Techniques for disambiguating clustered occurrence identifiers

• US 10,803,135 B2
• Filed: 12/13/2018
• Issued: 10/13/2020
• Est. Priority Date: 09/11/2018
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Hirmer, Benedikt M., Bessiere, Kevin, Circlaeys, Eric, Weilert, Shanni A., Foster, Christopher C., Behara, Krishna M., Kasibatta, Kartheekeya D.
• Primary Examiner(s): Al-Hashemi, Sana A
• Application Number:
  US16/219,661
• Publication Number:
  US 20200081931A1
• Time in Patent Office: 670 Days
• Field of Search: 707607, 707609, 707687, 707705, 707769, 707790, 707813, 707821
• CPC Class Codes: G06F 16/9035 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/906 Clustering; Classification
• CPC Class Codes: G06F 16/907 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

Embodiments of the present disclosure present devices, methods, and computer readable medium for disambiguating clustered occurrence identifiers. Digital assets contain a plurality of metadata that can be used to identify the occurrence or event during which the digital asset was captured. Techniques can use various types contextual information based on a category of the digital asset for disambiguation. Events can occur at various locations, over a dispersed area and it can be challenging to automatically identify and label the digital assets with the identification of the event. Automatically labelling the digital assets assists user in organizing and sharing the digital assets with friends and family. Users can search for events by event name, performer name, and category.

Claims

1. A method, comprising:

identifying a collection of digital assets having at least a first digital asset and a second digital asset, the collection of digital assets being stored on a computing device;

generating a consolidated address for a location cluster of digital assets comprising the first digital asset and the second digital asset;

determining a first geographic location for the consolidated address based at least in part on location metadata associated with the first digital asset;

determining a first time for the first digital asset based at least in part on time metadata associated with the first digital asset;

transmitting a request to a web service for a plurality of event identifiers within a target range of the first geographic location, each of the event identifiers specifying an event geographic location and an event time;

filtering the plurality of event identifiers, the filtering of the plurality of event identifiers to remove locations visited above a frequency threshold;

accessing a knowledge graph stored on the computing device to correlate metadata for the collection of digital assets with a category identified in the knowledge graph;

calculating a distance range between the first geographic location and a second geographic location, the second geographic location based at least in part on location metadata associated with the second digital asset, the second digital asset being within a target range of the event geographic location;

calculating a time range between the first time and a second time, the second time based at least in part on time metadata associated with the second digital asset;

calculating a confidence metric, the confidence metric indicating a degree of confidence that the first digital asset was generated at an event corresponding to at least one of the plurality of event identifiers, the confidence metric calculated based at least in part on rules for the category of the first digital asset, the rules specifying that the distance range satisfies a minimum distance, the time range satisfies a minimum duration, and a number of digital assets stored on the computing device that are within the distance range of the event geographic location and within the time range of an event time satisfies a minimum number;

associating the first digital asset with at least one of the plurality of event identifiers based at least in part on a determination that the confidence metric exceeds a threshold; and

updating the knowledge graph stored in the computing device to include the association between the first digital asset and the at least one of the plurality of event identifiers.

2. The method of claim 1, further comprising increasing the minimum distance to include additional digital assets captured within an expanded distance of the event geographic location.

3. The method of claim 1, further comprising expanding the event time to include additional digital assets captured prior to or after the event.

4. The method of claim 1, further comprising accessing the knowledge graph for a determination that scene metadata for the first digital asset identifies the category for the first digital asset based at least in part on image analysis of objects in the first digital asset.

5. The method of claim 1, further comprising:

transmitting a request, to a second location service, the second location service tracking a history of geographic locations for the computing device over time, the request to the second location service requesting a length of time the computing device was located within a specified distance from the plurality of event identifiers within the target range of the first geographic location; and

modifying the confidence metric based at least in part on the length of time the computing device spent within the specified distance from the plurality of event identifiers within the target range of the first geographic location.

6. The method of claim 1, further comprising:

associating the second digital asset with the at least one of the plurality of event identifiers based on a determination that the confidence metric exceeds a threshold; and

updating the knowledge graph stored in the computing device to include the association between the second digital asset and the at least one of the plurality of event identifiers.

7. The method of claim 1, further comprising linking the first digital asset associated with one of the plurality of event identifiers at least one of a name, a performer, and a venue for the event.

8. The method of claim 1, further comprising linking the first digital asset associated with one of the plurality of event identifiers with an event category for the event.

9. A computing device, comprising:

one or more memories; and

one or more processors in communication with the one or more memories and configured to execute instructions stored in the one or more memories to;

identify a collection of digital assets having at least a first digital asset and a second digital asset, the collection of digital assets being stored on the computing device;

generate a consolidated address for a location cluster of digital assets comprising the first digital asset and the second digital asset;

determine a first geographic location for the consolidated address based at least in part on location metadata associated with the first digital asset;

determine a first time for the first digital asset based at least in part on time metadata associated with the first digital asset;

transmit a request to a web service for a plurality of event identifiers within a target range of the first geographic location, each of the event identifiers specifying an event geographic location and an event time;

access a knowledge graph to correlate metadata for the collection of digital assets with a category for the first digital asset identified in the knowledge graph;

calculate a distance range between the first geographic location a second geographic location, the second geographic location based at least in part on location metadata associated with the second digital asset, the second digital asset being within a target range of the event geographic location;

calculate a time range between the first time and a second time, the second time based at least in part on time metadata associated with the second digital asset;

calculate a confidence metric, the confidence metric indicating a degree of confidence that the first digital asset was generated at an event corresponding to at least one of the plurality of event identifiers, the confidence metric calculated based at least in part on rules for the category of the first digital asset, the rules specifying that the distance range satisfies a minimum distance, the time range satisfies a minimum duration, and a number of digital assets stored on the computing device satisfies a minimum number of digital assets that are within the distance range of the event geographic location and within the time range of an event time;

associate the first digital asset with at least one of the plurality of event identifiers based at least in part on a determination that the confidence metric exceeds a threshold; and

update the knowledge graph stored in the computing device to include an association between the first digital asset and the at least one of the plurality of event identifiers.

10. The computing device of claim 9, wherein the one or more processors are further configured to execute the instructions to increase the minimum distance to include additional digital assets captured within an expanded distance of the event geographic location.

11. The computing device of claim 9, wherein the one or more processors are further configured to execute the instructions to expand the event time to include additional digital assets captured prior to or after the event.

12. The computing device of claim 9, wherein the one or more processors are further configured to execute the instructions to access the knowledge graph for a determination that scene metadata for the first digital asset identifies the category for the first digital asset based at least in part on image analysis of objects in the first digital asset.

13. The computing device of claim 9, wherein the one or more processors are further configured to execute the instructions to:

transmit a request, to a second location service, the second location service tracking a history of geographic locations for the computing device over time, the request to the second location service requesting a length of time the computing device was located within a specified distance from the plurality of event identifiers within the target range of the first geographic location; and

modify the confidence metric based at least in part on the length of time the computing device spent within the specified distance from the plurality of event identifiers within the target range of the first geographic location.

14. The computing device of claim 9, wherein the one or more processors are further configured to execute the instructions to link the first digital asset associated with one of the plurality of event identifiers at least one of a name, a performer, and a venue for the event.

15. The computing device of claim 9, wherein the one or more processors are further configured to execute the instructions to link the first digital asset associated with one of the plurality of event identifiers with an event category for the event.

16. A computer-readable medium storing a plurality of instructions that, when executed by one or more processors of a computing device, cause the one or more processors of the computing device to perform operations comprising:

identifying a collection of digital assets having at least a first digital asset and a second digital asset, the collection of digital assets being stored on the computing device;

generating a consolidated address for a location cluster of digital assets comprising the first digital asset and the second digital asset;

determining a first geographic location for the consolidated address based at least in part on location metadata associated with the first digital asset;

determining a first time for the first digital asset based at least in part on time metadata associated with the first digital asset;

transmitting a request to a first web service for a plurality of event identifiers within a target range of the first geographic location, each of the event identifiers specifying an event geographic location and an event time;

accessing a knowledge graph stored on the computing device to correlate metadata for the collection of digital assets with a category identified in the knowledge graph;

calculating a distance range between the first geographic location and a second geographic location, the second geographic location based at least in part on location metadata associated with the second digital asset, the second digital asset being within the target range of the event geographic location;

calculating a time range between the first time and a second time, the second time based at least in part on time metadata associated with the second digital asset;

calculating a confidence metric, the confidence metric indicating a degree of confidence that the first digital asset was generated at an event corresponding to at least one of the plurality of event identifiers, the confidence metric calculated based at least in part on rules for the category of the first digital asset;

associating the first digital asset with at least one of the plurality of event identifiers based at least in part on a determination that the confidence metric exceeds a threshold; and

updating the knowledge graph stored in the computing device to include the association between the first digital asset and at least one of the plurality of event identifiers.

17. The computer-readable medium of claim 16, further comprising increasing the target range to include additional digital assets captured within an expanded distance of the event geographic location.

18. The computer-readable medium of claim 16, further comprising expanding the event time to include additional digital assets captured prior to or after the event.

19. The computer-readable medium of claim 16, further comprising accessing the knowledge graph for a determination that scene metadata for the first digital asset identifies the category for the first digital asset based at least in part on image analysis of objects in the first digital asset.

20. The computer-readable medium of claim 16, further comprising

transmitting a request, to a second location service, the second location service tracking a history of geographic locations for the computing device over time, the request to the second location service requesting a length of time the computing device was located within a specified distance from the plurality of event identifiers within the target range of the first geographic location;

and

modifying the confidence metric based at least in part on the length of time the computing device spent within the specified distance from the plurality of event identifiers within the target range of the first geographic location.