VISUAL AND MULTI-DIMENSIONAL SEARCH

• US 20080005091A1
• Filed: 06/28/2006
• Published: 01/03/2008
• Est. Priority Date: 06/28/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Naam, Ramez, Flake, Gary W., Chaudhuri, Surajit, Gupta, Anoop, Goodman, Joshua T., Brill, Eric D., Lawler, Stephen, Meek, Christopher A., Hurst-Hiller, Oliver, Horvitz, Eric J.
• Granted Patent: US 7,739,221 B2
• Time in Patent Office: Days
• US Class Current: 707/4
• CPC Class Codes: G06F 16/283 Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: Y10S 707/913 Multimedia

Abstract

A system that can analyze a multi-dimensional input thereafter establishing a search query based upon extracted features from the input. In a particular example, an image can be used as an input to a search mechanism. Pattern recognition and image analysis can be applied to the image thereafter establishing a search query that corresponds to features extracted from the image input. The system can also facilitate indexing multi-dimensional searchable items thereby making them available to be retrieved as results to a search query. More particularly, the system can employ text analysis, pattern and/or speech recognition mechanisms to extract features from searchable items. These extracted features can be employed to index the searchable items.

Claims

1. A multi-dimension search system, comprising:

an input analyzer that extracts features from an input; and

a search engine that formulates a search query based at least in part upon a subset of the extracted features.

2. The multi-dimension search system of claim 1, the input is image data.

3. The multi-dimension search system of claim 1, the input is a combination of at least two of text, visual and audio data.

4. The multi-dimension search system of claim 1, the search engine comprises:

a multi-dimension index generator that collects and indexes search-related information across a plurality of dimensions; and

an index item locator component that conducts a search across one or more of the plurality of dimensions based at least in part upon the subset of extracted features.

5. The multi-dimension search system of claim 4, further comprising a text analyzer, a sound analyzer and an image analyzer that facilitates indexing the search-related information.

6. The multi-dimension search system of claim 1, further comprising at least one of a text analyzer, an image analyzer and a sound analyzer.

7. The multi-dimension search system of claim 6, the text analyzer includes a language parser that extracts the features from the input.

8. The system of claim 6, the sound analyzer includes a speech recognition component that extracts the features from the input.

9. The system of claim 6, the image analyzer includes a pattern recognition component that extracts the features of the input.

10. The multi-dimension search system of claim 1, further comprising a results configuration component that manages a plurality of search results related to the input.

11. The multi-dimension search system of claim 10, the results configuration component includes a filter component that sorts a subset of the plurality of search results in accordance with at least one of a user context, a user preference, a relevancy factor with respect to the input and a device context.

12. The multi-dimension search system of claim 10, the results configuration component includes a ranking component that arranges a subset of the plurality of search results based at least in part upon one of a user preference and a relevancy factor.

13. The multi-dimension search system of claim 10, the results configuration component includes an ordering component that determines a display order with respect to a subset of the plurality of search results.

14. The system of claim 1, further comprising machine learning and reasoning component that employs at least one of a probabilistic and a statistical-based analysis to infer an action that a user desires to be automatically performed.

15. A computer-implemented method of performing a multi-dimensional search, comprising:

receiving an input;

extracting a plurality of features terms from the input;

establishing a plurality of search terms based at least in part upon a subset of the extracted features; and

retrieving a plurality of results based at least in part upon a subset of the search terms.

16. The method of claim 15, further comprising:

recognizing image patterns in the input query; and

converting the recognized imaged patterns into a subset of the search terms.

17. The method of claim 15, further comprising:

gathering search-related data;

analyzing the search-related data; and

indexing the search-related data;

the plurality of results are included within the search-related data.

18. The method of claim 16, further comprising:

configuring a subset of the plurality of search results; and

rendering the subset of the plurality of search results to a user.

19. A computer-executable system comprising:

means for receiving an input;

means for extracting a plurality of features from the input; and

means for generating a search query based at least in part upon a subset of the plurality of features.

20. The computer-executable system of claim 19, further comprising,

means for gathering search-related information across a multi-dimensions;

means for indexing the gathered search-related information; and

means for conducting a search upon the search-related information based at least in part upon the search query.