Method, medium and apparatus for providing mobile voice web service

• US 9,251,786 B2
• Filed: 01/15/2008
• Issued: 02/02/2016
• Est. Priority Date: 08/24/2007
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Cho, Jeong-mi, Kim, Ji-yeun, Song, Yoon-kyung, Kwak, Byung-kwan, Kim, Nam-hoon, Han, Ick-sang
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US12/007,797
• Publication Number:
  US 20090055179A1
• Time in Patent Office: 2,940 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks

Abstract

Provided are a method and apparatus for providing a mobile voice web service in a mobile terminal. The method includes analyzing a web history of a user from web search logs of the user and generating a voice access list based on the analysis results, and performing voice recognition by dynamically generating a voice recognition syntax according to the generated voice access list. Accordingly, by limiting syntax required for voice recognition by generating a syntax suitable for a web context of the user, efficient voice recognition, which can be performed in a terminal not a server, can be implemented.

Claims

1. A method of providing a voice web service in a mobile terminal, the method comprising:

analyzing a web history of a user, using a processor comprised in the mobile terminal, from web search logs of the user, and generating a voice access list, using the processor, based on a result of the analyzing of the web history of the user;

generating a voice recognition syntax, using the processor, according to the generated voice access list; and

generating a web command, using the processor, by matching input voice of the user with the generated voice recognition syntax,

wherein the voice recognition syntax is generated based on an intention of the user which comprises an operation intended by the user via the input voice of the user.

2. The method of claim 1, wherein the voice access list is generated according to a default site list stored in the mobile terminal of the user and a bookmark list of favorite web sites of the user.

3. The method of claim 1, wherein (a) further comprises:

classifying a field of a site currently accessed by the mobile terminal, according to a uniform resource locator (URL) of the currently-accessed site, thereby obtaining a site classification result;

analyzing hypertext markup language (HTML) sources of web content corresponding to the currently-accessed site; and

extracting a link text for performing a web navigation and a web search in the currently-accessed site from results of analysis of the HTML sources, and

comprises analyzing a voice input intention of the user using the site classification result and the extracted link text and generating a voice recognition syntax according to the user'"'"'s intention.

4. The method of claim 3, wherein comprises extracting keywords from the generated voice access list and the extracted link text and generating a voice recognition syntax from the extracted keywords.

5. The method of claim 3, wherein the voice input intention analysis is performed by analyzing at least one of the user'"'"'s intention of a direct site access, a web navigation, a general web search, and a specific web search according to whether the mobile terminal of the user executes a web browser and whether the mobile terminal accesses a specific web site.

6. A non-transitory computer readable recording medium storing a computer readable program for executing the method of claim 1.

7. An apparatus for providing a voice web service in a mobile terminal, the apparatus comprising:

a content data management unit, implemented by a processor, configured to analyze a web history of a user from web search logs of the user and configured to generate a voice access list based on a result of analyzing of the web history of the user;

a dynamic syntax generator, implemented by the processor, configured to generate a voice recognition syntax according to the generated voice access list; and

a voice analyzer, implemented by the processor, configured to generate a web command by matching input voice of the user with the generated voice recognition syntax,

wherein the dynamic syntax generator generates the voice recognition syntax based on an intention of the user which comprises and operation intended by the user via the input voice of the user.

8. The apparatus of claim 7, wherein the content data management unit comprises:

a voice access list generator configured to generate the voice access list using results of analysis obtained by the web search log analyzer.

9. The apparatus of claim 8, wherein the voice access list generator generates the voice access list according to a default site list stored in the mobile terminal of the user and a bookmark list of favorites sites of the user.

10. The apparatus of claim 7, wherein the content data management unit further comprises:

a web site classifier configured to classify a field of a site currently accessed by the mobile terminal according to a uniform resource locator (URL) of the currently-accessed site, thereby obtaining a site classification result;

a web content analyzer configured to analyze hypertext markup language (HTML) sources of web content corresponding to the currently-accessed site; and

a link text extractor configured to extract a link text for performing a web navigation and a web search in the currently-accessed site according to results of analysis performed by the web content analyzer, and

the dynamic syntax generator further comprises;

a user intention analyzer configured to analyze a voice input intention of the user using the site classification result and the extracted link text; and

a syntax generator to generate a voice recognition syntax according to the user'"'"'s intention.

11. The apparatus of claim 10, wherein the dynamic syntax generator further comprises a keyword extractor configured to extract keywords from the generated voice recognition list and the extracted link text, and

the syntax generator generates a voice recognition syntax from the extracted keywords.

12. The apparatus of claim 10, wherein the user intention analyzer analyzes at least one of the user'"'"'s intention of a direct site access, a web navigation, a general web search, and a specific web search according to whether the mobile terminal of the user executes a web browser and whether the mobile terminal accesses a specific web site.