Organizing search results based upon clustered content

Patent metadata

Field	Value
Publication number	US-9703895-B2
Application number	US-81390910-A
Country	US
Kind code	B2
Filing date	Jun 11, 2010
Priority date	Jun 11, 2010
Publication date	Jul 11, 2017
Grant date	Jul 11, 2017

Abstract

Many users make use of search engines to locate desired internet content by submitting search queries. For example, a user may search for photos, applications, websites, videos, documents, and/or information regarding people, places, and things. Unfortunately, search engines may provide a plethora of information that a user may be left to sift through to find relevant content. Accordingly, one or more systems and/or techniques for organizing search results are disclosed herein. In particular, user generated content, such as photos, may be retrieved based upon a search query. The user generated content may be grouped into clusters of user generated content having similar features. Search results of the search query may be obtained and organized based upon comparing the search results with the clusters. The organized search results and/or a table of content based upon the clusters may be presented to provide an enhanced user experience.

First claim

What is claimed is:

1. A method performed by a computing device, the method comprising:
receiving a search query from a user, the search query identifying a specific location;
querying an image repository with the search query to obtain a plurality of positively-rated location-specific images for the specific location that have received positive user feedback;
extracting features from the plurality of positively-rated location-specific images for the specific location;
defining a first image cluster using the extracted features, the first image cluster comprising first positively-rated location-specific images that are associated with a first location-specific topic for the specific location;
defining a second image cluster using the extracted features, the second image cluster comprising second positively-rated location-specific images that are associated with a second location-specific topic for the specific location;
obtaining, from a search engine other than the image repository, a plurality of search results that are responsive to the search query identifying the specific location;
associating individual first search results with the first location-specific topic and individual second search results with the second location-specific topic; and
ranking the individual first search results relative to one another based at least on similarity to the first positively-rated location-specific images of the first image cluster and ranking the individual second search results relative to one another based at least on similarity to the second positively-rated location-specific images of the second image cluster.

2. The method of claim 1 , wherein the image repository comprises a social network website and the search engine comprises a general-purpose search engine.

3. The method of claim 1 , the querying the image repository comprising:
matching the search query with metadata associated with the positively-rated location-specific images, the metadata comprising:
tagging data,
user voting data,
descriptive data,
comments,
frequency of access metadata, or
amount of access metadata.

4. The method of claim 1 , the querying the image repository comprising:
querying an image-hosting website; and
querying a social network website other than the image-hosting website.

5. The method of claim 1 , further comprising:
assigning different topic names to the first image cluster and the second image cluster.

6. The method of claim 1 , further comprising:
computing term frequency-inverse-document frequency measures for the first image cluster and the second image cluster to determine a first key phrase for the first image cluster and a second key phrase for the second image cluster; and
assigning the first key phrase as a descriptive name for the first image cluster and the second key phrase as a descriptive name for the second image cluster.

7. The method of claim 1 , wherein the features used to define the first image cluster and the second image cluster include both visual features and textual features.

8. The method of claim 7 , wherein the first image cluster and the second image cluster are defined by:
executing a multimodal Dirichlet Process Mixture Sets model using both the visual features and the textual features of the positively-rated location-specific images.

9. The method of claim 1 , wherein the first image cluster relates to activities available at the specific location and the second image cluster relates to lodging facilities available at the specific location.

10. The method of claim 1 , the associating comprising:
executing a multimodal Dirichlet Process Mixture Sets model upon both visual features and textual features of the plurality of search results.

11. The method of claim 1 , further comprising:
presenting ranked individual first search results and ranked individual second search results in response to the received search query identifying the specific location.

12. The method of claim 11 , wherein the ranked individual first search results include first images other than the positively-rated location-specific images and the ranked individual second search results include second images other than the positively-rated location-specific images.

13. A system comprising:
a processor; and
a hardware computer readable medium storing instructions that, when executed by the processor, cause the processor to:
receive a search query identifying a specific location;
query an image repository with the search query to obtain a plurality of positively-rated location-specific images for the specific location;
extract features from the positively-rated location-specific images for the specific location;
define a first cluster of first positively-rated location-specific images using the extracted features;
define a second cluster of second positively-rated location-specific images using the extracted features;
obtain a plurality of search results, other than the positively-rated location-specific images, that are responsive to the search query identifying the specific location;
associate individual first search results with a first topic of the first cluster and individual second search results with a second topic of the second cluster;
rank the individual first search results with respect to the first topic based at least on similarity to the first cluster of first positively-rated location-specific images and rank the individual second search results with respect to the second topic based at least on similarity to the second cluster of second positively-rated location-specific images; and
present at least some ranked first search results and at least some ranked second search results in response to the search query.

14. The system of claim 13 , wherein the at least some ranked first search results include first blogs ranked based at least on similarity to the first cluster of first positively-rated location-specific images and the at least some ranked second search results include second blogs ranked based at least on similarity to the second cluster of second positively-rated location-specific images.

15. The system of claim 13 , wherein the at least some ranked first search results include first videos ranked based at least on similarity to the first cluster of first positively-rated location-specific images and the at least some ranked second search results include second videos ranked based at least on similarity to the second cluster of second positively-rated location-specific images.

16. The system of claim 13 , wherein the at least some ranked first search results include first web pages ranked based at least on similarity to the first cluster of first positively-rated location-specific images and the at least some ranked second search results include second web pages ranked based at least on similarity to the second cluster of second positively-rated location-specific images.

17. The system of claim 13 , wherein the extracted features include a scale-invariant feature transform (“SIFT”) feature of the positively-rated location-specific images.

18. The system of claim 13 , wherein the specific location comprises a city, the first cluster comprises individual first positively-rated images of a particular activity available in the city, and the second cluster comprises individual second positively-rated images of a particular tourist attraction in the city.

19. The system of claim 13 wherein the instructions, when executed by the processor, cause the processor to:
select the positively-rated

Assignees

• Wang Xin-Jing
• Zhang Lei
• Ma Wei-Ying
• Microsoft Technology Licensing Llc

Inventors

• Wang Xin-Jing
• Zhang Lei
• Ma Wei-Ying

Classifications

• G06F17/30247

  Physics · mapped topic

• G06F17/30991 Primary

  Physics · mapped topic

• G06F17/3028

  Physics · mapped topic

• G06F16/583

  using metadata automatically derived from the content · CPC title

• G06F16/51

  Indexing; Data structures therefor; Storage structures · CPC title