Educational case study media content creation based on crowdsource information collections

Patent metadata

Field	Value
Publication number	US-2025356768-A1
Application number	US-202418663480-A
Country	US
Kind code	A1
Filing date	May 14, 2024
Priority date	May 14, 2024
Publication date	Nov 20, 2025
Grant date	—

Abstract

In an approach for creating educational case study content based on crowdsourced media content, a processor receives a request for a video to be used with a case study and determines one or more requirements for the video. Based on the one or more requirements, the processor retrieves a plurality of crowdsourced videos from a social media network and determines at least one set of the plurality of crowdsourced videos that can form a closed loop contour. The processor further, based on the at least one set of the plurality of crowdsourced videos, creates the video to be used with the case study.

First claim

1 . A computer-implemented method comprising:
receiving a request for a video; determining one or more requirements for the video; retrieving, based on the one or more requirements, a plurality of crowdsourced videos from a social media network; extracting a set of metadata from the plurality of crowdsourced videos, the set of metadata including geographical and temporal information; clustering the plurality of crowdsourced videos into location clusters based on a geographical proximity; determining, based on the temporal information, a chronological sequence of clustered videos within the location clusters; determining a first temporal image set of the plurality of crowdsourced videos that form a closed loop contour at a given time and at a target location; and creating the video including sequentially arranging multiple temporal image sets including the first temporal image set, the video meeting the one or more requirements.

2 . The computer-implemented method of claim 1 , wherein retrieving the plurality of crowdsourced videos from the social media network includes:
determining, based on the one or more requirements, a search query for the social media network.

3 . The computer-implemented method of claim 1 , wherein retrieving the plurality of crowdsourced videos from the social media network includes:
determining a plurality of videos captured at a concurrent time, the plurality of videos meeting the one or more requirements for the video.

4 . (canceled)

5 . The computer-implemented method of claim 1 , wherein the set of metadata of the plurality of crowdsourced videos includes a location of capture, a direction of capture, and a timing of capture.

6 . The computer-implemented method of claim 1 , wherein creating the video further comprises:
synchronizing temporal image sets in terms of a temporal and a spatial alignment; reconstructing a three-dimensional (3D) model from the synchronized temporal image sets; extracting closed-loop contour information from the 3D model; and converting the 3D model to a volumetric video.

7 . (canceled)

8 . A computer program product comprising one or more computer readable storage media and program instructions stored therein, which, when executed by a processor, causes the processor to perform a method comprising:
receiving a request for a video; determining one or more requirements for the video; retrieving, based on the one or more requirements, a plurality of crowdsourced videos from a social media network; extracting a set of metadata from the plurality of crowdsourced videos, the set of metadata including geographical and temporal information; clustering the plurality of crowdsourced videos into location clusters based on a geographical proximity; determining, based on the temporal information, a chronological sequence of clustered videos within the location clusters; determining a first temporal image set of the plurality of crowdsourced videos that form a closed loop contour at a given time and at a target location; and creating the video including sequentially arranging multiple temporal image sets including the first temporal image set, the video meeting the one or more requirements.

9 . The computer program product of claim 8 , wherein retrieving the plurality of crowdsourced videos from the social media network includes:
determining, based on the one or more requirements, a search query for the social media network.

10 . The computer program product of claim 8 , wherein retrieving the plurality of crowdsourced videos from the social media network further comprises includes:
determining a plurality of videos captured at a concurrent time, the plurality of videos meeting the one or more requirements for the video.

11 . (canceled)

12 . The computer program product of claim 8 , wherein the set of metadata of the plurality of crowdsourced videos includes a location of capture, a direction of capture, and a timing of capture.

13 . The computer program product of claim 8 , wherein creating the video further comprises:
synchronizing the temporal image sets in terms of a temporal and a spatial alignment; reconstructing a three-dimensional (3D) model from the synchronized temporal image sets; extracting the closed loop contour from the 3D model; and converting the 3D model to a volumetric video.

14 . (canceled)

15 . A computer system comprising:
one or more computer processors; one or more computer readable storage media; wherein: the one or more computer processors are structured, located, connected, and/or programmed to run program instructions on the one or more computer readable storage media; and the program instructions, which, when executed by at least one processor of the one or more computer processors, cause the at least one processor to perform a method comprising:
receiving a request for a video;
determining one or more requirements for the video;
retrieving, based on the one or more requirements, a plurality of crowdsourced videos from a social media network;
extracting a set of metadata from the plurality of crowdsourced videos, the set of metadata including geographical and temporal information;
clustering the plurality of crowdsourced videos into location clusters based on a geographical proximity;
determining, based on the temporal information, a chronological sequence of clustered videos within the location clusters;
determining a first temporal image set of the plurality of crowdsourced videos that form a closed loop contour at a given time and at a target location; and
creating the video including sequentially arranging multiple temporal image sets including the first temporal image set, the video meeting the one or more requirements.

16 . The computer system of claim 15 , wherein retrieving the plurality of crowdsourced videos from the social media network includes:
determining, based on the one or more requirements, a search query for the social media network.

17 . (canceled)

18 . The computer system of claim 15 , wherein the set of metadata of the plurality of crowdsourced videos includes a location of capture, a direction of capture, and a timing of capture.

19 . The computer system of claim 15 , wherein creating the video further comprises:
synchronizing the temporal image sets in terms of a temporal and a spatial alignment; reconstructing a three-dimensional (3D) model from the synchronized temporal image sets; extracting the closed loop contour from the 3D model; and converting the 3D model to a volumetric video.

20 . (canceled)

21 . The computer-implemented method of claim 6 , wherein extracting the closed loop contour information includes identifying a silhouette of an object in each frame of the video;

22 . The computer-implemented method of claim 6 , wherein converting the 3D model to a volumetric video includes:
verifying consistency of the closed loop contour information; and creating a continuous loop based on the set of metadata.

23 . The computer-implemented method of claim 1 , wherein:
determining the first temporal image set includes identifying approximate closed loop contours by:
joining multiple points consisting of the target location and a direction vector, the multiple points including a first point and a last point; and
interpolating the multiple points sequentially using a linear interpolation formula starting with the first point and, finally, connecting the last

Assignees

• IBM

Inventors

• Rakshit Sarbajit K
• Padmanaban Manikandan
• Hazra Jagabondhu

Classifications

• G06F16/743

  a collection of video files or sequences · CPC title

• H04N21/816

  involving special video data, e.g 3D video · CPC title

• H04N21/854

  Content authoring · CPC title

• H04N21/2743

  Video hosting of uploaded data from client · CPC title

• G06Q50/20

  Education · CPC title