Generic card feature extraction based on card rendering as an image

Patent metadata

Field	Value
Publication number	US-10318573-B2
Application number	US-201615190030-A
Country	US
Kind code	B2
Filing date	Jun 22, 2016
Priority date	Jun 22, 2016
Publication date	Jun 11, 2019
Grant date	Jun 11, 2019

Abstract

Methods and apparatus for using features of images representing content items to improve the presentation of the content items are disclosed. In one embodiment, a plurality of digital images are obtained, where each of the images represents a corresponding one of a plurality of content items. Image features of each of the digital images are determined. Additional features including at least one of user features pertaining to a user of a client device or contextual features pertaining to the client device are ascertained. At least a portion of the content items are provided via a network to the client device using features that include or are derived from both the image features of each of the plurality of digital images and the additional features.

First claim

What is claimed is:

1. A method, comprising:
obtaining, by one or more servers, a plurality of digital images, each one of the plurality of digital images representing a corresponding one of a plurality of content items;
determining, by one or more servers, one or more image features of each one of the plurality of digital images, the image features including at least one of facial features, gender, geographic features, or color;
ascertaining, by one or more servers, one or more additional features including one or more user features of a user of a client device;
selecting, by one or more servers, at least a portion of the plurality of content items using a computer-generated model based, at least in part, on features that include both the image features of each of the plurality of digital images and the additional features;
providing, by one or more servers, the portion of the plurality of content items via a network to the client device; and
responsive to receiving an indication of user interaction of the user with a content item of the portion of the plurality of content items provided via the network to the client device, updating, by one or more servers, the computer-generated model based, at least in part, on the image features of the corresponding one of the plurality of images that represents the content item.

2. The method of claim 1 , wherein determining image features of each one of the plurality of digital images comprises:
extracting the image features from the one of the plurality of digital images using digital image processing.

3. The method of claim 1 , wherein obtaining the plurality of digital images comprises:
generating, by the one or more servers, a digital image for one of the plurality of content items.

4. The method of claim 1 , wherein obtaining the plurality of digital images comprises:
retrieving a digital image for one of the plurality of content items from a database.

5. The method of claim 1 , further comprising:
ranking the plurality of content items using the computer-generated model based, at least in part, on the corresponding image features and the additional features;
wherein the at least a portion of the plurality of content items are provided based, at least in part, on the ranking.

6. The method of claim 1 , the features including display features, the method further comprising:
selecting, using the computer-generated model, the display features for at least one of the plurality of digital images based, at least in part, on the corresponding image features and the additional features; and
wherein providing the portion of the plurality of content items includes providing the one of the plurality of digital images according to the selected display features.

7. The method of claim 1 , wherein the additional features further comprise:
document features for at least a portion of the plurality of content items.

8. An apparatus, comprising:
at least one processor; and
at least one memory, at least one of the processor or the memory being configured to:
obtain a plurality of digital images, each one of the plurality of digital images representing a corresponding one of a plurality of content items;
determine image features of each one of the plurality of digital images, the image features including at least one of facial features, gender, geographic features, or color;
ascertain one or more additional features including one or more user features of a user of a client device;
select at least a portion of the plurality of content items using a computer-generated model based, at least in part, on features that include both the image features of each of the plurality of digital images and the additional features;
provide the portion of the plurality of content items via a network to the client device; and
responsive to receiving an indication of user interaction of the user with a content item of the portion of the plurality of content items provided via the network to the client device, update the computer-generated model based, at least in part, on the image features of the corresponding one of the plurality of images that represents the content item.

9. The apparatus of claim 8 , at least one of the processor or the memory being further configured to:
determine image features of one of the plurality of digital images by extracting image features from the one of the plurality of digital images using digital image processing.

10. The apparatus of claim 8 , wherein obtaining the plurality of digital images comprises:
generating a digital image for one of the plurality of content items.

11. The apparatus of claim 8 , wherein obtaining the plurality of digital images comprises:
retrieving a digital image for one of the plurality of content items from a database.

12. The apparatus of claim 8 , at least one of the processor or the memory being further configured to:
rank, using the computer-generated model, the plurality of content items based, at least in part, on the corresponding image features and the additional features;
wherein the at least a portion of the plurality of content items are provided based, at least in part, on the ranking.

13. The apparatus of claim 8 , at least one of the processor or the memory being further configured to:
select, using the computer-generated model, display features for at least one of the plurality of digital images based, at least in part, on the corresponding image features and the additional features;
wherein providing the portion of the plurality of content items includes providing the one of the plurality of digital images according to the selected display features.

14. A computer program product comprising one or more non-transitory computer-readable storage media storing thereon computer-readable instructions, the computer program instructions being configured such that, when executed by one or more processors, the computer program instructions cause the one or more processors to:
obtain a plurality of digital images, each one of the plurality of digital images representing a corresponding one of a plurality of content items;
determine image features of each one of the plurality of digital images, the image features including at least one of facial features, hair, gender, geographic features, or color;
ascertain one or more additional features including one or more user features of a user of a client device;
select at least a portion of the plurality of content items using a computer-generated model based, at least in part, on features that include both the image features of each of the plurality of digital images and the additional features;
provide the portion of the plurality of content items via a network to the client device; and
responsive to receiving an indication of user interaction of the user with a content item of the portion of the plurality of content items provided via the network to the client device, update the computer-generated model based, at least in part, on the image features of the corresponding one of the plurality of images that represents the content item.

15. The computer program product of claim 14 , wherein the computer program instructions are further configured to cause the one or more processors to:
determine image features of one of the plurality of digital images by extracting the image features from the one of the plurality of digital images using digital image processing.

16. The computer program product of claim 14 , wherein the computer program instructions are further configured to cause the one or more processors to:
generate at l

Assignees

• Yahoo Inc
• Oath Inc

Inventors

• Golbandi Nadav
• Schonfeld Uri

Classifications

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/58

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/532 Primary

  Query formulation, e.g. graphical querying · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title

• G06V10/235

  based on user input or interaction · CPC title