Generating personalized banner images using machine learning

Patent metadata

Field	Value
Publication number	US-12086840-B2
Application number	US-202218055273-A
Country	US
Kind code	B2
Filing date	Nov 14, 2022
Priority date	Oct 9, 2018
Publication date	Sep 10, 2024
Grant date	Sep 10, 2024

Abstract

A machine is configured to generate in real time personalized online banner images for users based on data pertaining to user behavior in relation to an image of a product. For example, the machine receives a user selection indicating one or more data features associated with the user. The one or more data features include a data feature pertaining to user behavior in relation to an image of a product. The machine generates, using a machine learning algorithm, a data representation of the machine learning algorithm based on the one or more data features including the data feature pertaining to user behavior in relation to the image of the product. The data representation includes one or more data features pertaining to one or more characteristics of online banner images. The machine generates an online banner image for the user based on the data representation.

First claim

What is claimed is:

1. A system comprising:
one or more computing devices having one or more processors; and
a machine-readable medium storing instructions that, when executed by the one or more processors, cause the one or more computing devices to perform operations comprising:
monitoring a plurality of user responses to a plurality of online banner images, each online banner image of the plurality of online banner images associated with a different set of structural elements of a plurality of structural elements;
training, based at least in part on a ranking of the plurality of online banner images in accordance with a quantity of user selections of each respective online banner image of the plurality of banner images and based at least partially upon segmenting a user population from the plurality of user responses, a machine learning model to identify a first set of structural elements from the plurality of structural elements, the first set of structural elements associated with a desired user behavior, the desired user behavior selected from clicks on one or more of the plurality of online banner images or a purchase corresponding to one or more of the plurality of online banner images;
generating, using the first set of structural elements, a first online banner image for a listing for a product, the first online banner image including a product image that is selectable to cause display of a product listing; and
causing presentation, by a client device, of the first online banner image.

2. The system of claim 1 , wherein the operations to train the machine learning model further comprise:
training the machine learning model to identify the first set of structural elements based at least in part on demographic data, geographic data, profession data, or any combination thereof.

3. The system of claim 1 , wherein the desired user behavior includes clicks on one or more of the plurality of online banner images and a purchase corresponding to one or more of the plurality of online banner images.

4. The system of claim 1 , wherein the operations to train the machine learning model further comprise:
training the machine learning model to identify the first set of structural elements that are a color, a size, a text font, or any combination thereof, associated with the desired user behavior.

5. The system of claim 1 , wherein the causing presentation, by a client device, of the first online banner image is part of an iterative process of presenting banner images.

6. The system of claim 1 , wherein the product listing that is selectable to cause information about the product to be displayed.

7. A computer-implemented method comprising:
monitoring, using one or more processors, a plurality of user responses to a plurality of online banner images, each online banner image of the plurality of online banner images associated with a different set of structural elements of a plurality of structural elements;
training, using the one or more processors, based at least in part on a ranking of the plurality of online banner images in accordance with a quantity of user selections of each respective online banner image of the plurality of banner images and based at least partially upon segmenting a user population from the plurality of user responses, a machine learning model to identify a first set of structural elements from the plurality of structural elements, the first set of structural elements associated with a desired user behavior, the desired user behavior being selected from clicks on one or more of the plurality of online banner images or a purchase corresponding to one or more of the plurality of online banner images;
generating, using the first set of structural elements, a first online banner image for a listing for a product, the first online banner image including a product image that is selectable to cause display of a product listing; and
causing presentation, by a client device, of the first online banner image.

8. The computer-implemented method of claim 7 , wherein training the machine learning model further comprises:
training the machine learning model to identify the first set of structural elements that are associated with the desired user behavior that is user clicks on one or more of the plurality of online banner images.

9. The computer-implemented method of claim 7 , wherein training the machine learning model further comprises:
training the machine learning model to identify the first set of structural elements based at least in part on demographic data, geographic data, profession data, or any combination thereof.

10. The computer-implemented method of claim 7 , wherein the desired user behavior includes clicks on one or more of the plurality of online banner images and a purchase corresponding to one or more of the plurality of online banner images.

11. The computer-implemented method of claim 7 , wherein training the machine learning model further comprises:
training the machine learning model to identify the first set of structural elements that are a color, a size, a text font, or any combination thereof, associated with the desired user behavior.

12. The computer-implemented method of claim 7 , wherein training the machine learning model further comprises:
training the machine learning model to identify the first set of structural elements that indicate a position within an online banner image to place a product that is associated with the desired user behavior.

13. The computer-implemented method of claim 7 , wherein the causing presentation, by the client device, of the first online banner image is part of an iterative process of presenting banner images.

14. The computer-implemented method of claim 7 , wherein the product listing is selectable to cause information about the product to be displayed.

15. A non-transitory computer-readable medium storing code, the code comprising instructions executable by one or more processors to cause a system to:
monitor, using the one or more processors, a plurality of user responses to a plurality of online banner images, each online banner image of the plurality of online banner images associated with a different set of structural elements of a plurality of structural elements;
train, using the one or more processors, based at least in part on a ranking of the plurality of online banner images in accordance with a quantity of user selections of each respective online banner image of the plurality of banner images and based at least partially upon segmenting a user population from the plurality of user responses, a machine learning model to identify a first set of structural elements from the plurality of structural elements, the first set of structural elements associated with a desired user behavior, the desired user behavior being selected from clicks on one or more of the plurality of online banner images or a purchase corresponding to one or more of the plurality of online banner images;
generate, using the first set of structural elements, a first online banner image for a listing for a product, the first online banner image including a product image that is selectable to cause display of a product listing; and
cause presentation, by a client device, of the first online banner image.

16. The non-transitory computer-readable medium of claim 15 , wherein the instructions to train the machine learning model are further executable by the one or more processors to cause the system to:
train the machine learning model to identify the first set of structural elements based at least in part on demographic data, geogr

Assignees

• Ebay Inc

Inventors

• Zheng Shuai
• Kiapour Mohammadhadi
• Ramakrishnan Nandini
• Boudet Christophe
• Zaw Jr Fred Aye

Classifications

• G06Q30/0277

  Online advertisement · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G06F40/186

  Templates · CPC title

• G06N20/00

  Machine learning · CPC title

• G06Q30/0276 Primary

  Advertisement creation · CPC title