KR20190053633A - Stationary Sound Device for Circumstantial Judgement - Google Patents

Abstract

According to the present invention, a mountable sound device for situation determination comprises: a sound module including a sound input unit to receive a sound signal and a sound output unit to output a sound signal; and a communication module including at least one communication unit connected to a communication network. The mountable sound device for situation determination further comprises: a sound processing unit to buffer sound data corresponding to a sound signal of an audible frequency band inputted via the sound input unit in a designated buffer area or check sound data buffered in the designated buffer area; a feature sound recognition unit to read the buffered sound data to recognize a specific feature sound corresponding to at least one designated feature sound frequency band and corresponding to at least one feature sound pattern to recognize at least one designated feature sound for specific situation determination in a nonlinguistic sound or noise which can be created in a designated space; and a service control unit to activate at least s (1<=s<=S) service functions related to the feature sound among designated S (S>=1) services if the feature sound is recognized.

Description

Stationary Sound Device for Circumstantial Judgment &quot;

The present invention relates to a stationary sound device having a sound module for inputting and outputting a sound signal and a communication module for connecting to a communication network and for reading out sound data corresponding to a sound signal of an audible frequency band inputted through the sound module, Corresponding to at least one feature sound frequency band designated for recognizing at least one feature sound specified for a specific situation of non-verbal sounds or noises and / or corresponding to at least one feature sound pattern designated for recognizing the feature sounds (Or a combination of the two) of the sound module and the communication module when the sound module recognizes and attempts to recognize a specific sound of the specified service, or activates at least one designated service function related to the sound of the service To provide To provide a toothed sound device.

Recently, a stationary sound device has been sold which recognizes a user's voice and provides a service corresponding to the recognized voice. For example, stationary sound devices such as 'echo' from Amazon, 'who' from SK Telecom, and 'Kigajini' from KT are sold.

However, the conventional stationary sound device is a combination of a sound source service and a speech recognition technology. The conventional stationary sound device operates mainly on a service for providing or reproducing a desired sound source through voice recognition, and has a difficulty in being used in other fields.

In order to solve the above problems, an object of the present invention is to provide a communication module including a sound module including a sound input unit for receiving a sound signal and a sound output unit for outputting a sound signal, and at least one communication unit for connecting to a communication network And at least one non-verbal sound generated in the designated space and at least one characteristic sound designated for judging a specific situation among the noises, which is generated in the designated space, by reading the sound data corresponding to the sound signal of the audible frequency band inputted through the sound input unit (S &gt; = 1) service functions when it is recognized and attempted to recognize a specific feature sound corresponding to one feature sound frequency band and / or at least one feature sound pattern designated for recognizing the feature sound At least s (1? S? S) And a control module for activating the service functions of the stationary sound device.

The stationary sound device for the situation determination according to the present invention may include a communication module including a sound module including a sound input unit for receiving a sound signal and a sound output unit for outputting a sound signal and at least one communication unit for connecting to a communication network A sound processing unit for buffering sound data corresponding to a sound signal of an audible frequency band input through the sound input unit into a designated buffer area or confirming sound data buffered in a designated buffer area; Data corresponding to at least one feature sound frequency band designated for recognizing at least one feature sound specified for determining a specific situation among non-verbal sounds or noises that can be generated in a designated space and corresponding to at least one feature sound pattern (S &amp;le; s &amp;le; S) service functions related to the feature sound among the S (S? 1) service functions designated when the feature sound is recognized, And a control module including a service control unit.

According to the present invention, the characteristic sound may include at least one non-verbal sound selected from a baby cry for determining a crying condition of a baby, and a scream sound for determining an emergency situation.

According to the present invention, the characteristic sound may be a sound of unlocking a door lock of a door of a door designated to determine the home situation of the landlord or a family member, a door opening sound of the entrance door designated for the home owner or a family member, May include at least one noise of the beacon sound designated for it.

According to the present invention, the service control unit checks whether a feature sound is not recognized for a predetermined period of time or longer or a user's utterance is not recognized for a predetermined period of time or longer, and if a feature sound or a user's utterance is not recognized over a predetermined period of time And a function of setting the operation mode of the sound device to a sleep mode.

According to the present invention, the feature sound recognizing unit recognizes a feature sound in a sleep mode, and the service control unit wakes up when it recognizes the feature sound to provide s service functions May be included.

According to the present invention, the sleep mode may include a state in which the buffered sound data is read and the function of providing the service based on the recognized speech content is recognized by recognizing the user's speech content.

According to the present invention, the characteristic sound recognition unit may include a function of recognizing a characteristic sound corresponding to the characteristic sound frequency band of the specific sound source and corresponding to the characteristic sound pattern of the specific sound source.

According to the present invention, the control module may include M feature sound frequency band information corresponding to M (M? 1) feature sound frequency bands and N feature sound pattern information corresponding to N (N? 1) feature sound patterns To the designated storage area.

According to the present invention, the feature sound recognizing unit may read the buffered sound data to generate at least one feature sound pattern corresponding to at least one feature sound frequency band among the M feature sound frequency bands, And a function of recognizing a corresponding feature sound.

According to the present invention, the control module generates characteristic sound frequency distribution information corresponding to at least i (i? 2) valid recognized characteristic sound frequency distributions for a predetermined period using the M characteristic sound frequency band information (1? M? M) number of feature sounds that are optimized (or fitted) to a feature sound of a specific sound source in a space in which the sound device is mounted, by statistically processing the generated feature sound frequency distribution information. And an information determination unit for determining m feature frequency band information corresponding to the frequency band.

According to the present invention, the information storage unit may further comprise a function of newly setting or updating and storing the determined m characteristic sound frequency bands to a characteristic sound frequency band to be read first, and the characteristic sound recognizing unit recognizes the buffered sound data And recognizing the characteristic sound corresponding to at least one of the characteristic sound frequency bands among the stored m characteristic sound frequency bands.

According to the present invention, the control module generates a distribution pattern for generating characteristic sound pattern distribution information corresponding to at least j (j? 2) valid recognized characteristic sound pattern distributions for a predetermined period using the N characteristic sound pattern information (1 &amp;le; n &amp;le; N) feature sound patterns that are optimized (or fitted) to a feature sound of a specific sound source in a space in which the sound device is mounted by statistically processing the generated feature sound pattern distribution information. And the n-th feature pattern information.

According to the present invention, the information storage unit may further include a function of newly setting or updating and storing the determined n feature sound patterns as a feature sound pattern to be read first, and the feature sound recognition unit reads the buffered sound data And recognizing a feature sound corresponding to at least one feature sound pattern among the stored n feature sound patterns.

According to the present invention, the control module includes a speech content recognition unit for reading the buffered sound data and recognizing the user's speech uttered by the user and processing natural language words to recognize speech content information corresponding to the user's speech content; A recognition judging unit for recognizing whether the user's utterance is recognized or the utterance of the user is recognized within a predetermined time after the recognition of the characteristic sound is recognized; When the contents of speech are recognized, the intelligent processing unit may process the speech contents of the recognized user in association with s service functions related to the feature sounds.

According to the present invention, the service control unit may include a function of activating a specific service function corresponding to the feature sound and at the same time corresponding to the uttered contents of the recognized user.

According to the present invention, the s services include a server interlocking service provided in cooperation with an operating server on a communication network through the communication module, a sound based service provided through the sound module, And at least one of the multiple services provided by the service provider.

According to the present invention, the server interworking service may include a calling service using wireless terminal information, a status notification service using wireless terminal information, a calling service using an application installed in the wireless terminal, a status notification service using an application installed in the wireless terminal, A video service providing video information photographed through a camera of the mobile terminal to an application installed in a wireless terminal, and a video service providing video information photographed through at least one camera to a designated IPTV device.

According to the present invention, the sound-based service may include a noise output service for outputting a designated service sound through a sound output unit of the sound module at a designated signal output intensity.

According to the present invention, the signal output intensity may include a signal intensity that is inversely proportional to a signal input intensity of the characteristic sound.

According to the present invention, the composite service recognizes the user's utterance contents within a predetermined time period during or after the characteristic sound is recognized, and based on the result of analyzing the utterance contents of the user in association with the service function related to the characteristic sound And services provided through an operating server on the network.

According to the present invention, the stationary sound device for the situation determination may further include a near-field camera device and a near-field module for processing short-range wireless communication, wherein the service controller communicates with the camera device via the near- And a function of activating a video service function for photographing a sound source that generates the recognized characteristic sound through the apparatus.

According to the present invention, the communication module includes a short-distance network communication unit for connecting a camera apparatus in a short distance and a short-range wireless network-based wireless communication, and the service control unit communicates with the camera apparatus via the short- And a function of activating a video service function for photographing a sound source that has generated the recognized characteristic sound.

According to the present invention, the stationary sound device for the situation determination may further include a camera module for acquiring image information of a photographed subject, and the service control unit may include a sound source generating the recognized characteristic sound through the camera module, And a function of activating a video service function for photographing the image.

According to the present invention, the control module may further include a service providing unit for providing a service corresponding to the activated service function.

According to the present invention, when at least one feature sound specified for a specific situation determination among non-verbal sounds or noises that can be generated in a designated space is not recognized, the apparatus operates in a sleep mode that does not respond to the specific situation, Recognizes a specific feature sound corresponding to at least one feature sound frequency band designated for specifying the feature sound pattern and / or at least one feature sound pattern designated for recognizing the feature sound, and automatically wakes up in the sleep mode There is an advantage to provide a stationary sound device that activates at least a service function related to the feature sound or provides a service related to the feature sound.

1 is a functional block diagram of a stationary sound apparatus according to an embodiment of the present invention.
2 is a functional block diagram of a stationary sound apparatus and an operation server according to another embodiment of the present invention.
FIG. 3 illustrates an embodiment of recognizing a feature sound and activating a service related to the feature sound according to an embodiment of the present invention.
FIG. 4 illustrates an embodiment for optimizing (or fitting) a characteristic sound frequency band for recognizing a characteristic sound to a characteristic sound of a specific sound source according to an embodiment of the present invention.
FIG. 5 illustrates an embodiment of optimizing (or fitting) a feature sound pattern for recognizing a feature sound to a feature sound of a specific sound source according to another embodiment of the present invention.
FIG. 6 illustrates an embodiment of activating a service related to a feature sound by associating feature sounds with speech contents according to another embodiment of the present invention.

The operation principle of the preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings and description. It should be understood, however, that the drawings and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the invention, and are not to be construed as limiting the present invention.

In other words, the following embodiments correspond to the preferred embodiment of the preferred embodiment of the present invention. In the following embodiments, a specific configuration (or step) is omitted, or a specific configuration (or step) (Or steps), or an embodiment that incorporates functions implemented in more than one configuration (or step) into any one configuration (or step), a particular configuration (or step) It will be apparent that the present invention is not limited to the embodiments described below. Therefore, it should be clearly stated that various embodiments corresponding to subsets or combinations based on the following embodiments can be subdivided based on the filing date of the present invention.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The terms used below are defined in consideration of the functions of the present invention, which may vary depending on the user, intention or custom of the operator. Therefore, the definition should be based on the contents throughout the present invention.

As a result, the technical idea of the present invention is determined by the claims, and the following embodiments are merely means for effectively explaining the technical idea of the present invention to a person having ordinary skill in the art to which the present invention belongs Only.

1 is a functional block diagram of a stationary sound apparatus 100 according to an embodiment of the present invention.

1 is a block diagram of a communication system including a sound module 105 including a sound input unit 105a for receiving a sound signal and a sound output unit 105b for outputting a sound signal and at least one communication unit for connecting to a communication network. A sound processing unit having a module 120 and buffering sound data corresponding to a sound signal of an audible frequency band inputted through the sound input unit 105a into a designated buffer area or confirming buffered sound data in a designated buffer area 140) and at least one characteristic sound frequency band designated for recognizing at least one characteristic sound specified for determining a specific situation among non-verbal sounds or noises that can be generated in the designated space by reading the buffered sound data and / Characterized in that the at least one feature loudspeaker (S &lt; s &gt; S) associated with the feature sound among the S (S &gt; = 1) service functions specified when recognizing the feature sound, And a service control unit 150 for activating the service functions of the stationary sound apparatus 100. It should be noted that those skilled in the art will understand that the present invention is not limited to the above- , It will be appreciated that various implementations (e.g., some of the components may be omitted, or broken down or combined) for the stationary sound device 100 may be inferred by referring to and / or modifying Figure 1, The present invention is not limited to the above-described embodiments.

1, the stationary sound apparatus 100 includes a sound module 105 including a sound input unit 105a for receiving a sound signal and a sound output unit 105b for outputting a sound signal, And a communication module (120) including at least one communication unit for connecting to a communication network. The communication module (120) includes a sound input unit (105a) for reading sound data corresponding to a sound signal of an audible frequency band, Corresponding to at least one feature sound frequency band designated for recognizing at least one feature sound specified for a specific situation of non-verbal sounds or noises and / or corresponding to at least one feature sound pattern designated for recognizing the feature sounds And when it is recognized and attempted to recognize a specific feature sound of at least one And a control module 130 having at least one function unit for activating the service function or providing the designated service function. The power module 115 supplies operating power. The stationary sound apparatus 100 may include at least one of a near field camera device 185 and a near field module 125 for processing short range wireless communication and a camera module 110 for acquiring image information of a subject And may further include an input unit (not shown) including a keypad or a touchpad for receiving a user's operation, and / or an LED or a display for outputting various operation states or information And an output unit (not shown). On the other hand, in the embodiment of FIG. 1, the name " module &quot; is merely a term for distinguishing and describing the functions and roles of the stationary sound apparatus 100 for convenience, I will reveal.

The sound module 105 includes a sound input / output unit 105a including at least one sound input unit 105a that receives a sound signal from among the components of the stationary sound apparatus 100 and a sound output unit 105b that outputs a sound signal. The sound input unit 105a and the sound output unit 105b can input or output sound signals of at least an audible frequency band and the sound input unit 105a and the sound output unit 105b can be connected to the control module 130 And an interface unit (not shown) for interfacing with the interface unit.

The sound input unit 105a is a collective term for receiving a sound signal. The sound input unit 105a encodes one or more microphones that receive a sound signal obtained by detecting the vibration of air and convert the sound into an electrical signal, and a sound signal according to a specified encoding rule And a program (and / or circuit) module for generating sound data. Preferably, the sound input unit 105a receives a sound signal of an audio frequency band (for example, a sound signal including a speech signal generated by the user) through the microphone, receives the input audio frequency band And provide the sound data generated by encoding the sound signal to the control module 130.

According to the embodiment of the present invention, the sound input unit 105a includes one or more directional microphones for detecting a direction in which the feature sounds are generated when the feature sounds are recognized in the space where the sound apparatus 100 is mounted And the present invention is not limited thereto.

According to the method of the present invention, the characteristic sound may include at least one non-verbal sound selected from a baby cry for determining a crying condition of a baby, and a scream sound for determining an emergency situation.

According to the method of the present invention, the characteristic sound may be a sound of unlocking a door lock of a door of a door designated for judgment of the home situation of a homeowner or a family, a door opening sound of a doorway designated for judgment of a home owner or a family home, And may include at least one noise of the doorbell sound designated for the situation determination.

The sound output unit 105b is a collective term for outputting a sound signal and includes at least one speaker for outputting a sound signal and sound data to be outputted through the speaker and decoding the sound signal output through the speaker And a program (and / or circuit) module for controlling the signal output intensity and the output quality of the sound signal. Preferably, the sound output unit 105b outputs the sound signal generated by decoding the sound data requested to output sound through the control module 130 through the speaker, Amplifies or reduces the output intensity to a specified signal intensity (e.g., to a signal intensity that is set to be receivable (or audible) at a signal strength greater than or equal to a specified signal reception intensity at a distance greater than or equal to a specified reference distance, and / Amplified or reduced to a signal strength set to be capable of being received (or listened to) at a signal strength greater than or equal to the specified signal strength at a specified distance, and / or received at a signal strength greater than or equal to the specified signal strength at a specified distance, (Or listening) to a set signal strength (For example, speaker parameters such as Fs, Qts, Vas, etc.) of the sound output and / or blocking or suppressing the sound distortion as much as possible, The output quality of the sound is controlled so as to block / suppress the sound distortion caused by the resonance so that the sound component corresponding to the segmented sound on the sound signal is clearly defined so that the audibility (or audibility) The output quality of the sound is controlled so as to block or suppress the frequency at which the bit stream is encoded or the signal intensity when the bit stream is encoded and output, .

The communication module 120 is a collective term for a connection unit of the stationary sound apparatus 100. The communication module 120 preferably connects to a designated server (or device) via a wireless network (e.g., a mobile communication network, a portable Internet, (Or a wireless LAN) via a wireless AP or a repeater, and communicates with a designated server (or device) through a communication channel and communicates with the server And a local area network communication unit 120b, and an interface unit (not shown) for interfacing the communication unit with the control module 130. [

The wireless network communication unit 120a collectively refers to a communication unit that connects the stationary sound apparatus 100 to a wide area wireless network (e.g., a mobile communication network) via a base station. The wireless network communication unit 120a includes an antenna , An RF module, a baseband module, and a signal processing module. The controller 130a is connected to the controller 130a and transmits results of computation corresponding to wireless communication among the various computation results of the controller 130a through a wireless network Or receives data through a wireless network and transmits the data to the controller 130a, and also performs connection, registration, communication, and handoff procedures of the wireless communication.

According to an embodiment of the present invention, when the wireless network connected through the wireless network communication unit 120a is a mobile communication network, the wireless network communication unit 120a accesses a mobile communication network according to at least one mobile communication standard, , Call processing, call connection, data communication, and handoff. Meanwhile, according to the intention of those skilled in the art, the wireless network communication unit 120a may perform at least one of connection to a wide area wireless network other than the mobile communication network (e.g., portable Internet according to the IEEE 802.16 standard), location registration, data communication, And it is clear that the present invention is not limited by the wireless communication configuration provided by the wireless network communication unit 120a. That is, the wireless network communication unit 120a provides wireless data communication based on packet communication via the cell-based base station on the wireless network, regardless of the frequency band of the wireless section, the type or protocol of the communication network, To the data network to which the data is transmitted.

The short-range network communication unit 120b communicates with a network access device (for example, a wireless AP or the like) provided near by using a radio frequency signal as a communication medium within a predetermined distance (for example, within 10m or within 30m) And a communication network connecting the stationary sound apparatus 100 to the communication network to which the stationary sound apparatus 100 is connected through a short-range wireless network for connecting the station, the communication apparatus 100 preferably includes a Wi-Fi based short- A remote wireless communication session between the network connection device provided at a short distance through at least one of a network communication, a UWB-based local area network communication, and a public wireless communication is established between the stationary sound device 100 and the stationary sound device 100 100) to a communication network to which the network connection apparatus is connected.

According to the embodiment of the present invention, when the short-range wireless communication unit 120b is implemented with a short-range wireless communication session connecting a short-range wireless communication session with a network access device located within a predetermined distance from the stationary sound apparatus 100, And connects the stationary sound device 100 to a data network for providing wireless data communication based on packet communication via a network connection device of the short-range wireless network. Hereinafter, the network communication function of the stationary sound apparatus 100 will be described with reference to an embodiment using the wireless network communication unit 120a. However, the present invention is not limited thereto, and the network communication using the near field network communication unit 120b Function is also provided.

Meanwhile, according to one embodiment of the present invention, the short-range network communication unit 120b transmits a short-range wireless network-based wireless signal to the camera device 185 located near the sound device 100 via the short- Communication can be processed. The stationary sound apparatus 100 and the camera apparatus 185 may perform wireless communication based on a short-range wireless network when the near-field communication unit 120b processes wireless communication based on a short-range wireless network with a nearby camera apparatus 185 The key value for the encrypted communication can be exchanged or the key value for the encrypted communication can be exchanged at the time of connecting the wireless communication based on the short-range wireless network. As a result, the stationary sound device 100 and the camera device 185 can exchange key values, Can perform encrypted communication using the key value.

The near field module 125 is a collective term for the short range wireless communication of the stationary sound apparatus 100. The near field module 125 preferably includes a short range wireless unit 125a for connecting short range wireless communication of a specified standard, And an interface unit (not shown) that interfaces the control module 125a and the control module 130. For example, the short range wireless unit 125a may process Bluetooth based short range wireless communication according to the Bluetooth standard. However, it is clear that the standard for the short-range wireless communication of the short-range wireless unit 125a is not limited to the Bluetooth standard but may include all the short-range wireless communication standards including Wi-Fi, ZigBee or UWB. Meanwhile, the near-field wireless unit 125a may be the near-field communication unit 120b according to an embodiment of the present invention.

The short-range wireless unit 125a is a collective term for a unit for processing short-range wireless communication of a specified standard, and may preferably include a Bluetooth unit for processing Bluetooth-based short-range wireless communication according to the Bluetooth standard. However, the short range wireless communication related configuration of the short range wireless unit 125a is not limited to the Bluetooth based short range wireless communication according to the Bluetooth standard, and it is possible to use short range wireless communication of various standards other than Bluetooth according to the intention of those skilled in the art , Wi-Fi-based short-range wireless communication according to Wi-Fi standard, ZigBee-based short-range wireless communication according to ZigBee standard, and UWB-based short-range wireless communication according to UWB standard. Available). For the sake of convenience, the short range wireless unit 125a processes the Bluetooth based short range wireless communication according to an embodiment of the present invention. However, the present invention is not limited thereto.

According to the embodiment of the present invention, the near-field module 125 (or the short-range wireless unit 125a) processes the short-range wireless communication of the designated standard with the camera apparatus 185 provided in the vicinity of the sound apparatus 100 . The stationary sound device 100 and the camera device 185 may perform short-range wireless communication when the near-field module 125 (or the short-range wireless section 125a) processes near-field wireless communication with the near- The stationary sound device 100 and the camera device 185 can exchange the key value for the encrypted communication at the time of storing the key value for the encrypted communication or connecting the short distance wireless communication, Can be performed.

According to the embodiment of the present invention, when the stationary sound apparatus 100 is mapped to an application of a wireless terminal used by a user (for example, when an application specified in a user wireless terminal is installed and executed for the first time (or before mapping registration) The application of the wireless terminal registers the device identification information for identifying the stationary sound device 100 and the identification information of the user wireless terminal (or the unique identification information of the user wireless terminal) in the designated operation server 200, The short range wireless unit 125a may connect the short range wireless communication with the application of the matched user wireless terminal and may transmit various identification information designated for processing a specific service Processing information can be exchanged. For example, information received in an application of a user wireless terminal in a designated operation server 200 or inputted or extracted or generated through an application of the user wireless terminal may be transmitted to the user via the short- (E.g., sent to the sound output or operational server 200) and / or received at the designated operational server 200 to the stationary sound device 100 or to the control sound module 100 100 may be transmitted to the application of the user wireless terminal through the short-range wireless communication and processed (for example, output to the screen or transmitted to the operation server 200).

The camera module 110 is a collective term of a component for processing a camera photographing of the stationary sound apparatus 100 and is preferably a camera module for acquiring image information (e.g., image) or image information And an interface unit (not shown) for interfacing the control unit 130 with the camera unit 110a. Meanwhile, when the camera module 110 (or the camera unit 110a) can be interlocked with the near-field camera device 185 through the near-field module 125 (or the near-field wireless unit 125a) and / The present invention is not limited thereto.

The camera unit 110a includes at least one lens unit for receiving an optical signal reflected from a subject, an image sensor unit for detecting an optical signal input through the lens unit and converting the optical signal into an electrical image signal, (For example, an infrared filter or the like) between the lens unit and the image sensor unit according to an embodiment of the present invention, . Meanwhile, the camera unit 110a includes an image signal processor (ISP) which processes the image information or image information according to a designated procedure for improving the quality of image information or image information generated through the image sensor unit .

Meanwhile, when the sound module 100 is provided with the camera module 110, the camera module 110 includes a driver for changing a photographing direction of the camera module 110a, and the control module 130 Or the camera module 110) controls the driving unit to read image information or image information generated through the image sensor unit of the camera unit 110a while changing the photographing direction of the camera unit 110a, (For example, a person or a thing that generates a characteristic sound) in a space such as a stationary space, and drives the driving unit to photograph the sound source through the camera unit 110a. If the sound input unit 105a included in the sound module 105 includes one or more directional microphones, the control module 130 (or the camera module 110) 105a to detect a feature sound direction detected by the at least one directional microphone and drive the drive unit to photograph the feature sound direction confirmed through the camera unit 110a.

The control module 130 is a collective term for controlling various operations of the stationary sound apparatus 100. The control module 130 preferably generates image data through the camera module 110, And an operation of communicating with a server designated by the communication module 120 (for example, the operation server 200), or a combination of two or more of the operations of the controller 130a And a memory unit for storing various information and program codes necessary for the operation of the controller 130a.

The control unit 130a is a generic term for controlling the operation of the stationary sound apparatus 100. The control unit 130a may include at least one processor and an execution memory and / or may include various chips or control circuits. (For example, a bus (BUS), etc.) with each component provided in the stationary sound apparatus 100. [ According to the present invention, the control unit 130a loads at least one program code included in the stationary sound apparatus 100 into the execution memory through the processor, and outputs the result to at least one And controls the operation of the stationary sound apparatus 100. [ The functional configuration of the present invention may be implemented in the form of a program code and / or a chip or a control circuit. For convenience of explanation, the program configuration and / Or a control circuit according to the present invention will be described with reference to the control unit 130a.

The memory unit is a collective term of a nonvolatile memory corresponding to a storage resource of the stationary sound apparatus 100 and includes at least one program code executed through the control unit 130a and at least one data set used by the program code And stores it. The memory unit basically comprises a system program code and a system data set corresponding to the operating system of the stationary sound apparatus 100, a communication program code and a communication data set for processing a wireless communication connection of the stationary sound apparatus 100, An application code and an application data set, and a program code and a data set corresponding to a functional configuration implementing the present invention may also be stored in the memory unit.

The power supply module 115 is a collective term for supplying / supplying power required for operation of the stationary sound apparatus 100 and is preferably an external power supply (for example, an AC power source, a DC power source rectifying an AC power source, a USB power source, (Not shown) for supplying and receiving external power to the stationary sound apparatus 100. When the voltage value or the current value of the external power source is different from the voltage value or the current value required for the operation of the stationary sound apparatus 100, (Not shown) for converting the power supply voltage into an operating power having a value or a current value. Meanwhile, when the external power is supplied through the power supply unit or the external power is converted into the operation power through the power conversion unit, the power module 115 charges the external power or the operation power, (Not shown) for applying the charged power when the external power is not supplied to the battery.

According to the first embodiment of the present invention, the sound device 100 recognizes a designated sound feature for a specific situation of a specified space and provides a service related to the sound feature Sound device 100 as shown in FIG.

According to a second embodiment of the present invention, the sound device 100 is provided with a speech recognition mode of operation for providing a known speech recognition based service, wherein a specific setting through a predetermined input provided in the sound device 100 The mode switching sound device 100 may be switched from the voice recognition mode to the feature voice recognition mode for the feature-based voice recognition service according to the present invention based on specific voice recognition through input or voice recognition.

According to the third embodiment of the present invention, the sound device 100 may be a composite sound device (not shown) manufactured to provide a known speech recognition-based service and simultaneously recognize a feature sound according to the present invention, (100).

Referring to FIG. 1, the control module 130 recognizes recognition target information to be recognized for starting or processing a specific service among speech content information recognized through a speech recognition unit of the control module 130 and obtained through natural language processing And an information storage unit 135 for storing the information in a designated storage area of the memory unit.

When it is necessary to recognize the user's utterance contents in order to determine the initiation or processing of a specific service, the information storage unit 135 stores the recognition target information including the utterance content to be recognized from the utterance of the user, And mapping the service providing information for starting or processing of the specific service.

According to the embodiment of the present invention, the information to be mapped to be mapped to the service provision information is specified including the pre-designated speech content, and / or the sound output unit 105b of the stationary sound apparatus 100 May be input through the sound input unit 105a, and may be acquired and registered / updated through a natural language process after requesting a speech content to be used as the recognition object information. Meanwhile, according to an embodiment of the present invention, the recognition object information can be registered / updated through an application of a user wireless terminal mapped to the stationary sound device 100, and thus the present invention is not limited thereto.

For example, when the characteristic sound is a baby crying sound, the information to be recognized may include information about the utterance contents (for example, " agayajaja " or " mother sleepy " or " The service providing information may include a white noise (for example, a noise similar to a noise heard by a baby at a mother's speed, a vacuum cleaner washing machine sound, Dryer sound, etc.) at a specified signal output intensity.

Referring to FIG. 1, the control module 130 buffers sound data corresponding to a sound signal of an audible frequency band inputted through the sound input unit 105a in a designated buffer area or sound data corresponding to sound data A sound processing unit 140 for reading the buffered sound data and determining at least one characteristic sound frequency to recognize at least one characteristic sound designated for determining a specific situation, A characteristic sound recognition unit 145 for recognizing a characteristic sound corresponding to at least one characteristic sound pattern corresponding to the band and / or the characteristic sound to recognize the characteristic sound, S? 1) service functions, at least s (1? S? S) service units And a service controller (150) for setting the operation mode of the sound device (100) to a sleep mode when a feature sound or a user's speech content is not recognized for a predetermined period of time or longer, And a service providing unit 180 for providing a service corresponding to the activated service function. According to another embodiment of the present invention, at least one of the feature sound recognition unit 145, the service control unit 150, and the service providing unit 180 may be connected to an operating server (not shown) If the feature sound recognition unit 145 is implemented in the operation server 200, the sound processing unit 140 may transmit the sound data buffered in the designated buffer area to the operation server 200 Alternatively, sound data determined to correspond to the feature sound among the buffered sound data may be selectively extracted and may be provided to the operation server 200. 1, the feature of the present invention will be described with reference to an embodiment in which the feature sound recognition unit 145, the service control unit 150, and the service providing unit 180 are implemented through the sound apparatus 100 . If the feature sound recognition unit 145, the service control unit 150 and the service providing unit 180 are implemented through the sound device 100, the feature sound recognition unit 145, the service control unit 150, The studying unit 180 may be implemented as a combination of a program code form and a chip or a control circuit form, And the present invention is not limited by the method of implementation or the module to be implemented.

After the operating power is applied to the sound device 100 through the power module 115, the sound processor 140 receives the sound data corresponding to the sound signal of the audio frequency band input through the sound input unit 105a, (Or repeats) the process of buffering the sound data in the designated buffer area and / or checking the buffered sound data in the designated buffer area, and the feature sound recognizing part 145 reads the buffered sound data, A specific feature sound corresponding to at least one feature sound frequency band designated to recognize at least one feature sound designated for specific situation judgment and / or corresponding to at least one feature sound pattern designated for recognizing the feature sound Continue (or repeat) the process of recognition. If the characteristic sound recognition unit 145 is implemented in the operating server 200, the sound processing unit 140 provides the buffered sound data to the operating server 200 or the buffered sound data It is possible to selectively extract the sound data corresponding to the feature sound among the sound data and to provide the sound data to the operation server 200. Accordingly, the present invention is not limited thereto.

The service controller 150 determines whether a feature sound is not recognized for a predetermined period of time or longer after operating power is applied to the sound device 100 and / or recognizes the feature sound through the feature sound recognition unit 145 And / or to confirm that the speech uttered by the user has not been recognized for a specified period of time or longer after the operation power is applied to the sound apparatus 100, and / or (E.g., recognizing the user's utterance contents within a predetermined period of time during or after the characteristic sound is effectively recognized through the characteristic sound recognition section 145) in accordance with a designated procedure, Can not be recognized. The service control unit 150 determines the operation mode of the sound device 100 (or the control module 130) if the feature sound is not recognized for a predetermined period of time or is not recognized for a predetermined period of time or more And a function of setting a sleep mode. Here, the sleep mode reads the buffered sound data to recognize a feature sound even if the user's utterance is recognized, and wakes up in a sleep mode and / or pre-specified specific utterance information (e.g., (E.g., specific speaking information set to wake up the sound apparatus 100), and recognizes a service (e.g., a sound source or a beep sound as a sound based on the speaking content of the recognized user before waking up in the sleep mode) And a sound-based service for outputting sound). Hereinafter, the features of the present invention will be described focusing on an embodiment in which a characteristic sound is recognized for a sake of convenience and wakes up in a sleep mode.

According to the embodiment of the present invention, the sound processing unit 140 buffers the sound data corresponding to the sound signal of the audible frequency band inputted through the sound input unit 105a in the sleep mode in the designated buffer area and / It is preferable to continue (or repeat) the process of confirming the buffered sound data in the designated buffer area, and the characteristic sound recognition unit 145 may also read the buffered sound data in the sleep mode, Corresponding to at least one feature sound frequency band designated for recognizing at least one feature sound designated for a specific situation of sound or noise and / or corresponding to at least one feature sound pattern designated for recognizing the feature sound Continuing (or repeating) the process of recognizing a particular feature sound ). Preferably, in the sleep mode, when the feature sounds are effectively recognized through the feature sound recognition unit 145, the service controller 150 may wake up to activate s service functions related to the feature sounds, The service providing unit 180 may perform a procedure of providing a service corresponding to the activated s service functions.

Meanwhile, when two or more service functions related to the characteristic sound are activated through the service control unit 150, the service providing unit 180 performs a procedure of providing a service corresponding to the activated service function according to a specified order And / or a process of providing at least one service according to a predetermined condition among the activated service functions (for example, a condition for recognizing a user's utterance).

According to the embodiment of the present invention, the characteristic sound recognizing unit 145 recognizes a characteristic sound corresponding to a characteristic sound frequency band of a specific sound source and / or a unique characteristic sound of a specific sound source corresponding to the characteristic sound pattern of the specific sound source The control module 130 may be configured to learn at least one feature sound frequency band specific to a specific sound source and / or to learn at least one feature sound pattern specific to a specific sound source, .

1, the control module 130 stores M feature sound frequency band information corresponding to M (M? 1) feature sound frequency bands in a designated storage area and / or N (N? 1 And storing the N feature pattern information corresponding to the feature sound patterns in the designated storage area, wherein the feature sound recognition unit (145) The feature sounds can be recognized using the information and / or the feature pattern information. According to another embodiment of the present invention, at least one component of the information storage unit 135 and the feature sound recognition unit 145 is implemented through an operation server 200 on a communication network interlocked with the sound apparatus 100 . 1, the features of the present invention will be described with reference to an embodiment in which the information storage unit 135 and the feature sound recognition unit 145 are implemented through the sound device 100. FIG. If the information storage unit 135 and the feature sound recognition unit 145 are implemented through the sound device 100, the information storage unit 135 and the feature sound recognition unit 145 may store the program code form, The present invention is not limited to the embodiment in which the information storage unit 135 and the characteristic sound recognition unit 145 are implemented or the module is implemented.

The information storage unit 135 stores M feature sounds corresponding to M (M? 1) feature sound frequency bands in a designated storage area of the memory unit at the time of manufacturing the control module 130 (or the sound device 100) Frequency band information can be stored. The feature sounds designated for the determination of a specific situation among non-verbal sounds or noises that can be generated in the space designated in the present invention are various (or a wide range of frequency difference between the lowest frequency and the highest frequency is at least 100 Hz) Frequency band. Accordingly, the present invention can divide the frequency band of the characteristic sound into M frequency bands (for example, equally divided or selectively divided based on a plurality of frequency bands in which the characteristic sounds are concentrated experimentally) May store M feature sound frequency band information corresponding to the divided M feature sound frequency bands in a designated storage area.

The information storage unit 135 stores N characteristic sound patterns N corresponding to N (N? 1) characteristic sound patterns in a designated storage area of the memory unit at the time of manufacturing the control module 130 (or the sound device 100) Information can be stored in the designated storage area. The present invention firstly generates characteristic sound pattern information through a qualitative analysis and / or a quantitative analysis process for each case of the patterns of characteristic sounds identified through the sample experiment, and the information storage unit 135 stores the generated characteristic sound patterns Information can be stored in the designated storage area.

Meanwhile, according to the embodiment of the present invention, the sound device 100 (or the control module 130) can recognize the feature sound and transmit the recognized feature sound information to the designated operation server 200, The server 200 performs a normalization process of collecting the feature sound information from each sound device 100 (or the control module 130) and normalizing the individual sound characteristics of each sound source in the collected feature sounds, Or the qualitative analysis and / or the quantitative analysis for each case to refine or diversify the characteristic sound pattern information, and the thus-refined or diversified characteristic sound pattern information is transmitted to each sound device 100 (or the control module (130). The information storage unit 135 receives the feature sound pattern information that has been refined or diversified through the above process from the operation server 200 and stores N feature sound pattern information including the received feature sound pattern information Can be stored in a designated storage area.

According to an embodiment of the present invention, M characteristic sound frequency band information corresponding to M characteristic sound frequency bands is stored in the designated storage area and / or N characteristic sound frequency band information corresponding to N characteristic sound patterns is stored in the designated storage area When the sound pattern information is stored, the feature sound recognizing unit 145 reads the buffered sound data to correspond to at least one feature sound frequency band among the stored M feature sound frequency bands and / It is preferable to recognize a feature sound corresponding to at least one feature sound pattern out of the feature sound patterns.

On the other hand, the M feature frequency band information and / or the N feature pattern information stored in the designated storage area are not optimized (or fitted) to the feature sound of a specific sound source, but are stored in the frequency band of the statistical feature sound and / Information corresponding to the pattern. Therefore, in order to quickly recognize the characteristic sound of a specific sound source present in the space where the sound device 100 is mounted and / or to prevent (or minimize) the recognition error, the stored characteristic sound frequency band information and / A process of optimizing (or fitting) the pattern information to the characteristic sound of the specific sound source is required.

Referring to FIG. 1, the control module 130 generates a feature sound frequency corresponding to at least i (i? 2) valid recognized feature frequency distributions for a predetermined period using the M feature frequency ranges, Generating distribution information for generating characteristic sound pattern distribution information corresponding to at least j (j? 2) valid recognized characteristic sound pattern distributions for a predetermined period using the N characteristic sound pattern information and / (M (1) m (m) optimized for (or fitted to) a characteristic sound of a specific sound source in a space in which the sound device 100 is mounted, by statistically processing the generated characteristic sound frequency distribution information, ) Of the feature sound frequency band and / or statistical processing of the generated feature sound pattern distribution information, An information determination unit 160 for determining n characteristic sound pattern information corresponding to n (1? N? N) characteristic sound patterns optimized (or fitted) to the characteristic sound of a specific sound source in a stationary space Respectively. According to another embodiment of the present invention, at least one component of the distribution generating unit 155 and the information determining unit 160 is implemented through the operating server 200 on the communication network interlocked with the sound apparatus 100 . 1 for the sake of convenience, the characteristics of the present invention will be described mainly with reference to an embodiment in which the distribution generating unit 155 and the information determining unit 160 are implemented through the sound apparatus 100. FIG. If the distribution generating unit 155 and the information determining unit 160 are implemented through the sound apparatus 100, the distribution generating unit 155 and the information determining unit 160 may be implemented in the form of a program code and a chip or a control circuit And the present invention is not limited to the method of implementing the distribution generating unit 155 and the information determining unit 160 and the implemented modules.

If the M feature frequency band information corresponding to the M feature frequency bands is stored in the storage area designated by the information storage unit 135, the distribution generating unit 155 generates M feature information The frequency band information of the effectively recognized feature sounds can be stored in the designated storage area whenever the feature sounds are effectively recognized using the sound frequency band information. The distribution generating unit 155 may generate at least i (i, 2) valid recognized i-th sound frequency bands for a predetermined period based on the feature sound frequency band that is effectively recognized and stored through the M feature sound frequency band information And generate characteristic sound frequency distribution information corresponding to the distribution of the identified i characteristic sound frequency bands.

If the characteristic sound frequency distribution information corresponding to the currently recognized characteristic sound frequency distribution is generated at least for a predetermined period of time through the distribution generating unit 155, the information determining unit 160 determines that the characteristic sound frequency (Or fitting) the characteristic sound of the specific sound source in the space in which the sound device 100 is placed to statistically process the distribution information to quickly recognize (or minimize) the characteristic sound of the specific sound source, M characteristic sound frequency band information corresponding to m (1? M? M) characteristic sound frequency bands corresponding to the m characteristic frequency bands. Here, the m characteristic sound frequency bands may be any one of the M characteristic sound frequency bands, or may include a newly defined characteristic sound frequency band within the characteristic sound frequency band. When the m characteristic sound frequency band information is determined through the information determination unit 160, the information storage unit 135 sets the determined m characteristic sound frequency bands to a characteristic sound frequency band to be read first, Area, or may update and store the characteristic sound frequency band information stored in the storage area. Then, the feature-sound recognizing unit 145 may read the buffered sound data and recognize a feature sound corresponding to at least one feature frequency band among the m newly-stored feature frequency bands.

Meanwhile, when N feature sound pattern information corresponding to N feature sound patterns is stored in the storage area designated through the information storage unit 135, the distribution generator 155 generates N feature sound patterns The sophisticated pattern of the effectively recognized feature sound can be stored in the designated storage area whenever the feature sound is effectively recognized using the pattern information. The distribution generating unit 155 identifies j feature sound patterns recognized at least j (j? 2) times for a predetermined period based on the feature sound pattern information effectively recognized and stored through the N feature sound pattern information And generate characteristic sound pattern distribution information corresponding to the distribution of the identified j characteristic sound patterns.

Meanwhile, when the characteristic sound pattern distribution information corresponding to the characteristic sound pattern distribution that has been recognized at least j times for a predetermined period is generated through the distribution generating unit 155, the information determining unit 160 determines that the generated characteristic sound pattern (Or fitting) the characteristic sound of the specific sound source in the space in which the sound device 100 is placed to statistically process the distribution information to quickly recognize (or minimize) the characteristic sound of the specific sound source, N characteristic sound pattern information corresponding to n (1 &amp;le; n &amp;le; N) characteristic sound patterns. Here, the n feature sound patterns may be any one of the N feature sound patterns, or a combination of two or more feature sound patterns, or may include a new crying pattern. When the n feature sound patterns are determined through the information determination unit 160, the information storage unit 135 sets the determined n feature sound patterns as the feature sound patterns to be read first, and newly stores the feature sound patterns in the designated storage area The feature frequency band information stored in the storage area can be updated and stored. Then, the feature-sound recognizing unit 145 may read the buffered sound data and recognize a feature sound corresponding to at least one feature sound pattern among the n feature sound patterns first.

Referring to FIG. 1, the control module 130 includes a speech recognition unit (speech recognition unit) 130 that reads the buffered sound data and recognizes the user's speech utterance and processes the speech in a natural language to recognize utterance content information corresponding to the utterance contents of the user A recognition unit 170 for recognizing whether the user's utterance is recognized while the characteristic sound is recognized or whether the user's utterance is recognized within a predetermined period of time after the recognition of the characteristic sound is completed; And an intelligent processing unit (175) for processing the speech contents of the recognized user in association with s service functions related to the feature sounds when the user's speech contents are recognized within a predetermined period of time have. According to another embodiment of the present invention, at least one of the speech recognition unit 165, the recognition determination unit 170, and the intelligent processing unit 175 may be connected to an operating server (not shown) If the speech recognition unit 165 is implemented in the operation server 200, the sound processing unit 140 may transmit the sound data buffered in the designated buffer area to the operation server 200 Or selectively extract sound data determined to correspond to a user utterance among the buffered sound data and provide the sound data to the operation server 200. [ 1, the features of the present invention will be described with reference to an embodiment in which the speech recognition unit 165, the recognition determination unit 170, and the intelligent processing unit 175 are implemented through the sound apparatus 100 . If the speech recognition unit 165, the recognition determination unit 170, and the intelligent processing unit 175 are implemented through the sound device 100, the speech recognition unit 165, the recognition determination unit 170, The processing unit 175 may be implemented in the form of a program code and a chip or a control circuit in a form of a combination of at least one or both of the program codes and the speech recognition unit 165, the recognition / determination unit 170, and the intelligent processing unit 175 And the present invention is not limited by the method of implementation or the module to be implemented.

The feature recognition unit 165 reads out the buffered sound data through the feature recognition unit 145 and recognizes the feature sound. The speech recognition unit 165 reads the buffered sound data, And performs a process of recognizing the utterance contents information corresponding to the utterance contents of the user. When the speech recognition unit 165 is implemented in the operating server 200, the sound processing unit 140 provides the buffered sound data to the operating server 200 or the buffered sound data The sound data determined to correspond to the user's utterance (including, for example, segmented sounds) can be selectively extracted and provided to the operation server 200, so that the present invention is not limited thereto.

According to the embodiment of the present invention, the speech recognition unit 165 analyzes the buffered sound data through a designated speech recognition algorithm, recognizes and texts the speech uttered by the user, and performs a morphological analysis, a semantic analysis, The user can generate the utterance content information that recognizes the uttered utterance through the natural language processing procedure in the analysis.

Meanwhile, according to the embodiment of the present invention, the feature recognition unit 165 recognizes the feature sounds by the feature recognition unit 145 and transmits the feature sounds through the service control unit 150 in the sleep mode It is desirable to perform the function of recognizing the user's utterance contents when the user wakes up. If the operation mode of the sound device 100 is set to the sleep mode by the service controller 150, the speech recognition unit 165 may not perform the function of recognizing the user's utterance, Even if the user's speech content is recognized, it can be processed so as not to be used for the service.

Meanwhile, when the user's utterance is recognized through the utterance recognition unit 165, the recognition determination unit 170 recognizes the utterance contents of the user during the recognition of the feature sound through the utterance recognition unit 145 Or whether or not the user's utterance is recognized within a predetermined period of time after the recognition of the characteristic sound is completed through the characteristic sound recognition unit 145. [

If it is confirmed that the user's utterance is recognized within a certain time period during or after the recognition of the characteristic sound through the recognition determination unit 170, the intelligent processing unit 175 recognizes the utterance content recognition unit 165, The searched contents of the user are correlated with the s service functions related to the feature sounds so that the specific service functions corresponding to the uttered contents among the s service functions related to the feature sounds can be determined. In this case, the service control unit 150 may activate a specific service function corresponding to the specific sound and at the same time, the specific service function corresponding to the recognized user's utterance, and the service providing unit 180 may transmit the activated specific service function The procedures provided may be performed according to specified procedures.

If the user's utterance is not recognized within a certain period of time during or after recognition of the feature sound through the recognition determination unit 170, the intelligent processing unit 175 receives the sleep mode And / or performing a process of waking up in the sleep mode by the feature sound.

Meanwhile, according to the embodiment of the present invention, the s services related to the feature sounds that are activated by the service control unit 150 and / or provided through the service providing unit 180 may be transmitted through the communication module 120, A server-interlocking service provided in cooperation with the operation server 200, a sound-based service provided through the sound module 105, and a composite service providing a combined use of the sound module 105 and the communication module 120 And / or &lt; / RTI &gt;

Meanwhile, among the s services related to the feature sounds, the server interworking service may include a paging service using wireless terminal information, a status notification service using wireless terminal information, a paging service using an application installed in the wireless terminal, A status notification service, a video service for providing video information photographed through at least one camera to an application installed in a wireless terminal, and a video service for providing video information photographed through at least one camera to a designated IPTV device . &Lt; / RTI &gt;

Meanwhile, the sound-based service among the s services related to the feature sound may include a noise output service for outputting a designated service sound through the sound output unit 105b of the sound module 105 at a designated signal output intensity, Preferably, the signal output intensity of the sound-based service includes a signal intensity in inverse proportion to the signal input intensity of the feature sound.

On the other hand, among the s services related to the feature sounds, the composite service recognizes the user's utterance contents within a certain period of time during or after recognition of the feature sounds and correlates the utterance contents of the user with the service functions related to the feature sounds And a service provided through the operation server 200 on the communication network based on the result.

In the meantime, according to the first camera embodiment of the present invention, the sound device 100 is provided with a camera device 185 in the vicinity and a short-range module 125 for processing short-range wireless communication, When the short distance wireless communication with the nearby camera device 185 is performed, the service control unit 150 may recognize the feature sound through the near-field module 125, May activate s service functions including a video service function for communicating with the device 185 and photographing a sound source that generates the recognized feature sounds through the camera device 185, Communicates with the camera device 185 through the near field module 125 and receives image information photographed through the camera device 185 to receive the image information through an application installed in the wireless terminal through the operation server 200 A video service providing service and / or a video service providing service to a designated IPTV service. On the other hand, when the camera apparatus 185 can provide the image service, the service provider 180 may process the image service function of the camera apparatus 185 to operate through the near field module 125.

Alternatively, a short-range wireless network-based wireless communication may be performed with the near-field camera device 185 through the short-range network communication unit 120b of the communication module 120 provided in the sound device 100 according to the second camera embodiment of the present invention. The service control unit 150 may communicate with the camera device 185 through the local area network communication unit 120b to recognize the feature sound through the camera device 185 when the feature sound recognition unit 145 recognizes the feature sound. The service providing unit 180 may activate the s service functions including a video service function for photographing the sound source generating the recognized feature sounds through the short distance network communication unit 120b A video service that communicates with the camera device 185 and receives image information photographed through the camera device 185 and provides the image information through an application installed in the wireless terminal through the operation server 200 and / V device to provide at least one video service. On the other hand, when the camera apparatus 185 can provide the image service, the service provider 180 can process the image service function of the camera apparatus 185 through the near-field communication unit 120b.

Alternatively, when the camera module 110 is provided to acquire image information of a subject photographed by the sound device 100 according to the third camera embodiment of the present invention, the service controller 150 may recognize the feature sound recognition unit 145), the service providing unit 180 may activate a video service function for photographing a sound source that generates the recognized characteristic sound through the camera module 110, A video service for providing video information photographed through the camera module 110 to an application installed in a wireless terminal through the operation server 200 and / or a video service for providing to a designated IPTV device can be provided have.

2 is a functional block diagram of the stationary sound apparatus 100 and the operation server 200 according to another embodiment of the present invention.

2 shows an embodiment in which at least part of the functional configuration of the control module 130 of the stationary sound apparatus 100 shown in FIG. 1 is implemented on the operation server 200 side Those skilled in the art will be able to refer to and / or modify Figure 2 to implement an embodiment at least partially modifying the embodiment of Figures 1 and 2 Some of the functional configurations imple- mented on the operating server 200 of the stationary sound device 100 may be implemented in the operating server 200 as they are and some of them may be implemented in the control module 130 of the stationary sound device 100, 130, 130, and 130, but the present invention is not limited to the embodiments in which some of the components shown in FIG. 1 and FIG. 2 are omitted, Or subdivided, or summed Would be able to derive a binary exemplary method and the like), the present invention includes all embodiments wherein the method is inferred as the scope, not limited that the technical features of only the exemplary method shown in the figure 1 and the drawing 2.

Referring to FIG. 2, the operation server 200 includes a sound receiving unit 205 for receiving sound data input through a sound input unit 105a of a designated sound device 100 and temporarily storing the sound data in a designated storage medium, The sound data corresponding to at least one feature sound frequency band designated for recognizing at least one feature sound specified for determining a specific situation among non-verbal sounds or noises that can be generated in the designated space by reading the received sound data and / A feature sound recognizing unit 145 for recognizing a specific feature sound corresponding to at least one feature sound pattern designated for recognizing a feature sound and a feature sound among S (S? 1) (1 &lt; / = s &lt; / = S) service functions and / or a feature sound or a user's foot And a service control unit 150 for setting an operation mode of the sound apparatus 100 to a sleep mode when the contents are not recognized and the service providing unit 180 for providing a service corresponding to the activated service function ).

The sound receiving unit 205 receives the sound data transmitted from the sound apparatus 100 and temporarily stores the sound data in the designated storage medium in the designated sound apparatus 100. [ Can be stored. Meanwhile, in the case where the sound device 100 selectively transmits sound data corresponding to a feature sound or sound data corresponding to a user utterance, the sound receiving unit 205 receives the sound data from the sound apparatus 100 The sound data selectively transmitted may be received and temporarily stored in a designated storage medium.

The feature sound recognizing unit 145 reads the received sound data and generates at least one feature sound frequency band designated for recognizing at least one feature sound designated for a specific situation of non-verbal sounds or noises, (Or repeats) the process of recognizing a specific feature sound corresponding to at least one feature sound pattern corresponding to the feature sound and / or recognizing the feature sound.

The service controller 150 determines whether a feature sound is not recognized for a predetermined period of time or longer after operating power is applied to the sound device 100 and / or recognizes the feature sound through the feature sound recognition unit 145 And / or to confirm that the speech uttered by the user has not been recognized for a specified period of time or longer after the operation power is applied to the sound apparatus 100, and / or (E.g., recognizing the user's utterance contents within a predetermined period of time during or after the characteristic sound is effectively recognized through the characteristic sound recognition section 145) in accordance with a designated procedure, Can not be recognized. If the feature sound is not recognized for a predetermined period of time or the user's speech is not recognized for a predetermined period of time or longer, the service controller 150 sets the operation mode of the sound device 100 to a sleep mode And the like.

According to an embodiment of the present invention, the sound device 100 can transmit the input sound data in a sleep mode, and the sound receiver 205 can receive sound data in a sleep mode, And the characteristic sound recognition unit 145 also reads the received sound data in the state where the operation mode of the sound device 100 is in the sleep mode and outputs the non-linguistic sound or noise Corresponding to at least one feature sound frequency band designated for recognition of at least one feature sound designated for a specific situation determination and / or at least one feature sound pattern corresponding to at least one feature sound pattern designated for recognizing the feature sound (Or repeats) the process of recognizing the user. Preferably, when the feature sounds are effectively recognized through the feature sound recognition unit 145 in the sleep mode, the service controller 150 wakes up the sound apparatus 100, And the service providing unit 180 may perform a procedure of providing a service corresponding to the activated s service functions.

Meanwhile, when two or more service functions related to the characteristic sound are activated through the service control unit 150, the service providing unit 180 performs a procedure of providing a service corresponding to the activated service function according to a specified order And / or a process of providing at least one service according to a predetermined condition among the activated service functions (for example, a condition for recognizing a user's utterance).

According to the embodiment of the present invention, the characteristic sound recognizing unit 145 recognizes a characteristic sound corresponding to a characteristic sound frequency band of a specific sound source and / or a unique characteristic sound of a specific sound source corresponding to the characteristic sound pattern of the specific sound source The operating server 200 may recognize at least one feature sound frequency band specific to a specific sound source and / or at least one feature sound pattern specific to a specific sound source, .

Referring to FIG. 2, the operation server 200 stores M feature sound frequency band information corresponding to M (M? 1) feature sound frequency bands in a designated storage medium and / or N (N? 1 And storing the N feature pattern information corresponding to the feature sound patterns in the designated storage medium, wherein the feature sound recognition unit (145) The feature sound can be recognized using the information and / or the feature pattern information.

The information storage unit 135 may store M feature sound frequency band information corresponding to M (M? 1) feature sound frequency bands in a designated storage medium. The feature sounds designated for the determination of a specific situation among non-verbal sounds or noises that can be generated in the space designated in the present invention are various (or a wide range of frequency difference between the lowest frequency and the highest frequency is at least 100 Hz) Frequency band. Accordingly, the present invention can divide the frequency band of the characteristic sound into M frequency bands (for example, equally divided or selectively divided based on a plurality of frequency bands in which the characteristic sounds are concentrated experimentally) The M feature frequency band information corresponding to the M feature frequency bands may be stored in a designated storage medium.

The information storage unit 135 may store N characteristic sound pattern information corresponding to N (N? 1) characteristic sound patterns in a designated storage medium in a designated storage medium. The present invention firstly generates characteristic sound pattern information through a qualitative analysis and / or a quantitative analysis process for each case of the patterns of characteristic sounds identified through the sample experiment, and the information storage unit 135 stores the generated characteristic sound patterns Information can be stored in the designated storage medium.

According to the embodiment of the present invention, the sound device 100 can recognize the feature sound and transmit the recognized feature sound information to the specified operation server 200. The intelligent processing unit 175 of the operation server 200 ) Collects characteristic sound information from each sound apparatus 100, and performs a normalization process for normalizing individual sound characteristics of the respective sound sources in the collected characteristic sounds and / or a normalization process for performing qualitative analysis for each case and / The characteristic sound pattern information can be refined or diversified through an analysis process. The information storage unit 135 may receive the feature information of the refined or diversified features through the above process and may store the N feature pattern information including the received feature pattern information in a designated storage medium .

M characteristic sound frequency band information corresponding to M characteristic sound frequency bands may be stored in the designated storage medium and / or N characteristic sound frequency band information corresponding to N characteristic sound patterns may be stored in the designated storage medium according to an embodiment of the present invention. When the sound pattern information is stored, the feature sound recognizing unit 145 reads the received sound data to correspond to at least one feature sound frequency band among the stored M feature sound frequency bands and / It is preferable to recognize a feature sound corresponding to at least one feature sound pattern out of the feature sound patterns.

On the other hand, the M feature frequency band information and / or N feature sound pattern information stored in the designated storage medium are not optimized (or fitted) to the feature sound of the specific sound source, but the frequency band of the statistical feature sound and / Information corresponding to the pattern. Therefore, in order to quickly recognize the characteristic sound of a specific sound source present in the space where the sound device 100 is mounted and / or to prevent (or minimize) the recognition error, the stored characteristic sound frequency band information and / A process of optimizing (or fitting) the pattern information to the characteristic sound of the specific sound source is required.

Referring to FIG. 2, the operation server 200 generates a feature sound frequency corresponding to at least i (i? 2) valid recognized feature frequency distributions for a predetermined period using the M feature frequency bands information, Generating distribution information for generating characteristic sound pattern distribution information corresponding to at least j (j? 2) valid recognized characteristic sound pattern distributions for a predetermined period using the N characteristic sound pattern information and / (M (1) m (m) optimized for (or fitted to) a characteristic sound of a specific sound source in a space in which the sound device 100 is mounted, by statistically processing the generated characteristic sound frequency distribution information, ) Of the feature sound frequency band and / or statistical processing of the generated feature sound pattern distribution information, An information determination unit 160 for determining n characteristic sound pattern information corresponding to n (1? N? N) characteristic sound patterns optimized (or fitted) to the characteristic sound of a specific sound source in a stationary space Respectively.

When the M feature frequency band information corresponding to the M feature frequency bands is stored in the storage medium designated by the information storage unit 135, the distribution generating unit 155 generates M feature information I &lt; th &gt; number of feature sound frequency bands recognized for at least i (i 2) times for a predetermined period of time using the sound frequency band information, Information can be generated.

If the characteristic sound frequency distribution information corresponding to the currently recognized characteristic sound frequency distribution is generated at least for a predetermined period of time through the distribution generating unit 155, the information determining unit 160 determines that the characteristic sound frequency (Or fitting) the characteristic sound of the specific sound source in the space in which the sound device 100 is placed to statistically process the distribution information to quickly recognize (or minimize) the characteristic sound of the specific sound source, M characteristic sound frequency band information corresponding to m (1? M? M) characteristic sound frequency bands corresponding to the m characteristic frequency bands. Here, the m characteristic sound frequency bands may be any one of the M characteristic sound frequency bands, or may include a newly defined characteristic sound frequency band within the characteristic sound frequency band. When the m characteristic sound frequency band information is determined through the information determination unit 160, the information storage unit 135 sets the determined m characteristic sound frequency bands to a characteristic sound frequency band to be read first, The sound information may be newly stored in the medium or the characteristic sound frequency band information stored in the storage medium may be updated and stored. Then, the characteristic sound recognition unit 145 reads the received sound data and can recognize the characteristic sound corresponding to at least one characteristic sound frequency band among the m or the newly stored characteristic sound frequency bands.

On the other hand, when N pieces of characteristic sound pattern information corresponding to N characteristic sound patterns are stored in the storage medium designated by the information storage unit 135, the distribution generation unit 155 generates the N characteristic features (J &gt; = 2) validated j characteristic sound patterns for a predetermined period using the sound pattern information, and generates characteristic sound pattern distribution information corresponding to the distribution of the identified j characteristic sound patterns can do.

Meanwhile, when the characteristic sound pattern distribution information corresponding to the characteristic sound pattern distribution that has been recognized at least j times for a predetermined period is generated through the distribution generating unit 155, the information determining unit 160 determines that the generated characteristic sound pattern (Or fitting) the characteristic sound of the specific sound source in the space in which the sound device 100 is placed to statistically process the distribution information to quickly recognize (or minimize) the characteristic sound of the specific sound source, N characteristic sound pattern information corresponding to n (1 &amp;le; n &amp;le; N) characteristic sound patterns. Here, the n feature sound patterns may be any one of the N feature sound patterns, or a combination of two or more feature sound patterns, or may include a new crying pattern. When the n feature sound patterns are determined through the information determination unit 160, the information storage unit 135 sets the determined n feature sound patterns to a feature sound pattern to be read first, The characteristic sound frequency band information stored in the storage medium can be updated and stored. Then, the characteristic sound recognizing unit 145 may read the received sound data and recognize the characteristic sound corresponding to at least one characteristic sound pattern among the n characteristic sound patterns.

Referring to FIG. 2, the operation server 200 includes a speech recognition unit (e.g., a speech recognition unit) for recognizing the user's speech uttered by the received sound data and performing natural language processing to recognize speech content information corresponding to the user's utterance A recognition unit 170 for recognizing whether the user's utterance is recognized while the characteristic sound is recognized or whether the user's utterance is recognized within a predetermined period of time after the recognition of the characteristic sound is completed; And an intelligent processing unit (175) for processing the speech contents of the recognized user in association with s service functions related to the feature sounds when the user's speech contents are recognized within a predetermined period of time have.

The recognition unit 165 reads the received sound data through the feature sound recognition unit 145 and recognizes the feature sound, and the speech recognition unit 165 reads the received sound data, And performs a process of recognizing the utterance contents information corresponding to the utterance contents of the user.

According to the embodiment of the present invention, the speech recognition unit 165 analyzes the received sound data through a designated speech recognition algorithm to recognize and characterize the speech uttered by the user, and performs a morphological analysis, a semantic analysis, The user can generate the utterance content information that recognizes the uttered utterance contents through the natural language processing procedure in the analysis.

Meanwhile, according to the embodiment of the present invention, the feature recognition unit 165 recognizes the feature sounds by the feature recognition unit 145 and transmits the feature sounds through the service control unit 150 in the sleep mode It is desirable to perform the function of recognizing the user's utterance contents when the user wakes up. If the operation mode of the sound device 100 is set to the sleep mode by the service controller 150, the speech recognition unit 165 may not perform the function of recognizing the user's utterance, Even if the user's speech content is recognized, it can be processed so as not to be used for the service.

Meanwhile, when the user's utterance is recognized through the utterance recognition unit 165, the recognition determination unit 170 recognizes the utterance contents of the user during the recognition of the feature sound through the utterance recognition unit 145 Or whether or not the user's utterance is recognized within a predetermined period of time after the recognition of the characteristic sound is completed through the characteristic sound recognition unit 145. [

If it is confirmed that the user's utterance is recognized within a certain time period during or after the recognition of the characteristic sound through the recognition determination unit 170, the intelligent processing unit 175 recognizes the utterance content recognition unit 165, The searched contents of the user are correlated with the s service functions related to the feature sounds so that the specific service functions corresponding to the uttered contents among the s service functions related to the feature sounds can be determined. In this case, the service control unit 150 may activate a specific service function corresponding to the specific sound and at the same time, the specific service function corresponding to the recognized user's utterance, and the service providing unit 180 may transmit the activated specific service function The procedures provided may be performed according to specified procedures.

If the user's utterance is not recognized within a certain period of time during or after recognition of the feature sound through the recognition determination unit 170, the intelligent processing unit 175 receives the sleep mode And / or performing a process of waking up in the sleep mode by the feature sound.

According to an embodiment of the present invention, s services activated by the service control unit 150 of the operating server 200 and / or associated with a feature sound that can be provided through the service providing unit 180, 200), and a composite service provided in cooperation with the sound apparatus 100. The server-based service may include a server-based service,

Meanwhile, among the s services related to the feature sounds, the server-based service may include a paging service using wireless terminal information, a status notification service using wireless terminal information, a paging service using an application installed in the wireless terminal, A status notification service, a video service for providing video information photographed through at least one camera to an application installed in a wireless terminal, and a video service for providing video information photographed through at least one camera to a designated IPTV device . &Lt; / RTI &gt;

On the other hand, among the s services related to the feature sounds, the composite service recognizes the user's utterance contents within a certain period of time during or after recognition of the feature sounds and correlates the utterance contents of the user with the service functions related to the feature sounds And a service provided through the operation server 200 on the communication network based on the result.

FIG. 3 illustrates an embodiment of recognizing a feature sound and activating a service related to the feature sound according to an embodiment of the present invention.

In more detail, FIG. 3 illustrates an embodiment of recognizing a feature sound using M feature frequency band information and / or N feature pattern information stored in a designated storage area and activating a service related to the recognized feature sound And those skilled in the art will be able to refer to and / or modify the FIG. 3 to understand various aspects of the feature sound recognition or service activation process (e.g., However, it should be understood that the present invention is not limited to the above-described embodiments, and various modifications may be made without departing from the scope of the present invention. 3 may be provided through the sound device 100 or may be provided through the operation server 200 or may be provided in a distributed form through interlocking of the sound device 100 and the operation server 200 For convenience, FIG. 3 illustrates features of the present invention with reference to a process that is provided through the sound apparatus 100. FIG.

3, the sound apparatus 100 stores (300) M feature sound frequency band information corresponding to M feature sound frequency bands for recognizing feature sounds in a designated storage area (300) and / or N characteristic sound pattern information corresponding to N characteristic sound patterns for recognizing the characteristic sound is stored in the designated storage area (300). Thereafter, the sound apparatus 100 receives sound data corresponding to the sound signal of the audio frequency band through the sound input unit 105a, buffers the sound data in the designated buffer area (305), reads the buffered sound data, A feature sound corresponding to at least one feature sound frequency band designated for recognizing at least one feature sound designated for a specific situation judgment and / or corresponding to at least one feature sound pattern designated for recognizing the feature sound And performs a procedure of recognizing corresponding feature sounds (310).

According to one embodiment of the present invention, the sound apparatus 100 reads the buffered sound data to correspond to at least one feature sound frequency band among the stored M feature sound frequency bands and / A characteristic sound corresponding to at least one characteristic sound pattern among the characteristic sound patterns can be recognized (310). According to another embodiment of the present invention, m characteristic sound frequencies (m) optimized (or fitted) to a characteristic sound of a specific sound source in a space where the sound device 100 is mounted through the processes of FIGS. 4 and / When the band information is determined and stored in the designated storage area and / or n characteristic sound pattern information optimized (or adapted) to the characteristic sound of the specific sound source is determined and stored in the designated storage area, Reads out the buffered sound data and generates a specific sound corresponding to at least one characteristic sound pattern corresponding to at least one characteristic sound frequency band among the stored m characteristic sound frequency bands and / The characteristic sound of the source can be recognized (310).

If the operation mode of the sound device 100 is the sleep mode at the time of recognizing the feature sound, the sound device 100 may be woken up in the sleep mode (315).

On the other hand, when the feature sound is recognized and / or when the operation mode of the sound device 100 is woken up in the sleep mode, the sound device 100 is associated with a feature sound among the designated S (S? 1) At least s (1? S? S) service functions may be activated (320) and a procedure may be performed (325) to provide at least one service function among the activated s service functions according to a designated procedure.

On the other hand, if the sound data is read and the characteristic sound is not recognized, the sound device 100 determines whether the characteristic sound is not recognized effectively for a predetermined period of time (330). If the characteristic sound is not recognized effectively for a predetermined period of time, the sound device 100 may set the operation mode of the sound device 100 to the sleep mode (335).

FIG. 4 illustrates an embodiment of optimizing (or fitting) a feature sound frequency band for recognizing a feature sound to a feature sound of a specific sound source according to an embodiment of the present invention.

In more detail, FIG. 4 shows characteristic sound frequency distribution information corresponding to at least i (i? 2) valid recognized characteristic sound frequency distributions for a predetermined period using M characteristic sound frequency band information previously stored in a designated storage area (1? M? M) m (1? M? M) optimized (or fitted) to the characteristic sound of a specific sound source in the space where the sound device 100 is placed, by statistically processing the generated characteristic sound frequency distribution information M characteristic sound frequency band information corresponding to the characteristic sound frequency band is newly determined and stored in a designated storage area. If the person skilled in the art is familiar with the present invention, Referring to and / or modified with respect to FIG. 4, various implementations of the process of optimizing (or fitting) the feature frequency band (e.g., some steps may be omitted , Or would be able to infer the order of the exemplary method is changed), the present invention is made, including any exemplary way in which the inference, to which the technical feature that is not limited to the exemplary method shown in the figure 4. 4 may be provided through the sound apparatus 100 or may be provided through the operation server 200 or may be provided in a distributed form through interlocking of the sound apparatus 100 and the operation server 200 For convenience, FIG. 4 illustrates features of the present invention with reference to a process provided through the sound apparatus 100. FIG.

Referring to FIG. 4, the sound apparatus 100 recognizes the feature sounds using the M feature frequency band information previously stored in the designated storage area, and then recognizes the feature sounds The frequency band information is stored and managed in a designated storage area (400).

If i (i? 2) feature sound frequency band information used for effectively recognizing a feature sound for a predetermined period of time is stored in the storage area (405), the sound device (100) (410), and the generated feature frequency distribution information is statistically processed so as to be stored in the space where the sound device (100) is mounted M characteristic sound frequency band information corresponding to the m (1? M? M) characteristic sound frequency bands optimized (or fitted) to the characteristic sound of the specific sound source is determined 415, and the determined m characteristic sound frequencies Band is first set to a characteristic sound frequency band to be read first and then updated / stored in a designated storage area (420), and then the sound device 100 stores the stored m characteristic sound frequency bands The information can be recognized by the characteristic sound.

FIG. 5 illustrates an embodiment of optimizing (or fitting) a feature sound pattern for recognizing a feature sound to a feature sound of a specific sound source according to another embodiment of the present invention.

More specifically, FIG. 5 shows characteristic sound pattern distribution information corresponding to at least j (j? 2) valid recognized characteristic sound pattern distributions for a predetermined period using N characteristic sound pattern information previously stored in a designated storage area (1 &amp;le; n &amp;le; N) features (or fittings) optimized to the feature sound of the specific sound source in the space where the sound device 100 is placed, And the n feature pattern information corresponding to the sound pattern is determined and newly / updated stored in the designated storage area. If the person skilled in the art is familiar with the present invention, (E.g., omitting some steps or changing the order) for the process of optimizing (or fitting) the feature sound patterns by referencing and / It should be understood that the present invention includes all of the above-described embodiments, and the technical features of the present invention are not limited only by the method shown in FIG. 5 may be provided through the sound apparatus 100 or may be provided through the operation server 200 or may be provided in a distributed form through interlocking of the sound apparatus 100 and the operation server 200 For convenience, FIG. 5 illustrates the features of the present invention with reference to a process provided through the sound apparatus 100. FIG.

Referring to FIG. 5, the sound apparatus 100 recognizes a feature sound using N pieces of feature pattern information previously stored in a designated storage area, and then recognizes the feature sound pattern Information is stored in a designated storage area and managed (500).

If j (j? 2) feature sound frequency band information used for effectively recognizing a feature sound for a predetermined period of time is stored in the storage area (505), the sound device (100) The characteristic sound pattern distribution information corresponding to the recognized characteristic sound pattern distribution is generated (510), and the generated characteristic sound pattern distribution information is statistically processed to determine characteristics of the specific sound source in the space After determining n characteristic sound pattern information corresponding to n (1? N? N) characteristic sound patterns optimized for sound (515), the n characteristic sound patterns determined first (520), and the sound device 100 can recognize the feature sound using the stored n feature pattern information.

FIG. 6 illustrates an embodiment of activating a service related to a feature sound by associating feature sounds with speech contents according to another embodiment of the present invention.

In more detail, in FIG. 6, when the user's utterance contents are recognized within a predetermined time period during or after recognition of the feature sound, the uttered contents of the recognized user are analyzed in association with s service functions related to the characteristic sound, 6 is a flow chart illustrating a method of activating a service related to a feature sound and a service activation process according to an embodiment of the present invention. It will be understood that various implementations of the present invention (e.g., some steps omitted or alternatives in which the order is changed) may be deduced, but the present invention includes all of the above- The technical features are not limited by the method alone. 6 may be provided through the sound apparatus 100 or may be provided through the operation server 200 or may be provided in a distributed form through interlocking of the sound apparatus 100 and the operation server 200 For convenience, FIG. 6 illustrates features of the present invention with reference to a process provided through the sound apparatus 100. FIG.

Referring to the embodiment of FIG. 6, the sound apparatus 100 reads sound data buffered in a designated buffer area, recognizes the user's language utterance, processes it in natural language, and recognizes the utterance contents information corresponding to the utterance contents of the user (600). If the user's utterance is not recognized, the sound device 100 determines whether the user's utterance is not recognized for a predetermined period of time (605). If the user's utterance is not recognized for a predetermined period of time, the sound apparatus 100 may set the operation mode of the sound apparatus 100 to a sleep mode (operation 610).

Meanwhile, when the sound data is read and the user's utterance is recognized, the sound apparatus 100 confirms whether the operation mode of the sound apparatus 100 is the sleep mode (615). If the sleep mode is selected, it is preferable to recognize a characteristic sound and perform a wake-up process.

On the other hand, if the operation mode of the sound device 100 is not the sleep mode at the time of recognizing the user's utterance contents (for example, the feature sound is recognized during the recognition of the user's uttered content or a predetermined time, When the sleep mode is woken up), the sound apparatus 100 confirms that the user's utterance is recognized while the feature sounds are being recognized, and / or if the user's utterance It is checked whether the contents are recognized (620). If the user's utterance is not recognized within a certain period of time during or after the recognition of the feature sound, the sound device 100 preferably confirms the sleep mode or recognizes the feature sound to perform a wake-up process Do.

If the user's utterance is recognized within a certain period of time during or after the recognition of the characteristic sound, the sound device 100 correlates the uttered contents of the recognized user with s service functions related to the characteristic sound (625). Based on this, a specific service function corresponding to the specific sound among the S service functions and corresponding to the speech contents of the recognized user may be activated (630), and the activated specific service function may be designated The procedure provided by the procedure may be performed (635).

100: sound device 105: sound module
105a: sound input unit 105b: sound output unit
110: camera module 110a:
115: power supply module 120: communication module
120a: wireless network communication unit 120b:
125: short-distance module 125a: short-
130: Control module 130a:
130b: memory unit 135: information storage unit
140: sound processing unit 145: feature sound recognition unit
150: service control unit 155: distribution generating unit
160: information determination unit 165:
170: situation determination unit 175: intelligent processing unit
180: Service provisioner 185: Camera device
200: Operation server 205: Sound receiver

Claims (24)

1. A stationary sound device comprising: a sound module including a sound input section for receiving a sound signal and a sound output section for outputting a sound signal; and at least one communication section for connecting to a communication network,
A sound processing unit for buffering sound data corresponding to a sound signal of an audible frequency band inputted through the sound input unit in a designated buffer area or checking buffered sound data in a designated buffer area;
And a controller for reading the buffered sound data to detect at least one feature sound frequency band designated for recognizing a specific situation of a non-verbal sound or noise that can be generated in the designated space, A characteristic sound recognition unit for recognizing a characteristic sound corresponding to the characteristic sound; And
And a service controller for activating at least s (1? S? S) service functions related to the feature sounds among S (S? 1) service functions designated when the feature sounds are recognized Stationary sound device for situation judgment.
The method according to claim 1,
To determine the baby's crying situation, the designated baby cry,
And at least one non-verbal sound of a scream sound designated for an emergency situation determination.
The method according to claim 1,
The door lock unlocking sound of the designated entrance door for the judgment of the home owner or the family home,
The sound of door openings of designated entrance door for the judgment of home owner or family's home situation,
And a sound of at least one of the beacons sounded for the visitor or the guest to determine a visiting situation.
The method as claimed in claim 1,
If the feature sound is not recognized for a predetermined period of time or more or the user's utterance is not recognized for a predetermined period of time or longer and the feature sound or the user's utterance is not recognized for a predetermined period of time or longer, Sleep) mode. The stationary sound device according to claim 1, further comprising:
The method according to claim 1,
The characteristic sound recognizing unit recognizes a characteristic sound in a sleep mode,
Wherein the service control unit includes a function of waking up when the feature sounds are recognized and activating s service functions related to the feature sounds.
6. The method according to claim 4 or 5,
And a state in which the buffered sound data is read and a function of providing a service based on the recognized speech content is recognized by recognizing the user's speech content.
The apparatus according to claim 1 or 3,
And a function of recognizing a characteristic sound of a specific sound source corresponding to a characteristic sound frequency band of the specific sound source and corresponding to the characteristic sound pattern of the specific sound source.
The apparatus of claim 1,
M pieces of feature sound frequency band information corresponding to M (M? 1) feature sound frequency bands and N feature sound pattern information corresponding to N (N? 1) feature sound patterns are stored in a designated storage area Wherein the sound output device is further provided with a sound output section.
9. The apparatus according to claim 8,
And reading the buffered sound data to recognize a feature sound corresponding to at least one feature sound frequency band among the M feature sound frequency bands and corresponding to at least one feature sound pattern among the N feature sound patterns Wherein the sound source is a sound source.
9. The apparatus of claim 8,
A distribution generating unit for generating characteristic sound frequency distribution information corresponding to at least i (i? 2) valid recognized sound frequency distributions for a predetermined period using the M characteristic sound frequency band information; And
(1? M? M) number of characteristic sound frequency bands optimized (or fitted) to the characteristic sound of a specific sound source in a space in which the sound device is mounted by statistically processing the generated characteristic sound frequency distribution information and an information determining unit for determining m characteristic sound frequency band information.
11. The method of claim 10,
Wherein the information storage unit further comprises a function of newly setting or updating and storing the determined m characteristic sound frequency bands as a characteristic sound frequency band to be read first,
Characterized in that the feature sound recognizing unit includes a function of reading the buffered sound data and first recognizing a feature sound corresponding to at least one feature sound frequency band among the stored m feature sound frequency bands A stationary sound device for.
9. The apparatus of claim 8,
A distribution generator for generating characteristic sound pattern distribution information corresponding to at least j (j? 2) valid recognized characteristic sound pattern distributions for a predetermined period using the N characteristic sound pattern information;
(N) corresponding to n (1? N? N) feature sound patterns that are optimized (or fitted) to the feature sound of a specific sound source in the space where the sound device is mounted, And an information determination unit for determining the feature sound pattern information of the plurality of feature sound patterns.
13. The method of claim 12,
Wherein the information storage unit further comprises a function of newly setting or updating and storing the determined n feature sound patterns in a feature sound pattern to be read first,
Wherein the feature sound recognizing unit includes a function of reading the buffered sound data and first recognizing a feature sound corresponding to at least one feature sound pattern among the stored n feature sound patterns. Stationary sound device.
The apparatus of claim 1,
A speech recognition unit for reading the buffered sound data and recognizing a user's speech utterance and performing natural language processing to recognize utterance content information corresponding to the utterance contents of the user;
A recognition determination unit for determining whether the user's utterance is recognized during the recognition of the characteristic sound or the utterance of the user is recognized within a predetermined time after the recognition of the characteristic sound is completed;
And an intelligent processing unit for processing the speech contents of the recognized user in association with s service functions related to the feature sounds when the speech contents of the user are recognized within a predetermined time period during or after the feature sounds are recognized Wherein the sound source is a sound source.
15. The method according to claim 14,
And a function of activating a specific service function corresponding to the recognized sound of the user while being related to the feature sound.
The method as claimed in claim 1,
A server interlocking service for interlocking with an operation server on a communication network through the communication module,
A sound based service provided through the sound module,
And at least one of a composite service providing the sound module and the communication module in combination.
17. The server of claim 16,
A paging service using wireless terminal information,
A status notification service using wireless terminal information,
A calling service using an application installed in a wireless terminal,
A status notification service using an application installed in a wireless terminal,
A video service for providing video information photographed through at least one camera to an application installed in a wireless terminal,
And a video service for providing video information photographed through at least one camera to a designated IPTV device.
17. The method of claim 16,
And a noise output service for outputting a designated service sound through a sound output unit of the sound module at a designated signal output intensity.
19. The method of claim 18,
Wherein the characteristic sound includes a signal intensity in inverse proportion to a received signal intensity.
17. The method of claim 16,
A service provided through an operation server on a communication network based on a result of analyzing the user's utterance contents within a predetermined time period during or after the recognition of the feature sound and correlating the utterance contents of the user with service functions related to the feature sounds, And a sound output unit for outputting sound to the sound output unit.
The method according to claim 1,
And a short-range module for processing a short-range camera device and short-range wireless communication,
Wherein the service control unit comprises a function of activating a video service function for communicating with the camera device via the near field module and photographing a sound source for generating the recognized characteristic sound through the camera device A stationary sound device for judgment.
The method according to claim 1,
Wherein the communication module includes a short range network communication unit for connecting a short distance camera device and a short range wireless network based wireless communication,
Wherein the service control unit includes a function of activating a video service function for communicating with the camera apparatus via the short range network communication unit and photographing a sound source for generating the recognized feature sound through the camera apparatus Stationary sound device for situation judgment.
The method according to claim 1,
Further comprising a camera module for acquiring image information of a photographed subject,
Wherein the service control unit includes a function of activating a video service function for photographing a sound source that generates the recognized characteristic sound through the camera module.
The apparatus of claim 1,
Further comprising a service providing unit for providing a service corresponding to the activated service function.

Images