Systems and methods for automated content generation

Patent metadata

Field	Value
Publication number	US-10235349-B2
Application number	US-201815921958-A
Country	US
Kind code	B2
Filing date	Mar 15, 2018
Priority date	Feb 22, 2013
Publication date	Mar 19, 2019
Grant date	Mar 19, 2019

Abstract

A computerized method for automatically generating display content includes receiving a uniform resource locator, wherein the uniform resource locator specifies a landing resource and extracting visual information from the landing resource, wherein the visual information defines one or more images, texts, and colors displayed on the landing resource. The method further includes selecting one or more images, one or more text snippets, and one or more colors based on the visual information extracted from the landing resource, generating a layout for a content item based on one or more of the selected images or selected text snippets, and assembling the content item by applying the selected images, the selected text snippets, and the selected colors to the generated layout.

First claim

What is claimed is:

1. A method for generating a layout for a content item, the method comprising:
obtaining a plurality of images and a plurality of text snippets;
creating, by one or more processors, a frame for the content item;
calculating automatically, by the one or more processors, a score for each of the plurality of images based on a value proportional to a distance between a center of the respective image and a horizontal center of a landing resource;
selecting, by the one or more processors, an image of the plurality of images having a highest score;
placing, by the one or more processors, the selected image having the highest score in a starting location within the frame of the content item;
dividing, by the one or more processors, a remaining unused space within the frame into a plurality of rectangles, at least one of the plurality of rectangles having a dimension corresponding to a dimension of the placed image;
combining, by the one or more processors, two or more rectangles of the plurality of rectangles in the remaining unused space to create a combined rectangle having a dimension accommodating a dimension of an unplaced image or text snippet of the obtained images and text snippets; and
placing, by the one or more processors, the unplaced image or text snippet into the combined rectangle.

2. The method of claim 1 , wherein combining the two or more rectangles further comprises:
combining a first rectangle that is either horizontally adjacent or vertically adjacent to the location of the placed image with a second rectangle that is diagonally adjacent to the location of the placed image.

3. The method of claim 1 , wherein obtaining the plurality of images and the plurality of text snippets further comprises:
receiving a uniform resource locator specifying a landing resource; and
extracting the plurality of images and the plurality of text snippets from the landing resource.

4. The method of claim 3 , wherein extracting the plurality of images and the plurality of text snippets from the landing resource further comprises rendering the landing resource and generating a document object model tree based on the rendered resource.

5. The method of claim 1 , wherein obtaining the plurality of images and the plurality of text snippets further comprises retrieving the plurality of images and the plurality of text snippets from a database.

6. The method of claim 1 , wherein each of the plurality of images has respective associated metadata, and wherein calculating the score of each of the plurality of images further comprises calculating each score based on predetermined scores corresponding to each keyword in the metadata associated with the respective image.

7. The method of claim 6 , wherein the metadata includes at least one of a URL, a display position, a display size, or alt text.

8. The method of claim 1 , wherein calculating the score of each of the plurality of images further comprises calculating each score based on a display size of the respective image and a vertical placement of the respective image on a landing resource.

9. The method of claim 1 , wherein placing the unplaced image or text snippet into the combined rectangle further comprises:
resizing the unplaced image or text snippet to fit the combined rectangle.

10. A system for generating a layout for a content item, the system comprising:
an image extractor, executed by a processor of a computing device, configured to obtain a plurality of images and a plurality of text snippets; and
a layout module, executed by the processor, configured to:
create a frame for the content item,
calculate automatically a score for each of the plurality of images based on a value proportional to a distance between a center of the respective image and a horizontal center of a landing resource,
select an image of the plurality of images having a highest score,
place the selected image having the highest score in a starting location within the frame of the content item,
divide a remaining unused space within the frame into a plurality of rectangles such that at least one rectangle of the plurality of rectangles has a dimension equal to a dimension of the placed image;
combine two or more rectangles of the plurality of rectangles in the remaining unused space to create a combined rectangle having a dimension accommodating a dimension of an unplaced image or text snippet of the obtained images and text snippets, and
place the unplaced image or text snippet into the combined rectangle.

11. The system of claim 10 , wherein the layout module is further configured to:
combine a first rectangle that is either horizontally adjacent or vertically adjacent to the location of the placed image with a second rectangle that is diagonally adjacent to the location of the placed image.

12. The system of claim 10 , wherein the image extractor is further configured to:
receive a uniform resource locator specifying a landing resource; and
extract the plurality of images and the plurality of text snippets from the landing resource.

13. The system of claim 10 , further comprising a resource renderer configured to:
render the landing resource and generate a document object model tree based on the rendered resource.

14. The system of claim 10 , wherein the image extractor is further configured to retrieve the plurality of images and the plurality of text snippets from a database.

15. The system of claim 10 , wherein each of the plurality of images has respective associated metadata, and wherein the layout module is further configured to calculate the score of each of the plurality of images based on predetermined scores corresponding to each keyword in the metadata associated with the respective image.

16. The system of claim 15 , wherein the metadata includes at least one of a URL, a display position, a display size, or alt text.

17. The system of claim 10 , wherein the layout module is further configured to calculate the score of each of the plurality of images based on a display size of the respective image and a vertical placement of the respective image on a landing resource.

18. The system of claim 10 , wherein the layout module is further configured to resize the unplaced image or text snippet to fit the combined rectangle.

Assignees

• Google Llc

Inventors

• Zhang Guannan
• Ye Kai
• Zhu Yongtai
• Yan Zuo
• Foster Andrew
• Bayliss-Mcculloch Jordan
• Chang Daly
• Nonaka Ayaka

Classifications

• G06F16/5846

  using extracted text · CPC title

• G06F16/583

  using metadata automatically derived from the content · CPC title

• G06F16/345 Primary

  Summarisation for human users · CPC title

• G06F16/434

  using image data, e.g. images, photos, pictures taken by a user · CPC title

• G06F40/166 Primary

  Editing, e.g. inserting or deleting · CPC title