RU2412463C2 - Mobile communication terminal and menu navigation method for said terminal - Google Patents

Abstract

FIELD: information technology.

SUBSTANCE: mobile communication terminal has an input apparatus configured to receive input data for activating speech recognition functions in the mobile communication terminal, and memory configured to store a plurality of areas associated with the menu and with operating modes of the mobile communication terminal. Said terminal also includes a computer which is configured to access specific areas from the plurality of areas in the memory, based on received input data for activating speech recognition functions, recognise user speech based on the language model and the acoustic model of the area which has been accessed, and determine at least one menu and one operating mode for the mobile communication terminal based on the specific area which has been accessed, and the recognised user speech.

EFFECT: improved user speech recognition.

26 cl, 22 dwg

Description

The present invention relates to a mobile communication terminal and to a corresponding method capable of providing an increase in the percentage of correctly recognized words in speech recognition by defining an area for speech recognition in the form of information associated with specific menus or services.

State of the art

Currently, mobile communication terminals provide many additional services in addition to basic telephone services. For example, at present, a subscriber can access the Internet, play games, watch videos, listen to music, take photos and videos, record audio files, etc. Currently, mobile communication terminals also receive broadcast programs, so the subscriber can watch television shows, sports programs, videos, etc.

In addition, since there has been a significant expansion of the functions contained in the mobile communication terminals, the user interfaces have also become more complex. For example, user interfaces now include touch screens, giving the user the ability to touch the screen and select a specific item or menu item. Mobile communication terminals also contain very limited speech recognition functions that provide the user with the ability to perform basic functions. However, the frequency of occurrence of errors in determining the meaning of a user's speech command is too high, and therefore users, as a rule, do not use the limited speech recognition functionality available in the terminal.

SUMMARY OF THE INVENTION

Accordingly, one of the objectives of the present invention is to solve the above and other problems.

Another objective of the present invention is to provide a mobile communication terminal and a corresponding method for managing menus associated with its specific functions or services by recognizing the meaning of a speech command based on context and content.

Another objective of the present invention is to provide a mobile communication terminal and a corresponding method that provides a significant increase in the percentage of correctly recognized words in speech recognition by defining an area for speech recognition in the form of an area associated with specific menus or services.

Another objective of the present invention is to provide a mobile communication terminal and a corresponding method for managing menus associated with specific functions or services by applying one or more user interfaces (UIs) therein, while the speech recognition function is activated in this way what user manipulation reveals.

Another objective of the present invention is the creation of a mobile communication terminal and a corresponding method that provides the ability to control menus associated with specific functions or services, even by an inexperienced user, by his or her voice command, by providing reference information about entering a voice command in accordance with the operating state or with the operating mode of this mobile communication terminal.

To achieve these and other advantages, and in accordance with the purpose of the present invention, implemented and described here in General terms, according to one of the objects of the present invention, it proposes a mobile communication terminal containing an input device made in such a way that it is able to receive entered data for activating a speech recognition function in a mobile communication terminal, a storage device configured in such a way that it is able to memorize a plurality of areas related to menus and operating modes a mobile communication terminal, and a controller configured in such a way that it is able to access a specific area from a plurality of areas contained in the storage device, based on the received input data for activating a speech recognition function, to recognize a user's speech based on a language model and an acoustic area model accessed and determine at least one menu and one operating mode of the mobile communication terminal based on the specific area to which access is made n, and recognizes the user's speech.

According to another aspect of the present invention, there is provided a method for controlling a mobile communication terminal. The method comprises the following operations: receiving input data for activating a speech recognition function in a mobile communication terminal, accessing a specific area from a stored set of areas contained in a storage device of a mobile communication terminal, based on received input data for activating a speech recognition function, recognizing a user's speech based on the language model and the acoustic model of the accessed area, and at least one menu and an operating mode are output mobile erminala based on a particular field to which accessed, and recognizes the user's speech.

A further scope of applicability of the present invention will become apparent from the following detailed description. However, it should be understood that the detailed description and specific examples, despite indicating preferred embodiments of the present invention, are provided for illustrative purposes only, as for those skilled in the art from this detailed description, the possibility of various changes and modifications without departing from the scope will be apparent. the nature and scope of patent claims of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

The present invention will become more apparent from the following detailed description and from the accompanying drawings, which are given for illustrative purposes only and, therefore, do not limit the present invention, and which depict the following:

in FIG. 1 is a block diagram of a mobile communication terminal according to an embodiment of the present invention;

in FIG. 2 is a front perspective view illustrating a mobile communication terminal according to one embodiment of the present invention;

in FIG. 3 is a rear perspective view illustrating the mobile communication terminal shown in FIG. 2;

in FIG. 4 is a perspective view of a communication system capable of operating with a mobile communication terminal of the present invention;

in FIG. 5 is a flowchart illustrating a menu control method for a mobile communication terminal by means of a voice command according to one embodiment of the present invention;

in FIG. 6A generally shows a method for activating a speech recognition function for a mobile communication terminal according to one embodiment of the present invention;

in the drawings of FIG. 6B and FIG. 6C is a perspective view illustrating a method for outputting help information in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 7A is a flowchart showing a method for recognizing a voice command in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 7B is a perspective view illustrating a voice command recognition method in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 8 is a perspective view illustrating a menu display method in accordance with the percentage of correctly recognized words in speech recognition in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 9 is a perspective view illustrating a voice command recognition method in a mobile communication terminal according to another embodiment of the present invention;

in FIG. 10 generally shows a configuration of databases used as reference information for recognizing a voice command in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 11 is a general view of a state in which a voice recognition function is performed in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 12 is a perspective view illustrating a method for processing subcommands associated with a particular menu by means of a voice command in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 13 shows, in a general view, a metro search method using a voice command in a mobile communication terminal according to an embodiment of the present invention;

in FIG. 14 is a perspective view illustrating a method of reproducing multimedia files by means of a voice command in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 15 is a perspective view illustrating a method for transmitting an e-mail message using a voice command in a mobile communication terminal according to an embodiment of the present invention;

in FIG. 16 is a perspective view illustrating a method of making a telephone call using a voice command in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 17 shows, in a general view, a method for using information from a telephone book by means of a voice command in a mobile communication terminal according to one embodiment of the present invention;

in FIG. 18 shows, in a general view, a method for changing a displayed background image by a voice command in a mobile communication terminal according to one embodiment of the present invention; and

in FIG. 19 is a perspective view illustrating a method for reproducing multimedia files by means of a voice command in a mobile communication terminal according to one embodiment of the present invention.

DETAILED DESCRIPTION OF THE INVENTION

A detailed description will now be made of preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings.

In FIG. 1 is a block diagram of a mobile communication terminal 100 according to one embodiment of the present invention. As shown in the drawing, the mobile communication terminal 100 comprises a wireless communication unit 110 containing one or more components that allows wireless communication between the mobile communication terminal 100 and the wireless communication system or network within which the mobile communication terminal is located.

For example, the wireless communication unit 110 comprises a broadcast reception module 111 that receives a broadcast signal and / or information related to a broadcast from an external broadcast control entity via a broadcast channel. A broadcast channel may include, but is not limited to, a satellite channel and a terrestrial channel.

In addition, the term "broadcast control entity" generally refers to a system that transmits a broadcast signal and / or broadcast related information. An example of information related to broadcast transmission is, inter alia, information related to the broadcast channel, the broadcast program, the broadcast service provider, etc. For example, broadcast related information may include an electronic program guide (EPG) for a digital multimedia broadcasting system (DMB) and an electronic service guide (ESG) of a digital broadcasting system for portable devices (DVB-H).

In addition, the broadcast signal may be implemented, inter alia, in the form of a television broadcast signal, a broadcast signal, and a data broadcast signal. In addition, the broadcast signal may comprise a broadcast signal combined with a television broadcast signal or a broadcast signal.

The broadcast reception module 111 is also configured to receive broadcast signals transmitted from various types of broadcast systems. Such broadcasting systems are, for example, a terrestrial digital multimedia broadcasting system (DMB-T), a satellite digital multimedia broadcasting system (DMB-S), a digital broadcasting system for portable devices (DVB-H), a broadcasting system, Known as Direct Link Only Multimedia Information System (MediaFLO®) and Integrated Services Terrestrial Digital Broadcasting System (ISDB-T). Multicast reception is also possible. In addition, the data received by the broadcast reception module 111 may be stored in a corresponding device, for example, a storage device 160.

The wireless communication unit 110 also includes a mobile communication module 112, which transmits radio signals to one or more network entities (which, for example, are a base station, node B (Node B)) / receive radio signals from them. These signals may include, but are not limited to, audio signals, video signals, multimedia signals, transmitted control signals, and data.

It also includes an Internet wireless access module 113, which provides Internet access support for a mobile communication terminal. The connection of the module 113 with the terminal may be internal or external. The wireless communication unit 110 also includes a short-range communication module 114, which accordingly facilitates short-range communication. Technologies suitable for implementing this module include, but are not limited to: radio frequency identification (RFID) technology, infrared data transmission technology in accordance with the IrDA standard, approved by the Infrared Data Communication Association, ultra wideband radio communication (UWB) technology, as well as network technologies commonly referred to as Bluetooth technology and ZigBee technology.

The wireless communication unit 110 also includes a positioning module 115, and it recognizes the location of the mobile communication terminal 100 or otherwise obtains its location information. The positioning module 115 may be implemented using Global Positioning System (GPS) components that communicate with respective satellites, network components, and combinations thereof.

In addition, as shown in FIG. 1, the mobile communication terminal 100 also comprises an audio / video (A / V) signal input unit 120 that provides audio or video signals to the mobile communication terminal 100. As shown in the drawing, the audio / video (A / V) input unit 120 includes a camera 121 and a microphone 122. The camera 121 receives and processes image frames of photographs or videos.

In addition, when the portable device is in a particular mode, for example, in a telephone conversation mode, a recording mode, and a speech recognition mode, the microphone 122 receives an external audio signal. Then, the received audio signal is processed and converted into digital data. The portable device, and in particular the audio / video (A / V) signal input unit 120, also comprises various noise removal algorithms designed to remove noise generated during the reception of an external audio signal. In addition, the data generated by the audio / video (A / V) input unit 120 may be stored in the storage device 160, may be used by the output unit 150, or may be transmitted by one or more modules of the communication unit 110. If desired, two or more microphones and / or two or more cameras can be used.

The mobile communication terminal 100 also comprises a user data input device 130 that generates input data in response to user manipulation of a corresponding device or corresponding input devices. Examples of such devices are, for example, a keypad, a switch with an elastic dome-shaped key (dome switch), a touchpad (for example, based on a change in electric capacitance when static pressure is applied), a control wheel (jog wheel) and a joystick switch ( jog switch). A specific example is as follows: the user data input device 130 is configured as a touch panel cooperating with a touch screen display, which is described in more detail below.

The mobile communication terminal 100 also includes a sensor 140, and this sensor 140 provides status measurements of various aspects of the operation of the mobile communication terminal 100. For example, the sensor 140 may detect whether the mobile communication terminal 100 is in an open / closed state, the relative location of the components (eg, display and keypad) of the mobile communication terminal 100, the location of the mobile terminal 100 or a component of the mobile communication terminal 100, the presence or lack of user contact with the mobile communication terminal 100, orientation or acceleration / deceleration of movement of the mobile communication terminal 100, etc.

For example, when the mobile communication terminal 100 is a movable type mobile communication terminal, the sensor 140 may detect whether the movable portion of the mobile communication terminal 100 is open or closed. Other examples are, inter alia, the following: the sensor 140 detects the presence or absence of power provided by the power source 190, the presence or absence of a connection or other connection between the interface unit 170 and an external device, etc.

In addition, the interface unit 170 is often implemented in such a way that the mobile terminal 100 is in communication with external devices. Typical external devices include, but are not limited to, wired / cordless head phones, external chargers, power supplies, data storage devices designed to store data (e.g., audio data, video, images, etc.), headphones and microphones. In addition, the interface unit 170 can be configured using a wired / wireless data port, a card slot (for example, to connect to a memory card, to a subscriber identity module (SIM) card, to a subscriber identity module (UIM) card, with a plug-in Subscriber Identity Module (RUIM) card, etc.), audio input / output ports, and video input / output ports.

The output unit 150 typically contains various components that provide the output of the desired signals in the mobile communication terminal 100. The mobile communication terminal 100 also includes a display 151 that provides a visual display of information associated with the mobile communication terminal 100. For example, if the mobile communication terminal 100 is in a telephone conversation mode, then the display 151 typically provides a user interface or graphical user interface containing information related to ordering, conducting and ending the telephone conversation. As another example, if the mobile communication terminal 100 is in a videophone conversation mode or in a photographing mode, the display 151 may additionally or alternatively display images associated with these modes on the display screen.

In addition, the display 151 also preferably includes a touch screen that works in conjunction with an input device, such as a touch panel. This configuration allows the display 151 to function both as an output device and as an input device. In addition, the display 151 can be implemented using, inter alia, information display technologies such as, for example, a liquid crystal display (LCD), a thin-film transistor liquid crystal display (TFT-LCD), an organic light emitting diode (OLED) display, flexible display and three-dimensional display.

The mobile communication terminal 100 may also contain one or more such displays. An example of an embodiment with two displays is as follows: one display is designed to be an internal display (which is visible when the terminal is in the open position), and the second display is designed to be an external display (which is visible in both positions: in the open position and in the closed position).

In addition, FIG. 1 shows an output device 150 comprising an audio output module 152 that provides output of desired audio signals to a mobile communication terminal 100. Sound output module 152 may be implemented using one or more speakers, buzzers, other sound generating devices, and combinations of these devices. In addition, the audio output module 152 operates in various modes, including in a telephone call reception mode, in a telephone call execution mode, in a recording mode, in a speech recognition mode, and in a broadcast reception mode. During operation, the audio output module 152 outputs audio signals associated with a particular function (for example, with a received phone call, with a received message, and with errors).

In addition, the drawing shows that the output unit 150 further comprises a signaling device 153, which is used to signal the occurrence of a specific event associated with the mobile communication terminal 100, or to recognize the fact of its occurrence in another way. The events signaled are, inter alia, the received call, the received message and the received data entered by the user. An example of such an output effect is, inter alia, the creation of tactile sensations (for example, vibration) for the user. For example, the signal device 153 may be configured to vibrate in response to receiving a telephone call or message by the mobile communication terminal 100.

As another example, the signal device 153 vibrates in response to receiving user input at the mobile communication terminal 100, thereby providing a tactile feedback mechanism. In addition, the various output effects created by the components of the output device 150 may be implemented separately, or such an output effect may be implemented using any combination of these components.

In addition, a storage device 160 is used to store various types of data to provide the required processing, required control, and data storage in the mobile communication terminal 100. Examples of such data are, inter alia, program instructions for application programs operating in the mobile communication terminal 100, telephone call history, contact data, phone book data, messages, images, video information, etc.

In addition, the storage device 160 shown in FIG. 1 can be implemented using suitable volatile and non-volatile memory devices or storage devices of any type, which are, including random access memory (RAM), static random access memory (static RAM), electrically erasable programmable read-only memory ( EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (EPROM), read-only memory troystvo (ROM), magnetic memory, flash memory, magnetic or optical disk, memory device on memory cards or other similar memory or data storage device, or a combination of these devices.

The terminal 100 also includes a controller 180, which typically controls the operation of the entire mobile communication terminal 100. For example, the controller 180 performs control and processing that are associated with telephone calls in voice mode, with data transfer, with instant messaging, with calls in video telephony mode, with camera operations and recording operations. As shown in FIG. 1, the controller 180 may also comprise a multimedia module 181 designed to provide multimedia information playback functions. The multimedia module 181 may be implemented as part of the controller 180, or may be implemented as a separate component.

In addition, the power source 190 provides energy used by various components of the portable device. The power provided may be internal power, external power, or combinations thereof.

In the following drawing of FIG. 2, a mobile communication terminal 100 according to one embodiment of the present invention is shown in a front-side view. As shown in FIG. 2, the mobile communication terminal 100 comprises a first housing 200 configured so that it can slide along the rails in cooperation with the second housing 205. The user data input device 130 described with reference to FIG. 1 may include a first data input device, for example, function buttons 210, a second data input device, for example, a keypad 215, and a third data input device, for example, side keys 245.

Function buttons 210 are associated with the first housing 200, and the keypad 215 is associated with the second housing 205. The keypad 215 contains various keys (eg, numbers, letters, and symbols) allowing the user to make a phone call, prepare a text or multimedia message, and control the terminal 100 mobile communications in any other way.

In addition, the first housing 200 can be moved by sliding relative to the second housing 205 between the open position and the closed position. In the closed position, the first housing 200 is located on top of the second housing 205 so that the keypad 215 is substantially or completely closed by the first housing 200. In the open position, the user can access the keypad 215, as well as the display 151 and the function buttons 210, . Function buttons 210 are convenient for user input of commands such as, for example, start, stop, and scroll commands.

In addition, the mobile communication terminal 100 is capable of operating either in standby mode (in which it, for example, is capable of receiving a telephone call or message, receiving communication network control signals and responding to them) or in an active telephone call mode. Typically, the mobile communication terminal 100 operates in the standby mode when it is in the closed position, and in the active mode when it is in the open position. However, the configuration of the mode can be changed if necessary or as desired.

In addition, the first casing 200 is formed from the first casing 220 and the second casing 225, and the second casing 205 is formed from the first casing 230 and the second casing 235. The first and second casings are preferably made of a suitable material provided with stiffeners, for example, plastic obtained injection molding, or molded using metal, such as stainless steel (STS) and titanium (Ti).

If desired, one or more intermediate casings located between the first and second casings of one of the housings may be provided: the first housing 200 and the second housing 205, or both of these housings. In addition, the first housing 200 and the second housing 205 are sized to accommodate electronic components used to support the operation of the mobile communication terminal 100.

The first housing 200 also includes a camera 121 and a sound output device 152, which is designed as a loudspeaker appropriately positioned relative to the display 151. The camera 121 can also be designed so that it can optionally be set to a predetermined position (for example, rotated, swiveled, etc.) relative to the first housing 200.

In addition, function buttons 210 are located adjacent to the lower side of the display 151. As described above, the display 151 may be implemented as a liquid crystal display (LCD), or as an organic light emitting diode (OLED) display. The display 151 can also be made in the form of a touch screen equipped with a touch panel located beneath it, which generates signals in response to the user's touch (for example, with a finger, stylus pen, etc.) to the touch screen.

The second body 205 also includes a microphone 122 located adjacent to the keypad 215, and side keys 245, which are one type of user input device, located along the side of the second body 205. In a preferred embodiment, the side keys 245 are in the form of shortcut keys functions (hot keys) so that the side keys 245 are associated with a specific function of the mobile communication terminal 100. As shown in the drawing, an interface unit 170 is located adjacent to the side keys 245, and an electric power source 190 in the form of a battery is located at the bottom of the second housing 205.

3, the mobile communication terminal 100 shown in FIG. 2. depicted in rear-side view. As shown in FIG. 3, the second housing 205 comprises a camera 121 and its associated flash lamp 250 and a mirror 255. The flash lamp 250 functions in conjunction with the camera 121 of the second housing 205, and the mirror 255 is useful for assisting the user to properly position the camera 121 in self portrait mode. In addition, the camera 121 of the second body 205 faces in a direction opposite to that in which the camera 121 of the first body 200 shown in FIG. 2.

In addition, each of the chambers 121 of the first and second bodies 200 and 205 may have the same or different functionalities. For example, in one embodiment, the camera 121 of the first body 200 operates at a relatively lower resolution than the camera 121 of the second body 205. Such a device works well, for example, during telephone conferencing in a video conferencing mode, when the bandwidth of the feedback line can to be limited. In addition, the relatively higher resolution of the camera 121 of the second body 205 (FIG. 3) is useful for obtaining higher quality images for later use.

The second housing 205 also includes a sound output module 152, which is configured as a loudspeaker, and which is located at the top of the second housing 205. The audio output modules of the first and second housings 200 and 205 can also interact with each other to provide stereo audio output. In addition, either of these sound output modules, or both of them, may be configured in such a way that they function as a speakerphone.

The terminal 100 also includes an antenna 260 for receiving a broadcast signal located at the upper end of the second housing 205. The antenna 260 operates in conjunction with the broadcast reception module 111 (shown in FIG. 1). If desired, the antenna 260 can be mounted or configured in such a way that it can be pulled into the second housing 205. In addition, the rear side of the first housing 200 includes a rail sliding module 265 that is connected to a corresponding rail sliding module located on the front side of the second housing 205, with the possibility of its movement by sliding.

In addition, the illustrated arrangement of the various components of the first and second housings 200 and 205 may be modified as necessary or as desired. In the General case, in an alternative embodiment, some or all of the components of one housing can be implemented in such a way that they are located in another housing. In addition, the location and relative position of such components may be such that their locations differ from those shown in the drawings.

In addition, the mobile communication terminal 100 shown in the drawings of FIG. 1-3, can be performed in such a way that it works in a communication system that transfers data through frames or packets, including not only in wireless communication systems, but also in wired communication systems, and in satellite communication systems. Such communication systems use various radio interfaces and / or physical layers.

Examples of such radio interfaces used in communication systems are, for example, the following: frequency division multiple access, FDMA, time division multiple access, TDMA, code division multiple access, CDMA ( CDMA), and the radio communication interface of the Universal Mobile Telecommunications System (UMTS), the radio communication standard for the long-term development program (LTE) of the Universal Mobile Telecommunications System (UMTS) and the radio communication interface of the Global Mobile Telecommunications System (GSM). As a merely non-limiting example, the following description refers to a CDMA communication system, but the idea of this invention is equally applicable to other types of systems.

In the following drawing, FIG. 4 illustrates a CDMA wireless communication system comprising a plurality of mobile communication terminals 100, a plurality of base stations (BS) 270, a plurality of base station controllers (BSC) 275, and a mobile switching center 280 (MSC).

MSC 280 is configured in such a way that it is connected via an interface to the public switched telephone network 290 (PSTN), and MSC 280 is also such that it is connected via an interface to controllers 275 base stations (BSC). In addition, base station controllers (BSCs) 275 are connected to base stations 270 via feedback links. In addition, the feedback lines can be configured in accordance with any of several interfaces, which, for example, include the E1 / T1 line interface, the asynchronous transfer mode (ATM) line interface, the Internet Protocol (IP) interface, the interface point-to-point connection protocol (PPP), frame relay protocol interface (Frame Relay), high-speed digital subscriber line (HDSL) interface, asymmetric digital subscriber line (ADSL) or digital subscriber lines using xDSL technology. In addition, the system may contain more than two controllers 275 base stations (BSC).

In addition, each base station 270 may contain one or more sectors, with each sector containing an omnidirectional antenna or an antenna directed in a specific direction along the radius from the base station 270. Alternatively, each sector may contain two antennas for diversity reception . In addition, each base station 270 may be configured to support multiple allocations of the provided frequencies, with each distribution of the provided frequencies having a specific spectrum width (e.g., 1.25 MHz, 5 MHz).

The intersection of the sector and the frequencies provided may be referred to as a CDMA channel. Base stations 270 may also be referred to as base station transceiver subsystems, BTSs. In some cases, the term “base station” may be used in such a way that it refers to a combination of BSC 275 and one or more base stations 270.

Base stations 270 may also be referred to as "cellular network nodes." Alternatively, the nodes of a cellular network can be referred to as individual sectors of a particular base station 270 may. In addition, a transmitter 295 of a terrestrial digital multimedia broadcasting (DMB) system is shown broadcasting to mobile communication terminals 100 operating in the system.

In addition, the broadcast reception module 111 (shown in FIG. 1) of the mobile communication terminal 100 is typically configured to receive broadcast signals transmitted by the transmitter 295 of the digital multimedia broadcasting system (DMB). As described above, similar devices can be implemented for other types of broadcast and multicast signaling.

In addition, FIG. 4 illustrates several Global Positioning System (GPS) satellites 300. These satellites facilitate the location of some or all of the mobile communication terminals 100. In FIG. 4 shows two satellites, but location information can be obtained by more or less satellites.

In addition, the location module 115 (shown in FIG. 1) of the mobile communication terminal 100 is typically configured to communicate with satellites 300 to obtain desired location information. However, in an alternative embodiment, other types of positioning techniques may be implemented, such as a positioning technique that can be used in addition to, or instead of using, a Global Positioning System (GPS). Alternatively, or in addition to this, some or all of the satellites 300 of the Global Positioning System (GPS) can be arranged to transmit digital multimedia broadcasting (DMB) programs from satellites.

In addition, during normal operation of the wireless communication system, base stations 270 receive sets of signals transmitted on the feedback lines from various mobile communication terminals 100. Mobile communication terminals 100 participate in telephone calls, messaging, and other forms of communication.

In addition, each feedback signal received by a particular base station 270 is processed at the same base station 270 and the resulting data is sent to the corresponding BSC 275. The BSC 275 provides a telephone call resource allocation and mobility management functionality, including , soft handoffs of communication control between base stations 270.

In addition, the base station controllers 275 (BSC) also send the received data to the MSC 280, which provides additional routing services for communication with the PSTN 290. Similarly, the PSTN serves as a communication tool with the MSC 280, and the MSC 280 serves as a communication tool with 275 base controllers stations (BSC). Base station controllers (BSCs) 275 also control base stations 270 to provide for transmitting sets of signals over a direct link to mobile communication terminals 100.

In the description below, an explanation is given of a control method applicable to a mobile communication terminal 100 configured in the manner described above in various embodiments of the invention. However, the embodiments described below may be implemented independently or by combinations thereof. In addition, the description below assumes that the display 151 includes a touch screen. In addition, the touch screen or its screen is indicated below by the position number '400'.

In one embodiment of the present invention, a mobile communication terminal defines an area (or information retrieval range) of databases used as reference information for recognizing a voice command in the form of an area associated with a particular menu or with specific services. Accordingly, the percentage of correctly recognized words for the speech command increases and the total amount of resources used by the mobile communication terminal decreases.

In addition, the database area used as reference information for recognizing a speech command can be set via the operation mode setting menu of the mobile communication terminal. In addition, after the speech recognition function is activated, the predetermined area can be applied automatically.

In the description below, it is assumed that the predetermined area of the database for recognizing a speech command contains information related to the menu that is currently displayed on the display 151, or information associated with a submenu of one of the menus.

In the following drawing, FIG. 5 is a flowchart of a menu control method for a mobile communication terminal via a voice command according to one embodiment of the present invention. The following description also refers to FIG. 1. As shown in FIG. 5, the controller 180 determines whether the speech recognition function has been activated (operation S101).

Then, the speech recognition function can be activated by a user selecting hardware keys on a mobile communication terminal or touch keys displayed on the display unit 151. The user can also activate the speech recognition function by manipulating the specific menus displayed on the display 151. The speech recognition function can also be activated by the user creating specific sounds or sound effects, via short-range or long-range radio signals or through information coming from the user's body, for example by hand gesture or body movement.

More specifically, specific sounds or sound effects may include, but not limited to, shock sounds whose volume level exceeds a certain level. In addition, specific sounds or sound effects can be registered using a volume recognition algorithm. In addition to this, in a preferred embodiment, the volume recognition algorithm is simpler than the speech recognition algorithm and, therefore, consumes less resources of the mobile communication terminal. In addition, the volume level recognition algorithm (or circuit) may be implemented separately from the speech recognition algorithm or circuit, or it may be implemented in such a way that defines some functions of the speech recognition algorithm.

In addition, radio signals can be received by the wireless communication unit 110, and information about the hand gestures or the user's movements can be obtained by the sensor 140. Thus, in one embodiment of the present invention, the wireless communication unit 110, the user data input device 130 and sensor 140 may be referred to as a signal input device. In addition, the speech recognition function can also be completed in a similar manner.

The physical activation of a user’s speech recognition function is especially useful because the user is more aware that he / she is going to use voice commands to control the terminal. That is, since the user must first perform physical manipulation of the terminal, he or she intuitively realizes that they are going to enter a speech command or instruction into the terminal and, therefore, speak more distinctly or more slowly, thereby activating a specific function. Thus, since the user speaks more clearly or more slowly, then, for example, the likelihood of accurate recognition of voice commands increases. That is, in one embodiment of the present invention, the activation of the speech recognition function is performed by physically manipulating a key on the terminal, and not by activating the speech recognition function, speaking to the terminal.

Then, the controller 180 can start or complete the activation of the speech recognition function based on how many times the user has touched a particular key or a specific area of the touch screen, how long the user has touched a specific key or a specific area of the touch screen, etc. The user can also specify how the controller 180 should activate the speech recognition function using the appropriate menu item, which is provided by the present invention. For example, the user can select on the terminal the menu item that contains: 1) the installation of speech recognition activation based on the number of times equal to X that the speech control key was selected, 2) the installation of speech recognition activation based on the amount of time equal to X, during which the speech control key was selected, 3) the installation of speech recognition activation when the X and Y keys are selected, etc. The user can then enter the X and Y values to specify how the controller 180 determines whether the speech recognition activation function has been activated, with the possibility of changing these parameters. Thus, according to one embodiment of the present invention, the user actively activates the voice control function available in his own mobile communication terminal, which increases the likelihood that the controller 180 determines the correct function corresponding to the user's speech command and that allows the user to adapt the voice control function in accordance with his or her needs.

The controller 180 can also save the activated state of the speech recognition function during the time it touches a given key (to specified keys) or for the duration of pressing it (on them) and stop the speech recognition function when the specified key is released (specified keys are released). Alternatively, the controller 180 may retain activation of the speech recognition function for a predetermined period of time after touching or pressing a predetermined key (s), and stopping or completing the speech recognition function after a predetermined period of time. In yet another embodiment of the invention, the controller 180 may store the received speech commands in the memory 160 during the time that the speech recognition function is maintained in an activated state.

In addition, as shown in FIG. 5, the database area used as reference information for recognizing the meaning of the speech command is indicated as information associated with specific functions or menus in the terminal (operation S102). For example, a given area of the database may be indicated in information related to the menu displayed on the display 151 at the current time, or in information related to a submenu of one of the displayed menus. In addition, since the database area is specified, the percentage of correctly recognized words for the entered speech command increases. Examples of areas are, but are not limited to, the following: email area, area of received phone calls, area of multimedia information, etc.

Information associated with the submenu can also be configured as data in the database. For example, information may be configured as a keyword, and a plurality of pieces of information may correspond to a single function or menu. In addition, the database may be a plurality of databases corresponding to the characteristic features of the information, and it may be stored in the storage device 160.

In addition, the information in the database (s) of the data can be expediently adjusted or updated through the learning process. Each area of the respective databases can also be defined as an area associated with functions or with menus that are displayed at the current time, to increase the percentage of correctly recognized words of the speech command. This area can also be changed with further passage through the menu items.

After the speech recognition function has been activated (the result of operation S101 is “YES”) and the area has been set (operation S102), the controller 180 determines whether the user has entered the voice command (operation S103). In the case where the controller 180 determines that the user entered the voice command (the result of operation S103 is “YES”), the controller 180 analyzes the context and content of the voice command or instruction entered through the microphone 122 based on a specific database, finding out in fact, the meaning of the speech command (operation S104).

In addition, the controller 180 may determine the meaning of the speech instruction or command based on the language model and the acoustic model of the accessed area. In a more detailed presentation, the language model is directly related to the words themselves, and the acoustic model corresponds to how the words are spoken (for example, the frequency components of the spoken words or phrases). Using the language model and the acoustic model in conjunction with a specific area and with information about the operation mode of the mobile communication terminal 100, the controller 180 can effectively determine the meaning of the entered voice instructions or commands.

In addition, the controller 180 can immediately begin the process of ascertaining the meaning of the entered speech command when the user stops activating the speech recognition function, in the event that the controller 180 stores the entered speech command in the memory 160, or can perform the voice control function simultaneously with the input of the speech teams.

Then, if the voice command has not been entered completely (the result of operation S103 is “NO”), then the controller 180 may still perform other functions. For example, if the user performs a different action by touching a menu item on the screen, etc. or presses a key on the terminal (the result of operation S109 is “YES”), then the controller 180 performs the corresponding selected function (operation S110).

Then, after the meaning of the inputted voice command is determined by the controller 180 in step S104, the controller 180 outputs the resultant meaning of the command (step S105). That is, the resulting value may contain control signals for implementing menus related to functions or services that correspond to a specific meaning, for controlling specific components of a mobile communication terminal, etc. The resulting value may also contain data for visually displaying information associated with the recognized speech command.

The controller may also request the user to confirm that the output result value is accurate (step S106). For example, in the case when the percentage of correctly recognized words in the speech command is low, or when it is determined that it has many meanings, the controller 180 can display many menus associated with the corresponding meanings, and then implement the menu that is selected by the user (operation S107). The controller 180 may also prompt the user whether to implement a particular menu that corresponds to a high percentage of correctly recognized words, and then execute or display the corresponding function or the corresponding menu of the user's choice or according to his answer.

In addition, the controller 180 can also output a voice message asking the user to select a specific menu or menu item, for example, the following voice message: " Do you want to execute a photo album menu? Reply with Yes or No ""photo album? Answer yes or no"). Then, the controller 180 performs or does not perform a function corresponding to a particular menu or menu item based on the user's response. If the user does not respond within a specific period of time (equal to, for example, five seconds), then the controller 180 can also immediately implement a specific menu or menu item. That is, if no response has been received from the user, then the controller 180 may automatically execute the function or implement the menu, assuming that the absence of a response is a positive response.

In addition, the user can answer a question from the controller 180 using his or her voice (for example, “yes” or “no”) or through other input devices, such as hardware or soft keys, touch panel, etc. In addition, if a negative response is received from the user in operation S106 (the result of operation S106 is “NO”), that is, if the meaning of the speech command is not precisely determined, then the controller 180 may perform an additional error processing operation (operation S108).

That is, an error processing operation can be performed by repeatedly receiving an entered speech command, or it can be performed by displaying a plurality of menus for which the percentage of correctly recognized words exceeds a certain level or a plurality of menus that can be considered to have similar meaning. Then the user can select one of the many menus. Moreover, when the number of functions or menus for which the percentage of correctly recognized words exceeds a certain level is less than a predetermined number (equal to, for example, two), the controller 180 can automatically perform the corresponding function or implement the corresponding menu.

In the following drawing, FIG. 6A is a perspective view illustrating a method for activating a speech recognition function for a mobile communication terminal according to one embodiment of the present invention. As shown in the drawing, the user can activate the speech recognition function on the display screen 410 by touching the virtual key 411. The user can also end the speech recognition function by releasing the virtual key 411. In more detail, the user can activate the speech recognition function by touching the virtual key 411 and a continuous touch on the virtual key 411 or on the hardware key 412 until the speech command is completed. That is, the user can release the virtual key 411 or the hardware key 412 upon completion of the speech command. Thus, the controller 180 is aware of when to enter the voice command and when the voice command was completed. As stated above, since the user is directly involved in determining this, the accuracy of the interpretation of the entered speech command is improved.

The controller 180 may also be configured in such a way that it recognizes the start of the voice control function when the user first touches the virtual key 411, and then recognizes the fact that the voice command has been completed, for example, when the user touches the virtual key 411 a second time. Other choices are also possible. Furthermore, as shown on the display screen 410 of FIG. 6A, instead of using the virtual key 411, enabling and disabling voice control can be performed by manipulating the hardware key 412 on the terminal.

In addition, the virtual key 411 shown on the display screen 410 may be a single virtual key that the user presses or releases to enable / disable the speech recognition function, or may be a menu call button that, when selected, creates a menu list (e.g. : "1. Turn on voice control and 2. Turn off voice control"). A virtual key 411 may also be displayed, for example, during standby mode.

In another example, and as shown on the display screen 420, the user can also enable or disable the speech recognition function by touching an arbitrary location on the screen. The display screen 430 illustrates another example in which the user enables and disables the speech recognition function by creating specific sounds or sound effects whose volume level exceeds a specific level. For example, to create such a punch sound, the user can clap his hands.

Thus, according to one embodiment of the present invention, the speech recognition function can be implemented in two modes. For example, the speech recognition function can be implemented in the first mode for detecting specific sound or sound effects whose volume level exceeds a certain level, and in the second mode for recognizing a speech command and determining the meaning of a speech command. If in the first mode the volume level of sounds or sound effects exceeds a certain level, then the second mode is activated in order to recognize the speech command through it.

The display screen 440 illustrates yet another method for enabling and disabling a speech recognition function by a user. In this example, the controller 180 is configured to interpret the movements of the user's body to enable or disable the speech control function. For example, and as shown on the display screen 440, the controller 180 may be configured to interpret the movement of the user's hand toward the display as a command to activate the speech recognition function and the movement of the user's hand from the display as a command to complete the voice control function. To enable or disable the speech recognition function, short-range or long-range radio signals can also be used.

Thus, according to one embodiment of the present invention, since the voice control function is turned on and off, the speech recognition function is performed intermittently. That is, when the speech recognition function is continuously maintained in an activated state, the amount of resources consumed in the mobile communication terminal increases compared to an embodiment of the present invention.

In addition, as described above with reference to FIG. 5, when the speech recognition function is activated, the controller 180 sets the region of the specific database used as reference information for recognizing the speech command in the form of the region associated with the menu list on the display 151. Then, if a specific menu is selected or implemented from the menu list , then the database area can be defined as information associated with the selected menu or submenu of a particular menu.

In addition, when a particular menu is selected or implemented by means of a speech command or touch input, the controller 180 may output help information associated with a submenu of a particular menu in the form of a voice message or in the form of pop-up windows or prompts. For example, as shown in FIG. 6B, when the user selects the “multimedia information” menu by a touch operation or a speech command, the controller 180 displays on the display information associated with the submenu (which, for example, are the following menu items: “broadcast”, “camera”, “text viewer "," game ", etc.) of the" multimedia information "menu, as reference information 441 in the form of a tooltip. Alternatively, the controller 180 may output a speech signal 442 containing reference information. Then, the user can select one of the items of reference information using a speech command or through a touch operation.

FIG. 6B illustrates an embodiment of the invention in which the user selects a menu item using the movements of his or her body (which in this example is the user's hand gesture). In more detail, when a user moves his or her finger closer to menu item 443, the controller 180 displays submenus 444 associated with the menu 443. The controller 180 can recognize information about the movement of the user's body, for example, through the sensor 140. In addition The help information displayed on the screen can be displayed in such a way that it has transparency or brightness, adjustable in accordance with the distance to the user. That is, as the user's hand approaches, the elements displayed on the display screen can be additionally highlighted.

As described above, the controller 180 may be configured in such a way that determines whether the speech recognition function is turned on and off based on a variety of different methods. For example, the user can select / activate virtual or hardware keys, touch the touch screen in any place, etc. The controller 180 may also maintain activation of the speech recognition function for a predetermined period of time, and then automatically complete the activation at the end of the predetermined period of time. In addition, the controller 180 can maintain activation only for the duration of pressing a particular key or performing a touch operation, and then automatically completes the activation when releasing this data input means. The controller 180 may also complete the activation process when the speech command no longer arrives at the input within a certain amount of time.

In the following drawing, FIG. 7A is a flowchart of a voice command recognition method in a mobile communication terminal according to one embodiment of the present invention. With reference to FIG. 7A, when the speech recognition function is activated, the controller 180 sets the database area, which can be used as reference information for recognizing the speech command, in the form of the area associated with the menu displayed on the display 151, or to a submenu of this menu (operation S201) . The user also enters a speech command (operation S202) either using the exact menu name or using natural language (for example, spoken English).

Then, the controller 180 stores the input speech command in the storage device 160 (operation S203). Furthermore, when the speech command is inputted in such a way that it corresponds to a predetermined area, the controller 180 analyzes the context and contents of the speech command based on the predetermined area using a speech recognition algorithm. In addition, the speech command can be converted into text information for analysis (step S204), and then stored in a specific database in the storage device 160. However, the operation of converting the speech command into text information can be omitted.

Then, to analyze the context and contents of the speech command, the controller 180 detects a characteristic word or keyword of the speech command (operation S205). Based on the detected words or keywords, the controller 180 analyzes the context and content of the speech command and determines or ascertains the meaning of the speech command by accessing information stored in a specific database (operation S206).

In addition, as described above, the database used as reference information contains a predetermined area, and perform functions or implement menus that correspond to the meaning of the speech command found on the basis of the database (operation S207). In addition, since the speech recognition database is set for each information associated with a particular menu, the percentage of correctly recognized words and the recognition speed of the speech command are increased, and the amount of resources used in the terminal is reduced. In addition, the percentage of correctly recognized words indicates the degree of correspondence with the name predefined for a particular menu.

The percentage of correctly recognized words for the entered speech command can also be judged by the amount of information associated with specific functions or menus that are invoked through the speech command. Consequently, the percentage of correctly recognized words for the entered speech command increases when the information exactly corresponds to the specific function or menu (for example, the name of the menu) contained in the speech command.

In more detail, FIG. 7B is a perspective view illustrating a method for recognizing a voice command in a mobile communication terminal according to one embodiment of the present invention. As shown in FIG. 7B, the user enters in a natural language a speech command consisting of six words: " I want to see my pictures "(" I want to see my pictures "). In this example, the percentage of correctly recognized words can be judged based on the number of significant words (which are, for example, "see" ( "see"), "pictures" ( "Image")) associated with a particular menu (for example, menu " photo album "). In addition, the controller 180 may determine whether the words contained in the speech command are meaningful words associated with a particular function or a specific menu based on information stored in the database. For example, insignificant words contained in a natural language speech command that are not related to a particular menu may include the following: the subject " I "("I"), the preposition "to " and the possessive pronoun " my "("mine").

In addition, natural language is the language commonly used by people, and its concept is the opposite of the concept of artificial language. In addition, natural language data processing can be carried out using a natural language processing algorithm. Natural language may or may not contain the exact name associated with a particular menu, which sometimes makes it difficult to accurately recognize a speech command. Therefore, according to an embodiment of the present invention, when the percentage of correctly recognized words of the speech command exceeds a certain level (equal to, for example, 80%), then the controller 180 decides that the recognition is accurate.

In addition, when the controller 180 believes that the plurality of menus have the same meaning, the controller 180 displays a plurality of menus on the display screen, and the user can select one of the displayed menu menus to perform its functions. In addition, a menu that corresponds to a relatively higher percentage of correctly recognized words can be displayed first in order or can be displayed more distinctly than other menus.

For example, in FIG. 8, a general view illustrates a method for displaying a menu in accordance with the percentage of correctly recognized words in speech recognition in a mobile communication terminal according to one embodiment of the present invention. As shown in FIG. 8, a menu icon corresponding to a higher percentage of correctly recognized words is displayed in the center of the display screen 510, or it can be displayed with a larger size or darker color, as shown on the display screen 520. The menu icon, which corresponds to a higher percentage of correctly recognized words, can also be displayed first, and then follow, in order or sequentially, a menu with lower percentages of correctly recognized words.

In addition, the controller 180 can clearly display a plurality of menus by changing at least one of the following parameters: size, position, color, brightness of the menu, or by highlighting them with brightness in the order of a higher percentage of correctly recognized words. The transparency of the menu can also be appropriately changed or adjusted.

In addition, as shown in the lower part of Fig. 8, a menu having a higher frequency of its selection by the user can be adjusted or set so that it corresponds to the percentage of correctly recognized words. That is, the controller 180 remembers the history of the choices made by the user (operation S301) and performs the learning process (operation S302) so that it can correct a specific percentage of correctly recognized words for that menu item that the user selects more often than other menu items ( operation S303). Thus, data on the number of times that a frequently used menu was selected by the user can be applied to the percentage of correctly recognized words for the menu. Consequently, a speech command entered in the same or similar way in pronunciation or content can have a different percentage of correctly recognized words in accordance with how many times the user selects a particular menu.

In addition, the controller 180 may also memorize the point in time at which the user performs specific functions. For example, a user can check emails or missed messages each time he wakes up, on the days of the week from Monday to Friday. This time information can also be used to increase the percentage of correctly recognized words. Information about the operating mode of the terminal (for example, standby mode, etc.) can also be used to increase the percentage of correctly recognized words. For example, a user can check e-mail messages or missed messages when they first turn on their mobile terminal, when opening the terminal from a closed position, etc.

The following drawing, Fig. 9 in General view shows a method for recognizing a voice command in a mobile communication terminal according to another embodiment of the present invention. As shown in FIG. 9, the user activates the speech recognition function and enters the voice command “ I want to see my pictures ”. Then, the controller 180 determines the database area for recognizing the speech command in the form of the area associated with the submenus displayed on the display. Then, the controller 180 interprets the speech command (operation S401) and in this example displays a plurality of menus for which the probability exceeds a specific value (equal to, for example, 80%) (operation S402). As shown on the display screen 610 in FIG. 9, the controller displays four “multimedia information” menus.

The controller 180 also clearly displays the menu having the highest probability (which in this example is, for example, item 621 of the "photo album" menu). Then the user can select any of the displayed menus to perform the function corresponding to the selected menu. In the example shown in FIG. 9, the user selects “photo album” menu item 621, and the controller 180 displays images from the selected photo album on the display screen, as shown on the display screen 620.

Moreover, in operation S402 shown at the bottom of FIG. 9, the controller 180 can also immediately execute a function when it is determined that only one menu exceeds a predetermined probability indicator. That is, when it is determined that item 621 of the photo album menu is the only menu having a higher percentage of correctly recognized words or a higher probability than a predetermined threshold value, the controller 180 immediately displays images from the photo album on the display screen as shown on the display screen 620, without the need for the user to select item 621 of the "photo album" menu. In addition, even though the menu has an exact name, for example, “photo album”, the storage device 160 may store a lot of data related to the menu, such as, for example, “photo, image, album”.

In addition, as described above with reference to Fig.6B, the controller 180 can also display help information for the user when selecting or executing a specific menu through a speech command or touch data input in accordance with the state or mode of operation (for example, the mode of indicating the speech recognition function ) In addition, the user can set the operation mode for displaying reference information using the corresponding menu items provided in the "setting operation mode" menu. Accordingly, the user can work with the terminal of the present invention without the need for a high level of qualification or without it. That is, many older people may not have enough experience in managing the many different menus provided in the terminal. However, in the terminal of the present invention, a user who, as a rule, is not familiar with the complexities of the user interfaces provided in the terminal, can easily work with a mobile communication terminal.

In addition, when the controller 180 recognizes that the speech command has many meanings (that is, when the natural language speech command does not contain an exact menu name, for example, when the menu is contained in the "multimedia information" category but does not have an exact word name “camera”, “photo album” and “video”), the controller 180 displays a plurality of menus on the screen for which the percentage of correctly recognized words is greater than a certain value (equal, for example, 80%).

In the following drawing, FIG. 10 generally shows a plurality of databases used by the controller 180 to recognize a voice command in a mobile communication terminal according to one embodiment of the present invention. In this embodiment of the invention, these databases store information that the controller 180 uses to determine the meaning of the speech command, and they can be any number of databases in accordance with the characteristic features of the information. In addition, the respective databases configured in accordance with the characteristic features of the information can be updated through a continuous learning process under the control of the controller 180.

For example, in the learning process, an attempt is made to compare the user's speech with the corresponding word. For example, when the Korean word "Saeng-il" (meaning "birthday") spoken by the user is not correctly understood as the word "Saeng-hwal" (meaning "life"), the user corrects this word to "Saeng-il". Accordingly, the same pronunciation that will subsequently be entered by the user must be recognized as “Saeng-il”.

As shown in FIG. 10, respective databases according to characteristic features of the information comprise a first database 161, a second database 162, a third database 163, and a fourth database 164. In this embodiment, the first database 161 stores speech information for recognizing speech inputted through a microphone in units of phonemes or syllables, or morphemes. In the second database 162 data is stored information (for example, about grammar, pronunciation accuracy, sentence structure, etc.) to clarify the meaning of the speech command as a whole based on the recognized speech information. The third database 163 stores information related to the menu for the functions or services of the mobile communication terminal, and the fourth database 164 stores the message or voice information that must be output from the mobile terminal in order to obtain user confirmation of the clarified sense of speech teams.

In addition, the third database 163 can be defined as information associated with a particular menu category, in accordance with an area predefined for recognizing a speech command. In addition, sound information (pronunciation information) and phonemes, syllables, morphemes, words, keywords or sentences corresponding to pronunciation information can be stored in the appropriate database. Accordingly, the controller 180 can determine or ascertain the meaning of the speech command using at least one of the plurality of data bases 161-164, and execute menus associated with those functions or services that correspond to the clarified meaning of the speech command.

The following drawing of FIG. 11 shows in a general view a state in which a voice recognition function is performed in a mobile communication terminal according to one embodiment of the present invention. As shown in the drawing, when the controller 180 performs the speech recognition function, the controller 180 displays a special indicator or icon 500 on the display that informs the user that the speech recognition function is being performed. The controller 180 may also output a sound or message to notify the user that a speech recognition function is being performed.

In addition, the above-described embodiments of the invention relate to the recognition of a user's voice command. However, the present invention is also applicable to the case when the user performs an additional function of data input during recognition of a speech command. For example, the functions of speech recognition and touch data input, speech recognition and data input via keys, or speech recognition and touch data input / data input by keys can be performed simultaneously.

In addition, the controller 180 may not allow the speech recognition function to execute in a particular mode or menu, or in a particular mode of operation. In addition, audio information (eg, audio notification or instructional information) or video information (eg, indicator 500 in FIG. 11) indicating that a speech recognition function is currently being applied can be played back in a speech recognition mode, in a menu or in operating mode indicator. In addition, information that the speech recognition function is currently being applied can be provided to the user by displaying reference information.

12, a general view illustrates a method for processing subcommands associated with a particular menu in a mobile communication terminal by means of a voice command according to one embodiment of the present invention. In this embodiment of the invention, it is assumed that the speech recognition function is already activated by the user.

Then, as shown on the left side of FIG. 12, the user touches the alarm / calendar icon, and the controller 180 displays a pop-up help menu listing available functions (for example: 1) an alarm clock, 2) a schedule, 3) a list of scheduled tasks (To Do) and 4) memo). Then, the user enters the “list of scheduled tasks” speech command, and the controller 180 interprets the meaning of the speech command and displays a plurality of menus that are defined as corresponding to the speech command, as shown on the display screen 611.

That is, as shown on the display screen 611, the controller 180 displays on the display four events related to the Scheduled To Do List function. Then the user enters the voice command "select number 2", and the controller 180 selects option number 2 (Meeting 1). Then the user enters the speech command "I want to delete this." Then, the controller 180 displays a pop-up menu 613, in which the user is asked to confirm the deletion of the record by the answer “yes” or “no”. Then, the user enters the yes command, and the controller 180 then deletes the recording, as shown on the display screen 616 of FIG. 12.

In addition, if no response has been received from the user, then the controller 180 may automatically execute the subcommands, regarding the absence of a response as a positive response. The controller 180 also outputs a speech command 615, notifying the user that the data item has been deleted. In addition, instead of selecting the first menu "alarm / calendar" by touching the menu, the user could instead issue another voice command. In addition, when the user first selects the alarm / calendar icon, the controller 180 may issue a voice message 617 to notify the user that the corresponding task will be performed.

In addition, as described above, when a specific menu is executed, the controller 180 sets the database area used as reference information for recognizing a speech command in the form of an area associated with the menu being executed. That is, this area contains information associated with a submenu of a particular menu, or information associated with subcommands that can be executed from a specific menu.

In the following drawing, FIG. 13 shows, in general terms, a metro search method using a voice command in a mobile communication terminal according to an embodiment of the present invention. This example again assumes that the speech recognition function has already been activated by the user. In addition, it is also contemplated that controller 180 implements a specific menu related to displaying a subway circuit based on a user's voice command or manipulation using other input devices.

That is, the controller 180 displays a subway circuit on the display screen, as shown on the display screen 621. As described above, when a specific menu is executed, the controller 180 can set the area of the database used as reference information for recognizing the voice command in the form of the area associated with the menu (for example, names of metro stations, information about the distance (time) between each stations). In addition, this area contains information associated with a submenu of a particular menu, or information associated with subcommands that can be executed from a specific menu.

Then, the controller 180 issues a voice command 626 asking the user to enter information about the start station and the end station. Then, the user selects two stations on the display screen 621. That is, the controller 180 receives information about the two stations 622 and 623 from the subway circuitry displayed on the screen, for which the user wants to know the amount of time spent traveling between the two stations. The user can select two stations using a speech command when the terminal gives the appropriate prompt (that is, "say the name of the start and end stations), or by touching the designations of the two stations 622 and 623 on the screen. Other ways to select two stations are also possible. After the two stations have been selected by the user, the controller 180 outputs through the loudspeaker a voice message 624 containing the two selected stations (that is, the following stations were selected: ISU station and Seoul station). hundred and output a voice message, the controller 180 may instead be displayed on the display screen pop-ups requested or entered information.

In addition, when two stations are selected, the controller 180 can also output help information. For example, as shown on the display screen 621 of FIG. 13, the controller displays a pop-up help information window listing station names and the color of the subway line. The user then issues a request for information about the amount of time that the trip between the two selected stations will take. The user can request this information by entering the next voice command; " I want to know how long it will take from ISU to Seoul Station "(" I want to know how long it will take to travel from ISU to Seoul Station").

Then, the controller 180 detects significant words (for example, “ how long ”, “ take ”, “ ISU ”, “ Seoul Station ”) associated with processing information about the subway in a given area for analysis of the context and content of the speech team. Based on the analyzed information, the controller 180 determines that the meaning of the voice command is that a request has been issued to receive information about the travel time between two metro stations: ISU station and Seoul Station.

In addition, when the controller 180 determines the meaning of the speech commands, the controller 180 may first issue a request for confirmation by the user whether the intended meaning of the speech command is accurate. Then, the controller 180 displays two stations in the metro scheme along with data on the distance (or time) between the two stations, the number of stops between the two stations, etc. and outputs a voice message 627 informing the user of the result, which is shown on the display screen 625 in FIG. 13. In addition, as described above, if the user does not respond to the request for confirmation within a specific period of time, then the controller 180 can interpret this as a positive response and provide the results of the requested service.

In the following drawing, FIG. 14 is a perspective view illustrating a method for reproducing multimedia files by means of a voice command in a mobile communication terminal according to one embodiment of the present invention. In addition, the description below assumes that the activation control signal has already been entered by the user, and that the controller 180 starts activating the speech recognition function. It is also contemplated that the controller 180 has implemented a specific menu associated with the “multimedia information playback” menu by receiving an inputted voice command or user manipulation data using other input devices.

That is, as shown on the display screen 631, the controller 180 displays on the display a list of songs that the user can select to play. Thus, in the present invention, the search for the desired file for the user with multimedia content to play it can be carried out directly through a speech command. In a more detailed description, after the "multimedia information playback" menu is implemented, the controller 180 sets the area of the database used as reference information for recognizing the speech command in the form of an area associated with the implemented menus.

As described above, this area contains information related to the submenus contained in the “multimedia information playback” menu, information associated with subcommands that can be executed from the “multimedia information playback” menu, or information associated with the multimedia content file ( for example, file names, playing time, copyright holder information, etc.).

In addition, the controller 180, having received an inputted speech command or user manipulation data using other input devices, may display a list of multimedia files. In the example shown in FIG. 14, the user enters his speech command in natural language (for example, “ Let's play this song”) in the state when one file is selected from the file list, which is shown on the display screen 631.

After the speech command is entered, the controller 180 detects significant words (eg, “ play ”, “ this song ”) associated with a submenu or subcommands to process the selected menu within a given area. In addition, the controller 180 determines the meaning of the speech command by analyzing the detected words, the entire context and content of the speech command.

Once the meaning of the speech command has been clarified, the controller 180 receives user confirmation of whether the clarified meaning of the speech command is accurate. For example, as shown in FIG. 13, the controller 180 displays a pop-up window 633, asking the user to say “yes” or “no” regarding the playback of the selected song. The controller can also output a voice message 632, asking the user whether the song number 2 is the song to be played. The user can then say yes, and the controller 180 outputs the selected song, as shown on the display screen 634.

Alternatively, the controller 180 may automatically play the selected song without asking the user to confirm the selection. The user can also use the appropriate menu items to set the default when the controller 180 asks for confirmation of the selected task or does not request this confirmation. In addition, if no response was received from the user, then the controller 180 can automatically execute a speech command, the meaning of which was clarified, regarding such a reaction as a positive response.

Therefore, in this embodiment of the invention, the file to be reproduced is selected, and the playback command of the selected file is entered through the speech command. However, when the user already knows the file name, the file name can be directly entered from a higher level menu by means of a speech command.

In the following drawing, FIG. 15 is a perspective view illustrating a method for transmitting an e-mail or text message by means of a voice command in a mobile communication terminal according to one embodiment of the present invention. Again, in the description of this embodiment of the invention, it is assumed that the activation control signal has already been entered, that the controller 180 has started the activation of the speech recognition function, and that the controller 180, having received the entered speech command or user manipulation data using other input devices, has implemented a specific menu (for example, the menu "send / receive mail / messages").

In more detail, after the "send / receive mail (or message)" menu is implemented, the controller 180 sets the database area used as reference information for recognizing the speech command in the form of an area associated with the implemented menu. This area contains information related to the submenus contained in the "send / receive mail / messages" menu, information related to subcommands that can be executed from the "send / receive mail / messages" menu, information related to sent / received mail letters / messages (for example, about the transmitter, about the receiver, about the transmission / reception time, about the header, etc.).

The controller 180, having received an entered speech command or data about user manipulations using other input devices, also displays a list of transmitted / received mail (transmitted / received messages) on the display. As shown on the screen 641 of the display, the user enters the speech command " I want to reply "("I want to send a response"). The controller 180 then displays received messages that the user can respond to, as shown on the display screen 645. In this example, the user uses his natural language (for example, " Reply to this message ") in the state when one mail letter / message is selected from the list of mail correspondence / messages, which is shown on screen 645 of the display .

In addition, after the speech command is entered, the controller 180 detects significant words (eg, “ reply ”, “ this message ”) associated with processing the response for the selected mail message / message within the area. Then, the controller 180 ascertains the meaning of the speech command (implementation of the "reply to mail / message" menu) by analyzing the detected words and the entire context and content of the speech command.

After the meaning of the speech command has been clarified, the controller 180 may receive user confirmation of whether the clarified meaning of the speech command is accurate. For example, to receive confirmation from the user, a voice message 642 may be output, or a text message 643 may be output. When a message is displayed to receive confirmation from the user, the user can respond in voice form or through other input devices. In the absence of a response from the user, the controller 180 can automatically perform the functions corresponding to the clarified meaning, regarding this reaction as a positive response. Then, when the "reply to mail / message" menu is implemented, the controller 180 automatically enters the address / telephone number of the selected recipient in the mail message / message recording window 644.

Therefore, in this embodiment of the invention, the mail letter / message to be answered is first selected, and the reply command for the selected mail letter / message is entered using the voice command. However, when the user knows the recipient information, the response to the mail letter / message sent to the recipient can be directly entered by means of a speech command.

In addition, the embodiment of the invention shown in FIG. 15 may be modified to suit text messaging. In more detail, the controller 180 contains software for converting the user's speech into text, so the user can tell the terminal what he or she wants to say, and the controller 180 converts the inputted speech into a text message. The controller also 180 can display the converted text for the user on the display, so the user can confirm that the conversion is acceptable. The user can then request that the terminal send a text message to the desired subscriber.

This modified embodiment of the invention is particularly useful because manually entering a text message is a very laborious and tedious process. Many users want to send a text message instead of calling a person on the phone for several different reasons, but they do not want to go through the time-consuming process of selecting multiple buttons manually in order to send a single text message. A modified embodiment of the present invention enables the user to enter desired text information using his voice, and then send a text message to the desired subscriber.

On Fig in General terms shows a method of making a phone call through a voice command in a mobile communication terminal according to one embodiment of the present invention. Similar to the above-described embodiments of the invention, it is also assumed in this embodiment that the activation control signal has already been entered by the user, that the controller 180 has already activated the speech recognition function, and that the controller 180 has already implemented a specific menu (for example, a phone book or a menu with a list of the last received phone calls) associated with phone calls by receiving an entered voice command or data about user manipulations using other input devices.

After the menu related to telephone calls has been implemented, the controller 180 sets the area of the database used as reference information for recognizing a voice command in the form of an area associated with telephone calls. In addition, this area contains information related to outgoing phone calls, incoming phone calls, missed phone calls, etc., and information associated with each phone (for example, about the time of an outgoing call, about the time of an incoming call, about transmitter, about the receiver, about the duration of a phone call, about the frequency of phone calls, etc.).

In addition, the controller 180, having received an entered speech command or data about user manipulations using other input devices, displays a list of telephone calls. That is, the user uses his or her natural language to enter a voice command (for example, " I want to see the received phone calls "), as shown on the display screen 711.

After the speech command is entered, the controller 180 detects meaningful words (e.g., " see ", " received "("received")," phone "("telephone"),"calls"("calls" )) associated with phone calls in the area and finds out that the voice command has the following meaning: "display data on received phone calls" by analyzing the words found and the entire context and content of the speech command. After the meaning of the speech command has been clarified, the controller 180 displays a list of received phone calls shown on the display screen 712.

In addition, the user then enters a voice command, “ Call this person ”, in the state when the data item is selected from the displayed list. As a result of this, the controller 180 finds out that the speech command has the following meaning: "call the opposite party of the selected received call." Then, the controller 180 receives user confirmation of whether the clarified meaning of the speech command is accurate. That is, the controller 180 may output a voice message 713 or a text message 715.

The user can also respond with voice or other input devices. As mentioned above, if no response has been received from the user, then the controller 180 can automatically perform a function corresponding to the clarified meaning, regarding such a reaction as a positive response. The controller 180 also displays a message 714 indicating that a telephone connection is being established.

Thus, in this embodiment of the invention, a destination is selected from the list of telephone calls and a “call to selected destination” command is entered using a voice command. However, when the user already knows the information about the addressee, a phone call to this person can be directly made through a speech command.

The following drawing Fig.17 in General terms shows a method of using information from the phone book through a voice command in a mobile communication terminal according to one embodiment of the present invention. In the description of this method, the same assumptions are made that were described above in other embodiments of the invention. That is, it is assumed that after the activation control signal is input, the controller 180 starts the activation of the speech recognition function, and that the controller 180, having received an entered speech command or user manipulation data using other input devices, selects or implements a specific menu (for example, the telephone menu book ") shown on the display screen 720.

After the phonebook menu is implemented, the controller 180 sets the database area used as reference information for recognizing the voice command in the form of an area associated with submenus contained in the phonebook menu or with subcommands that can be executed from the "phone book" menu. In addition, this area is set in such a way as to increase the percentage of correctly recognized words, but this may not be a prerequisite.

In addition, the user enters a speech command in his natural language (for example, " Edit James "("edit James data"), " Add James "("add James data"), " Find James "("find James data ")," Call James "," I want to send a Message to James "in standby mode or when the menu associated with the phone book is selected After the speech command is entered, the controller 180 detects meaningful words (for example, “ Edit ”, “ Add ”, “ Find ”, “ Call ” it ")," Send Message "( " send a message ")," James "(" James ")) associated with telephone calls within the region, and finds out the meaning of each of the voice commands by analyzing the detected words and the entire context and content speech commands.

After the meaning of each of the speech commands has been clarified, the controller 180 performs functions or implements menus corresponding to the appropriate speech commands, which are shown on the display screens 722-724. In addition, before executing them, the controller 180 may receive user confirmation of whether the clarified meanings of the speech commands are accurate. As described above, a voice message or text message can be displayed to receive confirmation from the user.

In addition, when a message is displayed to receive confirmation from the user, the user can respond by voice or other input devices. If no response has been received from the user, then the controller 180 can automatically perform the functions corresponding to the clarified meanings, regarding such a reaction as a positive response.

In the following drawing, FIG. 18 is a perspective view illustrating a method for changing a displayed background image by a voice command in a mobile communication terminal according to one embodiment of the present invention. Again, in the description of this method, it is assumed that after the activation control signal has been input, the controller 180, having received the entered speech command or user manipulation data using other input devices, starts the activation of the speech recognition function and implements a specific menu (for example, menu "photo album").

The menu "photo album" can be implemented by entering a speech command or through a multi-stage submenu using other input devices. In addition, the menu "photo album" can be directly implemented by means of a speech command in natural language (which, for example, is the following command: " I want to see my photo album "), as shown in display screen 731. In accordance with the clarified meaning of the speech command, the controller 180 displays a list of photos by implementing the menu "photo album" shown on the screen 732 of the display. Then, the controller 180 receives one photograph selected from the displayed list of photographs contained in the photo album.

If a voice command is entered by the user in this state (for example, “Change my wall paper using this picture”), then the controller 180 detects meaningful information (for example, the words “ change ” (“change ")," wall paper "(" background image ")) associated with the submenu or subcommands of the implemented menu. Then, the controller 180 determines the meaning of the speech command by analyzing the detected words and the entire context and content of the speech command. That is, the controller 180 finds out that the meaning of the speech command is Xia is: "Replace the displayed background image of the selected photo."

After the meaning of the speech command has been clarified, the controller 180 displays a background image corresponding to the selected photo on the display screen and receives user confirmation of whether the clarified meaning of the speech command is accurate. In this case, to receive confirmation from the user, a voice message 733 can be displayed, or a text message 734 can be displayed. A speech command, the meaning of which is clarified, can also be executed directly without user confirmation in accordance with a high percentage of correctly recognized words or with a predefined menu "setting the operating mode".

When a message is displayed to receive confirmation from the user, the user can respond with voice or other input devices. If no response has been received from the user, then the controller 180 may automatically perform a function corresponding to the clarified meaning of the speech command, regarding such a response as a positive response.

To change the background image, the “photo album” menu does not have to be implemented first, as shown in this embodiment of the invention. Instead, a search for a desired user photo to change the background image can be performed after the background image menu is implemented.

On Fig in General terms shows a method of reproducing files with multimedia content through a speech command in a mobile communication terminal according to one of the embodiments of the present invention. Similar to the above-described embodiments of the invention, it is assumed in this description that, after the activation control signal is input, the controller 180, having received the inputted speech command or user manipulation data using other input devices, starts activating the speech recognition function and implements a specific menu (e.g. , menu "playback of multimedia information").

To play a file with multimedia contents, the user implements a special menu, selects one of the submenus of the special menu to display a list of files, and select one file from this list of files to play it. However, in the present invention, the search for a user-desired file with multimedia content for playback can be carried out directly using a speech command.

For example, if a specific speech command (for example, “ Move to the Beatles album ”) is entered after the speech recognition function has been activated, then the controller 180 determines the meaning of the speech command by analyzing the entire context and content of the speech commands, which is shown on the display screen 741. Based on the analyzed information, the controller 180 performs specific functions or implements specific menus or displays a list of files by moving to a specific file folder, as shown on the display screen 742.

When a speech command (for example, "Play this song" or "Play number 3") is entered after one file is selected from the list of files, then the controller 180 finds out the meaning speech command by analyzing the entire context and content of the speech command. In addition, functions or menus that correspond to the meaning of the speech command can be performed directly in accordance with a high percentage of correctly recognized words or with a predetermined menu "setting the operating mode".

Once the meaning of the speech command has been clarified, the controller 180 receives user confirmation of whether the clarified meaning of the speech command is accurate. Here, to receive confirmation from the user, a text message or voice message 743 can be displayed. When a message is displayed to receive confirmation from the user, the user can respond to it with voice or other input devices. If no response has been received from the user, then the controller 180 may automatically perform the function of the clarified speech command, regarding such a reaction as a positive response. Then, the controller 18 executes or plays the selected song, as shown on the display screen 744.

Thus, in this embodiment of the invention, the file to be played is selected, and a command to play the selected file by the voice command is entered. However, when the user knows the file name, this file name can be directly entered from a higher level menu by voice to play it.

Therefore, according to embodiments of the present invention, in a state where the speech recognition function is activated, the inputted speech command is converted into a special form, and the context and its contents are compared with the database defined in the area used as reference information. In addition, the resulting value corresponding to the clarified meaning of the speech command is output to a specific component of the mobile communication terminal.

The mobile communication terminal of the present invention can manage menus associated with its specific functions or services by ascertaining the meaning of the entered speech command based on context and content. In addition, the mobile communication terminal of the present invention can provide an increase in the percentage of correctly recognized words in speech recognition by defining an area for speech recognition in the form of an area associated with a particular menu or with specific services, in accordance with its operating state or mode of operation.

In addition, the mobile communication terminal of the present invention can simultaneously select or implement menus associated with specific functions or services by applying one or more of its user interfaces (UIs), even while the speech recognition function is activated, to detect user manipulation. In addition, the mobile communication terminal of the present invention can manage the menus associated with specific functions or services through a voice command, regardless of the user's qualifications, by providing reference information about entering a voice command in accordance with the operating state or mode of operation of the terminal.

In addition, the plurality of areas may comprise at least two areas from an email related area that correspond to email messages sent from the mobile communication terminal and received at the mobile communication terminal, a scheduled task area that corresponds to scheduled events assigned in the mobile communication terminal, the contact area corresponding to the contact information available in the mobile communication terminal, the phone book area corresponding to the telephone numbers, storing the area of cards corresponding to the card information provided by the mobile communication terminal, the area of photographs corresponding to the photos stored in the mobile communication terminal, the message area corresponding to messages sent from the mobile communication terminal and received in the mobile communication terminal, region multimedia information corresponding to multimedia functions performed in a mobile communication terminal, an area of external devices corresponding to external devices to which A mobile terminal may be connected, a telephone call history area corresponding to telephone calls transmitted from the mobile communication terminal and received at the mobile communication terminal, and a setting area corresponding to parameter setting functions performed in the mobile communication terminal.

In addition, a predetermined threshold value for the percentage of correctly recognized words can be set by the manufacturer of the mobile communication terminal or by the user of the mobile communication terminal.

In addition, the various embodiments described above can be implemented in a computer-readable storage medium using, for example, computer software, hardware, or some combination thereof. For a hardware implementation, the above-described embodiments of the invention can be implemented in one or more specialized integrated circuits (ASICs), processors for digital signal processing (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), programmable the user of gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, other electronic devices designed to perform the functions described here, or a juxtaposed combination of these devices.

For a software implementation option, embodiments of the invention described herein may be implemented by separate software modules, for example, procedures and functions, each of which performs one or more of the functions and operations described herein. Software codes may be implemented by an application program written in any suitable programming language, and may be stored in a storage device (e.g., storage device 160) and executed by a controller or processor (e.g., controller 180).

In addition, the mobile communication terminal 100 may be implemented in many different configurations. Examples of such configurations are, inter alia, the following: a folding type structure, a sliding type structure, a rectangular type structure, a rotary type structure, a hinge type structure, and combinations thereof.

For specialists in the art it is obvious that in the present invention can be made of various modifications and changes without going beyond the essence or scope of patent claims of the invention. Therefore, it is intended that the present invention cover the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents.

Claims (26)

1. A mobile communication terminal, comprising:
an input device configured in such a way that it is capable of receiving input data to activate a speech recognition function in a mobile communication terminal;
a storage device configured in such a way that it is capable of storing a plurality of areas related to menus and operating modes of the mobile communication terminal; and
a controller configured in such a way that it is capable of defining a specific area for recognizing voice commands from a plurality of areas stored in the memory when the speech recognition function is activated, to analyze the context and information content of the voice command in a specific area, when the voice command is entered, recognize the voice command based on the language model and the acoustic model of the specific area that is accessed, and determine at least one menu and one operating mode of the term mobile Nala, based on a specific area, the accessed and recognizes the user's speech,
however, the controller is also designed so that it is able to determine a specific area in the information related to the currently displayed menu, or information related to the submenu of a particular menu selected from these menus. 2. The mobile communications terminal of claim 1, wherein the particular menu or mode of operation is at least one of the following: a menu or a mode for working with multimedia information, a menu or contact mode, a menu or a messaging mode, a menu or a sound mode , menu or organizer mode, menu or screen mode, menu or utility mode, menu or camera mode, and menu or parameter setting mode. 3. The mobile communication terminal according to claim 1, in which the controller is also configured in such a way that determines the percentage of correctly recognized words so that a certain menu and operation mode exactly match the entered speech of the user. 4. The mobile communication terminal according to claim 3, also containing a display made in such a way that provides a visual display of information,
at the same time, the controller is also configured in such a way that it displays all the menus and operating modes of the mobile communication terminal based on the specific area that was accessed and the user's recognized speech, for which it was determined that the percentage of correctly recognized words in it exceeds in advance set threshold value. 5. The mobile communication terminal according to claim 1, in which the input device is also designed in such a way that it is able to receive a voice input command to select one of the displayed menus and operating modes, and the controller recognizes the entered voice command and displays information requesting that whether the recognized inputted speech command is accurate. 6. The mobile communication terminal according to claim 4, in which the controller is also configured in such a way that it displays all the mentioned menus and operating modes of the mobile communication terminal based on the specific area to which access is made and the user's recognized speech, where the percentage of correctly recognized words exceeds a predetermined threshold value, in order from a higher percentage of correctly recognized words to a lower percentage of correctly recognized words. 7. The mobile communication terminal according to claim 4, in which a predetermined threshold value is set by the manufacturer of the mobile communication terminal or the user of the mobile communication terminal. 8. The mobile communication terminal according to claim 4, in which the controller is also configured in such a way that it displays on the display that menu or the operating mode that corresponds to the highest percentage of correctly recognized words by adjusting at least one of the size , position, color, brightness and backlight of this menu or operating mode. 9. The mobile communication terminal according to claim 3, in which the controller is also configured in such a way that determines how many times a particular menu or a particular operating mode has been selected in the terminal, and adjusts the percentage of correctly recognized words for a particular menu or operating mode based on of this certain number of times that a particular menu or a particular operating mode was previously selected. 10. The mobile communication terminal according to claim 1, in which the input device contains at least one of the following means: 1) a touch virtual key that is touched to activate the speech recognition function, 2) a hardware key that is pressed or with which perform manipulations to activate the speech recognition function, 3) an arbitrary place on the touch screen contained in the input device that is touched to activate the speech recognition function, 4) the beat sound that is entered to activate the speech recognition function, 5) p diosignal short-range or long-range radio signal, and 6) a signal from a user with information about his gestures. 11. The mobile communication terminal according to claim 1, also containing:
the first database, configured in such a way that it stores voice information or pronunciation information used by the controller to recognize the entered speech of the user;
the second database, configured in such a way that it stores information about words, keywords or sentences used by the controller to recognize the entered speech of the user;
a third database, configured in such a way that it stores information related to the functions or menu of the mobile communication terminal; and
the fourth database, configured in such a way that it stores reference information that must be output to inform the user that the controller is trying to determine the meaning of the entered speech of the user. 12. The mobile communications terminal of claim 1, wherein the controller is also configured to output audio or video information indicating that the speech recognition function is in an activated state. 13. The mobile communications terminal of claim 1, wherein the plurality of regions comprises at least two regions from an email related area that corresponds to email messages sent from the mobile communication terminal and received at the mobile communication terminal, scheduled areas tasks corresponding to the scheduled events assigned in the mobile communication terminal, the contact area corresponding to the contact information available in the mobile communication terminal, the phone book area corresponding to the telephone numbers stored in the mobile communication terminal, the card area corresponding to the card information provided by the mobile communication terminal, the photo area corresponding to the photos stored in the mobile communication terminal, the message area corresponding to messages sent from the mobile communication terminal and received in the mobile terminal communication, the field of multimedia information corresponding to multimedia functions performed in the mobile communication terminal, the field of external devices corresponding to the external devices which can be connected to the mobile communication terminal, the history field of telephone calls the respective telephone calls transmitted from the mobile communication terminal and received in the mobile communication terminal and the area setting parameters corresponding to the parameter setting functions performed on the mobile terminal. 14. A method for controlling a mobile communication terminal, comprising the steps of:
activate the speech recognition function in the mobile communication terminal in accordance with the entered data;
determining a specific area for recognizing voice commands from a plurality of areas stored in the storage device when the speech recognition function is activated;
accessing a specific area when a voice command is entered;
recognize the entered speech command based on the language model and
an acoustic model of a specific area that is accessed by analyzing the context and information content of the speech command in a given specific area; and
at least one menu and an operating mode of the mobile communication terminal are derived based on the specific area to which the access is made and the recognized speech of the user,
however, a specific area includes information related to the currently displayed menu, or information related to a submenu of a particular menu selected from these menus. 15. The method according to 14, in which a particular menu or mode of operation is at least one of the following: a menu or a mode for working with multimedia information, a menu or a mode of contacts, a menu or a mode of messaging, a menu or a mode of sounds, a menu or organizer mode, menu or screen mode, menu or utility mode, menu or camera mode, and menu or parameter setting mode. 16. The method according to 14, also containing stages in which:
displaying help information related to a submenu of a particular menu in the form of at least one of: a voice message displayed on a window screen and a tooltip when a particular menu is selected by means of a speech command;
determining at least one menu and one operating mode of the mobile communication terminal based on the specific area to which access is made and the recognized speech of the user; and
determine the percentage of correctly recognized words so that this particular menu and this particular mode of operation exactly match the input speech. 17. The method according to clause 16, also containing a stage on which:
display on the display screen of the mobile communication terminal all the menus and operating modes of the mobile communication terminal based on the specific area to which access is made and the recognized speech of the user, for which it was determined that the percentage of correctly recognized words in it exceeds a predetermined threshold value. 18. The method according to 17, also containing stages in which:
accept a voice input command to select one of the displayed menus and operating modes;
recognize the entered speech command; and
outputting information requesting whether the recognized inputted voice command is accurate. 19. The method according to 17, also containing a stage in which:
all the mentioned menus and operating modes of the mobile communication terminal are displayed on the basis of the particular area to which the access is made and the user's recognized speech, where the percentage of correctly recognized words exceeds a predetermined threshold value, in order from a higher percentage of correctly recognized words to more low percentage of correctly recognized words. 20. The method of claim 17, wherein the predetermined threshold value is set by the manufacturer of the mobile communication terminal or by the user of the mobile communication terminal. 21. The method according to 17, also containing a stage in which: the menu or the operating mode that corresponds to the highest percentage of correctly recognized words is displayed differently by adjusting at least one of the size, position, color , brightness and backlight of this menu or operating mode. 22. The method according to clause 16, also containing stages in which:
determine how many times a particular menu or a particular operating mode in the terminal was previously selected, and correct the percentage of correctly recognized words for a particular menu or operating mode based on that specific number of times that a particular menu or a specific operating mode was previously selected. 23. The method of claim 14, wherein the receiving step comprises applying at least one of the following means: 1) a touch virtual key that is touched to activate the speech recognition function, 2) a hardware key that is pressed or made manipulations to activate the speech recognition function, 3) an arbitrary place on the touch screen contained in the input device that is touched to activate the speech recognition function, 4) the shock sound that is entered to activate the speech recognition function, 5) radio signal ala short-range or long-range radio signal, and 6) signal from the user with information about his gestures. 24. The method of claim 14, further comprising the steps of:
storing speech information or pronunciation information in the first database used to recognize the inputted speech of the user;
store in the second database information about words, keywords or sentences used to recognize the entered speech of the user;
storing in a third database information related to the functions or menu of the mobile communication terminal; and save in the fourth database reference information that is to be output to inform the user that at the current time determine the meaning of the entered speech of the user. 25. The method of claim 14, further comprising: outputting audio or video information indicating that the speech recognition function is in an activated state. 26. The method of claim 14, wherein the plurality of areas comprises at least two areas from an email related area that corresponds to email messages sent from the mobile communication terminal and received at the mobile communication terminal, the scheduled task area, which corresponds to the scheduled events assigned in the mobile communication terminal, the contact area corresponding to the contact information available in the mobile communication terminal, the phone book area corresponding to the telephone numbers stored in the mobile communication terminal, a map area corresponding to card information provided by the mobile communication terminal, a photo area corresponding to photographs stored in the mobile communication terminal, a message area corresponding to messages sent from the mobile communication terminal and received at the mobile communication terminal, an area of multimedia information corresponding to multimedia functions performed in a mobile communication terminal, an area of external devices corresponding to external devices, to which may be connected to a mobile communication terminal, a telephone call history area corresponding to telephone calls transmitted from the mobile communication terminal and received at the mobile communication terminal, and a setting area corresponding to parameter setting functions performed in the mobile communication terminal.

Images