KR20110070386A - The system and method for automatically making image ars - Google Patents

Abstract

PURPOSE: An automatic image ARS manufacture system and a method thereof are provided to offer visualized menu or information to a customer. CONSTITUTION: A voice recognition unit(110) changes the voice of a voice ARS(Auto Response System) into a text. A keyword extraction unit(120) extracts a set keyword from the text. In case the same keyword as the set keyword exists within a keyword DB(125), a matching unit(140) matches a stored image with the keyword. An alignment unit(150) aligns matched images in the time sequence of a recognized voice. A display unit(160) displays the aligned images.

Description

Image ARS automatic production system and its method {The system and method for automatically making image ARS}

The present invention relates to a video ARS automatic production system and a method thereof, and more particularly, to a video ARS automatic production system and method for easily replacing a system for converting an existing audio ARS system to a video ARS system.

Recently, as the computer, electronic, and communication technologies have developed rapidly, various mobile communication services using a mobile communication network have been provided.

Accordingly, mobile communication service subscribers can receive various types of information such as news, weather, sports, securities, exchange rates, and traffic information in various forms such as text, voice, still image, and video through wireless Internet service.

As a result of the development of mobile communication technology, the services provided by the mobile communication system are developing into a multimedia communication service for transmitting not only voice services but also circuit data and packet data.

The mobile communication system for this purpose has been developed through the first generation analog AMPS (Advanced Mobile Phone System) method and the second generation cellular and personal communication service (PCS) method, and recently established as a standard by ITU-R. IMT-2000 (International Mobile Telecommunication 2000; for example, CDMA 2000 1X, EV-DO, WCDMA, etc.), which is a third generation mobile communication system, is commercially available.

More specifically, the mobile communication ^{system, 3GPP (3 rd Generation Partnership Projects} ) haewatgo development as GSM, GPRS, WCDMA networks standardized by the international standardization ^{conference, 3GPP2 (3 rd Generation Partnership Projects} 2) normalized IS by the International Standardization Conference -95A, IS-95B, CDMA20001x, CDMA1x-EVDO.

Among these wireless mobile communication technologies, in the case of the IMT-2000 network, the synchronous IMT-2000 is called CDMA2000 1x-EVDO, and the asynchronous IMT-2000 is called WCDMA.

IMT-2000 is CDMA 2000 1x, EV-DO, WCDMA, etc. It is a data transmission speed that can be supported in IS-95A and IS-95B networks by using IS-95C network that has evolved from IS-95A and IS-95B networks. It is a service that can provide wireless Internet at 144Kbps transmission speed much faster than 14.1Kbps or 56Kbps.

In particular, by using the IMT-2000 service, it is possible to more efficiently provide various multimedia services as well as improve existing voice and WAP service quality.

Here, the WCDMA method is a mobile communication system asynchronously implemented in the IMT-2000 system. The wireless access method for communication between the base station and the mobile communication terminal adopts the CDMA method, but the technology related to the mobile communication network is GSM (Global System for Mobile communication). Based on network technology.

WCDMA method does not need to use Global Positioning System (GPS) to synchronize the entire base station, supports international roaming service, widens the frequency bandwidth to 5MHz, and has a data rate of 2Mbps, which is suitable for high-speed data transmission. Diversity is provided according to the reverse call quality, which cannot be provided in the IS-95 and GSM methods, so that the call and data transmission performance is relatively good even in a poor communication environment.

However, since the WCDMA scheme does not support backward compatibility with the existing CDMA and GSM schemes, a new mobile communication network must be constructed and a mobile communication terminal supporting the WCDMA scheme should be used.

Here, for video call service, WCDMA network is provided based on wired circuit network, and part of ITU-T H.324 protocol standard is changed to 3GPP standardization organization to wireless circuit network and standardized to 3G-324M protocol standard. On the other hand, in the CDMA 2000 1x-EVDO network, the ITU-T H.323 protocol specification used in the wired packet network is used for the wireless packet network without a separate standard specification in the wireless network.

On the other hand, SIP (Session Initiation Protocol) based provides a video phone service that integrates the synchronous network and asynchronous network, and web phone provides a video phone service using the existing packet data network because the price is low, computer technology It is attracting the spotlight as next generation technology because it can create new service in combination with.

Since these video call services have recently been provided, the number of video call subscribers has exceeded 10 million thanks to many technological developments and promotions, and mobile carriers are providing various services and developing more video call related services. In the process.

The increase in the number of subscribers of the video call service was caused by the fact that it is possible to make a call while watching the video of the other party, away from the format of the call using only existing voice. It is true that provision also played a big role.

An example of the differentiated additional service of the video call service is the provision of a video ARS service having many advantages over the voice ARS.

In general, the Automatic Response System (ARS) stores each information as a voice, and when the user accesses the system using a telephone, it teaches the user how to search for necessary information by voice and at the same time, necessary information. If is found, it refers to a system that speaks it.

The telephone information service using the voice ARS (hereinafter, referred to as a voice ARS service) is a method of installing a voice mail device in a telephone exchange and storing various types of information, and allowing an information user to make a call and listen to desired information.

This voice ARS service is designed to reduce the number of agents and to efficiently handle the guidance requested from multiple customers.

These voice ARS services are applied to a wide variety of fields such as finance, securities, transportation, tourism, sports, performances, health, fortune telling, weather customer service, medical counseling, or legal counseling. In addition, it is common to charge an information fee in proportion to the time used.

In this regard, in the case of the existing voice ARS service, a voice-oriented service is provided in which a user who needs to listen to a voice guide by making a paid ARS call when a user who wants to receive a specific service is provided.

However, in the case of the existing voice ARS service that provides voice-oriented information, the amount of information that a user can take is limited compared to the service that provides visual information. Means that you must use.

In addition, the ARS service is typically configured to transmit a preliminary guide message to the terminal of the customer when the customer requests a call connection, and provide the submenu according to the number selected by the customer.

However, if there are a large number of submenus or a large amount of information included in each menu, and it takes a long time to listen, the customer must continuously listen to the voice messages for all the menus that do not need to be heard in order to select the desired menu. If the wrong number for the desired menu is selected, there is an inconvenience of returning to the upper menu or starting again from the beginning.

In other words, the existing voice ARS service is required to provide unnecessary services, such as unnecessary announcements related to the service, and such voice guidance acts as an inefficient factor that causes waste of call charges from the user's point of view.

In addition, typical ARS services provide only the information (or content) that the customer ultimately wants, so that the customer may not hear or misrepresent the voice, and it is not easy for the customer to listen to the voice message and write it down. not.

Based on this, the existing voice ARS service has a problem in that it is extremely limited in terms of service diversification due to the inefficiency and the limitation of information amount caused by the provision of the voice-oriented service.

Accordingly, there is a need for an image ARS system that can provide a visualized menu or information (or content) so that customers can visually view the final information (or content) selected through the menu.

1 is a schematic configuration diagram of an image ARS system.

As shown in FIG. 1, the system requests a call connection for using an ARS service and receives a call according to a call connection request from a user terminal 1 receiving a video ARS service and a user terminal 1 through a mobile communication network. A switch 2 that performs connection control and an ARS service server 3 that provides a video ARS service when the user terminal 1 connects through the switch have a configuration.

The user terminal 1 provides the ARS service to the exchange 2 to receive various ARS services such as finance, securities, transportation, tourism, sports, performances, health, fortune telling, weather, customer center, medical counseling, or legal counseling. A call connection with the server 3 is requested.

The switch 2 performs a call connection with the ARS service server 3 when the user terminal 1 is a video ARS service supporting terminal according to a call connection request of the user terminal 1 through a mobile communication network.

The ARS service server 3 determines whether to provide the video ARS service based on the terminal type information of the user terminal 1 connected through the exchange 2, and provides the video ARS service when the video ARS service is supported.

As described above, there is an increasing demand for an image ARS service capable of efficiently receiving visualized menus or information (or contents).

However, the voice ARS service is currently applied to a wide variety of fields, and therefore, in order to provide the video ARS service, the existing voice ARS service providers must convert the existing voice ARS system into the video ARS system.

Therefore, replacement work for converting the voice ARS system into the video ARS system must be accompanied, and there is a need for a technology for facilitating such a system replacement.

The present invention was devised to solve the above problems, and provides a visualized menu or information (or content) so that the customer can visually view the final information (or content) selected through the menu or menu of the ARS system. An object of the present invention is to provide a video ARS automatic production system and a method for automatically producing a video ARS system.

In addition, an object of the present invention is to provide a video ARS automatic production system and a method for easily replacing a system for converting an existing voice ARS system to a video ARS system.

In order to achieve the object of the present invention as described above, the automatic ARS video production method of the present invention includes reproducing a voice ARS, recognizing a voice of the voice ARS, and extracting a plurality of preset keywords from the recognized voice. And matching the extracted plurality of keywords with pre-stored images corresponding to the keywords, and arranging the matched images in order.

Here, after the step of arranging the matched image in order, it is preferable to include the step of displaying the image arranged in the order.

In addition, after the displaying of the images arranged in the order, it is preferable to include the step of replacing a specific image of the image to be stored with another image stored in advance.

On the other hand, the video ARS automatic production system of the present invention for achieving the above object of the present invention, a voice recognition unit for recognizing the voice from the voice ARS and a keyword extraction unit for extracting a predetermined keyword from the recognized voice; And a matching unit for matching pre-stored images and an alignment unit for aligning the matched images in order.

The image DB may further include an image DB in which an image corresponding to a preset keyword is stored.

In addition, one image may be stored corresponding to one keyword in the image DB, or a plurality of images may be stored in correspondence with one keyword.

In addition, an image corresponding to a preset keyword may be tagged and stored in the image DB.

In addition, the keyword extracting unit may further include a keyword DB for presetting and storing a specific keyword.

Further, the keyword is preferably set in advance corresponding to each menu of the voice ARS.

Furthermore, the automatic image ARS production system according to the present invention may further include a display unit for displaying the images arranged in the above order.

According to the video ARS automatic production system and method of the present invention, a visualized menu or information (or content) is provided so that a customer can visually view the final information (or content) selected through the menu or menu of the ARS system. There is an effect that can automatically produce a video ARS system that can be.

In addition, in the present invention, there is an advantage that the system replacement work for converting the existing voice ARS system to the video ARS system is easy.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the embodiments of the present invention described below are provided to enable those skilled in the art to more easily understand the present invention, and the scope of the present invention is not limited to the described embodiments.

Hereinafter, the automatic image ARS production system of the present invention will be described in detail with reference to FIG. 2.

2 is a block diagram schematically showing the configuration of an automatic ARS video production system according to the present invention.

2, the automatic video ARS production system according to the present invention includes a voice recognition unit 110, a keyword extraction unit 120, an image DB 130, a matching unit 140, and an alignment unit 150. It is composed.

The voice recognition unit 110 reproduces the existing voice ARS, performs voice recognition on the voice of the voice ARS, and converts the recognized voice into text.

Here, any of the "traditional voice ARS" that is conventionally applied to a wide variety of fields such as finance, securities, transportation, tourism, sports, performances, health, fortune telling, weather customer center, medical counseling or legal counseling, etc. Say.

The keyword extraction unit 120 extracts a predetermined keyword from the speech recognition contents converted into the text.

The " preset keyword " is a menu set as a voice guide in a general voice ARS system as a keyword, and is stored in advance in the keyword DB 125 and managed.

The voice ARS system is currently used to reduce the number of agents in finance, securities, transportation, tourism, sports, performances, health, fortune-telling, weather call centers, medical counseling or legal counseling, and to efficiently handle guidance from multiple customers. It is used.

Therefore, the voice content of the voice ARS has different contents according to the user who uses the voice ARS system, and accordingly, a menu guided through the voice ARS is also different.

In this case, the keyword is set as a key word for a variety of menus previously provided through the voice ARS, the key word may be one or a plurality of key words per menu.

The keyword extracting unit 120 compares the plurality of words used in the contents of the ARS converted into text through the speech recognition unit 110 with the keywords stored in the keyword DB 125. Only keywords pre-stored in 125 are extracted.

In the present embodiment, the keyword DB 125 refers to the configuration included in the keyword extraction unit 120, but the keyword DB 125 may be configured as a separate DB.

In the image DB 130, various images corresponding to the keyword are prepared in advance and stored.

Here, the image corresponding to the keyword may be an image (photo or picture), a still image, a video, or the like, which matches the idea of the keyword or the feeling of rising through the keyword.

For example, if the voice guidance menu is related to the “phone charge”, and the keyword for the “charge” is preset and stored, the image corresponding to the “charge” may be an image (picture or picture) related to the charge or a still image. It may be an image or a video.

For example, a "money" -shaped image becomes a corresponding image with respect to the keyword "rate" and is stored in the image DB 130.

Here, one image corresponding to the one keyword may be stored in the image DB 130, or a plurality of images may be stored for one keyword.

In this case, when the image corresponding to the keyword is stored, the keyword may be tagged and stored with the image corresponding to the keyword.

Tagging is primarily used on blogs or web pages, where a site administrator can process a site's image or text into related topics or categories, or simply tag (representing the content of web content). Keyword).

That is, the keyword DB 130 may be stored together with various tagging information by combining the keyword with a unique ID of the image corresponding to the keyword.

When there is a keyword identical to a preset keyword stored in the keyword DB 125 among the voice recognition contents, the matching unit 140 matches the stored image with the keyword.

In this case, when a plurality of keywords are included in the voice recognition content, the matching process is performed on all keywords.

Here, a plurality of images may exist for the extracted one keyword, and in this case, a plurality of images may be given a rank arbitrarily determined by the producer of the image ARS automatic production system or ranked among the plurality of images using various statistical information. An algorithm may be applied.

Therefore, the highest image and the keyword may be matched.

The sorter 150 sorts the matched plurality of images in chronological order of the speech recognized from the speech ARS.

In other words, the keywords extracted from the speech recognized from the speech ARS are sorted in chronological order of the speech, and the images are sorted in the same order as the sorted keyword sequence.

The aligned images form an image ARS in which the voice of the audio ARS is replaced with the image.

The display unit 160 displays the images arranged through the alignment unit 150 so that the user can view them, and may be a user's mobile phone or a computer monitor.

Hereinafter, with reference to the accompanying drawings will be described in detail for the automatic image ARS production method according to the present invention.

3 is a flowchart illustrating a method of automatically producing video ARS according to the present invention.

First, when a user of an existing audio ARS system wants to use the video ARS automatic production system according to the present invention, the user of the existing voice ARS system requests the use of the producer of the video ARS automatic production system.

Referring to FIG. 3, the user of the existing voice ARS system accesses the video ARS automatic production system according to the present invention through an application for use and the like, and plays back the previously used voice ARS (S210).

Here, the "existing voice ARS" is any of those that are conventionally applied to a wide variety of fields such as finance, securities, transportation, tourism, sports, performances, health, fortune telling, weather customer center, medical counseling or legal counseling. Say that.

Next, the voice recognition unit 110 performs voice recognition on the voice of the voice ARS (S215), and converts the recognized voice into text.

Subsequently, the keyword extracting unit 120 of the recognized speech contents extracts the keyword in real time when there is a keyword according to the presence or absence of a predetermined keyword (S220), and when there is no keyword, the speech recognition continues. Perform the process (S215).

The keyword extracting unit 120 compares the plurality of words used in the contents of the ARS converted into text through the speech recognition unit 110 with the keywords stored in the keyword DB 125. Only keywords pre-stored in 125 are extracted.

In the present embodiment, the keyword DB 125 refers to the configuration included in the keyword extraction unit 120, but the keyword DB 125 may be configured as a separate DB.

Here, the "preset keyword" is a menu set as a voice guide in a general voice ARS system as a keyword, and is stored in advance in the keyword DB 125 and managed.

The voice ARS system is currently used to reduce the number of agents in finance, securities, transportation, tourism, sports, performances, health, fortune-telling, weather call centers, medical counseling or legal counseling, and to efficiently handle guidance from multiple customers. It is used.

Therefore, the voice content of the voice ARS has different contents according to the user who uses the voice ARS system, and accordingly, a menu guided through the voice ARS is also different.

In this case, the keyword is set as a key word for a variety of menus previously provided through the voice ARS, the key word may be one or a plurality of key words per menu.

Next, when there is a corresponding image according to whether the image corresponding to the extracted keyword exists in the image DB 130 (S230), the matching keyword 140 is matched with the extracted keyword through the matching unit 140. (S235).

If the corresponding image does not exist, the voice recognition process is continued (S215).

In the image DB 130, various images corresponding to the keyword are prepared in advance and stored.

In addition, the image corresponding to the keyword may be an image (picture or picture), a still image, or a video that is arbitrarily set to match the idea of the keyword or the feeling of rising through the keyword.

In addition, one image corresponding to the one keyword may be stored in the image DB 130, or a plurality of images may be stored for one keyword.

In this case, when the image corresponding to the keyword is stored, the keyword may be tagged and stored with the image corresponding to the keyword.

That is, the keyword DB 130 may be stored together with various tagging information by combining the keyword with a unique ID of the image corresponding to the keyword.

The matching process (S235) is continued until the voice of the voice ARS is finished.

That is, when a plurality of keywords are included in the speech recognition content, the matching process is performed on all keywords.

Here, a plurality of images may exist for the extracted one keyword, and in this case, a plurality of images may be given a rank arbitrarily determined by the producer of the image ARS automatic production system or ranked among the plurality of images using various statistical information. An algorithm may be applied.

Therefore, the highest image and the keyword may be matched.

Subsequently, the matched plurality of images are arranged in a voice time order of a voice ARS (S240).

In other words, the keywords extracted from the speech recognized from the speech ARS are sorted in chronological order of the speech, and the images are sorted in the same order as the sorted keyword sequence.

The aligned images form an image ARS in which the voice of the audio ARS is replaced with the image.

Next, the display unit 160 displays the aligned images so that a user can view the display unit S245. In this case, the display unit 160 may be a user's mobile phone or a computer monitor.

When the user examines the automatically produced video ARS displayed and there is an image to be replaced (S250), the user may select the desired image through the search of the image DB 130 to replace the image to be replaced (S255). have.

In addition, when there is an image to be replaced, the process of replacing the image may be partially performed or may be entirely performed for the automatically produced image ARS.

After the user partially replaces the image, the user may repeatedly replace the image through a process of reviewing the image ARS including the replaced image.

On the other hand, if the user does not want to replace the image ARS automatically produced by the image (S250), the video ARS automatic production process is terminated (S260), thereby completing the automatic production process of the video ARS.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments described in the present invention are not intended to limit the technical idea of the present invention but to explain, and the technical idea of the present invention is not limited by these embodiments. The protection scope of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

1 is a schematic configuration diagram of an image ARS system,

Figure 2 is a block diagram schematically showing the configuration of the automatic image ARS production system according to the present invention,

3 is a flowchart illustrating a method of automatically producing video ARS according to the present invention.

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

110: speech recognition unit 120: keyword extraction unit

125: keyword DB 130: image DB

140: matching unit 150: alignment unit

160: display unit

Claims (11)

Playing the voice ARS; Recognizing a voice of the voice ARS; Extracting a plurality of preset keywords from the recognized voice; Matching the extracted plurality of keywords with pre-stored images corresponding to the keywords; And Sorting the matched images in order; Automatic video ARS production method comprising a. The method of claim 1, After sorting the matched images in order, Displaying the images arranged in the order; Automatic video ARS production method comprising a. The method of claim 1, After displaying the images arranged in the above order, Replacing a specific image among the displayed images with another previously stored image; Automatic video ARS production method comprising a. A voice recognition unit for recognizing a voice from the voice ARS; A keyword extraction unit for extracting a predetermined keyword from the recognized voice; A matching unit which matches pre-stored images in correspondence with the extracted plurality of keywords; And An alignment unit to arrange the matched images in order; Image ARS automatic production system comprising a. The method of claim 4, wherein An image DB storing an image corresponding to the preset keyword; Image ARS automatic production system further comprises. The method of claim 5, The video ARS automatic production system, characterized in that one video is stored corresponding to one keyword in the video DB. The method of claim 5, Automatic image production system ARS, characterized in that a plurality of images corresponding to one keyword is stored in the image DB. The method of claim 5, The video ARS automatic production system, characterized in that the video corresponding to the predetermined keyword is stored in the image DB is tagged. The method of claim 4, wherein The keyword extraction unit is a keyword DB for storing a predetermined keyword in advance; Image ARS automatic production system further comprises. The method of claim 9, The keyword is set in advance corresponding to each menu of the voice ARS video ARS automatic production system. The method of claim 4, wherein A display unit for displaying the images arranged in the order; Image ARS automatic production system further comprises.

Images