Generating congruous metadata for multimedia

Patent metadata

Field	Value
Publication number	US-11748401-B2
Application number	US-201916281158-A
Country	US
Kind code	B2
Filing date	Feb 21, 2019
Priority date	Mar 4, 2008
Publication date	Sep 5, 2023
Grant date	Sep 5, 2023

Abstract

A method of generating congruous metadata is provided. The method includes receiving a similarity measure between at least two multimedia objects. Each multimedia object has associated metadata. If the at least two multimedia objects are similar based on the similarity measure and a similarity threshold, the associated metadata of each of the multimedia objects are compared. Then, based on the comparison of the associated metadata of each of the at least two multimedia objects, the method further includes generating congruous metadata. Metadata may be tags, for example.

First claim

What is claimed is:

1. A method comprising:
determining, by a computing device of a multimedia system, a similarity between content of a first content item and content of a second content item, the determining comprising analyzing digital data of the first and second content items to determine the similarity;
using, by the computing device, information indicating an absence of user verification of computer-generated congruous metadata to make a determination to dynamically adjust an adjustable similarity threshold configured for adjustment between being more or less restrictive;
adjusting, by the computing device, in response to the determination, the adjustable similarity threshold to be more restrictive requiring a higher degree of similarity between the first and second content items in the absence of user verification of the computer-generated congruous metadata;
determining, by the computing device, that the similarity determined for the first and second content items satisfies the adjustable similarity threshold;
responsive to determining that the similarity satisfies the adjustable similarity threshold, comparing, by the computing device, a first set of metadata associated with the first content item with a second set of metadata associated with the second content item, the comparing comprising identifying metadata found in both the first and second sets of metadata;
automatically generating, by the computing device, the congruous metadata comprising the identified metadata found in both the first and second sets of metadata; and
in response to a retrieval request comprising at least some of the congruous metadata as selection criteria, retrieving, via the computing device and from a data store, at least one of the first and second content items.

2. The method of claim 1 , further comprising:
storing, by the computing device and in the data store, the congruous metadata, the storing comprising associating the congruous metadata with both the first and second content items.

3. The method of claim 1 , determining a similarity between content of a first content item and content of a second content item further comprising:
determining, for the first content item, a first set of content items similar to the first content item;
determining, for the second content item, a second set of content items similar to the second content item;
determining that the similarity of the first and second content items satisfies the similarity threshold if the first content item is included in the second set of content items similar to the second content item and the second content item is included in the first set of content items similar to the first content item.

4. The method of claim 3 , further comprising:
determining the first set of content items comprising using a similarity measure associated with each content item of the first set, the similarity measure associated with a content item of the first set indicating the similarity of the content item to the first content item; and
determining the second set of content items comprising using a similarity measure associated with each content item of the second set, the similarity measure associated with a content item of the second set indicating the similarity of the content item to the second content item.

5. The method of claim 1 , determining a similarity between content of a first content item and content of a second content item further comprising:
determining a representation of the first content item using the content of the first content item;
determining a representation of the second content item using the content of the second content item; and
determining a difference between the representation of the first content item and the representation of the second content item.

6. The method of claim 5 , the representation of the first content item and the representation of the second content item comprising a vector representation.

7. The method of claim 5 , the representation of the first content item and the representation of the second content item comprising a video mosaic representation.

8. The method of claim 5 , the representation of the first content item and the representation of the second content item comprising an audio waveform signal.

9. The method of claim 1 , the identified metadata found in both the first and second sets of metadata used in automatically generating the congruous metadata comprising user-generated metadata found in both the first and second sets of metadata.

10. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a processor associated with a computing device perform a method comprising:
determining a similarity between content of a first content item and content of a second content item, the determining comprising analyzing digital data of the first and second content items to determine the similarity;
using information indicating an absence of user verification of computer-generated congruous metadata to make a determination to dynamically adjust an adjustable similarity threshold configured for adjustment between being more or less restrictive;
adjust, in response to the determination, the adjustable similarity threshold to be more restrictive requiring a higher degree of similarity between the first and second content items in the absence of user verification of the computer-generated congruous metadata;
determining that the similarity determined for the first and second content items satisfies the adjustable similarity threshold;
responsive to determining the similarity satisfies the adjustable similarity threshold, comparing a first set of metadata associated with the first content item with a second set of metadata associated with the second content item, the comparing comprising identifying metadata found in both the first and second sets of metadata;
automatically generating the congruous metadata using the identified metadata found in both the first and second sets of metadata; and
in response to a retrieval request comprising at least some of the congruous metadata as selection criteria, retrieving, from a data store, at least one of the first and second contents.

11. The non-transitory computer-readable storage medium of claim 10 , determining a similarity between content of a first content item and content of a second content item further comprising:
determining, for the first content item, a first set of content items similar to the first content item;
determining, for the second content item, a second set of content items similar to the second content item;
determining that the similarity of the first and second content items satisfies the similarity threshold if the first content item is included in the second set of content items similar to the second content item and the second content item is included in the first set of content items similar to the first content item.

12. The non-transitory computer-readable storage medium of claim 11 , further comprising:
determining the first set of content items comprising using a similarity measure associated with each content item of the first set, the similarity measure associated with a content item of the first set indicating the similarity of the content item to the first content item; and
determining the second set of content items comprising using a similarity measure associated with each content item of the second set, the similarity measure associated with a content item of the second set indicating the similarity of the content item to the second content item.

13. The non-transitory computer-readable storage

Assignees

• Yahoo Assets Llc

Inventors

• Slaney Malcolm
• Weinberger Kilian

Classifications

• G06F16/58 Primary

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/5838 Primary

  using colour · CPC title

• G06F16/68

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/683

  using metadata automatically derived from the content · CPC title

• G06F16/78

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title