- Number
- 10817565
- Published
- 2020-10-27
- Filed
- 2017-11-06
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Farre Guiu; Miquel Angel, Petrillo; Matthew, Alfaro; Monica, Beltran Sanchidrian; Pablo, Junyent Martin; Marc, Binder; Evan A., Accardo; Anthony M., Ettinger; Katharine S., Swerdlow; Avner
- CPC
- G06F16/75; G06F16/738; H04N21/8456; H04N21/44; H04N21/8405; G06F16/7867; H04N21/84; H04N21/435; G06F16/9535
- Verdict
- Set aside content tagging automation, business/analytics
- Source
- Google Patents · FreePatentsOnline
Abstract
A media content tagging system includes a computing platform having a hardware processor, and a system memory storing a tag selector software code configured to receive media content having segments, each segment including multiple content elements each associated with metadata tags having respective pre-computed confidence scores. For each content element, the tag selector software code assigns each of the metadata tags to at least one tag group, determines a confidence score for each tag group based on the pre-computed confidence scores of its assigned metadata tags, discards tag groups having less than a minimum number of assigned metadata tags, and filters the reduced number of tag groups based on the second confidence score to identify a further reduced number of tag groups. The tag selector software code then selects at least one representative tag group for a segment from among the further reduced number of tag groups.
Background
BACKGROUND(1) Media content in a wide variety of formats is consistently sought out and enjoyed by consumers. Video content, for example, is a popular medium for the enjoyment of entertainment content in the form of movies, television, and sports, as well as for information content such as news. Due to its popularity with consumers, ever more video content is being produced and made available for distribution. Consequently, the accuracy and efficiency with which video content can be classified and managed has become increasingly important to producers, owners, and distributors of such content.(2) Techniques for improving the accuracy with which media content can be classified have tended to apply metadata tags to the media content at ever finer levels of granularity. However, those techniques impose a heavy burden on human annotators tasked with reviewing the accuracy of the applied metadata tags.SUMMARY(3) There are provided systems and methods for automating media content tag selection, substantially as shown in and/or described in connection with at least one of the figures, and as set forth more completely in the claims.
Claims
1. A media content tagging system comprising: a computing platform including a hardware processor and a system memory; a tag selector software code stored in the system memory; the hardware processor configured to execute the tag selector software code to: receive a media content including multiple content elements, each of the multiple content elements being associated with a plurality of metadata tags, each of the plurality of metadata tags having a pre-computed first confidence score, each of the multiple content elements also being associated with one of several segments of the media content, each segment of the several segments of the media content including more than one of the multiple content elements; for each one of the multiple content elements, assign each of the plurality of metadata tags associated with the one of the multiple content elements to at least one tag group of a first plurality of tag groups of the media content; discard each tag group of the first plurality of tag groups having less than a minimum number of assigned metadata tags, resulting in a reduced second plurality of tag groups of the media content; determine a second confidence score for each one of the reduced second plurality of tag groups based on the respective pre-computed first confidence score of each of the plurality of metadata tags assigned to the each one of the reduced second plurality of tag groups; filter the reduced second plurality of tag groups based on the second confidence score to identify a further reduced third plurality of tag groups; select at least one representative tag group for each of the several segments of the media content from among the further reduced third plurality of tag groups; and render the at least one representative tag group on a display for a user of the media content tagging system.
10. A method being executed by a media tagging system including a computing platform having a hardware processor and a system memory storing a tag selector software code, the method comprising: receiving, using the hardware processor executing the tag selector software code, a media content including multiple content elements, each of the multiple content elements being associated with a plurality of metadata tags, each of the plurality of metadata tags having a pre-computed first confidence score, each of the multiple content elements also being associated with one of several segments of the media content, each segment of the several segments of the media content including more than one of the multiple content elements; assigning, for each one of the multiple content elements and using the hardware processor executing the tag selector software code, each of the plurality of metadata tags associated with the one of the multiple content elements to at least one tag group of a first plurality of tag groups of the media content; discarding, using the hardware processor executing the tag selector software code, each tag group of the first plurality of tag groups having less than a minimum number of assigned metadata tags, resulting in a reduced second plurality of tag groups of the media content; determining, using the hardware processor executing the tag selector software code, a second confidence score for each one of the reduced second plurality of tag groups based on the respective pre-computed first confidence score of each of the plurality of metadata tags assigned to the each one of the reduced second plurality of tag groups; filtering, using the hardware processor executing the tag selector software code, the reduced second plurality of tag groups based on the second confidence score to identify a further reduced third plurality of tag groups; selecting, using the hardware processor executing the tag selector software code, at least one representative tag group for each of the several segments of the media content from among the reduced third plurality of tag groups; and rendering, using the hardware processor executing the tag selector software code, the at least one representative tag group on a display for a user of the media content tagging system.