Method and system for mining image searches to associate images with concepts

• US 8,065,611 B1
• Filed: 06/30/2004
• Issued: 11/22/2011
• Est. Priority Date: 06/30/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jindal, Deepak, Ranganath, Rama, Agarwal, Sumit, Wiseman, Leora Ruth, Chan, Wesley
• Primary Examiner(s): Hong; Stephen
• Assistant Examiner(s): LUDWIG, MATTHEW J
• Application Number:
  US10/880,375
• Time in Patent Office: 2,701 Days
• Field of Search: 715/500, 715/243, 715/253, 715/273, 705/14.25, 705/14.49, 705/14.67, 382/305
• US Class Current: 715/253
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• 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 16/5846 using extracted text
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06Q 30/0224 based on user history
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

A system and method for associating a document with a concept are provided. One or more idea-electronic document associations is identified, wherein each idea-electronic document association is based on a user performance criteria relative to the electronic document and the idea. At least one of the one or more electronic documents is identified with a concept based on the one or more idea-electronic document associations, wherein the concept is related to the one or more ideas.

Claims

1. A computer-implemented method for associating an electronic image document with a concept, comprising:

receiving one or more search queries;

for each query, identifying a plurality of image electronic documents associated with a given search query where a given image electronic document is to be associated with a given query based at least in part on the query being resolved to and responsive to the submitted query forming part of a responsive search result and providing a listing of the plurality of documents as a search result;

receiving a user indication of a selection of one or more of the identified documents responsive to a presentation of the search result;

automatically identifying one or more concepts derived from the search query and one or more electronic image documents that were provided as being responsive to the search query based at least in part on the prior selection of the electronic image documents after presentation as search results;

creating and storing, using at least one processor, an association between at least one of the one or more electronic image documents and concepts associated with the one or more electronic image documents;

after storing the association, receiving a new query for electronic image documents independently of receipt of the one or more queries used to derive the concept associated with the one or more electronic image documents;

determining that the image document query is related to the concept derived from the stored one or more queries that are associated with the one or more electronic image documents; and

identifying at least one of the one or more electronic image documents as satisfying the image document query based upon determining that the image document query is related to the concept.

2. The method of claim 1, further comprising:

receiving a request for an electronic image document associated with a subject matter of interest associated with the concept; and

delivering at least one of the one or more electronic image documents based on the association between the concept and the subject matter of interest.

3. The method of claim 1, wherein each association comprises a selection of one of the one or more image documents from among a plurality of image documents associated with one of the one or more queries by one of the one or more users.

4. The method of claim 1, wherein each of the one or more queries comprises an interne search query, and wherein each association comprises an association between an electronic image document comprising a selected search result document and the search query.

5. The method of claim 4, wherein the selected search result electronic image document comprises an image selected from among a plurality of images associated with the search query, and the plurality of images are provided from a database of images based on an association between the plurality of images and the concept.

6. The method of claim 5, wherein the act of associating comprises identifying content of an image based on the one or more associations, and wherein the concept is representative of the content of the image.

7. The method of claim 1, further comprising storing the one or more selected images in a database of images.

8. The method of claim 7, further comprising:

receiving a request for an image advertisement associated with a subject matter of interest; and

suggesting one or more of the selected images for use in the image advertisement based on an association between the subject matter of interest and the concept.

9. The method of claim 7, wherein the concept comprises a keyword, further comprising:

receiving a request for an image advertisement associated with a graphic;

processing the graphic to determine that at least one of the one or more stored selected images is substantially similar to the graphic; and

suggesting the keyword for use in the image advertisement based on processing the graphic.

10. The method of claim 1, further comprising:

determining that an unassociated electronic image document is substantially similar to at least one of the one or more electronic image documents; and

associating the unassociated electronic image document with the concept based on determining that the unassociated electronic image document is substantially similar to at least one of the one or more electronic image documents.

11. The method of claim 1, further comprising:

generating a database of approved public images based on the one or more associations.

12. The method of claim 11, further comprising:

suggesting one or more of the approved public images for an image advertisement based on a request for an image advertisement.

13. The method of claim 1, wherein the at least one of the one or more electronic image documents comprises at least one of an animation, pop-up ability, sound, voice, and music.

14. The method of claim 1, wherein the one or more associations comprises a selection of a graphic on a web page.

15. The method of claim 1, wherein the one or more associations comprises a selection of a document from a search result document list.

16. The method of claim 1, wherein the one or more associations comprises the selection of a website from among a plurality of websites.

17. The method of claim 1, wherein the at least one associated image document is an encrypted document.

18. The method of claim 1, further comprising:

identifying preference data of a specific one of the one or more users based on at least one association made by the user; and

providing a targeted advertisement to the specific user based on the identified preference data.

19. The method of claim 1, wherein the one or more associations comprises a plurality of associations between a single image and the concept.

20. The method of claim 19, further comprising:

identifying content in the image based on the plurality of associations.

21. The method of claim 1, wherein the electronic image documents are selected from the document corpus based on an idea in the search queries.

22. The method of claim 21, where the idea is a keyword.

23. The method of claim 21, wherein the concept and the idea are different.

24. A system for associating an electronic image document with a concept, comprising:

an input device for receiving one or more electronic image document selections responsive to one or more search queries;

determining one or more ideas associated with the selected electronic image documents; and

associating one or more ideas with each selected electronic image document;

a database for storing the one or more idea-electronic image document associations; and

a processor for automatically creating an association between at least one of the one or more electronic image documents and a concept derived from a new search query, the association between the one or more electronic image documents and the concept being based on the one or more idea-electronic image document associations, wherein the concept is related to the idea;

wherein subsequent image queries from other users are served based upon correlation of the subsequent queries with the concept, thereby providing the associated one or more electronic image documents.

25. A computer-readable medium encoded with computer program code to associate an electronic image document with a concept, the program code effective to cause one or more machines to perform the following operations:

identify one or more idea-image associations, wherein each idea-image association is based on a selection of an image presented as search results responsive to a search query that includes the idea including identifying one or more image selections that have been presented as search results responsive to requests and identifying a concept associated with a respective one of the image selections;

automatically creating an association between at least one of the one or more images and a concept derived from the search query, the association between the one or more images and the concept being based on the one or more idea-image associations, wherein the concept is related to the idea; and

provide results for subsequent image queries related to the concept, the queries being received from other users and the results including at least one of the associated one or more images.