Image evaluation

Patent metadata

Field	Value
Publication number	US-11449719-B2
Application number	US-201816225338-A
Country	US
Kind code	B2
Filing date	Dec 19, 2018
Priority date	Apr 4, 2014
Publication date	Sep 20, 2022
Grant date	Sep 20, 2022

Abstract

A machine may be configured to perform image evaluation of images depicting items for sale and to provide recommendations for improving the images depicting the items to increase the sales of the items depicted in the images. For example, the machine accesses a result of a user behavior analysis. The machine receives an image of an item from a user device. The machine performs an image evaluation of the received image based on an analysis of the received image and the result of the user behavior analysis. The performing of the image evaluation may include determining a likelihood of a user engaging in a desired user behavior in relation to the received image. Then, the machine generates, based on the evaluation of the received image, an output that references the received image and indicates the likelihood of a user engaging in the desired behavior.

First claim

What is claimed is:

1. A system comprising:
a non-transitory machine-readable medium for storing instructions that, when executed by one or more hardware processors of a machine, cause the one or more hardware processors to perform operations comprising:
receiving an image of an item from a client device, the item to be included in a publication published by a web server of a publication system;
extracting one or more visual features from the received image;
determining that the item included in the received image is of a particular type of item based on the extracted one or more visual features;
accessing user behavior data pertaining to interactions by a plurality of users with a plurality of test images pertaining to the particular type of item;
identifying an image attribute of the received image;
generating a suggestion to improve the image attribute based on the particular type of item;
generating, based on determining that the item included in the received image is of the particular type of item, a recommendation comprising a recommended presentation type for the item for publication based on the particular type of item and results of an analysis performed on the interactions by the plurality of users, the recommended presentation type indicating a style in which the item is displayed within the publication published by the web server of the publication system, wherein the recommendation includes the suggestion; and
providing the recommendation to the client device.

2. The system of claim 1 , wherein the particular type of item corresponds to a clothing category,
wherein the style comprises one of a flat presentation, a mannequin presentation, and a person presentation, and
wherein the recommendation of the recommended presentation type for the clothing category is based on a user behavior analysis for the clothing category, the user behavior analysis comprising an analysis of displayed items, clicked items, and unclicked items for each style.

3. The system of claim 1 , wherein the operations further comprise:
storing the results of the analysis performed on the interactions in a database.

4. The system of claim 1 , wherein the operations further comprise:
generating, based on determining that the item included in the received image is of the particular type of item, an output for display in the client device, the output including a reference to the received image and the recommended presentation type for the item included in the received image of the item based on results of analysis of interactions of the system with other client devices.

5. The system of claim 4 , wherein the recommended presentation type corresponds to an attribute-value pair of one or more attribute-value pairs associated with one or more images of the plurality of test images corresponding to a user behavior, and wherein the operations further comprise:
determining, for the received image, a likelihood of a user engaging in the user behavior in relation to the received image based on one of the one or more attribute-value pairs associated with the received image.

6. The system of claim 1 , wherein the operations further comprise: determining a likelihood of a user engaging in a user behavior based on a publication, by the web server of the publication system, of an image of the particular type of item using the recommended presentation type, wherein the recommendation further includes a reference to the likelihood of a user engaging in the user behavior.

7. The system of claim 1 , wherein the operations further comprise:
performing an evaluation of the received image based on an image analysis of the received image, the image analysis including identifying one or more image attributes and one or more values that correspond to the one or more image attributes, the one or more image attributes comprising at least one of an image quality attribute and a display type attribute, the display type attribute indicating a visual context in which the item is displayed.

8. The system of claim 7 , wherein the determining that the item included in the received image is of the particular type of item includes classifying the received image into a category based on the one or more image attributes and the one or more values that correspond to the one or more image attributes.

9. The system of claim 8 , wherein the recommendation includes a suggestion of an action pertaining to the received image to increase a likelihood of a user engaging in a user behavior.

10. A method comprising:
receiving an image of an item from a client device, the item to be included in a publication published by a web server of a publication system;
extracting, by one or more processors, one or more visual features from the received image;
determining, by the one or more processors, that the item included in the received image is of a particular type of item based on the extracted one or more visual features;
accessing user behavior data pertaining to interactions by a plurality of users with a plurality of test images pertaining to the particular type of item;
identifying an image attribute of the received image;
generating, by the one or more processors, a suggestion to improve the image attribute based on the particular type of item;
generating, based on determining that the item included in the received image is of the particular type of item, a recommendation comprising a recommended presentation type for the item for publication based on the particular type of item and results of an analysis performed on the interactions by the plurality of users, the recommended presentation type indicating a style in which the item is displayed within the publication published by the web server of the publication system, wherein the recommendation includes the suggestion; and
providing, by the one or more processors, the recommendation to the client device.

11. The method of claim 10 , wherein the particular type of item corresponds to a clothing category,
wherein the style comprises one of a flat presentation, a mannequin presentation, and a person presentation, and
wherein the recommendation of the recommended presentation type for the clothing category is based on a user behavior analysis for the clothing category, the user behavior analysis comprising an analysis of displayed items, clicked items, and unclicked items for each style.

12. The method of claim 10 , further comprising:
storing the results of the analysis performed on the interactions in a database.

13. The method of claim 10 , further comprising:
generating, based on determining that the item included in the received image is of the particular type of item, an output for display in the client device, the output including a reference to the received image and the recommended presentation type for the item included in the received image of the item based on results of analysis of interactions of the system with other client devices.

14. The method of claim 13 , wherein the recommended presentation type corresponds to an attribute-value pair of one or more attribute-value pairs associated with one or more images of the plurality of test images corresponding to the user behavior data, the method further comprising:
determining, for the received image, a likelihood of a user engaging in the user behavior in relation to the received image based on one of the one or more attribute-value pairs associated with the received image.

15. The method of claim 10 , further comprising:
determining a likelihood of a user engaging in a user behavior based on a publication, by the web server of the publ

Assignees

• Ebay Inc

Inventors

• Di Wei
• Jagadeesh Vignesh
• Piramuthu Robinson
• Churchill Elizabeth
• Bhardwaj Anurag

Classifications

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title

• G06Q30/0201 Primary

  Market modelling; Market analysis; Collecting market data · CPC title

• G06F18/24 Primary

  Classification techniques · CPC title

• G06F16/60

  of audio data · CPC title

• G06F16/63

  Querying · CPC title