Iterative image search algorithm informed by continuous human-machine input feedback

Abstract

System and computer-implemented image search engine of analyzing tags associated with a sequence of images presented to a user to present a current object of interest of the user is disclosed. An image from among a plurality of images is presented on an electronic display. The image is associated with a set of tags. An input is received indicating a user's preference for the image. A plurality of tags is processed based on the preference and the set of tags to determine a next set of tags from the plurality of tags. A next image is determined from the plurality of images based on the next set of tags. The next image represents a physical object, different from a physical object represented by the previous image. A sequence of images is generated by repeating the above process with the next image in place of the previous image for present a user's current object of interest.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 transmitting, from one or more computer devices, one or more first electronic images, from among a plurality of electronic images stored on the one or more computer devices, to an electronic device associated with a user, each electronic image of the one or more first electronic images representing one or more first possible interests of the user and being associated with a corresponding set of tags from a pool of tags, each tag of the pool of tags representing an attribute of the one or more first possible interests of the user;   receiving, by the one or more computer devices, an input from the user indicating one or more preferences for the one or more first possible interests represented by the one or more first electronic images;   processing, by the one or more computer devices, at least a subset of the pool of tags based on the one or more preferences and the corresponding set(s) of tags for the one or more first electronic images to generate one or more next set of tags;   determining, by the one or more computer devices, one or more next electronic images from the plurality of electronic images associated with the one or more next set of tags, the one or more next images representing one or more next possible interests of the user, different from the one or more first possible interests, and the one or more next set of tags describing or characterizing attributes of the one or more next possible interests represented by the one or more next electronic images; and   generating a sequence by repeating the transmitting, the receiving, the processing, and the determining with the one or more next electronic images in place of the one or more first electronic images during a session of determining a current interest of the user.