Audience engagement feedback systems and techniques

Patent metadata

Field	Value
Publication number	US-9843768-B1
Application number	US-201615274338-A
Country	US
Kind code	B1
Filing date	Sep 23, 2016
Priority date	Sep 23, 2016
Publication date	Dec 12, 2017
Grant date	Dec 12, 2017

Abstract

Embodiments of a system and method for indicating audience engagement are generally described herein. A method may include sending speech from a speaker to be played for a plurality of members of an audience, receiving audience reaction information, for the plurality of members of the audience, from a plurality of sensors, the audience reaction information captured by the plurality of sensors while the speech is playing for the plurality of members of the audience, processing the audience reaction information to aggregate the audience reaction information, determining, using the processed information, an engagement factor, and sending an aggregated engagement level indicator to a speaker device, the aggregated engagement level indicator based on the engagement factor and indicating overall engagement of the audience to the speech.

First claim

What is claimed is:

1. A system for indicating audience engagement, the system comprising:
a server, including processing circuitry and memory, the processing circuitry to:
send speech from a speaker to be played for a plurality of members of an audience;
receive audience reaction information, for the plurality of members of the audience, from a plurality of sensors, the audience reaction information captured by the plurality of sensors while the speech is playing for the plurality of members of the audience;
process the audience reaction information to aggregate the audience reaction information;
determine, using the processed information, an engagement factor;
send an aggregated engagement level indicator to a speaker device, the aggregated engagement level indicator based on the engagement factor and indicating overall engagement of the audience to the speech;
save the processed information and the speech to the memory; and
correlate audio tones or key words in the speech with emotional responses in the processed information, wherein to correlate includes using a time offset to account for a transmission delay.

2. The system of claim 1 , wherein the speech includes a video of the speaker.

3. The system of claim 1 , wherein the speaker is remote from the audience.

4. The system of claim 1 , wherein the plurality of sensors include a camera, the camera to capture physical responses of at least one of the plurality of members of the audience while the speech is playing.

5. The system of claim 4 , wherein the physical responses include at least one of a facial emotion, a body gesture, or a hand gesture.

6. The system of claim 1 , wherein the plurality of sensors include a wearable sensor, the wearable sensor to capture biometric data from at least one of the plurality of members of the audience while the speech is playing.

7. The system of claim 1 , wherein the audience reaction information is received from at least one of the plurality of members of the audience in response to the at least one of the plurality of members of the audience opting in to provide data.

8. The system of claim 1 , wherein to process the audience reaction information, the processing circuitry is to anonymize the audience reaction information.

9. The system of claim 1 , wherein to determine the engagement factor includes using data of the plurality of members of the audience, the data including at least one of location data, personal data, cultural data, familiarity data, time data, age data, or gender data.

10. The system of claim 1 , wherein to send the aggregated engagement level indicator, the processing circuitry is to send a plurality of aggregated engagement level indicators corresponding to the plurality of members.

11. The system of claim 1 , wherein the aggregated engagement level indicator is an emoticon.

12. The system of claim 1 , wherein the aggregated engagement level indicator is a 3D avatar.

13. The system of claim 1 , wherein the overall engagement of the audience to the speech is a weighted average of engagement of the plurality of members of the audience.

14. The system of claim 1 , wherein to send the aggregated engagement level indicator, the processing circuitry is to send a series of aggregated engagement level indicators in real time updates to the speaker device, the real time updates adjusted based on aggregated or individual received updated audience reaction information.

15. The system of claim 1 , wherein the processing circuitry is further to predict emotional reactions of a hypothetical audience to a second speech using the correlated audio tones or key words and previous reactions from past audiences stored in the memory.

16. The system of claim 15 , wherein the processing circuitry is further to suggest modifications to the second speech based on the predicted emotional reactions of the hypothetical audience.

17. The system of claim 1 , wherein the processing circuitry is further to send the aggregated engagement level indicator to a device of a member of the plurality of members of the audience.

18. A method for indicating audience engagement, the method comprising:
sending speech from a speaker to be played for a plurality of members of an audience;
receiving audience reaction information, for the plurality of members of the audience, from a plurality of sensors, the audience reaction information captured by the plurality of sensors while the speech is playing for the plurality of members of the audience;
processing the audience reaction information to aggregate the audience reaction information;
determining, using the processed information, an engagement factor;
sending an aggregated engagement level indicator to a speaker device, the aggregated engagement level indicator based on the engagement factor and indicating overall engagement of the audience to the speech;
saving the processed information and the speech to the memory; and
correlating audio tones or key words in the speech with emotional responses in the processed information, wherein correlating includes using a time offset to account for a transmission delay.

19. The method of claim 18 , wherein the speech includes a video of the speaker.

20. The method of claim 18 , wherein the speaker is remote from the audience.

21. The method of claim 18 , wherein the plurality of sensors include a camera, the camera capturing physical responses of at least one of the plurality of members of the audience while the speech is playing.

22. At least one non-transitory machine-readable medium including instructions for operation of a computing system, which when executed by a machine, cause the machine to:
send speech from a speaker to be played for a plurality of members of an audience;
receive audience reaction information, for the plurality of members of the audience, from a plurality of sensors, the audience reaction information captured by the plurality of sensors while the speech is playing for the plurality of members of the audience;
process the audience reaction information to aggregate the audience reaction information;
determine, using the processed information, an engagement factor;
send an aggregated engagement level indicator to a speaker device, the aggregated engagement level indicator based on the engagement factor and indicating overall engagement of the audience to the speech;
save the processed information and the speech to the memory; and
correlate audio tones or key words in the speech with emotional responses in the processed information, wherein to correlate includes using a time offset to account for a transmission delay.

23. The at least one machine-readable medium of claim 22 , wherein the plurality of sensors include a wearable sensor, the wearable sensor capturing biometric data from at least one of the plurality of members of the audience while the speech is playing.

24. The at least one machine-readable medium of claim 22 , wherein the audience reaction information is received from at least one of the plurality of members of the audience in response to the at least one of the plurality of members of the audience opting in to provide data in an individual or an aggregated form.

Assignees

• Intel Corp

Inventors

• Negi Ansuya
• Tatourian Igor
• Wouhaybi Rita H

Classifications

• G10L15/08

  Speech classification or search · CPC title

• G10L25/63

  for estimating an emotional state · 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

• H04H60/33

  Arrangements for monitoring the users' behaviour or opinions · CPC title

• G10L2015/088

  Word spotting · CPC title