IP Library Granted Patent US 12,536,370
Granted Patent B2
US 12,536,370 · App. 18/196,746 · Granted Jan 27, 2026

Arbitrary size content item generation

Inventors: Guannan Zhang (Shanghai, CN); Zuo Yan (Seattle, WA)
Assignee: GOOGLE LLC
G06F40/186G06F7/24G06F40/205
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,536,370
App. No.
18/196,746
Granted
Jan 27, 2026
Kind
B2
Abstract

A system for automatically generating a content item may include receiving a content item template having a set of elements for creating a content item and content item data for the set of elements. A placeholder for each element of the set of elements may be generated and a space allocation for each element may be selected based on the generated placeholders for each element. A determination if a conflict exists based on the determined space allocations for each element may be made and, when a conflict exists, an element from the set of elements may be eliminated and a new reduced set of elements may be returned. Responsive to determining no conflict exists, a content item may be generated using the content item data for the reduced set of elements and the determined space allocations.

Claims (58)

1 . A system for automatically generating a content item for a content provider, the system comprising:

one or more processors; and

one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving a content item template having a set of elements for creating the content item;

retrieving, using a uniform resource locator (URL) of a landing page of the content provider, content item data for the set of elements from the landing page, the content item data including at least text data and image data;

generating a text description for the content item based on the content item data,

generating a placeholder for each element of the set of elements of the content item template;

selecting a space allocation for each element of the set of elements based, at least in part, on the generated placeholders for each element of the set of elements;

determining whether a conflict exists based on determining whether a portion of a first space allocation of a first element of the set of elements overlaps a portion of a second space allocation of a second element of the set of elements;

eliminating, when the conflict exists, an element from the set of elements and returning a new reduced set of elements to generate the placeholders based on the new reduced set of elements; and

generating, when the conflict does not exist, the content item for the content provider using the content item data for the reduced set of elements, the generated text description, and the selected space allocations.

2 . The system of claim 1 , wherein each element of the set of elements of the content item template comprises an index and an anchor.

3 . The system of claim 2 , wherein the anchor comprises an anchor reference, an anchor type, and a distance between two elements of the content item template.

4 . The system of claim 3 , wherein the anchor type is a direction relative to the content item.

5 . The system of claim 3 , wherein the distance is a predetermined value or a relative value relative to the content item.

6 . The system of claim 2 , wherein the anchor comprises a flexibility indicator.

7 . The system of claim 1 , wherein an element of the set of elements of the content item template comprises a requirement indicator.

8 . The system of claim 2 , wherein generating the placeholder for each element of the set of elements comprises:

sorting the set of elements based on the index of each element of the set of elements.

9 . The system of claim 2 , wherein generating the placeholder for each element of the set of elements comprises:

determining a left value, a top value, a right value, and a bottom value for each element of the set of elements based, at least in part, on the anchor associated with each element.

10 . The system of claim 1 , wherein generating the content item comprises:

generating a snapshot image of a landing page resource; and

selecting one or more colors from the snapshot image for the content item.

11 . The system of claim 10 , wherein selecting the one or more colors from the snapshot image comprises extracting a plurality of color clusters from the snapshot image using a clustering technique.

12 . The system of claim 11 , wherein the clustering technique is a k-means clustering technique.

13 . The system of claim 1 , wherein selecting the space allocation for each element of the set of elements comprises:

determining an initial space allocation for an element of the set of elements based on a generated placeholder for the element;

determining a minimum space allocation for the element of the set of elements based on the initial space allocation; and

incrementing a dimension of the determined minimum space allocation for the element of the set of elements by a predetermined pixel value.

14 . A computer-implemented method for automatically generating a content item for a content provider, the method comprising:

receiving a content item template having a set of elements for creating the content item;

retrieving, using a uniform resource locator (URL) of a landing page of the content provider, content item data for the set of elements from the landing page, the content item data including at least text data and image data;

generating a text description for the content item based on the content item data;

generating a placeholder for each element of the set of elements of the content item template;

selecting a space allocation for each element of the set of elements based, at least in part, on the generated placeholders for each element of the set of elements;

determining whether a conflict exists based on determining whether a portion of a first space allocation of a first element of the set of elements overlaps a portion of a second space allocation of a second element of the set of elements;

eliminating, when the conflict exists, an element from the set of elements and returning a new reduced set of elements to generate the placeholders based on the new reduced set of elements; and

generating, when the conflict does not exist, the content item for the content provider using the content item data for the reduced set of elements, the generated text description, and the selected space allocations.

15 . The method of claim 14 , wherein each element of the set of elements of the content item template comprises an index and an anchor.

16 . The method of claim 15 , wherein the anchor comprises an anchor reference, an anchor type, and a distance between two elements of the content item template.

17 . The method of claim 16 , wherein the anchor type is a direction relative to the content item.

18 . The method of claim 16 , wherein the distance is a predetermined value or a relative value relative to the content item.

19 . The method of claim 15 , wherein generating the placeholder for each element of the set of elements comprises:

determining a left value, a top value, a right value, and a bottom value for each element of the set of elements based, at least in part, on the anchor associated with each element.

20 . The method of claim 14 , wherein generating the content item comprises:

generating a snapshot image of the landing page resource; and

selecting one or more colors from the snapshot image for the content item.

21 . The method of claim 20 , wherein selecting the one or more colors from the snapshot image comprises extracting a plurality of color clusters from the snapshot image using a clustering technique.

22 . The method of claim 21 , wherein the clustering technique is a k-means clustering technique.

23 . The method of claim 14 , wherein the score is a first score and the generated content item is a first generated content item, the method further comprising:

determining a second score for a second generated content item based, at least in part, on second determined space allocations for each element of a second set of elements;

comparing the first score and the second score; and

selecting the first generated content item or the second generated content item based, at least in part, on the compared first score and second score.

24 . The method of claim 14 , wherein selecting the space allocation for each element of the set of elements comprises:

determining an initial space allocation for an element of the set of elements based on a generated placeholder for the element;

determining a minimum space allocation for the element of the set of elements based on the initial space allocation; and

incrementing a dimension of the determined minimum space allocation for the element of the set of elements by a predetermined pixel value.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 8, 2023
From: ZHANG, GUANNAN; YAN, ZUO
To: GOOGLE INC.
Reel/Frame 064524/0640 →
CHANGE OF NAME Recorded Aug 8, 2023
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 064528/0788 →
Continuity (3)
Continuation 14585685 · Dec 30, 2014
Continuation PCTCN2014071880 · Feb 7, 2014
Related Publication 20230281383A1 · Sep 7, 2023
References Cited (28)
US 9135292B1 · Tsun · 2015 [cited by examiner]
US 20020078096A1 · Milton · 2002 [cited by examiner]
US 20030040926A1 · Milton · 2003 [cited by examiner]
US 20060155699A1 · Purvis · 2006 [cited by examiner]
US 20070038929A1 · Miyazawa · 2007 [cited by applicant]
US 20070079236A1 · Schrier et al. · 2007 [cited by applicant]
US 20070166887A1 · Chen · 2007 [cited by examiner]
US 20080120536A1 · Osaka · 2008 [cited by applicant]
US 20080147553A1 · Orner et al. · 2008 [cited by applicant]
US 20080187241A1 · Talati · 2008 [cited by examiner]
US 20080250052A1 · Jones et al. · 2008 [cited by applicant]
US 20090113282A1 · Schultz · 2009 [cited by examiner]
US 20090254572A1 · Redlich et al. · 2009 [cited by applicant]
US 20100110495A1 · Letocha · 2010 [cited by examiner]
US 20100115400A1 · Yamanakajima · 2010 [cited by examiner]
US 20130086031A1 · Marantz · 2013 [cited by examiner]
US 20130132209A1 · Belwadi · 2013 [cited by applicant]
US 20140089124A1 · Jha et al. · 2014 [cited by applicant]
US 20140164352A1 · Denninghoff · 2014 [cited by examiner]
US 20150100606A1 · Bonner · 2015 [cited by applicant]
US 20180107641A1 · Choi · 2018 [cited by examiner]
CN 1912825A · 2007 [cited by applicant]
CN 101976261A · 2011 [cited by applicant]
WO WO2012057726A1 · 2012 [cited by applicant]
Extended European Search Report on EP14881880.0 dated Sep. 22, 2017. [cited by applicant]
First Office Action for CN Application No. 201480077640.0 dated Aug. 28, 2018. [cited by applicant]
Second Office Action for CN Appln. Ser. No 201480077640.0 dated Mar. 6, 2019. [cited by applicant]
International Search Report and Written Opinion of PCT/CN2014/071880, mailed Nov. 15, 2014. [cited by applicant]