WO2002039422A2

WO2002039422A2 - Voice telephone book service system using voice recognition and method thereof

Info

Publication number: WO2002039422A2
Application number: PCT/KR2001/001898
Authority: WO
Inventors: Choong-Hee Cho
Original assignee: Mc Global, Inc.
Priority date: 2000-11-10
Filing date: 2001-11-08
Publication date: 2002-05-16
Also published as: WO2002039422A3; KR20010100037A

Abstract

The present invention relates a voice telephone book service system to automatically call by voice recognition and a method for the same, particularly, the method comprising making a phone call a communication partner by voice only and automatically putting the caller through to the partner, instead of finding out a phone number of the partner with common personal telephone book. The above described invention is to provide a technique to search the subject subscriber by internaly analyzing both of the voice input name and the registered name of the subscriber by means of voice recognition engine; and a specific web program to input the name and phone number of the subscriber after connecting to a desired web server through internet when the subscriber is registered.

Description

VOICE TELEPHONE BOOK SERVICE SYSTEM USING VOICE

RECOGNITION AND METHOD THEREOF

BACKGROUND OF THE INVENTION

1. Field of the Invention

The present invention relates to a voice telephone book service system to

automatically call by voice recognition and a method for the same, particularly, the

method comprising making a phone call to a communication partner by voice only and

automatically putting the caller through to the partner, instead of finding out a phone

number of the partner in any common personal telephone book.

2. Description of the Related Art

The existing dialing mode has some drawbacks, for instance, is troublesome to

browse through a phone book itself; needs to search a subject subscriber at least one

time even the phone number of the subscriber is recorded in the book in order to

identify it; has a difficulty in efficiently managing phone numbers since a caller has

generally several phone numbers in his(her) pocket phone book and often modifies parts

of them and/or writes the modified numbers on any memo paper; may generate error in

dialing caused by the operation mistake of push-button telephones; and has an inconvenience to call repeatedly for several times equal to number of the

communication partners and/or subscribers.

In order to solve problems mentioned above, for example, a method to register

the phone number of a subject subscriber in wire/wireless phone terminals was

introduced, however, it has restricted to be used in a wide application as it could be

implemented by only the registered telephone set and has limited numbers to be

registered. In addition, when an user chooses the automatic calling function by voice,

he(she) needs to input and record name and address of the communication partner into

his(her) wire/wireless phone terminal to be used by his(her) voice. Only in such case, it

is executed to compare the voice corresponding to the input name with the voice to be

registered and support the speaker dependent function to allow the auto-connection of

phone call. Alternatively, it applies the technology having reduced voice recognition

rate that, when the voice corresponding to name is registered in the terminal to be

employed, the noise circumstance at registering should be similar to the environmental

condition at using it to recognize the voice, to thereby have the limitation of utilizing in

various application circumstances.

SUMMARY OF THE INVENTION It is, therefore, an object of the present invention is to provide convenient use

and efficient management of a phone book with eliminating the limitation of any

existing personal phone book and/or the built-in phone book in wire/wireless phone

terminal, comprising producing the personal phone book for oneself by freely using

internet and dialing it with voice.

The present invention is directed toward achieving several technological tasks,

for instance, to allow the registration of names of subject partners independent of

number of the partners by accessing to a certain web server through internet instead of

the wire/wireless phone terminal to be used; to provide a particular voice recognition

manner by the speaker independent function with no need of further inputting voice

corresponding to registered name of the partners; and, if it is only known of phone

number, to provide a variety of value-added services including the recognition of

numbers spoken by an user and making a phone call.

To achieve the object described above, the invention comprises to provide a

technique for searching a subject partner by internally analyzing both of the voice input

name and the registered name of the partner by means of voice recognition engine; a

specific web program able to input name, phone number and other information of the

partner after connecting to a desired web server through internet at the registration of the partner; and to provide a function for searching a text result obtained by utilizing

said recognition engine from the input voice in a particular partner collection database

and for performing auto-dialing action after accepting identification of partner by the

user.

Briefly, the present invention relates to provide an auto-dialing function by

voice recognition, comprising easily and freely producing a personal phone book for

himself(herself) through internet by an user and to automatically call a partner with only

voice by using the produced phone book. Therefore, it will be believed that the present

invention can eliminate the major inconvenience of browsing through a common phone

book and provide multi-channel speaking and multi-address transmission and other

functions therewith.

BRIEF DESCRIPTION OF THE DRAWINGS

The above objects, features and advantages of the present invention will

become more apparent from the following detailed description when taken in

conjunction with the accompanying drawings, in which:

Fig. 1 is an overall schematic block diagram illustrating auto-dialing function

by voice recognition according to a preferred embodiment of the present invention; and

Fig. 2 is a flow chart illustrating the movement of a particular system among plural systems shown in Fig. 1.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT

A preferred embodiment of the present invention will now be described with

reference to the accompanying drawings. The matters defined in the description such as

a detailed construction is nothing but the ones provided to assist in a comprehensive

understanding of the invention. Thus, it is apparent that the present invention can be

carried out without those defined matters. Also, well-known functions or constructions

are not described in detail since they would obscure the invention in unnecessary detail.

Fig. 1 is a schematic block diagram illustrating a system according to a

preferred embodiment of the present invention. The system available for typically

calling/receiving the call by accessing a wire/wireless telephone 100 and 110 of any

customer to Public Switched Telephone Network (hereinafter referred to as PSTN) 10

and Private Branch Exchange (hereinafter referred to as PBX) 20 comprises a voice

telephone book service device (hereinafter referred to as VTBS device) 30; a voice

recognition server 40 to receive the input name by voice, analyze it and return a name

character sequence obtained from the analyzed result; a particular web server 50 to be

accessed by the above PBX 20, VTBS device 30 and the server 40 and having a built-in

personal database and/or database containing names, phone numbers and/or business addresses of communication partners (or subscribers); and a personal computer, that is,

PC 70 connecting with the above web server 50 through internet 60.

According to such system of the present invention, an user can register a

communication partner (or subscriber) in his(her) personal DB sever through the

connection with the web server 50 by means of PC 70. More particularly, by inputting

ID and password of the user, the system determines whether he(she) is an existing

person who was already registered and, if he(she) was not yet registered, sends a

registering picture to lead hem(her) to the registration procedure, whereas another

picture to manage his(her) own DB in case he(she) has been registered.

When the user has been registered, the system directly displays a picture

showing the personal DB information of the user. On such screen, it is possible to

register data concerning names, phone numbers, business addresses and similar

information of further added subscribers on said DB after receiving them; modify,

delete and/or search existing information; and designate a group for multi-address

transmission, add new members to the group and or delete existing members.

For the information already stored, the system exhibits a message to show the

duplication of information and, otherwise, stores the information in the personal DB if it

is a new one, and can repeatedly stores many times equal to number of desired partners . The NTBS device 30 receives the call through PSTN 10 and PBX 20 in case

that the user calls the phone number provided from VTBS device 30 by the

wire/wireless telephones 100 and 110. Subsequently, the wireless phone 110 obtains

information regarding the customer, that is, the caller by using ANI information,

whereas the wire phone 100 directly obtains the information from the caller's input. If it

is supported with source number displaying service, the auto-identification of customer

can be obtained.

Thereafter, the inventive system sends the result analyzed by the recognition

server 40 to the caller in return to identify the name, after receiving the name which was

inputting by the voice of caller. In other words, the server 40 analyzes the input name

after receiving it by. the caller's voice then sends the analyzed result in a form of name

characters sequence in return to the caller. The output result is identified by the caller

through the VTBS device 30. The identification of output result means that the system

provides the searched name to the caller, then, receives the identified result by means of

voice or button.

Using the identified name, the phone number corresponding to the name can be

obtained by searching content of the personal DB in the web server 50. With the

obtained information, the VTBS device 30 implements auto-dialing the phone number.

Concerning a series of the processes from inputting name of partners by a

customer to auto-dialing, the system according to the present invention including

NTBS device 30, the voice recognition server 40 and web server 50 is described in

detail hereinbelow.

Referring to Fig. 2, it shows a flow chart illustrating the movement of major

parts among the apparatus shown in Fig. 1 according to the present invention, such as

the NTBS device 30, the voice recognition server 40 and the web server 50.

The system is operated by a plurality of steps comprising calling the NTBS

device 30 by wire/wireless telephone sets 100 and 110 particular (S10); introducing

different services to be provided to a customer after receiving the call from said NTBS

device 30 (S20); asking the selection of any one among the services (S30); selecting one

of the services by the customer (S40); selecting the NTBS service (S50); requesting the

customer to input name of a subject with voice to provide the customer with the NTBS

service (S60); inputting the name of partner with voice by the customer through the

phone call (S70); requesting the storage of the input voice as a digital type data file to

analyze it by the voice recognition server, and the analysis/processing of the file having

information of input voice (S80); making the customer to identify whether an output of characters sequence from the analyzed result of the voice recognition server is identical

to the input name by the customer (S90); after the identification of name, if it is yes

(that is, both are same) connecting to the web server having the personal DB registered

through internet and searching the phone number of the subject partner to get it (SI 00)

and identifying whether the partner is registered in the DB (SI 10); otherwise, if it is no

(that is, both are not same) asking the registration of the partner (SI 20); alternatively,

after searching the DB, if the partner is existing in the DB, taking the phone number of

the partner and auto-calling the partner (SI 30); speaking to the partner by the connected

phone and completing it.

As for such step S80, the file is transmitted to the voice recognition server by

means of a socket program using TCP/IP protocol. After analyzing the file, its result is

transmitted in a form of characters sequence as an output of the server in return. In other

word, the analysis/processing of file is completed after transforming a sound form of the

input name by the customer into a characters sequence.

The NTBS device 30 asks the customer's identification whether the characters

sequence output as the analyzed result from the voice recognition server 40 is same to

the input name by the customer (step S90); and transforms the internal characters

sequence of name into the voice audible by the customer. After identifying the name information, if both are same, it is executed the step

SI 00 for connecting with the web server having the personal DB registered through

internet to get the phone number of the subject partner.

The customer must register names, phone numbers and other information of

desired communication partners in the personal DB before utilizing the service

mentioned above in order to search the partners by employing such information and find

out desired phone numbers and implement further processes. After accessing to the web

server, it is executed the step SI 10 checking the existence of a subject partner in the

personal DB. In such step, if the partner is not included in the DB, the system asks the

customer to register the partner in the DB (step SI 20).

Alternatively, when it is confirmed from the analyzed result that the partner is

registered in the DB, the system gets the phone number of such partner and executes the

auto-dialing process (step SI 30) with this information, to thereby permit the customer to

talk with the partner over the connected phone.

Meanwhile, it will be believed that the system and method according to the

present invention described above can implement the multi-speaking and multi-

addressed transmission functions.

With regard to the multi-addressed transmission, an user can produce a phone number DB for himself(herself) through internet 60. When the user wants to find out

any phone number, he(she) needs to access to the NTBS device 30 with a specific phone

number. Thereafter, the device identifies the customer through AΝI for a wireless

telephone 110 whereas, in case of the wire telephone 100, processes after receiving the

input information such as ID and password. When the user speaks a group to be

searched to find out the group phone number, the voice recognition server 40 recognizes

words of the user, inquires a specific DB pre-registered through internet, transmits the

group phone number information obtained from a searching result and makes a phone

call to such group to allow the multi-speaking process.

As for the multi-addressed transmission (which is a service to recognize voice

as the customer asks a subject group to be recorded in a voice mail box, NMB, and to be

transmitted when several communication partners are existing; to search and call such

group; and to inform the content of such VMB to all of the partners, the user can

produce a phone number DB for himself(herself) through internet 60. When the user

wants to find out any phone number, he(she) also needs to access to the NTBS device

30 with a specific phone number. Afterward, the device identifies the customer through

AΝI for a wireless telephone 110 whereas, in case of the wire telephone 100, processes

after receiving the input information such as ID and password. When the user intends to execute the multi-addressed transmission, he(she) should choose the multi-addressed

transmission item among a menu of the device 30; implement the recordation of desired

message to be transmitted; then, speak a group to be searched. The voice recognition

server 40 recognizes words of the user, inquires a specific DB pre-registered through

internet, transmits the multi-addressed transmission group phone number information

obtained from a searching result and makes up a phone call to such transmission group

to complete the transmission of message.

As described above, according to the voice telephone book service system to

automatically call by voice recognition and a method for the same of the present

invention, it will be believed that the present invention can reduce disadvantages of

known art, more particularly, remove the inconvenience to browse through a phone

book itself; prevent error generated in dialing by the operation mistake of push-button

telephones; has a benefit to conveniently make a phone call to a communication partner

by voice only and automatically putting the caller through to the partner without finding

out a phone number of the partner with common personal telephone book. Additionally,

the present invention can efficiently prevent the risk of auto-dialing process during

operation because it has the partner name recognition and (phone) number recognition

functions. Other than the above described advantages, it will be appreciated that the

present invention has a valuable feature of eliminating the inconvenience which a caller

should call to everyone of a subject group, that is, the inconvenience to call repeatedly

for several times equal to number of the communication partners, since it provides the

multi-addressed transmission service to permit auto-dialing to the group with no

limitation to individual partners by inputting voice of the caller just once.

While the invention has been shown and described with reference to certain

preferred embodiments thereof, it will be understood by those skilled in the art that

various changes in form and details may be made therein without departing from the

spirit and scope of the invention as defined by the appended claims.

Claims

What Is Claimed Is:

1. A voice telephone book service system with voice recognition for typically

calling/receiving the call by accessing a wire/wireless telephone 100 and 110

of a customer to PSTN 10 and PBX 20, comprising a NTBS device 30; a

voice recognition server 40 to receive the input name with voice, analyze it

and return a name characters sequence obtained from the analyzed result; a

web server 50 to be accessed by the above PBX 20, VTBS device 30 and the

server 40 and having a built-in personal database and/or database containing

names, phone numbers and/or business addresses of communication partners;

and a personal computer, PC 70 connecting with the above web server 50

through internet 60.

2. A voice telephone book service method with voice recognition executed by a

plurality of steps comprising calling the NTBS device 30 by wire/wireless

telephone sets 100 and 110 particular (S10); introducing different services to

be provided to a caller after receiving the call from said NTBS device 30

(S20); asking the caller to select any one among the services (S30); selecting

one of the services by the caller (S40); selecting the NTBS service (S50);

requesting the caller to input name of a subject with voice to provide the caller with the NTBS service (S60); inputting the name of partner with voice

by the caller through the phone call (S70); requesting the storage of the input

voice as a digital type data file to analyze it by the voice recognition server,

and the analysis/processing of the file having information of input voice

(S80); making the caller to identify whether an output of characters sequence

from the analyzed result of the voice recognition server is identical to the

input name by the caller (S90); after the identification of name, if it is yes,

that is, both are same, connecting to the web server having the personal DB

registered through internet and searching the phone number of the subject

partner to get it (S 100) and identifying whether the partner is registered in the

DB (SI 10); otherwise, if it is no, that is, both are not same, asking the

registration of the partner (SI 20); furthermore, after searching the DB, if the

partner is existing in the DB, taking the phone number of the partner and

auto-calling the partner (SI 30); speaking to the partner by the connected

phone and completing it.

3. The method according to Claim 2, wherein it permits the multi-addressed

transmission and the multi-speaking functions.