TWI703958B - Intelligent human body monitoring system and abdominal sound monitoring device thereof - Google Patents

Abstract

The present disclosure provides an intelligent human body monitoring system that includes an abdominal sound monitoring device. The abdominal sound monitoring device senses an audio and transmits the audio to a mobile device, so that the mobile device determines whether the audio is a bowel sound. If so, the mobile device calculates the number of times of the audio per unit time.

Description

Intelligent human body monitoring system and its abdominal sound monitoring device Set

The present invention relates to a system and a device, and in particular to an intelligent human body monitoring system and an abdominal sound monitoring device.

Nowadays, as the population ages, long-term care becomes extremely important. Although there are many health management products on the market, there are few related products for abdominal diseases.

In the physical examination of the abdomen, it is very inconvenient to use a stethoscope to listen to the peristaltic sounds of the abdomen to judge the intestinal condition.

The present invention proposes an intelligent human body monitoring system and abdomen sound monitoring device to improve the problems of the prior art.

In an embodiment of the present invention, the intelligent human body monitoring system proposed by the present invention includes an abdominal sound monitoring device and a server, and the abdominal sound monitoring device includes a communication device, a sound sensor, and a processor. The sound sensor senses audio. The processor transmits the audio to the mobile device through the communication device, so that The mobile device determines whether the audio is bowel sounds, and if so, the mobile device counts the number of times the audio is pronounced per unit time. The server receives audio from the mobile device and converts it into an audio image, and analyzes the audio and image convolutional neural network to obtain an analysis result. When the analysis result meets at least one preset condition, the server pushes a notification to the mobile device.

In an embodiment of the present invention, the sound sensor is a microphone array to correspond to a plurality of abdominal regions, and the audio includes audio from a plurality of abdominal regions.

In an embodiment of the present invention, when the number of pronunciations of at least one of the plurality of abdominal region audio signals per unit time does not fall within the predetermined range, the mobile device displays the abdominal region corresponding to at least that one of the plurality of abdominal region audio signals Exception information.

In an embodiment of the present invention, the server performs a convolution operation on the audio to extract sound features, and then builds a neural-like model based on the sound features, and the analysis result includes the neural-like model.

In an embodiment of the present invention, the abdominal sound monitoring device provided by the present invention includes a communication device, a sound sensor, and a processor. The sound sensor senses audio. The processor transmits the audio to the mobile device through the communication device, so that the mobile device determines whether the audio is bowel sounds. If so, the mobile device counts the number of times the audio is pronounced per unit time. The mobile device sends audio to the server, and the server analyzes the audio through the convolutional neural network to obtain an analysis result. When the analysis result meets at least one preset condition, the server pushes a notification to the mobile device.

In an embodiment of the present invention, the sound sensor is a microphone array to correspond to a plurality of abdominal regions, and the audio includes a plurality of abdominal region sounds News.

In an embodiment of the present invention, when the number of pronunciations of at least one of the plurality of abdominal region audio signals per unit time does not fall within the predetermined range, the mobile device displays the abdominal region corresponding to at least that one of the plurality of abdominal region audio signals Exception information.

In an embodiment of the present invention, the server converts the audio into an audio image, performs a convolution operation on the audio image to extract sound features, and then builds a neural-like model based on the sound features, and the analysis result includes the neural-like model.

In summary, the technical solution of the present invention has obvious advantages and beneficial effects compared with the prior art. The technical scheme of the present invention designs a sound monitoring instrument located on the abdomen to monitor peristalsis sounds and can be wirelessly transmitted to the cloud for storage and analysis.

Hereinafter, the above description will be described in detail by way of implementation, and a further explanation will be provided for the technical solution of the present invention.

In order to make the above and other objects, features, advantages and embodiments of the present invention more obvious and understandable, the description of the attached symbols is as follows:

110‧‧‧Abdominal sound monitoring device

112‧‧‧Communication device

114‧‧‧Sound sensor

116‧‧‧Processor

120‧‧‧Mobile device

130‧‧‧Server

200‧‧‧Microphone array

210‧‧‧Connecting parts

In order to make the above and other objectives, features, advantages and embodiments of the present invention more obvious and understandable, the description of the accompanying drawings is as follows: Figure 1 is a block diagram of an intelligent human body monitoring system according to an embodiment of the present invention; And FIG. 2 is a partial schematic diagram of an abdominal sound monitoring device according to an embodiment of the present invention.

In order to make the description of the present invention more detailed and complete, please refer to the attached drawings and various embodiments described below. The same numbers in the drawings represent the same or similar elements. On the other hand, well-known elements and steps are not described in the embodiments to avoid unnecessary limitations on the present invention.

In the implementation and the scope of the patent application, the description of "connection" can generally refer to a component that is indirectly coupled to another component through other components, or that one component is directly connected to another component without other components.

In the scope of implementation and patent application, the description of "connection" can generally refer to a component that is indirectly connected to another component through other components, or that a component is physically connected to another component without going through other components. .

In the implementation mode and the scope of the patent application, unless the article is specifically limited in the context, "a" and "the" can generally refer to a single or plural.

"About", "approximately" or "approximately" used in this article are used to modify any amount that can be slightly changed, but such slight changes will not change its essence. If there is no special description in the implementation, it means that the error range of the value modified with "about", "approximately" or "approximately" is generally allowed within 20%, preferably within 10% Within, and better within five percent.

Figure 1 is a block diagram of an intelligent human body monitoring system according to an embodiment of the invention. As shown in Figure 1, the intelligent human body monitoring system may include an abdominal sound monitoring device 110 and a server 130. In terms of architecture, the abdominal sound monitoring device 110 and the mobile device 120 establish wired and/or wireless communication. The device 120 and the server 130 establish wired and/or wireless communication.

In Figure 1, the abdominal sound monitoring device 110 includes a communication device 112, a sound sensor 114, and a processor 116. In terms of architecture, the processor 116 is electrically connected to the communication device 112 and the sound sensor 114. For example, the processor 116 may be an image processor, a central processing unit, a microcontroller, other processing circuits, or a combination of the foregoing, and the communication device 112 may be a wired communication device (such as a USB transmission device, etc.) and/or Wireless communication devices (such as: Bluetooth communication devices, infrared communication devices, Wi-Fi communication devices... etc.).

In use, the sound sensor 114 senses audio. The processor 116 transmits the audio to the mobile device 120 through the communication device 112, so that the mobile device 120 determines whether the audio is bowel sounds. For example, the mobile device 120 compares the waveform of the audio with a plurality of preset bowel sounds. The waveform of is roughly matched with any preset bowel sound waveform, the audio should be bowel sounds (for example, bowel sounds), and the mobile device 120 calculates the number of times the audio is pronounced per unit time.

In order to further explain the sound sensor 114 of the abdomen sound monitoring device 110, please refer to FIGS. 1 and 2. FIG. 2 is a partial schematic diagram of an abdomen sound monitoring device 114 according to an embodiment of the present invention. As shown in FIG. 2, the sound sensor 114 is a microphone array 200 corresponding to a plurality of abdominal regions, and the audio sensed by the microphone array 200 includes a plurality of abdominal region audio. The microphone array 200 is fixed to the connecting part 210. The connecting part 210 can be a strap or other wearable part, which is mainly comfortable and can minimize the size of the device on the underwear.

For example, the microphone array 200 has nine microphones 201 arranged in a nine-square grid to correspond to nine abdominal regions (e.g., upper abdomen, middle abdomen, lower abdomen). The abdomen, right quarter rib, right abdomen, right iliac fossa, left quarter rib, left abdomen, left iliac fossa), the audio sensed by the microphone array 200 includes nine abdominal region audio (such as: upper abdominal audio, mid abdominal audio, Lower abdominal audio, right abdominal audio, right abdominal audio, right skeletal fossa audio, left quarter rib audio, left abdominal audio, left skeletal fossa audio).

When the number of pronunciations of at least one of the plurality of abdominal region audio signals per unit time does not fall within the predetermined range, the mobile device 120 presents abnormal information of at least the abdominal region corresponding to the plurality of abdominal region audio signals.

For example, the predetermined range may be between about 34 to about 5 abdominal sounds per minute. If the bowel sounds in a certain abdominal region (such as epigastric sound) are between about 34 to about 5 times per minute, it means that the bowel in the abdominal region (such as the upper abdomen) is normal, and the mobile device 120 presents the abdominal region (Eg: upper abdomen) normal information.

If the bowel sounds in a certain abdominal region (such as mid-abdomen) exceed 34 times per minute, it means that the intestines in the abdominal region (such as mid-abdomen) are active, and the mobile device 120 displays abnormally active information in the abdominal region (such as mid-abdomen) .

If the bowel sounds in a certain abdominal region (such as the right iliac fossa) are less than 5 times per minute but greater than 0 times per minute, it means that the bowel activity in the abdominal region (such as the right iliac fossa) is low, and the mobile device 120 displays the abdomen Abnormally low information in areas (eg, right iliac fossa).

If the bowel sounds in a certain abdominal region (such as lower abdomen) are 0 times per minute, it means that the intestines in the abdominal region (such as the lower abdomen) are inactive, and the mobile device 120 displays abnormalities in the abdominal region (such as the lower abdomen). Event information.

On the other hand, the server 130 receives audio from the mobile device 120 And analyze the audio through a convolutional neural network to get the analysis result. In an embodiment of the present invention, the server 130 converts the audio into an audio image (e.g., waveform graph, voiceprint graph, spectrogram... etc.), and performs a convolution operation on the audio image to extract sound features, and then based on The sound characteristics are used to establish a neural-like model, and the analysis result includes the neural-like model.

When the analysis result meets at least one preset condition (such as a disease condition), the server 130 pushes a notification to the mobile device 120. For example, the above-mentioned neural model is a voiceprint model. If the voiceprint model meets the preset irritable bowel syndrome voiceprint model, and the analysis result meets the irritable bowel syndrome condition, the server 130 sends a notice of recommended medical treatment to the mobile device 120 To remind users.

In summary, the technical solution of the present invention has obvious advantages and beneficial effects compared with the prior art. The technical scheme of the present invention designs a sound monitoring instrument located on the abdomen to monitor peristalsis sounds and can be wirelessly transmitted to the cloud for storage and analysis.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone familiar with the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection of the present invention The scope shall be subject to those defined in the attached patent scope.

110‧‧‧Abdominal sound monitoring device

112‧‧‧Communication device

114‧‧‧Sound sensor

116‧‧‧Processor

120‧‧‧Mobile device

130‧‧‧Server

Claims (6)

An intelligent human body monitoring system includes: an abdominal sound monitoring device, including: a communication device; a sound sensor for sensing an audio signal; and a processor for transmitting the audio signal to a mobile device through the communication device, Make the mobile device determine whether the audio is a bowel sound, if so, the mobile device counts the number of times the audio is pronounced per unit time; and a server receives the audio from the mobile device and passes it through a convolutional neural network The audio is analyzed to obtain an analysis result. When the analysis result meets at least one preset condition, the server pushes a notification to the mobile device, wherein the analysis result includes a type of neural model, and the type of neural model is a voiceprint Model, if the voiceprint model meets a preset irritable bowel syndrome voiceprint model, and the analysis result meets an irritable bowel syndrome condition, the server pushes a notice of recommended consultation to the mobile device, and the server converts the audio An audio image is formed, and a convolution operation is performed on the audio image to extract voice features, and then the neural model of this type is established based on the voice features. The intelligent human body monitoring system according to claim 1, wherein the sound sensor is a microphone array corresponding to a plurality of abdominal regions, and the audio includes audio from a plurality of abdominal regions. The intelligent human body monitoring system according to claim 2, wherein when the number of pronunciations of at least one of the abdominal region audio signals per unit time does not fall within a predetermined range, the mobile device displays at least the number of the abdominal region audio signals Abnormal information of the abdominal region corresponding to the person. An abdominal sound monitoring device, comprising: a communication device; a sound sensor for sensing an audio; and a processor, through the communication device, transmitting the audio to a mobile device so that the mobile device can determine whether the audio is If it is a bowel sound, the mobile device counts the number of times the audio is pronounced per unit time. The mobile device sends the audio to a server, and the server analyzes the audio through a convolutional neural network to obtain a The analysis result, when the analysis result meets at least one preset condition, the server pushes a notification to the mobile device, wherein the analysis result includes a type of neural model, the type of neural model is a voiceprint model, if the voiceprint model Meets a preset irritable bowel syndrome voiceprint model, the analysis result meets an irritable bowel syndrome condition, the server pushes a notice of recommended medical treatment to the mobile device, wherein the server converts the audio into an audio image, and The audio image is subjected to a convolution operation to extract voice features, and then the neural model of this type is established based on the voice features. The abdominal sound monitoring device according to claim 4, wherein the sound sensor is a microphone array to correspond to a plurality of abdominal regions Domain, the audio includes a plurality of abdominal region audio. The abdominal sound monitoring device according to claim 5, wherein when the number of pronunciations of at least one of the abdominal region audio signals per unit time does not fall within a predetermined range, the mobile device displays at least the number of the abdominal region audio signals Abnormal information of the abdominal region corresponding to the person.

Images