Personal voice-based information retrieval system

• US 7,516,190 B2
• Filed: 02/06/2001
• Issued: 04/07/2009
• Est. Priority Date: 02/04/2000
• Status: Expired due to Term

• Current Assignee: Parus Holdings, Inc.
• Original Assignee: Parus Holdings, Inc.
• Inventors: Kurganov, Alexander
• Primary Examiner(s): Vaughn, Jr.; William C
• Assistant Examiner(s): Shingles; Kristie D
• Application Number:
  US09/777,406
• Publication Number:
  US 20010054085A1
• Time in Patent Office: 2,982 Days
• Field of Search: 709/218, 709/219, 709/317, 709/224, 709/203, 379/105, 379/67, 379/88, 370/354, 370/79, 179/2.A, 179/18, 364/188, 364/514, 455/417, 704/275, 704/270.1
• US Class Current: 709/217
• CPC Class Codes: G06F 16/638 Presentation of query results
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/54 for retrieval
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04M 2201/39 using speech synthesis speech synthesis per se G10L13/00
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/405 involving speaker-dependent recognition adaptation to speaker for speech recognition G10L15/07
• CPC Class Codes: H04M 2207/40 terminals with audio html browser
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

The present invention relates to a system for retrieving information from a network such as the Internet. A user creates a user-defined record in a database that identifies an information source, such as a web site, containing information of interest to the user. This record identifies the location of the information source and also contains a recognition grammar based upon a speech command assigned by the user. Upon receiving the speech command from the user that is described within the recognition grammar, a network interface system accesses the information source and retrieves the information requested by the user.

Claims

1. A method for allowing users to use speech commands to obtain information from a pre-defined portion of a pre-selected web site in audio format, said method comprising the steps of:

(a) providing a computer having a speech processor, said computer being operatively connected to the internet and to at least one phone;

(b) providing a URL to said computer, said URL indicating a pre-selected web site from which the information is to be retrieved;

(c) using said computer to designate a pre-defined portion of the pre-selected web site which contains the information to be retrieved;

(d) using said computer to identify a named object associated with the content of the information to be retrieved;

(e) using said computer to generate a regular expression based on said pre-defined portion of said pre-selected web site and said named object, said regular expression corresponding to said content of said information to be retrieved, wherein said regular expression is a text string used for describing a search pattern;

(f) providing a speech command to said speech processor, said speech command corresponding to said regular expression;

(g) said speech processor converting said speech command to a digital-form command;

(h) said computer receiving said digital-form command from said speech processor, said computer assigning said regular expression to said digital-form command;

(i) after steps (a) through (h) are completed, transmitting an audio speech command to said speech processor, said speech command corresponding to said regular expression;

(j) said speech processor converting said speech command to said digital-form command;

(k) said computer receiving said digital-form command from said speech processor;

(l) said computer retrieving said regular expression corresponding to said digital-form command;

(m) said computer retrieving the information from the pre-defined portion of the pre-selected web site corresponding to said regular expression when the requested information is found in the pre-defined portion of the pre-selected website;

(n) said computer searching said pre-selected web site for said named object when the requested information is not found in the pre-defined portion of the pre-selected web site;

(o) said computer providing said retrieved information to said speech processor;

(p) said speech processor converting said retrieved information into an audio message; and

(q) said speech processor forwarding said audio message to a user.

2. The method of claim 1 wherein the pre-defined portion of the pre-selected web site being retrieved is periodically updated.

3. The method of claim 1 wherein the step of providing a URL to a computer is performed by a user.

4. The method of claim 1 wherein the step of using said computer to designate a pre-defined portion of the web site which contains the information to be retrieved comprises the steps of:

displaying the web site on a graphical display operatively connected to the computer; and

using computer software to select the pre-defined portion of the pre-selected web site which contains the information to be retrieved.

5. The method of claim 4 wherein the step of using said computer to designate a pre-defined portion of the web site which contains the information to be retrieved is performed by a user.

6. A system for retrieving information from a pre-defined portion of a pre-selected web site by uttering speech commands into a phone and for providing to a user retrieved information in an audio form, said system comprising:

a server, said server operatively connected to the internet and to at least one phone, said server comprising;

telephony hardware, said telephony hardware operatively connected to said phone and to said server;

at least one speech recognition engine, said speech recognition engine operatively connected to said server and to said telephony hardware;

a speech synthesis engine, said speech synthesis engine operatively connected to said server and to said telephony hardware; and

a call processing system, said call processing system configured to receive speech commands through said telephony hardware and forward said speech commands to said speech recognition engine and said call processing system further configured to receive an audio message from said speech synthesis engine and forward said audio message through said telephony hardware;

a first instruction set stored on said server, said first instruction set configured to identify the pre-defined portion of the pre-selected web site and to identify a named object associated with the content of the information to be retrieved, said pre-defined portion containing the information to be retrieved from the web site, said first instruction set comprising;

a uniform resource locator address for said web site; and

the named object;

a second instruction set stored on said server, said second instruction set configured to generate a regular expression based on said pre-defined portion of said pre-selected web site and said named object, said regular expression corresponding to said content of said information to be retrieved, wherein said regular expression is a text string used for describing a search pattern;

a recognition grammar corresponding to each said instruction set and corresponding to a speech command;

said speech recognition engine configured to receive said speech command and to select the corresponding recognition grammar, said speech recognition engine further configured to retrieve each said instruction set corresponding to said recognition grammar upon receiving said speech command;

a web browser operatively connected to said server, said web browser including at least a content extraction agent, a content fetcher, and a content descriptor file, said web browser configured to access said pre-defined portion of said web she defined by said instruction sets and to retrieve said information defined by said instruction sets;

said speech synthesis engine configured to convert the retrieved information from said pre-defined portion of said pre-selected web site into an audio message, and said speech synthesis engine further configured to transmit said audio message to said user.

7. The system of claim 6 wherein the phone is a landline telephone.

8. The system of claim 6 wherein the phone is a wireless telephone.

9. The system of claim 6 wherein the phone is an internet protocol telephone.

10. The system of claim 6 wherein the server is operatively connected to a local area network.

11. The system of claim 6 wherein the server is operatively connected to a wide area network.

12. The system of claim 6 wherein the server is operatively connected to the Internet.

13. The system of claim 6 further comprising a database operatively connected to the server, the database configured to store said instruction set and said recognition grammars.

14. The system of claim 6 further comprising computer software stored on the server, said computer software configured to create said instruction set based on user-defined information.

15. The system of claim 6 further comprising:

a graphical display operatively connected to the server, said graphical display configured to display the pre-selected web site; and

computer software stored on the server, said computer software configured to select the pre-defined portion of the pre-selected web site which contains the information to be retrieved.

21. The system of claim 6 wherein the named object is selected from the group consisting of:

“

weather”

, “

forecast”

, “

high”

, “

low”

, “

radar”

, “

temp”

, “

temperature”

, “

humidity”

, “

humidity level”

, “

wind”

, “

wind speed”

, “

wind direction”

, “

pressure”

, “

sunrise”

, “

sunset”

, “

time”

, “

month”

, “

day”

, “

stock”

, “

stock quote”

, “

news”

, “

news reel”

, “

airline”

, “

carrier”

, “

flight”

, and “

flight number”

.

16. A method for allowing a phone user to set up and subsequently retrieve information in an audio format from a pre-defined portion of a pre-selected web she, said method comprising the steps of:

providing a server operatively connected to the internet and to at least one phone, said server being operatively connected to a speech recognition engine and to a speech synthesis engine;

providing a first instruction set stored on said server for identifying the pre-defined portion of a pre-selected web she containing the content of the information to be retrieved from the web site, said first instruction set comprising;

a uniform resource locater address for said web site; and

a named object associated with the content of the information to be retrieved;

providing a second instruction set stored on said server for generating a regular expression based on said pre-defined portion of said pre-selected web site and said named object, said regular expression corresponding to said content of said information to be retrieved, wherein said regular expression is a text string used for describing a search pattern;

providing a speech command to said speech recognition engine, said speech command corresponding to said instruction sets;

said speech recognition engine assigning said speech command to a recognition grammar, said speech command and said recognition grammar corresponding to each said instruction set;

transmitting said speech command to said speech recognition engine;

said speech recognition engine receiving said speech command and selecting the corresponding recognition grammar;

said server retrieving each said instruction set corresponding to said recognition grammar;

said server accessing said pre-defined portion of said pre-selected web site defined by said instruction sets and retrieving said information defined by said instruction sets when the requested information is found in the pre-defined portion of the pre-selected web site;

said server searching said pre-selected website when the requested information is not found in the pre-defined portion of the pre-selected web site;

said speech synthesis engine converting the retrieved information from said pre-selected web site into an audio message; and

said speech synthesis engine transmitting said audio message to said user.

17. The method of claim 16 wherein the step of providing at least one instruction set to the server is performed by the user.

18. The method of claim 16 wherein the step of providing at least one instruction set to the server comprises the steps of:

displaying the web site on a graphical display operatively connected to the server; and

using computer software to select the pre-defined portion of the pre-selected web site which contains the information to be retrieved.

19. The method of claim 18 wherein the step of providing at least one instruction set to the server is performed by the user.

20. The method of claim 16 wherein the pre-defined portion of the pre-selected web site being retrieved is periodically updated.