Adjacent content classification and targeting
AssigneeAmazon Technologies, Inc.
InventorsRonnie Dean Gauny, Andrew Christopher Chud, Scott Anthony Siegler
Life of this patent
Estimating the term…
Abstract
Video content is evaluated to classify one or more scenes or objects of the video content. The classifications may be evaluated against one or more rules for determining whether to include key words associated with the classifications for targeting supplemental content. Classifications that satisfy the one or more rules may be used for selection of supplemental associated with one or more key words Selected supplemental content may be included in video content in a break period following primary content.
Claims20
A computer-implemented method, comprising:
- receiving video data including at least a portion of primary content, the primary content including a plurality of scenes;
- analyzing at least a portion of the primary content using an object recognition module to identify one or more items within the portion of the primary content;
- applying a classification to the portion of primary content, based at least in part on the identified one or more items;
- determining a usage criterion associated with the classification, the usage criterion restricting presentation of related supplemental content, with respect to the classification;
- determining the usage criterion satisfies one or more rules associated with a break period, the break period being after a duration of the portion of primary content;
- selecting supplemental content associated with the classification of the portion of primary content, the supplemental content being identified by a line item that corresponds to the classification;
- generating output video content including the primary content and the supplemental content, the supplemental content being within the break period.
A computer-implemented method, comprising:
- obtaining a time index classification of a least a portion of primary content, the time index classification identifying at least one time within the portion of primary content associated with a classification;
- determining the classification satisfies at least one rule associated with inclusion of supplemental content with the primary content, the at least one rule corresponding to a position of the classification with respect to other segments of the primary content;
- comparing the classification to a set of key words associated with the supplemental content;
- selecting first supplemental content associated with at least one key word related to the classification;
- and
- including the first supplemental content and the primary content in provided content.
A system, comprising:
- at least one processor;
- and
- memory including instructions that, when executed by the at least one processor, cause the system to:
- obtain a time index classification of a least a portion of primary content, the time index classification identifying at least one time within the portion of primary content associated with a classification;
- determine the classification satisfies at least one rule associated with inclusion of supplemental content with the primary content, the at least one rule corresponding to a position of the classification with respect to other segments of the primary content;
- compare the classification to a set of key words associated with the supplemental content;
- select first supplemental content associated with at least one key word related to the classification;
- and
- include the first supplemental content and the primary content in provided content.
Dependencies are inferred from the claim text.