenting conversation information, including the event notification, in a graphical user interface based on the speaker identities, transcript, and the features.