Notification device, wearable device, and notification method

Abstract

A notification device includes a pressure sensor, a microcontroller, and an output device. The pressure sensor is used to detect the environment to provide a pressure signal. The microcontroller is connected to the pressure sensor to receive the pressure signal. The microcontroller is used to calculate the dynamic threshold value of the pressure signal within a period of time. When the magnitude of the pressure signal is greater than the dynamic threshold value, the microcontroller transmits a first feedback signal to the output device. The output device is connected to the microcontroller. The output device is used to provide a first feedback action according to the first feedback signal. In this way, it is convenient for the user to perceive the change of the environment.

Description

Technical Field

[0001] The present disclosure relates to a notification device and a wearable device provided with the notification device. Background Art

[0002] In some workplaces, it is not convenient to communicate directly by voice. For example, there are hearing-impaired people in the workplace, or the working environment is noisy. In these situations, it is not conducive to communication when workers keep themselves isolated from voices. If other auxiliary communication devices on the market are used, it may affect the work. Therefore, how to provide a portable and instant notification device is one of the problems to be solved by those skilled in the relevant field. Summary of the Invention

[0003] One aspect of the present disclosure relates to a notification device.

[0004] According to an embodiment of the present disclosure, the notification device includes a pressure sensor, a microcontroller, and an output device. The pressure sensor is used to detect the environment to provide a pressure signal. The microcontroller is connected to the pressure sensor to receive the pressure signal. The microcontroller is used to calculate the dynamic threshold value of the pressure signal within a period of time. When the magnitude of the pressure signal is greater than the dynamic threshold value, the microcontroller transmits a first feedback signal to the output device. The output device is connected to the microcontroller. The output device is used to provide a first feedback action according to the first feedback signal.

[0005] In one or more embodiments, the output device includes a light-emitting device, a vibrator, a sound amplifier, or a text and graphic display device.

[0006] In one or more embodiments, the pressure sensor is a sound sensor. The dynamic average value is the average volume within a period of time.

[0007] In some embodiments, the notification device further includes a distance sensor and a circuit board connected to the microcontroller. The sound sensor and the distance sensor are integrated on the circuit board.

[0008] In some embodiments, the notification device further includes a server. The server is connected to the microcontroller through a network. The microcontroller transmits a sound signal to the server. The server identifies and classifies the type of the sound signal, and transmits a second feedback signal to the microcontroller according to the type of the sound signal. The output device provides a second feedback action according to the second feedback signal.

[0009] In some embodiments, the server further includes a sound recognition module, a classification module, and a microprocessor. The sound recognition module is used to recognize the sound signal. The classification module is used to classify the type of the recognized sound signal. The microprocessor is used to provide the second feedback signal according to the type of the sound signal.

[0010] One aspect of the present disclosure relates to a wearable device having the notification device as described above.

[0011] According to an embodiment of the present disclosure, a wearable device includes the notification device as described above and clothing. The pressure sensor, microcontroller, and output device of the notification device are disposed on the clothing.

[0012] One aspect of the present disclosure relates to a notification method, which can be implemented by the notification device as described above.

[0013] In an embodiment of the present disclosure, the notification method includes the following processes. Detect the environment to provide a pressure signal, process the pressure signal to obtain a dynamic average value of the pressure signal within a period of time. Set a dynamic threshold value according to the dynamic average value. Confirm whether the current volume of the sound signal exceeds the dynamic threshold value. If the dynamic average value of the sound signal exceeds the threshold value, transmit a feedback signal to the output device. The output device provides a feedback action according to the feedback signal.

[0014] In one or more embodiments, the pressure signal is a sound signal, and the dynamic average value is the average volume of the sound signal within a period of time.

[0015] One aspect of the present disclosure relates to a notification method, which can also be implemented by the notification device as described above.

[0016] In an embodiment of the present disclosure, the notification method includes the following processes. Detect the environment to obtain an analog sound signal. The content of the analog sound signal is identified by sound and the type of the analog sound signal is classified thereby. Output a feedback signal according to the type of the analog sound signal. The output device makes a feedback action according to the feedback signal.

[0017] In summary, the present disclosure provides a notification device, a wearable device using the notification device, and a corresponding notification method to notify the user in real time according to the environmental volume, so that the user can easily perceive the change of the environment.

[0018] The above is only used to elaborate on the problems to be solved by the present disclosure, the technical means for solving the problems, and the effects produced thereby. The specific details of the present disclosure will be introduced in detail in the following embodiments and related drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The advantages of the present disclosure and the drawings should be better understood by the following listed embodiments and with reference to the drawings. The descriptions of these drawings are only the listed embodiments, so it should not be considered as limiting individual embodiments or the scope of the claims of the invention.

[0020] Figure 1 A block diagram of the notification device is illustrated according to an embodiment of the present disclosure;

[0021] Figure 2 Flowchart of a notification method according to an embodiment of the present disclosure;

[0022] Figure 3 Block diagram of a notification device according to an embodiment of the present disclosure;

[0023] Figure 4 Block diagram of a server according to an embodiment of the present disclosure;

[0024] Figure 5 Flowchart of a notification method provided by a notification device according to an embodiment of the present disclosure;

[0025] Figure 6 Flowchart of a training method for training a voice recognition module according to an embodiment of the present disclosure;

[0026] Figure 7 Flowchart of a training method for training a classification module according to an embodiment of the present disclosure; and

[0027] Figures 8 to 10 Front view, back view, and perspective view of the interior of a pocket of a smart vest as a wearable device according to an embodiment of the present disclosure. Detailed implementation manners

[0028] Examples are given below and described in detail in conjunction with the accompanying drawings. However, the provided examples are not intended to limit the scope covered by the present disclosure, and the description of the structure and operation is not intended to limit the order of its execution. Any structure formed by recombining elements, which produces a device with equivalent functions, is within the scope covered by the present disclosure. In addition, the drawings are for illustrative purposes only and are not drawn to the original size. For ease of understanding, the same or similar elements will be denoted by the same reference numerals in the following description.

[0029] In addition, the terms used throughout the specification and claims, unless otherwise specified, generally have their ordinary meanings as used in this field, in the context of the present disclosure, and in the context of the particular content. Certain terms used to describe the present disclosure will be discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art in the description of the present disclosure.

[0030] In this document, terms such as "first", "second", etc. are only used to distinguish elements or operation methods with the same technical terms, and are not intended to indicate order or limit the present disclosure.

[0031] Furthermore, similar terms such as "comprising", "including", "providing", etc. are open-ended limitations in this document, meaning including but not limited to.

[0032] Further, in this document, unless the article is specifically limited in the text, the indefinite article "a" and the definite article "the" may refer to a single or multiple entities. It will be further understood that the terms "comprising", "including", "having", and similar terms used herein specify the features, regions, integers, steps, operations, elements, and / or components described, but do not preclude one or more other features, regions, integers, steps, operations, elements, components, and / or groups thereof that are described or additional thereto.

[0033] Please refer to Figure 1 . Figure 1 A block diagram of the notification device 1 is illustrated according to an embodiment of the present disclosure. As Figure 1 shown, the notification device 1 includes a sound sensor 10, a microcontroller 20, and an output device 30. Through the notification device 1, a user can obtain notifications in a timely manner according to environmental changes.

[0034] The sound sensor 10 is configured to detect the environment to receive sound signals in the environment. When the notification device 1 is used in an environment such as a warehouse or a factory, the received sound signals are, for example, the sounds of engineering equipment or the voices of other workers, which are analog signals. In some embodiments, the sound sensor 10 is, for example, a microphone sensing module (such as a capacitive type), or a capacitive microphone sensing module can also be simply arranged in an array.

[0035] The microcontroller (microcontroller, or microcontroller unit, abbreviated as MCU) 20 is connected to the sound sensor 10. The microcontroller 120 has the advantage of a small size and is easy to carry, and can be used to implement simple computing functions. The sound sensor 10 can transmit the sound signal to the microcontroller 20, and the microcontroller 20 can simply process the sound signal from the sound sensor 10. The microcontroller 20 can also integrate the function of judging the volume of the sound signal. Thus, the microcontroller 20 can record a sound signal over a period of time and provide a feedback signal according to the volume change of the sound signal.

[0036] The output device 30 is connected to the microcontroller 20 to provide a feedback action according to the feedback signal. The output device 30 may include a light-emitting device, a vibrator, a sound amplifier, or a text and graphic display device. The text and graphic device directly reminds the user more intuitively by displaying text or other graphics. The text and graphic display device includes a small portable display.

[0037] In this way, the notification device 1 can detect the environment through the sound sensor 10 to provide a sound signal. The microcontroller 20 connected to the sound sensor 10 processes the dynamic volume average value of the sound signal over a period of time. The dynamic volume average value refers to the average of the volume sizes of the sound signal in the previous period. According to the dynamic average value, a dynamic threshold value can be predetermined. If the volume of the current sound signal is greater than the dynamic threshold value calculated from the dynamic average value of the previous period, it represents that the environment has changed, there may be danger, or there is a communication requirement in the vicinity. The microcontroller 20 then provides a feedback signal to the output device 30, so that the output device 30 provides a feedback action to notify the user.

[0038] In some embodiments, the notification device 1 can also use other types of pressure sensors to replace the sound sensor 10. The sound sensor 10 is a type of pressure sensor, which is used to sense the sound pressure change in the sound transmission in the environment, convert it into a sound signal, and calculate the dynamic average value to obtain the dynamic threshold value. In some embodiments, other types of pressure sensors such as a barometric pressure sensor can be used in the notification device 1. Taking the barometric pressure sensor as an example, it can sense the dynamic average value of the barometric pressure over a period of time. Once the current barometric pressure value is greater than the dynamic average value calculated in the previous period, the microcontroller 20 can send a feedback signal to make the output device 30 provide a feedback action to immediately notify the user using the notification device 1.

[0039] To further illustrate how the notification device 1 notifies the user, please refer to Figure 2 . Figure 2 According to an embodiment of the present disclosure, a flowchart of a notification method 600 is shown. The notification method 600 includes processes 610 to 650.

[0040] In process 610, the sound sensor 10 of the notification device 1 can be used to detect the environment around the user to obtain a sound signal over a period of time.

[0041] In process 620, the sound signal can be processed by the microcontroller 20 connected to the sound sensor 10 to obtain a dynamic threshold value over a period of time. The microcontroller 20 can first calculate the dynamic average value of the volume of the sound signal over a period of time according to the sound signal. For example, the sound sensor 10 can obtain the dynamic average value of the volume in the period from 3 seconds ago to 1 second ago. When the notification device 1 is started, the dynamic average value of the volume may change continuously.

[0042] According to the dynamic average value of the volume, the microcontroller 20 can define a dynamic threshold value for the volume of the sound signal, so as to judge whether there is a large change in the volume of the sound signal in a short period of time. In some embodiments, the dynamic threshold value can be set to the dynamic average value. In some embodiments, a dynamic threshold value different from the dynamic average value can be set according to the magnitude of the dynamic average value. For example, when the dynamic average value of the volume of the sound signal is less than a specific decibel number, the dynamic threshold value is set to a value greater than the dynamic average value; and when the dynamic average value of the volume of the sound signal is greater than a specific decibel number, the dynamic threshold value is directly set equal to the dynamic average value.

[0043] After going through process 620 to set the dynamic average value of the volume of the received sound signal, in process 630, it is possible to confirm whether the current volume of the sound signal exceeds the dynamic threshold value according to the current volume of the sound signal. If so, proceed to process 640 to transmit a feedback signal to the output device 30. If not, return to process 610 to continue detecting the environment to provide a sound signal.

[0044] For example, in a specific embodiment, the microcontroller 20 calculates that the dynamic average value of the volume of the sound signal from 3 seconds ago to 1 second ago is a specific decibel number (such as 60 decibels), and the microcontroller 20 sets the dynamic average value of the volume of the sound signal as the dynamic threshold value (process 620). Subsequently, once the current volume of the sound signal is greater than the dynamic threshold value (such as greater than 60 decibels), corresponding to the judgment in process 630 being yes, then enter process 640, and the microcontroller 20 can immediately provide a feedback signal to the output device 30.

[0045] In this way, in process 650, the output device 30 can provide a suitable feedback action according to the feedback signal from the microcontroller 20, so as to notify the user using the notification device 1. The notification method 600 can be implemented on a mobile device. For example, a mobile device such as a smartphone has a microphone, a processor, and a vibrator that vibrates the phone. By installing an application program (APP) on the smartphone, the microphone can be used as the sound sensor 10, the processor of the phone can perform the function of the microcontroller 20, and the vibrator of the phone can be used as the output device 30, and the notification vibration is used to provide a feedback action.

[0046] Please refer to Figure 3 。 Figure 3 A block diagram of the notification device 100 is shown according to an embodiment of the present disclosure. The notification device 100 is based on the notification device 1 and can, in addition to performing the functions of the notification device 1, further provide functions of intelligent notification and warning. As Figure 3As shown, the notification device 100 includes a sound sensor 110, a microcontroller 120, a server 130, an output device 150, and a distance sensor 160. In this embodiment, the sound sensor 110, the output device 150, and the distance sensor 160 are connected to the microcontroller 120, and the server 130 is set remotely and connected to the microcontroller 120 through a network, for example. The server 130 can be used for complex operations. Since the server 130 can be set remotely, when using the notification device 100, only the sound sensor 110, the microcontroller 120, the output device 150, and the distance sensor 160 need to be carried. In some embodiments, the network is, for example, a wireless network shared by the user's mobile phone. In some embodiments, the microcontroller 120 can be connected to the network through Bluetooth communication. In some embodiments, the network can be other types of wireless networks (Wi-Fi), such as Zigbee. In some embodiments, the network can also be the narrow band Internet of things (NBIoT) of the fourth generation mobile communication technology (4G) or the LTE-M technology. In some embodiments, the network can be provided by the fifth generation mobile communication technology (5G) to achieve faster transmission rates and interactions.

[0047] The sound sensor 110 is similar to Figure 1 the sound sensor 10. The sound sensor 110 is used to detect the environment to receive sound signals in the environment. For example, when the notification device 100 is used in an environment such as a warehouse or a factory, the received sound signals are, for example, the sounds of engineering equipment or the voices of other workers, which are analog signals. Specifically, in some embodiments, the sound sensor 110 is, for example, a microphone sensing module. The microphone sensing module is, for example, capacitive. In some embodiments, the capacitive microphone sensing modules can also be simply arranged in an array.

[0048] After the sound sensor 110 receives the sound signals in the environment, for the convenience of analysis, the analog sound signals can be processed to filter out noise. In some embodiments, other devices for filtering noise can also be provided on the sound sensor 110.

[0049] The microcontroller 120 is similar to Figure 1 the microcontroller 20. The microcontroller 120 is connected to the sound sensor 110. The microcontroller 120 has the advantage of a small volume and is easy to carry, and can be used to implement simple arithmetic functions. Further, the microcontroller 120 can be connected to the remote server 130 through a network. Through the connection with the microcontroller 120, the sound sensor 110 can transmit the sound signals to the microcontroller 120. In some embodiments, the network can be provided by, for example, a mobile phone.

[0050] Server 130 is set remotely to perform relatively complex computations. Please also refer to Figure 3 and Figure 4 . Figure 4 A block diagram of server 130 is shown according to an embodiment of the present disclosure. In this embodiment, server 130 includes a voice recognition module 135, a classification module 140, and a processor 145. In some embodiments, the voice recognition module 135, the classification module 140, and the processor 145 are computer components within server 130. And in some embodiments, the voice recognition module 135, the classification module 140, and the processor 145 can be integrated into the same hardware.

[0051] The voice recognition module 135 is used to recognize voice signals. The classification module 140 is used to classify the types of recognized voice signals. The processor 145 provides a feedback signal according to the type of the voice signal. The specific operation method will be described later. Through remote transmission over the network, the microcontroller 120 can be used to receive the feedback signal from the remote server 130.

[0052] The output device 150 is connected to the microcontroller 120 to provide a feedback action according to the feedback signal. The output device 150 is similar to Figure 1 the output device 30 includes a light-emitting device, a vibrator, a sound amplifier, or a text graphic display device. The text graphic display device includes a small portable display. To cope with an environment where it is inconvenient to communicate by voice, in some embodiments, the feedback action of the output device 150 does not include voice feedback.

[0053] The distance sensor 160 is connected to the microcontroller 120 to sense the distance between the notification device 100 and an object. For example, the distance sensor 160 is, for example, an ultrasonic distance sensing device. In some embodiments, the distance sensor 160 senses distance through infrared rays, or uses a millimeter-wave radar or a sub-millimeter-wave radar. Due to the shorter wavelength used, it has a wider sensing range and can detect an object within a larger angular range.

[0054] Please refer to Figure 5 . Figure 5 A flowchart of the notification method 200 provided by the notification device 100 is shown according to an embodiment of the present disclosure, illustrating the specific process of the notification device 100 from receiving the voice signal of the environment to emitting a feedback action for warning.

[0055] In step 210 of the notification method 200, the sound sensor 110 of the notification device 100 detects the environment to obtain an analog voice signal.

[0056] Continuing with process 210, in process 220, the microcontroller 120 transmits an analog voice signal to the server 130, which can be, for example, via a network.

[0057] In process 230, the server 130 identifies the analog voice signal according to the voice recognition module 135. Through the identification of the voice recognition module 135, the server 130 can obtain the voice contained in the analog voice signal, such as a warning voice from a person and the specific content of the warning voice, or the sound of construction machinery.

[0058] In process 240, the server 130 can classify the type of the analog voice signal through the classification module 140. And in process 250, the server 130 outputs a feedback signal according to the type of the voice signal. In other words, one type of voice signal can correspond to one feedback signal. The type of voice signal referred to here is classified according to the response method after receiving the voice signal, such as for warning of danger or for calling and communicating.

[0059] In some embodiments, the voice signals in the working environment can be classified into multiple types, and these types of voice signals respectively correspond to a situation, and these situations respectively correspond to a feedback action. The types of voice signals are limited, and can be customized and increased according to the situation.

[0060] For example, in some embodiments, there is only one type of voice signal, "There is danger". After the notification device 100 receives the voice signal (process 210), uploads it to the server (process 220) and completes the identification of the voice signal (process 230), and learns that the content of the voice signal is to notify the user that there is danger (the content of the voice signal may be the sound of working equipment or human voice), at this time, the notification device 100 can classify the voice signal into the type of "There is danger", so that the server 130 outputs a corresponding feedback signal to the output device 150 to notify the user of the notification device 100 that there is danger.

[0061] Specifically, in another practical example, there are six types of voice signals, including flash left when there is danger, flash right when there is danger, emit vibration, there is other type of danger, move right, and remind someone is calling. For example, after the notification device 100 receives the voice signal (process 210), uploads it to the server (process 220) and completes the identification of the voice signal (process 230), and learns that the content of the voice signal is to notify the user that there is danger on the right and should flash left, at this time, the notification device 100 can classify the voice signal into the type of flash left when there is danger (process 240). Subsequently, the server 130 outputs a feedback signal of flashing left (process 250).

[0062] In some embodiments, the distance sensor 160 may also provide environmental information about the vicinity of the user of the notification device 100 to facilitate more accurate judgment by the server 130. For example, in some embodiments, a large work instrument moves from the right rear towards the user of the notification device 100. When the sound sensor 110 detects the sound information of the large instrument sound and at the same time the distance sensor 160 senses an object approaching from the right rear, the server 130 can identify and classify the type of the sound signal as a left flash based on the above information, and thus provide a feedback signal for a left flash.

[0063] Continuing from process 250, in process 260, the microcontroller 120 receives a feedback signal from the server 130 remotely via the network.

[0064] In process 270, the output device 150 connected to the microcontroller 120 makes a feedback action according to the feedback signal. For example, the output device 150 may be vibrators arranged on the user's left and right shoulders. When the microcontroller 120 receives the feedback action for a left flash, the vibrator on the user's left shoulder vibrates, immediately warning the user of the notification device 100 through touch.

[0065] In some embodiments, the notification device 100 may be further connected to a console. The console can be used to manage one or more notification devices 100 simultaneously, or the wearable device provided with the notification device 100. For example, the console can actively send a feedback signal to a specific notification device 100 to directly drive the output device to provide a warning. In this way, by providing active notification in the above manner, the warning function of the notification device 100 can be further enhanced. In some embodiments, the console can further set one or more notification devices 100 into multiple different groups to make notifications for specific groups or all notification devices 100 in different situations in a high-noise environment.

[0066] In the present embodiment, the voice recognition module 135 and the classification module 140 can be customized and trained through machine learning to achieve the recognition and classification of voice signals customizedly to adapt to different types of working environments, as will be described in detail later.

[0067] Please refer to Figure 6 。 Figure 6 The flowchart of the training method 300 for training the voice recognition module 135 is shown according to an embodiment of the present disclosure.

[0068] As shown in the figure, in process 310, the environment is detected by the sound sensor 110 to obtain an analog sound signal. The user of the notification device 100 can select different detection environments according to actual needs.

[0069] In some embodiments, the sound sensor 110 can detect signals by means of sound dynamic detection according to the signal detection theory (SDT).

[0070] In process 320, after the sound sensor 110 detects an analog sound signal in the environment, the analog sound signal is converted into a time-domain digital sound file through digital processing. In some embodiments, the digital processing can be performed by the microcontroller 120. In some embodiments, the digital processing can also be remotely processed by the server 130. In some embodiments, through frame blocking processing, the time-domain digital sound file can be further segmented into several specific sound frames according to time, and the signals within the frames are processed and analyzed.

[0071] Continuing from process 320, in process 330, the time-domain digital sound file is converted into a frequency-domain digital sound file. Specifically, the time-domain digital sound file can be subjected to a fast Fourier transform (FFT) by the server 130 or other computer devices connected to the server 130 to convert the time-domain digital sound file into a frequency-domain digital sound file. In some embodiments, by establishing the frequency-domain digital sound file, a spectrogram can be further obtained, which corresponds to the intensity of the time-domain digital sound file at different frequencies at different times.

[0072] Continuing from process 330, in process 340, the eigenvalue extraction module for sound extracts the eigenvalues of the frequency-domain digital sound file. The eigenvalue extraction module for sound is provided within the server 130. The eigenvalues of the frequency-domain digital sound file correspond to different sounds. For example, the sounds emitted by construction machinery and human voices have different characteristics, which are manifested in, for example, the frequency spectrum diagram or spectrogram of the sound. By analyzing the frequency spectrum diagram or spectrogram of the frequency-domain digital sound file, the eigenvalues of the frequency-domain digital sound file can be extracted therefrom to distinguish the differences between the sounds emitted by construction machinery and human voices.

[0073] For example, the voice feature extraction module includes using the Mel-Frequency Cepstral Coefficients (MFCCs) method. Through the calculation module of the voice feature extraction module, the frequency-domain digital voice file can be converted into the corresponding Mel-Frequency Cepstrum (MFC) to obtain the corresponding Mel-Frequency Cepstral Coefficients. The Mel-Frequency Cepstral Coefficients can be used as the feature values of the frequency-domain digital voice file, so as to obtain the voice corresponding to the frequency-domain digital voice file, such as the sound emitted by engineering equipment or human voices. In some embodiments, the voice feature extraction module can use the Deep Neural Networks (DNN) technology in the field of artificial intelligence to extract the feature values of the frequency-domain digital voice file. The deep neural network technology has good performance in image recognition. Therefore, conceptually, by converting the frequency-domain digital voice file into an image, the voice corresponding to the image of the frequency-domain digital voice file can be recognized through image recognition to obtain the corresponding feature values.

[0074] Specifically, in one embodiment, the server 130 includes a Convolutional Neural Network (CNN) model. In the deep neural network technology, the convolutional neural network module can effectively implement the function of image recognition. The convolutional neural network model can be pre-input with a sequence spectrogram provided by other voices to complete the training of image recognition. The sequence spectrogram can refer to the frequency intensity distribution diagram corresponding to different times arranged in a sequence. For example, for the sound of working equipment or human voices, multiple groups of corresponding sequence spectrograms can be provided as the basis for image recognition. In this way, after completing the learning of image recognition, another sequence spectrogram can be input into the convolutional neural network model, and the convolutional neural network model can obtain which voice the other sequence spectrogram is similar to through image recognition, so as to output the corresponding feature values. In some embodiments, the voices used to train the convolutional neural network model are sampled in the actual working environment to establish a customized recognition scheme according to the actual environment. The user of the notification device 100 can, according to the needs, convert the sound signal simulated in the environmental detection into a frequency-domain digital voice file as the input, and then perform training based on the existing files of human voices or the sounds of tool equipment.

[0075] In this way, another implementation of process 340 can be achieved as follows. First, convert the frequency-domain digital sound file into a sequence of spectrograms. A spectrogram presents the variation of the intensity of different frequencies over time. Here, a frequency-intensity distribution diagram of the frequency-domain digital sound file at different times in the sequence can be output. Subsequently, input the sequence of spectrograms of this frequency-domain digital sound file into the convolutional neural network model in the sound feature value extraction module, and the feature values of the frequency-domain digital sound file can be output.

[0076] In process 350, the voice recognition module 135 can be trained based on the frequency-domain digital sound file and its feature values. Training the voice recognition module 135 can apply deep neural networks in the field of artificial intelligence. The feature values of the frequency-domain digital sound file correspond to the sounds of human voices or tools and instruments. When the feature values of the frequency-domain digital sound file indicate that it is a human voice, the corresponding information content of the frequency-domain digital sound file is further input to train the voice recognition module 135. When the feature values of the frequency-domain digital sound file indicate that it is the sound of a tool or instrument, the corresponding context information can be provided. In this way, when the trained voice recognition module 135 receives a sound signal, it can identify whether the sound signal is a human voice or the sound of a tool or instrument. When the sound signal is a human voice, it can determine the information content to be conveyed, and when the sound signal is the sound of a tool or instrument, it provides the corresponding context information. In some embodiments, a single-chip computer can be directly connected to the microcontroller 120 to achieve edge computing for voice recognition on the premise of being portable. Examples of single-chip computers include Raspberry Pi.

[0077] Please refer to Figure 7 。 Figure 7 The flowchart of the training method 400 for training the classification module 140 is shown according to an embodiment of the present disclosure. Similar to the voice recognition module 135, the classification module 140 can also be customized through deep neural networks. The classification module 140 is used to distinguish the types of different analog sound signals to provide appropriate feedback signals.

[0078] In process 410, an analog sound signal is input. In process 420, the input analog sound signal can be recognized, for example, by the voice recognition module 135.

[0079] Subsequently, in process 430, the context information corresponding to the analog sound signal is input. For example, when it is recognized that there is a warning of "flash left" issued by a person in the input analog sound signal, the corresponding context at this time, which is to flash left, is input.

[0080] In process 440, the classification module 140 can be trained based on the simulated sound signal and its corresponding situation. Specifically, the identified simulated sound signal is used as the input, and the corresponding specific situations are used as the training targets, so that the classification module 140 can classify the identified simulated sound signal into different situations. Different situations are, for example, the situation of flashing left as described above. Different situations correspond to different types of sound signals. In this way, the notification device 100 substantially combines with the wireless network and can also personalize the setting of the artificial intelligence recognition parameters, while the server 130 has to receive different situation information and then train. This is an implementation of the overall service Internet of Things architecture of the notification device 100 disclosed herein. In addition, the microcontroller 120 can also implement a warning function outside the Internet of Things architecture. For example, the microcontroller 120 integrating the function of judging the volume of the sound signal can be used to check the abnormal change of the ambient volume, so as to issue another feedback signal for warning notification. The specific process is similar to Figure 2 , the notification device 100 can perform the same functions as the notification device 1. In this way, in an environment without Internet connection, the notification device 100 can also play a role in warning notification.

[0081] Please refer to Figure 8 、 Figure 9 and Figure 10 . Figures 8 to 10 The front view, back view and perspective view of the inside of the pocket of the smart vest 500 as a wearable device are shown respectively according to an embodiment of the present disclosure. In this embodiment, the notification device 100 is disposed on the vest 505 to serve as the smart vest 500. In some embodiments, other clothing than the vest 505 can also be used.

[0082] Refer to simultaneously Figure 8 and Figure 9 . As shown in the figure, the smart vest 500 includes a front 510, a back 530, and shoulders 520 connecting the front 510 and the back 530. A pocket 513 is provided on the front 510 to accommodate a mobile phone to provide network. A pocket 533 is also provided on the back 530 of the smart vest 500. The pocket 533 is used to accommodate and fix the components of the notification device 100, including the sound sensor 110, the distance sensor 160, and the circuit board 170.

[0083] As Figure 10 shown, the sound sensor 110, the microcontroller 120, the power supply module 180 for supplying power, and the distance sensor 160 of the notification device 100 are integrated on the support board 170. The power supply module 180 includes a battery and a switch. The wires can be integrated on the circuit board 170, inside the interlayer, or on the opposite side.

[0084] In the present embodiment, the sound sensor 110, the distance sensor 160, and the circuit board 170 are disposed in the pocket 533 on the back 530 of the smart vest 500. Since it is not easy for the user's sight to reach the back, disposing the sound sensor 110 for detecting the ambient sound and the distance sensor 160 on the back 530 of the smart vest 500 can better exert the function of the notification device 100 to detect danger and issue a warning. In some embodiments, the outwardly exposed portions of the sound sensor 110 and the distance sensor 160 are provided with a waterproof structure to cope with different environmental changes. In the present embodiment, the output device 150 disposed on the smart vest 500 includes a light bar 153 and a vibrator 156. The vibrator 156 is connected to the circuit board 170 through a wire 185.

[0085] In summary, the present disclosure provides a notification device and a wearable device using the notification device. The notification device can detect the volume level of the environment in a period of time, so as to notify the user immediately when the ambient volume changes. The notification device can also be remotely connected to the server through the use of a microcontroller network. This is not only convenient for portable carrying, but the server can identify and classify the received sound signals to provide feedback for the type of the sound signal. The type of the sound signal is, for example, a human voice or the sound of engineering equipment. The wearable device is, for example, a smart vest combined with the notification device, which is convenient to wear. Through the output device disposed thereon, such as a vibrator and a light bar, the user is convenient to perceive environmental changes in a way other than sound, which is beneficial for immediate communication and warning. The notification device is further set to be conducive to customized training to provide more accurate identification and warning effects in different working environments.

[0086] Although the present disclosure has been disclosed as above in embodiments, it is not intended to limit the present disclosure. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to that defined by the claims.

[0087]

Symbol Description

[0088] 1,100: Notification device

[0089] 10,110: Sound sensor

[0090] 20,120: Microcontroller

[0091] 30,150: Output device

[0092] 130: Server

[0093] 135: Sound recognition module

[0094] 140: Classification module

[0095] 145: Processor

[0096] 150: Output device

[0097] 153: Light bar

[0098] 156: Vibrator

[0099] 160: Distance sensor

[0100] 170: Circuit board

[0101] 180: Power supply module

[0102] 185: Electric wire

[0103] 200: Notification method

[0104] 210~270: Process

[0105] 300: Training method

[0106] 310~350: Process

[0107] 400: Training method

[0108] 410~440: Process

[0109] 500: Smart vest

[0110] 505: Vest

[0111] 510: Front

[0112] 513: Pocket

[0113] 520: Shoulder

[0114] 530: Back

[0115] 533: Pocket

[0116] 600: Notification method

[0117] 610~650: Process.

Claims

1. A notification device, characterized in that, comprising: a pressure sensor for detecting the environment to provide a plurality of pressure signals; a microcontroller connected to the pressure sensor to receive the pressure signals, wherein the microcontroller is used to calculate the dynamic average value of the pressure signals at a plurality of times within a period before the current time, and the microcontroller sets a dynamic threshold according to the dynamic average value. When the dynamic average value is greater than the set pressure value, the dynamic average value is set as the dynamic threshold. When the dynamic average value is less than the set pressure value, the set pressure value is set as the dynamic threshold; and an output device connected to the microcontroller, wherein when the magnitude of the current pressure signal at the current time is greater than the dynamic threshold, the microcontroller sets to transmit a first feedback signal to the output device, and the output device is used to provide a first feedback action according to the first feedback signal.

2. The notification device according to claim 1, characterized in that, the output device includes a light-emitting device, a vibrator, a sound amplifier or a text and graphic display device.

3. The notification device according to claim 1, characterized in that, the pressure sensor is a sound sensor, the pressure signals are a plurality of sound signals, and the dynamic average value of the sound signals is the average volume size in the period.

4. The notification device according to claim 3, characterized in that, further comprising a distance sensor and a circuit board connected to the microcontroller, and the sound sensor and the distance sensor are integrated on the circuit board.

5. The notification device according to claim 3, characterized in that, further comprising a server, wherein the server is connected to the microcontroller through a network, the microcontroller transmits the sound signals to the server, the server identifies and classifies the types of the sound signals, and transmits a second feedback signal to the microcontroller according to the types of the sound signals, and the output device provides a second feedback action according to the second feedback signal.

6. The notification device according to claim 5, characterized in that, the server further comprises: a sound identification module for identifying the sound signals; a classification module for classifying the types of the identified sound signals; and a processor for providing the second feedback signal according to the types of the sound signals.

7. A wearable device, characterized in that, comprising: the notification device according to claim 1; and clothing, wherein the pressure sensor, the microcontroller and the output device of the notification device are arranged on the clothing.

8. A notification method, characterized in that, comprising: detecting the environment through a pressure sensor to provide a plurality of pressure signals; processing the pressure signals to obtain the dynamic average value of the pressure signals within a period; setting a dynamic threshold according to the dynamic average value, wherein when the dynamic average value is greater than the set pressure value, the dynamic average value is set as the dynamic threshold. When the dynamic average value is less than the set pressure value, the set pressure value is set as the dynamic threshold; confirming whether the current pressure signal outside the period exceeds the dynamic threshold; If the current pressure signal exceeds the dynamic threshold value, a feedback signal is transmitted to the output device; and The output device provides a feedback action according to the feedback signal.

9. The notification method according to claim 8,[ wherein,[ The pressure signals are multiple sound signals, and the dynamic average value of the sound signals is the volume average value of the sound signals in the time period.

10. A notification method,[ wherein,[ comprising:[ Detecting the environment to obtain multiple analog sound signals; Processing the analog sound signals to obtain the dynamic average value of the analog sound signals within a time period; Setting a dynamic threshold value according to the dynamic average value, wherein when the dynamic average value is greater than the set pressure value, the dynamic average value is set as the dynamic threshold value, and when the dynamic average value is less than the set pressure value, the set pressure value is set as the dynamic threshold value; Confirming whether the current analog sound signal exceeds the dynamic threshold value outside the time period of the analog sound signals; Identifying the content of the analog sound signal by sound and classifying the type of the analog sound signal accordingly; If the current analog sound signal exceeds the dynamic threshold value, outputting a feedback signal according to the type of the analog sound signal; and Causing the output device to perform a feedback action according to the feedback signal.

Images