Methods and systems for creating image-based content based on text-based content

• US 9,501,499 B2
• Filed: 10/21/2013
• Issued: 11/22/2016
• Est. Priority Date: 10/21/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sanio, Jason Robert Richard, Hampson, Courtney
• Primary Examiner(s): Hershley, Mark E
• Application Number:
  US14/058,702
• Publication Number:
  US 20150112980A1
• Time in Patent Office: 1,128 Days
• Field of Search: 707/728
• US Class Current: 1/1
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0276 Advertisement creation

Abstract

Systems and methods for creating image-based content based on text-based content. A data processing system receives a text-based content item based on which an image-based content item is to be created. The data processing system determines a context of the text-based content item based on the content of the text-based content item and the content of a landing page associated with the text-based content item. The data processing system determines one or more search terms from the determined context of the text-based content item. The data processing system then identifies from an image database, one or more candidate images that match at least one of the search terms determined from the context of the text-based content item. The data processing system then creates an image-based content item based on the text-based content item using at least one of the candidate images.

Claims

1. A method for creating image-based content based on text-based content, comprising:

receiving, by a data processing system, a text-based content item including a link to a landing page, the text-based content for serving in one or more text-based content slots of one or more information resources;

determining, by the data processing system, a context of the text-based content item based on the content of the text-based content item and the content of the landing page accessible via the link included in the text-based content item;

determining, by the data processing system, one or more search terms from the determined context of the text-based content item;

identifying from an image database, by the data processing system, one or more candidate images that match at least one of the search terms determined from the context of the text-based content item;

identifying, by the data processing system, text from the text-based content item; and

creating, by the data processing system, an image-based content item, for serving in one or more image-based content slots of the one or more information resources, based on the text-based content item using at least one of the candidate images, the image-based content item including the text identified from the text-based content item and the link to the landing page associated with the text-based content item.

2. The method of claim 1, wherein receiving a text-based content item further comprises receiving an indication to automatically create an image-based content item from the text-based content item.

3. The method of claim 1, wherein determining a context of the text-based content item comprises:

performing clustering of the content of the landing page to identify landing page keyword clusters; and

determining a context of the text-based content item based in part on the identified landing page keyword clusters.

4. The method of claim 3, wherein determining a context of the text-based content item based in part on the identified landing page keyword clusters comprises:

determining a weight of one or more of the landing page keyword clusters, the weight indicating a relevance of the content of the landing page to the one or more landing page keyword clusters associated with the weight; and

ranking the landing page keyword clusters according to their weight.

5. The method of claim 3, wherein determining a context of the text-based content item comprises:

identifying one or more bidding keywords associated with the text-based content item on which bids are placed;

determining content keywords from the content of the text-based content item; and

determining a context of the text-based content item based on the bidding keywords, content keywords and the landing page keyword clusters.

6. The method of claim 1, further comprising:

determining, for each of the candidate images, from context-related attributes associated with the candidate image, a contextual relevance score of the candidate image indicating a relevance of the candidate image to the context of the text-based content item; and

ranking the candidate images based on their contextual relevance scores.

7. The method of claim 6, further comprising:

determining, for each of the candidate images, from visual attributes associated with the candidate image, a visual attribute score of the candidate image indicating a visual appeal level for an appearance of an image-based content item that includes the candidate image when the image-based content item is displayed; and

ranking the candidate images based on their visual attribute scores and contextual relevance scores.

8. The method of claim 1, wherein creating an image-based content item using at least one of the candidate images comprises selecting a target image from the candidate images based on a contextual relevance score of the target image indicating a relevance of the target image to the context of the text-based content item.

9. The method of claim 1, further comprising:

receiving, by the data processing system, a request to display a content item, the request including display-related information associated with a computing device on which to display the content item; and

selecting, for display, an image-based content item based in part on display-related information included in the request.

10. The method of claim 1, further comprising:

providing the created image-based content item for display responsive to receiving a request to display a content item;

monitoring performance of the image-based content item provided for display; and

responsive to monitoring the performance of the image-based content item, modifying a contextual relevance score of the image used to create the image-based content item, the contextual relevance score of the image indicating a relevance of the image to the context of the text-based content item.

11. A system for creating image-based content based on text-based content, comprising:

a data processing system having a content item analysis module, an image selection module and an image-based content selection module, the data processing system further comprising

a memory storing processor-executable instructions; and

a processor configured to execute the processor-executable instructors to;

receive a text-based content item including a link to a landing page, the text-based content for serving in one or more text-based content slots of one or more information resources;

determine a context of the text-based content item based on the content of the text-based content item and the content of the landing page accessible via the link included in the text-based content item;

determine one or more search terms from the determined context of the text-based content item;

identify from an image database, one or more candidate images that match at least one of the search terms determined from the context of the text-based content item;

identify text from the text-based content item; and

create an image-based content item, for serving in one or more image-based content slots of the one or more information resources, based on the text-based content item using at least one of the candidate images, the image-based content item including the text identified from the text-based content item and the link to the landing page associated with the text-based content item.

12. The system of claim 11, wherein receiving a text-based content item further comprises receiving an indication to automatically create an image-based content item from the text-based content item.

13. The system of claim 11, wherein in determining a context of the text-based content item, the processor is further configured to:

perform clustering of the content of the landing page to identify landing page keyword clusters; and

determine a context of the text-based content item based in part on the identified landing page keyword clusters.

14. The system of claim 13, wherein in determining a context of the text-based content item based in part on the identified landing page keyword clusters, the processor is further configured to:

determine a weight of one or more of the landing page keyword clusters, the weight indicating a relevance of the content of the landing page to the one or more landing page keyword clusters associated with the weight; and

rank the landing page keyword clusters according to their weight.

15. The system of claim 13, wherein in determining a context of the text-based content item, the processor is further configured to:

identify one or more bidding keywords associated with the text-based content item on which bids are placed;

determine content keywords from the content of the text-based content item; and

determine a context of the text-based content item based on the bidding keywords, content keywords and the landing page keyword clusters.

16. The system of claim 11, wherein the processor is further configured to:

determine, for each of the candidate images, from context-related attributes associated with the candidate image, a contextual relevance score of the candidate image indicating a relevance of the candidate image to the context of the text-based content item; and

rank the candidate images based on their contextual relevance scores.

17. The system of claim 16, wherein, the processor is further configured to:

determine, for each of the candidate images, from visual attributes associated with the candidate image, a visual attribute score of the candidate image indicating a visual appeal level for an appearance of an image-based content item that includes the candidate image when the image-based content item is displayed; and

rank the candidate images based on their visual attribute scores and contextual relevance scores.

18. The system of claim 11, wherein in creating an image-based content item using at least one of the identified images, the processor is further configured to select a target image from the candidate images based on a contextual relevance score of the target image indicating a relevance of the target image to the context of the text-based content item.

19. The system of claim 11, wherein, the processor is further configured to:

receive a request to display a content item, the request including display-related information associated with a computing device on which to display the content item; and

select, for display, an image-based content item based in part on the display-related information included in the request.

20. The system of claim 11, wherein, the processor is further configured to:

provide the created image-based content item for display responsive to receiving a request to display a content item;

monitor performance of the image-based content item provided for display; and

responsive to monitoring the performance of the image-based content item, modify a contextual relevance score of the image used to create the image-based content item, the contextual relevance score of the image indicating a relevance of the candidate image to the context of the text-based content item.