Automated actions based upon event content in a conferencing service
Disclosed are various approaches for detecting whether an event in a conferencing service is advanced or delayed relative to an agenda providing by the conferencing service or an event organizer. A speech-to-text conversion of the audio component can be performed and compared against the agenda. Segments of interest can be identified and users notified if the event is advanced or delayed.
1 . 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 of a user or a conferencing service, the event having a plurality of attendees;
generate a bot instance configured to join the event as a participant on behalf of the user by accessing one or more application programming interfaces (APIs) of the conferencing service, wherein the bot instance records an audio component and a video component of the event;
identify an agenda associated with the event based upon the user calendar;
determine a plurality of time segments and a plurality of keywords associated with the event based upon an analysis of the agenda;
identify a segment of interest associated with the user within the event based upon the analysis of the agenda;
obtain the audio component and the video component corresponding to the event recorded by the bot instance and generate a speech-to-text conversion of the audio component;
generate one or more tags utilizing Named Entity Recognition based upon the speech-to-text conversion;
associate a current time in the event with the agenda based upon the speech-to-text conversion of the audio component and the one or more tags;
determine that the segment of interest within the event is advanced or delayed based upon the association of the current time in the event with the agenda; and
generate a notification for the user associated with the segment of interest based upon the determination that the segment of interest within the event is advanced or delayed.
2 . The system of claim 1 , wherein the notification comprises an invitation to join the event in the conferencing service when the segment of interest is occurring.
3 . The system of claim 1 , wherein the user indicates the segment of interest in a user interface element when adding the event to the user calendar.
4 . The system of claim 1 , wherein the user indicates the segment of interest by selecting one or more keywords from the agenda.
5 . The system of claim 1 , wherein the machine-readable instructions further cause the at least one computing device to perform a syntactical match between the one or more tags generated and at least one of the plurality of attendees.
6 . 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 of a user or a conferencing service, the event having a plurality of attendees;
generate a bot instance configured to join the event as a participant on behalf of the user by accessing one or more application programming interfaces (APIs) of the conferencing service, wherein the bot instance records an audio component and a video component of the event;
identify an agenda associated with the event based upon the user calendar;
determine a plurality of time segments and a plurality of keywords associated with the event based upon an analysis of the agenda;
identify a segment of interest associated with the user within the event based upon the analysis of the agenda;
obtain the audio component and the video component corresponding to the event recorded by the bot instance and generate a speech-to-text conversion of the audio component;
generate one or more tags utilizing Named Entity Recognition based upon the speech-to-text conversion;
associate a current time in the event with the agenda based upon a speech-to-text conversion of the audio component and the one or more tags;
determine that the segment of interest within the event is advanced or delayed based upon the association of the current time in the event with the agenda; and
generate a notification for the user associated with the segment of interest based upon the determination that the segment of interest within the event is advanced or delayed.
7 . The non-transitory computer-readable medium of claim 6 , wherein the notification comprises an invitation to join the event in the conferencing service when the segment of interest is occurring.
8 . The non-transitory computer-readable medium of claim 6 , wherein the user indicates the segment of interest in a user interface element when adding the event to the user calendar.
9 . The non-transitory computer-readable medium of claim 6 , wherein the user indicates the segment of interest by selecting one or more keywords from the agenda.
10 . The non-transitory computer-readable medium of claim 6 , wherein the machine-readable instructions further cause the at least one computing device to perform a syntactical match between the one or more tags generated and at least one of the plurality of attendees.
11 . A method comprising:
identifying an event in at least one of a user calendar of a user or a conferencing service, the event having a plurality of attendees;
generating a bot instance configured to join the event as a participant on behalf of the user by accessing one or more application programming interfaces (APIs) of the conferencing service, wherein the bot instance records an audio component and a video component of the event;
identifying an agenda associated with the event based upon the user calendar;
determining a plurality of time segments and a plurality of keywords associated with the event based upon an analysis of the agenda;
identifying a segment of interest associated with the user within the event based upon the analysis of the agenda;
obtaining the audio component and the video component corresponding to the event recorded by the bot instance and generating a speech-to-text conversion of the audio component;
associating a current time in the event with the agenda based upon a speech-to-text conversion of the audio component and the one or more tags;
determining that the segment of interest within the event is advanced or delayed based upon the association of the current time in the event with the agenda; and
generating a notification for the user associated with the segment of interest based upon the determination that the segment of interest within the event is advanced or delayed.
12 . The method of claim 11 , wherein the notification comprises an invitation to join the event in the conferencing service when the segment of interest is occurring.
13 . The method of claim 11 , wherein the user indicates the segment of interest in a user interface element when adding the event to the user calendar.
14 . The method of claim 11 , wherein the user indicates the segment of interest by selecting one or more keywords from the agenda.