IDENTIFYING DATA FROM KEYWORD SEARCHES OF COLOR PALETTES AND KEYWORD TRENDS

• US 20150379004A1
• Filed: 06/26/2014
• Published: 12/31/2015
• Est. Priority Date: 06/26/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Sayre, Paul Barnhart III, Dorner, Charles Shearer, Blackburn, Jenny Ann, Ong, Timothy Andrew
• Granted Patent: US 9,792,303 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/54 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

Systems and methods are described herein to determine data associated with keyword searches of color palettes based at least in part on keyword trends. A keyword trend may include popular colors of color palettes associated with the keyword. Color palettes may be searched by name or other data associated with the color palettes. Furthermore, color palettes associated with a keyword may be filtered by color trends and/or keyword trends. The items and/or images associated with the filtered color palettes may be identified and presented to a user.

Claims

1. A system comprising:

a data store configured to store at least a plurality of color palettes and a plurality of images, wherein each color palette of the plurality of color palettes comprises a name and a plurality of colors, and wherein each image of the plurality of images comprises one or more colors; and

a hardware processor in communication with the data store, the hardware processor configured to execute computer-executable instructions to at least;

receive a search phrase;

determine a first subset of the plurality of color palettes associated with the search phrase based at least in part on the names of the first subset of the plurality of color palettes, wherein the first subset of the plurality of color palettes are associated with a first time;

determine a second subset of the plurality of color palettes associated with the search phrase based at least in part on the names of the first subset of the plurality of color palettes, wherein the second subset of the plurality of color palettes are associated with a second time;

determine a color trend based at least in part on the first subset of the plurality of color palettes and the second subset of the plurality of color palettes;

update the second subset of the plurality of color palettes based at least in part on the determined color trend, wherein updating includes at least one of;

removing at least one color palette from the second subset of the plurality of color palettes or adding at least one color palette to the second subset of the plurality of color palettes;

identify, for each color of the plurality of colors of the updated second subset of the plurality of color palettes, an image matching the color; and

provide at least some of the identified images for presentation.

2. The system of claim 1, wherein the color trend comprises at least one popular color of the second subset of the plurality of color palettes associated with the second time.

3. The system of claim 1, wherein the color trend comprises at least one of a darker color trend or lighter color trend.

4. The system of claim 1, wherein the search phrase is based at least in part on user input.

5. The system of claim 1, wherein at least one color palette of the plurality of color palettes comprises human generated data.

6. The system of claim 1, wherein the hardware processor is further configured to execute computer-executable instructions to at least determine, for each color of the plurality of colors of the updated second subset of the plurality of color palettes, one or more color names.

7. A computer-implemented method comprising:

under control of a hardware computing device configured with specific computer-executable instructions,

receiving a search phrase;

determining a color trend based at least in part on the search phrase;

determining a plurality of color palettes associated with the search phrase based at least in part on names of the plurality of color palettes, wherein each color palette of the plurality of color palettes comprises one or more colors;

updating the plurality of color palettes based at least in part on the determined color trend, wherein updating the plurality of color palettes includes at least one of removing at least one color palette from the plurality of color palettes or adding at least one color palette to the plurality of color palettes; and

identifying, for each color of the plurality of colors of the updated plurality of color palettes, an image corresponding to the color.

8. The computer-implemented method of claim 7, wherein the color trend comprises at least one popular color of the plurality of color palettes.

9. The computer-implemented method of claim 7, wherein the color trend comprises at least one of a lighter color trend or darker color trend.

10. The computer-implemented method of claim 7, wherein the search phrase is based at least in part on user input.

11. The computer-implemented method of claim 7, wherein at least one color palette of the plurality of color palettes comprises human generated data.

12. The computer-implemented method of claim 7, wherein determining the color trend is further based at least in part on geolocation data associated with the search phrase.

13. The computer-implemented method of claim 7, wherein determining the color trend is further based at least in part on a cyclical color palette trend associated with the search phrase.

14. The computer-implemented method of claim 7, wherein determining the color trend is further based at least in part on purchase data of a plurality of items associated with the search phrase, and wherein each item of the plurality of items is associated with an item image comprising one or more colors.

15. A non-transitory computer-readable storage medium storing computer executable instructions that when executed by a processor perform operations comprising:

receiving a search phrase;

determining a color trend based at least in part on the search phrase;

determining a plurality of color palettes associated with the search phrase based at least in part on names of the plurality of color palettes, wherein each color palette of the plurality of color palettes comprises one or more colors, and wherein determining the plurality of color palettes is further based at least in part on the color trend; and

identifying, for each color of the plurality of colors of the updated plurality of color palettes, an image corresponding to the color.

16. The non-transitory computer-readable storage medium of claim 15, wherein determining the color trend is further based at least in part on purchase data associated with a plurality of items associated with the search phrase, and wherein each item of the plurality of items is associated with an item image comprising one or more colors.

17. The non-transitory computer-readable storage medium of claim 15, wherein the color trend is based at least in part on a first set of color palettes associated with the search phrase at a first time and a second set of color palettes associated with the search phrase at a second time.

18. The non-transitory computer-readable storage medium of claim 15, wherein the search phrase is based at least in part on user input.

19. The non-transitory computer-readable storage medium of claim 15, wherein at least one color palette of the plurality of color palettes comprises human generated data.

20. The non-transitory computer-readable storage medium of claim 15, wherein determining the color trend is further based at least in part on geolocation data associated with the search phrase.