AUTOMATED EVENT DETECTION AND PHOTO PRODUCT CREATION
A computer-implemented method for automatically detecting events and creating photo-product designs based on the events in a photo-product design system includes automatically identifying an event by an event detection module based on daily numbers of captured photos over a plurality of days, automatically selecting a photo-product type by an intelligent product design creation engine in the photo-product design system, calculating a daily weight for a photo product design in the photo-product type based on the daily numbers of captured photos, automatically determining a number of product photos allocated to each day based on associated daily weight, automatically selecting product photos from the captured photos each day at the event according to the number of product photos allocated to each day, and automatically creating a photo-product design for the event using the selected product photos.
1 - 20 . (canceled)
21 . A method for automatically detecting events and selecting images associated with the events, the method comprising:
identifying an event based at least in part on one or more properties of a plurality of images associated with the event;
selecting a photo-product type based at least in part on a number of images in the plurality of images;
selecting a plurality of product photos from the plurality of images based at least in part on information and analysis of the event, wherein the photo-product type defines a total number of product photos to be selected; and
causing a user device to display at least a portion of the plurality of product photos.
22 . The method of claim 21 , further comprising:
creating a photo-product design of the photo-product type comprising the plurality of product photos, wherein causing the user device to display at least the portion of the plurality of product photos comprises causing the user device to display the photo-product design.
23 . The method of claim 22 , further comprising:
receiving an edit input from the user device; and
editing the photo-product design based on the edit input.
24 . The method of claim 21 , further comprising selecting a product style and one or more product layouts for one or more pages of the photo-product type.
25 . The method of claim 24 , further comprising:
determining a type of the event based at least in part on any one of (i) geo location metadata of one or more of the plurality of images, (ii) a time of one or more of the plurality of images, (iii) face and object recognition in one or more of the plurality of images, or (iv) any combination of (i)-(iii), wherein selecting the product style is based at least in part on the type of the event.
26 . The method of claim 21 , further comprising, for each subset of a plurality of subsets of the plurality of images:
determining a subset weight based on a number of captured photos associated with the respective subset and a total number of the plurality of images;
determining a portion of the total number of product photos for the respective subset based on a multiplication of the subset weight and the total number of product photos; and
selecting product photos of the respective subset equivalent to the portion of the total number of product photos,
wherein the plurality of product photos comprises the product photos of each subset.
27 . The method of claim 26 , further comprising, for each subset of the plurality of subsets:
merging adjacent images into one or more scenes;
determining a scene weight for each of the one or more scenes based on a total number of captured photos in the one or more scenes; and
determining a percentage of the portion of the total number of product photos of the respective subset allocated to each of the one or more scenes based on the associated scene weight,
wherein selecting the product photos of the respective subset comprises selecting product photos for each of the one or more scenes according to the percentage of the portion of the total number of product photos allocated to each of the one or more scenes.
28 . The method of claim 21 , further comprising:
merging adjacent images of the plurality of images into one or more scenes;
determining a scene weight for each of the one or more scenes based on a total number of captured photos in the one or more scenes; and
determining a portion of the total number of product photos allocated to each of the one or more scenes based on the associated scene weight,
wherein selecting the plurality of product photos comprises selecting product photos for each of the one or more scenes according to the portion of the total number of product photos allocated to each of the one or more scenes.
29 . The method of claim 21 , further comprising:
calculating a ranking the plurality of images based at least in part on any one of (i) image quality, (ii) significance to a user, (iii) similarity between photos, (iv) social relevance, or (v) any combination of (i)-(iv),
wherein selecting the plurality of product photos is based at least in part on the ranking.
30 . The method of claim 21 , wherein the one or more properties of the plurality of images comprises any one of (i) a distribution of captured images over time, (ii) geo location metadata of one or more of the plurality of images, (iii) a time of one or more of the plurality of images, (iv) face and object recognition in one or more of the plurality of images, or (v) any combination of (i)-(iv).
31 . A system for automatically detecting events and selecting images associated with the events, comprising:
at least one processor; and
at least one memory coupled to the at least one processor and storing instructions that, when executed by the at least one processor, cause the system to:
identify an event based at least in part on one or more properties of a plurality of images associated with the event;
select a photo-product type based at least in part on a number of images in the plurality of images;
select a plurality of product photos from the plurality of images based on information and analysis of the event, wherein the photo-product type defines a total number of product photos to be selected; and
cause a display to display at least a portion of the plurality of product photos.
32 . The system of claim 31 , wherein the system is further caused to:
create a photo-product design of the photo-product type comprising the plurality of product photos, wherein to cause the display to display at least the portion of the plurality of product photos comprises causing the display to display the photo-product design.
33 . The system of claim 32 , wherein the system is further caused to:
receive an edit input; and
edit the photo-product design based on the edit input.
34 . The system of claim 31 , wherein the system is further caused to select a product style and one or more product layouts for one or more pages of the photo-product type.
35 . The system of claim 34 , wherein the system is further caused to:
determine a type of the event based at least in part on any one of (i) geo location metadata of one or more of the plurality of images, (ii) a time of one or more of the plurality of images, (iii) face and object recognition in one or more of the plurality of images, or (iv) any combination of (i)-(iii), wherein to select the product style is based at least in part on the type of the event.
36 . The system of claim 31 , wherein the system is further caused to, for each subset of a plurality of subsets of the plurality of images:
determine a subset weight based on a number of captured photos associated with the respective subset and a total number of the plurality of images;
determine a portion of the total number of product photos for the respective subset based on a multiplication of the subset weight and the total number of product photos; and
select product photos of the respective subset equivalent to the portion of the total number of product photos,
wherein the plurality of product photos comprises the product photos of each subset.
37 . The system of claim 36 , wherein the system is further caused to, for each subset of the plurality of subsets:
merge adjacent images into one or more scenes;
determine a scene weight for each of the one or more scenes based on a total number of captured photos in the one or more scenes; and
determine a percentage of the portion of the total number of product photos of the respective subset allocated to each of the one or more scenes based on the associated scene weight,
wherein to select the product photos of the respective subset comprises to select product photos for each of the one or more scenes according to the percentage of the portion of the total number of product photos allocated to each of the one or more scenes.
38 . The system of claim 31 , wherein the system is further caused to:
merge adjacent images of the plurality of images into one or more scenes;
determine a scene weight for each of the one or more scenes based on a total number of captured photos in the one or more scenes; and
determine a portion of the total number of product photos allocated to each of the one or more scenes based on the associated scene weight,
wherein to select the plurality of product photos comprises to select product photos for each of the one or more scenes according to the portion of the total number of product photos allocated to each of the one or more scenes.
39 . The system of claim 31 , wherein the system is further caused to:
calculate a ranking the plurality of images based at least in part on any one of (i) image quality, (ii) significance to a user, (iii) similarity between photos, (iv) social relevance, or (v) any combination of (i)-(iv),
wherein to select the plurality of product photos is based at least in part on the ranking.
40 . The system of claim 31 , wherein to select the plurality of product photos from the plurality of images is further based at least in part on social data.