Methods and systems for session management in digital telepresence systems using machine learning

1. A computer-implemented method for guiding one or more interactions conducted via a telepresence system implemented using a computer system, comprising:

receiving information at the computer system, wherein

the information comprises

participant information for each participant of a plurality of participants in a telepresence event conducted using the telepresence system;

determining one or more participant attributes of each participant of the plurality of participants from the participant information;

determining an affinity metric value for the each participant of the plurality of participants, using the one or more participant attributes of the each participant of the plurality of participants;

generating a participant behavioral model, wherein

the participant behavioral model is generated based, at least in part, on participant behavioral information for one or more of the each participant of the plurality of participants;

assigning at least one participant of the plurality of participants to each of one or more subgroups, wherein

the at least one participant is assigned to the each of the one or more subgroups based, at least in part, on

the affinity metric values as between the at least one of the plurality of participants and another participant of the plurality of participants, and

engagement score information,

the affinity metric is a measure of affinity between ones of the plurality of participants, and

the affinity metric is based, at least in part, on the affinity metric values;

guiding participation of the each participant of the plurality of participants by controlling one or more components of the telepresence system, based, at least in part, on the assigning;

generating updated engagement score information for the one or more of the each participant of the plurality of participants, wherein

the updated engagement score information is based, at least in part, on the engagement score information; and

updating the participant behavioral model, wherein

the participant behavioral model is updated based, at least in part, on the updated engagement score information.

2. The computer-implemented method of claim 1 , further comprising:

generating engagement score information for the at least one participant; and

non-volitionally reassigning the at least one participant from a first one of the each of the one or more subgroups to a second one of the each of the one or more subgroups based, at least in part, on the engagement score information.

3. The computer-implemented method of claim 1 , wherein the assigning comprises:

performing a thresholding operation for a first affinity metric value between a first participant of the plurality of participants and a second participant of the plurality of participants.

4. The computer-implemented method of claim 1 , further comprising:

generating engagement score information for the at least one participant, wherein

the at least one participant is also assigned to one of the each of the one or more subgroups based, at least in part, on the engagement score information.

5. The computer-implemented method of claim 4 , wherein

the engagement score information based, at least in part, on a participant behavioral model, and

the telepresence event is a conference held in a virtual reality environment.

6. The computer-implemented method of claim 5 , further comprising:

generating the participant behavioral model, wherein

the participant behavioral model is generated based, at least in part, on participant behavioral information for one or more of the each participant of the plurality of participants.

7. The computer-implemented method of claim 6 , wherein

the information further comprises organizer information for an organizer of the telepresence event, and

the participant behavioral model is generated further based, at least in part, on the participant information for the one or more of the each participant of the plurality of participants and the organizer information.

8. The computer-implemented method of claim 1 , further comprising:

determining whether an affected participant is no longer a member of a subgroup; and

in response to a determination that the affected participant is no longer a member of the subgroup,

assigning the affected participant to another subgroup of the one or more subgroups.

9. The computer-implemented method of claim 8 , further comprising:

determining whether the another subgroup exists; and

in response to a determination that the another subgroup does not exist, generating the another subgroup.

10. The computer-implemented method of claim 1 , wherein

the affinity metric comprises at least one of

at least two participants knowing one another other,

the at least two participants not knowing one another other,

the at least two participants wanting to meet,

the at least two participants not wanting to meet,

the at least two participants being in compatible industries,

the at least two participants being from a certain geographical area, or

the at least two participants working for compatible employers.

11. The computer-implemented method of claim 1 , further comprising:

determining whether a session of a subgroup has ended; and

in response to a determination that the session having ended,

assigning each of participants that were members of the subgroup, to one or more other subgroups of the one or more subgroups.

12. The computer-implemented method of claim 11 , further comprising:

determining whether the one or more other subgroups of the one or more subgroups do not exist; and

in response to a determination that one or more of the one or more other subgroups do not exist,

generating the one or more of the one or more other subgroups.

13. The computer-implemented method of claim 1 , further comprising:

generating engagement score information for the at least one participant, wherein

the at least one participant is also assigned to one of the each of the one or more subgroups based, at least in part, on the engagement score information, and

the engagement score information based, at least in part, on a participant behavioral model; and

generating the participant behavioral model, wherein

the participant behavioral model is generated based, at least in part, on participant behavioral information for one or more of the each participant of the plurality of participants,

the participant behavioral information comprises at least one of

analyzed audio information,

analyzed video information, or

analyzed human interface device information.

14. The computer-implemented method of claim 13 , wherein

the telepresence event is at least one of

a telepresence technical conference,

a telepresence social event,

a telepresence professional seminar,

a telepresence recreational event, or

telepresence education,

the analyzed audio information is generated by performing at least one of

speech analysis,

pitch analysis,

volume analysis, or

Mel-Frequency Cepstrum analysis,

the analyzed video information is generated by performing at least one of

silhouette analysis,

lean analysis,

head pitch analysis,

head yaw analysis,

facial expression analysis, or

gestural analysis, and

the analyzed human interface device information is generated by performing at least one of

analysis of use of a mouse or other pointing device,

analysis of use of a keyboard,

analysis of use of a touchscreen, or

analysis of use of a user interface.

15. A non-transitory computer-readable storage medium, comprising program instructions, which, when executed by one or more processors of a computing system, perform a method for guiding one or more interactions conducted via a telepresence system comprising:

receiving information at the computer system, wherein

the information comprises

participant information for each participant of a plurality of participants in a telepresence event conducted using the telepresence system;

determining one or more participant attributes of each participant of the plurality of participants from the participant information;

determining an affinity metric value for the each participant of the plurality of participants, using the one or more participant attributes of the each participant of the plurality of participants;

generating a participant behavioral model, wherein

the participant behavioral model is generated based, at least in part, on participant behavioral information for one or more of the each participant of the plurality of participants;

assigning at least one participant of the plurality of participants to each of one or more subgroups, wherein

the at least one participant is assigned to the each of the one or more subgroups based, at least in part, on

the affinity metric values as between the at least one of the plurality of participants and another participant of the plurality of participants, and

engagement score information,

the affinity metric is a measure of affinity between ones of the plurality of participants, and

the affinity metric is based, at least in part, on the affinity metric values; and

guiding participation of the each participant of the plurality of participants by controlling one or more components of the telepresence system, based, at least in part, on the assigning;

generating updated engagement score information for the one or more of the each participant of the plurality of participants, wherein

the updated engagement score information is based, at least in part, on the engagement score information; and

updating the participant behavioral model, wherein

the participant behavioral model is updated based, at least in part, on the updated engagement score information.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the method further comprises:

generating engagement score information for the at least one participant, wherein

the at least one participant is also assigned to one of the each of the one or more subgroups based, at least in part, on the engagement score information.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the method further comprises:

determining whether an affected participant is no longer a member of a subgroup; and

in response to a determination that the affected participant is no longer a member of the subgroup,

assigning the affected participant to another subgroup of the one or more subgroups.

18. A computing system comprising:

one or more processors; and

a computer-readable storage medium coupled to the one or more processors, comprising program instructions, which, when executed by the one or more processors, perform a method for guiding one or more interactions conducted via a telepresence system comprising

receiving information at the computer system, wherein

the information comprises

participant information for each participant of a plurality of participants in a telepresence event conducted using the telepresence system,

determining one or more participant attributes of each participant of the plurality of participants from the participant information,

determining an affinity metric value for the each participant of the plurality of participants, using the one or more participant attributes of the each participant of the plurality of participants,

generating a participant behavioral model, wherein

the participant behavioral model is generated based, at least in part, on participant behavioral information for one or more of the each participant of the plurality of participants,

assigning at least one participant of the plurality of participants to each of one or more subgroups, wherein

the at least one participant is assigned to the each of the one or more subgroups based, at least in part, on

the affinity metric values as between the at least one of the plurality of participants and another participant of the plurality of participants, and

engagement score information,

the affinity metric is a measure of affinity between ones of the plurality of participants, and

the affinity metric is based, at least in part, on the affinity metric values, and

guiding participation of the each participant of the plurality of participants by controlling one or more components of the telepresence system, based, at least in part, on the assigning,

generating updated engagement score information for the one or more of the each participant of the plurality of participants, wherein

the updated engagement score information is based, at least in part, on the engagement score information, and

updating the participant behavioral model, wherein

the participant behavioral model is updated based, at least in part, on the updated engagement score information.