US 12,438,983 B2
Communication session interruption and dynamic learning system
Nipun Mahajan, Lawrenceville, NJ (US); Amit Mishra, Chennai (IN); Yogesh Raghuvanshi, Pennington, NJ (US); S. B. Pravin Kumar, Nagercoil (IN); Balaji Sugumar, Chennai (IN); Yaksh Kumar Singh, Uttar Pradesh (IN); Sushil Golani, Charlotte, NC (US); and Stephanie Ann Hammond, Newark, DE (US)
Assigned to Bank of America Corporation, Charlotte, NC (US)
Filed by Bank of America Corporation, Charlotte, NC (US)
Filed on Nov. 8, 2023, as Appl. No. 18/387,981.
Prior Publication US 2025/0150535 A1, May 8, 2025
Int. Cl. H04M 3/00 (2024.01); G10L 15/16 (2006.01); G10L 15/18 (2013.01); H04M 3/523 (2006.01)
CPC H04M 3/5233 (2013.01) [G10L 15/16 (2013.01); G10L 15/1822 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing platform, comprising:
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
a memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
receive, from a plurality of communication sessions each communication session of the plurality of communication sessions being between a first computing device associated with an agent and a second computing device associated with a user, audio data associated with each communication session of the plurality of communication sessions;
identify, from the audio data associated with each communication session of the plurality of communication sessions, a topic and a sub-topic of each communication session of the plurality of communication sessions;
extract, from the audio data associated with each communication session of the plurality of communication sessions, metadata associated with each communication session of the plurality of communication sessions;
receive, from a plurality of different communication channels, feedback data associated with the plurality of communication sessions;
execute a dynamic learning machine learning model, wherein executing the dynamic learning machine learning model includes inputting, to the dynamic learning machine learning model, the identified topic and sub topic of each communication session, the extracted metadata from each communication session, and the feedback data to output one or more topics or sub-topics of concern;
monitor a plurality of ongoing communication sessions to identify an ongoing communication session related to one of: a topic or a sub-topic of concern;
identify, based on an agent mapping graph, a first plurality of agents who are not subject matter experts in the identified topic or sub-topic of concern;
identify, from the first plurality of agents, a second plurality of agents who have an available status; and
join, to the identified ongoing communication session related to one of:
the topic or sub-topic of concern, computing devices of the second plurality of agents in a dynamic learning session.