IDENTIFYING SIGHT FOR A LOCATION

• US 20080086468A1
• Filed: 10/10/2006
• Published: 04/10/2008
• Est. Priority Date: 10/10/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Ma, Wei-Ying, Zhang, Lei, Jing, Feng
• Granted Patent: US 7,707,208 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• 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 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries

Abstract

A method and system for identifying sights associated with a location and for displaying images associated with those sights is provided. A tour system identifies sights associated with a location by submitting a search request formed using the location to an image search service. The tour system identifies salient phrases of metadata of the search results to be the candidate sight names. The tour system also provides a user interface for displaying the images associated with the locations. The user interface may present a slideshow of sights encountered when traveling on a trip.

Claims

1. A method in a computing system for identifying sights for a location, the method comprising:

submitting to a search service a search request based on the location;

identifying candidate sights from results of the search request; and

selecting as sights for the location those candidate sights that correspond to sights of interest.

2. The method of claim 1 wherein the search service is an image search service.

3. The method of claim 1 wherein the identifying of candidate sights includes identifying salient phrases from the search results and scoring the identified salient phrases to be a name for a cluster of search results.

4. The method of claim 3 wherein the search service is an image search service and wherein the identifying of salient phrases includes selecting phrases from metadata of a search result.

5. The method of claim 1 wherein the selecting as sights for the location includes submitting a name of a candidate sight to a geographic name service and, when the geographic name service indicates that the name of the candidate sight is a geographic name, indicating the candidate sight as a sight associated with the location.

6. The method of claim 5 wherein when the geographic name service indicates that the name of the candidate sight is not a geographic name, not indicating the candidate sight as a sight for the location.

7. The method of claim 1 wherein the search service is an image search service and wherein the selecting as sights for the location factors in quality of an image as indicated by metadata of the search results.

8. The method of claim 1 wherein the search service is an image search service and wherein the selecting of candidate sights includes:

identifying salient phrases from the search results;

scoring the identified salient phrases to be a name for a cluster of images of the search results;

submitting a name of a candidate sight with a score above a threshold to a geographic name service; and

when the geographic name service indicates that the name of the candidate sight is a geographic name, selecting the candidate sight as a sight associated with the location.

9. A computing system for identifying sights for a location, comprising:

a component that submits to an image search service a search request based on the location and receives search results that identify images and associated metadata that includes quality of the images;

a component that identifies candidate sights from metadata associated with the identified images of the search results and scores the candidate sights based on relevance of the metadata of images to the location and based on quality of the images; and

a component that submits names of candidate sights to a sight of interest name service and selects sights for the location based on candidate sights that are sights of interest and their scores.

10. The computing system of claim 9 wherein the identifying of candidate sights includes identifying salient phrases from the search results and the scoring of candidates is based on appropriateness of a salient phrase to be a name for a cluster of images of the search results.

11. The computing system of claim 9 wherein the sight of interest name service is a geographic name service and wherein a candidate sight corresponds to a sight of interest when the geographic name service indicates that the name of the candidate sight is a geographic name.

12. The computing system of claim 9 wherein the identifying of candidate sights includes identifying salient phrases from the search results and the scoring of candidate sights is based on appropriateness of a salient phrase to be a name for a cluster of images of the search result, wherein the sight of interest name service is a geographic name service, and wherein a candidate sight corresponds to a sight of interest when the geographic name service indicates that the name of the candidate sight is a geographic name.

13. A computer-readable medium for controlling a computing system to identify sights for a location, by a method comprising:

submitting to an image search service a search request based on the location;

receiving search results of the search request that include identified images and associated metadata;

identifying candidate sights from the metadata associated with the identified images; and

selecting as sights for the location those candidate sights that correspond to sights of interest.

14. The computer-readable medium of claim 13 wherein the identifying of candidate sights includes identifying salient phrases from the metadata and scoring the identified salient phrases to be a name for a cluster of search results.

15. The computer-readable medium of claim 14 wherein the scoring of the identified salient phrases factors in quality of the images as indicated by the metadata.

16. The computer-readable medium of claim 13 wherein the identifying of candidate sights includes identifying salient phrases from the metadata and scoring the identified salient phrases based on relevance to the location.

17. The computer-readable medium of claim 16 wherein relevance to the location is based on similarity between the location and the metadata that contains an identified salient phrase.

18. The computer-readable medium of claim 13 wherein the selecting as sights for the location includes submitting a name of a candidate sight to a geographic name service and, when the geographic name service indicates that the name of the candidate sight is a geographic name, selecting the candidate sight as a sight for the location.

19. The computer-readable medium of claim 13 wherein the identifying of candidate sights includes identifying salient phrases from the metadata and scoring the identified salient phrases to be a name representing a cluster of images and wherein the selecting as sights for the location includes submitting a name of a candidate sight to a geographic name service and, when the geographic name service indicates that the name of the candidate sight is a geographic name, selecting the candidate sight as a sight for the location.

20. The computer-readable medium of claim 13 wherein the image search service searches an image forum having quality ratings and including normalizing the quality ratings of different photographic image forums.