Granted Patent B2

US 9,189,525 · App. 13/775,367 · Granted Nov 17, 2015

Abstract

Claims (71)

1. A computer-implemented method of generating automated tags for a video file, the method comprising:

receiving a list of candidate tags for a video file;

receiving a transcript of audio associated with the video file;

evaluating the transcript of audio associated with the video file;

ranking the list of the candidate tags for the video file based on a plurality of ranking factors, wherein

ranking the list of the candidate tags for the video file based on the plurality of ranking factors includes ranking the list of the candidate tags based on the evaluated transcript;

associating a rank with each of the candidate tags in the list of the candidate tags, based on the ranking;

forming a filtered list of the candidate tags by removing ones of the candidate tags from the list of the candidate tags, the ones of the candidate tags that are removed having an associated rank that is below a threshold value, wherein

evaluating the transcript comprises generating a list of top concepts for the video file in light of the selection of one or more of the filtered list of the candidate tags;

establishing a relationship between the video file and at least one other video file based on corresponding top concepts between the video file and the at least one other video file;

presenting the filtered list of the candidate tags in a user interface;

receiving a selection of one or more of the filtered list of the candidate tags from the user interface; and

producing an updated list of the candidate tags for the video file, based on the selection.

2. The computer-implemented method of generating automated tags for a video file as in claim 1 , wherein presenting the filtered list of the candidate tags comprises:

generating a heat map for the video file, wherein the heat map comprises a graphical display that indicates offset locations of words within the video file with the highest associated rank; and

presenting the heat map in the user interface.

3. The computer-implemented method of generating automated tags for a video file as in claim 2 , wherein presenting the heat map in the user interface is concurrent with presenting the filtered list of the candidate tags in the user interface.

4. The computer-implemented method of generating automated tags for a video file as in claim 1 , wherein the plurality of ranking factors comprises a term frequency-inverse document frequency score of words in the transcript that are associated with the candidate tags.

5. The computer-implemented method of generating automated tags for a video file as in claim 1 , wherein the plurality of ranking factors comprises relative volume of a word in context of the video file.

6. The computer-implemented method of generating automated tags for a video file as in claim 1 , wherein the plurality of ranking factors comprises distribution of a word within the transcript.

7. The computer-implemented method of generating automated tags for a video file as in claim 1 , wherein the plurality of ranking factors comprises finding a word that is related to a ranked word within the transcript.

8. The computer-implemented method of generating automated tags for a video file as in claim 1 , further comprising repeating the steps of ranking, associating, filtering, presenting, receiving a selection of one or more of the filtered list of the candidate tags, evaluating, and producing the updated list, to fine tune the list of scored top concepts.

9. The computer-implemented method of generating automated tags for a video file as in claim 1 , further comprising providing one or more suggested video files associated with the video file based on the relationship between the video file and the at least one other video file.

10. A system that generates tags for a video file, comprising:

one or more processors;

a storage device that includes a non-transitory, computer-readable storage medium;

a communications subsystem; and

a user interface including at least one input device and at least one graphical display;

wherein the storage medium stores the video file and instructions that, when executed by the one or more processors, cause the system to perform operations including:

receiving a list of candidate tags for the video file through the communications subsystem;

receiving a transcript of audio associated with the video file;

evaluating the transcript of audio associated with the video file;

ranking the list of the candidate tags for the video file based on a plurality of ranking factors, wherein:

ranking the list of candidate tags for the video file based on the plurality of ranking factors include ranking the list of candidate tags based on the evaluated transcript;

associating a rank with each of the candidate tags in the list of the candidate tags, based on the ranking;

forming a filtered list of the candidate tags by removing ones of the candidate tags having an associated rank that is below a threshold value from the list of the candidate tags, wherein:

evaluating the transcript cause the system includes generating a list of top concepts for the video file in light of the selection of one or more of the filtered list of candidate tags;

establishing a relationship between the video file and at least one other video file based on corresponding top concepts between the video file and the at least one other video file;

presenting the filtered list of the candidate tags in the user interface;

receiving a selection of one or more of the filtered list of the candidate tags from the user interface;

producing an updated list of the candidate tags for the video file based on the selection; and

storing the updated list of the candidate tags associated with the video file in the storage medium.

11. The system that generates tags for a video file as in claim 10 , the storage medium storing additional instructions that, when executed by the one or more processors, cause the system to perform operations including:

generating a heat map for the video file, wherein the heat map comprises a graphical display that indicates offset locations of words within the video file with the highest rankings;

presenting the heat map in the user interface;

receiving a selection of one or more of the filtered list of the candidate tags from the user interface; and

producing an updated list of the candidate tags for the video file, based on the selection.

12. The system that generates tags for a video file as in claim 11 , the additional instructions causing the system to present the filtered list of the candidate tags, and the heat map, concurrently in the user interface.

13. The system that generates tags for a video file as in claim 10 , the storage medium storing additional instructions that, when executed by the one or more processors, cause the system to perform operations including:

providing one or more suggested video files associated with the video file based on the relationship between the video file and the at least one other video file.

14. A computer-implemented method of generating automated tags for a video file, the method comprising:

generating a targeted transcript of the video file, wherein the targeted transcript includes a plurality of words;

generating an ontology of the plurality of words based on the targeted transcript;

ranking the plurality of words in the ontology based on a plurality of scoring factors;

based on the ranking of the plurality of words, generating one or more automated tags associated with the video file;

generating a list of top concepts for the video file in light of the one or more automated tags associated with the video file;

establishing a relationship between the video file and at least one other video file based on corresponding top concepts between the video file and the at least one other video file; and

generating a heat map for the video file, wherein the heat map comprises a graphical display that indicates offset locations of words within the video file with the highest rankings.

15. The computer-implemented method of generating automated tags for a video file as in claim 14 , further comprising:

presenting the heat map in a user interface;

receiving a selection of one or more of the filtered list of the candidate tags from the user interface; and

producing an updated list of the candidate tags for the video file, based on the selection.

16. The computer-implemented method of generating automated tags for a video file as in claim 14 , wherein ranking the plurality of words in the ontology is based on scoring factors that include one or more of:

distribution of words within the targeted transcript of the video file,

words related to the plurality of words within the targeted transcript of the video file, occurrence age of the related words,

vernacular meaning of the plurality of words, or colloquial considerations of the meaning of the plurality of words,

frequency of words and

proximity of words relative to other words.

17. The computer-implemented method of generating automated tags for a video file as in claim 14 , further comprising determining a score for each of the plurality of words, wherein the score is based on word frequency, word distribution, and word variety.

18. The computer-implemented method of generating automated tags for a video file as in claim 14 , further comprising cross-referencing words with the plurality of words to determine correlations between words or to construct phrases, wherein the cross-referencing of the word or words is configured to increase the ranking of the word or words.

19. The computer-implemented method of generating automated tags for a video file as in claim 14 , further comprising providing one or more suggested video files associated with the video file based on the relationship between the video file and the at least one other video file.

Assignments (9)