KR101741237B1 - System and method for providing multi modal typed interactive auto response service - Google Patents

Abstract

According to an embodiment of the present invention, a bidirectional automatic answering service system provides a bidirectional answering service of a multimodal form to a user terminal having a multimodal interface, and includes an application server and a media server.
Here, the application server creates a session for the bidirectional automatic answering service with the user terminal using the IMS (IP Multimedia Subsystem) call session control protocol, and is connected to the screen interface of the user terminal. The media server is connected to a voice interface of a user terminal, wherein the voice interface outputs voice information synchronized with a screen output of the screen interface according to a scenario of a bi-directional automatic answering service, and transmits voice information. At this time, a session is created with the application server using the IMS call session control signaling protocol and operates according to the control command received from the application server.

Description

TECHNICAL FIELD [0001] The present invention relates to a bi-directional automatic response system using a multimodal interface,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a bidirectional automatic response system using a multimodal interface and a method thereof, and more particularly to a system and a method for providing a bidirectional automatic response service combined with a voice interface and a screen interface.

Generally, an IVR (Interactive Voice Response) service is a service for guiding service information to a customer, accessing service information requested by a customer through a DB or Host, converting the service information into voice, and providing the service. According to this IVR service, a user presses a keypad to transmit a dual-tone multi-frequency signaling (DTMF) signal in order to exchange information with the other party during a call. The system then combines these DTMF signals to perform predefined services, such as entering a credit card number, entering a password, selecting a menu, and so on.

As described above, in the conventional IVR service, the user guides the user through the voice prompt to select the corresponding service information by a key or voice of the telephone by one step, and the user performs various operations to reach desired service information.

However, in recent years, the IVR service has been demanding more complex interactions to handle more work than ever before. Therefore, the conventional IVR service based on voice and DTMF signals has become less scalable and convenient.

Accordingly, according to the trend of replacing the conventional IVR service, IVVR (Interactive Voice & Video Response) service, which provides an automatic response service of video and audio by adding a video content providing function to a conventional IVR service, .

This IVVR service is a concept that can provide the IVR service to the customers as a video, and it can be said that it is one of the multimodal services that is currently in the spotlight.

Here, the multimodal service means a service using a multimodal interface. The multimodal means a plurality of modalities, and the modality means each sensory channel such as visual, auditory, tactile, taste, and smell. According to this multi-modal service, a user can access voice, data, video, audio, etc. with one or more modalities and receive with different modalities.

In recent years, as the terminal has been miniaturized and intelligent, and research has been conducted on input methods that are more convenient and easy to use by users, the interest in multi-modal interfaces has increased, and IVR service is not simply a voice- And is provided as an IVVR service using a built-in multimodal interface.

FIG. 1 is a view schematically showing a configuration of a conventional IVVR system.

Referring to FIG. 1, a user terminal 10 is a terminal that provides a multimodal interface, and includes a screen interface (not shown) and a voice interface (not shown).

A screen interface (not shown) of the user terminal 10 is connected to the IVVR server 30 through the data network 20 and a voice interface (not shown) of the user terminal 10 is connected to the voice communication network 40 To the media server 50 via the Internet.

In this manner, the screen interface (not shown) and the voice interface (not shown) of the user terminal 10 are connected to the IVVR server 30 and the media server 50 using different communication protocols, respectively.

Therefore, in order to provide the IVVR service by synchronizing the screen interface (not shown) and the voice interface (not shown), the IVVR server 30 and the media server 50 must cooperate with each other. . For this reason, the media server 50 must have an SCXML (State Chart XML) engine. In addition, in order to provide the IVVR service, the media server 50 must be a video media server.

However, since the media server 50, which is now popular, is a voice-based media server 50 without a SCXML (State Chart XML) engine, it is not implemented to enable multimodal services.

Therefore, in order to provide the IVVR service, there is a burden of replacing the media server 50 currently being provided with a new media server 50 having an SCXML engine and having a high video streaming-enabled value. However, since the IVVR service provider and the media server 50 are largely separate from each other, replacement of the new media server 50 is not easy. As a result, these problems are becoming a major obstacle to the commercialization of IVVR services.

In IVVR service, a web browser is installed and an internet connection is possible. In addition to a voice interface for realizing a call function of the terminal, a service is provided through a web to a user terminal having a screen interface such as a touch screen, So that the call can be made.

In this case, in the case of the conventional IVVR service using the touch method, the DTMF method is used for the menu selection method included in the image screen. That is, when the user touches a specific menu area, the user terminal confirms the coordinate value of the touched menu area and transmits the corresponding DTMF signal to the IVVR server.

Accordingly, the user terminal must have a configuration for converting the touch coordinate value into the DTMF signal, and the IVVR server also needs a separate device for extracting and analyzing the touch coordinate value from the DTMF signal.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a system and a method for providing a bi-directional automatic response service using a multimodal interface based on an IMS (IP Multimedia Subsystem) network.

According to one aspect of the present invention, a bi-directional answering system is provided. A bidirectional automatic answering system for providing a multi-modal bidirectional automatic answering service to a user terminal equipped with a multimodal interface, the system comprising: an IMS (IP Multimedia Subsystem) call session control protocol, An application server which creates a session for an automatic answering service and is connected to a screen interface of the user terminal; And generating a session with the application server using the IMS call session control signaling protocol, wherein the voice interface of the user terminal in response to a control command received from the application server through the session, And outputting audio information synchronized with a screen output of the screen interface according to a service scenario.

According to another aspect of the present invention, a bi-directional automatic answering service method is provided. The method includes the steps of: providing an application server connected to a screen interface of a user terminal; and a media server connected to a voice interface of the user terminal, the method comprising: Creating a session for the bidirectional voice response service with the user terminal using an IP multimedia subsystem call session control protocol; Wherein the application server generates a session with the media server using the IMS call session control protocol and transmits a control command for the bidirectional voice response service to the media server, The voice information synchronized with the screen output of the screen interface is transmitted through the voice communication channel set with the user terminal.

According to the embodiment of the present invention, it is not necessary to replace the existing equipment with new dedicated equipment by providing the bi-directional automatic response service using only the equipment based on the IMS standard.

In addition, a menu selection signal is transmitted using a HyperText Transfer Protocol (HTTP) method on a SIP session, so that a configuration for analyzing menu selection coordinate values is not required.

In addition, since the service structure is capable of interworking with a conventional media server using a general protocol called SIP (Session Initiation Protocol), unlike the conventional method, a user terminal does not need to use different protocols for a multimodal interface.

Thus, the termination structure is simplified, and the system can be constructed at low cost without a dedicated equipment, so that commercialization can be easily applied.

FIG. 1 is a view schematically showing a configuration of a conventional IVVR system.
2 is a network configuration diagram for providing a bidirectional automatic answering service according to an embodiment of the present invention.
FIG. 3 is a block diagram illustrating the configuration of the user terminal of FIG. 2 in detail.
4 is a detailed block diagram of the bi-directional answering system of FIG.
5 is a flowchart illustrating a process of a bi-directional automatic answering service method according to an embodiment of the present invention.
6 is a flowchart illustrating a series of steps of a bi-directional automatic answering service method according to another embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise.

Herein, the bi-directional automatic response service includes an IVR (Interactive Voice Response) service or an IVVR (Interactive Voice & Video Response) service.

Hereinafter, a bi-directional automatic response system and a method thereof using a multimodal interface according to an embodiment of the present invention will be described in detail with reference to the drawings.

2 is a network configuration diagram for providing a bidirectional automatic answering service according to an embodiment of the present invention.

2, the user terminal 100 is connected to a bi-directional automatic response system 300 through an IP Multimedia Subsystem (hereinafter, referred to as 'IMS' network)

Here, the IMS network 200 links a network providing IP (Internet Protocol) packet-based data service and a network providing a circuit-based voice service. Here, since IMS and Next Generation Networking (NGN) are roughly equivalent, 'IMS' can be used to collectively refer to both IMS and NGN when applicable in the beginning of the embodiment of the present invention.

The IMS network 200 conforming to the standards defined by the 3GPP entity is designed to allow the service provider to manage various services that can be delivered over IP over any network type.

At this time, the IMS network 200 uses a Session Initiation Protocol (hereinafter referred to as 'SIP') adopted as an official standard of the International Engeneering Task Force (IETF) in 1999 as a signaling protocol. SIP is an application layer signaling protocol. SIP based messages are text based, and include a request message and a response message model.

The IMS network 200 includes an IMS call session control unit 201. The IMS call session control unit 201 performs SIP call control and session handling functions. That is, relaying the session connection from the user terminal 100 to the bi-directional automatic response system 300.

The IMS call session control unit 201 may be classified into an I-CSCF (Interrogating CSCF), an S-CSCF (Serving CSCF), and a P-CSCF (Proxy CSCF) Groups play a key role in the signaling of the IMS network 200.

The IMS call session control unit 201 transmits a call connection request to the bi-directional automatic response system 300 when a call connection is requested from the user terminal 100. When a response is received, the IMS call session control unit 201 transmits a call connection request to the user terminal 100 and the bi- 300).

Here, the user terminal 100 is a multimodal terminal having a voice interface (not shown) and a screen interface (not shown), and is a terminal having a web browser and capable of accessing the Internet.

At this time, a voice interface (not shown) and a screen interface (not shown) transmit and output voice information synchronized with each other according to a scenario of a bidirectional automatic answering service.

The bi-directional answering system 300 includes an application server 310 and a media server 320.

The application server 310 stores a web document and a voice announcement, and can simultaneously perform a role as a web server and a role as a SIP agent.

It is a server that provides bidirectional auto-reply service combined with web by using Session Initiation Protocol (SIP) and Real-time Transport Protocol (RTP) as standard protocol stacks of IMS. The application server 310 transmits and receives web information and a user response through the HTTP (Hyper Text Transfer Protocol) with the user terminal 100 and connects to the user terminal 100 through the SIP through the IMS call session control unit 201 Is a web-based SIP application server that sends voice announcements. The application server 310 is connected to a screen interface (not shown) of the user terminal 100 through SIP.

The media server 320 generates a SIP session with the application server 310 and is connected to a voice interface (not shown) of the user terminal 100 according to a control command received from the application server 310 through a SIP session, And transmits information. The media server 320 sets up a real time transport protocol (RTP) channel for transmitting a voice stream to the user terminal 100. RTP is a transport layer protocol that can transmit streaming traffic such as voice or video over the Internet and is designed to transmit real time data for multimedia services.

In this way, the user terminal 100 is connected to the application server 310 through the IMS network 200 through a SIP session, and the application server 310 also interacts with the media server 320 through a SIP session. In response to the control command received through the SIP session, the media server 320 transmits the voice information through the RTP channel connected to the user terminal 100.

Hereinafter, configurations of the user terminal 100 and the bi-directional automatic answering system 300 for implementing the embodiment of the present invention will be described in detail with reference to FIG. 2 and FIG.

3 is a block diagram illustrating the configuration of the user terminal of FIG. 2 in detail.

3, the user terminal 100 includes a Web browser unit 101, an SIP processing unit 103, a speaker 105, a microphone 107, a display unit 109, an input unit 111, and a control unit 113 .

The web communication unit 101 mounts a web browser and communicates with the application server 310 using HTTP. The web communication unit 101 requests and receives web information from the application server 310, and sends information inputted by the user.

The SIP processing unit 103 sets up an RTP channel for voice stream management and management such as call initiation and termination so as to make a call in the IMS network 200 using SIP.

The speaker 105 and the microphone 107 are means for providing a voice interface. The speaker 105 outputs the voice information received from the media server 320 connected via the RTP channel, and the microphone 107 receives the user's voice and transmits the voice to the media server 320.

The display unit 109 may include a pen / touch screen as a means for providing a screen interface. The display unit 109 displays on the screen the web information received by the web communication unit 101 and information input by the user.

The input unit 111 may include a key pad, an optical joystick, a touch pad, or the like as means for providing an input interface for receiving information from a user.

At this time, the display unit 109 and the input unit 111 may be combined and implemented with a touch screen.

The control unit 113 is connected to the web browser unit 101, the SIP processing unit 103, the speaker 105, the microphone 107, the display unit 109 and the input unit 111 to control the organic operation among the respective components You can browse the web while listening to the voice announcement.

The control unit 113 transmits an SIP INVITE message to the IMS call session control unit 201 through the SIP processing unit 103 to start an IMS-based voice call. Then, the web browser is started with the Web address included in the 200 OK message received from the application server 310. Then, the received web information is analyzed and displayed on the screen, and the voice information received from the media server 320 through the RTP channel is outputted through the speaker 105.

Next, FIG. 4 is a detailed block diagram of the bi-directional automatic answering system of FIG.

Referring to FIG. 4, the bi-directional answering system 300 includes an application server 310, a media server 320, and a billing server 330.

At this time, the application server 310 includes a signaling communication unit 311, a web communication unit 312, a service control unit 313, and a content DB 314.

The signaling communication unit 311 transmits and receives SIP messages to the user terminal 100 and the media server 3320 to generate a SIP session. The signaling communication unit 311 transmits and receives general signaling signals related to a call through a SIP session connected to the user terminal 100. [ In addition, it transmits a signal instructing to reproduce voice information through a SIP session connected to the media server 320. [

At this time, the 'SIP INFO method' is used to transmit / receive a response to the control command and the control command with the media server 320. The 'SIP INFO method' is for transmitting application level information using a SIP session.

The web communication unit 312 receives a request for web information from the user terminal 100 via HTTP and transmits a response including the corresponding web information. Here, the web information refers to a web document to be output by the screen interface of the user terminal 100 according to the scenario of the bidirectional automatic answering service.

The service control unit 313 interprets the user selection information received through the web communication unit 312 to determine the next web information and voice announcement, puts the corresponding web information in the HTTP response message, requests to play the announcement To the media server (320).

In the contents DB 314, a web document and a voice announcement containing information for a bidirectional automatic answering service are stored with respective web addresses. Here, the web address is a storage path of a web document, and is a URL (Uniform Resource Locator). Further, the web document includes text, images, and moving images for a two-way automatic answering service.

The content DB 314 includes at least two tables as shown in Tables 1 and 2 below.

Service phone number Initial Service URL 15881004 15881004 / index.jsp 15882424 15882424 / index.jsp ... ...

The table shown in Table 1 is used for searching for a URL based on a service telephone number when a user requests a service by pressing a service telephone number.

Service URL Web document Voice announcement file 15881004 / index.jsp <html> ... ref = "15881004 / potato_pizza.jsp" ... 15881004 / index.wav 15881004 / potato_pizza.jsp "<html> ... </ html> 15881004 / potato_pizza.wav ... ... ...

The table shown in Table 2 is used to find a web document and a voice announcement file as a service URL when a request for a web document for the initial service URL in Table 1 is input.

At this time, the web document is divided into a first web document including information for displaying a service initial screen including one or more user selection items, and a second web document corresponding to a web address linked by one or more user selection items. The second web document includes URLs for the next progress according to the user's selection.

For example, in Table 2, the web document of the service URL '15881004 / index.jsp' lists various pizza images, and each URL is linked to the pizza image. Accordingly, when the user selects a specific pizza image, a guide screen for the selected pizza is provided by accessing '15881004 / potato_pizza.jsp' linked to the selected pizza image.

At this time, the web communication unit 312 uses the HTTP method when the first web document for the initial service URL and the second web document for the URL linked to the first web document are requested from the user terminal 100.

The HTTP method uses the HTTP GET method and the HTTP POST method. Here, the HTTP GET method is generally used to request resources of a specific URL (Uniform Resource Locators), and the HTTP POST method is used to change the state by transmitting data entered in a form to a server.

Meanwhile, when the application server 310 generates a session with the user terminal 100 and the media server 320, the billing server 330 starts billing, generates a billing record when the session ends, Lt; / RTI &gt; At this time, although it is shown to be connected to the application server 310, it may be connected to the IMS call session control unit 201.

Hereinafter, the operation of the bi-directional automatic answering service based on the above-described configuration will be described.

5 is a flowchart illustrating a process of a bi-directional automatic answering service method according to an embodiment of the present invention. 2 to 4, the same reference numerals as those in FIGS. 2 to 4 are used.

Referring to FIG. 5, the user starts to call the application server 310 by pressing or touching a service telephone number to request a bidirectional automatic answering service.

At this time, the user terminal 100 transmits a SIP INVITE message requesting a bidirectional automatic answering service to the application server 310 through the IMS call session control unit 201 (S101). Here, the header of the SIP INVITE message includes a specific bit to indicate whether the user terminal 100 supports the touch screen.

On the other hand, the application server 310 transmits the SIP INVITE message received in step S101 to the media server 320 (S103) to proceed with the SIP call setup.

The media server 320 transmits a SIP 200 OK message to the application server 310 (S105), responds to the SIP call setup, and prepares the RTP channel.

The application server 310 stores the URL of the web document to be provided to the user in the SIP 200 OK message received in step S105 (S107) and transmits the URL to the user terminal 100 (S109).

At this time, in step S107, the URL mapped to the service telephone number requested by the user terminal 100 using the table of Table 1 may be extracted and recorded.

In addition, a new field can be defined in the header of the SIP 200 OK message to store the URL. For example, a URL may be stored in a field such as 'P_SERVICE_URL', but various modifications can be made to the URL where the URL is to be stored.

A SIP session is established between the user terminal 100 and the application server 310 and between the application server 310 and the media server 320 and an RTP channel is established between the user terminal 100 and the media server 320 S111).

Then, the user terminal 100 transmits the HTTP GET method requesting the URL connection extracted from the SIP 200 OK message received in step S109 to the application server 310 (S113).

The application server 310 interprets the URL (S115) and inquires the corresponding web document from the content DB 340 (S117). In step S119, the Web document, i.e., the first web document, is stored in the HTTP 200 OK message and transmitted to the user terminal 100. [

Then, the user terminal 100 outputs the received first web document to the screen (S121).

In step S123, the application server 310 transmits the SIP INFO method including the URL of the voice information corresponding to the first web document retrieved in step S117 and requesting transmission of the voice announcement to the media server 320 (step S123) .

Then, the media server 320 transmits the SIP 200 OK message to the application server 310 and responds (S125). In step S123, the media server 320 transmits the HTTP GET method requesting connection to the received URL to the application server 310 (S127).

Then, an HTTP 200 OK message including a voice announcement file corresponding to the requested URL is received (S129), and the voice announcement file is reproduced to the user terminal 100 via the RTP channel (S131).

On the other hand, the user terminal 100 outputs the first web document in step S121, and then waits for the input of the user. That is, the user waits until he or she presses a specific menu on the web screen or enters a number while listening to the voice announcement. For example, a variety of pizza images and a voice prompt "Please touch the desired pizza menu" is sent out while waiting for the user's input.

At this time, if the user selects an arbitrary user selection item among a plurality of user selection items displayed in the first web document (S133), the user terminal 100 transmits an HTTP POST requesting connection to the URL linked to the selected item to the application server (Step S135).

Then, the application server 310 analyzes the URL requested in step S135 (S137), extracts the corresponding web document, i.e., the second web document, from the content DB 314 (S139) (S141). The user terminal 100 outputs the second web document to the screen (S143).

The application server 310 also transmits a SIP INFO method requesting playback of the voice announcement file corresponding to the second web document extracted in step S139 to the media server 320 (S145) and receives the SIP 200 OK message (S147).

The media server 320 transmits an HTTP GET method requesting connection to the URL received in step S145 to the application server 310 in step S149 and receives an HTTP 200 OK message including the voice announcement file stored in the requested URL (S151).

Then, the voice announcement received in step S151 is broadcast to the user terminal 100 through the RTP channel (S153).

The user terminal 100 determines whether the service is to be terminated (S155), and if it is determined that the service is continued, the process returns to step S133.

However, if it is determined that the service is to be terminated, a SIP BYE message requesting termination of the call is transmitted to the application server 310 (S157).

The application server 310 transmits a SIP BYE message to the media server 320 in operation S159 and transmits a SIP ACK message in operation S161 to the user terminal 100 in operation S163.

As a result, the SIP session is released, and the call for the two-way automatic answering service is terminated.

Meanwhile, although not shown in the figure, when a SIP session is established after step S109, the billing server 330 starts billing, and when the call is terminated in step S163, a billing record is generated to measure bidirectional automatic answering service usage fee .

FIG. 6 is a flowchart illustrating a sequence of a bi-directional automatic answering service method according to another exemplary embodiment of the present invention. Referring to FIG. 6, an application server 310 transmits an automatic answering service Web-based TS (Touch Screen) -IVR) is included in the response message.

Referring to FIG. 6, when a user dials a service number, the user terminal 100, i.e., a touch screen terminal (UE) transmits an INVITE message including Web-based TS-IVR Indication Information (S201).

Here, the Web-based TS-IVR Indication Information indicates that the user terminal 100 has a touch screen device and is capable of supporting a web-based TS (Touch Screen) -IVR service.

Then, the application server (AS-FE) 310 receives the INVITE message transmitted in step S201 from the IMS call control unit 201, for example, the switch (S-CSC-FE) based on the recipient identity . The application server (AS-FE) 310 recognizes that the user terminal 100 supports the Web-based TS (Touch Screen) -IVR service through the Web based TS-IVR Indication Information.

The application server (AS-FE) 310 transmits the INVITE message having the SDP of the user terminal 100 to the media server (MRC-FE) 320 in order to set up a voice call (S203).

Then, the media server (MRC-FE) 320 transmits 200 OK (S205).

Then, the application server (AS-FE) 310 transmits a 200 OK message including the initial URL and the Web based TS-IVR Notification Information to the user terminal 100 (S207). Here, the initial URL refers to the initial web page of the IVR service, and the Web-based TS-IVR Notification indicates that the application server (AS-FE) 310 has the web-based TS (Touch Screen) 100).

The user terminal 100 transmits an ACK message (S209), and the application server (AS-FE) 310 transmits an ACK message to the media server (MRC-FE) 320 (S211).

Thereby, an RTP voice channel is initialized and connected between the user terminal 100 and the media server (MRC-FE) 320 (S213).

Then, the user terminal 100 accesses the application server (AS-FE) 310 via HTTP in order to obtain web contents such as an HTML document and an image (S215, S217). Then, the user terminal 100 displays the initial web page of the IVR service. When the application server (AS-FE) 310 receives the HTTP request, the application server (AS-FE) 310 analyzes the URL and determines the web contents and the voice media in the current service stage.

The application server (AS-FE) 310 exchanges media control messages with the media server (MRC-FE) 320 (S219). Such a media control message includes a media play command.

Then, the media server (MRC-FE) 320 reproduces the guidance by a media play command (S221).

The user then views the web page while listening to the announcement. He touches the hyperlink of the web page. Then, the user terminal 100 transmits a user action form to the application server (AS-FE) 310 via HTTP (S223). The application server (AS-FE) 310 analyzes the user action form and transits to the next service stage, and returns the web content in the service stage to the user terminal 100 (S225). The user terminal 100 displays the returned web content.

The application server (AS-FE) 310 exchanges media control messages with the media server (MRC-FE) 320 in step S227, and the media server MRC- Play command) (S229).

Thereafter, when the user desires to terminate the call, the user terminal 100 transmits a call termination message Bye (S231) and receives 200OK (S233) to complete the call termination.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It belongs to the scope of right.

Claims (16)

A bidirectional automatic answering system for providing a multi-modal bidirectional automatic answering service to a user terminal having a multimodal interface,
An application server connected to the screen interface of the user terminal to create a session for the bidirectional automatic answering service with the user terminal using an IMS (IP Multimedia Subsystem) call session control protocol; And
Generating a session with the application server using the IMS call session control protocol, and in response to a control command received from the application server via the session, the voice interface of the user terminal, And outputting the voice information synchronized with the screen output of the screen interface according to the scenario.
Lt; / RTI &gt; The method according to claim 1,
The application server comprises:
A signaling communication unit for transmitting and receiving a Session Initiation Protocol (SIP) message for creating the session with the user terminal and the media server;
A web communication unit for transmitting and receiving a request and a response of a web document to be output by the screen interface to the user terminal according to the scenario of the bidirectional automatic answering service; And
When the SIP message requesting the bidirectional automatic answering service is received from the user terminal, the web address providing the bidirectional answering service is included in the SIP message responding to the bidirectional answering service request and transmitted, And a service control unit for generating a session with the media server by transmitting the requesting SIP message to the media server,
Wherein the media server connects a voice communication channel with the user terminal when the requesting SIP message is received, and the user terminal requests the web document using the web address. 3. The method of claim 2,
The service control unit,
And the web address is included in a newly defined field in the header of the responding SIP message. 3. The method of claim 2,
The service control unit,
And transmits a response to the control command and the control command to the media server using a SIP INFO method. 5. The method according to any one of claims 2 to 4,
The service control unit,
When receiving a request for the web document from the user terminal, transmits a control command for transmitting a web document corresponding to the web address to the user terminal and requesting the media server to transmit voice information corresponding to the web address Bi-directional automated answering system. 6. The method of claim 5,
The application server comprises:
Further comprising a database for respectively storing web documents and audio information corresponding to the web addresses,
The web communication unit,
Receives a request for the web document using a Hyper Text Transfer Protocol (HTTP) GET method,
The media server comprises:
And downloads voice information corresponding to the web address from the database using the HTTP GET method. The method according to claim 6,
The web document includes:
A first web document including information for displaying a service initial screen including at least one user selection item and a second web document corresponding to a web address linked by the at least one user selection item,
The service control unit,
When a connection request to a web address linked to a specific user selection item selected by the user is received from the user terminal, transmits a second web document corresponding to the linked web address to the user terminal, And transmits a control command for requesting transmission of voice information corresponding to the web address. 8. The method of claim 7,
The web communication unit,
And a connection request to the linked web address is received using an HTTP POST method. The method according to claim 1,
When a session is created with the user terminal and the media server, the billing server starts billing, generates a billing record when the session ends, and performs billing based on the bi-
Further comprising: a bi-directional automatic answering system. A bidirectional automatic answering service method of a bidirectional answering service providing system including an application server connected to a screen interface of a user terminal and a media server connected to a voice interface of the user terminal,
Generating a session for the bidirectional automatic answering service with the user terminal using the IMS (IP Multimedia Subsystem) call session control protocol;
Wherein the application server generates a session with the media server using the IMS call session control protocol and transmits a control command for the bidirectional automatic answering service to the media server,
Wherein the media server transmits voice information synchronized with a screen output of the screen interface according to the control command through a voice communication channel set with the user terminal. 11. The method of claim 10,
Wherein the generating comprises:
Receiving, by the application server, a Session Initiation Protocol (SIP) message requesting the bidirectional automatic answering service from the user terminal;
Storing a web address providing the bidirectional automatic answering service in a SIP message responding to the bidirectional answering service request; And
Transmitting the response SIP message to the user terminal to generate the session
Lt; RTI ID = 0.0 &gt; a &lt; / RTI &gt; 12. The method of claim 11,
Wherein the transmitting the control command comprises:
Transmitting, by the application server, the requesting SIP message received from the user terminal to the media server to request a connection of a voice communication channel;
Receiving the responding SIP message from the media server and creating the session with the media server;
Receiving a request for a web document corresponding to a web address from the user terminal; And
Transmitting a control command for requesting transmission of voice information corresponding to the web address through a session created with the media server
Lt; RTI ID = 0.0 &gt; a &lt; / RTI &gt; 13. The method of claim 12,
Wherein the step of receiving a request for a web document corresponding to a web address from the user terminal comprises:
Receiving an HTTP (Hyper Text Transfer Protocol) GET method for the application server to request connection to the web address; And
Analyzing the web address and transmitting an HTTP response message including the web document corresponding to the web address to the user terminal,
After transmitting through the session,
Receiving an HTTP GET method requesting voice information corresponding to the web address from the media server; And
Transmitting an HTTP response message including the voice information to the media server
Further comprising the steps of: 14. The method of claim 13,
Wherein the transmitting through the session comprises:
Wherein the application server transmits to the media server a SIP INFO method for requesting transmission of voice information corresponding to the web address. 14. The method of claim 13,
The web document includes:
A first web document including information for displaying a service initial screen including at least one user selection item and a second web document corresponding to a web address linked by the at least one user selection item,
After transmitting the HTTP response message including the voice information to the media server,
Receiving, by the application server, an HTTP POST method requesting a web document corresponding to a web address linked to a specific user selection item selected by the user from the user terminal; And
Transmitting an HTTP response message including a web document corresponding to the linked web address to the user terminal
Further comprising the steps of: 12. The method of claim 11,
The step of storing the web address providing the bidirectional automatic answering service in a SIP message responding to the bidirectional answering service request
Storing the web address in the responding SIP message; And
Adding the notification information for informing that the application server performs bidirectional automatic answering service to the responding SIP message
Lt; RTI ID = 0.0 &gt; a &lt; / RTI &gt;

Images