US 11,928,611 B2
Conversational interchange optimization
Paul R. Bastide, Ashland, MA (US); Liam S. Harpur, Dublin (IE); Matthew E. Broomhall, Goffstown, NH (US); and Robert E. Loredo, North Miami Beach, FL (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Nov. 18, 2019, as Appl. No. 16/686,248.
Prior Publication US 2021/0150398 A1, May 20, 2021
Int. Cl. G06N 20/00 (2019.01); G06F 17/18 (2006.01); G06F 40/30 (2020.01); G06N 7/00 (2023.01); G06N 7/01 (2023.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01)
CPC G06N 7/01 (2023.01) [G06F 17/18 (2013.01); G06F 40/30 (2020.01); G06N 7/00 (2013.01); G06N 20/00 (2019.01); G10L 15/1815 (2013.01); G10L 15/22 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
monitoring, by one or more processors, a conversation in a communication system;
generating, by one or more processors, a list of topics in the conversation based on an identification of a plurality of predetermined topics and an expected conversation length of time for each topic of the predetermined topics from data provided by a scheduling system, wherein the expected conversation length of time for a respective topic is based on a mean and standard deviation of time of one or more prior conversations pertaining to the respective topic;
determining, by one or more processors, a flow for each topic based on the expected conversation length of time for the respective topic, number of participants, and sentiment associated to each topic, the flow being the progress of interactions and shifts for each topic;
building, by one or more processors, a statistical model for each topic based on the flow indicating predicted success of a topic progression for an ongoing conversation; and
updating, by one or more processors, the topic progression for the ongoing conversation based on the predicted success.