Adjacent content classification and targeting

Patent metadata

Field	Value
Publication number	US-11057652-B1
Application number	US-201916399506-A
Country	US
Kind code	B1
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	Jul 6, 2021
Grant date	Jul 6, 2021

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.

First claim

What is claimed is:

1. 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.

2. The computer-implemented method of claim 1 , wherein the video data is stored video data, further comprising:
analyzing the video data to identify a plurality of primary content portions;
determining a plurality of break periods; and
inserting the plurality of break periods between the plurality of primary content portions.

3. The computer-implemented method of claim 1 , wherein the usage criterion is a threshold period of time, further comprising:
determining a start time for the classification;
applying the threshold to the start time;
determining an end time for the classification;
determining the end time expires after a break start time for the break period.

4. The computer-implemented method of claim 1 , wherein the one or more rules includes a threshold period of time between classification and the break period, a number of other classifications between the classification and the break period, a priority, or a combination thereof.

5. 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.

6. A computer-implemented method of claim 5 , wherein the at least one rule is a time threshold, further comprising:
determining a first time associated with the classification;
determining a second time associated with a break period, the break period receiving at least a portion of the supplemental content; and
determining a difference between the first time and the second time is less than the time threshold.

7. A computer-implemented method of claim 5 , wherein the at least one rule is a time threshold, further comprising:
determining a first time associated with the classification;
determining a second time associated with a break period, the break period receiving at least a portion of the supplemental content;
determining a difference between the first time and the second time is greater than the time threshold;
selecting second supplemental content different than the first supplemental content; and
including the second supplemental content in the provided content.

8. The computer-implemented method of claim 5 , further comprising:
determining a primary content portion, the primary content portion having a duration extending between a first break period and a second break period;
determining a plurality of scenes within the primary content portion, the scenes corresponding to primary content and each having a duration,
determining at least one respective classification for each scene of the plurality of scenes; and
determining a plurality of supplemental content corresponding to the at least one respective classifications.

9. The computer-implemented method of claim 8 , further comprising:
selecting second supplemental content, of the plurality of supplemental content, having a closest time proximity to at least one respective classification.

10. The computer-implemented method of claim 5 , wherein the one or more rules includes a threshold period of time between classification and the break period, a number of other classifications between the classification and the break period, a priority, or a combination thereof.

11. The computer-implemented method of claim 5 , wherein the at least one rule is a quantity threshold, further comprising:
determining a first identification associated with the first classification;
determining a second identification associated with a second classification, the second identification being later in time than the first identification;
determining a break period, the break period arranged later in time than both the first identification and the second identification; and
determining a number of identifications between the first identification and the break period is less than the quantity threshold.

12. The computer-implemented method of claim 5 , further comprising:
receiving video data including at least a portion of the primary content;
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 the classification to the portion of primary content, based at least in part on the identified one or more items.

13. The computer-implemented method of claim 12 , wherein the video data is stored video data and the time index classification is generated before comparing the classification with the supplemental content.

14. The computer-implemented method of claim 12 , wherein the video data is live video data and the time index classification is generated in near-real time as the video data is received.

15. The computer-implemented method of claim 5 , further comprising:
adding the classification to a set of context stream contextual targeting keywords.

16. The computer-implemented method of claim 15 , further comprising:
determining a second classification fails at least one rule associated with inclusion of supplemental content with the primary content;
applying a weighting factor to the second classification;
determining the second classification satisfies the at least one rule associated with inclusion of supplemental content with primary content;
selecting second supplemental content associated with the second classification; and
including the second supplemental content in the provided content.

17. 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 satisfi

Assignees

• Amazon Tech Inc

Inventors

• Gauny Ronnie Dean
• Chud Andrew Christopher
• Siegler Scott Anthony

Classifications

• G06V20/41

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• G06V20/49

  Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes · CPC title

• H04N21/8455

  involving pointers to the content, e.g. pointers to the I-frames of the video stream · CPC title

• H04N21/266

  Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel · CPC title

• H04N21/23418 Primary

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title