Creating and Modifying an Image Wiki Page

• US 20120117449A1
• Filed: 11/08/2010
• Published: 05/10/2012
• Est. Priority Date: 11/08/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Yang, Linjun, Tian, Qi
• Granted Patent: US 8,875,007 B2
• Time in Patent Office: Days
• US Class Current: 715/201
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/532 Query formulation, e.g. graphical querying
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation

Abstract

An ImageWiki architecture is used to generate an image-based web page for an image on the Web. An ImageWiki page may be created automatically or individually, by a user of the Web. Additionally, a user may revise existing ImageWiki pages to update a particular page or correct an incorrect or misleading previous entry. The ImageWiki application indexes images located on the Web. Once the images are indexed, the information related to the images is mined and extracted from various sources of web data. Finally, an ImageWiki page or web page is generated for each image. The resulting ImageWiki page contains the image as well as the aggregated information relating to the image.

Claims

1. A method comprising:

retrieving a plurality of images in response to a query;

selecting an image from the indexed plurality of images;

retrieving a plurality of information automatically from the plurality of web data related to the image that is selected;

extracting a subset of the plurality of information to create a plurality of selected information;

aggregating the plurality of selected information; and

generating a new web page containing the image and the aggregated plurality of selected information.

2. The method of claim 1, wherein the plurality of selected information comprises:

an author, a title, a date, and a source of the image that is selected.

3. The method of claim 1, wherein the plurality of selected information comprises a textual story describing the image that is selected.

4. The method of claim 1, wherein the plurality of selected information comprises a plurality of other images related to the image that is selected.

5. The method of claim 1, wherein the plurality of selected information further comprises a plurality of videos related to the image that is selected.

6. The method of claim 1, wherein the plurality of optimal information further comprises a plurality of news events related to the image that is selected.

7. The method of claim 1, wherein the plurality of selected information comprises a plurality of links to a plurality of web pages that are related to the image that is selected.

8. The method of claim 1, wherein the new web page comprises a caption which provides additional background information on a subject of the image that is selected.

9. The method of claim 1, wherein the indexing of the plurality of images discovers duplicates from the plurality of images to enable selection of an optimal image.

10. The method of claim 1, wherein the extracting a subset of the plurality of information from the plurality of web pages uses a majority voting technique.

11. The method of claim 1, further comprising conducting a cross media recommendation analysis to further optimize the quality of the aggregated plurality of selected information.

12. The method of claim 11, wherein the cross media recommendation uses a textual representation of a video based on a plurality of tags surrounding the video to provide a recommendation for selection of a plurality of additional information to optimize the quality of the new web page.

13. The method of claim 1, wherein the query is an image-based query that is submitted by selecting a region in the image that is a subject of the query.

14. The method of claim 1, wherein the plurality of web data comprises:

a plurality of image data, a plurality of web pages, a plurality of social tagging sites anda plurality of query logs.

15. The method of claim 1, wherein the new web page is generated automatically by a computer.

16. A method comprising:

selecting, by a user, an existing web page;

identifying, by the user, a plurality of additional information that the user desires to add to the existing web page;

retrieving the plurality of additional information from a plurality of web data associated with an image;

adding the plurality of additional information to the existing web page; and

generating a new web page by incorporating the plurality of additional information with the existing web page.

17. The method of claim 16, further comprising identifying, by the user, a plurality of incorrect information that the user desires to correct in the existing web page.

18. A system comprising:

a memory;

one or more processors operatively coupled to the memory and disposed within one or more devices;

an application for accessing a plurality of web pages stored in the memory and executed by the one or more processors;

a web image mining component for accessing web data from a plurality of sources and selecting;

an image from a plurality of images; and

aggregating a plurality of information from the plurality of web data to create a plurality of selected information that is related to the web image and collected from a plurality of sources that may be separate from the source that provided the web image; and

a page generation component for generating a new web page containing the image and the aggregated plurality of selected information.

19. The method of claim 18, wherein the web image mining component further comprises conducting a cross media recommendation analysis that uses a textual representation of a video based on a plurality of tags surrounding the video to provide a recommendation for selection of a plurality of additional information to optimize the quality of the new web page to further optimize the quality of the aggregated plurality of selected information.

20. The method of claim 18, wherein the plurality of web data comprises:

a plurality of image data, a plurality of web pages, a plurality of social tagging sites and a plurality of query logs.