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

• US 10,146,776 B1
• Filed: 01/05/2017
• Issued: 12/04/2018
• Est. Priority Date: 05/10/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Chan, Wesley T., Agarwal, Sumit, Ranganath, Rama, Wiseman, Leora Ruth, Jindal, Deepak
• Primary Examiner(s): Hong, Stephen
• Assistant Examiner(s): LUDWIG, MATTHEW J
• Application Number:
  US15/399,576
• Time in Patent Office: 698 Days
• Field of Search: 715253, 715273, 705 14, 705 25, 382305
• 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, comprising:

identifying, by a computing system, that a user input at a first computing device selected, from among a set of search results provided to the first computing device responsive to a first query, a search result that references a first electronic document;

generating, by the computing system and in response to identifying that the user input at the first computing device selected the search result that references the first electronic document, an association between the first electronic document and one or more terms derived from the first query;

after generating the association between the first electronic document and the one or more terms derived from the first query;

receiving a second query specified by a user of a second computing device;

determining a relevance of the first electronic document to the second query based at least in part on a level of similarity between (i) the one or more terms derived from the first query and associated with the first electronic document and (ii) one or more second terms derived from the second query;

generating a second set of search results responsive to the second query, including selecting or ranking the first electronic document represented in the second set of search results based on the determined relevance; and

transmitting the second set of search results to the second computing device.

2. The computer-implemented method of claim 1, wherein the set of search results provided to the first computing device responsive to the first query comprise image search results that show previews of images that are determined to be responsive to the first query, wherein the search result that references the first electronic document is among the image search results.

3. The computer-implemented method of claim 1, further comprising:

identifying, by the computing system, that a second user input selected, from among a third set of search results provided to a computing device responsive to a third query, a particular search result that references the first electronic document; and

generating, by the computing system and in response to identifying that the second user input selected the particular search result that references the first electronic document, a second association between the first electronic document and the one or more terms derived from the third query.

4. The computer-implemented method of claim 3 comprising, after generating the second association between the first electronic document and the one or more terms derived from the third query:

receiving a fourth query;

determining a relevance of the first electronic document to the fourth query based at least in part on a level of similarity between (i) the one or more terms derived from the third query and associated with the first electronic document and (ii) one or more terms derived from the fourth query;

generating a fourth set of search results responsive to the fourth query, including selecting or ranking the first electronic document in the fourth set of search results based on the determined relevance; and

transmitting the fourth set of search results.

5. The computer-implemented method of claim 1, wherein generating the association between the first electronic document and the one or more terms derived from the first query comprises correlating the first electronic document with a concept expressed by the one or more terms.

6. The computer-implemented method of claim 1, comprising increasing a ranking of a particular search result in the second set of search results as a result of the level of similarity between (i) the one or more terms derived from the first query and (ii) the one or more second terms derived from the second query.

7. A computing system comprising:

one or more computers; and

a computer-readable medium having instructions stored thereon that, when executed by the one or more computers, cause performance of operations comprising;

identifying, by the computing system, that a user input at a first computing device selected, from among a set of search results provided to the first computing device responsive to a first query, a search result that references a first electronic document;

generating, by the computing system and in response to identifying that the user input at the first computing device selected the search result that references the first electronic document, an association between the first electronic document and one or more terms derived from the first query;

after generating the association between the first electronic document and the one or more terms derived from the first query;

receiving a second query specified by a user of a second computing device;

determining a relevance of the first electronic document to the second query based at least in part on a level of similarity between (i) the one or more terms derived from the first query and associated with the first electronic document and (ii) one or more second terms derived from the second query;

generating a second set of search results responsive to the second query, including selecting or ranking the first electronic document represented in the second set of search results based on the determined relevance; and

transmitting the second set of search results to the second computing device.

8. The computing system of claim 7, wherein the set of search results provided to the first computing device responsive to the first query comprise image search results that show previews of images that are determined to be responsive to the first query, wherein the search result that references the first electronic document is among the image search results.

9. The computing system of claim 7, wherein the operations further comprise:

identifying, by the computing system, that a second user input selected, from among a third set of search results provided to a computing device responsive to a third query, a particular search result that references the first electronic document; and

generating, by the computing system and in response to identifying that the second user input selected the particular search result that references the first electronic document, a second association between the first electronic document and the one or more terms derived from the third query.

10. The computing system of claim 9, wherein the operations comprise, after generating the second association between the first electronic document and the one or more terms derived from the third query:

receiving a fourth query;

determining a relevance of the first electronic document to the fourth query based at least in part on a level of similarity between (i) the one or more terms derived from the third query and associated with the first electronic document and (ii) one or more terms derived from the fourth query;

generating a fourth set of search results responsive to the fourth query, including selecting or ranking the first electronic document in the fourth set of search results based on the determined relevance; and

transmitting the fourth set of search results.

11. The computing system of claim 7, wherein generating the association between the first electronic document and the one or more terms derived from the first query comprises correlating the first electronic document with a concept expressed by the one or more terms.

12. The computing system of claim 7, wherein the operations comprise increasing a ranking of a particular search result in the second set of search results as a result of the level of similarity between (i) the one or more terms derived from the first query and (ii) the one or more second terms derived from the second query.

13. A non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors, cause performance of operations comprising:

identifying, by a computing system, that a user input at a first computing device selected, from among a set of search results provided to the first computing device responsive to a first query, a search result that references a first electronic document;

generating, by the computing system and in response to identifying that the user input at the first computing device selected the search result that references the first electronic document, an association between the first electronic document and one or more terms derived from the first query;

after generating the association between the first electronic document and the one or more terms derived from the first query;

receiving a second query specified by a user of a second computing device;

determining a relevance of the first electronic document to the second query based at least in part on a level of similarity between (i) the one or more terms derived from the first query and associated with the first electronic document and (ii) one or more second terms derived from the second query;

generating a second set of search results responsive to the second query, including selecting or ranking the first electronic document represented in the second set of search results based on the determined relevance; and

transmitting the second set of search results to the second computing device.

14. The non-transitory computer-readable medium of claim 13, wherein the set of search results provided to the first computing device responsive to the first query comprise image search results that show previews of images that are determined to be responsive to the first query, wherein the search result that references the first electronic document is among the image search results.

15. The non-transitory computer-readable medium of claim 13, wherein the operations further comprise:

identifying, by the computing system, that a second user input selected, from among a third set of search results provided to a computing device responsive to a third query, a particular search result that references the first electronic document; and

generating, by the computing system and in response to identifying that the second user input selected the particular search result that references the first electronic document, a second association between the first electronic document and the one or more terms derived from the third query.

16. The non-transitory computer-readable medium of claim 15, wherein the operations comprise, after generating the second association between the first electronic document and the one or more terms derived from the third query:

receiving a fourth query;

determining a relevance of the first electronic document to the fourth query based at least in part on a level of similarity between (i) the one or more terms derived from the third query and associated with the first electronic document and (ii) one or more terms derived from the fourth query;

generating a fourth set of search results responsive to the fourth query, including selecting or ranking the first electronic document in the fourth set of search results based on the determined relevance; and

transmitting the fourth set of search results.

17. The non-transitory computer-readable medium of claim 13, wherein generating the association between the first electronic document and the one or more terms derived from the first query comprises correlating the first electronic document with a concept expressed by the one or more terms.

18. The non-transitory computer-readable medium of claim 13, wherein the operations comprise increasing a ranking of a particular search result in the second set of search results as a result of the level of similarity between (i) the one or more terms derived from the first query and (ii) the one or more second terms derived from the second query.