Method and system for providing access to information of potential interest to a user

Patent metadata

Field	Value
Publication number	US-9286385-B2
Application number	US-201213484134-A
Country	US
Kind code	B2
Filing date	May 30, 2012
Priority date	Apr 25, 2007
Publication date	Mar 15, 2016
Grant date	Mar 15, 2016

Abstract

The present invention provides a method and system for providing access to information of potential interest to a user. Closed-caption information is analyzed to find related information on the Internet. User interactions with a TV which receives programming including closed-caption information are monitored to determine user interests or topics.

First claim

What is claimed is:

1. An apparatus comprising:
at least one hardware processor;
a memory storage device maintaining different extraction rules for different types of program; and
a plurality of modules executed by the at least one hardware processor, the modules comprising:
a closed-caption decoder configured to decode a raw closed caption stream for a program and produce closed caption text;
a language detection module configured to determine a language of the closed caption text;
a sentence detection module configured to determine one or more sentences in the closed caption text;
a tagger configured to tag keywords in the closed caption text based on the determined language of the closed caption text and the determined sentences;
a topic extractor configured to request one or more extraction rules relating to a type of the program from the memory storage device, and extract one or more topics from the closed caption text based on the tagged keywords and the one or more extraction rules relating to the type of the program; and
a validation module configured to validate the extracted topics by checking each extracted topic against at least one local source and at least one remote source.

2. The apparatus of claim 1 , wherein the tagger includes one or more natural language processing functions.

3. The apparatus of claim 1 , wherein:
the type of the program identifies a genre of the program; and
the one or more extraction rules relate to the genre identified, such that the extracted topics are relevant to the genre identified.

4. The apparatus of claim 3 , wherein:
the memory storage device includes a genre-rule map providing a mapping between the different extraction rules and different genres.

5. The apparatus of claim 1 , wherein the one or more extraction rules are stored in a rule library.

6. The apparatus of claim 1 , wherein the validation module includes:
a local validation module for checking each extracted topic against at least one local source; and
a remote validation module for checking each extracted topic against at least one remote source.

7. The apparatus of claim 6 , wherein:
at least one local source comprises a local word list;
at least one remote source comprises an online source connected to the apparatus over a network; and
the remote validation module is configured to submit each extracted topic as a query to online source that includes an Internet search engine.

8. The apparatus of claim 1 , wherein the language detection module receives one or more character sets for one or more languages and one or more stop words corresponding to one or more languages as input.

Assignees

• Rathod Priyang
• Nguyen Phuong
• Messer Alan
• Samsung Electronics Co Ltd

Inventors

• Rathod Priyang
• Nguyen Phuong
• Messer Alan

Classifications

• G06F16/7844 Primary

  using original textual content or text extracted from visual content or transcript of audio data · CPC title

• G06F16/7867

  using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings · CPC title

• G06F17/3082

  Physics · mapped topic

• G06F17/30796 Primary

  Physics · mapped topic