Method and apparatus for obtaining information from the web

• US 9,299,348 B2
• Filed: 07/16/2014
• Issued: 03/29/2016
• Est. Priority Date: 01/26/2011
• Status: Active Grant

• Current Assignee: Thaddeus Gabara
• Original Assignee: TrackThings LLC
• Inventors: Gabara, Thaddeus John
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US14/332,427
• Publication Number:
  US 20140330562A1
• Time in Patent Office: 622 Days
• Field of Search: 704231-257, 704270-275
• US Class Current: 1/1
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/953 Querying, e.g. by the use of web search engines
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 21/034 Automatic adjustment
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence

Abstract

An intelligent conversation system augmenting a conversation between two or more individuals uses a speech to text block configured to convert voices of the conversation into text, a determination circuit configured to determine topics from the text of the conversation, search parameters determined by the determination circuit from the topics are sent to an Internet, search results corresponding to the search parameters are received from the Internet; and a memory configured to store the search results received from the Internet. The speech to text block is configured to convert the search results to speech. An earphone is configured to transmit the speech to one of the two or more individuals. The speech is used by one of the individuals to augment the conversation.

Claims

1. An intelligent conversation system augmenting a conversation between two or more individuals comprising:

a speech to text block configured to convert voices of the conversation into text;

a determination circuit configured to determine topics from the text of the conversation, wherein search parameters determined by the determination circuit from the topics are sent to an Internet and search results corresponding to the search parameters are received from the Internet;

a memory configured to store the search results; and

a finite state machine configured to sequence through the search results to generate recall topics.

2. The apparatus of claim 1, wherein

a search engine is configured to operate on the search parameters to generate the search results.

3. The apparatus of claim 1, wherein

the speech to text block is configured to convert the recall topics to speech.

4. The apparatus of claim 3, further comprising:

an interface block configured to apply the speech of the recall topics to one of the two or more individuals.

5. The apparatus of claim 3, further comprising:

an earphone configured to transmit the speech of the recall topics to one of the two or more individuals.

6. The apparatus of claim 5, wherein

the recall topics are used by one of the individuals to augment the conversation.

7. An intelligent conversation system augmenting, a conversation between two or more individuals comprising:

a determination circuit configured to segregate the conversation into topics and to extract search parameters from the topics, wherein

the search parameters are sent to a search engine and

search results corresponding to the search parameters are received from the search engine;

a memory configured to store the search results; and

a finite state machine configured to sequence through the search results to generate recall topics.

8. The apparatus of claim 7, further comprising:

a speech to text block configured to convert voices of the conversation into text.

9. The apparatus of claim 7, wherein

a server is located on the world wide web configured to perform operations corresponding to the search engine.

10. The apparatus of claim 7, wherein

the speech to text block is configured to convert the recall topics to speech.

11. The apparatus of claim 10, wherein

the speech to text block conforms to an AAC (Advanced Audio Codec) standard.

12. The apparatus of claim 10, further comprising:

an interface block configured to apply the speech of the recall topics to one of the two or more individuals.

13. The apparatus of claim 10, wherein

an earphone is configured to transmit the speech to one of the individuals.

14. The apparatus of claim 13, wherein

the recall topics are used by one of the individuals to augment the conversation.

15. A method of augmenting a conversation between two or more individuals comprising the steps of:

segregating the conversation into topics using a determination circuit;

extracting search parameters from the topics using the determination circuit;

sending the search parameters to a search engine;

receiving search results corresponding to the search parameters from the search engine;

storing the search results into a memory; and

sequencing through the search results stored in the memory with a finite state machine to generate recall topics.

16. The method of claim 15, further comprising the steps of:

configuring a speech to text block, to convert voices of the conversation into text.

17. The method of claim 15, wherein

a server located on the world wide web is configured to perform a search of the search results.

18. The method of claim 15, wherein

the speech to text block is configured to convert the recall topics to speech.

19. The method of claim 18, further comprising, the step of:

transferring the recall topics to one of the two or more individuals to augment the conversation.