Granted Patent B2

US 12,205,372 · App. 18/295,733 · Granted Jan 21, 2025

Inventors: Thomas H. Strader (Fort Worth, TX); Christopher Buchholz (Norwalk, CT)

Assignee: Seismic Software, Inc.

G06V20/41G06V20/49G06V20/60

Abstract

Claims (49)

1. A system, comprising:

a processor configured to:

obtain a recorded video comprising a plurality of video frames, wherein the recorded video comprises a recording of an online, video-based meeting;

select a subset of the plurality of video frames as sampled video frames;

identify a document portion that appears during the recorded video based at least in part on detecting, within a sampled video frame, a presence of a document portion identifier corresponding to the document portion; and

determine a video segment during which the document portion appears in the recorded video;

wherein the video segment is defined by a start timestamp and an end timestamp within the recorded video, wherein the start timestamp of the video segment is determined based at least in part on detecting the presence of the document portion identifier corresponding to the document portion within the sampled video frames, and wherein the end timestamp of the video segment is determined based at least in part on no longer detecting the presence of the document portion identifier corresponding to the document portion within the sampled video frames; and

a memory coupled to the processor and configured to provide the processor with instructions.

2. The system of claim 1 , wherein to select the subset of the plurality of video frames comprises to obtain a file associated with screen shared content associated with the recorded video.

3. The system of claim 1 , wherein to select the subset of the plurality of video frames comprises to select video frames at each predetermined interval within the plurality of video frames.

4. The system of claim 1 , wherein to select the subset of the plurality of video frames comprises to determine unique video frames within the plurality of video frames.

5. The system of claim 1 , wherein the processor is further configured to:

obtain a document comprising a plurality of document portions, wherein the plurality of document portions comprises the document portion;

obtain a plurality of new document portion identifiers corresponding to the plurality of document portions belonging to the document; and

apply the plurality of new document portion identifiers to the plurality of document portions.

6. The system of claim 5 , wherein the plurality of new document portion identifiers comprises a plurality of barcodes.

7. The system of claim 1 , wherein the processor is further configured to:

determine a first set of signals from an audio segment corresponding to the video segment;

determine a second set of signals from text transcription corresponding to the video segment;

determine a third set of signals from video frames included in the video segment; and

determine a comparison between detected content associated with the document portion that appears in the recorded video and a stored version of a stored document portion associated with the document portion identifier.

8. The system of claim 7 , wherein the processor is further configured to update aggregated analysis associated with the document portion identifier with one or more of the following: the first set of signals, the second set of signals, the third set of signals, and the comparison.

9. The system of claim 8 , wherein the processor is further configured to:

compare the aggregated analysis associated with the document portion identifier to stored rules to generate a recommendation; and

present the recommendation at a user interface.

10. The system of claim 9 , wherein the processor is further configured to update aggregated analysis associated with a document to which the document portion belongs with one or more of the following: the first set of signals, the second set of signals, the third set of signals, and the comparison.

11. The system of claim 1 , wherein the document portion belongs to a document that comprises a slideshow, a word processing document, a portable document format (PDF), a video, or a set of images.

12. A method, comprising:

obtaining a recorded video comprising a plurality of video frames, wherein the recorded video comprises a recording of an online, video-based meeting;

selecting a subset of the plurality of video frames as sampled video frames;

identifying a document portion that appears during the recorded video based at least in part on detecting, within a sampled video frame, a presence of a document portion identifier corresponding to the document portion; and

determining a video segment during which the document portion appears in the recorded video;

wherein the video segment is defined by a start timestamp and an end timestamp within the recorded video, wherein the start timestamp of the video segment is determined based at least in part on detecting the presence of the document portion identifier corresponding to the document portion within the sampled video frames, and wherein the end timestamp of the video segment is determined based at least in part on no longer detecting the presence of the document portion identifier corresponding to the document portion within the sampled video frames.

13. The method of claim 12 , wherein selecting the subset of the plurality of video frames comprises obtaining a file associated with screen shared content associated with the recorded video.

14. The method of claim 12 , wherein selecting the subset of the plurality of video frames comprises selecting video frames at each predetermined interval within the plurality of video frames.

15. The method of claim 12 , wherein selecting the subset of the plurality of video frames comprises determining unique video frames within the plurality of video frames.

16. The method of claim 12 , further comprising:

obtaining a document comprising a plurality of document portions, wherein the plurality of document portions comprises the document portion;

obtaining a plurality of new document portion identifiers corresponding to the plurality of document portions belonging to the document; and

applying the plurality of new document portion identifiers to the plurality of document portions.

17. The method of claim 16 , wherein the plurality of new document portion identifiers comprises a plurality of barcodes.

18. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

obtaining a recorded video comprising a plurality of video frames, wherein the recorded video comprises a recording of an online, video-based meeting;

selecting a subset of the plurality of video frames as sampled video frames;

identifying a document portion that appears during the recorded video based at least in part on detecting, within a sampled video frame, a presence of a document portion identifier corresponding to the document portion; and

determining a video segment during which the document portion appears in the recorded video;

wherein the video segment is defined by a start timestamp and an end timestamp within the recorded video, wherein the start timestamp of the video segment is determined based at least in part on detecting the presence of the document portion identifier corresponding to the document portion within the sampled video frames, and wherein the end timestamp of the video segment is determined based at least in part on no longer detecting the presence of the document portion identifier corresponding to the document portion within the sampled video frames.

19. The system of claim 1 , wherein the sampled video frames are reviewed chronologically to detect for the presence of the document portion identifier corresponding to the document portion.

20. The method of claim 12 , wherein the sampled video frames are reviewed chronologically to detect for the presence of the document portion identifier corresponding to the document portion.

Assignments (1)

Continuity (2)

References Cited (82)