Knowledge graph metadata network based on notable moments

• US 10,324,973 B2
• Filed: 12/27/2016
• Issued: 06/18/2019
• Est. Priority Date: 06/12/2016
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Circlaeys, Eric, Bessiere, Kevin, Aujoulet, Kevin, Huyghe, Killian, Vergnaud, Guillaume, Hirmer, Benedikt
• Primary Examiner(s): Serrao, Ranodhi
• Application Number:
  US15/391,276
• Publication Number:
  US 20170359236A1
• Time in Patent Office: 903 Days
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/487 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 16/489 using time information
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: H04L 43/045 for graphical visualisation of monitoring data
• CPC Class Codes: H04L 43/16 Threshold monitoring

Abstract

Techniques of generating a knowledge graph metadata network (metadata network) for digital asset management (DAM) are described. A DAM logic/module can obtain one or more first metadata assets describing characteristics associated with digital assets (DAs) in the DA collection. The DAM logic/module can also determine second metadata asset(s) and third metadata asset(s) describing characteristics associated with DAs in the DA collection based on the first metadata asset(s). The DAM logic/module can generate at least some of the metadata assets as nodes in a metadata network associated with the DA collection. The DAM logic/module can also determine, for at least two of the metadata assets, a correlation between the at least two metadata assets. The DAM logic/module can generate an edge in the metadata network between the nodes that represent the at least two metadata assets to represent the determined correlation.

Claims

1. A computer-implemented method for generating a metadata network for digital asset management, comprising:

obtaining, by a processor, a collection of metadata assets describing characteristics associated with digital assets (DAs) in a DA collection;

identifying one or more first metadata assets in the collection of metadata assets, wherein each first metadata asset comprises a moment;

generating nodes in the metadata network to represent at least some of the metadata assets associated with the DA collection;

determining, for at least two of the metadata assets, a correlation between the at least two metadata assets, wherein determining the correlation between the at least two metadata assets includes determining, for at least one of the at least two metadata assets, at least one confidence weight, wherein the at least one confidence weight is indicative of an estimated level of certainty that an element of one or more DAs has been properly identified by a corresponding metadata asset;

determining, for at least one of the at least two metadata assets, a relevance weight, wherein the relevance weight is indicative of an importance of the at least one of the at least two metadata assets, and wherein the relevance weight is configured to change over time based, at least in part, on a number of detections of the at least one of the at least two metadata assets in the metadata network; and

generating an edge in the metadata network between the nodes that represent the at least two metadata assets, the edge representing the determined correlation.

2. The computer-implemented method of claim 1, wherein each metadata asset describes at least one DA in the DA collection.

3. The computer-implemented method of claim 2, wherein each metadata asset describes a group of DAs in the DA collection.

4. The computer-implemented method of claim 1, wherein the correlation between the at least two metadata assets is determined based on at least one of:

(i) a combination of the at least one confidence weight and the relevance weight being equal to or greater than a threshold correlation;

(ii) the at least one confidence weight being equal to or greater than a confidence threshold;

or

(iii) the relevance weight being equal to or greater than a correlation threshold.

5. The computer-implemented method of claim 1, further comprising:

determining one or more second metadata assets based on the one or more first metadata assets, wherein each second metadata asset comprises one or more of;

time metadata, geo-position metadata, geolocation metadata, people metadata, scene metadata, content metadata, object metadata, and sound metadata.

6. The computer-implemented method of claim 5, further comprising:

determining one or more third metadata assets, wherein each third metadata asset is determined or inferred from one or more of;

(i) the one or more first metadata assets and (ii) the one or more second metadata assets.

7. A non-transitory computer readable medium comprising instructions for generating a metadata network for digital asset management, which when executed by one or more processors, cause the one or more processors to:

obtain a collection of metadata assets describing characteristics associated with digital assets (DAs) in a DA collection;

identify one or more first metadata assets in the collection of metadata assets, wherein each first metadata asset comprises a moment;

generate nodes in the metadata network to represent at least some of the metadata assets associated with the DA collection;

determine, for at least two of the metadata assets, a correlation between the at least two metadata assets, wherein determining the correlation between the at least two metadata assets includes determining, for at least one of the at least two metadata assets, at least one confidence weight, wherein the at least one confidence weight is indicative of an estimated level of certainty that an element of one or more DAs has been properly identified by a corresponding metadata asset;

determine, for at least one of the at least two metadata assets, a relevance weight, wherein the relevance weight is indicative of an importance of the at least one of the at least two metadata assets, and wherein the relevance weight is configured to change over time based, at least in part, on a number of detections of the at least one of the at least two metadata assets in the metadata network; and

generate an edge in the metadata network between the nodes that represent the at least two metadata assets, the edge representing the determined correlation.

8. The non-transitory computer readable medium of claim 7, wherein each metadata asset describes at least one DA in the DA collection.

9. The non-transitory computer readable medium of claim 8, wherein each metadata asset describes a group of DAs in the DA collection.

10. The non-transitory computer readable medium of claim 7, wherein the correlation between the at least two metadata assets is determined based on at least one of:

(i) a combination of the at least one confidence weight and the relevance weight being equal to or greater than a threshold correlation;

(ii) the at least one confidence weight being equal to or greater than a confidence threshold;

or

(iii) the relevance weight being equal to or greater than a correlation threshold.

11. The non-transitory computer readable medium of claim 7, wherein the instructions further comprise instructions, which, when executed by the one or more processors, cause the one or more processors to:

determine one or more second metadata assets based on the one or more first metadata assets, wherein each second metadata asset comprises one or more of;

time metadata, geo-position metadata, geolocation metadata, people metadata, scene metadata, content metadata, object metadata, and sound metadata.

12. The non-transitory computer readable medium of claim 11, wherein the instructions further comprise instructions, which, when executed by the one or more processors, cause the one or more processors to:

determine one or more third metadata assets, wherein each third metadata asset is determined or inferred from one or more of;

(i) the one or more first metadata assets and (ii) the one or more second metadata assets.

13. A processing system for generating a knowledge graph metadata network for digital asset management, comprising:

one or more processors configured to;

obtain a collection of metadata assets describing characteristics associated with digital assets (DAs) in a DA collection;

identify one or more first metadata assets in the collection of metadata assets, wherein each first metadata asset comprises a moment;

generate nodes in the metadata network to represent at least some of the metadata assets associated with the DA collection;

determine, for at least two of the metadata assets, a correlation between the at least two metadata assets, wherein determining the correlation between the at least two metadata assets includes determining, for at least one of the at least two metadata assets, at least one confidence weight, wherein the at least one confidence weight is indicative of an estimated level of certainty that an element of one or more DAs has been properly identified by a corresponding metadata asset;

determine, for at least one of the at least two metadata assets, a relevance weight, wherein the relevance weight is indicative of an importance of the at least one of the at least two metadata assets, and wherein the relevance weight is configured to change over time based, at least in part, on a number of detections of the at least one of the at least two metadata assets in the metadata network; and

generate an edge in the metadata network between the nodes that represent the at least two metadata assets, the edge representing the determined correlation.

14. The system of claim 13, wherein each metadata asset describes at least one DA in the DA collection.

15. The system of claim 14, wherein each metadata asset describes a group of DAs in the DA collection.

16. The system of claim 13, wherein the correlation between the at least two metadata assets is determined based on at least one of:

(i) a combination of the at least one confidence weight and the relevance weight being equal to or greater than a threshold correlation;

(ii) the at least one confidence weight being equal to or greater than a confidence threshold;

or

(iii) the relevance weight being equal to or greater than a correlation threshold.

17. The system of claim 13, wherein the one or more processors are further configured to:

determine one or more second metadata assets based on the one or more first metadata assets, wherein each second metadata asset comprises one or more of;

time metadata, geo-position metadata, geolocation metadata, people metadata, scene metadata, content metadata, object metadata, and sound metadata.

18. The system of claim 17, wherein the one or more processors are further configured to:

determine one or more third metadata assets, wherein each third metadata asset is determined or inferred from one or more of;

(i) the one or more first metadata assets and (ii) the one or more second metadata assets.