User-initiative voice service system and method

• US 8,504,370 B2
• Filed: 02/16/2007
• Issued: 08/06/2013
• Est. Priority Date: 10/23/2006
• Status: Active Grant

• Current Assignee: IP3 2017, Series 200 of Allied Security Trust I (Allied Security Trust)
• Original Assignee: Sungkyunkwan University Foundation For Corporate Collaboration (SungKyunKwan University)
• Inventors: Hong, Kwang Seok, Kwon, Hyeong Joon
• Primary Examiner(s): He, Jialong
• Application Number:
  US11/676,137
• Publication Number:
  US 20080097760A1
• Time in Patent Office: 2,363 Days
• Field of Search: 704/270, 704/270.1, 704/275
• US Class Current: 704/270
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A voice service system which includes a database storing information and is connected with a plurality of terminals by a communication network, comprising a call connection unit for transmitting-receiving a signal, on a voice service to/from each of the terminals, a voice processing unit for interpreting a voice instruction received from the terminal and converting an internally-created voice service document into a voice message, a recognition management unit for extracting a grammar, which is expected to be spoken by a user, from the database, a document management unit for creating the voice service document including the extracted grammar as a voice anchor, and a control unit for controlling information related to the voice anchor matching with the voice instruction to be provided.

Claims

1. A voice service system comprising:

a database storing a plurality of voice nodes and a plurality of voice anchors, wherein each of the plurality of voice nodes includes information to be provided to a user, each of the plurality of voice anchors are keywords of the information to be provided to the user, and each voice node includes at least one voice anchor associated with another voice node;

a call connection unit to receive a voice instruction from a terminal and to transmit a voice message to the terminal in response to the voice instruction, wherein the voice message includes one or more of the plurality of voice anchors;

a voice processing unit to convert the voice instruction received from the terminal into a data format and to convert an internally-created voice service document into the voice message;

a grammar management unit to determine that the converted voice instruction includes data matching one of the plurality of voice anchors and an associated voice node, the grammar management unit further to extract a grammar from the associated voice node, wherein the grammar is registered as matching one of the plurality of voice anchors and expected to be spoken by a user in response to the associated voice node, wherein extracting a grammar from the associated voice node includes

dividing text of the associated voice node according to word phrases,

removing prefixes, suffixes, and special characters from the divided text of the associated voice node to create a word list, and

extracting a word from the word list that matches with one of the plurality of voice anchors stored in the database;

a document management unit for creating the voice service document from the associated voice node ; and

a control unit for controlling information related to the registered voice anchor.

2. The voice service system according to claim 1, wherein the control unit counts the number of voice anchors used and stores a resultant counter in the database.

3. The voice service system according to claim 1, wherein the voice service document comprises a voice extensible markup language document.

4. A voice service method in a voice service system, which includes a database storing data and is connected with a terminal by a communications network, in which the data includes a plurality of voice nodes and a plurality of voice anchors, wherein each of the plurality of voice nodes includes information to be provided to a user, each of the plurality of voice anchors are keywords of the information to be provided to the user, and each voice node includes at least one voice anchor associated with another voice node, the method comprising:

receiving a connection request from the terminal;

transmitting a service guide voice message in response to the connection request to the terminal, the service guide voice message including a voice anchor associated with another voice node;

receiving a voice instruction from the terminal;

determining that the voice instruction includes data matching the voice anchor included in the service guide voice message; and

transmitting, in response to the voice instruction, an information voice message including one or more of the plurality of voice anchors to the terminal, wherein transmitting the information voice message includes

extracting a grammar from the voice node associated with the anchor included in the service guide voice message, the grammar being registered as matching one of the plurality of voice anchors and expected to be spoken by a user in response to the associated voice node, wherein the extracting includes

dividing a text of the associated voice node according to word phrases,

removing prefixes, suffixes, and special characters from the divided text,

creating a word list from the divided text, and

extracting a word from the word list that matches one of the plurality of voice anchors as the grammar,

converting the associated voice node into a voice service document, and

converting the created voice service document into the information voice message.

5. The voice service method according to claim 4, further comprising:

counting the number of voice anchors used and storing a resultant counter in the database.

6. The voice service method according to claim 4, wherein the voice service document comprises a voice extensible markup language document.