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

A computer-implemented method comprising:

• receiving, from an electronic device associated with a user, an indication of an instance of an application executed on the electronic device, wherein the application, together with one or more computer devices, is configured to direct the user to a current interest of the user;
• causing a presentation on a display of the electronic device of one or more first electronic images, from among a plurality of electronic images stored on the one or more computer devices, 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 one or more possible interests of the user;
• processing, by the one or more computer devices, at least a subset of the pool of tags to determine a first potential set of tags corresponding to a positive preference from the user for at least one corresponding interest represented by at least one of the one or more first electronic images and a second potential set of tags corresponding to a negative preference from the user for at least corresponding interest represented by at least one of the one or more first electronic images, prior to receiving an input from the user indicating a preference for the one or more first electronic images, the processing comprising:
• determining weighting of tags from the at least the subset of the pool of tags based, at least in part, on a number of times each tag of the tags from the at least the subset of the pool of tags is associated with at least one of a positive preference or a negative preference by the user, the each tag of the tags from the at least the subset of the pool of tags being associated with at least one positive preference and at least one negative preference by the user;
• and
• determining the one or more next set of tags based on the one or more next set of tags including at least one tag of the tags from the at least the subset of the pool of tags, wherein the one or more next set of tags includes a highest weighted tag from the at least the subset of the pool of tags;
• transmitting, from the one or more computer devices, at least one first potential electronic image and at least one second potential electronic image, prior to receiving the input, the at least one first potential electronic image being associated with the first potential set of tags and the at least one second potential electronic image being associated with the second potential set of tags;
• receiving, from the electronic device, the input from the user;
• causing, by the one or more computer devices, a presentation of the at least one first potential electronic image or the at least one second potential electronic image based on the preference for the one or more first electronic images being the positive preference or the negative preference;
• and
• generating a sequence of electronic images presented to the user on the display of the electronic device by repeating the processing, the transmitting, the receiving the input from the user, and the causing of the presentation of the at least one first potential electronic image or the at least one second potential electronic image in place of the one or more first electronic images a plurality of times during a session of the instance of the application executed on the electronic device until the user indicates the at least one first potential electronic image or the at least one second potential electronic image is the current interest of the user.