Promoting representations of items to users on behalf of sellers of those items

Abstract

This disclosure describes systems and methods for establishing promotions for sellers and promoting images of items to users on behalf of sellers. A management service receives a source location identifier from a seller, processes images stored in an image data store to determine images that include the source location identifier in the corresponding image information and includes those images in a promotion that is established for the seller. Likewise, the management service may determine users that have previously interacted with the images and include those users in the promotion campaign.

1 . (canceled) 
     
     
         2 . A computer-implemented method, comprising:
 receiving a promotion information corresponding to a seller and associated with an item;   processing a first plurality of images using one or more image processing algorithms to determine a first respective object represented in each of the first plurality of images;   comparing first characteristics of each first respective object represented in each of the first plurality of images to second characteristics associated with a plurality of item categories to determine an item category from the plurality of item categories that corresponds to each first respective object;   determining a second plurality of images from the first plurality of images that includes a same item category as the item associated with the promotion information and a first plurality of image information, wherein each of the first plurality of image information includes at least one of a first plurality of feature vectors or a first histogram associated with a respective second image from the second plurality of images;   comparing at least a portion of the first plurality of image information with second image information associated with the item associated with the promotion information to determine a third plurality of images from the second plurality of images that includes a similarity score indicating that the third plurality of images correspond to the item associated with the promotion information, wherein the second image information includes at least one of a second plurality of feature vectors or a second histogram associated with the item;   storing an association in a mapping data store for each of the third plurality of images and the promotion information; and   establishing a promotion campaign based at least in part on the promotion information and the third plurality of images.   
     
     
         3 . The computer-implemented method of  claim 2 , further comprising:
 determining a first user that interacted with at least one image of the third plurality of images; and   including the first user in the promotion campaign.   
     
     
         4 . The computer-implemented method of  claim 3 , further comprising:
 causing, for presentation to the first user, the at least one image to be transmitted to the first user as part of the promotion campaign; and   causing a purchase control that may be selected by the first user to initiate purchase of the item to be presented with the at least one image.   
     
     
         5 . The computer-implemented method of  claim 3 , further comprising:
 determining a secondary image that includes a representation of the item; and   causing, for presentation to the first user, the secondary image to be transmitted to the first user as part of the promotion campaign.   
     
     
         6 . The computer-implemented method of  claim 3 , further comprising:
 determining that an elapsed time since the first user interacted with the at least one image exceeds a threshold time.   
     
     
         7 . A computing system, comprising:
 one or more processors; and   a memory coupled to the one or more processors and storing program instructions that, when executed by the one or more processors, cause the one or more processors to at least:
 receive promotion information corresponding to a promotional campaign associated with a seller; 
 determine, based at least in part on the promotion information and first image information associated with a first plurality of images, that a second plurality of images of the first plurality of images correspond to the promotional campaign associated with the seller; 
 determine, based at least in part on the second plurality of images, a first plurality of users from a corpus of users to be included in the promotional campaign; and 
 establish the promotional campaign to the first plurality of users. 
   
     
     
         8 . The computing system of  claim 7 , wherein determination that the second plurality of images correspond to the promotional campaign associated with the seller includes:
 determining that respective second image information associated with each image of the second plurality of images includes a first source location identifier that corresponds to a second source location identifier associated with the promotional campaign.   
     
     
         9 . The computing system of  claim 7 , wherein:
 the first image information includes at least one of a feature vector or a histogram associated with each image of the first plurality of images; and   determination that the second plurality of images correspond to the promotional campaign associated with the seller includes:
 comparing the first image information, including at least one of the feature vectors or the histograms, to an item associated with the promotional campaign associated with the seller; and 
 determining the second plurality of images from the first plurality of images based at least in part on similarities of objects represented in the first plurality of images with the item. 
   
     
     
         10 . The computing system of  claim 9 , wherein:
 determination that the second plurality of images correspond to the promotional campaign associated with the seller further includes:
 determining a respective item category for each object represented in the first plurality of images; and 
 identifying, based on the respective item categories, a third plurality of images from the first plurality of images that include representations of objects having a same item category as the item; and 
   comparison of the first image information to the item associated with the promotional campaign includes a comparison of the first image information that is associated with the third plurality of images.   
     
     
         11 . The computing system of  claim 7 , wherein determination of the first plurality of users includes determining that each user of the first plurality of users interacted with at least one image of the second plurality of images. 
     
     
         12 . The computing system of  claim 11 , wherein determination of the first plurality of users includes determining that a respective time elapsed associated with each user of the first plurality of users that indicates a time since each user interacted with the at least one image of the second plurality of images exceeds a threshold time. 
     
     
         13 . The computing system of  claim 11 , wherein the program instructions that, when executed by the one or more processors, further cause the one or more processors to at least:
 cause, for presentation to the first user, the at least one image to be transmitted to the first user as part of the promotional campaign; and   cause a purchase control that may be selected by the first user to initiate purchase of an item represented in the at least one image to be presented with the at least one image.   
     
     
         14 . The computing system of  claim 11 , wherein the program instructions that, when executed by the one or more processors, further cause the one or more processors to at least:
 determine, for a first user of the first plurality of users and based at least in part on a user history associated with the first user, a secondary image that includes a representation of the item;   cause, for presentation to the first user, the secondary image to be transmitted to the first user as part of the promotional campaign; and   cause a purchase control that may be selected by the first user to initiate purchase of an item represented in the secondary image to be presented with the secondary image.   
     
     
         15 . The computing system of  claim 7 , wherein the first plurality of images are user-supplied images from users that are independent of the seller. 
     
     
         16 . A computer-implemented method, comprising:
 determining, based at least in part on promotion information corresponding to a promotional campaign and first image information associated with a first plurality of images, that a second plurality of images of the first plurality of images is associated with the promotional campaign, wherein:
 the promotional campaign is associated with a seller and a promotional item; and 
 determination of the second plurality of images includes at least one of:
 determining that second image information associated with the second plurality of images includes a first source location identifier that corresponds to a second source location identifier associated with the promotional campaign to determine the second plurality of images; or 
 comparing at least one of a plurality of feature vectors or a plurality of histograms included in the first image information and associated with the first plurality of images to item information associated with the promotional item to determine the second plurality of images based at least in part on a visual similarity between the first plurality of images and the promotional item; 
 
   storing an association in a mapping data store for each of the second plurality of images and the promotion information; and   establishing the promotional campaign based at least in part on the promotion information and the second plurality of images.   
     
     
         17 . The computer-implemented method of  claim 16 , further comprising:
 determining a respective item category for each object represented in the first plurality of images; and   identifying, based on the respective item categories, a third plurality of images from the first plurality of images that include representations of objects having a same item category as the promotional item,   wherein:
 determination of the second plurality of images includes comparing the at least one of the plurality of feature vectors or the plurality of histograms included in the first image information and associated with the first plurality of images to item information associated with the promotional item; and 
 comparison of the at least one of the plurality of feature vectors or the plurality of histograms to the item information associated with the promotional item includes comparison of at least one of the plurality of feature vectors or the plurality of histograms that is associated with the third plurality of images. 
   
     
     
         18 . The computer-implemented method of  claim 16 , further comprising:
 determining a first plurality of users interacted with at least one image of the second plurality of images; and   associating the first plurality of users with the promotional campaign.   
     
     
         19 . The computer-implemented method of  claim 18 , further comprising:
 causing the at least one image to be presented to a first user of the first plurality of users as part of the promotional campaign; and   causing a purchase control that may be selected by the first user to initiate purchase of the promotional item represented in the at least one image to be presented with the at least one image.   
     
     
         20 . The computer-implemented method of  claim 18 , further comprising:
 determining, for a first user of the first plurality of users and based at least in part on a user history associated with the first user, a secondary image that includes a representation of the promotional item;   causing the secondary image to be presented to the first user as part of the promotional campaign; and   causing a purchase control that may be selected by the first user to initiate purchase of the promotional item represented in the secondary image to be presented with the secondary image.   
     
     
         21 . The computer-implemented method of  claim 16 , wherein the first plurality of images are user-supplied images from users that are independent of the seller.