Automated lecture deconstruction

Patent metadata

Field	Value
Publication number	US-11797597-B2
Application number	US-202117498706-A
Country	US
Kind code	B2
Filing date	Oct 11, 2021
Priority date	Oct 27, 2014
Publication date	Oct 24, 2023
Grant date	Oct 24, 2023

Abstract

An online platform generates a playlist of clips of a lecture accessed by a plurality of users of the online platform. The online platform receives a recording of the lecture, and receives a plurality of events captured during a time period corresponding to the lecture. Each captured event is associated with a time stamp corresponding to a time at which a user performed an activity while listening to the lecture. The online platform clusters the captured events based on the time stamps, and generates one or more clips of the recording of the lecture from the clustered events. The online platform generates a playlist including the clips of the lecture.

First claim

What is claimed is:

1. A method for generating a playlist of clips of a lecture accessed by a plurality of users of an online platform, the method comprising:
at an online platform,
augmenting a recorded lecture with supplemental data to generate an augmented recorded lecture;
providing the augmented recorded lecture for playback at a plurality of user devices accessing the online platform;
receiving, from each user device from the plurality of user devices, a plurality of events captured at the respective user device, each event from the plurality of events occurring during a playback of the augmented recorded lecture at the respective user device and each event from the plurality of events for the respective user device being associated with a time stamp corresponding to a time at which a user of the respective user device performed an activity associated with the online platform;
clustering the plurality of events received from each user device from the plurality of user devices to generate a plurality of clusters of events;
generating a plurality of clips of the augmented recorded lecture based on the plurality of clusters of events, each clip from the plurality of clips including a portion of the augmented recorded lecture, each portion of the augmented recorded lecture having a beginning time and an ending time within the augmented recorded lecture identified based on the time stamps associated with the events from the plurality of events clustered in the plurality of clusters of events; and
generating a playlist including the plurality of clips of the augmented recorded lecture.

2. The method of claim 1 , wherein generating the plurality of clips includes:
ranking each cluster of events from the plurality of clusters of events based on a number of events in that cluster of events to generate a ranking;
selecting one or more clusters of events from the plurality of clusters of events based on the ranking; and
generating a clip of the augmented recorded lecture based on each cluster of events from the one or more selected clusters of events.

3. The method of claim 1 , wherein generating the plurality of clips of the augmented recorded lecture includes:
selecting the beginning time in the augmented recorded lecture for a clip from the plurality of clips based on a time stamp associated with an early event in a cluster of events from the plurality of clusters of events.

4. The method of claim 1 , wherein an activity associated with the online platform includes at least one of accessing a page of an electronic document distributed by the online platform, taking a note via the online platform, or answering a question on the online platform.

5. The method of claim 1 , wherein generating the plurality of clips of the augmented recorded lecture based on the plurality of clusters of events includes:
ranking each cluster of events from the plurality of clusters of events based on a number of events in that cluster of events to generate a ranking; and
selecting one or more highest-ranked clusters of events from the plurality of clusters of events based on the ranking, the generated plurality of clips based on the selected one or more highest-ranked clusters of events from the plurality of clusters of events.

6. The method of claim 1 , wherein generating the plurality of clips includes:
ranking each cluster of events from the plurality of clusters of events based on a percentage of a plurality of users accessing the augmented recorded lecture who performed an activity associated with the online platform associated with the events of that cluster of events to generate a ranking; and
selecting one or more highest-ranked clusters of events from the plurality of clusters of events based on the ranking, the generated plurality of clips based on the selected one or more highest-ranked clusters of events from the plurality of clusters of events.

7. The method of claim 1 , wherein clustering the plurality of events to generate the plurality of clusters of events includes clustering the plurality of events based at least in part on an activity type of the activity associated with the online platform that is associated with each event from the plurality of events, the activity type for each event from the plurality of events including one of a passive activity, an active activity, and a recall activity.

8. The method of claim 1 , wherein the supplemental data includes a secondary audio track.

9. The method of claim 1 , wherein the supplemental data includes a sub-title track.

10. The method of claim 1 , further comprising storing the augmented recorded lecture in association with an identifier of a course.

11. A non-transitory computer-readable storage medium storing executable computer program instructions for generating a playlist of clips of a lecture accessed by a plurality of users of an online platform, the computer program instructions when executed by a processor causing the processor to:
augment a recorded lecture with supplemental data to generate an augmented recorded lecture;
provide the augmented recorded lecture for playback at a plurality of user devices accessing the online platform;
receive, from each user device from the plurality of user devices, a plurality of events captured at the respective user device, each event from the plurality of events occurring during a playback of the augmented recorded lecture at the respective user device and each event from the plurality of events for the respective user device being associated with a time stamp corresponding to a time at which a user of the respective user device performed an activity associated with the online platform;
cluster the plurality of events received from each user device from the plurality of user devices to generate a plurality of clusters of events;
generate a plurality of clips of the augmented recorded lecture based on the plurality of clusters of events, each clip from the plurality of clips including a portion of the augmented recorded lecture, each portion of the augmented recorded lecture having a beginning time and an ending time within the augmented recorded lecture identified based on the time stamps associated with the events from the plurality of events clustered in the plurality of clusters of events; and
generate a playlist including the plurality of clips of the augmented recorded lecture.

12. The non-transitory computer-readable storage medium of claim 11 , wherein the computer program instructions to cause the processor to generate the plurality of clips include computer program instructions to cause the processor to:
rank each cluster of events from the plurality of clusters of events based on a number of events in that cluster of events to generate a ranking;
select one or more clusters of events from the plurality of clusters of events based on the ranking; and
generate a clip of the augmented recorded lecture based on each cluster of events from the one or more selected clusters of events.

13. The non-transitory computer-readable storage medium of claim 11 , wherein the computer program instructions to cause the processor to generate the plurality of clips include computer program instructions to cause the processor to:
select the beginning time in the augmented recorded lecture for a a clip from the plurality of clips based on a time stamp associated with an early event in a cluster of events from the plurality of clusters of events.

14. The non-transitory computer-readable storage medium of claim 13 , wherein an activity associated with the online platform includes at least one of accessing a page of an electronic documen

Assignees

• Chegg Inc

Inventors

• Raskin Oliver
• Murphy Colin
• Le Chevalier Vincent

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F16/4387 Primary

  by the use of playlists · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G06F16/45

  Clustering; Classification · CPC title

• G06F16/489

  using time information · CPC title