Multiple web-based content category searching in mobile search application

• US 8,949,266 B2
• Filed: 08/27/2010
• Issued: 02/03/2015
• Est. Priority Date: 03/07/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Vlingo Corporation (Microsoft Corporation)
• Inventors: Phillips, Michael S., Nguyen, John N.
• Primary Examiner(s): Fleurantin, Jean B
• Application Number:
  US12/870,221
• Publication Number:
  US 20110055256A1
• Time in Patent Office: 1,621 Days
• Field of Search: 707/706, 707/709, 707/758, 707/760, 707/769, 707/770, 709/203, 704/7, 704/9, 704/245, 704/256.1, 704/270.1
• US Class Current: 707/769
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

In embodiments of the present invention improved capabilities are described for multiple web-based content category searching for web content on a mobile communication facility comprising capturing speech presented by a user using a resident capture facility on the mobile communication facility; transmitting at least a portion of the captured speech as data through a wireless communication facility to a speech recognition facility; generating speech-to-text results for the captured speech utilizing the speech recognition facility; and transmitting the text results and a plurality of formatting rules specifying how search text may be used to form a query for a search capability on the mobile communications facility, wherein each formatting rule is associated with a category of content to be searched.

Claims

1. A method of searching for web content comprising:

capturing speech presented by a user using a resident capture facility on a mobile communication facility having multiple web-based search facilities;

transmitting at least a portion of the captured speech as data through a wireless communication facility to a speech recognition facility;

receiving, from the speech recognition facility, generated speech-to-text results for the captured speech and a plurality of formatting rules to form a query for a search capability for web content on the mobile communications facility, wherein each formatting rule is associated with a category of content to be searched, and wherein the speech-to-text results are generated based on, at least in part, recognition models adapted from data from a plurality of users, wherein the speech-to-text results include URL usage information configured to enable a user to conduct the search on the mobile communication facility, wherein the URL usage information is included for a plurality of distinct web-based search facilities; and

providing the speech-to-text results, a plurality of base URLs, and the plurality of formatting rules to a web-based search utilizing a first of multiple web-based search facilities, where results of the search are returned to and cached in the mobile communications facility as a first search result, wherein the plurality of formatting rules include rules to combine speech to-text results with the plurality of base URLs to form a search URL.

2. The method of claim 1, wherein the category of content includes at least one of web information, music, videos, audio, and social network related information.

3. The method of claim 1, wherein the search capability for web content comprises a browser on the mobile communication facility.

4. The method of claim 1, further comprising selecting at least one language model from an initial set comprising a plurality of language models;

and transmitting the selected at least one language model to the speech recognition facility, wherein the speech-to-text is generated based on, at least in part, the selected at least one language model.

5. The method of claim 4, further comprising receiving feedback including the selected at least one selected language model provides insufficient recognition output for the speech-to-text results and selecting at least one other language model from the initial set of language models for generating speech-to-text results.

6. The method of claim 4, wherein the selected at least one language model comprises a statistical language model.

7. The method of claim 4, wherein the at least one language model is selected based on the multiple web-based search facilities running on the mobile communication facility.

8. The method of claim 1, wherein the category of content to be searched comprises web information and the formatting rules specify how search text may be used to form a query for web information.

9. The method of claim 1, wherein the category of content to be searched comprises music and the formatting rules specifying how search text may be used include song titles, artist names and music categories.

10. The method of claim 1, wherein the category of content to be searched comprises videos and audio and the formatting rules specifying how search text may be used include video titles and artist names.

11. The method of claim 1, wherein the category of content to be searched comprises social network related information and the plurality of formatting rules comprises at least one formatting rule for a social network.

12. A method of searching for web content comprising:

capturing speech presented by a user using a resident capture facility on a mobile communication facility having multiple web-based search facilities;

transmitting at least a portion of the captured speech as data through a wireless communication facility to a speech recognition facility;

selecting at least one language model from a plurality of language models based at least in part on information relating to the captured speech;

receiving, from the speech recognition facility, generated speech-to-text results for the captured speech and a plurality of formatting rules to form a query for a web browser on the mobile communications facility, wherein each formatting rule is associated with a category of content to be searched, and wherein the speech-to-text results are generated based on, at least in part, recognition models adapted from data from a plurality of users, wherein the speech-to-text results include URL usage information configured to enable a user to conduct the search on the mobile communication facility, wherein the URL usage information is included for a plurality of distinct web-based search facilities; and

providing the speech-to-text results, a plurality of base URLs, and the plurality of formatting rules to a web-based search utilizing a first of multiple web-based search facilities, where results of the search are returned to and cached in the mobile communications facility as a first search result, wherein the plurality of formatting rules include rules to combine speech to-text results with the plurality of base URLs to form a search URL.

13. The method of claim 12, wherein the information relating to the captured speech is based on likely search content.

14. The method of claim 12, further comprising receiving feedback including the selected at least one selected language model provides insufficient recognition output for the speech-to-text results and selecting at least one other language model apart from the plurality of language models for generating speech-to-text results.

15. The method of claim 12, wherein the information relating to the captured speech is selected from a group consisting of usage history for the web browser, a user identification and a current state of at least one web-based search facility.

16. A method of searching for web content comprising:

receiving at least a portion of captured speech as data through a wireless communication facility from a mobile communication facility;

generating speech-to-text results and a plurality of formatting rules for the captured speech based on, at least in part, recognition models adapted from data from a plurality of users;

transmitting the speech-to-text results to the mobile communication facility to search for web content on the mobile communications facility using multiple web-based search facilities, wherein the speech-to-text results include URL usage information configured to enable a user to conduct the search on the mobile communication facility, wherein the URL usage information is included for a plurality of distinct web-based search facilities; and

providing the speech-to-text results, a plurality of base URLs, and the plurality of formatting rules to a web-based search utilizing a first of multiple web-based search facilities, where results of the search are returned to and cached in the mobile communications facility as a first search result, wherein the plurality of formatting rules include rules to combine speech to-text results with the plurality of base URLs to form a search URL; and

wherein each formatting rule is associated with a category of content to be searched.

17. The method of claim 16, wherein the mobile communication facility comprises a global positioning (GPS) capability.

18. The method of claim 16, further comprising transmitting a plurality of formatting rules to form a query for the search capability on the mobile communications facility, wherein each formatting rule is associated with a category of content to be searched.

19. The method of claim 16, further comprising providing feedback based on, at least in part, at least one selected statistical language model.

20. The method of claim 16, wherein the search capability comprises a web browser.