Controlling conference calls

Patent metadata

Field	Value
Publication number	US-9420108-B1
Application number	US-201514966491-A
Country	US
Kind code	B1
Filing date	Dec 11, 2015
Priority date	Aug 11, 2015
Publication date	Aug 16, 2016
Grant date	Aug 16, 2016

Abstract

Embodiments of the present invention provide a method and system for determining participants for a conference call where the participants may be selected based on similar attributes as well as the descriptions of the conference call. Additionally, the conference call may be split into smaller breakout sessions, further separating the participants based on various attributes. Further, the conference call participants may be shuffled thereby creating different breakout sessions with different participants with like attributes. The conference call including the selected participants is initiated.

First claim

What is claimed is:

1. A computer implemented method comprising:
determining, by one or more processors residing in a computing device configured to perform one or more user interface operations to communicate during a conference call, a set of participants for a conference call, from a set of potential participants, wherein determining the set of participants comprises:
identifying, by one or more processors, a first set of common attributes between the set of potential participants using data retrieved from each potential participant, wherein the first set of common attributes is based, in part, on: a historical interest in the conference call topic, a hierarchical relationship between the set of potential participants, a job based relationship between the set of potential participants, an age based relationship between the set of potential participants, geographic location based relationship between the set of potential participants, technological connections between the set of potential participants, commonalities shared by the set of potential participants, and a prior analysis of the set of potential participants;
analyzing a topic of the conference call using a natural language processor, wherein a rule is established, specifying a relationship between each potential participant, from the set of potential participants and a received topic of the conference call;
applying, by one or more processors, a set of stored patterns to each potential participant, from the set of potential participants, wherein the set of stored patterns are based on historical data associated with behavioral patterns of participants of previous conference calls; and
responsive to identifying the first set of common attributes between the set of potential participants and applying the set of stored patterns to each potential participant, matching, by one or more processors, the set of potential participants, with the established rule in relation to the received topic of the conference call;

receiving, by one or more processors, a first indication for a breakout session, wherein the breakout session splits the conference call into separate sub-conference calls, wherein the first indication is based on a predetermined time interval;
responsive to receiving the first indication for the breakout session, selecting, by one or more processors, a subset of participants, from the set of participants, for each of the separate sub-conference calls, wherein selecting the subset of participants for each separate sub-conference call, comprises:
determining, by one or more processors, the subset of participants to be included in each sub-conference call, based, in part on,
a second set of common attributes, wherein the second set of common attributes are based on the geographic location of each participant from the set of participants, and
a plurality of spoken words of each participant, wherein the plurality of spoken words relate to a topic of the separate sub-conference calls;

receiving, by one or more processors, a second indication for a for a second breakout session wherein the second breakout session splits the conference call into at least two new subsets of the conference calls;
responsive to receiving the second indication, determining, by one or more processors, at least two new subsets of participants associated with the at least two new subs subsets of the conference call, wherein each of the at least two new subsets of participants are based in part on a third set of common attributes;
receiving, by one or more processors, an indication to merge the separate sub-conference calls into a single conference call; and
responsive to receiving the indication to merge the separate sub-conference calls into a single conference call, combining, by one or more processors, the separate sub-conference calls into a single conference call.

Assignees

• IBM

Inventors

• Bostick James E
• Cunico Hernan A
• Ganci Jr John M
• Rakshit Sarbajit K

Classifications

• H04M3/568

  audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants (echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30) · CPC title

• H04L65/1093

  by adding participants; by removing participants · CPC title

• H04L65/403

  Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title

• H04M3/564 Primary

  whereby the feature is a sub-conference · CPC title

• H04M3/4936

  Speech interaction details (speech recognition per se G10L15/00) · CPC title