Automated actions in a conferencing service
Disclosed are various approaches for performing automated actions in a conferencing service. Distractions can be detected and users can be muted. Breakout rooms can be suggested to attendees based upon the user's identity. Additionally, event summaries and recaps can be generated for users who are late-arriving or who depart and return to the event.
1. A method comprising:
identifying an event in at least one of a user calendar or a conferencing service, the event having a plurality of attendees;
identifying a primary language associated with the event based upon an identity of the attendees;
obtaining an audio component and a video component corresponding to the event;
analyzing the audio component and the video component to identify at least one of a visual distraction or an audio distraction, wherein the visual distraction or the audio distraction is associated with a beginning;
identifying an attendee of the event associated with the at least one of a visual distraction or an audio distraction by detecting a spoken language in a portion of the audio component that is spoken by the attendee during the event and obtained from the attendee that is different from the primary language associated with the event, wherein the portion of the audio component originates from a client associated with the attendee;
performing a remedial action with respect to the attendee in response to identifying the at least one of the visual distraction or the audio distraction;
detect an end of the visual distraction or the audio distraction; and
generate a summary of the event from the beginning and the end, the summary generated based upon spoken content and video content using a natural language processing (NLP) model applied to the spoken content from the beginning and the end of the visual distraction and the audio distraction.
2. The method of claim 1 , wherein the remedial action comprises at least one of: muting the attendee, adjusting a volume associated with the attendee, or generating a suggestion for the attendee to be placed into a breakout room within the conferencing service.
3. The method of claim 1 , wherein generating the suggestion for at least one breakout room is based upon an identity of the attendees, the suggestion communicated to the attendees using an attendee chat feature associated with the conferencing service.
4. The method of claim 3 , wherein the suggestion comprises a first breakout room for a first subset of attendees associated with a first user group and a second breakout room for a second subset of attendees associated with a second user group.
5. The method of claim 1 , further comprising detecting a conclusion of the event and generating a text summary of the event based upon a natural language processing process performed on the audio component, wherein the summary of the event is provided to attendees of the meeting through a conferencing service client.
6. A system, comprising:
a computing device comprising at least one processor and at least one memory; and
machine-readable instructions stored in the at least one memory, wherein the instructions, when executed by the at least one processor, cause the computing device to at least:
identify an event in at least one of a user calendar or a conferencing service, the event having a plurality of attendees;
identify a primary language associated with the event based upon an identity of the attendees;
obtain an audio component and a video component corresponding to the event;
analyze the audio component and the video component to identify at least one of a visual distraction or an audio distraction, wherein the visual distraction or the audio distraction is associated with a beginning;
identify an attendee of the event associated with the at least one of a visual distraction or an audio distraction by detecting a spoken language in a portion of the audio component that is spoken by the attendee during the event and obtained from the attendee that is different from the primary language associated with the event, wherein the portion of the audio component originates from a client associated with the attendee;
perform a remedial action with respect to the attendee in response to identifying the at least one of the visual distraction or the audio distraction;
detect an end of the visual distraction or the audio distraction; and
generate a summary of the event from the beginning and the end, the summary generated based upon spoken content and video content using a natural language processing (NLP) model applied to the spoken content from the beginning and the end of the visual distraction and the audio distraction.
7. The system of claim 6 , wherein the remedial action comprises at least one of: muting the attendee, adjusting a volume associated with the attendee, or generating a suggestion for the attendee to be placed into a breakout room within the conferencing service.
8. The system of claim 6 , wherein the machine-readable instructions generate a suggestion for at least one breakout room based upon an identity of the attendees, the suggestion communicated to the attendees using an attendee chat feature associated with the conferencing service.
9. The system of claim 8 , wherein the suggestion comprises a first breakout room for a first subset of attendees associated with a first user group and a second breakout room for a second subset of attendees associated with a second user group.
10. The system of claim 6 , wherein the machine readable instructions further cause the at least one computing device to at least detect entry into the event by an attendee after commencement of the event and generate a summary of a previous time period associated with the event.
11. The system of claim 6 , wherein the machine readable instructions further cause the at least one computing device to at least detect a conclusion of the event and generate a text summary of the event based upon a natural language processing process performed on the audio component, wherein the summary of the event is provided to attendees of the meeting through a conferencing service client.
12. A non-transitory computer-readable medium comprising machine-readable instructions, wherein the instructions, when executed by at least one processor, cause a computing device to at least:
identify an event in at least one of a user calendar or a conferencing service, the event having a plurality of attendees;
identify a primary language associated with the event based upon an identity of the attendees;
obtain an audio component and a video component corresponding to the event;
analyze the audio component and the video component to identify at least one of a visual distraction or an audio distraction, wherein the visual distraction or the audio distraction is associated with a beginning;
identify an attendee of the event associated with the at least one of a visual distraction or an audio distraction by detecting a spoken language in a portion of the audio component that is spoken by the attendee during the event and obtained from the attendee that is different from the primary language associated with the event, wherein the portion of the audio component originates from a client associated with the attendee;
perform a remedial action with respect to the attendee in response to identifying the at least one of the visual distraction or the audio distraction;
detect an end of the visual distraction or the audio distraction; and
generate a summary of the event from the beginning and the end, the summary generated based upon spoken content and video content using a natural language processing (NLP) model applied to the spoken content from the beginning and the end of the visual distraction and the audio distraction.
13. The non-transitory computer-readable medium of claim 12 , wherein the remedial action comprises at least one of: muting the attendee, adjusting a volume associated with the attendee, or generating a suggestion for the attendee to be placed into a breakout room within the conferencing service.
14. The non-transitory computer-readable medium of claim 12 , wherein the machine-readable instructions generate a suggestion for at least one breakout room based upon an identity of the attendees, the suggestion communicated to the attendees using an attendee chat feature associated with the conferencing service.
15. The non-transitory computer-readable medium of claim 14 , wherein the suggestion comprises a first breakout room for a first subset of attendees associated with a first user group and a second breakout room for a second subset of attendees associated with a second user group.
16. The non-transitory computer-readable medium of claim 12 , wherein the instructions detect entry into the event by an attendee after commencement of the event and generate a summary of a previous time period associated with the event.
17. The non-transitory computer-readable medium of claim 12 , wherein the instructions further cause the at least one computing device to at least detect a conclusion of the event and generate a text summary of the event based upon a natural language processing process performed on the audio component, wherein the summary of the event is provided to attendees of the meeting through a conferencing service client.