Back to results
US 11,909,784 B2Granted
Automated actions in a conferencing service
AssigneeVMware, Inc.
InventorsRohit Pradeep Shetty, Ravish Chawla, Adam Chow
Life of this patent
Estimating the term…
Abstract
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.
Claims17
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.
6 more elements
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.
9 more elements
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.
6 more elements
Dependencies are inferred from the claim text.