Voice-enabled web portal system

• US 8,782,171 B2
• Filed: 07/21/2008
• Issued: 07/15/2014
• Est. Priority Date: 07/20/2007
• Status: Expired due to Fees

• Current Assignee: Voice Enabling Systems Technology Incorporated
• Original Assignee: Voice Enabling Systems Technology Incorporated
• Inventors: Karray, Fakhreddine, Sun, Jiping
• Primary Examiner(s): Nguyen, Dustin
• Application Number:
  US12/176,711
• Publication Number:
  US 20090024720A1
• Time in Patent Office: 2,185 Days
• Field of Search: 379/88.1, 379/88.13, 379/88.16, 379/88.03, 707/514, 455/412.2, 704/4, 704/235, 704/270.1, 704/252, 704/9, 704/277, 709/203
• US Class Current: 709/219
• CPC Class Codes: H04M 3/4211 where the identifier is used to access a profile
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A voice-enabled web portal system includes a web portal server and a call manager software module. The web portal server is operable to download data according to parameters of a web portal. The call manager software module is operable to accept a voice query from a user via telephone, to retrieve a portion of the downloaded data in response to the voice query, and to provide the portion of downloaded data to the user via telephone. A method of providing information from a web portal includes downloading data via a web portal according to parameters of the web portal at a predetermined time interval, filtering the downloaded data to produce portal information, and selectively providing portions of the portal information in response to a voice query.

Claims

1. A voice-enabled web portal system, comprising:

a computer server on which is programmed a web portal server, the web portal server including a portal data processor receiving downloaded data and filtering the downloaded data into content areas and identifying automatic speech recognition (“

ASR”

) grammars and portal information for each content area, wherein a user has a user profile that includes a profile username and a profile password and a third party portal username and a third party portal password for a third party web portal, wherein the third party web portal downloads data according to a defined set of parameters, and wherein the web portal server downloads data from the third art web portal; and

a speech server comprising;

a call manager software module operable to accept a voice query from a user via telephone, to retrieve a portion of the downloaded data in response to the voice query, and to provide the portion of downloaded data to the user via telephone; and

a natural language understanding (“

NLU”

) software module, wherein the speech server is operable to use the NLU software module to perform NLU-based vocabulary expansion and phoneme-based garbage model identification to interpret the voice query, wherein the NLU-based vocabulary expansion includes hypernyms, synonyms, or symbol resources, wherein the speech server resides on at least one computing device.

2. The system of claim 1, wherein the user has a user profile that includes parameters defining a desired data set, and wherein the web portal server downloads data according to the parameters.

3. The system of claim 1, wherein the web portal server includes a registration manager module operable to enable a user to create a user profile, to update the user profile, and to delete the user profile.

4. The system of claim 1, wherein the web portal server includes a portal data downloader module operable to download data according to a user profile at a predetermined time interval.

5. The system of claim 4, wherein the portal data downloader module saves the downloaded data in a file using a filename that includes a user ID and a password from the user profile.

6. The system of claim 5, wherein the file is a hypertext markup language, and wherein the portal data processor module converts the hypertext markup language file to a text file.

7. The system of claim 6, wherein the automatic speech recognition grammars are stored in a Nuance Grammar Specification Language format.

8. The system of claim 5, wherein the web portal server includes a user profile manager module that includes a portal information database that stores the portal information from the portal data processor module.

9. The system of claim 1, including a speech server containing the call manager software module and a computer telephone integration module, a text to speech software module, and an automatic speech recognition module.

10. The system of claim 1, wherein the web portal server is operable to transmit the downloaded data to a user computer in response to a query from the user computer.

11. The system of claim 1, including a universal section containing data for all web portals, and a plurality of personal sections each corresponding to an individual web portal.

12. The system of claim 1, wherein the web portal server and the call manager software module use a shared database update protocol, and wherein the call manager software module and the natural language understanding software module use a shared data query protocol.

16. The system of claim 1 wherein the web portal server is configured to access the third party web portal over the Internet using the third party portal username and the third party portal password, and to download the data from the third party web portal over the Internet.

13. A method of providing information from a web portal comprising:

accessing a third party web portal using a third party portal username and a third party portal password of a user in a user profile;

downloading data from the third party web portal onto a server, the data being downloaded via a web portal according to parameters of the web portal at a predetermined time interval;

filtering the downloaded data to produce portal information, wherein said step of filtering the downloaded data to produce portal information includes identifying content areas of the downloaded data, filtering the downloaded data into the content areas, and identifying automatic speech recognition grammars for each content area, and identifying portal information for each content area;

receiving a voice query;

interpreting the voice query using a natural language understanding (NLU) software model, wherein a speech server is operable to use the NLU software module to perform NLU-based vocabulary expansion and a phoneme-based garbage model to detect the voice query and key concepts, wherein the NLU-based vocabulary expansion includes hypernyms, synonyms, and symbol resources;

and

selectively providing portions of the portal information in response to the voice query.

14. The method of claim 13, further comprising:

saving the downloaded data in a file having a file name that includes a user ID and password from a user profile.

15. The method of claim 13, including performing a natural language vocabulary expansion on the content areas, the automatic speech recognition grammars, and the portal information.

19. The method of claim 13 wherein the downloaded data includes an html file and wherein the step of filtering the downloaded data into the content areas includes filtering the html file into the content areas.

17. A voice-enabled web portal system, comprising:

a computer server on which is programmed a web portal server including a portal data downloader operable to download data via a web portal according to parameters of the web portal the web portal server further including a portal data processor receiving the downloaded data and filtering the downloaded data into content areas and identifying automatic speech recognition (“

ASR”

) grammars and portal information for each content area; and

a speech server comprising;

a call manager software module operable to accept a voice query from a user via telephone, to retrieve a portion of the downloaded data in response to the voice query, and to provide the portion of downloaded data to the user via telephone; and

wherein the speech server resides on at least one computing device,

a natural language understanding (“

NLU”

) software module, wherein the speech server is operable to use the NLU software module to perform NLU-based vocabulary expansion and phoneme-based garbage model identification to interpret the voice query,

wherein the NLU-based vocabulary expansion includes hypernyms, synonyms, or symbol resources;

wherein the user has a user profile that includes a profile username and a profile password and a third party portal username and a third party portal password for a third party web portal, wherein the third party web portal downloads data according to a defined set of parameters, and wherein the web portal server is configured to access the third party web portal over a wide-area network and to download data from the third party web portal over the wide-area network.

18. The system of claim 17 wherein the wide-area network is the Internet and wherein the web portal server accesses the third party web portal using the username and password.