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

• US 9,779,160 B2
• Filed: 03/15/2016
• Issued: 10/03/2017
• Est. Priority Date: 08/15/2014
• Status: Active Grant

• Current Assignee: Ask Sydney, LLC
• Original Assignee: Paul Lawrence Epstein, Sydney Nicole Epstein
• Inventors: Epstein, Sydney Nicole, Epstein, Paul Lawrence
• Primary Examiner(s): Pond, Rob
• Application Number:
  US15/070,371
• Publication Number:
  US 20160196337A1
• Time in Patent Office: 567 Days
• Field of Search: 705 26, 705 27
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences

Abstract

System and computer-implemented method of analyzing tags associated with a sequence of images presented to a user to present a current 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 interest.

Claims

1. A computer-implemented method for an improved iterative image search engine informed by continuous human-machine input feedback, the method comprising the steps of:

retrieving, using the computer, information in a user profile associated with a user operating a computer terminal;

retrieving, using a computer, a first set of digital images, each depicting a different image, and associated with a plurality of tags indicating one or more attributes of the image;

causing to be displayed on a video display device of or operatively coupled to the computer terminal, a first one of the digital images in the first set-based on a comparison between the tags associated with the first digital image and the information in the user profile, to initiate a search session; and

repeating, during the search session a plurality of times until the search session ends, the following steps of;

selecting a next image from the first set of digital images and causing the next image to be displayed on the video display device;

responsive to selecting the next image, receiving via a user input device one of at least two input options, the at least two input options including a favorable indication of a preference for an item or object depicted in the next image or an unfavorable indication of a disinclination for the item or object depicted in the next image;

analyzing, using the computer or another computer, the tags associated with the next image to determine a next set of tags that are required to be present in a subsequent image having at least a probable chance of being liked by the user,

wherein the determining the next set of tags is based on, responsive to the at least two input options selected via user input device being favorable, a weighting of tags to be included in the next set of tags;

ending the search session in response to (a) receiving an input via the user input device such that the next image displayed on the video display device is the final image of the search session, (b) the repeating occurring a predetermined number of times, or (c) there remain no further tags from the plurality of tags to select a subsequent image or there remain no further images from the first set of digital images to be presented to the user.

2. The method of claim 1, wherein the at least two input options further includes a neutral indication for the item or object depicted in the next image.

3. The method of claim 1, in response to the received input option being the unfavorable indication, the analysing the tags associated with the next image including removing at least one of the tags associated with the next image from the plurality of tags for the remainder of the search session.

4. The method of claim 1, wherein the first one of the digital images is randomly selected from the first set.

5. The method of claim 1, further comprising determining a location associated with the user operating the computer terminal, wherein the first one of the digital images is associated with the location.

6. The method of claim 1, further comprising logging each of the input options received via the user input device.

7. The method of claim 1, further comprising determining a location associated with the user operating the computer terminal and presenting, via the video display device, a list of physical entities proximate the location.

8. The method of claim 7, further comprising:

receiving via the user input device, an input by the user selecting one of the physical entities provided in the list; and

presenting, via the video display device, a user interface element displaying a profile associated with the selected physical entity.