KR100380829B1 - System and method for managing conversation -type interface with agent and media for storing program source thereof - Google Patents

Abstract

The disclosed invention relates to a system and method for operating an interactive interface using an agent, and a recording medium having recorded thereon a program source.

The present invention displays a dynamic animation character on the display means of the mobile communication terminal, allowing the animation character to take action to listen to the user's voice command or to say content to the user, while the corresponding voice signal is moved. It supports to be output through speaker of communication terminal.

That is, an interface for allowing a user to use the service provided by the mobile communication terminal while talking to the animation character is provided.

Therefore, the present invention has the advantage that it can be easily used by a user having a physical handicap or driving a car by reducing the hassle caused by data input.

Description

SYSTEM AND METHOD FOR MANAGING CONVERSATION -TYPE INTERFACE WITH AGENT AND MEDIA FOR STORING PROGRAM SOURCE THEREOF}

The present invention relates to a user interface operating system and method, and a recording medium having recorded thereon a program source.

In particular, a system and method for operating an interactive interface using an agent that processes voice recognition of a user, outputs a synthesized sound that can be heard by a user through a speaker, and outputs a corresponding dynamic animation character to a display means of a mobile communication terminal. A recording medium having a program source recorded thereon is provided.

Recently, mobile phones are not only able to use functions as mobile phones but also can use services such as personal information management, text message transmission, e-mail and Internet search, and the popularity of mobile phones is rapidly expanding due to the miniaturization and low price of terminals.

Most of the terminals currently used are microphones and keypads as input means for interaction with users, and speakers and display means are used as output means.

Among the input and output means, a microphone and a speaker are mainly used for a telephone call, and a keypad and a display means are mainly used for a function operation of a terminal, data input and progress display.

In addition, most terminals adopt a menu-button method as a user interface. The functions provided by the user terminal are selected by using a menu displayed on the keypad and the display means.

However, the menu-button method adopted as a user interface in the current terminal has the following problems.

First, it is difficult to find and use a desired service because the menu system is complicated.

Because many functions provided in the terminal are usually provided in a multi-level menu form through a small display means of about 40 characters.

For example, if you want to send a text message using Samsung Electronics Co., Ltd. PCS terminal, you have to go through the menu of 4 steps except inputting the message contents and have to press function key more than 20 times.

Second, it takes a lot of effort and time to enter data such as a person's name, the contents of a text message, the contents of a schedule, an e-mail address and contents, or an internet address using about 15 buttons. For example, to enter the contents of a text message that will be sent to Samsung Electronics Co., Ltd., "Scheduled to visit at 2pm on July 7," you must press the function key more than 60 times.

Third, users unfamiliar with the menu-button approach require a user interface that is more familiar and easier to use.

In order to solve this problem, the interface means using voice, which is the most common and easy communication means for human beings, has been developed.

However, the current terminal has only poor computational processing capability and small memory capacity, and generally only about 50 simple voice commands can be accepted as speaker dependent, so the speech recognition technology is only partially used for dialing by name. This does not significantly improve the user interface of.

Accordingly, an object of the present invention is to solve the above problems, and to recognize the voice command or data input by the user and to process the resulting signal output to the display means, the voice command or data recognition An interactive interface operating system and method using an agent for displaying an animation character that dynamically expresses a processing state or service support state or completion state on a display means or outputs a corresponding synthesized sound to a speaker, and a recording medium recording the program source thereof. In providing.

A first embodiment of the present invention for achieving the above object, in the mobile communication system to receive a specific command information from the user and transmits to the processing means, the mobile communication means for outputting the processing result according to the specific command to the user In the user interface operating method, a voice command input by the user is recognized and output as a result signal is displayed on the display means, while an animation character that dynamically expresses the voice command recognition processing progress and completion status display means Outputting the synthesized sound to the speaker or outputting the corresponding synthesized sound to the speaker, while outputting an animation character that dynamically expresses the service function provision state to the display means while the service function corresponding to the recognition processing result is performed. Corresponding In the second step of outputting the vocal sound to the speaker, if the voice command or data recognition fails, the voice command is transmitted to a server wirelessly connected to the mobile communication terminal to transmit a result signal or corresponding animation character or synthesized sound data. It provides a method of operating an interactive interface using an agent, characterized in that configured to include a third step of receiving.

A second embodiment of the present invention for achieving the above object, in the user interface system for receiving a specific command from the user to pass to the processing means, and outputs the processing result according to the specific command to the user, the user input A voice command is recognized and output as a result signal, while an animation character which dynamically expresses the voice command recognition processing progress state and completion state is output to a display means and a corresponding synthesized sound is output to a speaker, and the recognition process is performed. A client agent included in a mobile communication terminal device for outputting an animation character that dynamically represents the service provision state to the display means and a corresponding synthesized sound to a speaker while a service function corresponding to a result is performed; Or day If it fails to recognize, the server comprises a server agent for transmitting the voice command to a server that is wirelessly connected to the mobile communication terminal device to transmit a result signal or a corresponding animation character or synthesized sound data to the client agent. It provides an interactive interface operating system using an agent.

According to a third embodiment of the present invention for achieving the above object, a mobile communication system receives specific command information from a user in a mobile communication system and transmits the same to a processing means, and outputs a processing result according to the specific command to a user. A recording medium on which a user interface operating program source is recorded, wherein a voice command input by a user is recognized and output as a result, a signal is displayed on a display means, and the voice command recognition processing progress state and completion state are dynamically expressed. While the command recognition process for outputting the animation character to the display means or a corresponding synthesized sound to the speaker, and the service function corresponding to the result of the recognition processing is performed, the animation character to dynamically express the service function provision state Service support process for outputting to the display means or the corresponding synthesized sound to the speaker, if the voice command or data recognition fails, the voice command is transmitted to the server wirelessly connected to the mobile communication terminal result signal or the corresponding It provides a recording medium recording the interactive interface operating program source using the agent, characterized in that it comprises a process for receiving the animation character or synthesized sound data.

1 is an overall configuration diagram of an interactive interface operating system using an agent of the present invention.

2 is a flowchart illustrating a method of operating an interactive interface using an agent of the present invention.

<Explanation of symbols for the main parts of the drawings>

100: client agent (CA; CLIENT AGENT)

200: server agent (SA; SERVER AGENT)

110: CA manager 120: small capacity speech recognition engine

130: application service module / CA 140: character driver

150: DB / CA 210: SA manager

220: large speech recognition engine 230: speech-to-text converter

240: large-capacity speech synthesis engine 250: application service module / SA

260: semantic interpreter 270: character generator

280: DB / SA

These objects, features and advantages of the present invention will be more readily understood by reference to the accompanying drawings and the following detailed description.

In the following, the present invention will be described by introducing a first system configuration in which a client agent, which is an interface means in a mobile communication terminal supported by a wirelessly connected server, is included.

Alternatively, a description will be made by introducing a second system configuration in which a server agent supporting the client agent is included in the server.

It recognizes and processes the voice command or data input by the user, and outputs the signal to the display means, while the animation character dynamically expresses the voice command or data recognition processing state or service support state or completion state. An interface operating method for displaying on a display means or outputting corresponding synthesized sound to a speaker and a system implemented to support the same are provided as a preferred embodiment.

In addition, preferred embodiments of the present invention include embodiments such as computer systems and computer program products programmed to carry out the methods of the present invention. According to an embodiment of a computer system, a set of instructions for carrying out a method resides in one or more memories (RAM), which sets of other instructions, such as, for example, disk drives, until needed by the computer system. Can be stored as a computer program product.

Figure 1 shows the overall configuration of the interactive interface operating system using the agent of the present invention.

The interactive interface operating system using the agent of the present invention can be variously applied to a mobile communication terminal (CELLULAR PHONE), a PCS (PERSONAL COMMUNICATIONS SERVICE), a personal information terminal PDA (PERSONAL DIGITAL ASSISTANTS), or a home automation device. Can be.

However, in order to understand the present invention, a description will be given of the second system.

Subsequently, the voice signal for requesting a specific service by the user is called a voice command, and the voice signal that becomes information to be input from the user according to the performance of the specific service by the agent is called voice data.

For example, the voice command is a command for calling a specific service such as "registering a telephone number", and the voice data is "Kim Mi-young" as a person to register and corresponding telephone number data required for registering the telephone number. "02-405 -9956 ".

The interactive interface operating system using the agent of the present invention is included in a client agent (100, CLIENT AGENT; CA) included in a mobile communication terminal and supporting an interactive user interface, and included in a server wirelessly connected to the mobile communication terminal, It is configured to include a server agent (200, SERVER AGENT; SA) for supporting the CA (100).

Referring to FIG. 1, the CA 100 recognizes and processes a voice signal received from a client agent manager 110 and a user agent that controls data input / output and overall functions, and outputs a resultant voice. An application service module / CA 130 for supporting a service corresponding to a recognition engine 120 and a voice command, a character driver 140 for outputting the animation character, and a DB / CA 150 for storing information necessary for operating an interface. It is configured to include.

Referring to FIG. 2, the SA 200 recognizes and processes a server agent major 210 (SERVER AGENT MANAGER; SA manager) that controls data input / output and overall functions and a voice signal received from the CA manager 110. A speech recognition engine 220, a large-capacity speech synthesis engine 240 for generating a voice signal, an application service module / SA 250 for supporting a service corresponding to a voice command, and a character generator 270 for generating the animated character; It is configured to include a DB / SA 280 for storing the character produced by the character generator.

The CA manager 110 is driven according to the user's interactive interface mode request, and then the detailed operation will be described when explaining the method of operating the interactive interface using the agent.

The small-capacity speech recognition engine 120 incorporates a speech recognition algorithm to perform simple speech recognition at a fixed command level.

The small-capacity speech recognition engine 120 receives a speech signal recognition processing request from the CA manager 110 or the application service module / CA 130, extracts the speech pattern, and then extracts the speech pattern to the DB / CA 150. If there is an item that matches the registered voice pattern, the corresponding command is converted into a text form and transmitted to the CA manager 110 or the application service module / CA 130.

The application service module / CA 130 is one or more modules supporting a service corresponding to a voice command received from a user.

The application service module / CA 130 performs various functions such as telephone number registration, voice dialing, schedule registration, text message transmission, e-mail transmission, Internet search, and life information service.

Therefore, the application service module / CA 130 may be added or deleted as necessary.

In addition, the application service module / CA 130 processes the application service, requests the character driver 140 for the appropriate animation character service, and processes the voice data received from the user.

The character driver 140 processes the character animation service request received from the CA manager 110 or the application service module / CA 130.

The character driver 140 processes a dynamic animation character in response to the requirement to be displayed on the display means and outputs a corresponding synthesized sound to a speaker mounted in the mobile communication terminal.

That is, while the animation character speaks, it is possible to use a variety of services such as taking a specific action as if the user is talking to the animation character.

The DB / CA 150 includes a plurality of command information, a plurality of phone number information, a plurality of schedule information, a plurality of email address information, a plurality of character information, and the like, and the information includes a command DB and a phone book DB, respectively. And it can be divided into separate DB such as schedule DB, email address DB and character DB.

The command DB stores a command corresponding to the voice pattern of the voice command in text form.

The telephone directory DB stores telephone number information using the user name as an index.

The schedule DB stores schedule contents using the date and time as an index.

The email address DB stores the email address using the user name as an index.

The character DB stores a compressed image of the basic character and animation used in the mobile communication terminal.

The SA manager 210 receives the service request from the CA 110, outputs a result signal corresponding thereto, and supports retransmission to the CA 110.

In this case, the voice signal transmitted from the CA manager 110 to the SA manager 210 may be a voice command or voice data.

If the voice signal transmitted from the CA manager 110 is a voice command, the SA manager 210 transmits the voice command to the large-capacity voice recognition engine 220 and requests recognition processing.

The SA manager 210 receives the recognition processing result in the text form from the mass speech recognition engine 220 and transmits the recognition processing result in the text form to the semantic interpreter 260 according to the request.

The SA manager 210 receives the meaning of the extracted command using the various recognition processing results output from the semantic interpreter 260, and transmits the meaning of the received command to the CA manager 110.

When the voice signal transmitted from the CA manager 110 is voice data, the SA manager 210 receives the voice data and transmits the voice data to the corresponding application service module / SA 250 and transmits the processing result in text form. Received to transmit to the CA manager 110.

The large-capacity speech recognition engine 220 incorporates a large-capacity lexical recognition algorithm to recognize a speech signal based on a phoneme, convert the speech signal into a text, and output the text.

Since the small voice recognition engine 120 stores some fixed voice commands and recognizes only the commands corresponding to the stored voice commands, the large voice recognition engine is based on speaker-dependent recognition in which the user should memorize the commands. 240 is a speaker independent recognition base that recognizes and extracts various languages.

The reason for implementing the second system by including a server agent in the first system is as follows.

Due to the large volume of the large-capacity speech recognition engine, current technology cannot provide a speaker-independent interface using only a mobile communication terminal.

Therefore, by using the small-capacity speech recognition engine, the large-capacity speech recognition engine included in the server can convert the interface in the speaker-dependent base to the speaker-independent basis.

However, in the future, the miniaturization of the speech recognition engine may provide a speaker-independent interface basis using only the mobile communication terminal, so that the first system is also presented as a range of rights.

The large-capacity speech synthesis engine 240 incorporates a large-capacity speech synthesis algorithm, receives text from the application service module / SA 250, generates the text as a synthesized sound, and retransmits the text to the application service module / SA 250. do.

The meaning interpreter 260 extracts a command intended by a user by analyzing various types of voice commands having the same meaning.

The application service module / SA 250 is a module that actually processes a service corresponding to each voice command.

The application service module / SA 250 generates a prompt message to be provided in the mobile communication terminal using the mass speech synthesis engine 240 and transmits the prompt message to the mobile communication terminal.

The character generator 270 includes a character and animation production tool for mobile communication agent service.

The produced image is mainly compressed by the service provider and stored in the DB / SA 280 in a compressed form.

In this case, individual users may also make and use personal characters through the Internet.

The DB / SA 280 is a master DB that stores the character produced by the character generator and mobile communication terminal user information.

The SA 200 may search for user information stored in the SA and transmit specific animation character or synthesized sound data corresponding to personal information or an anniversary date to the CA 100.

2 is a flowchart illustrating a method of operating an interactive interface using an agent of the present invention.

Referring to FIG. 2, the present invention recognizes a voice command input by a user and outputs a signal as a result, while outputting an animation character that dynamically expresses the voice command recognition processing progress state and completion state to a display means. A first step (S300 ˜ S330) of outputting the synthesized sound corresponding to the speaker;

A second step (S340 ˜ S420) of outputting an animation character dynamically expressing the service function provision state to the display means or a synthesized sound corresponding thereto while the service function corresponding to the recognition processing result is performed; It is configured to include.

In order to understand the interactive interface operating method using the agent of the present invention, the mobile communication means will be described with reference to an embodiment in a process of supporting a schedule registration service.

In describing the above embodiment, 'xx' is spoken for clarity by the character driver that 'a specific dynamic animation character is displayed on the display means and a corresponding synthesized sound is output to the speaker'. , xx action animated character.

When the CA manager 110 is driven according to an interactive interface mode request from the user, the CA manager 110 outputs a dynamic animation character output request signal to the character driver 140.

Then, the character driver 140 provides a greeting animation character and a voice command input prompt in response to the request signal from the CA manager 110 (S300).

For example, 'Hello? What can I do for you? "And you take an action to greet and output an animated character that turns into the action you are listening to.

When the CA manager 110 receives a voice command from the user (S310), the CA manager 110 transmits the input voice command to the small voice recognition engine 120 to perform a recognition process, and provides a voice command recognition animation (S320). )do.

For example, the CA manager 110 takes an action that the voice command has been heard through the character driver 140, and then outputs an animation character that takes an action of working while saying “Please wait”. Support.

Although not shown in the drawing, the voice command recognition process will be described in more detail.

For example, when the small voice recognition engine 120 searches for the text "schedule registration" by searching for the voice command "register a schedule" through the DB / CA 150, the text is stored in the CA manager ( 110).

If the small-capacity speech recognition engine 120 fails to search for the "register schedule" command, the CA manager 110 transmits the voice command and the user ID to the SA manager 210.

Then, the SA manager 210 receives the voice command and makes a request for recognition processing to the large-capacity speech recognition engine 220.

The SA manager 210 transmits the text "schedule registration" to the CA manager 110, which is a result of recognition processing from the mass recognition engine 220.

Then, the CA manager 110 receives the text from the small capacity speech recognition engine 120 or the SA manager 210, and displays the text on the display means (S330).

Although not shown, the CA manager 110 drives the application service module / CA 130 corresponding to the voice command.

In this case, the application service module / CA 130 determines whether an application service corresponding to the voice command requires voice data (S340).

When the voice data is required, the application service module / CA 130 supports the voice data request animation and the prompt to be provided (S350).

For example, the application service module / CA 130 supports an animation character that takes an action of listening while saying “tell me the schedule date and time” through the character driver 140.

When the application service module / CA 130 receives the voice data, for example, “2 pm on August 8” from the user (S360), the application service module / CA 130 transmits the voice data to the small capacity voice recognition engine 120 to recognize the voice. Processing and voice data recognition animation character animation support is provided (S370).

For example, the application service module / CA 130 supports an animation character that takes an action of processing after the action that the user's voice data is received through the character driver 140.

If the small capacity speech recognition engine 120 does not recognize the voice data, the CA manager 110 transmits the voice data not recognized by the small capacity speech recognition engine 120 to the SA 200. In addition, the voice recognition process may be performed by the SA 200, and thus, an animated character and text may be extracted and provided to the user.

The application service module / CA 130 supports the voice data recognition result to be displayed on the display means (S380) and returns to the process of S340.

As a result of the determination of S340, according to the present embodiment, it may be determined that voice data regarding schedule contents is required.

The application service module / CA 130 supports an output of an animation character that takes an action of listening while saying "tell me the schedule" through the character driver 140, and for example, "conference" from the user. Voice data is inputted, and the steps S370 to S380 are performed.

After the step S380, the process goes through the step S340 again.

In this embodiment, the application service module / CA (S130) determines that no further voice data input is required in the present embodiment. However, in the case of other application services, the application service module / CA (S130) does not need to input any voice data necessary to perform a service. The steps of are rotated.

The application service module / CA 130 supports an animation and a prompt confirming whether a service is executed using the input voice command and data.

For example, the character driver 140 may say, “Do you want to register the input schedule?” And support an animation character that takes a listening action.

The application service module / CA 130 determines whether an execution confirmation voice signal is input from the user (S400).

When it is confirmed that the execution confirmation voice signal is input from the user, the application service module / CA 130 supports the execution confirmation voice signal recognition processing and outputs an animation during processing (S410).

For example, after taking an action that has been understood through the character driver 140, an animation character taking an action of recording while saying "is registering" is outputted.

In addition, the application service module / CA 130 stores the schedule registration information in the DB / CA 150, and the animation character taking an action of disappearing while saying “registration completed” through the character driver 140 is present. It supports to be output (S420).

However, when the application service module / CA 130 receives a voice command rejected from the user, the application service module / CA 130 deletes the received voice data received from the DB / CA 150 although not shown in the drawing.

In addition, the application service module / CA 130 takes an action of acquiring it through the character driver 140 and supports an output of an animation character taking an action of erasing the recording while saying "registration canceled".

Although not shown in the drawing, the CA 100 may support to receive and output specific animation character or synthesized sound data corresponding to the personal information or the anniversary of the user.

The present invention is not limited to the embodiments described above, and various modifications and changes can be made by those skilled in the art, which are included in the spirit and scope of the present invention as defined in the appended claims.

According to the present invention, there are the following advantages.

First, even users who are not familiar with the menu-button method can easily and quickly access a desired service by using simple voice commands.

Second, by inputting the data input by voice and automatically recognizing the contents and converting the contents into text, the trouble of pressing a key and the text input time can be shortened.

Third, it can solve the awkwardness and fear of interaction with the machine by supporting the interaction with dynamic characters similar to humans.

Fourth, the physically handicapped person can also easily use the terminal.

Fifth, it is possible to use a mobile phone without using a hand can prevent accidents that can occur while driving a car.

Claims (21)

In the method of operating a user interface in a mobile communication means for receiving a specific command information from a user in a mobile communication system to pass to the processing means, and outputs the processing result according to the specific command to the user, The voice command input by the user is recognized and processed, and as a result, a signal is output and displayed on the display means, while an animation character dynamically expressing the voice command recognition processing progress state and completion state is output to the display means or a corresponding synthesized sound. Outputting the speaker to the speaker; While the service function corresponding to the recognition processing result is performed, a second step of outputting to the display means an animation character that dynamically expresses the service function provision state or a corresponding synthesized sound to the speaker; And when the voice command or data recognition fails, transmitting the voice command to a server wirelessly connected to the mobile communication terminal to receive a result signal or a corresponding animation character or synthesized sound data. Method of operating an interactive interface using an agent. The method of claim 1, wherein the first step A method of operating an interactive interface using an agent, which processes a fixed standard voice command or a similar voice command having the same meaning and outputs a result signal. The method of claim 1, wherein the second step When data is to be input from a user to process the service function, a message for requesting input of specific voice data is output through the speaker, a corresponding dynamic animation character is displayed, and the specific voice data received from the user is output. And outputting an animation character that dynamically expresses the voice command recognition processing progress state and completion state to a display means, or outputs a synthesized sound corresponding thereto to a speaker while performing a recognition process. How to operate the interactive interface. delete The method of claim 1 or 3, wherein the second step Before the service function is performed, a synthesized sound corresponding to a message confirming whether the service function is executed is output to the speaker, an animation character corresponding thereto is generated and output to the display means, and a corresponding voice command is determined and recognized. And if the voice command agrees, determining the service function execution or completion state and outputting an animation character and a synthesized sound corresponding thereto. The method of claim 1, wherein the second step Before the service function is performed, a synthesized sound corresponding to a message confirming whether the service function is executed is output to the speaker, an animation character corresponding thereto is generated and output to the display means, and a corresponding voice command is determined and recognized. And if the voice command agrees, determining the service function execution or completion state and outputting an animation character and a synthesized sound corresponding thereto. The method according to any one of claims 1 to 3, And a fourth step of receiving and outputting specific animation character or synthesized sound data corresponding to a user's personal information or an anniversary from a server wirelessly connected to the mobile communication terminal, and operating an interactive interface using an agent. Way. delete The method of claim 5, And a fourth step of receiving and outputting specific animation character or synthesized sound data corresponding to a user's personal information or an anniversary from the server. The method of claim 6, And a fourth step of receiving and outputting specific animation character or synthesized sound data corresponding to a user's personal information or an anniversary from the server. In the user interface system for receiving a specific command from the user and passing it to the processing means, and outputs the processing result according to the specific command to the user, Outputs a signal of the voice command input by the user and outputs a result signal, while outputting an animation character dynamically expressing the voice command recognition processing progress state and completion state to a display means, and a corresponding synthesized sound to a speaker; A client agent included in a mobile communication terminal device outputting an animation character that dynamically represents the service provision state to the display means and a corresponding synthesized sound to a speaker while a service function corresponding to the recognition processing result is performed; If the voice command or data recognition fails, a server agent for transmitting the voice command to a server that is wirelessly connected to the mobile communication terminal device to transmit a result signal or a corresponding animation character or synthesized sound data to the client agent. Interactive interface operating system using an agent, characterized in that configured to. 12. The method of claim 11 wherein the client agent And a specific animation character or synthesized sound data corresponding to a user's personal information or an anniversary from the server agent and outputs the received animation data. delete The method according to any one of claims 11 to 13, wherein the client agent or server agent And a process of recognizing a fixed standard voice command or a similar voice command having the same meaning and outputting a result signal. A recording medium in which a user interface operating program source is recorded in a mobile communication system for receiving specific command information from a user in a mobile communication system and delivering the same to a processing means, and outputting a processing result according to the specific command to a user. The voice command input by the user is recognized and processed, and as a result, a signal is output and displayed on the display means, while an animation character dynamically expressing the voice command recognition processing progress state and completion state is output to the display means or a corresponding synthesized sound. A command recognition process of outputting the to the speaker; A service support process of outputting an animation character dynamically expressing the service function provision state to the display means or a synthesized sound corresponding to the speaker while the service function corresponding to the recognition processing result is performed; And when the voice command or data recognition fails, transmitting the voice command to a server wirelessly connected to the mobile communication terminal and receiving a result signal or a corresponding animation character or synthesized sound data. Recording medium recording the interactive interface operating program source using the agent. The method of claim 15, wherein the command recognition process is A recording medium having recorded thereon an interactive interface operating program source using an agent, characterized by recognizing and processing a fixed standard voice command or a similar voice command having the same meaning. 17. The process of claim 15 or 16 wherein the service support process is When data is to be input from a user to process the service function, a message for requesting input of specific voice data is output through the speaker, a corresponding dynamic animation character is displayed, and the specific voice data received from the user is output. And a data input support process for outputting an animation character that dynamically expresses the voice command recognition processing progress state and completion state to a display means or a synthesized sound corresponding to the same while performing the recognition process. A recording medium that records an interactive interface operating program source using an agent. delete 18. The process of claim 17, wherein the command recognition process or service support process is When the voice command or data recognition fails, the voice command is transmitted to a server wirelessly connected to the mobile communication terminal to receive a result signal or a corresponding animation character or synthesized sound data. The recording medium that records the interface operating program source. 17. The process of claim 15 or 16 wherein the service support process is Before the service function is performed, a synthesized sound corresponding to a message confirming whether the service function is executed is output to the speaker, an animation character corresponding thereto is generated and output to the display means, and a corresponding voice command is determined and recognized. And if the voice command agrees, determining whether the service function is performed or completed, and outputting an animation character and a synthesized sound corresponding to the service function. The method according to claim 15 or 16, A method of dialogue using an agent, characterized by further comprising an animation character automatic support process for receiving and outputting specific animation character or synthesized sound data corresponding to a user's personal information or an anniversary from a server wirelessly connected to a mobile communication terminal. The recording medium that records the interface operating program source.