Selecting digital content for inclusion in media presentations

1. A computer-implemented method for selecting digital content to be included in a media presentation, the method being executed using one or more processors and comprising:

receiving, by the one or more processors, items of digital content from one or more data sources associated with a user;

clustering, by the one or more processors, the items of digital content into a hierarchy of clusters, the hierarchy of clusters including moment clusters and scene clusters, individual moment clusters including two or more of the scene clusters, and individual scene clusters including one or more of the items of digital content;

determining, by the one or more processors, a goodness measure for each item of digital content within the individual scene clusters, the goodness measure indicating a quality of a respective item of digital content, the goodness measure being at least partially based on metadata associated with the respective item of digital content;

identifying, by the one or more processors, at least one item of digital content from the individual scene clusters based on the goodness measure;

selecting, by the one or more processors, a plurality of the identified items of digital content from the individual moment clusters for inclusion in the media presentation;

identifying, by the one or more processors, two or more of the selected items of digital content as redundant digital content based on overlap between the metadata associated with the respective item of digital content such that a first item of digital content is identified as being redundant of a second item of digital content based on overlap between the metadata associated with the first item of digital content and the metadata associated with the second item of digital content;

removing, by the one or more processors, an item of redundant digital content from inclusion in the media presentation based on the quality of the item of redundant digital content indicated by the goodness measure not being sufficiently high such that one of the first item of digital content and the second item of digital content is removed from inclusion in the media presentation based on a first goodness measure of the first item of digital content and a second goodness measure of the second item of digital content not exceeding a threshold goodness measure while both the first item of digital content and the second item of digital content are retained for inclusion in the media presentation based on the first goodness measure of the first item of digital content and the second goodness measure of the second item of digital content exceeding the threshold goodness measure, wherein the first goodness measure of the first item of digital content and the second goodness measure of the second item of digital content exceeding the threshold goodness measure indicates that the qualities of the first item of digital content and the second item of digital content are sufficiently high such that that removal of the item of redundant digital content from inclusion in the media presentation is not performed for the first item of digital content and the second item of digital content; and

providing, by the one or more processors, the media presentation for display on a computing device of the user, the media presentation comprising at least one selected item of digital content.

2. The method of claim 1 , wherein identifying two or more of the selected items of digital content as redundant digital content is performed based on one or more of an overlap in the metadata, and a difference in respective goodness measures.

3. The method of claim 1 , wherein the goodness measure is further determined based on content of the respective item of digital content.

4. The method of claim 1 , wherein the metadata comprises time, location, duration, keyword, and type.

5. The method of claim 1 , wherein items of digital content comprise images, videos or text.

6. The method of claim 1 , wherein at least one data source is associated with a computer-implemented service accessed by the user.

7. The method of claim 1 , wherein at least one data source comprises the computing device of the user.

8. The method of claim 1 , wherein the individual moment clusters correspond to a period of time, and the individual scene clusters correspond to a sub-period of time.

9. The method of claim 8 , wherein the period of time corresponding to the individual moment clusters is changed based on a number of items of digital content within one or more of the moment clusters.

10. The method of claim 1 , wherein the individual moment clusters correspond to a geographic area, and the individual scene clusters correspond to a sub-geographic area.

11. The method of claim 10 , wherein the geographic area corresponding to the individual moment clusters is changed based on a number of items of digital content within one or more of the moment clusters.

12. The method of claim 1 , wherein a number of items of digital content selected from the individual moment clusters for inclusion in the media presentation is based on sizes of the individual moment clusters.

13. The method of claim 1 , wherein metadata associated with the respective item of digital content includes values for brightness, contrast, color histogram, blur/sharpness, and/or number of human faces in the respective item of digital content, and the goodness measure for the respective item of digital content is determined based on the values for brightness, contrast, blur/sharpness, and/or number of human faces.

14. The method of claim 13 , wherein the goodness measure for the respective item of digital content is determined based on a weighted average of the values for brightness, contrast, blur/sharpness, and/or number of human faces.

15. The method of claim 1 , wherein the goodness measure for the respective item of digital content is set to a minimum value based on the metadata associated with the respective item of digital content not including any values for brightness, contrast, color histogram, blur/sharpness, or number of human faces in the respective item of digital content.

16. The method of claim 1 , wherein the respective item of digital content is removed from a respective cluster based on the metadata associated with the respective item of digital content not including any values for brightness, contrast, color histogram, blur/sharpness, or number of human faces in the respective item of digital content.

17. The method of claim 1 , wherein the two or more of the selected items of digital content are identified as redundant digital content based on the overlap between the metadata associated with the respective item of digital content exceeding a threshold overlap.

18. The method of claim 17 , wherein the two or more of the selected items of digital content are identified as redundant digital content further based on a difference in the goodness measure of the respective items of redundant digital content being less than a threshold difference.

19. A system comprising:

a data store for storing data; and

one or more processors configured to interact with the data store, the one or more processors being further configured to perform operations f comprising:

receiving items of digital content from one or more data sources associated with a user;

clustering the items of digital content into a hierarchy of clusters, the hierarchy of clusters including moment clusters and scene clusters, individual moment clusters including two or more of the scene clusters, and individual scene clusters including one or more of the items of digital content;

determining a goodness measure for each item of digital content within the individual scene clusters, the goodness measure indicating a quality of a respective item of digital content, the goodness measure being at least partially based on metadata associated with the respective item of digital content;

identifying at least one item of digital content from the individual scene clusters based on the goodness measure;

selecting a plurality of the identified items of digital content from the individual moment clusters for inclusion in the media presentation;

identifying two or more of the selected items of digital content as redundant digital content based on overlap between the metadata associated with the respective item of digital content such that a first item of digital content is identified as being redundant of a second item of digital content based on overlap between the metadata associated with the first item of digital content and the metadata associated with the second item of digital content;

removing an item of redundant digital content from inclusion in the media presentation based on the quality of the item of redundant digital content indicated by the goodness measure not being sufficiently high such that one of the first item of digital content and the second item of digital content is removed from inclusion in the media presentation based on a first goodness measure of the first item of digital content and a second goodness measure of the second item of digital content not exceeding a threshold goodness measure while both the first item of digital content and the second item of digital content are retained for inclusion in the media presentation based on the first goodness measure of the first item of digital content and the second goodness measure of the second item of digital content exceeding the threshold goodness measure, wherein the first goodness measure of the first item of digital content and the second goodness measure of the second item of digital content exceeding the threshold goodness measure indicates that the qualities of the first item of digital content and the second item of digital content are sufficiently high such that that removal of the item of redundant digital content from inclusion in the media presentation is not performed for the first item of digital content and the second item of digital content; and

providing the media presentation for display on a computing device of the user, the media presentation comprising at least one selected item of digital content.

20. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving items of digital content from one or more data sources associated with a user;

clustering the items of digital content into a hierarchy of clusters, the hierarchy of clusters including moment clusters and scene clusters, individual moment clusters including two or more of the scene clusters, and individual scene clusters including one or more of the items of digital content;

determining a goodness measure for each item of digital content within the individual scene clusters, the goodness measure indicating a quality of a respective item of digital content, the goodness measure being at least partially based on metadata associated with the respective item of digital content;

identifying at least one item of digital content from the individual scene clusters based on the goodness measure;

selecting a plurality of the identified items of digital content from the individual moment clusters for inclusion in the media presentation;

identifying two or more of the selected items of digital content as redundant digital content based on overlap between the metadata associated with the respective item of digital content such that a first item of digital content is identified as being redundant of a second item of digital content based on overlap between the metadata associated with the first item of digital content and the metadata associated with the second item of digital content;

removing an item of redundant digital content from inclusion in the media presentation based on the quality of the item of redundant digital content indicated by the goodness measure not being sufficiently high such that one of the first item of digital content and the second item of digital content is removed from inclusion in the media presentation based on a first goodness measure of the first item of digital content and a second goodness measure of the second item of digital content not exceeding a threshold goodness measure while both the first item of digital content and the second item of digital content are retained for inclusion in the media presentation based on the first goodness measure of the first item of digital content and the second goodness measure of the second item of digital content exceeding the threshold goodness measure, wherein the first goodness measure of the first item of digital content and the second goodness measure of the second item of digital content exceeding the threshold goodness measure indicates that the qualities of the first item of digital content and the second item of digital content are sufficiently high such that that removal of the item of redundant digital content from inclusion in the media presentation is not performed for the first item of digital content and the second item of digital content; and

providing the media presentation for display on a computing device of the user, the media presentation comprising at least one selected item of digital content.