KR20040032523A - Method and Apparatus for interfacing internet site of mobile telecommunication terminal using voice recognition - Google Patents

Abstract

PURPOSE: An Internet site access apparatus of a mobile communication terminal using a voice recognition and a method therefor are provided to enable a voice recognition server to recognize an inputted voice of a mobile terminal user and move to a desired Internet site. CONSTITUTION: A mobile communication terminal(100) access the Internet through a Web browser and transmits voice data and a current URL(Uniform Resource Locator). A multimodal server(200) maps a voice recognition grammar by using the URL and generates a target URL of a new page to be accessed. A voice recognition server(300) recognizes a voice by using voice data and voice recognition grammar transmitted from the multimodal server(200). A gateway(400) and a CP(Content Provider) Web server(500) allow the mobile communication terminal(100) to access the Internet.

Description

Method and Apparatus for interfacing internet site of mobile telecommunication terminal using voice recognition}

The present invention relates to an internet search apparatus and method for a mobile communication terminal using voice recognition, and more particularly, a mobile terminal using voice recognition for recognizing a voice input through a mobile communication terminal and moving to a desired internet site. An internet search apparatus and method for a communication terminal.

With the spread of mobile communication terminals, the necessity of using information on the Internet is increasing in these mobile communication terminals, and the performance of hardware, speed of communication network, screen size, input device, etc. are compared with PCs. Due to the significant difference in performance and constraints, there are many problems in using the Internet browser and contents for the conventional PC and the wired Internet network. However, this problem has been solved through new content formats and input methods (eg, navigation using numeric buttons), such as WAP, but there are limitations in showing many menus and links at the same time on a small screen of a mobile communication terminal. In order to move from the menu of the initially set web page to the web page with the data desired by the user, it is necessary to continuously input specific keys along the linked links to reach the final content. Can be. Therefore, there is a problem in that the time required for connection is increased because a special function key must be clicked in order to continuously select characters along the tree and input of characters such as URLs.

Such an inconvenience caused by the connection has been attempted to be solved by using voice recognition technology. As shown in FIG. 1, a button input unit 10 receiving a command from a user, a memory 11 storing data, and A display unit 12 for displaying predetermined data to a user, a data transceiver 13 for processing data transmission and reception with another mobile communication terminal, a CPU 14 for processing the data, and a microphone for receiving sound An attempt has been made to solve the problem through a mobile communication terminal in which a voice recognizer composed of a voice controller 15 for inputting and outputting voices through the speaker 16 for outputting sound is provided. However, the mobile terminal capable of voice recognition should have a separate voice recognition module. Since the mobile terminal capable of voice recognition can process only the same voice data as the voice command stored in the memory 11, Since there is a need to consume resources of the storage means of the mobile communication terminal and have a separate module, there is a problem in that the space inside the mobile communication terminal is consumed.

2 is a block diagram showing a configuration of connecting to the Internet using a conventional mobile communication terminal, comprising a mobile communication terminal 20, a base station 21, a WAP gateway 22, and a web server 23 do. When a button for accessing the Internet of the button input unit 10 of the mobile communication terminal 20 is input, the mobile communication terminal 20 establishes a connection with the Internet web server 23 through the base station 21. It is connected to the WAP gateway 22 to enable, and receives the data for the web page initially set from the web server 23 through the data transmission and reception unit 13, and provides it to the user through the display unit 12 do. In addition, by using voice XML and voice recognition technology in the above configuration, it is possible to provide a service through a command or a voice from the limitation of a narrow screen and limited key input of a mobile communication terminal, but the content or web browser provided in the past There is a problem in that independent content must be produced because it is incompatible with.

Accordingly, in order to solve the above problems, the present invention provides an internet of a mobile communication terminal using voice recognition that can access and search an Internet site using a user's voice without changing the hardware format of the mobile communication terminal and the format of the wireless Internet content. It is an object to provide a site connection device.

Another object of the present invention is to provide a method for accessing an internet site of a mobile communication terminal using voice recognition, which can access and search an internet site using a voice of a mobile communication terminal user.

1 is a block diagram showing the configuration of a conventional general mobile communication terminal.

2 is a block diagram showing a configuration for connecting to the Internet using a conventional mobile communication terminal.

Figure 3 is a block diagram showing the configuration of the Internet site access device of the mobile communication terminal using the voice recognition according to the present invention.

4 is a block diagram showing the configuration of a mobile communication terminal of FIG.

5 is a block diagram showing the configuration of a server for voice recognition of FIG.

6 is a flowchart illustrating a process of accessing an internet site of a mobile communication terminal using voice recognition according to the present invention.

7 is a flowchart illustrating a process of accessing an internet site in a mobile communication terminal of FIG. 6 in an offline state.

8 is a flowchart illustrating a process of accessing an internet site by the mobile communication terminal of FIG. 6 in an online state.

9 is a flowchart illustrating a speech recognition grammar mapping process for speech recognition of FIG. 6.

(Explanation of symbols for the main parts of the drawing)

100: mobile communication terminal 110: microphone

120: EVRC encoder 130: multi-modal module

140: browser 150: wireless module

200: multi-modal server 210: network connection

220: voice data conversion unit 230: speech recognition grammar mapping unit

240: global grammar mapping unit 250: target URL generation unit

260: database 300: speech recognition server

400: WAP Gateway 500: CP Web Server

In order to achieve the above object, the present invention provides a browser for accessing the Internet through a wireless network, an encoder for converting voice data input into a microphone, and URL information of a site currently being accessed from the browser, and the voice converted by the encoder. A mobile communication terminal having multi-modal means for transmitting data and information of the mobile communication terminal to a multi-modal server; A target to determine a grammar required for voice recognition from the current URL information transmitted from the mobile communication terminal, transmit the voice recognition grammar together with the voice data to a voice recognition server, and access through a result recognized by the voice recognition server A multimodal server generating a URL and transmitting the generated URL to a mobile communication terminal; A speech recognition server for recognizing speech using the speech data and the speech recognition grammar transmitted from the multi-modal server, and transmitting the recognized result to the multi-modal server; And a web server to which the mobile communication terminal accesses using a target URL transmitted from the multi-modal server.

The present invention also provides a mobile communication terminal, a multimodal server for mapping a speech recognition grammar using a voice data and a URL transmitted from the mobile communication terminal, generating a target URL, and a data transmitted from the multimodal server. In the Internet access device of the voice recognition mobile communication terminal consisting of a voice recognition server for performing voice recognition using a CP web server connected to the mobile communication terminal, it is determined whether the web browser of the mobile communication terminal is executed, Transmitting voice data input to a mobile communication terminal, URL information of a current page, and information of the mobile communication terminal to a multimodal server when a web browser is executed; Generating a speech recognition grammar required for speech recognition using the URL of the current page transmitted from the terminal, and transmitting the generated speech recognition grammar to the speech recognition server together with the speech data; Transmitting a voice recognition result using the voice data transmitted from the multi-modal server and a voice recognition grammar to a multi-modal server; Generating a target URL to be moved to a new page using the recognition result and transmitting the generated target URL to a mobile communication terminal; Requesting a new page to be moved by transmitting a target URL transmitted from the multi-modal server to a CP server; And outputting a new page transmitted from the CP server to the terminal.

Hereinafter, exemplary embodiments of the present invention will be described with reference to the accompanying drawings.

3 is a block diagram showing the configuration of the Internet site access device of the mobile communication terminal using the voice recognition according to the present invention. In FIG. 3, a mobile communication terminal 100 is connected to the Internet through a web browser and transmits voice data and a current URL (uniform resource locator), and the voice is transmitted using the current URL transmitted from the mobile communication terminal 100. Multi-modal server (MultiModal server: 200) for mapping the recognition grammar and generating a target URL of the new page to move, and voice recognition using the voice data and the speech recognition grammar transmitted from the multi-modal server 200 The server 300 and the mobile communication terminal 100 are configured with a gateway 400 and a CP web server (Content Provider Web Server: 500) to access the Internet.

4 is a block diagram showing the configuration of the mobile communication terminal of FIG. 3, wherein the mobile communication terminal 100 includes a communication unit (not shown), a microphone 110, an encoder 120, a multi-modal module 130, and a browser. 140, and a wireless module 150.

The encoder 120 compresses and converts the voice input through the microphone 110, and the encoder 120 is 8Kbps EVRC or 13Kbps QCELP, and other types of encoders may be used according to the type of mobile communication terminal. Preferably, the encoder 120 is an 8 Kbps EVRC encoder.

The multi-modal module 130 includes voice data compressed and converted by the encoder 120, URL information of the current page detected by the browser 140, and terminal information (eg, a type of browser, a mobile communication phone). Number, etc.) is transmitted to the voice recognition system (not shown) through the wireless module 150.

FIG. 5 is a block diagram illustrating a configuration of a server for voice recognition of FIG. 3. In FIG. 5, the server for speech recognition includes a multi-modal server 200 and a voice data transmitted from the multi-modal server 200 generating a target URL to be newly moved according to a unique speech recognition grammar and a recognition result for speech recognition. And a voice recognition server 300 for recognizing the voice using the voice recognition grammar and transmitting the recognition result to the multi-modal server 200.

The multi-modal server 200 includes a network connection unit 210, a voice data conversion unit 220, a speech recognition grammar mapping unit 230, a global grammar mapping unit 240, and a target URL generation unit 250. And a database 260.

The network connection unit 210 is connected to a mobile communication terminal (not shown) to transmit and receive data, preferably by using the TCP / IP protocol.

The voice data conversion unit 220 is connected to the network connection unit 210, and converts the voice data transmitted from the network connection unit 210 so that the voice recognition engine can process, preferably converted to PCM format, If the speech recognition engine can directly process the compression format (for example, EVRC format) transmitted from the mobile communication terminal, the conversion process can be omitted.

The speech recognition grammar mapping unit 230 detects a valid speech recognition grammar valid for the page from the URL transmitted from the network connection unit 210 and maps it to the transmitted URL. Map the conditions that should occur in relation. That is, the voice recognition grammar specifies a predetermined voice command to be generated for a predetermined URL, and the list of voice commands inputted from the URL becomes the voice recognition grammar. For example, in a page that outputs a stock quote, when a voice name is inputted, the list of company names of all listed companies becomes a voice recognition grammar so that the current stock price of the voice input company can be reported. URLs are mapped.

The global grammar mapping unit 240 may have a unique voice recognition grammar determined by the voice recognition mapping unit 230 and a voice command that is commonly valid regardless of the current page of the browser (eg, help, bookmark). Maps to a speech recognition grammar.

The target URL generation unit 250 is connected to the network connection unit 210 and the voice recognition server 300 and target URL to move the URL designated by the command using a command according to the transmitted terminal information and the voice recognition result Create and transmit to the network connection unit 210. For example, when the "stock quote" site has a voice recognition of "Samsung Electronics", the target URL is set to view the current stock quotes of Samsung Electronics among sub-sites of the stock quote site.

The speech recognition server 300 is connected to the multi-modal server 200, and recognizes the speech using the speech data and the speech recognition grammar transmitted from the multi-modal server 200, the speech recognition known in the present invention Use the system.

6 is a flowchart illustrating a process of accessing an internet site of a mobile communication terminal using voice recognition according to the present invention. 3 to 6, the controller (not shown) of the mobile communication terminal 100 determines whether the web browser is executed (S10), and when the web browser 140 is not executed, as shown in FIG. Detecting whether a key input has occurred (S11), when a specific key input has occurred, the voice input into the microphone is converted and stored by the encoder, and the stored information is a URL of an initially set page (for example, a URL of "nate" http: // wap.nate.com) and transmits to the multi-modal server (S13), and further comprises the step (S12) of performing a function of a general mobile terminal when a specific key input does not occur in step S11. .

In step S10, when the web browser 140 is executed, voice data input to the mobile communication terminal 100, URL information of the current page, and information of the mobile communication terminal are transmitted to the multimodal server 200. Step S20 is performed.

In step S20, as shown in FIG. 8, it is determined whether an input is generated from the microphone 110 (S21). When no voice input occurs, general web surfing is performed (S22). In step S21, the voice input is performed. In this case, the voice input from the microphone 110 is converted by the encoder 120 and transmitted to the multi-modal module 130 (S23). When the converted voice data is transmitted in step S23, the multi-modal module 130 is transmitted. ) Requests the browser information and the URL information of the current page from the currently running web browser 140 (S24), the voice data converted in step S23 and the URL information of the current page obtained in step S24 and the mobile communication terminal. Information (eg, browser type, mobile communication phone number, etc.) is transmitted to the multimodal server 200 through the wireless module 150 (S25). In addition, the step S21 may be performed after the web browser 140 is executed and a specific key value is input.

After performing the step S20, using the URL of the current page transmitted from the terminal 100 to generate a speech recognition grammar required for speech recognition, the generated speech recognition grammar with the voice data to the speech recognition server (300) ) S30.

In step S30, as shown in FIG. 9, the mobile terminal 100 requests voice recognition to receive voice data transmitted from the mobile communication terminal 100, the current URL, and terminal information (S31). In operation S33, a unique speech recognition grammar corresponding to each URL is mapped from the current URL information received in step S31, and the unique speech recognition grammar mapped in step S33 is combined with a global speech recognition grammar valid in any page ( S34).

The step S33 is a method of mapping using the speech recognition grammar corresponding to each URL stored in the database 260 of the multi-modal server 200 and the URL stored in the database 260, the multi-modal server 200 Only the URL is stored, and the unique speech recognition grammar corresponding to the URL is stored in the external CP server 500, and if necessary, a method for mapping the speech recognition grammar of the external CP server 500 specified by the URL, and for screen display. If you do not extend the grammar of the scripting language with minimal or no extension, specify a URL in the meta tag or the comment of the script to specify a URL for valid speech recognition grammar on the page, and display the script for the screen display. The speech recognition grammar obtained from the web server of the CP is detected, and the speech recognition grammar stored in the database 260 of the multi-modal server 200 using the URL. Maps by using any of the methods from the method of mapping, preferably maps all of the data from the multi-modal server.

The step S30 further includes a PCM conversion to process the voice data transmitted from the mobile communication terminal 100 to the voice recognition engine.

After performing the step S30, the voice is transmitted using the voice data transmitted from the voice recognition server 300 and the voice recognition grammar, and the recognized result is transmitted to the multi-modal server 200 (S40). The speech recognition method used in the step S40 may use a known speech recognition method, preferably speaker-independent speech recognition method.

Using the speech recognition result transmitted in step S40, a target URL to be moved to a new page is generated and transmitted to the mobile communication terminal 100 (S50). In step S50, the target URL is basically specified in the speech recognition grammar, but may have a variable that is not simply a fixed URL. For example, if the command recognized in the stock quote page is "Samsung", the target URL is "Samsung" recognized in $ {x} above at http://stock.nate.com?name=${x}. The word is inserted. In addition, when using a multi-slot speech recognition engine that can extract one or more keywords from a sentence, the slot name can be mapped to the query variable name of the target URL. For example, if a voice of "Wake up call tomorrow at 6:30" is inputted, the speech recognition engine that recognizes the voice may generate a http://pim.nate.com?action=newitem&time=$ { t} & item = $ {item} &. In the $ {t} "tomorrow 6:30" and $ {item} in the "wake".

When the target URL generated after performing step S50 is transmitted to the CP server 500 and requests a new page to be moved (S60), the CP server 500 searches for the information of the new page and URL information of the new page to be moved. Is transmitted to the mobile communication terminal 100 and output through a display device (not shown) of the mobile communication terminal (S70).

As described above, the present invention has the advantage that a user of a wireless Internet using a mobile communication terminal can conveniently use desired information using a keypad or voice. It has the advantage that it can be used without modifying the format.

In the above, the present invention has been illustrated and described with respect to certain preferred embodiments. However, the present invention is not limited only to the above-described embodiments, and those skilled in the art to which the present invention pertains may vary without departing from the spirit of the technical idea of the present invention described in the claims below. It will be possible to carry out the change.

Claims (11)

A browser accessing the Internet through a wireless network, an encoder for converting voice data input into a microphone, and URL information of the current site detected by the browser, voice data converted by the encoder, and information of a mobile communication terminal. A mobile communication terminal having multi-modal means for transmitting to a server; A target to determine a grammar required for voice recognition from the current URL information transmitted from the mobile communication terminal, transmit the voice recognition grammar together with the voice data to a voice recognition server, and access through a result recognized by the voice recognition server A multimodal server generating a URL and transmitting the generated URL to a mobile communication terminal; A speech recognition server for recognizing speech using the speech data and the speech recognition grammar transmitted from the multi-modal server, and transmitting the recognized result to the multi-modal server; And An internet access device of a mobile communication terminal using voice recognition comprising a web server to which the mobile communication terminal accesses using a target URL transmitted from the multi-modal server. The apparatus of claim 1, wherein the multimodal server comprises: a speech recognition grammar mapping unit configured to search a database for a unique speech recognition grammar valid on the page from a current URL and map the current speech to a current URL; A global grammar mapping unit for mapping the unique speech recognition grammar mapped by the speech recognition grammar mapping unit and the global speech recognition grammar valid in all URLs; And And a target URL generator configured to generate a target URL to which the URL of the current page is to be moved using the recognition result. The Internet access apparatus of claim 1, wherein the multi-modal server further comprises a voice data converter for converting the voice data encoded by the mobile communication terminal into a predetermined format. A voice recognition grammar is mapped using the mobile communication terminal, the voice data transmitted from the mobile communication terminal and the URL, a multimodal server generating a target URL, and the voice recognition is performed using the data transmitted from the multimodal server. In the Internet access device of the voice recognition mobile communication terminal consisting of a voice recognition server to be executed and a CP web server connected to the mobile communication terminal, It is determined whether a web browser of the mobile communication terminal is executed, and when the web browser is executed, voice data input to the mobile communication terminal, URL information of the current page, and information of the mobile communication terminal are transmitted to the multimodal server. Doing; Generating a speech recognition grammar required for speech recognition using the URL of the current page transmitted from the terminal, and transmitting the generated speech recognition grammar to the speech recognition server together with the speech data; Transmitting a voice recognition result using the voice data transmitted from the multi-modal server and a voice recognition grammar to a multi-modal server; Generating a target URL to be moved to a new page by using the recognition result and transmitting it to a mobile communication terminal; Requesting a new page to be moved by transmitting a target URL transmitted from the multi-modal server to a CP server; And Outputting a new page transmitted from the CP server to the terminal. The method of claim 4, wherein the determining of whether the web browser is executed comprises: detecting whether a specific key input has occurred when the web browser is not executed, converting and storing a voice input by a microphone in the encoder when a specific key input occurs, Transmitting the stored information to the multimodal server together with the URL of the initially set page; And If the specific key input does not occur, further comprising the step of performing the function of the general mobile communication terminal Internet access method of the mobile communication terminal using the voice recognition. The method of claim 4, wherein the transmitting of the voice data and the current URL information to the multi-modal server comprises determining whether a voice input has occurred and performing general web surfing when no voice input has occurred, and when the voice input has occurred. Converting and transmitting the input voice in an encoder; Requesting browser information and URL information of the current page from a running web browser; And And transmitting the converted voice data, the URL information of the current page, and the mobile communication terminal information. The method of claim 4, wherein the generating of the voice recognition grammar required for voice recognition using the URL of the current page comprises: receiving voice data, current URL, and terminal information by connecting to a mobile communication terminal requesting voice recognition; ; Mapping from the received current URL information to a unique speech recognition grammar corresponding to each URL; And Combining the mapped unique speech recognition grammar and voice recognition commands useful anywhere, Internet access method of a mobile communication terminal using a voice recognition characterized in that it comprises. The method of claim 7, wherein the mapping of the received current URL information to a unique speech recognition grammar corresponding to each URL is performed by comparing the current URL with a URL stored in the multimodal server to each URL stored in the multimodal server database. An internet access method of a mobile communication terminal using speech recognition, characterized in that mapping with a corresponding unique speech recognition grammar. 8. The method of claim 7, wherein mapping from the received current URL information to a unique speech recognition grammar corresponding to each URL corresponds to a current URL, a URL stored in a multimodal server, and a URL stored in an external CP web server. Internet access method of a mobile communication terminal using a voice recognition, characterized in that for mapping the unique speech recognition grammar. 8. The method of claim 7, wherein the mapping of the received current URL information to a unique speech recognition grammar corresponding to each URL comprises a predetermined marking on a screen display script to designate a URL for the speech recognition grammar valid for the page. And the screen display script is obtained from a web server of a CP to detect a URL of a speech recognition grammar, and the speech recognition grammar stored in a multi-modal server is mapped using the URL. Internet connection method of the terminal. The method of claim 4, wherein the generating of the speech recognition grammar required for speech recognition using the URL of the current page further comprises converting the speech data transmitted from the terminal into a PCM. Internet access method of mobile communication terminal.